In this article, a novel machine learning (ML)-derived control performance assessment (CPA) classification system is proposed. It is dedicated for a wide class of PID-based control industrial loops with processes exhibiting dynamical properties close to second order plus delay time (SOPDT). The proposed concept is very general and easy to configure to distinguish between acceptable and poor closed-loop performance. This approach allows for determining the best (but also robust and practically achievable) closed-loop performance based on very popular and intuitive closed-loop quality factors. Training set can be automatically derived off-line using a number of different, diverse control performance indices (CPIs) used as discriminative features of the assessed control system. The proposed extended set of CPIs is discussed with comprehensive performance assessment of different ML-based classification methods and practical application of the suggested solution. As a result, a general-purpose CPA system is derived that can be immediately applied in practice without any preliminary or additional learning stage during normal closed-loop operation. It is verified by practical application to assess the control system for a laboratory heat exchange and distribution setup.

This paper concentrates on the possibilities of the application of the virtual commissioning procedure for the design and verification of the control systems for the continuous industrial processes. After short review and defining the motivation and recognizing the bottlenecks, the case study is presented. It is based on the laboratory pneumatic setup representing the nonlinear continuous process of the higher relative degree. The stages of its modeling are presented and the potential possibilities of the application of the virtual commissioning for its control are discussed, based on the practical results.

This paper deals with the practical aspects of the implementation of the balance-based adaptive control (B-BAC) technique. It gives the simple mathematical background of this methodology, shows the case-independent implementation concept as the ready-to-use flexible function block that results from the B-BAC generality, discusses how to embed the additional functionalities required in professional industrial control applications and finally presents three implementation examples for three different programming and hardware platforms. The control performance of each B-BAC function block is validated experimentally and compared with the performance of the corresponding platform-related standard PID function blocks. The comparative results and the potential accessibility of both the flexible function block and the simple tuning method put forward B-BAC methodology as a strong alternative for PID-based industrial control applications.

The paper presents comparison between two popular predictive control algorithms DMC and PFC. General description of both algorithms are presented in details for FOPDT (First Order Plus Dead Time) dynamics. Heating process with heat source and heat exchanger was used as an example control plant for testing both algorithms. Design of controllers and tuning procedures are presented. Results of control and performance tests are included as well as conclusion remarks on practical aspects of implementation of the algorithms.