关键词: IAWF算法, 图像数据, 煤矿井下, 供水管道, 信号特征, 泄漏定位

Abstract: Due to the presence of a large number of outliers in the pipeline leakage signals collected by sensors, the extracted leakage signal features are inaccurate, resulting in low accuracy in locating pipeline leakage points. To this end, a leak location method for underground water supply pipelines in coal mines based on the IAWF algorithm and image data is proposed. Based on the characteristics of pipeline leakage signals, the IAWF algorithm is used to weight and fuse the collected monitoring values. The support matrix is used to calculate the support of the target sensor supported by other sensors, and the data measured by the sensor with the highest support is used to replace the abnormal values in the dataset. From this, the characteristics of the pipeline leakage signal are extracted, and the salient map of the pipeline image is obtained by introducing image data to determine the range of pipeline leakage. Based on this, the pressure gradient method is used to calculate the distance between the leakage point and the inlet end of the pipeline according to the changes in pipeline pressure and flow rate, in order to determine the location of the leakage point. The experimental results show that using the proposed method to locate the leakage point of the pipeline, the obtained positioning distance is consistent with the actual distance, and the positioning accuracy is high.