3 results about "Deep cnn" patented technology

The application relates to a model pruning method of an interpretable CNN classification model, belongs to the field of image compression, and solves the problems of high operation complexity, large time and memory consumption and difficulty in deployment on terminal equipment of an existing deep CNN model, and solves the problem of lack of interpretability of an existing model pruning algorithm. The method comprises the following steps: inputting a training picture into a neural network model to be pruned, and extracting a feature map matrix of each convolution layer; upsampling the feature map matrix to the size of the input picture, and then performing a normalization operation to construct a saliency map; multiplying the saliency map and the input picture element by element to construct a weighted input picture; subtracting the input picture from the weighted picture element by element to construct an attention region occlusion map; inputting the attention occlusion map into the model to be pruned, observing the change of model accuracy as an importance score of the channel, and pruning the channel to obtain a pruned lightweight model. The application realizes high pruning rate of the model and improves the interpretability of the pruning process.

The application discloses a pumping unit noise positioning method based on deep learning, and steps are as follows: S1, local seismic trace sets of several fixed sizes are obtained by using sliding window single-step sliding to block seismic data by columns, if the number of seismic traces containing pumping unit noise reaches threshold Th1, it is marked as 1, and if the number of seismic traces containing pumping unit noise is lower than threshold Th2, it is marked as 0; S2, the local seismic trace sets are pretreated, the energy spectrum is calculated, mean filtering is carried out, then down-sampling is carried out, and part of data is randomly selected as a training set, and the remaining part is used as a test set; S3, a deep CNN network is built, and the training set obtained in step S2 is used to train the CNN network, and in the training process, the misclassified data is used to supplement the training set for repeated training; S4, the test sample is used to test the CNN network trained in step S3, and the positioning function is quantitatively evaluated; S5, the width of the positioned pumping unit noise is estimated according to the positioning result in step S4.

A method for intelligent extraction of damage features and construction of health indicators from multi-source data in aircraft structural monitoring is proposed. First, raw monitoring signal data from multiple sources, including acoustic emission waveform stream data and guided wave data, are acquired. A convolutional neural network (CNN) is then constructed to automatically learn deep features from the raw data. Expert knowledge features are extracted from the raw data and fused with the deep features of the CNN. The fused feature vector is then input into a classifier for classification. Next, a feature vector sequence is extracted using sliding window sampling to construct a full-lifecycle feature dataset. A health indicator construction model based on a deep CNN is established, employing a contrastive learning loss function as the optimization objective and iteratively training the model using gradient descent. Finally, the health indicators from the acoustic emission waveform stream data and guided wave data are fused from multiple sources. By utilizing the consistent changes in the data at the time of damage, the damage evolution process is comprehensively judged, and a fused health indicator is output. This invention improves the accuracy and reliability of the health indicators.