Elevator Error Diagnosis Method Based on Neural Network Model

With the continuous acceleration of urbanization, elevators as vertical transportation tools have become an indispensable part of modern cities. However, elevator malfunctions pose a huge threat to the safety of life and property, as well as the normal travel of users This study aims to improve elevator error diagnosis methods using NN models and achieve automatic error diagnosis for elevators. With the increasing demand for safety and reliability in elevator operation, traditional error diagnosis methods can no longer meet practical needs. The elevator error diagnosis method based on NN models has the advantages of automation and high precision, which has attracted much attention. Firstly, a NN model was used to achieve elevator error diagnosis, and a comparative experiment was conducted with traditional error diagnosis methods. Experiments have shown that the error diagnosis method based on NN models can efficiently and accurately diagnose elevator faults automatically, with very high precision, recall rate, and F1 score. Compared with traditional methods, error diagnosis methods based on NN models have higher efficiency and precision, and can automatically identify fault types based on vibration signals, achieving unmanned error diagnosis. A new method based on NN models has been provided to achieve automatic diagnosis of elevator faults, expanding the methods and ideas of elevator error diagnosis.