Optimization of blade length control based on least squares support vector regression

The length of the dicing blade affects its performance, while the blade exposure is the key process to control the dicing blade’s length. In the continuous production, the dicing blade’s exposure fluctuates due to the corrosion of multiple blades at one time. To solve this problem, the extreme differences of the sub-set dicing blade’s length were taken as response, with solution temperature, solution concentration and workpiece rotation speed as influence factors. An orthogonal experimental design method was selected to get the test points and then a sample set. Then the least square support vector regression method was used to build a model. Finally, a particle swarm optimization algorithm was used to optimize the model and obtain the optimized process parameters. The experimental results show that this method is effective to reduce the dicing blade’s exposure fluctuation.The difference between the experimental results and the modeling results is only 2.1 μm.