Research On Key Technology Of Quality Control Of Pulse Assembly Process For Marine Diesel Engine

With the development of artificial intelligence technology and the further implementation of “made in China 2025” strategy,digitization,informatization and intelligence are the future development direction of China’s manufacturing industry.As the key component of ship power system,the assembly quality of marine diesel engine directly affects the performance of ship.However,due to the complex assembly process of marine diesel engine,its quality influence factors are numerous,and the utilization rate of data analysis is low,which leads to the lack of prior and in-process control basis in the assembly process,which limits the improvement of the overall manufacturing quality of diesel engine.In order to solve the problem of quality control of marine diesel engine assembly process,this research constructs a system framework to meet the quality control of marine diesel engine assembly process based on the overall analysis of enterprise requirements,assembly characteristics and system function requirements.Finally,the system software is developed for the key technologies of this study.The specific research work of this thesis is as follows:1.According to the structure characteristics of marine diesel engine,combined with the assembly line layout and process characteristics,the thesis proposes the overall scheme of the assembly process quality control system for marine diesel engine according to the quality control requirements of the assembly process,and elaborates the function and data base design of the assembly process quality control system of marine diesel engine.2.According to the assembly quality characteristics of marine diesel engine and its influencing factors,aiming at the problem of low success rate of one-time assembly in the assembly process,a multi process assembly quality prediction method based on prediction model is proposed to realize the assembly quality prediction of marine diesel engine in advance.Aiming at the problems of high dimension and different influence degree of quality characteristics influencing factors,grey correlation and principal component analysis are used to extract the key assembly parameters,so as to achieve the purpose of dimension reduction and improve the prediction accuracy of the model.An assembly quality prediction model based on PSO-SVM is constructed to realize the assembly quality prediction in advance.3.According to the type of process quality control chart in product assembly process,Monte Carlo method is used to generate control chart data for the difficulty of using actual production data.Aiming at the problem of abnormal diagnosis in marine diesel engine assembly process,combined with feature extraction technology,a control chart pattern recognition method based on 1d-cnn is proposed.In order to obtain higher recognition rate,the network structure parameters are optimized The results show that this method has better performance and higher recognition accuracy.4.Based on the above system functional requirements and key technology research,the development framework of marine diesel engine assembly process quality control system is constructed,and the assembly process quality control system is developed.The system module workflow is introduced,the system operation process is demonstrated,and the process quality prediction and control chart pattern recognition are realized.