Optimization Of Maintenance Strategy For Vehicle Chip Production Line Based On Multivariate Exponential Weighted Moving Average Control Chart

With the continuous development of science and technology,with the rapid development of automobile electrification and intelligence,the product quality and equipment reliability requirements of on-board chips are getting higher and higher.As an important part of the production system,the quality control of the on-board chip production system and the stability of the on-board chip production equipment have an important influence on its product quality,production cost and production scale.This paper takes the vehicle chip production line as the research object,and uses the control chart as the sensor of the equipment state to monitor the production system,and then analyze the state of the equipment and select the appropriate maintenance strategy.On this basis,a joint economic model is established to reduce equipment maintenance costs and improve the overall performance of the system.First of all,this thesis studies and analyzes the key processes and their characteristics in the automotive chip production line,and uses control charts to conduct statistical process control research on the key processes.Analyze the statistical performance of the univariate quality control chart and the multivariate quality control chart.Since the covariance matrix estimation has a greater impact on the performance of the multivariate quality control chart,based on the three commonly used covariance matrix estimation methods,the parameter combination estimation method is used to minimize the effect of the estimation error and the setting error on the performance of the control chart.And using the key process data of the on-board chip production line to show that when the overall parameters are unknown,the sample data is small,and the offset is small,the parameter combination estimation method has a good performance effect.Then,for the vehicle-mounted chip production repairable system,the abnormality of the equipment can cause the deviation of the process quality characteristics.Use the control chart to monitor the deviation to analyze the state of the equipment,and then establish a variable sampling multivariate exponential weighted moving average control chart Combined with the maintenance strategy,a joint economic model is established to effectively reduce the unit time cost of the system.Monitor the status of the production system by constructing a multivariate exponential weighted moving average control chart,and then combine preventive maintenance to analyze all possible scenarios in the system,and calculate the probability of occurrence in each scenario.On this basis,considering sampling inspection costs,maintenance waiting costs,maintenance costs and downtime costs,etc.,the update process theory is used to establish a joint design model of condition-based maintenance and multivariate exponentially weighted moving average control charts,and finally find the unit of the repairable system Time costs.The simulation method is compared with the calculation results to prove the validity of the model.Finally,considering that in the vehicle chip production line,the sample size of the key processes is small,small fluctuations are prone to occur,and the sample collection cost is high,the establishment of a variable sampling multivariate exponentially weighted moving average control chart is combined with a joint economy for preventive maintenance.The decision-making model is applied to the key processes of the on-board chip production line to monitor small fluctuations in its quality characteristics and determine the abnormal state of the equipment,thereby reducing the overall cost of the system.The genetic algorithm is used to solve the model and optimize its parameters.The comparison with the calculation results of the parameters before optimization shows the superiority of the model.From a cost perspective,it can reduce the cost of the implementation of control charts and maintenance strategies,thereby reducing the overall cost of the system and improving the performance of the production line.