基于深度学习的天然气管道气体压力超声检测模式识别方法

针对天然气管道气体压力超声检测模式识别问题,提出了对原始信号进行预处理去除冗余信息,然后对信号进行变分模态分解(variational modal decomposition,VMD)提取最优本征模态函数(intrinsic model functin,IMF)对信号进行重构,接着对处理好的信号进行连续小波变换(con...

Ultrasonic detection pattern recognition method for natural gaspipeline gas pressure based on deep learning

In order to solve the problem of pattern recognition of gas pressure detection in natural gas pipeline, the original signal ispreprocessed to remove redundant information, and then the signal is decomposed by variational mode decomposition to extract theoptimal Intrinsic mode function and reconstruct the signal. Then, the processed signal is transformed into a high-resolution twodimensional image in time and frequency domain by continuous wavelet transform. Finally, the image is extracted by deep convolutionneural network, and the output of part of the network is connected with support vector machine to realize supervised learning andtraining. The trained support vector machine is used for unsupervised pattern recognition of the remaining data. Experiments show thatthe accuracy of vmd-cnn-svm is 90. 66%, which is the highest compared with other methods.