The Design Of Control System And Research On Fault Diagnosis Of Flexible Ultra-long Stroke Pumping Unit

At present,in the oil exploitation industry,the pumping unit has become the most widely used mechanical oil extraction method.The working environment of the pumping unit is relatively complex and the probability of failure is high,which seriously affects the normal production of the oil field.Therefore,the research on the control system design of flexible ultra-long stroke pumping unit and the fault diagnosis method of pumping unit,the optimization design of the automatic control system of pumping unit and the establishment of a more accurate fault diagnosis model of pumping unit are of great significance to improve the efficiency of oil production.(1)The control system of flexible ultra-long stroke pumping unit is designed,which mainly includes the design of hardware and software in the lower computer system and the design of monitoring and management software in the upper computer.In the hardware design of the lower computer subsystem,the selection of hardware equipment and electrical design are mainly completed.The software design part mainly studies and designs the system program,and gives a detailed program flow chart and some ladder programs.MCGS component is used in the design of host computer monitoring and management software.By setting the main control window,equipment window,user window and database,the system can meet the actual work needs and collect equipment operation data and alarm data.It not only realizes the real-time display of human-computer interaction interface,but also has the functions of data storage and memory.(2)The multi feature fusion method of pumping unit indicator diagram is studied.The basic principles of principal component analysis and linear discriminant analysis are introduced respectively,and the characteristics of the two methods are compared.Due to the better separability of linear discriminant analysis,linear discriminant analysis is determined to be used as the multi feature fusion method of indicator diagram.(3)Using the binarization method and Canny operator to process the indicator diagram,the binarization and edge detection of the indicator diagram image are realized.Using the wavelet moment feature and circularity extraction algorithm,12 wavelet moment features and 1 circularity feature of the indicator diagram are determined.Combined with the linear discriminant method,the wavelet moment feature and circularity feature are fused to reduce the dimension of the indicator diagram feature,make it have better separability.(4)The PSO algorithm is improved by using the shrinkage factor,and the fuzzy kernel clustering algorithm is optimized by using the improved particle swarm optimization algorithm.The IPSO-KFCM indicator diagram fault type diagnosis model based on multi feature fusion is established.The diagnosis effect of the model is verified by using the actual indicator diagram sample data,and compared with other fault diagnosis models.The results show that,the correctness of the fault diagnosis method of IPSO-KFCM is verified by the indicator diagram of the fault type in this thesis.