Fault Prediction in Elevator Door System Using Motor Motion Control Information

The door system is an important part of an elevator, and faults within this system can affect the overall operation of the elevator and potentially cause harm to passengers. Therefore, fault prediction is an invaluable tool for accident prevention. This paper aims to develop a practical and effective method for detecting and recognizing early signs of impending faults in the elevator door system. The proposed method is based on motor motion control information, from which relevant feature variables are extracted using statistical analysis and spatial path similarity analysis techniques. The prediction of early fault symptoms in the elevator door system is performed using the Adaptive Neuro Fuzzy Inference System (ANFIS). The proposed method is validated using real data obtain from an experimental test bench, and its performance is compared with other methods on same datasets. The results show the superiority of the ANFIS classifier.