NEWS | FEATURES | PRODUCTS | CASE STUDIES www.pwemag.co.uk @PWEmagazine1 OEE and the value of time Inside this issue 10 > Building the data foundation for credible AI in additive manufacturing 20 > Bespoke compressed air solution supports refinery operations 30 > Preventing tomorrow’s occupational lung disease page 14 @plant-&-works-engineering PWE Plant & Works Engineering Since 1981 August/September 2026 | Issue 494
VSE903: Vibration diagnostics in the field ifm.com • Fast, error-free installation and retrofitting thanks to the standard M12 connector • Robust IP 67 housing for decentralized use • Integrated separation between automation and IT networks • Compatible with all common acceleration sensors • Six signal inputs collect all relevant data to improve machine availability
Questions around critical production assets, recovery priorities and the practicalities of restarting plant all require engineering input. When cyber risk reaches the factory floor The latest cybersecurity figures from Make UK make uncomfortable reading for manufacturers. Some 30% experienced a cyber incident, either directly or through their supply chain, during the past 12 months. Perhaps more significant for those concerned with the performance of plant is what happened next. Where incidents caused disruption, production downtime was among the most commonly reported consequences. That places cybersecurity in a rather different context. Much of the discussion surrounding cyber risk understandably concentrates on data, networks and business systems, but on a manufacturing site the consequences can extend much further. When production is interrupted, cybersecurity stops being an abstract corporate risk and becomes a very practical operational problem. Manufacturers hardly need reminding of the cost of downtime. Considerable effort and investment goes into preventing it, whether through planned maintenance, Editor’s Comment ‘ ’ condition monitoring, critical spares or improvements to equipment reliability. Cyber disruption presents another route to much the same unwanted destination, albeit one that has not traditionally featured prominently in maintenance planning. A high-profile case last year showed just how disruptive a cyber incident can be for manufacturing, with the effects reaching far beyond the IT department and onto the factory floor. Incidents on that scale may be unusual, but the potential consequences of lost production are something every manufacturer will recognise. Most manufacturers will never experience disruption on anything approaching that scale. Nevertheless, greater connectivity between production equipment, control systems and wider business networks means an IT problem can have consequences for the plant. Once an incident affects production, engineering knowledge will almost certainly be required as part of the response. There is no suggestion that maintenance teams should become cybersecurity specialists. That expertise belongs with those trained to provide it, just as other specialist disciplines do. Engineering does, however, have an important role in understanding the operational consequences of an incident and deciding how production can be recovered safely. It is therefore notable that Make UK found only around half of manufacturers have an incident response plan. For a manufacturing business, such a plan surely needs to consider the factory as well as the office. Questions around critical production assets, recovery priorities and the practicalities of restarting plant all require engineering input. None of this is particularly far removed from the principles already applied to plant reliability. Maintenance teams routinely consider likely failure modes, consequences, recovery times and the availability of critical spares. The source of the disruption may be different, but much of the thinking required to prepare for it is familiar. The challenge is ensuring that cybersecurity does not sit in an organisational silo until an incident occurs. IT and cybersecurity teams understand the threat and how to contain it; engineering understands the plant and the practical consequences of losing it. Bringing those areas of expertise together before production is affected makes sense. Cybersecurity may not be a maintenance responsibility in the traditional sense. Cyberrelated downtime most certainly is a plant issue. August/September 2026 www.pwemag.co.uk Plant & Works Engineering | 03
AWARDS OPEN TO EVERYONE We’re celebrating the very best in the electro-mechanical service and repair industry — and every company is invited to enter. Big or small. First-time entrant or seasoned contender. If you, your company, a project, or a product/service offering is making an impact, we want to hear your story. The 2026 AEMT Awards Join the industry celebration: Thursday 19th November 2026 Doubletree by Hilton, Coventry 30th Sep Judges Convene 20th Apr Nominations Open 11th Sep Nominations Close 19th Nov Winners Announced 9th Oct Finalists Announced Entry is free of charge and multiple entries are not only allowed, but encouraged! For more information and to submit your entries, please visit: AEMTAWARDS.COM Enter one (or more) of the 10 categories: • Product of the Year • Project of the Year • Supplier of the Year • Rising Star • Diversity in Engineering • Service Centre of the Year – Large • Service Centre of the Year – Small • Electro-Mechanical Champion of the Year • Contribution to Skills and Training • Sustainable Organisation of the Year Sponsors: More sponsorship opportunities available!
August/September 2026 www.pwemag.co.uk Plant & Works Engineering | 05 Editor: Aaron Blutstein t| 01732 370340 e| editorial@dfamedia.co.uk Content Sub Editor: Leslah Garland t| 01732 370340 e| leslah.garland@dfamedia.co.uk Sales Director: Damien Oxlee t| 01732 370342 e| damien.oxlee@dfamedia.co.uk Sales Manager: Sara Gordon t| 01732 370341 e| sara.gordon@dfamedia.co.uk Sales Manager: Andrew Jell t| 01732 370347 e| andrew.jell@dfamedia.co.uk DFA Direct: Damien Oxlee t| 01732 370342 e| damien.oxlee@dfamedia.co.uk Production Manager & Designer: Chris Davis e| chris.davis@dfamedia.co.uk Marketing Manager: Hope Jepson e| hope.jepson@dfamedia.co.uk Reader/Circulation Enquiries: Perception t| +44 (0) 1825 701520 e| cs@perception-sas.com Financial: Finance Department e| accounts@dfamedia.co.uk Managing Director: Ryan Fuller e| ryan.fuller@dfamedia.co.uk Published by: DFA Media Group 192 The High Street, Tonbridge, Kent TN9 1BE t| 01732 370340 e| info@dfamedia.co.uk w| www.pwemag.co.uk Official Supporters: Printer: Warners, UK © Copyright 2026, DFA Manufacturing Media Ltd, ISSN 0262-0227 PWE is a controlled circulation magazine, published 11 times a year. Please contact DFA Media with any subscription enquiries. Paid subscriptions are also available on an annual basis at £100.00 (UK) or £170.00 (Overseas) P+P included. The content of this magazine, website and newsletters do not necessarily express6the views of the Editor or publishers. The publishers accept no legal responsibility for loss arising from information in this publication. All rights reserved. No part of this publication may be produced or stored in a retrieval system without the written consent of the publishers. Contents 20 38 26 30 BCAS official media partner Audit Bureau of Circulation – Average net circulation 10,274 January 2024 to December 2024 COMMENT 3 NEWS 6 A round-up of what’s happening in industry. INSIGHT 10 MAINTENANCE MATTERS - INCORPORATING PROBLEM SOLVER 12 Focus on: CMMS/ OEE Terry Alexander explains why a CMMS is only as effective as the discipline behind it, and how better data, governance and performance metrics can improve reliability and profitability. PROCESS, CONTROLS, & PLANT 20 Focus on: Compressed Air/ Seals, Bearings & Lubrication When the largest refinery in Southern France experienced a critical equipment failure, Petroineos called upon Aggreko to provide a bespoke air production solution in record time, allowing the site to avoid extremely costly unplanned downtime. PWE reports. ENERGY & ENVIRONMENTAL MANAGEMENT 26 Focus on: Boilers, Burners & Controls/ HVAC At a specialist aerospace equipment manufacturer in Portsmouth, an initiative to reduce energy costs identified steam energy usage that could be optimised. Paul Hobden reports. HANDLING & SAFETY MATTERS 30 Focus on: Health & Safety The relaunch of the British Safety Industry Federation’s Clean Air? Take Care! campaign comes at an important time for occupational health, explains John Hooker, Chief Executive Officer at the British Safety Industry Federation. SPECIAL FOCUS NET ZERO 32 SKILLS & TRAINING 34 PPMA PREVIEW 36 AI 38 PRODUCTS & SERVICES DIRECTORY 42
News 6 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 Rubix, one of Europe’s leading industrial distributors, has announced it has secured a three-year agreement with EDF to become a key supplier of maintenance, repair and overhaul (MRO) products and associated services for the construction of Hinkley Point C in Somerset. The appointment broadens Rubix’s long-standing relationship with EDF through which the business has provided proven delivery across its nuclear sites and demonstrated operational performance, alongside robust product traceability and a secure and compliant supply chain. The new agreement builds on this expertise, reflecting EDF’s confidence in Rubix’s understanding of the sector’s stringent requirements, including operating within highly regulated, safety-critical environments. Under the new agreement, Rubix will provide access to its industrial product range and technical expertise, alongside its managed inventory service. The scope covers products and services used to support the construction of the nuclear facility, but is not associated with the equipment used within the nuclear reactors themselves. Wayne Luke, Strategic Account Manager at Rubix UKII, will lead activity and said: “We’ve enjoyed a really successful relationship with EDF for many years now, so we understand the rigorous standards and high level of quality that is needed for landmark projects such as Hinkley Point C. Our new agreement allows us to build on our work to date, supporting them to consolidate their MRO supply and ensure site teams have reliable access to the products, technical expertise and responsive service they need. We’re looking forward to working closely with the team and continuing our relationship on another important project.” Alongside its experience in nuclear, with capabilities strengthening counterfeit avoidance, supplier auditing and quality management, Rubix also holds Cyber Essentials Plus certification. This provides greater confidence in public sector projects and ensures operations processes are aligned with the requirements of the nuclear sector. Vince McGurk, CEO of Rubix UKII, added: “Being selected to support Hinkley Point C is a reflection of the trust we’ve built with EDF over many years and recognition of the hard work our teams have delivered. We’re proud to be continuing our work together and supporting Hinkley Point C as a nationally significant infrastructure project.” Hinkley Point C represents the new generation of nuclear power stations in Britain and will provide low-carbon electricity to around six million homes once operational. Rubix secures three-year MRO agreement for Hinkley Point Pump Industry Awards entries remain open for 2027 Entries for the 2027 Pump Industry Awards are still open for companies, organisations and individuals across the pump sector to put themselves forward with the deadline for submissions set for Friday 27th November 2026. Organised by the British Pump Manufacturers Association (BPMA), the Pump Industry Awards provide a high-profile platform for recognising engineering excellence, innovation, business performance and the people making a significant contribution to the pump industry. With ten award categories spanning products, projects, manufacturing, distribution, skills, sustainability and aftermarket support, the programme offers businesses and individuals from across the sector an opportunity to showcase their achievements and gain valuable industry recognition. The 2027 categories are: Product of the Year – Sponsored by DFA Media Project of the Year – Sponsored by World Pumps Environmental Contribution of the Year – Sponsored by SPP Pumps Manufacturer of the Year – Sponsored by WEG Distributor of the Year – Sponsored by Caprari & Calpeda Supplier of the Year – Sponsored by Wilo Pump Maintenance Provider of the Year – Sponsored by Apex Pumps Contribution to Skills & Training Award – Sponsored by ABB Rising Star Award – Sponsored by Innomotics Sustainable Contribution for a Better World – Sponsored by AESSEAL The introduction of the ‘Pump Maintenance Provider of the Year’ category for 2027 also reflects the increasingly important contribution made by specialist maintenance, repair and
News August/September 2026 www.pwemag.co.uk Plant & Works Engineering | 07 aftermarket organisations in maximising equipment reliability, efficiency and whole-life performance. Wayne Rose, CEO at the BPMA, said: “I would encourage every eligible business and individual to put forward their achievements for the 2027 Pump Industry Awards. Whether recognising innovation, engineering excellence, sustainability, skills or outstanding service, becoming a Finalist provides valuable industry recognition, while winning an Award represents a significant endorsement of achievement.” The culmination of the 2027 programme will be the Pump Industry Awards Gala Dinner, taking place on Thursday 11th March 2027 at The Hilton at St George’s Park, Burton upon Trent. The BPMA would like to acknowledge and thank all of the 2027 Pump Industry Awards sponsors for their continued support in helping to make the programme possible. Prospective entrants are encouraged to visit www.pumpindustryawards.com, review the category criteria and start their online submission. Made Smarter has announced it has bolstered its North West team with four new specialists as SME manufacturers accelerate investment in technology and skills. Mike Richards-Brown and Tabs Khojani will help firms find practical ways to digitalise their operations, while Jane Duffy and Mike Connolly will help businesses prepare their people and develop the leadership needed to deliver change. Together they bring decades of experience from some of the region’s leading manufacturing, technology and business support organisations. Richards-Brown joins following roles at the Advanced Manufacturing Research Centre North West (AMRC NW) and the North of England Robotics Innovation Centre (NERIC). Khojani brings 20 years of experience in Greater Manchester’s innovation and business support sector and also joins from NERIC at the University of Salford. Duffy previously supported businesses through the Business Growth Hub across Greater Manchester, while Connolly, a Mechanical Engineer, has spent more than three decades with global manufacturer Hubbell, working across engineering, quality, operations and HR. Their recruitment to the Governmentbacked adoption programme comes as manufacturers face growing pressure to become more productive, overcome skills challenges and keep pace with rapidly evolving technologies. New registrations rose 49% last year, with a further 128 manufacturers coming forward in the first five months of 2026/27. The new recruits will work alongside Made Smarter’s existing team to help companies develop a digital roadmap and decide where and how to invest, including accessing matchfunded grants of up to £20,000. They will also help businesses build the leadership and workforce skills needed to make those investments work, through the Leading Digital Transformation and Leading Change for Digital Champions programmes, and Digital Technology Internships. Donna Edwards, Programme Director for Made Smarter North West, said: “Manufacturers know they need to change, and the appetite to embrace digital transformation continues to grow. “Technology can unlock huge gains in productivity, efficiency and competitiveness, but businesses need the right expertise and the right people to make it work. These four appointments bring an incredible breadth of experience and will help us meet that growing demand and support even more manufacturers to turn their ambitions into action.” Tabs Khojani, Technology Adoption Specialist, said: “I’m excited to join Made Smarter and work directly with manufacturers to help them unlock their potential. Technology can feel overwhelming, so my role is to help businesses understand where it can make a practical difference. It’s not about technology for technology’s sake, it’s about solving genuine business challenges and creating lasting value.” Mike Connolly, Organisational Development and Skills Specialist, said: “I’ve spent my career in manufacturing and experienced many of the challenges businesses face, from engineering and operations to skills and people development. “Made Smarter gives me the opportunity to use that experience to help SME manufacturers develop their people, navigate change and build the skills and capability they need for the future.” Launched in 2019, Made Smarter North West has engaged with 2,500 manufacturers, created 705 digital roadmaps and supported 451 technology projects. The programme has provided £8.3m in funding, helping unlock £28m of investment from manufacturers, while 282 businesses have received skills or leadership training and 105 digital interns have been placed with businesses. Technology projects supported by the programme are forecast to generate £336m in additional gross GVA, create 2,231 new jobs and upskill 4,036 roles, delivering an estimated £8 return for every £1 of government investment. Made Smarter expands team as manufacturers step up digital investment LtoR - Mike Connolly, Mike Richards-Brown, Jane Duffy and Tabs Khojani, of Made Smarter North West
News 08 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 Automation Fair 2026 Opens Registration Rockwell Automation, Inc. the world’s largest company dedicated to industrial automation and digital transformation, announces that registration is now open for Automation Fair 2026, taking place November 16-19 at the Thomas M. Menino Convention & Exhibition Centre in Boston. Centred on the theme Future in Focus, Automation Fair 2026 will bring together more than 14,000 manufacturing, technology and industrial operations professionals from around the world for four days of learning, innovation and collaboration. Attendees will explore emerging technologies, gain practical insights and connect with people shaping the future of industrial operations. Recognised as one of the industry’s premier events, Automation Fair offers attendees direct access to industry professionals, technology innovators, hands-on training, interactive exhibits and valuable networking opportunities designed to help manufacturers move forward with confidence. “Automation Fair is where the future of industrial operations comes into focus,” said Brian Hovey, vice president, global marketing and chief marketing officer at Rockwell Automation. “This event brings together the people, technologies and ideas that are transforming manufacturing. Whether organisations are advancing digital transformation initiatives, scaling AI, strengthening resilience or improving productivity, attendees will leave with actionable strategies and meaningful connections that help turn vision into results.” Registration and event information are available at: www.rockwellautomation.com/automationfair Cyber resilience is business resilience The cyber risk in manufacturing is akin to an iceberg below the surface, largely unseen to it hits you with the results potentially existential. Industry can plan and mitigate the risks they see, but in reality the biggest threats can cause the most damage. It’s the vulnerabilities below the surface, in the systems, machinery and supply chains, that can catch businesses out. And that’s because manufacturing is distinctly at risk as digital systems are directly connected to physical production. Meaning that the risk doesn’t stay in the digital world for too long. What starts as an IT issue very quickly becomes a production problem, a customer problem and a financial problem very quickly. It may come as a surprise but manufacturing is the sector of the economy which suffers the most cyber attacks which highlights the scale of the challenge facing manufacturers today. A recent Make UK survey1 showed that almost a third of manufacturers experienced a cyber incident in the past 12 months, either directly or through their supply chain. Where cyber incidents had a direct impact, production downtime and increased operational costs were the most common consequences. In addition almost a third of manufacturers affected by supplier cyber attacks reported delays to customer deliveries, while a third reported reduced production capacity. Across the economy, Government research has estimated the cost t business from cyber attacks as almost £15 billion annually. Make UK’s survey also showed that while two thirds of manufacturers have cyber insurance, almost a fifth don’t and a similar number are unsure whether they are covered. However, taking out insurance is only akin to closing the door once the horse has bolted. What really matters is treating cyber security with the same strategic priority companies would give to any other aspect of operational performance such as productivity or health & safety. In practice this means understanding where the vulnerabilities lie, taking sensible steps to reduce them, and ensuring that when incidents do happen, they do not become business threatening events. In short, cyber attacks are no longer abstract technical events for manufacturers. They are showing up on the factory floor through downtime, higher costs, delayed orders and pressure on supply chains. In a connected industrial economy, a digital weakness can quickly become a production problem. As a result, the message for manufacturers is clear: cyber resilience is business resilience. Firms do not need to do everything at once, but they do need clear leadership, basic controls, tested recovery plans and stronger assurance across their supply chains. The businesses that get this right will be better placed to keep production moving, protect customers and invest in digital technologies with confidence. 1Cyber Security in Manufacturing | Make UK By MAKE UK chief executive, Stephen Phipson MAKE uk - the manufacturers’ organisation monthly news comment
If you or your company have achieved something worthy of industry-wide recognition, the 2027 Pump Industry Awards provide the perfect opportunity to showcase your success and gain the acknowledgement it deserves. Following the outstanding success of last year’s event, the 2027 Pump Industry Awards Presentation Evening will once again take place at the prestigious St George’s Park, the home of English Football. Now is the ideal time to consider which products, projects, initiatives and team members deserve recognition. With a little planning, effort and ambition, you could soon be joining our prestigious list of Pump Industry Award winners. Online entry forms are now available at www.pumpindustryawards.com. You can submit multiple entries across the full range of award categories. Companies and individuals shortlisted as 2027 Finalists by our independent judging panel will also benefit from valuable publicity in the lead-up to the Gala Awards Ceremony in March. So, what have you got to lose? Start your entries today and take the first step towards becoming a 2027 Pump Industry Award winner. PUMP INDUSTRY AWARDS 2027 Recognising and Rewarding Excellence Nominations Close: 27th November 2026 Judging Session: Mid December 2026 Voting: 11th – 15th January 2027 Winners Announced: 11th March 2027 www.pumpindustryawards.com Organised by on behalf of Hilton St George’s Park, Burton Upon Trent Thursday 11th March 2027 NOMINATIONS NOW OPEN Ensure you gain the recognition you deserve! 2027 Award Categories and Sponsors Event Calendar sponsored by PRODUCT OF THE YEAR PROJECT OF THE YEAR sponsored by ENVIRONMENTAL CONTRIBUTION OF THE YEAR sponsored by MANUFACTURER OF THE YEAR sponsored by DISTRIBUTOR OF THE YEAR sponsored by sponsored by SUPPLIER OF THE YEAR PUMP MAINTENANCE PROVIDER OF THE YEAR sponsored by CONTRIBUTION TO SKILLS & TRAINING AWARD sponsored by RISING STAR AWARD sponsored by SUSTAINABLE CONTRIBUTION FOR A BETTER WORLD sponsored by
10 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 Insight There is a sentence I hear more and more often in additive manufacturing: “We want to use AI.” It is usually said with good intent. The company wants to reduce scrap, shorten qualification loops, automate analysis, predict quality, optimise parameters, or make production more autonomous. These are valid goals. In fact, they are exactly the kind of ambitions AM needs if it is going to mature into a truly scalable production technology. But there is an uncomfortable question that must be asked before any serious AI discussion begins. What exactly is the AI supposed to learn from? Because if the answer is “machine logs in one folder, powder records in Excel, inspection PDFs in another folder, and a few tribal assumptions held by two experienced engineers,” then the AI project is not ambitious. It is premature. This may sound provocative, but the AM industry does not have an AI problem. It has a data credibility problem. Too many organisations are trying to talk about artificial intelligence before they have created the conditions in which intelligence (artificial or human) can operate reliably. AI does not create truth. It amplifies the quality of the data environment it is given. If that environment is fragmented, inconsistent, poorly labelled, or disconnected from process context, AI will not solve the problem. It will industrialise the confusion. AM generates data, not usable evidence One of the myths in additive manufacturing is that because the process is digital, the data foundation is automatically strong. This is not true. AM certainly generates data. Machines produce logs. Powder is tracked. Parameter sets are stored. Sensors record signals. CT scans, CMMs, and mechanical tests generate reports. Postprocessing steps create additional evidence. Operators sign off work instructions. Maintenance activities are documented somewhere. Building the data foundation for credible AI in additive manufacturing As artificial intelligence gains traction in additive manufacturing, Tim Wischeropp, CEO of amsight, explains why connected, contextualised quality data is essential for turning AI ambitions into credible production tools. But generating data is not the same as building a usable evidence chain. The real challenge is not whether data exists. The challenge is whether powder history, machine state, build parameters, post-processing, inspection outcomes, and partlevel conformity can be linked in a way that is consistent, queryable and trusted over time. That distinction matters enormously for AI. An algorithm does not simply need “more data.” It needs data with context. It needs to know which powder lot was used, how many reuse cycles were involved, which machine produced the build, whether maintenance had occurred, which parameter revision was active, which post-processing route followed, and which inspection result belongs to which part or coupon. It needs to know what changed, when it changed, and whether that change mattered. Without that connected context, AI becomes pattern recognition without accountability. The danger of “dashboard theatre” The next years in AM will produce a lot of AI theatre. We will see attractive dashboards that claim to detect risk, predict defects, or recommend actions. Some will be valuable. Many will be impressive demonstrations built on weak foundations. The danger is that organisations mistake visual sophistication for process understanding. A coloured warning icon is not quality management. A predicted anomaly is not rootcause analysis. A machine learning model that cannot explain the evidence chain behind its recommendation will struggle to survive the realities of regulated production. This is especially important in sectors such as space, aerospace, defence, energy, semiconductor, and medtech. In these environments, quality decisions are not just technical decisions, they are accountable decisions. If an AI system recommends that a build is acceptable, a customer or auditor may eventually ask why. If the answer cannot be traced back to controlled data, validated assumptions, and documented process evidence, the recommendation is not credible. AI must therefore be built on an AM quality data backbone, not scattered files. What a quality data backbone actually means It is not a generic data lake, a document repository, or an MES with extra attachments.. For AM, a quality data backbone is a structured system that connects the full production evidence chain around the part and process. It captures and normalises data from machines, powders, parameters, post-processing steps, Figure 1: Connected context makes data usable for traceability, SPC, root-cause analysis, and AI.
Insight August/September 2026 www.pwemag.co.uk Plant & Works Engineering | 11 inspection systems, and quality records. It links that information across builds and across time. It makes the data usable for traceability, reporting, SPC, root-cause analysis and, eventually, AI. The word “backbone” is important. AI cannot be a floating layer above production. It needs a spine: a reliable model of the process that tells it what the data means. This is where many AM organisations need to rethink their IT architecture. ERP remains essential for business truth. MES remains essential for execution truth. But AM needs a dedicated production-level quality software that owns quality truth (part-level evidence, powder genealogy, process history, inspection results, stability metrics, and repeatable reports.) Only then can AI move from experimentation to operational credibility. SPC before AI One of the mistakes companies make is jumping directly from manual reporting to AI prediction. That skips a crucial maturity step, statistical process control. SPC is not old-fashioned. It is one of the best readiness tests for AI in production AM. If a company cannot define critical-to-quality characteristics, monitor process stability, detect drift, understand variation, and respond through defined control limits and reaction plans, then it is not ready to delegate judgement to AI. It is still learning how to describe its process. SPC forces discipline. It asks, what are we measuring? Why does it matter? How stable is the process within a build and across builds? What input variables appear to influence the outcome? Which variations are normal, and which are signals of risk? These are exactly the questions that make AI useful later. A mature AI strategy in AM should therefore not replace SPC. It should build on it. SPC gives the process its language. AI can then help recognise more complex relationships, accelerate analysis, and suggest earlier interventions. But without SPC discipline, AI risks becoming a black box sitting on top of a grey fog. AI needs labels, and AM often hides them In machine learning, labelled data is precious. In production AM, the labels are often buried. A part may be accepted or rejected, but why? Was the root cause powder condition, laser drift, parameter choice, build layout, post-processing variation, operator error, inspection uncertainty, or a maintenance event? Was it truly scrap, or was it accepted under deviation? Did it fail CT but pass mechanical testing? Did the coupon represent the part accurately? Was the parameter set later revised? These details matter because they turn outcomes into learning signals. If organisations only store final reports, AI learns very little. It sees results, not reasons. It sees pass/fail, not process history. It sees defect categories, not the chain of events that produced them. A quality data backbone turns production into a learning environment. Every build becomes more than an isolated event. It becomes a structured data point in an evolving understanding of the process. That is where AI becomes powerful. The commercial reason to care There is a practical commercial reason to build this backbone before chasing AI, and that is credibility. Customers in regulated sectors do not want experimental intelligence. They want controlled intelligence. They want confidence that recommendations are grounded in traceable evidence and that data can support qualification, audit readiness, and continuous improvement. If a supplier can show that its AI efforts are built on connected powder, process, and inspection data, the conversation changes. AI is no longer a marketing claim. It becomes an extension of quality maturity. This is powerful because the market is becoming more demanding. It is no longer enough to show a successful build. Customers increasingly want to know whether the supplier can reproduce quality, explain variation, prove conformity, and reduce risk as production scales. The companies that can answer these questions with structured data will be in a stronger commercial position than those offering only machine capacity and enthusiasm. What AM leaders should do now The path does not begin with hiring a data scientist and asking for a prediction model. It begins with building the evidence chain. Start with traceability. Link powder, build, postprocessing, and inspection at part level. Standardise how quality data is captured. Reduce manual reporting. Define critical-to-quality attributes. Implement SPC where variation matters most. Make root-cause analysis faster by connecting machine events, maintenance, powder state, and inspection outcomes. Create repeatable reports that do not require forensic spreadsheet work. Then, and only then, ask where AI can add value. Can AI help detect early drift? Can it identify correlations between powder reuse and quality outcomes? Can it suggest more targeted inspection? Can it shorten root-cause analysis by surfacing likely process changes? Can it support parameter development by learning from historical production evidence? These are credible AI questions because they start from a credible data foundation. The future is not AI versus quality management Some people talk about AI as if it will replace quality management. I think the opposite is true. AI will make quality management more important, not less. As algorithms become more involved in production decisions, the need for structured evidence, traceability, governance, and accountability increases. The better the AI, the more important it becomes to understand what it was trained on, what it sees, what it does not see, and why its recommendations should be trusted. For AM, this is a significant opportunity. The industry has always been data-rich, but it has not always been data-disciplined. AI gives us a reason to become disciplined faster. At amsight, our view is clear, the future of AM quality will be data-powered, but only if the data is connected, contextualised and usable. The digital quality backbone is the enabling part. Without it, AI remains a slide in a strategy deck. With it, AI becomes a practical tool for supporting more reliable, lower-risk AM production at scale.. The companies that understand this will move faster. Not because they adopt AI first, but because they build the foundation that makes AI worth trusting. And in production AM, trust is the real technology. For further information please visit: https://www.amsight.de Figure 2: AI is only as credible as the quality backbone beneath it.
Maintenance Matters Focus on: CMMS 12 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 The Computerised Maintenance Management System (CMMS) is frequently sold as a silver bullet for industrial operational headaches. Companies invest heavily in these platforms, hoping software alone will fix deeply ingrained reliability issues. Yet, no platform operates as a magic wand. A CMMS is an advanced instrument whose power hinges entirely on organisational discipline. In discussions with leaders, I compare a CMMS to an office filing cabinet, both are useless without clear structure, deliberate use, and diligent maintenance. To turn your CMMS into a genuine profit driver, treat it as a dynamic, living ecosystem that captures the true heartbeat of your operations. The bedrock of data integrity and asset hierarchy To construct a high-performing CMMS, organisations must begin with a rock-solid structural foundation. Rather than allowing data to decay, a best-practice system requires that all assets are recorded in exhaustive, granular detail. This includes capturing complete nameplate information and documenting exact physical locations on the plant floor. The same rigorous standards must apply to the Bill of Materials (BOM), where a planner must be able to find parts and vendors instantly. This is achieved by building BOMs with sub-assemblies to make complex component searches intuitive, and by clearly identifying stock versus non-stock items. When the CMMS is fully integrated into an Enterprise Asset Management (EAM) framework, it enables the creation of work orders directly against the asset, allowing for the requisitioning of parts and the capturing of all labour and material costs in one seamless flow. The foundation of any optimised CMMS is a well-defined asset hierarchy. A robust hierarchy allows for more accurate planning, better component control, and the allocation of maintenance costs to the correct equipment at a granular level. Further, it allows the condition and performance of equipment to be tracked with precision, aiding in failure tracking and downtime analysis. Once the hierarchy is established, the organisation must prioritise its assets, moving away from a one-size-fits-all maintenance approach and toward a strategy based on criticality (ranging from the most critical to run-to-fail). Importantly, this is not a task for the maintenance department alone. A multidisciplinary team of subject matter experts from operations, engineering, and administration must agree upon the criticality list, considering factors such as mission impact, safety, environmental risks, and spares lead times. Additionally, this list is not static as frequent reviews must be established to update criticality criteria as the plant evolves. A living document requires a guardian. Without written standards and clear rules for specific job positions, the integrity of a CMMS will inevitably decay. We must ask ourselves, who is the gatekeeper? Is it a Reliability Engineer or a dedicated CMMS coordinator? Without a designated authority, new personnel will often interact with the system based on their personal preferences, making unauthorised changes that erode the standardized structure and compromise long-term data integrity. Designing for reliability over accounting One of the primary reasons maintenance organizations struggle with CMMS optimisation is a fundamental misalignment during the implementation phase. All too often, these systems are designed primarily for accounting purposes, for example, tracking spend and labour for the finance department, rather than for maximum asset careand reliability. When a CMMS is built through the narrow lens of an accounting ledger, it fails to serve the maintenance team on the shop floor. In reality, the best-in-class CMMS serves as a one-stop shop for all the information a maintenance organisation needs to locate asset details quickly and efficiently, which directly correlates to superior asset reliability. For a CMMS to transcend its role as a digital file cabinet, it must be the primary tool for reviewing performance, ordering parts, investigating failures, and examining actual Turning your CMMS into a reliability and profit driver Terry Alexander, CMRP, REC, Senior Reliability Engineer at Life Cycle Engineering, explains why a CMMS is only as effective as the discipline behind it, and how robust data, asset hierarchy, governance and performance metrics can transform maintenance from a cost centre into a driver of reliability and profitability.
August/September 2026 www.pwemag.co.uk Plant & Works Engineering | 13 Focus on: CMMS Maintenace Matters performance against Key Performance Indicators (KPIs). If a technician is informed of a failure and must waste valuable time traveling to a physical site just to find nameplate data because the digital record is incomplete, the system has failed its primary mission. Custom integration, true partnerships, and respecting data Implementation cannot be achieved via a generic software installation. It requires establishing a true, deep partnership with specialised organisations to configure, customize, and align the system to the specific operational realities of your plant. Setting up a CMMS is not a one-sided data entry chore as it can and should be a collaborative design process that must mirror your actual workflow standards. Finding specialised organisations who can train your people and help guide this configuration is a critical success factor that determines whether the software succeeds or is abandoned. Central to this partnership is being deeply respectful of your existing data. In many cases, plants either blindly migrate decades of corrupted naming conventions into a new system, or they discard valuable legacy data entirely. A partner-led implementation approach balances this by auditing, cleansing, and validating existing data. This process ensures that clean historical records are mapped accurately into the new granular asset hierarchy, maintaining the integrity of failure trends while filtering out the system noise of the past. Furthermore, general software training is a major driver of CMMS failure. Technical staff do not benefit from generic online videos that cover basic software features. Instead, organisations must work with their integration partners to develop specific training on how your CMMS is actually set up and customised. Training must be grounded in your specific asset names, local rules of use, and defined workflows. When technicians are trained on the exact screens, codes, and equipment they interact with daily, they develop immediate proficiency and become active champions of data integrity on the floor. Transforming cost centres into profit centres To shift the maintenance organisation from a drain on resources to a driver of profit, the CMMS must be governed by strict rules of use and shift from being reactive to proactive. Poorly managed systems are characterised by leakage such as task work not captured on work orders, materials removed from stock without records, and inaccurate labour hours. When these activities are not tracked, the true cost of an asset remains a mystery. In a wellmanaged system, the benefits are clear. Leadership gains an understanding of the total asset cost over its entire life cycle, which allows for accurate budgeting and 3-to-5-year outlook forecasts. A disciplined CMMS supports the transition from invasive, expensive preventative maintenance toward predictive, condition-based maintenance. By utilizing a Ranking Index for Maintenance Expenditures (RIME), planners can prioritise work orders based on equipment criticality and the risk associated with deferred actions, ensuring that the most vital assets receive the most attention. Shifting a budget from a negative to a healthy, positive variance results in a surplus that allows you to reinvest heavily in your people. Reinvesting those funds into high-quality maintenance training, advanced diagnostic tools, power equipment, and consumables greatly improves the morale and technical capabilities of your team. By documenting specific asset improvements, for example, tracking the exact percentage of uptime and ensuring machines performed above standard, we can finally quantify maintenance’s contribution to the organisational bottom line. Moving from reactive to proactive leads to significant safety improvements on the floor, with the maintenance team leading as active subject matter experts. Driving improvement through rigorous metrics The old saying remains true. You cannot improve what you do not measure. Managing a CMMS requires the application of rigorous metrics, such as those found in the Society for Maintenance & Reliability Professionals (SMRP) Body of Knowledge (BoK). These Pillar 5 metrics provide a roadmap for continuous improvement. Key indicators include measuring the percentage of total assets fully recorded in the CMMS and the percentage of BOM completion. More advanced organisations track metrics such as Planning Variance Index, Schedule Compliance, and Wrench Time. For example, by tracking Wrench Time, an organization can identify administrative delays that keep technicians away from the assets. Deploying mobile CMMS applications can further optimise this by providing technicians with real-time access to manuals and the ability to close work orders on the shop floor, eliminating paper-based delays. CMMS optimisation is a journey, not a destination. It requires applying the right resources, ensuring all personnel are engaged, and using KPIs to drive a culture of continuous improvement. By establishing consistent naming conventions and standardised codes for failures and repairs, you ensure that the data fed into the system is clean, which is the only foundation upon which reliable trend analysis can be built. Ultimately, a CMMS should be more than a digital version of a dusty file cabinet. It should be an automated workflow management tool that optimises the lifecycle of a work order, from the initial request to final completion, by matching technician skill sets with tool availability and asset priority. When the system is treated as a living document, it ceases to be a burden of data entry and becomes the most powerful asset in your reliability arsenal. For further information please visit: www.LCE.com
Maintenance Matters Focus on: OEE 14 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 Overall Equipment Effectiveness (OEE) has proved useful because it brings three familiar sources of production loss into a common measure. Availability reflects the proportion of planned production time during which equipment is actually running, performance accounts for losses associated with running below the ideal production rate, including slow cycles and small stops, and quality reflects the proportion of output produced correctly first time. Used properly, OEE therefore provides production and engineering teams with a consistent way of identifying where productive capacity is being lost, although the headline percentage is considerably less informative than the losses from which it is calculated. One limitation is that OEE principally describes production performance rather than equipment health. By the time a four-hour breakdown appears as an availability loss, the maintenance department is already well aware that the machine has stopped, while repeated minor stops or a gradual reduction in production rate may have affected output for several shifts before the accumulated performance loss attracts attention. Real-time OEE reporting shortens the delay in seeing these effects, but it does not by itself establish the mechanical, electrical or process condition responsible for them. Condition monitoring addresses a different part of the problem and has been doing so since long before the current interest in artificial intelligence. Vibration analysis, oil analysis, thermography, electrical measurements and process parameters can all provide evidence of developing faults, while established diagnostic and prognostic techniques can help engineers assess deterioration and, where sufficient information exists, estimate future asset condition. Predictive maintenance should not therefore be regarded as synonymous with AI, since the principle of using information about asset condition to inform maintenance decisions is already well established. What has changed is the quantity and variety of information that can economically be collected from production equipment and the ability to analyse relationships within those data. PLCs, drives, machine controllers, condition monitoring systems, vision equipment and additional sensors can provide information about an asset while it is operating, allowing production behaviour to be examined alongside indicators of mechanical or process condition. A motor drawing progressively more current, for example, may be unremarkable in isolation, as might a small change in cycle-time consistency, but a relationship between several OEE and the value of time Overall Equipment Effectiveness (OEE) has traditionally helped manufacturers quantify where productive capacity is being lost, but the growing availability of machine, process and condition data is creating an opportunity to recognise some of the conditions associated with those losses earlier. Artificial intelligence may extend that capability, provided it is applied to an engineering problem rather than treated as an end in itself. PWE reports.
IF YOU’RE READING THIS, THEN SO ARE 30,000+ ENGINEERS IMAGINE THE IMPACT YOUR ADVERTISEMENT COULD HAVE Contact Damien Oxlee at PWE Tel: 01732 370342 Plant&Works Engineering www.pwemag.co.uk If You ARE FILLER q.qxd_If u Filler 26/02/2018 13:12 Page 1
16 | Plant & Works Engineering www.pwemag.co.uk August/September 2026 Maintenance Matters Focus on: OEE such changes may warrant investigation even though none has reached an established alarm level. Looking beneath the OEE figure Machine learning can be useful where relevant behaviour is represented by relationships between several variables or where normal operating conditions vary according to product, speed, load or process state. This does not make established condition monitoring obsolete, nor does it mean that an algorithm will necessarily identify a developing fault more reliably than an experienced analyst using an appropriate technique. Its potential lies in examining larger and more complex sets of operating data than would normally be practical for a person to monitor continuously, then highlighting patterns or changes that may merit engineering attention. The connection with OEE becomes particularly interesting when deterioration affects production before it causes a breakdown. A packaging machine, for example, may develop a handling problem that causes increasingly frequent brief interruptions without suffering a prolonged stoppage. Operators clear the fault and restart the machine, with each interruption perhaps lasting only 20 or 30 seconds, yet the accumulated effect over a shift can become a significant performance loss. If the increasing frequency of those events coincides with changes in drive load, vibration or another relevant condition indicator, examining the information together may provide useful evidence of a developing problem and give engineers a reason to investigate it. Quality losses can develop in a similar manner because a process does not necessarily move directly from producing acceptable components to producing rejects. Tool wear, temperature variation, pressure changes and other forms of process drift can move measured characteristics gradually towards specification limits while production remains acceptable. Where there is a repeatable relationship between that movement and machine or process data, statistical analysis or machine-learning techniques may help identify conditions associated with the drift before they result in scrap. Whether that approach is worthwhile will depend upon the process, the available measurements and the cost of the losses involved rather than simply upon the availability of an AI system. Forecasting an OEE value is not, however, the same as predicting the physical conditions that will cause future production losses. OEE forecasts can be produced from historical production and machine data, and machinelearning techniques are among the methods that have been investigated for doing so. Such a forecast may indicate that availability, performance or quality is likely to deteriorate, but it does not necessarily explain the engineering reason for that deterioration. For a maintenance team, evidence about the developing condition of an asset may therefore be considerably more useful than knowing only that a future OEE figure is expected to be lower. There are also practical limitations that become particularly apparent in factories containing equipment of different ages and from different suppliers. Machine learning depends upon appropriate data, and no analytical method can compensate for unreliable sensors, poorly defined production states or inaccurate production parameters. Ideal cycle time, for example, should represent the theoretical fastest rate at which the process can produce rather than an easily achievable target or budget rate. Setting it incorrectly can distort the performance component of OEE before any more advanced analysis has taken place. The same caution applies to downtime classification and operating context. A data set showing that a machine has stopped does not necessarily establish whether the cause lies with the machine, an upstream process, unavailable material, an operator intervention or a downstream blockage. Relationships discovered in historical data can also be misleading when changes in product mix, production schedule or operating practice are not represented properly, which means that engineering interpretation remains at least as important as the sophistication of the analytical method. For that reason, an OEE loss analysis provides a sensible starting point for deciding where additional condition or process information might have value. Where one asset repeatedly constrains a production line through availability losses, additional monitoring may help engineers understand the failure mechanisms and recognise signs of deterioration earlier. Another asset may rarely suffer a significant breakdown but consistently lose output through reduced speed or minor stops, in which case production states, cycle behaviour, drive loads or process variables could be more informative than measurements aimed solely at assessing component condition. Earlier evidence for engineering decisions Experienced operators and maintenance engineers already carry out a considerable amount of pattern recognition, often noticing changes in sound, vibration, temperature, product behaviour or machine response that are difficult to reduce to a single alarm value. Their accumulated knowledge may include an understanding that a particular machine becomes troublesome after extended operation, that a certain combination of apparently unrelated symptoms has previously preceded a stoppage or that a process behaves differently with one product variant. Analytical systems are most valuable when they complement this knowledge by examining information that cannot reasonably be observed continuously, rather than attempting to replace engineering judgement with a numerical prediction. The way an analytical result is presented consequently matters almost as much as the calculation behind it. A statement that a machine has a particular percentage probability of failing within a specified period can create an impression of precision without giving the maintenance team enough information to decide what should be inspected. Evidence showing that vibration behaviour has changed over several shifts while motor load has increased and cycle-time variation has become greater provides a more useful basis for investigation, because the engineer can compare those observations with the machine’s physical condition, operating history and known failure modes before deciding whether intervention is justified. Any investment in this area also needs to be judged against production outcomes rather than the quantity of data collected. Condition monitoring, machine learning and additional sensing have a stronger business case where their use can be associated with fewer unplanned stops, reduced performance losses, more stable quality or better use of planned maintenance opportunities. The current UK approach to industrial AI reflects the same practical difficulty, with manufacturers facing issues around legacy equipment, fragmented data, integration, assurance and demonstrating value as they attempt to move applications from trials into routine production. For many plants, the useful development will consequently be less dramatic than the suggestion that forecasting OEE will somehow reveal what is happening inside the equipment. OEE can continue to show where productive capacity has actually been lost, while forecasts may indicate how that performance is likely to develop and condition, process and production data can provide evidence about the reasons behind it. If engineers approaching a planned shutdown on Friday can see on Tuesday that a critical machine is behaving differently from its established operating pattern, they still have to determine what the data mean and whether intervention is justified, but they have gained something maintenance departments rarely complain about having too much of: time.
RkJQdWJsaXNoZXIy MjQ0NzM=