PID control :
One of the control methods of application of PID control is developed early, still widely, it is a method object based on mathematical model, especially for the deterministic control system to establish the precise mathematical model of. But it is difficult to achieve the ideal control effect with the conventional PID controller for nonlinear and time-varying uncertain systems. Moreover, in the actual production, due to the complexity of the parameter setting method, the conventional PID parameters are often poor and poor performance.
Artificial neural network control :
The origin of artificial neural network in 1940s, it reflects the basic characteristics of the brain in some aspects, but is not the real description of human brain, but its simplification and simulation, the network information processing by the interaction between neurons to achieve. Neural network control is the key to select a suitable neural network model, and its training and learning, until it reaches the requirements, that is, to find the optimal neural network structure and weight. However, neural network learning requires a certain experimental sample, which must be obtained from known experience and prior experiments. At the same time, neural network training and learning process, sometimes more complex, need to run thousands of times to get the best structure. Sometimes it is a local optimal solution, but not the global optimal solution, because of the limitations of the method, it is also difficult to achieve effective control of the object to be discussed.
Fuzzy control :
In practical engineering, a very skilled operator, by virtue of their own rich experience in practice, through a variety of phenomena on the scene to obtain a satisfactory control effect. If the measures taken by experience are transformed into the corresponding control rules, and the development of a controller to replace these rules can also be achieved for the control of complex industrial processes. Practice has proved that the fuzzy control theory based fuzzy controller (FC) to complete the task.
Fuzzy control is based on fuzzy reasoning and imitating human thinking method, and it is difficult to establish a mathematical model of the object of the implementation of a control. It uses the fuzzy set in the fuzzy mathematics to describe these vague language, and uses the production rule, namely "if the condition is established, the implementation" the statement to realize. The application of fuzzy control technology in China has achieved remarkable results.
Expert control :
Expert control is an important part of intelligent control, it will be in the expert system theory and technology with the theory and method of control theory based on the combination of imitation, expert intelligence in unknown environment, realize the effective control of the system. The core of expert control is the expert system, it has a variety of non structural problems, especially qualitative and heuristic or uncertainty of knowledge and information, through various reasoning process to achieve control target system.
Human simulated intelligent control :
Human simulated intelligent control (HSIC) after 20 years of efforts, has formed a basic theoretical system and a more systematic design methods, and in a large number of practical applications to achieve success. Its main content is to sum up people's control experience, imitate human's control thought and behavior, in order to produce rules to describe its control in the control of the heuristic and intuitive reasoning behavior. Because the basic characteristic of HSIC is to imitate the control behavior of the expert, its control algorithm is the multi mode control, and it is used for each other. This algorithm can perfectly coordinate the control quality of the control system in the control system. For example, robustness and accuracy, rapidity and stability, etc..