论文部分内容阅读
针对压力容器声发射检测的实际情况 ,选择 5个主要的声发射信号特征参量为研究对象 ,利用人工神经网络 (ANN)信号处理技术 ,对声发射信号进行有效性识别的理论和实验研究 .数据处理结果表明 ,采用改进的多层前向误差反传网络算法和编制的程序 ,可以显著提高声发射检测数据中有效信号的处理速度和识别率 .对声发射实验数据进行有效性分析 ,共得有效数据个数为 14 5 4个 ,近似误判率为 0 .8%
According to the actual situation of AE detection in pressure vessel, five major AE parameters are selected as the research object, and the theoretical and experimental studies on the effectiveness of AE signals are carried out by using artificial neural network (ANN) signal processing technology. The processing results show that the improved multi-layer forward error backpropagation network algorithm and programmed can significantly improve the processing speed and recognition rate of the effective signal in the acoustic emission detection data.Analysis of the effectiveness of acoustic emission experimental data, a total of The number of valid data is 14 5 4, the approximate false positive rate is 0.8%