Research of fuzzy neural network PID in hoist constant deceleration system

For mine hoist constant deceleration system in existing problems, such as large overshoot, control accuracy is not high, the response time is not ideal, this paper presents a hoist fuzzy PID control with constant deceleration fused BP neural network control method.The method takes hoist deceleration error and deceleration error change rate as input, takes PID parameter changes ΔKp, ΔKi, ΔKd as network output, and uses the constructed neural network topology layer structure and pre-prepared training set data, iteratively optimize the weights and thresholds of the membership function and fuzzy rules to improve the trimming accuracy of the PID value of the hoist constant deceleration system, so as to obtain a trained offline assignment table reflecting the relationship between input and output, and then write the table into the PLC's global data block and store it in a two-dimensional array, and finally get the best PID three parameter values through the program call, so as to realize the real-time and accurate control of the constant deceleration, and in MATLAB perform simulation and compare with other algorithms.The results show that under the fuzzy neural network PID control strategy, the response is faster and the overshoot is more in line with industry requirements.