Research On The Fault Tolerant Control And Remote Monitoring System Of The Transport Mechanism Of The Baler

The continuous operation baler developed by China is a wheat straw collection equipment that can realize continuous operation without stopping.Its conveying mechanism is the key component of the baler to realize continuous baling operation.Due to the lack of research experience in the field of strapping machines,the conveyor mechanism of the strapping machine is prone to failures such as blockage of the storage bin and wear of parts because of the influence of the structural design and the working environment,and its reliability is poor.Once the equipment fails,the traditional method of fault diagnosis based on manual experience is inefficient,and it is easy to ignore the fundamental factors of equipment failure,and it is impossible to make early warning and prediction in the early stage of the failure.Sudden fault may cause the baler to shut down,which would lead to farm time delays and economic losses.In response to the above problems,the monitoring,prediction and diagnosis of the operating status and faults of the strapping machine’s conveying mechanism are proposed to improve the reliability of the equipment,and the occurrence of frequent failures is prevented through active measures to ensure the normal operation of the strapping machine.The fault tolerant control and monitoring and diagnosis system is studied.The adaptive control algorithm is used to realize the active fault tolerance of the fault such as blocking.A remote state monitoring system is developed to monitor the state of the machine’s conveying mechanism,prediction and fault diagnosis.The main contents are as follows:1.The whole structure and working principle of the continuous operation strapping machine are studied,and the terminal of the remote monitoring system of the strapping machine is built and designed to realize the functions of data collection,fault-tolerant control and communication with the server.The remote monitoring interface is designed which has built-in functions such as equipment parameter management,status data monitoring and fault diagnosis.2.The theory and method of fault diagnosis for electromechanical equipment are researched.The rough set theory is used to realize the selection of fault characteristic parameters.The genetic algorithm is used as the theory of attribute reduction in rough set.And it has been further improved to achieve a higher convergence speed.This method is applied to the transmission mechanism gearbox fault diagnosis,and the advantages of the improved genetic algorithm are verified by comparison.The experimental results prove that the method can effectively realize fault diagnosis with a accuracy rate of 100%,and the convergence speed is effectively improved.3.The prediction and fitting method of the time series information of the strapping machine is studied.Variational modal decomposition(VMD)is used to improve the fitting accuracy of the support vector regression model,and the mirror continuation windowing algorithm is used to eliminate the influence of the end effect.The decomposition forecast model(DFM)is proposed to predict the trend signal of the working condition of the strapping machine.The comparison experiment of the vibration signal of the strapping machine was carried out.Its results show that the mean square error of the prediction results of the DFM model is 9.703,and the MSE values of the traditional prediction model are 24.6249 and 141.4%,which is an overall increase of 65%.The algorithm realizes the accurate prediction of the state trend change.4.The application of adaptive dynamic control in the active fault tolerance of the strapping machine is researched.The RQN algorithm based on the parallel network structure is proposed on the basis of deep learning.Simultaneous evaluation and training are carried out through two sets of neural networks to improve the timeliness of the algorithm.Simulation analysis verifies the feasibility and effectiveness of the algorithm.The results show that the blockage rate of the conveyor mechanism of the strapping machine based on the RQN algorithm has dropped from 84% to 1%,and the early failures have been reduced from 50% to 0,and the late failures have been 58%.The failures are mainly concentrated in the middle and late stages.It also proves that the RQN algorithm can effectively realize the self-adaptive control of the conveyor mechanism of the strapping machine and solve the problems such as blockage of the storage bin.