Detection and classification of bearing faults in industrial geared motors using temporal features and adaptive neuro-fuzzy inference system

Abstract

This paper concerns the automatic diagnosis of ball bearing defects in industrial geared motor based on statistical indicators and the Adaptive Neuro-Fuzzy Inference System (ANFIS). The approach consists of three essential steps: the first is the extraction of statistical indicators from the root mean square (RMS) of the raw vibration signals measured experimentally for different states of the bearing (healthy and in the presence of defects). The second step consists of the selection of the more relevant indicators, and finally the introduction of these indicators to the ANFIS network in order to classify the various defects in the bearing (inner and outer race faults, and combined fault). A test campaign was conducted on an industrial installation (Wheeled Conveyor) to collect data as the RMS trend of the raw vibrations using adequate instrumentation in order to verify the validity of the method in real test conditions. The obtained results show that the proposed approach can reliably detect and classify various faults at different speeds of rotation of the electric motor. The effectiveness of the proposed method was also approved by using additional test data.

Empowering Predictive Maintenance: A Hybrid Method to Diagnose Abnormal Situations

“…ANFIS have been applied in many recent works to FDI, e.g., [14][15][16]. All of them are in an ad-hoc approach since such works have used ANFIS straightforwardly to analyze system output data.…”

Equipo para la verificación de conexiones soldadas de tuberías recubiertas internamente

“…Finalmente, en la Tabla 2, también se calcularon los preescaladores del procesador del microcontrolador y tiempos parciales para la medición de cada frecuencia y el tiempo total de muestreo que corresponde a 7.86 minutos para un punto de inspección, lo que indica que para un muestreo completo de los cuatro (4) puntos a inspeccionar el equipo tardara 31.45 minutos, a este valor debe sumarse los dos (2) minutos que tarda el equipo en llegar al punto de interés que es la junta de soldadura donde se encuentra el sleeve, recorrido lineal de 12 metros [19][20].…”

Deep Learning Approach for Vibration Signals Applications

“…For signals analysis, methods of frequency spectra can also be used for prediction or diagnosis [ 15 , 16 ]. The statistical features are usually utilized to be inputs of machine learning for diagnosis model development [ 17 , 18 , 19 ]. Herein, the convolutional neural network (CNN) discussed in this paper is also widely applied for bearing diagnosis using raw signals or spectra of signals [ 20 , 21 , 22 , 23 , 24 , 25 , 26 ].…”