https://doi.org/10.1016/j.watres.2022.118973

The role of deep learning in urban water management: A critical review.

Acoustic leak detection approaches for water pipelines

This paper proposes a reliable technique for pipeline leak detection using acoustic emission signals. The acoustic emission signal of a pipeline contains leak-related information. However, the noise in the signal often obscures the leak-related information, making traditional acoustic emission features, such as count and peaks, less effective. To obtain leak-related features, first, acoustic images were obtained from the time series acoustic emission signals using continuous wavelet transform. The acoustic images (AE images) were the wavelet scalograms that represent the time–frequency scales of the acoustic emission signal in the form of an image. The acoustic images carried enough information about the leak, as the leak-related information had a high-energy representation in the scalogram compared to the noise. To extract leak-related discriminant features from the acoustic images, they were provided as input into the convolutional autoencoder and convolutional neural network. The convolutional autoencoder extracts global features, while the convolutional neural network extracts local features. The local features represent changes in the energy at a finer level, whereas the global features are the overall characteristics of the acoustic signal in the acoustic image. The global and local features were merged into a single feature vector. To identify the pipeline leak state, the feature vector was fed into a shallow artificial neural network. The proposed method was validated by utilizing a data set obtained from the industrial pipeline testbed. The proposed algorithm yielded a high classification accuracy in detecting leaks under different leak sizes and fluid pressures.

/pdf/a-method-for-pipeline-leak-detection-based-on-acoustic-j7x8lesc.pdf

A Method for Pipeline Leak Detection Based on Acoustic Imaging and Deep Learning

Non-surfacing leaks constitute the dominant source of water losses for utilities worldwide. This paper presents advanced data-driven analysis methods for leak monitoring using commercial field-deployable semi-permanent vibro-acoustic sensors, evaluated on live data collected from extensive multi-sensor deployments across a sprawling metropolitan city. This necessarily includes a wide variety of pipeline sizes, materials and surrounding soils, as well as leak sources and rates brought about by external factors. The novel proposition for structural pipe health monitoring shows that excellent leak/no-leak classification results (>94% accuracy) can be observed using Convolutional Neural Networks (CNNs) trained with Short-Time Fourier Transforms (STFTs) of the raw audio files. Most notably, it is shown how this can be achieved irrespective of the sensor used, with four models from different manufactures being part of the investigation, and over time across extended densely populated areas.

/pdf/vibro-acoustic-distributed-sensing-for-large-scale-data-16wi78hy.pdf

Vibro-Acoustic Distributed Sensing for Large-Scale Data-Driven Leak Detection on Urban Distribution Mains

Water loss in distribution networks known as Non-Revenue Water (NRW) is one of the major challenges facing water utilities. In a densely populated city, the acoustic listening method manually conducted by waterworks operators during routine leak pinpointing tasks is vital for NRW reduction. However, this method is considered to be typically labor-intensive, skill-dependent, non-systematic, and sometimes imprecise due to fatigue and inexperience of newly trained staff. This paper presents the development of an AI-based water leak detection system with cloud information management. The system can systematically collect and manage leakage sounds and generate a model used by a mobile application to provide operators with guidance for pinpointing leaking pipes. A leakage sound collection and management system was designed and implemented. Leakage sound datasets were collected from some multiple areas of the Metropolitan Waterworks Authority. Machine learning algorithms including Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Support Vector Machine (SVM), were developed and compared. The results show that the DNN performed better than SVM and as well as CNN, but with less complex structure. DNN was then selected to generate a model used in field trials for pinpointing leakage by novice operators. The field trial results show that the accuracy of the system is above 90% and the results were similar to those conducted by experts. 

AI-based acoustic leak detection in water distribution systems

\n The main purpose of this study was to investigate whether machine learning can be used to detect leak sounds in the field. A method for detecting water leaks was developed using a convolutional neural network (CNN), after taking recurrence plots and visualising the time series as input data. In collaboration with a pipeline restoration company, 20 acoustic datasets of leak sounds were recorded by sensors at 10 leak sites. The detection ability of the constructed CNN model was tested using the hold-out method for the 20 cases: 19 showed more than 70% accuracy, of which 15 showed more than 80%.

T. Kunizane

Papers

Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method