Development Of Fault Feature Extraction And Monitoring System For Vibrating Screen

Vibrating screen is one of the key equipment in the quarry processing industry.It is often used in the screening and cleaning of materials,which will cause the whole production line to be shut down and the economic loss is huge.Therefore,it is of great academic value and practical engineering significance to study the fault diagnosis method of vibrating screen and to develop the corresponding fault monitoring system of vibrating screen.According to the fault type,the vibration experiment platform of vibrating screen is set up to extract the vibration acceleration signal of the vibrating screen fault.The vibration and acceleration of the vibrating screen are obtained by using the vibration sieve fault,such as the beam fault,the spring fault,the side plate cracking,the bolt fracture and the screen wear.The wavelet coefficients energy,d3 layer wavelet coefficient energy,a3 layer wavelet coefficient energy,skew factor,crest factor,margin index and peak index are extracted by time domain analysis and wavelet transform technique.Construction of Vibrating Screen Fault Feature Vector Based on Characteristic Volume.BP neural network,support vector machine and support vector machine based on principal component analysis(PCA)are used to study the fault identification method of vibrating screen.The results show that the recognition rate of BP neural network algorithm is only 86% and the operation time is 10.12 s,while the support vector machine algorithm has the highest recognition rate of 99.82% and the computation time is only 8.63 s.In order to ensure that the algorithm has good portability in the DSP system,the principal component analysis is used to extract the first two principal elements with the cumulative contribution rate of 94.9%.The contribution rate of each feature quantity in these two principal elements is analyzed,and the contribution rate is the largest The two feature quantities are used to support fault identification of vector machines,which reduces the information redundancy.The support vector machine algorithm based on principal component analysis has the fastest operation speed of 6.21 s,the fault recognition rate is 91.85%,and the vibration can be realized Screening of ScreenFailure Monitoring System.According to the analysis of the characteristic feature of the vibrating screen and the research of the fault recognition algorithm,the hardware part of the vibration screen fault monitoring system is designed.In order to realize the 12-channel synchronous high-speed acquisition,a signal acquisition module based on AD7606 chip is designed.The DSP chip is used as the processor,and the DSP chip is used as the processor.In this paper,the signal acquisition module based on AD7606 chip is designed.Of the microcontroller module to achieve a large number of data fast operation and fault identification algorithm to run.The software part weighs the feasibility and real-time,simplifies the fault recognition algorithm,and sets the fault threshold of the two feature quantities to judge the vibration screen failure.Finally,the prototype of the vibrating screen fault monitoring system is finished and tested.The three types of fault types such as the unbalance of the vibrating screen,the spring stiffness change and the spring height are experimented.The results show that the fault recognition rate is 80%,which is of practical value for the enterprise to prevent the vibration sieve fault.