| The micro-casting,forging and milling composite additive manufacturing equipment has the advantage of being able to personally customize complex shaped components.It can greatly reduce the part design cycle and reduce the design cost in the design stage of complex shaped components.The equipment is widely used.The form has been used and has been put on the agenda.In order to meet the needs of equipment owners and equipment renters to view the manufacturing process status of many micro casting forging and milling composite additive manufacturing equipment in real time,the micro casting and forging and milling composite additive manufacturing monitoring system has been studied.The contents are as follows:(1)Designed a micro-casting,forging and milling composite additive manufacturing monitoring system,including a perception layer,an edge layer,and a cloud platform layer,and analyzed the contents of each layer to be studied.(2)The system monitoring objects are selected and the corresponding sensor selection is completed.Because the manufacturing process of the micro-casting,forging and milling composite additive is a process of high heat input,the temperature drift phenomenon will occur in the sensor near the metal cladding layer,which directly affects the abnormal decision of the composite additive manufacturing process.The temperature sensor is used as an example to study the temperature drift compensation method In this paper,the effect of temperature drift compensation between least square method and BP neural network method is compared,and finally the BP neural network method is selected to compensate the temperature drift of the sensor in the sensing layer.(3)Research on the abnormal analysis method of equipment monitoring parameters,focusing on the development of the molten pool defect detection algorithm in the manufacturing process,to detect the porosity and discontinuous defects generated in the molten pool,and to judge whether the microcasting,forging and milling composite additive manufacturing process is from two aspects Abnormal.(4)Developed an edge layer task coordination scheduling algorithm,comprehensively considering the edge server’s computing,network and other resources,offloading the relatively busy edge server’s monitoring data anomaly analysis task and molten pool defect detection task to the relatively idle edge server for processing In order to achieve the purpose of minimizing the task consumption delay and ensure the real-time performance of the monitoring system,the simulation results prove that the algorithm can reduce the task consumption delay.Developed a cloud platform layer software monitoring system,and tested the functions of the cloud platform software monitoring system with the laboratory micro-casting,forging and milling composite additive manufacturing equipment.The results show that the cloud platform software monitoring system meets the requirements.The milling composite additive manufacturing monitoring system can effectively monitor the composite additive manufacturing process. |