The Expert System Of Electrical Upsetting Process For Valve Based On Artificial Neural Networks

With the proliferating amount and the improving performance of automobile in recent years, the development of engine orients to aggrandizement, more specifications, varieties, larger quantity, and better quality. There are two mainly kinds of valve forging billet producing techniques in national and international manufactories. One is to screw press after electrical upsetting. The other is hot extrusion process, which have two-position on hot forging press. The first position is to perform billet,and the second is for final forging. The first one is widely used in our country.The electrical upsetting process has a lower cost of equipment, higher precision of the forging billet and better qualities. But due to the variety of parameters during electrical upsetting procedure, some of them are not easy to be stable, and mismatch appears among some related parameters, which will lead the inevitable quality defects and a reduction of rate of finished product during electrical upsetting procedure. Recently most research on electrical upsetting process focus on the qualitative analysis. Albeit these methods adopt numerical simulation and academic deducing, these research is difficult to use in the real production, because there are many factors influence the process, and the models of these methods are set up from hypothesis, which is undependable and unbelievable.Artificial Neural Networks has the merit of appropriately describing the objects, which have black box and none-linear attitude. Therefore, the procedure of certifying electric upsetting parameters is seem as the black box; the factors that influence the parameters are used as inputs; and the parameters are outputs. This model is set up, and enough data samples are used to train ANN in order to describe the procedure. This article adopts combined BP ANN to ascertain parameters gradually and uses suitable data sample to train the net. Not only does this method describe the procedure of process, but also can preview reasonable control parameters.In order to provide practicable system, ANN and expert system are combined to set up valve electric upsetting combined expert system. The process parameters, which are easily deduced by logic, are ascertained by traditional expert system model; other parameters by ANN. This way combined traditional expert system and ANN, and provides the practical commingled system for the whole process.This article adopts Object Oriented Programming technology, and knowledge expression way based on archetype, for the purpose of encapsulating knowledge base and deducing machine. The ANN parts are achieved by MATLAB programming, and are used by MATLAB's engine to dispose and transfer the data. The user's interface is designed by MFC. The ANN expert system proves useful by practice, and gains the reasonable parameters for valve electric upsetting process.