Multidimensional information fusion and broad learning system-based condition recognition for energy pipeline safety

Abstract

Mechanical activities near energy pipelines pose a significant threat to energy transportation safety and energy system supply. The distributed acoustic sensing (DAS) system, which is an emerging intelligent sensing technology, can help to identify threat activities outside the pipeline. However, existing research has not distinguished fine-grained threat conditions because of insufficient information utilization and real-time requirements in the DAS system dataset, resulting in a large number of false alarms and time-consuming training in practice. To address these issues, this study proposes a pipeline radial threat condition recognition model based on multidimensional information fusion and a broad learning system (MIFBLS). First, the signal is preprocessed to improve the signal-to-noise ratio and generate the original features. Then, the extracted multidimensional temporal features are dimensionally reduced through information entropy, and the time-frequency map is fused and extracted based on a pretrained deep module, thereby achieving information fusion. Finally, the BLS incremental learning strategy is adopted to enhance the updating ability of the model and reduce the burden of data increments on the model training. Comparative experiments on a real-world natural gas pipeline dataset demonstrate the effectiveness and efficiency of the proposed method, indicating the potential for real-time monitoring and intelligent identification in pipeline transportation scenarios.