Smart sensorless prediction diagnosis of electric drives

Innovations and Prospects of Development of Mining Machinery and Electrical Engineering

矿业工程;电工学

Kruglova, T.N.^1 ; Glebov, N.A.^1 ; Shoshiashvili, M.E.^1

Platov South Russian State Polytechnic University, Novocherkassk, 132 Prosveshchenia Str., Novocherkassk, Rostov Region

346428, Russia^1

关键词: Artificial intelligent;    Diagnostic methods;    Different speed;    Electrical motors;    Forecasting accuracy;    Fuzzy sub-models;    Learning time;    Technical conditions;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/87/3/032019/pdf
DOI  :  10.1088/1755-1315/87/3/032019

来源: IOP

【 摘 要 】

In this paper, the discuss diagnostic method and prediction of the technical condition of an electrical motor using artificial intelligent method, based on the combination of fuzzy logic and neural networks, are discussed. The fuzzy sub-model determines the degree of development of each fault. The neural network determines the state of the object as a whole and the number of serviceable work periods for motors actuator. The combination of advanced techniques reduces the learning time and increases the forecasting accuracy. The experimental implementation of the method for electric drive diagnosis and associated equipment is carried out at different speeds. As a result, it was found that this method allows troubleshooting the drive at any given speed.