Method and equipment for optimizing model and storage medium

The invention discloses a method and equipment for optimizing a model and a computer readable storage medium. The method comprises the following steps: inputting a time domain version of data marked as normal or abnormal into an anomaly detection model based on a convolutional neural network, and inputting a frequency domain version of the data into a physical model; if the output of the anomaly detection model is the same as the mark of the data and the output of the physical model is different from the mark of the data, adjusting a threshold value of the physical model; and if the output of the anomaly detection model is different from the mark of the data and the output of the physical model is the same as the mark of the data, training the anomaly detection model, the training of the anomaly detection model comprising: adjusting a threshold value of the physical model, and obtaining data of which the mark is inverted relative to the threshold value from the physical model using the adjusted threshold valu