Digital AIUpdated 21 October 20268 min read

Predictive Maintenance Explained: A Practical Guide for UK Plants

Predictive maintenance schedules repairs from the measured condition of a machine rather than the calendar. Siemens' 2024 survey found nearly half of large industrial firms now have dedicated predictive-maintenance teams, twice the share of 2019. This guide compares the four maintenance strategies, the sensors involved, where PLCs and SCADA fit, and a realistic adoption path.

Predictive MaintenanceCondition MonitoringMachine LearningSCADAIndustry 4.0Reliability
Technician using a handheld diagnostic tool beside a server rack in a data centre

Key takeaways

  • Predictive maintenance forecasts failure from measured condition (vibration, temperature, current), while preventive maintenance follows the calendar and condition-based maintenance reacts to a limit.
  • Siemens' 2024 survey found almost half of large industrial firms have dedicated predictive-maintenance teams, twice the 2019 share, and nine in ten do some condition monitoring.
  • A 2002 US Department of Energy guide estimated preventive maintenance saves 12% to 18% over run-to-failure and predictive a further 8% to 12%; treat that as dated and indicative.
  • PLCs and SCADA supply clean, timestamped, state-aware data; the analytics usually run on an edge device or platform, connected over OPC UA, not inside the PLC scan.
  • Most plants lack failure histories, so start with anomaly detection and handheld thermal or vibration routes on five to ten critical assets before buying a full platform.

Predictive maintenance (PdM) means using measured condition data, such as vibration, temperature and motor current, to forecast when a machine is likely to fail so you can repair it at the right time rather than too late or too early. It pays off on a short list of critical assets with known failure modes, and only when the data actually reaches a person who can act on it. According to Siemens' True Cost of Downtime 2024 report, almost half of the large industrial firms it surveyed now have dedicated PdM teams, twice the proportion seen in 2019, and nine out of ten do some form of condition monitoring.

What is the difference between reactive, preventive, condition-based and predictive maintenance?

The four strategies differ in what triggers the work: a failure, the calendar, a measured limit, or a forecast. Most plants run a mix, and the sensible goal is to put each asset in the cheapest strategy that its failure consequences allow.

StrategyWhat triggers the workGood forMain weakness
Reactive (run to failure)The machine breaksCheap, non-critical, easily replaced itemsUnplanned stops, secondary damage, overtime
Preventive (time or run-hours)A fixed intervalLubrication, filters, wear items with predictable lifeReplaces parts that still have life; misses random failures
Condition-basedA measured value crosses a limit (for example a vibration alarm)Assets where one or two variables show degradationWarns late if the limit is crude; no forecast of time left
PredictiveA trend or model forecasts remaining useful lifeCritical rotating equipment with slow, detectable degradationNeeds good data, baselines and a process to act on alerts

The US Department of Energy's Federal Energy Management Program published an Operations and Maintenance Best Practices Guide in 2002 that puts rough numbers on the progression. It estimated that preventive maintenance can save 12% to 18% over a purely reactive programme, and that a properly functioning predictive programme can save a further 8% to 12% over preventive alone. Treat these as dated, indicative estimates from a US facilities context, not as a promise for your plant. The same guide is candid about the downside: predictive equipment was expensive to start with, and staff training needed real funding.

What does unplanned downtime cost?

Siemens' report estimates that the world's 500 biggest companies lose almost $1.4 trillion a year to unplanned downtime, equivalent to 11% of their revenues. It puts the cost of a lost hour at $36,000 in fast-moving consumer goods and $2.3 million in automotive, and says SME manufacturers can lose up to $150,000 an hour at the top end. Large plants in its sample averaged 25 downtime incidents and 27 lost hours a month, down from 42 incidents and 39 hours in 2019.

Read those figures with care. They come from a survey run by a vendor that sells predictive-maintenance software, they are in US dollars, and they describe very large plants. Your own number is better: lost margin per hour, plus idle labour, scrap, expedited parts and any contractual penalties, multiplied by realistic hours lost per year on each asset. That calculation, not an industry headline, decides where PdM is worth the effort.

Which sensors and data do you need?

Most useful PdM data comes from three families of measurement, each catching different faults.

Technician pointing a handheld thermal imager at an open electrical control cabinet to check for hot connections
Technician pointing a handheld thermal imager at an open electrical control cabinet to check for hot connectionsPhoto: Carlos Part, CC BY-SA 4.0, via Wikimedia Commons
MeasurementWhat it tends to revealTypical sourceEasy to bring into a PLC?
Vibration (acceleration or velocity)Bearing wear, imbalance, misalignment, loosenessAccelerometers, often with a dedicated analyser or gatewayOverall levels yes; raw waveforms usually no
Temperature and thermal imagingOverheating bearings or windings, loose electrical connectionsRTDs and thermocouples on the machine; handheld thermal camera on roundsYes for fixed probes
Motor current and powerLoad changes, blockages, pump problems, some rotor and mechanical faultsVariable frequency drive diagnostics, current transformersYes, often over PROFINET or Modbus
Run-hours, starts, cycle countsWear that follows usage rather than timeThe PLC itselfYes, already there

Vibration is the workhorse for rotating machines. The ISO 20816-1 standard sets out general conditions and procedures for measuring and evaluating machine vibration, which is why many sites express alarm limits as vibration velocity bands by machine class. A thermal camera on a monthly route is one of the cheapest ways to start, and it needs no integration at all. Other signals, such as ultrasound, oil condition and pressure or flow, matter for specific equipment.

Vibration Analysis for beginners 1 (Predictive Maintenance and vibration explanation. How it works?)

One rule saves many projects: always record the operating state alongside the measurement. The same vibration level means different things at idle, at half load and at full speed, so a model that does not know the machine's state will raise false alarms.

Where do PLCs and SCADA fit in predictive maintenance?

The PLC and SCADA layer is where PdM data is cleaned, given context and turned into action, even though the heavy analysis often runs elsewhere. A PLC already holds run status, start counts, run-hours, drive current, temperatures, valve travel times and alarms, all time-aligned with what the machine was doing.

A typical architecture looks like this:

  1. Sensors and drives feed values to the PLC, or to a dedicated condition-monitoring gateway for high-rate vibration data.
  2. The PLC scales and timestamps signals, applies simple health logic (start counts, run-hour limits, high-high alarms) and publishes the data.
  3. SCADA and a historian trend the values, add context such as product, recipe and speed, and show alarms to operators.
  4. An edge device or analytics platform pulls the data, typically over OPC UA, runs anomaly detection and returns a health score. The OPC Foundation describes OPC UA as a platform-independent, service-oriented architecture that protects communication with encryption and certificates, which is why it is the usual bridge between the control network and analytics.
  5. The maintenance system receives a work order when a health score crosses a defined threshold.

Keep machine-learning workloads out of the PLC scan. Control and safety logic should stay deterministic and separate from experimental analytics. For deeper background, see our guides to OPC UA connectivity, SCADA systems and IO-Link smart sensors.

How does the machine learning actually work?

At a practical level, PdM machine learning is feature extraction followed by either anomaly detection or forecasting, and most plants should start with the simpler anomaly side. The steps are:

  • Features: raw signals are reduced to numbers that describe health, such as RMS vibration, spectral band energy, temperature rise above ambient, or current compared with load.
  • Baseline: a few weeks or months of normal operation across the real range of loads and products.
  • Anomaly detection: an unsupervised model learns what normal looks like and flags departures. Scikit-learn's documentation describes this as novelty detection: the training data is not polluted by outliers, and you want to know whether a new observation is an outlier. Isolation Forest and one-class support vector machines are common starting points.
  • Classification and remaining-useful-life models: these need labelled examples of faults or run-to-failure histories, and most plants have very few. Without them, a forecast is guesswork.

You can practise on public data before touching a plant. Case Western Reserve University's Bearing Data Center offers vibration recordings from a 2 hp test motor with faults seeded on the inner raceway, rolling element and outer raceway at diameters from 0.007 to 0.040 inches, at motor loads from 0 to 3 horsepower. Python, covered in our guide to Python for automation engineers, is enough to build a first detector.

The honest limits: models drift when products or speeds change, false alarms destroy trust faster than missed faults, and a clever model with no owner and no work-order route delivers nothing.

How should a UK plant adopt predictive maintenance?

Start small, prove value on a handful of assets and only then scale. A realistic sequence:

  1. Rank assets by consequence. Combine downtime cost per hour with how often each asset fails. Pick five to ten.
  2. Use the data you already have. Check PLC tags, drive diagnostics and the maintenance system's failure history before buying anything.
  3. Pilot on three to five assets. Begin with route-based thermal and vibration readings, then fit permanent sensors only where they earn their keep.
  4. Define the action. Who receives an alert, what they check, and what work order follows. Decide how you will count avoided failures and false alarms.
  5. Integrate and secure. Bring signals into SCADA and the historian over segmented networks, and keep analytics access read-only.
  6. Scale or stop. If the pilot did not avoid a failure or improve planning, fix the process before adding more sensors.

For smaller manufacturers, Made Smarter, described on its website as a national movement backed by businesses and the UK government, says on its website that it helps manufacturing SMEs digitalise their processes through regional delivery partners, and what is available varies by region. Check your local partner before budgeting.

What is predictive maintenance on electric motors - low power motors

How EDWartens can help

PdM sits on top of solid control, instrumentation and troubleshooting skills. The EDWartens Professional Module is a five-day live online class in Siemens TIA Portal covering PLC programming, HMI and WinCC SCADA, followed by self-paced Basic Engineering modules that include instrumentation and sensors and maintenance and reliability. It does not teach machine-learning-based predictive maintenance. To build the groundwork for free, try the process control simulator and the PLC electrical troubleshooting course, then see the Professional Module or sign up.

Start free

Learn AI and machine learning free, then practise the job

Free job simulation

Machine Learning Engineer

Train, evaluate and document a model, and catch target leakage.

The first five days are free, no card needed.

Live UK jobs

AI and ML jobs in the UK

Updated daily, with licensed visa sponsors marked.

Browse all engineering jobs

Frequently asked questions

What is predictive maintenance in simple terms?

Predictive maintenance uses measurements such as vibration, temperature and motor current to detect early signs of wear and forecast when a machine will fail. Work is then planned for a convenient time before the failure, instead of waiting for a breakdown or replacing parts on a fixed schedule whether or not they need it.

What is the difference between predictive and preventive maintenance?

Preventive maintenance is triggered by time or run-hours, for example changing a filter every three months. Predictive maintenance is triggered by the machine's measured condition and a forecast of how long it can keep running. Predictive avoids unnecessary work on healthy parts but needs sensors, data and analysis effort.

Do I need AI for predictive maintenance?

Not always. Many successful programmes start with handheld thermal imaging, route-based vibration readings and simple trend limits. Machine learning, usually anomaly detection first, adds value when you have continuous data from many assets and enough baseline history. Forecasting remaining life needs failure data that many plants do not have.

Where does the PLC fit in predictive maintenance?

The PLC already holds run status, start counts, drive current and temperatures, so it supplies clean, timestamped data and simple health logic. SCADA and a historian trend and contextualise it, and an edge device or platform runs the analytics, typically fed over OPC UA. Analytics should not run inside the PLC scan.

How do I start predictive maintenance in a small UK manufacturer?

Rank assets by downtime cost, pick five to ten, and pilot on three to five using the data you already hold plus handheld thermal and vibration checks. Define who acts on alerts, measure avoided failures and false alarms, then scale. Ask your regional Made Smarter delivery partner what support exists locally.

Sources

  1. Siemens (Senseye), The True Cost of Downtime 2024
  2. US DOE FEMP / PNNL, Operations & Maintenance Best Practices: A Guide to Achieving Operational Efficiency (2002)
  3. DIN Media, DIN ISO 20816-1: Measurement and evaluation of machine vibration, general guidelines
  4. OPC Foundation, OPC UA technology overview
  5. scikit-learn documentation, Novelty and Outlier Detection
  6. Case Western Reserve University, Bearing Data Center
  7. Made Smarter, national movement for UK manufacturing digitalisation

Share this article

About the author

EDWartens Team

EDWartens Instructional Team

The EDWartens instructional team brings together UK-based automation engineers, certified Siemens and Rockwell specialists, and industry practitioners with decades of combined experience in PLC programming, SCADA engineering, and industrial AI.

View all articles by EDWartens

Ready to become job-ready?

Start with a free course today, or train live in Siemens PLC, HMI and SCADA on the Professional Module.