Research And Application Of Fault Diagnosis Of Main Bearing Of Shearer Cutting Section Based On Improved SVM

The shearer is one of the key equipment to realize the safe and efficient production of coal mines.It plays an important role in the production of coal mines.Long-term operation under the harsh environment causes the failure of coal mining machines to occur from time to time.As the key rotating mechanism of the shearer,the main bearing of the cutting section will inevitably have corresponding mechanical failures if it runs under high load for a long time.After the main bearing fails,abnormal vibration will directly affect the normal and stable operation of the shearer,and at the same time reduce the performance of the entire coal mining system to a certain extent.The traditional method of regular maintenance wastes some material and manpower resources.Then,that is very necessary to research the working status of the main bearing of the shearer cutting section,and diagnose whether it has a fault and the severity and type of the fault in time by analyzing the monitored parameters,so as to ensure the reliability and safety of the shearer operation.This research combines signal processing,feature extraction,fault diagnosis and other related theories and technologies to carry out the research on the fault diagnosis method of the main bearing of the shearer cutting part to form a fault diagnosis technology for the main bearing of the shearer cutting part based on vibration signal analysis.Provided theoretical support and technical solutions for the safe operation of the coal mining system in the mine.First,The failure mechanism of shearer and rolling bearing are stated,and according to the special working environment of shearer,the experimental platform of main bearing of shearer cutting part is built,and the multi-type vibration signals of shearer under actual working conditions are collected.A method based on the combination of divergence index and empirical mode decomposition is proposed.The false components appearing after signal decomposition of empirical mode decomposition are eliminated,and the simulation and experimental verification are carried out to extract the corresponding fault features to form feature vectors.Then,a classification method based on improved support vector machine for cutting part bearing failure mode is proposed,and an optimized support vector algorithm based on genetic algorithm and particle swarm optimization is studied.Using Western Reserve University data and experimental data to verify that the number of iteration steps of the fusion algorithm is smaller than that of a single algorithm.The optimization of the kernel parameters and penalty factors of the support vector machine is realized.And it highlights the feasibility and robustness of the proposed method.Finally,the condition monitoring and fault diagnosis application system of main bearing in shearer cutting department is built and applied to Liangshuijing mine of Shenmu group.The software and hardware system for fault diagnosis of main bearing of shearer cutting department are designed,and the operation and debugging of the system are completed.There are 73 figures,10 tables and 140 references in this dissertation.