Research On Wiped Film Evaporator Modeling And Motor Chaos Control Technology

The wiped-film molecular distiller introduces a scraper,which makes the flow on the surface of the evaporator extremely complicated,and it is difficult to establish a corresponding model.In order to solve the problems that the process parameters of wiped film molecular distillation are difficult to accurately measure in real time and the measurement time is too long,soft measurement technology is used to establish a prediction model for the evaporation process of wiped film molecular distillation.Soft measurement technology does not need to establish a complex mathematical model.It only needs to use different mathematical calculations or estimation methods on the basis of previous experience knowledge to find the mathematical relationship between the auxiliary variable and the target variable,and estimate the data that is not easily available.prediction.First,based on the analysis of the factors affecting the molecular distillation process parameters,the feed rate,system temperature,vacuum degree,and wiper motor speed are selected as auxiliary variables,and guidelines and normalization are used to preprocess the data,and then use BP Neural network and Support Vector Regression have established a soft-sensing model for wiped film evaporation process data.After simulation analysis,it is found that these two data-driven methods have the disadvantages of weak global convergence,poor stability,and easy to fall into local optimum.Therefore,the established model needs to be improved and optimized.Secondly,in view of the problems of BPNN and SVR two soft sensing models,a soft sensing method of wiped film evaporation process based on the combination of Improved Grey Wolf Optimizer and support vector regression is proposed.Use the improved Opposition Based Learning strategy to optimize the Grey Wolf Optimizer,and then use the optimized Grey Wolf algorithm to optimize the model parameters of the support vector machine,and finally pass IGWO-SVR soft measurement model realizes accurate prediction of process parameters of wiped film evaporation process.In order to verify the effectiveness of this method,the prediction results obtained by this method are compared with the prediction results of GWO-SVR,PSO-SVR,SVR and BPNN.The results show that the prediction performance of the soft sensor model based on IGWO-SVR is better than others.The model proves that the method has strong superiority in the process of predicting the process parameters of the wiped film evaporation process.Finally,the performance of the wiped film motor in the wiped film molecular distillation device is of great significance to the optimization of molecular distillation process parameters.The delay estimation control method is used to control the stability of the Brushless DC Motor.The parameter uncertainty and external interference are regarded as the total disturbance of the system,and the delay estimation controller is designed to perform the error expectation.Compensation to effectively suppress the chaotic behavior of the BLDCM drive system;then use delayed feedback to control the chaos of the BLDCM,so that the BLDCM enters the chaotic state from the stable state and the limit cycle state,and the system simulation is designed based on the current converter(CCCⅡ)Circuit,and synchronous simulation circuit.