Industry · Manufacturing

AI in manufacturing. Predictive maintenance on your shop floor.

We build AI solutions that turn sensor data from your machines into concrete maintenance actions, before the failure occurs. With integrations to your existing CMMS, PLC and ERP. Not a lab experiment, but production-ready on the shop floor.

Use casePredictive maintenance
Use caseQuality control
Use caseYield optimisation
Use caseEnergy & safety

Dutch manufacturing in numbers.

~71.000
Industrial manufacturing companies in the Netherlands
~830.000
People employed in industry
~12%
Share of industry in Dutch GDP
61%
Cite unplanned downtime as their biggest OEE risk

Source: CBS Statline Industry 2024, FME Manufacturing Industry Monitor.

Off-the-shelf predictive maintenance platforms rarely fit your machine park.

The major PdM platforms — Siemens Industrial Edge, GE Predix, Schneider EcoStruxure, Rockwell FactoryTalk Analytics, PTC ThingWorx, SAP Predictive Maintenance — work excellently in a homogeneous, single-vendor park. The reality on most Dutch shop floors is different: a Siemens line next to an Allen-Bradley cell, a Mitsubishi press in the corner, and a few older machines with no native connectivity.

The result: you buy licences that cover only part of your park, get dashboards the maintenance engineer never reads, and the valuable correlations between machines and process parameters disappear into vendor silos. The ROI on a standard package is often disappointing because the model a vendor supplies has never been trained on your products, your cycles, your operators.

A custom AI solution takes a different approach: a single data layer on top of all your machines, models trained on your history, and an interface that the maintenance engineer in the cab, not the IT manager at a desk, actually uses. Also see our view on custom manufacturing software and enterprise AI implementation.

In practice, the difference lies in the details: an engineer who sees with every alert which component is likely to fail, which parts are in stock, and what work order history already exists for that exact asset. That is where you win or lose adoption. A dashboard that only the site manager opens is a dead dashboard. What you need is a tool in the hands of both the operator and the engineer, on a tablet or phone, with the right information at the right moment.

For OEMs and machine builders there is also a commercial layer: predictive maintenance as a service sold alongside every new machine, with multi-tenant data isolation per end customer and SLA reporting. That opens up a recurring service revenue stream next to the one-off machine sale. We build that service layer, including customer portal, user management and billing integration.

AI use cases that prove themselves on the factory floor.

Predictive maintenance is usually the first step. After that, quality control, yield optimisation and energy and safety applications open up on the same data infrastructure.

Predictive maintenance

The top use case for AI in manufacturing. With sensors for vibration, temperature, motor current and pressure, you build a continuous picture of the health of every asset. A well-trained model detects deviations that an operator only hears when it is already too late, and links them to a Remaining Useful Life prediction that maintenance planning can act on.

We design the complete stack: sensor selection, edge inference in the control cabinet, cloud-level anomaly-detection models, integration with your CMMS maintenance system and a mobile app for the engineer. We train the model on your history, validate it alongside existing inspection rounds, and only go live once the false-positive rate is acceptable.

Alongside predictive maintenance, we build use cases for quality control (computer vision on the assembly line for defect detection), yield optimisation (tuning process parameters based on AI recommendations, with the operator in the loop), demand forecasting (which product, which batch, which volume), energy optimisation (HVAC plus machine consumption), worker safety (camera vision for PPE checks and hazardous actions), supply-chain AI, robotics (cobots and autonomous mobile robots), digital twins with AI simulation and document AI (CE files, quality reports, ISO work instructions). In many cases, the data infrastructure you set up for predictive maintenance is the same layer these follow-on use cases run on, so that foundation pays for itself twice.

  • Vibration and motor-current monitoringDetection of bearing, balance and alignment issues before damage becomes audible.
  • Remaining Useful Life modelsAn RUL estimate per asset that your planning can steer by.
  • CMMS integration with automatic work ordersA prediction immediately triggers a work order and a parts pick.
  • Mobile app for engineersWork order, machine history and root cause on a single screen on the shop floor.

Built on the standards that matter in industry.

Compliance is not a separate audit step. From the first sprint, we work within the framework of Industry 4.0, ISO standards, the EU Machinery Regulation and the AI Act.

Industry 4.0 / RAMI 4.0

Asset Administration Shell

We model machines according to the Reference Architecture Model Industry 4.0, with the Asset Administration Shell as the interoperability layer. That keeps your data foundation vendor-independent and extensible.

ISO 22301 — BCM

Business continuity management

Predictive maintenance is a continuity tool. We document the impact of model failure, provide fallback procedures and link critical alerts to your BCM plan.

ISO 27001

Information security

OT data only leaves your factory through encrypted tunnels. Access control, audit logs and key management are set up for ISO 27001 certification, with an external audit partner if you wish.

EU Machinery Regulation 2027

Safety of AI components

The new EU Machinery Regulation treats AI software that affects machine safety as a safety component. From the scoping phase, we map out risk classification, conformity assessment and the CE file.

EU AI Act

High-risk classification for safety AI

Safety-critical AI (worker-safety camera detection, machine safety decisions) falls under high-risk. Data quality, transparency, human oversight and log retention are part of our defaults.

Seamlessly connected to your existing OT and IT stack.

We integrate with the control systems, sensors and software your factory already works with. No vendor lock-in: our layer complements them and stays manageable by your own team.

OPC UA
Machine-to-cloud protocol
MQTT
IoT messaging
Modbus
Legacy PLC integration
Azure IoT
Cloud aggregation
AWS IoT
Cloud aggregation
Siemens S7
PLC family
Allen-Bradley
Rockwell PLC
SAP / Dynamics
ERP integration

One data layer on top of all your machines.

We have standardised the integrations above across multiple industrial projects. For a new project, we set up sensor streams using the same abstraction layer: raw signals via OPC UA or MQTT to an edge broker, preprocessing in the cabinet, and aggregated features sent to the cloud for model training. That means fewer integration bugs, faster turnaround, and your own automation team can manage it once we step out.

For legacy machines without native connectivity, we build retrofit solutions: additional sensors, a gateway with edge compute, and a translation layer into your modern stack. This brownfield approach is exactly where off-the-shelf packages fall short. Read more about our data engineering approach and computer vision applications for visual quality control.

At the ERP and CMMS layer, we typically work with SAP, Microsoft Dynamics, Ultimo, Planon and Maximo. The alerts from the AI model are not delivered as an extra inbox stream, but land directly as a work order in your existing system, with the right priority, a parts suggestion and a link to the asset history. That way, your maintenance planning, time registration and cost reporting keep working just as you are used to. For the technician on the shop floor, we deliver a mobile app that fits seamlessly into that work order flow.

Finally, we are fundamentally opposed to vendor lock-in. The code, models, training data and infrastructure-as-code remain yours. On handover you receive the complete documentation, and your own team, or another party, can take it over. We see that as a mark of quality, not a commercial threat.

Not sure about a large project yet?

Test your idea first: a working prototype in 1 day

With OneDayBuild, we make your idea tangible in a single day for €1,150, so you know whether further development is worth the investment. Decide to go ahead with the full build? Then we deduct the cost in full.

View OneDayBuild →

From first audit to production-ready AI model.

An AI implementation on the shop floor has its own rhythm, different from a typical software project. Five phases that are identical for every manufacturer.

01 · Audit

Shop floor walk

A day on site with your maintenance manager and plant manager. Result: top 3 critical assets, available data, priority use case.

02 · Data foundation

Sensors & pipeline

Sensor selection, connectivity, edge broker, cloud bucket. Collect data first, and only then train a model. A few sprints to get a working ingest.

03 · Model development

Anomaly & RUL

Anomaly detection on operational data, followed by RUL models where there is enough failure data. Validation alongside existing inspection rounds.

04 · Integration

CMMS & mobile

Alerts translated into work orders in your CMMS, a dashboard for operators, and a mobile app for the technician, without anyone needing a new login.

05 · MLOps

Ongoing

Models re-weighted on new data, drift detection, retraining pipeline. A fixed monthly maintenance cycle, not a one-and-done.

Our work in manufacturing.

Food · Multi-line

Vibration monitoring on a packaging line

Edge sensors on critical motors, an anomaly detection model with CMMS work order integration. Operator dashboard on tablets at the line.

−42%
unplanned downtime
14 assets
monitored live
Machine building · OEM

Predictive platform for machines sold

The OEM provides predictive maintenance as a service with new machines. Multi-tenant data platform, customer portal and SLA reporting per customer.

Service revenue
new revenue stream
Multi-tenant
one platform, multiple customers
Chemicals · Process plant

Yield optimisation for a batch reactor

Tuning process parameters based on AI-driven recommendations, alongside the existing SCADA. Operators stay in control, the model advises.

+3,1%
yield on pilot line
Operator-in-the-loop
no autonomous control

Recognised within Dutch manufacturing.

FME Manufacturing Industry Monitor 2024

"AI applications in predictive maintenance will make their definitive breakthrough in Dutch manufacturing in 2024, particularly among mid-market producers that cannot bear the licensing structure of the large platforms."

Smart Industry Roadmap NL

"The biggest OEE gains lie in brownfield implementations: fitting existing machines with sensors and building on top of an open data layer, rather than replacing the entire fleet."

Customer survey, food producer

"The combination of edge inference and a mobile app for the technician has genuinely changed the way of working on the line within the first few months. Alerts reach the right person at the right moment."

Answers for the plant manager starting with AI.

The questions we hear most often from maintenance managers, plant managers and OEM product directors.

What exactly is predictive maintenance, and how does it differ from preventive maintenance?
Preventive maintenance runs on a schedule (a service every 1,000 running hours), regardless of the machine's actual condition. Predictive maintenance uses continuous sensor data and AI models to determine the real health of an asset and only steps in when a deviation appears. It saves you both unnecessarily early maintenance and unplanned downtime. It is most effective on critical rotating machinery (motors, pumps, compressors, conveyor belts) with measurable degradation signals.
Which sensors do we need to get started?
It depends on the type of machine. For rotating assets, vibration (accelerometers) is the most valuable first sensor, followed by motor current, temperature and, for hydraulic systems, pressure. Often the PLC already has sensors that we don't need to add, only expose via OPC UA or Modbus. We always start a project with an audit in which we look at which data is already available before advising on any hardware investment.
How much data do we need for a working model?
For anomaly detection (deviation from normal behaviour), a few months of operational data is often enough to get started. For true Remaining Useful Life prediction, you also need failure data: examples of assets that have actually failed. In a factory where breakdowns are rare, that takes longer. We are realistic about this and start with anomaly detection as a foundation while RUL data builds up.
Our machines date from the 1990s. Is this even possible?
Brownfield installations are exactly where our custom approach adds value. Older machines often have no native connectivity, but they can be monitored perfectly well with retrofit sensors and an edge gateway. We tap signals from the existing control system or fit external sensors to housings, bearings and motors. The big standard platforms expect greenfield – we don't.
When will we see ROI on a project like this?
That depends heavily on your starting point. For a factory with regular unplanned downtime and high downtime costs per hour, the business case is often made within several months of going live. For a park of machines that is already well maintained, the gains are smaller and lie more in labour efficiency and deferred replacement. We always carry out a baseline measurement beforehand (current OEE, average downtime costs) so that ROI can be assessed objectively afterwards.
Does our AI solution fall under the EU AI Act?
For pure predictive maintenance models (predicting maintenance), the classification is usually limited, so not high-risk. When AI touches safety functions (worker-safety camera detection, automatic machine stop), you are in high-risk territory with stricter requirements around data quality, transparency and human oversight. We map out that classification from the scoping phase onwards and document conformity. Also read our page on software for the manufacturing industry for the broader compliance context.
What does a predictive maintenance project cost?
A pilot on a single line or asset group with a handful of critical machines is a more compact project. A factory-wide platform with multiple production sites and deep ERP/CMMS integration is a larger project, depending on the number of assets, sensors, integrations and compliance requirements. We work with a fixed sprint budget and give you a concrete price for the complete build after the audit and scoping phase.
Do you work with edge computing or everything in the cloud?
For most predictive maintenance use cases, hybrid is the right answer. Raw sensor streams (vibration at a high sampling rate) don't belong in the cloud, so we pre-process them locally on an edge gateway in the switch cabinet. The first layer of anomaly detection runs there. Only aggregated features and alerts go to the cloud for long-term history, model training and cross-asset correlations. For worker safety and computer vision, inference runs locally anyway, because latency and bandwidth don't allow a cloud round trip.
What if you step away. Can we manage it ourselves?
Yes, that is a starting principle. We deliver all code, training data, model artefacts and infrastructure-as-code into your own repositories and your own cloud account. We also provide a written architecture guide and run at least one handover session with your own automation team. We offer maintenance contracts, but never as a dependency: your team can always carry on independently.

Talk to us about your predictive maintenance project?

An initial half-hour conversation with your maintenance or plant manager. We listen to your critical assets, ask questions about your data maturity and give you an initial direction. No obligation.

Edit content