In the Radio Frequency IDentification (RFID) real-time defect detection task in industrial scenes, the deep learning target detection algorithms such as You Only Look Once (YOLO) are often adopted in order to ensure the detection precision and speed. However, these algorithms are still difficult to meet the speed requirement of industrial detection, and the corresponding network models cannot be deployed on resource-constrained devices. To solve these problems, the YOLO model must be pruned and compressed. A new network pruning method of the weighted fusion of feature information richness and feature information diversity based on rank information was proposed. Firstly, the unpruned model was loaded and reasoned, and the rank information of the corresponding feature maps of the filters was obtained in forward propagation to measure the feature information richness. Secondly, according to the different pruning rates, the rank information was clustered or the similarity of the rank information was calculated to measure the feature information diversity. Finally, the importance degrees of the corresponding filters were obtained after the weighted fusion and were sorted, and the filters with low importance were cut off. Experimental results show that, for YOLOv4, when the pruning rate is 28.87% and the weight of feature information richness is 0.75, the proposed method has the mean Average Precision (mAP) improved by 2.6% - 8.9% compared with the method that uses rank information of the feature maps alone, and the model pruned by the proposed method even has the mAP increased by 0.4% and the model parameters reduced by 35.0% compared with the unpruned model, indicating that the proposed method is conducive to the model deployment.
To solve the problem of feature extraction and state prediction of intermittent non-stationary time series in the industrial field, a new prediction approach based on Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA) and Support Vector Machine (SVM) was proposed in this paper. Firstly, the intermittent non-stationary time series was analyzed by multiple time scales and decomposed into a couple of IMF components which possessed the different scales by the EEMD algorithm. Then, the noise energy was estimated to determine the cumulative contribution rate adaptively on the basis of 3-sigma principle. The feature dimension and redundancy were reduced and the noise in IMF was removed by using PCA algorithm. Finally, on the basis of the determining of SVM key parameters, the principal components were regarded as input variables to predict future. Instance's testing results show that Mean Average Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE) and Mean Squared Percentage Error (MSPE) were 514.774, 78.216, 12.03% and 1.862%, respectively. It is concluded that the SVM prediction of the time series of output power of wind farm possesses a higher accuracy than not using PCA because the frequency mixing phenomena was inhibited, the non-stationary was reduced and the noise was further eliminated by EEMD algorithm and PCA algorithm.