Applications of Intelligent Control

Accurate mathematical models of real systems are generally unavailable due to complexity, nonlinearity, time-varying, uncertainty and incompleteness.

The application of traditional control theory for control must make and follow some relatively harsh linearization assumptions, which often do not match the actual situation in applications.

For some complex and uncertainty-ridden control processes, it is simply not possible to represent them with traditional mathematical models, i.e., the modeling problem cannot be solved.

In order to improve the control performance, the traditional control system may become very complex, which increases the investment in equipment and reduces the reliability of the system. 1.Intelligent control in industrial processes

Intelligent control of production processes consists of two main aspects: local level and global level. Intelligent control at the local level refers to the introduction of intelligence into a unit of the process for controller design, such as intelligent PID controllers, expert controllers, neuron network controllers and so on. The research hotspot is the intelligent PID controller, because it has obvious advantages in parameter calibration and online adaptive adjustment, and it can be used to control some nonlinear complex objects. Global-level intelligent control is mainly aimed at the automation of the entire production process, including the control of the entire operating process, process fault diagnosis, planning process operation to deal with abnormalities.

2. Intelligent control in machine manufacturing

In modern advanced manufacturing systems, which need to rely on data that are not complete and precise enough to solve difficult or unpredictable situations, artificial intelligence technology provides an effective solution to this challenge. Intelligent control has subsequently been widely used in the machinery manufacturing industry, which utilizes fuzzy mathematics and neural network methods to model the dynamic environment of the manufacturing process, and sensor fusion technology to pre-process and synthesize information. The "Then-If" inverse reasoning of the expert system can be used as a feedback mechanism to modify the control mechanism or select a better control mode and parameters. Utilizing the robustness of fuzzy sets and fuzzy relationships, the fuzzy information is integrated into the outer-loop decision selection mechanism of the closed-loop control to select the control action. Utilizing the learning function of neural networks and the ability to process information in parallel, on-line pattern recognition is carried out to deal with information that may be crippled.

3. Intelligent control in the research field of power electronics

The design, production, operation, and control of electrical and electronic equipment such as generators, transformers, and motors in the electric power system is a complex process, and electrical workers at home and abroad have introduced artificial intelligence technology into the optimal design, fault diagnosis, and control of electrical equipment to achieve good control results. Genetic algorithm is an advanced optimization algorithm, the use of this method to optimize the design of electrical equipment, can reduce costs, shorten the calculation time, improve the efficiency and quality of product design. Intelligent control techniques applied to fault diagnosis of electrical equipment are: fuzzy logic, expert systems and neural networks. In the many application fields of power electronics, the application of intelligent control in current control PWM technology is one of the representative directions of technology application and one of the new hot spots of research.