Blog by Willem Offermans: Artificial intelligence in self-direction

Willem Offermans is a passionate principal engineer at Sitech with a particular love for ICT, automation and digitalisation. Structuring, visualising and analysing data, as well as finding possible response paths and recognising patterns and trends, are at the heart of his work. He is still fascinated by the combination of chemistry and technology every day.

Artificial intelligence seems to be taking on mythical forms. If you weigh up the focus on and expectations of AI, it seems to be bound to become the solution to many of our contemporary challenges.

Human resource shortage in the engineering industry, autonomous systems, climate issues, energy and resource transition, etc. In some way or another, AI is regularly linked to these challenges as a solution or at least a contribution to it. But what can we really expect from AI? To what extent are expectations realistic? How can we respond to this as a company? Being critical about and creative with artificial intelligence (AI) are our guiding principles at Sitech.

Collaboration for understanding and application
Unfortunately, even Sitech does not yet have all the answers to the above questions, but we are trying to discover the (added) value of AI. In doing so, we take a pragmatic approach. AI cannot happen without people and companies, who make AI possible. But people and businesses then do need to understand what AI is all about. Sitech would like to participate in a club of people, companies, and educational institutions to build understanding and knowledge about AI. To this end, we are trying to involve educational institutions in our region, such as VISTA, Zuyd Hogeschool and Maastricht University in forming so-called “Communities” and/or “Field Labs” concerning AI. These clubs are necessary to achieve cross-fertilization. We learn from the educational institutions’ knowledge of AI, and they learn about our needs and challenges. Together, we fill our knowledge gaps and together we discover the value of AI. In doing so, we are not looking for key solutions, but want to develop generic methodologies for deploying AI. We want to understand it together, so we can all apply it. In collaboration with educational institutions in the region, we want to put AI into practice. Together we want to be creative with AI and together we want to take a critical look at its possibilities. As a bonus of this collaboration, we are educating our current employees, today’s students, and therefore the employees of the future on how to apply and understand AI.

Dates: The key to reliable AI
AI cannot function without data. Sitech can provide data from normally operated, chemical plants. However, we cannot provide enough failure data, simply due to the fact that this data is less prevalent in our datasets. Reliable AI must be trained on data, covering as wide a range as possible. To recognize anomalies in data and interpret them as a particular failure, data must be available about this failure. This can be done by simulating failures. Unfortunately, we cannot do this in Chemelot’s plants. We will be solving this by building test rigs together with VISTA college in Sittard. Engineers from Sitech and students from VISTA will work together to design and build a test rig, which will be fitted with appropriate sensors. Students will run the setup companies and generate data. Together with Sitech engineers, some failures of the test rig will be introduced based on the failure mechanisms, which are known to Sitech. Thus, we can create interesting data sets, which will serve as the basis for growing AI, which cannot only detect the failure as an anomaly, but also interpret the anomaly. The datasets are made available to our engineers and college and/or university students. In-depth analysis and the creation of descriptive and perhaps predictive models then lie ahead.

Monitoring of control valves with AI
Modern process plants use an extensive network of control circuits to operate a plant. These control circuits are designed to maintain a process variable (e.g., pressure, flow, level, temperature, etc.) within a desired range to produce a high-quality end product. An essential component of this control circuit is the control valve. The control valve manipulates the flow rate of a liquid, gas, steam, water or chemical compounds to keep process variables as close as possible to the desired set point. Control valves are often used in difficult conditions such as high temperatures, high pressure, corrosive and abrasive media. An improperly designed or poorly maintained valve can lead to wear, aging and eventual failure. Valve failure can lead to unsafe situations, process chaos or a plant shutdown. When a valve fails it is usually “silent” and the problem becomes suddenly and unexpectedly noticeable to the process operator. To detect potential problems at an early stage, we want to monitor the ‘health’ of valves based on data. Monitoring control valves in factories is very important to ensure safety and prevent production losses.

Smart positioners and AI
Control valves are controlled by positioners. In addition to a control function, these positioners can also have data, which gives an indication of the health of the valve. These data consist of statistical data (histograms) as well as raw data such as air pressure and the actual position of the valve. The valve positioners with this kind of data are called smart positioners. Existing valves can be equipped with smart positioners. The positioners produce data on the control behavior and health of the respective control valve.

Overcoming fragmentation in AI solutions
Artificial intelligence can help determine, interpret and perhaps even predict the state of a control valve based on data. The condition of a valve is tracked by a kind of fingerprint of its data. A change in this fingerprint indicates a different state, provided the change is large enough to detect. A comparison of this change with changes already known and indicated can help to not only notice but also interpret the state change. A trend in change can help predict a state. The methodology is well known, but the number of successful applications is still limited. In any case, too limited to be widely used in the process industry.

Steps to self-direction in AI research and implementation
Commercial solutions already exist to determine valve status based on data from positioners or control circuits. However, these solutions have the major disadvantage of being key solutions to a specific supplier. Other suppliers may also have a similar solution. However, the data from the different providers cannot be merged without question because the data is “stuck” in the solution provider’s data silo. These data also cannot be enriched with other process data, which prevents the full potential of valve failure detection. We need to avoid the fragmentation of data and make data available without constraints to exploit its full potential. Furthermore, the models, which are used in said solutions, are also not public, so the quality of the solutions cannot be improved by using other models, even if they are available.

By taking control of the exploration of artificial intelligence and doing so together with companies and educational institutions in the region, Sitech aims not only to be prepared for future developments, but also to participate in these developments itself.

Do you have any questions? If so, please contact us at

Related articles


Sitech deploys scale-up and engineering expertise in commisioning bench scale installation Brightsite Plasmalab

Case, News

Ebert HERA adopts Sitech designation policy (aanwijsbeleid) with direct benefit to customer in Europoort area


Customers satisfied with Mechanical Services Sitech and Ebert HERA