Scientific

The test set data is input into LSTM model to verify the effectiveness of model early warning. The prediction results

Randomly select 25% of the training set data as the verification set, set the model loss value as Mae, and

The LSTM model is trained by selecting the normal operation data of the unit. When the gearbox bearing is in

A new kurtosis spectral entropy index is proposed, which consists of kurtosis value and envelope spectral entropy. When there are

Particle swarm optimization algorithm has good global optimization ability. Suppose there are m particles in the d-dimensional space, which form

According to the working principle of Sanc, the separation effect of adaptive filter mainly depends on the selection of delay

After the candidate region is generated, the ROI pooling layer is used to further extract the features of the candidate

In order to generate accurate candidate regions, 512 feature maps are used as input of RPN (region proposal networks) and

The deep learning algorithm is introduced into the field of Ferrography Image recognition. The wear status of gearbox is evaluated

During the operation of the equipment, when abnormal friction occurs on the relative moving metal surface, wear particles will be

Five models are used to test the model fault on the validation data set. The validation data set has 5000

Sanc obtains the reference signal by delaying the original signal, extracts the periodic signal component by autocorrelation analysis, and finally