The Research Of Neural Network PID Controller Applicated In The Temperature Control Of Roller Kiln

The traditional PID control which based on mathematic model was steady and reliable, and was applied in many fields. However, with the development of technology, the object becomes more and more complex. So, the conditional PID controller will not get ideal control effect for some object which can not be described by accurate mathematic model. And neural network afford new method to solve the problem.Neural network can learn and adopt dynamics of uncertain system, so it has strongly robustness,and can deal with the questions that can not be described by model and rule,andhas been successful in many control of uncertain system. Firstly, this thesis research the neural network and PID and simulates by MATLAB, then verified the feasibility of neural network PID controller using the simulated system.Investigated characteristics and thermal process of the inland ceramic kiln, in this paper, the temperature control system of roller kiln is designed by using USB data acquisition card. USB data acquisition card can be compatible with Visual C++, C++ Builder, Visual Basic, Delphi, etc. function interface. Visual Basic 6.0 is choosed to compile temperature control interface. The results of laboratory and scene testing show that:the entire control program can be a steady run, the electric kiln temperature points was controlled on real-time, the real-time firing curve can better track a given firing curve and the effect of control achieve the desired purpose.