Study On Fault Diagnosis Of Rotating Machinery Based On Data Mining Technology

Rotating machinery can exist in all sorts of equipment, its importance is self-evident. In today’s society, computer application in various enterprises in the production of more and more widely, a high degree of automation of this for various enterprises at present complex operation data record processing equipment has the very big help. But the more complex the equipment and high-end, its data the more big. The data mining technology is applied to the equipment of computer remote fault diagnosis, will improve the previous traditional diagnosis method of hysteresis, high cost and unpredictable situation. Data mining technology has the function of data analysis and processing, it has the advantage of the intelligent diagnosis widely promotion and application in various industries.In this paper, we apply the discernibility matrix algorithm in data mining, this method belongs to the rough set theory. This algorithm, the purpose is to want to get a simple knowledge, knowledge is contracted disjunctive normal form for each of the conjunction, disjunctive normal form from conjunctive normal form, and conjunctive normal form of the structure of the discernibility function derived from the building of discernibility matrix. Then use the decision tree algorithm to classify the data. That combine the two methods can eliminate the irrelevant data of the data set the training sample, and simplifies the calculation, saves the computation time, improve the diagnostic efficiency.Application of discernibility matrix of rough set attribute reduction algorithm, after the attributes reduction can eliminate the noise in the data and redundant item, and then classified by decision tree C4.5 algorithm operation. Can improve the running speed, and also avoid the decision tree subtree repeat and repeat, selection of generation rule properties. For the future offered faster progress in the direction of the choice.