Analysis of fault diagnosis of DC motors by power consumption pattern recognition

Early detection of faults in DC motors extends their life and lowers power usage. There are a variety traditional soft computing techniques for detecting motors. Many diagnostic have been developed the past to detect such fault-related patterns. These methods aforementioned potential failures can be utilized scientific technological domains. Motor Power Pattern Analysis (MPPA) is technology that analyzes current voltage provided an electric motor using particular patterns protocols assess operational status without disrupting production. Engineers researchers, particularly industries, face difficult challenge monitoring spinning types equipment. In this work, we going explain how use pattern/signature analysis signal driving servo find mechanical defects gear train. A hardware setup used simplify demonstration obtaining spectral metrics from consumption signals. motor, set metal or nylon drive gears, control circuit employed. The speed was eliminated allow direct motor's profiles. Infrared (IR) photo-interrupters with 35 mm diameter, eight-holed, standard wheel were employed gather tachometer at servo's output. mean value measurements 318 V healthy profile, while it 330 faulty gears data. proposed profile approach succeeds recognize gear-box servomotor via examining level pattern as well extraction Spectral Density (PSD) through comparing profiles