Trend Detection Revisited: AI-based Predictive Maintenance from Factory Floor to Cloud

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.When predictive maintenance prevents a breakdown, the operational benefit may be clear. Proving its financial value is harder. Because the failure never happened, manufacturers need a credible way to estimate what was avoided without exaggerating the impact.In this episode of the Trend Detection podcast, we were joined by Rafael Iadocicco, Customer Success Manager at Siemens, to explore how manufacturers can turn avoided downtime into a fair, transparent and repeatable estimate of financial value.In this episode, we discussed:Why calculating avoided downtime begins with the operational story, not the financial formulaHow early warnings, inspections and maintenance actions create a credible chain of evidenceWhy maintenance, operations and finance must agree on the affected scope, avoided hours and financial basisWhen a simple cost-per-hour calculation is sufficient and when a detailed breakdown is neededHow to account for lost production, scrap, restart waste, emergency labour and spare partsWhy conservative assumptions build more trust than pursuing the largest possible numberHow to avoid exaggeration, double counting and confusion between gross impact and net valueHow a consistent process can be replicated across assets, plants and industriesYou can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.In this episode of the Trend Detection podcast, Niall Sullivan is joined once again by Dr. Peter Schopf, an AI and organizational development expert with a background spanning industry, leadership and information systems.Drawing on his latest projects and research, Peter explores the shift from individual AI towards team-based AI, where shared knowledge, context and intelligent agents could help people collaborate, make decisions and solve problems more effectively.In this episode, we discuss:The shift from individual AI to team AI and what it could mean for organizationsAI agents on the factory floor, from shift handovers and troubleshooting to onboarding and knowledge sharingAI as a leadership assistant, including better meetings, decision-making and conflict resolutionWhy context matters, and how organizations can build and continuously improve shared AI knowledgeThe rapid evolution of AI engineering, from prompt and context engineering to skills, harnesses and multi-agent systemsKeeping humans in the loop, particularly as AI becomes more proactive and autonomousAdoption, security and trust, and why understanding how people interact with AI will be critical to scaling it successfullyPeter also introduces his work on European Verified Agents, a proposed research initiative looking at how team-based AI could be adopted effectively in industrial and organizational environments.You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenanceConnect with Peter on LinkedIn here.

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.Predictive maintenance can transform how manufacturers approach equipment reliability, but that doesn’t mean it’s the right solution for every asset, failure mode or situation.In this episode of the Trend Detection podcast, we're joined by Jordan Walters, Delivery Lead at Siemens, to explore when predictive maintenance makes sense, and when a different maintenance approach might be the better choice.In this episode, they discuss:Why the most critical assets aren’t always the best place to start with predictive maintenanceThe importance of having the right data, not simply more dataHow asset selection, failure frequency and available lead time can determine whether predictive maintenance will deliver valueWhy context is essential for AI to interpret machine behaviour effectivelyThe difference between not being ready for predictive maintenance and predictive maintenance not being right for a particular use caseWhy predictive maintenance should complement, rather than automatically replace, other maintenance strategiesThe role of maintenance teams and human expertise in validating insights and turning predictions into actionThe three foundations for success: the right data, the right machines and the right peopleYou can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.Moving from reactive maintenance to a more predictive approach sounds straightforward. In reality, technology is only one part of the equation.In this episode of Trend Detection, Niall Sullivan is joined by maintenance and asset management experts Kevin Clark, Corey Dickens, Rachel Green and Marc Trusio to explore what it really takes to build a more proactive maintenance strategy.They discuss:Why predictive maintenance should be part of a broader asset strategy, rather than the strategy itselftHow manufacturers can move beyond reactive maintenance and escape “pilot purgatory”Why engaging maintenance teams early is critical to adoption and long-term successThe value of predictive approaches beyond reducing downtime, from workforce confidence and knowledge capture to better planning and decision-makingWhy having more asset data doesn't automatically translate into better insightsHow manufacturers can make use of data from older and less connected equipmentWhere industrial AI can support maintenance teams, including identifying anomalies, capturing expertise and making knowledge more accessibleWhy people, culture and change management can ultimately determine whether new maintenance technologies succeed or stallWhether you're still largely reactive or already expanding predictive maintenance across your operations, this episode explores how to take the next step towards a more proactive, data-driven approach to maintenance.You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.This is the fourth and final episode in Rethinking Predictive Maintenance, a Trend Detection podcast series exploring the people, data and decisions behind successful predictive maintenance.Host Niall Sullivan is joined by Peter O’Hara to explore what it takes to expand predictive maintenance from one site to a wider, multi-site programme.Peter explains why scaling is not simply about copying the same deployment across every factory. Different sites may have different reliability challenges, infrastructure, assets and maintenance priorities. The conversation explores how manufacturers can share lessons and standardise where appropriate, while still adapting the approach to deliver value at each location.In this episode, you’ll learn:Why predictive maintenance often demonstrates more value at scaleWhy a successful deployment cannot always be copied directly to another siteHow local engagement and global knowledge-sharing support adoptionWhy each site needs clearly defined problems and measures of successHow documentation helps preserve knowledge as programmes expandWhat successful multi-site adoption can look like over timeListen to discover how manufacturers can build momentum, share successful practices and scale predictive maintenance without ignoring the needs of individual sites.You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.This is the third episode in Rethinking Predictive Maintenance, a Trend Detection podcast series exploring the people, data and decisions behind successful predictive maintenance.We're joined by Ryan Falcini to examine why some predictive maintenance evaluations demonstrate meaningful value while others struggle to progress beyond the pilot stage.Ryan explains why a successful evaluation must begin with a clearly defined business problem, the right assets and realistic measures of success. The conversation explores the limitations of free proof-of-concept projects, the importance of good operational context and why maintenance teams need to be involved from the beginning.In this episode, you’ll learn:Why predictive maintenance evaluations should start with a business objective, not the technologyHow choosing the wrong assets can create a misleading impression of valueWhy machine data needs operational context to produce useful insightsHow maintenance-team involvement builds trust and supports adoptionWhy predicting failures should not be the only measure of successWhat needs to be in place before an evaluation can progress to wider deploymentListen to discover how manufacturers can move beyond simply testing predictive maintenance and build the foundations for a scalable programme.You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.This is the second episode in Rethinking Predictive Maintenance, a Trend Detection podcast series exploring the people, data and decisions behind successful predictive maintenance.Host Niall Sullivan is joined by Tom Jacques to explore how an International Tech Talents project turned existing PLC status lights into a new source of machine data. Using a camera, the team monitored the lights controlling automated railway points and combined the information with Senseye Predictive Maintenance to identify changing behaviour, without adding sensors or altering the existing control logic.Tom discusses what the demonstrator could mean for manufacturers whose machines may already display useful information that is not currently being captured as data. He also explains where non-intrusive monitoring could be valuable, what further testing would be required for operational use and how collaboration across Siemens helped transform the original idea.In this episode, you’ll learn:How a camera turned existing PLC status lights into usable dataHow the demonstrator identified changes in machine behaviourWhy non-intrusive monitoring could help when systems are difficult to modifyWhy manufacturers should consider the information their machines already displayHow cross-business collaboration changed the direction of the projectListen to discover why some of the machine signals manufacturers need may already be hiding in plain sight.You can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.This episode launches Rethinking Predictive Maintenance, a new Trend Detection podcast series exploring how manufacturers can retain expertise, capture new forms of machine information, evaluate predictive maintenance and expand successful approaches across multiple sites.In this first episode, host Niall Sullivan is joined by Rachel Green to explore what happens when experienced manufacturing and maintenance professionals leave the workforce, taking decades of knowledge with them.Rachel explains why technical information alone cannot replace the experience, judgement and credibility built over a long career.She discusses how manufacturers can reduce their dependence on a small number of experts by capturing maintenance history, adding context to machine data and using predictive maintenance and AI to help people access the right knowledge when they need it.In this episode, you’ll learn:Why critical maintenance knowledge is so difficult to replaceHow reliance on a small number of experts creates operational riskWhy standard procedures cannot capture every real-world maintenance scenarioHow predictive maintenance and AI can make experience more accessibleWhy technology should support experts and develop the next generation, rather than replace peopleYou can find out more about how Senseye Predictive Maintenance can reduce unplanned downtime and contribute towards improved sustainability within your manufacturing plants, by visiting: www.siemens.com/senseye-predictive-maintenance

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – which gives you visibility and insights into all your assets, from single machines to full plants to help you reduce downtime, increase knowledge sharing and accelerate digital transformation across your organization.From the Trend Detection archive - a factory-floor perspective on AI-based predictive maintenance.Tobias, Head of Maintenance and Improvement at Siemens, shares the predictive maintenance journey of Siemens’ highly automated factory in Bavaria.The discussion explores how smart hardware, OT modernisation and AI-driven analytics were brought together in a live brownfield production environment. It also examines how Senseye Predictive Maintenance helped maintenance teams focus on critical assets, act on emerging equipment issues and reduce reactive firefighting.This episode was recorded previously, so references to the project and product reflect the position at the time of recording.

Welcome to the Trend Detection podcast, brought to you by Senseye Predictive Maintenance – the platform which enables predictive maintenance at scale across all of your assets, across all of your plants.This week, Trend Detection revisits a standout episode from the archive.In this conversation, Chris Wonson shares the story behind the deployment of Senseye Predictive Maintenance at BlueScope Steel and explores how predictive maintenance was being applied across its operations.The episode covers:How Senseye Predictive Maintenance was deployed at BlueScope SteelA success case that helped avoid 24 hours of unplanned downtimeHow Senseye Copilot was supporting the way teams worked at the time of recordingPractical advice for manufacturers implementing predictive maintenanceThis archive episode provides a valuable customer perspective on scaling predictive maintenance and turning asset data into practical maintenance action.Find out more about how Senseye Predictive Maintenance can help manufacturers reduce unplanned downtime and improve maintenance efficiency across their plants by visiting: www.siemens.com/senseye-predictive-maintenancePlease note that this conversation was originally recorded and published previously. Some product details may have evolved since the original recording.