Improve your production with Model Predictive Control (MPC)
Many production processes are running for more then 20 years using the same conventional controls and technology for many years. Most of the time the standard PID controller is used to control some process values. However, some production processes are hard to control using the standard PID controllers, especially when there is a big ‘dead-time’, when laboratory tests are needed or when several parameters influence each-other.
Current production: Mostly not cost optimal
Examples of these processes are water purification, extruders and chemical processes like production of sunscreen lotion, absorbers for diapers etc. Several PID controllers manage most of the ‘hard to control’ processes and the operators know how to adjust the setpoints to keep the process within specifications. But most of the time, this does not mean that the process is running at the optimal cost effective working point.
Solution: Model Predictive Control (MPC)
The PID controller technology is more then 50 years old so the question arises: are there any better and modern controls possible to control these ‘hard to control’ processes? Luckily the answer is yes: MPC (Model Predictive Control). MPC has been used for many years now, mainly in the Oil and Gas industry. Reason for this is that the technology was expensive to use, requiring specialized skilled persons and expensive software and computing power. This is changing however: MPC is not a special tool for experts anymore but has evolved to a modern technology, which can be used by a wider range of people. This creates great opportunities to use this MPC technology also into other markets.
MPC explained
Model predictive control is thus a software model of the process you want to control. By means of the model the software can predict what is coming out of the process before it actually (physically) gets out or happens. If the product you are making is not according to the specification, you are now able to interact with the process and correct it. A picture below is showing a production process which is for example being controlled by a DCS system.
The DCS interacts with the physical production process and controls it. The model interacts with the DCS, getting the actual values (measurements) and predicting the output. If the predicted output is not desired (for instance quality not good or output volume to low) we can adjust the correct parameters. The new parameters are sent as setpoint to the PID controllers who in turn influence the actual process. This is a great solution, providing the Model is an accurate ‘copy’ of the physical production process. So the problem now arises: how do we get an accurate model of the physical production process? Most current MPC solutions in the market use a step-response approach for each suspected input and some linearization to build a model. Not only is this very time-consuming (costly), but most of the time a simplified model is created. Another disadvantage is that during Model building, your actual production process is influenced by the step-responses.
Our cost effective SmartMPC solution
The solution we offer is based on an unique starting point: your historical process data! By using your data of your production process as a starting point we can build an accurate model and check for the influencing input parameters. Part of the data is used to build the model, the remaining part is used for verification. This ensures an accurate model. Our 3-phase approach:
- Business case study: based on your historical data we build a first model and check together for a business case.
- Advanced analytics phase: during this phase the input parameters are determined, the detailed model is build and is verified.
- Implementation phase: connection to your control system (DCS) is made and the system is tested.
The way the system is implemented can also vary, depending on your demands. The MPC can be implemented as a predictor, leaving the interaction to the process at operator hands (manual). Also the operator can test what-if scenarios before adjusting setpoints in the actual process. The closed-loop (predicting and controlling the setpoints) is of course possible as mentioned and shown earlier. Even a unique extra option is possible: automatic re-training of the model during production. For instance in case new products are being made or in case the process is in a special (rare) state. Our SmartMPC solution is the leading solution for optimizing your production process regarding costs, quality and plant output.
Optimal working point
Most of the processes are running at a working point far from the optimal working point. This means that more costs (like energy) are used and that the output (productivity) is also lower than can be possible. Quality might be higher but most of the time the higher quality is not part of the agreed specification. So the goal is to produce the right quality (not more) at the lowest cost and with the highest productivity: the optimal working point.
