Research On PID Type Controller Based On Fuzzy Neural Network

From the points view from actual industrial use, the applications and design procedures of fuzzy neural network controller are researched in this dissertation. The main content is about the intelligence algorithms and its applications in several fields of modern control science, including artificial neural network, gene algorithms and fuzzy logic and its application in model identification, PID parameters design and controller designed.These fellows are the main research points in this dissertation:1. A survey of PID-type fuzzy neural network controller's devolopments is summarized.2. The method of indentification on delaytime constant of the common industry time delay system and its procedure are researched, delaytime constant indentification based on BP neural network is designed and simulated. The recursive least square algorithm and projection algorithm combined with genen algorithm is argued to indentify the object system parameters. Using the gene algorithms to optimized the parametes of the classic PID controller. Through the procedure, a regular and optimized PID controller is designed out, which is the base of the later fuzzy neural network controller design. 3. Present the introduction about the background of the combination of the fuzzy logic and neural network, and the architecture of the regular fuzzy neural network is detailed. The fuzzy neural network based on RBF network is researched and the PID type controller based on RBF fuzzy neural network is argued and simulated.4. The controller based on the fuzzy CMAC network is deeply studied and the regular fuzzy CMAC is generalized. Based on this generalized fuzzy neural network, the combined control strategy is researched and simulated. Aimed at the strong time varied non-linear systems, a new neural network weight backwards modification method based on modern control stability rule is argued and simulated. Based on the simulations and Industrial application, the control strategy argued in this dissertation has good robustation and be able to against disturb. And the method is concise, and has a good future on modern industry control fields.