Method and system for detecting a structural anomaly in a pipeline network

A method for detecting a structural anomaly in a pipeline supply network, the pipeline supply network configured to supply fluid to multiple receiving locations, comprising:

• receiving acoustic signal data from a selected location in the pipeline supply network;
• generating a first time window of acoustic signal data based on the acoustic signal data;
• benchmarking the first time window of acoustic signal data with respect to historical background acoustic signal data characterising the pipeline supply network to generate a corresponding background benchmarked first time window of acoustic signal data, wherein benchmarking the first time window of acoustic signal data with respect to historical background acoustic signal data characterising the pipeline supply network includes:
• determining an estimated spectral content difference between the first time window of acoustic signal data and the historical background acoustic signal data, wherein determining the estimated spectral content difference between the first time window and the background acoustic signal data includes:
• determining the spectral content of the historical background acoustic signal data;
• determining the spectral content of the first time window of acoustic signal data;
• and
• determining in frequency space the difference between the spectral content of the background acoustic signal data and the spectral content of the first time window of acoustic signal data;
• and
• removing the spectral content difference from the first time window of acoustic signal data to generate the corresponding background benchmarked first time window of acoustic signal data;
• and
• determining an anomaly measure for the background benchmarked first time window of acoustic signal data, wherein the anomaly measure indicates a presence of the structural anomaly, wherein on determining the presence of the structural anomaly in the background benchmarked first time window of acoustic signal data then:
• generating a subsequent second time window of acoustic signal data;
• benchmarking the subsequent second time window of acoustic signal data with respect to the first time window of acoustic signal data to generate a corresponding comparison benchmarked second time window of acoustic signal data;
• determining the anomaly measure for the comparison benchmarked second time window of acoustic signal data;
• and
• characterising the structural anomaly by comparing the anomaly measure determined for the background benchmarked first time window of acoustic signal data with the anomaly measure determined for the comparison benchmarked second time window of acoustic signal data, wherein characterising the structural anomaly includes determining whether the structural anomaly is increasing, reducing or remains unchanged for a time period between the first and second time windows.