Method, apparatus, computer device and storage medium for detecting operating state of apparatus

The invention relates to a method and a device for detecting the operating state of an apparatus. The method comprises the following steps: detecting the current data of a measuring point of the running state of the equipment, and converting the current data into a first trend diagram; inputting a first trend map into a neural network model, and obtaining a second trend map from which the neural network model reconstructs and outputs the first trend map; calculating a reconstruction deviation between the second trend map and the first trend map; according to the reconstruction deviation, sincethe neural network model is based on the normal data of the equipment, being able to learn characteristics such as trend distribution of normal data. The reconstruction deviation between the first trend graph of current data input and the second trend graph of neural network model reconstruction can accurately reflect whether the equipment is in abnormal operation state, thereby improving the accuracy and comprehensivene