A new method of early fault diagnosis based on machine learning

A new method of early fault diagnosis for manufacturing system based on machine learning is presented. It is necessary for manufacturing enterprises to detect the states of production process in real time, in order to rind the early faults in machines, so that the losses of production failure and investments of facility maintenance can be minimized. This paper proposes a new fault diagnosis model, which extracts multi-dimension features from the detected signal to supervise the different features of the signal simultaneously. Based on the model, the method of inductive learning is adopted to obtain the statistical boundary vectors of the signal automatically, and then a normal feature space is built, according to which an abnormal signal can be detected, and consequently the faults in a complicated system can be found easily. Furthermore, under the condition of without existing fault samples, the precise results of fault diagnosis can also be achieved in real time. The theoretical analysis and simulation example demonstrate the effectiveness of the method.