Identification For Control Based on Neural Networks: Approximately Linearizable Models

This work presents a control-oriented identification scheme for efficient control design and stability analysis of nonlinear systems. Neural networks are used to identify a discrete-time nonlinear state-space model to approximate time-domain input-output behavior of a nonlinear system. The network is constructed such that the identified model is approximately linearizable by feedback, ensuring that the control law trivially follows from the learning stage. After the identification and quasi-linearization procedures, linear control theory comes at hand to design robust controllers and study stability of the closed-loop system. The effectiveness and interest of the methodology are illustrated throughout the paper on popular benchmarks for system identification.

Operating data of a specific Aquatic Center as a Benchmark for dynamic model learning: search for a valid prediction model over an 8-hour horizon

This paper presents an identification repository based on data from a public swimming pool in operation. Such a system is both a complex process and easily understandable by all with regard to the issues. Ultimately, the aim is to reduce the energy bill while maintaining the level of quality of service. This objective is general in scope and not just limited to public swimming pools. It can be done efficiently through what is known as economic predictive control. This type of advanced control is based on a process model. It is the problem of this article and the benchmark considered to show that such a dynamic model can be obtained from operating data. For this, operational data is formatted and shared, and model quality indicators are proposed. On this basis, the first identification results illustrate the results obtained by a linear multivariable model on the one hand, and by a neural model on the other hand. They call for other proposals and results from control and data scientists for comparison.