Abstract
The optimization of deburring process with fluid-impact to automobile main cylinder cross hole is studied in this paper to achieve higher processing quality and processing efficiency, so as to enable a system to automatically adapt to the change of processing state and not affect the processing quality due to the change of processing status. The improved fuzzy RBF expert system is used to optimize the processing parameters intelligently. Training and reasoning are done with fuzzy RBF neural network and double object optimization is done with particle swarm optimization based on flow dispersion and processing efficiency. A method of orthogonal combination is proposed in the number of hidden bodes in inference layer of fuzzy RBF neural network and their combination modes. Compared with the method of forming hidden nodes by combining the whole fuzzy layer, this method greatly reduces the amount of calculation and has obvious effect in solving complex problems. Experiment has been done on different processing programs, which shows that the processing quality has been greatly improved with the optimized process, the processing quality is obviously higher than that in the national standard, and the process level has been further improved.
Keywords
Get full access to this article
View all access options for this article.