Testing Machine Control Based On Neural Network Technology Research

In this thesis, by referring to the information of the state-of-art of the Cement Compression Testing Machine(CCTM) both at home and abroad ,a new means of direct digital control is introduced for the loading rate control of CCTM. One of the most advanced algorithm, neural network (NN), is discussed for the applying feasibility to the hydraulic loading control system.In Chapter 1, the necessity of applying fully automatic control technology in the CCTM is synthetically analyzed and discussed. The advantage of the direct digital control in CCTM is demonstrated. The content and the technical method used in this study is presented at the end of the Chapter.In Chapter 2, the operating principal of the hydraulic loading subsystem's of the TM is briefly introduced and the open-loop mathematical model is built up and study is carried out by means of simulation under the circumstance of MATLAB. The static working points are obtained and lay foundation for the proceeding dynamic simulation.In Chapter 3, base on the nonlinear model, the dynamic characteristics is simulated , by considering in detail the influence of the environmental factors, such as oil modulus, load stiffness etc.In Chapter 4, the control strategy of the PID is summarized. After the introduction of the digital valve, the closed-loop model is simplified by means of linear theory and simulated through the algorithm of incremental PID control.In Chapter 5, the study is concentrated on the experimental study. The shift of the characteristics of CCTM is observed while the coefficients of PID is applied. A group of ideal PID coefficients are acquired for later comparison the results produced by NN method.In Chapter 6, overviews systematically the advancement of neural network adaptive control ,discusses its main model and algorithm ,and also probes into its existing questions, applications and developing trend.In Chapter 7, we describe the frame of BP NN(neural network) and the algorithm of BP NN(neural network) PID control. After applying to the CCTM, we can testify the feasibility by comparing the traditional PID control and normal control without PID.Chapter 8 is the summarization and prospect.