Multi-sensor data collaborative sensing algorithm for aluminum alloy TIG welding pool state

Aiming at the non-linear correspondence between the real-time state of welding process parameters and the three-dimensional size of the weld pool in the tungsten inert gas arc (TIG) welding process of aluminum alloy, a multi-sensor TIG welding process based on cyber-physical fusion is studied to establish a multi-sensor TIG welding process collaborative sensing calculation method. First, build a TIG welding process molten pool state information physical fusion system architecture consisting of infrared temperature sensors, arc shape sensors, arc energy sensors and welding position sensors. Then, considering the influence of the environment and measurement noise in the welding process, a three-dimensional parameter state sensing strategy of the length, width and depth of the molten pool based on the exchange of temperature, position, and energy sensor information is designed. Based on the asynchronous and heterogeneous characteristics of multi-sensor data, a new method based on Multi-sensor data collaborative sensing algorithm for the state of the molten pool in the welding process based on trace Kalman filtering. Finally, taking the TIG welding process of 7075 super-hard aluminum alloy as the test object, the test results show that the proposed algorithm can calculate the welding pool parameter results in real time according to the motion characteristics of the welding torch and the arc in the welding seam of the TIG welding process. The error of the calculation results of the weld width and weld height can be controlled within 10%, and the response time of the algorithm is within 0.3 s, which can accurately evaluate the real-time state of the weld pool.