Complex and multi-dimensional problems are easily mapped to neural networks, as any number of complex non-linear effects can be represented.

However, this approach is only applicable if large amount of process data is available and the model output is strictly limited to plant states present in these process data (extrapolation impossible).

Neural networks independently extract relevant correlations from large amounts of data. Hence, they provide a valuable complement to physical-logical modeling, which is often insufficient or only feasible with a great deal of effort.

Neural networks rely on artificial intelligence to model and control complex processes. Pattern recognition enables them to recognize and adapt to non-linear relationships in the process. Thus, a main field of application is related to predictive maintenance.

In practice, we deploy neural networks as so-called black-box models.

We address the following problems with neural networks

• Non-linear system identification

• State observer design

• Controller design

  • Neural adaptive control

  • Neural optimal control

  • Reinforcement learning

  • NLq stability theory

PID controller (proportional-integral-derivative controller):

• Widely used and versatile

• Consists of three components: the proportional, the integral and the differential part

• Used to control processes where fast and precise reactions are required

PID controllers are the most versatile type of controller. We adapt the controller behavior to your specific application using a variety of practical approaches:

• Intelligent min/max limits

• Situational freezing of the controller output

• Feed-forward control

• Gain scheduling for different controller dynamics

• Anti-windup for cascade controls

• Limiting controllers that are switched through to the controller output by a min/max selection

• Controller tracking when the controller is inactive for skip-free switching

Fuzzy logic controller:

• Uses fuzzy logic to control complex and non-linear systems

• Particularly useful when mathematical modeling of the system is difficult

• Frequently used in the chemical industry and in the control of combustion processes

In order to achieve optimal control performance and generate long-term added value, we also incorporate concepts from the field of fuzzy control in the sense of holistic APC solutions into the respective specific customer solutions, depending on the problem and objective.

Adaptive control

• continuously adjusts the control parameters to take account of changes in system behavior

• is suitable for processes in which the properties change over time

• applied in the automotive industry and in the control of bioprocesses