Research And Development Of Drilling Database System Based On The Neural Network Of Particle Swarm Optimization

Drilling is one of the most complex methods in manufacture. Drilling parameters is susceptible to the machine, tool, material of work piece, processing quality, allowing production time, cost of production and many other factors. If we use conventional methods, it is not only difficult to draw reasonable results, but also may be unable to proceed in new materials, new techniques and new equipment. New methods are needed to rapidly and accurately decide the parameters of a drilling operation in designing the machining technology, among which building drilling tools' database and providing optimized data is one of the effective methods to improve machining efficiency and lower the cutting cost.This paper analyses the characteristics of the back–propagation (BP) neural network and particle swarm optimization (PSO). Since the BP neural network has some shortcomings, such as slow convergent speed and easy convergence to the local minimum points, the paper presents a new method to train the BP neural network with PSO algorithm. This method is applied to drilling database system for choosing drilling parameter. It has certain level of intelligence, and it can improve the computing efficiency of the system and avoid a lot of algorithmic defects of BP.This paper also designs a drilling database system based on the algorithm,whose characteristics are as following: it is able to obtain study samples from experimental data; it is able to decide rapidly and reasonably cutting speed, feed of cutting-tool's tooth, cutting depth with the condition of drilling tool, material of work piece, and the required quality. It can improve the database and decision-making abilities with the feedback of processing information and self-study, so that it makes the decision results more reasonable. Experiments show that the method proposed in this paper can rapidly and accurately decide drilling parameters,save much time in choosing tools, cut down on labors, thus lower the processing cost. Besides, it overcomes the influence of human factor during tool choice, and brings manufacturing quality under finer control.