An Intelligent Fault Diagnosis Method for Safety Locking Devices of Amusement Facilities Based on Neural Networks

This paper presents an intelligent fault diagnosis method for safety locking devices of amusement facilities based on neural networks, aimed at ensuring the safety and reliable operation of amusement equipment. Utilizing a neural network model, the system performs real-time monitoring of the safety locking device by collecting vibration data, followed by feature extraction and analysis. To improve the accuracy and timeliness of fault diagnosis, a hybrid feature extraction strategy combining dimensional and multi-dimensional features is proposed. The neural network is trained using multi-dimensional time-domain features to achieve efficient identification and classification of common faults. Experimental results indicate that this method can achieve efficient fault classification while maintaining low energy consumption and computational complexity, providing reliable technical support for the safety management of amusement facilities.