Leak Detection in Water Distribution Pipes Based on CNN with Mel Frequency Cepstral Coefficients

Machine Hearing for Industrial Fault Diagnosis

“…Since the 1940s, there have been multiple breakthroughs for ANNs from different disciplines, such as the research of nerve cells by neurobiologists, the study of learning behavior by psychologists, and more recently and more relevantly, by mathematicians, the establishment of mathematical models for the neurons and the neuron learning. Although the present models are nowhere near the realistic modelling of the structure and dynamics of the natural neural networks in the brain, ANNs did find continuously successful applications that other AI methods have never achieved, in performing regression, recognition and prediction tasks based on complex, noisy and/or incomplete data, which also include considerable case studies of industrial fault diagnosis [8,9,11,14,15].…”

“…As known, conventional spectrogram based on STFT bears an inherent fixed resolution drawback, which clearly does not represent the frequency response properties of the basilar membrane. To overcome this issue, mel-frequency cepstrum (MFC) is commonly used in sound processing [11]. Similarly, MFC is a short-term power spectrum, but based on a log power spectrum on a nonlinear mel-scale of frequencymel, as in melodyindicating that the mel-scale is defined through pitch comparisons, as in music.…”

Viability of Pressure-Reducing Valves for Leak Reduction in Water Distribution Systems

“…Leak location is possible through modeling (Adedeji et al 2019;Liu et al 2021), monitoring (Cheng 2021), PRVs in conjunction with SCADA (Güngör et al 2019), and has implications for time and energy savings (Mysorewala 2019). Leaks can also be found using machine-based learning (Cantos et al 2020), using multiple paths algorithm (Hao Png et al 2020), non-destructive techniques (Aslam et al 2018), deep learning convolutional neural networks (Lei et al 2020), monitoring and occupancy data (de Coning and Mouton 2020), multistage optimal valve operations and smart demand metering (Huang et al 2020), a hybrid model-based method (Fereidooni 2021 et al), modeling-based algorithms (Taghlabi et al 2020), computational intelligence (Quiñones-Grueiro et al 2021), a pressure and data-driven classifier approach (Sun et al 2020), acoustics (Stephens et al 2020), IoT (Thenmozhi et al 2021), an integrated bottom-up approach (Yu et al 2021), a CNN with mel frequency cepstral coefficients (Chuang et al 2019), and pressure analysis using a machine learning ensemble (Fuentes and Pedrasa 2019), among others.…”

Acoustic Leak Detection in Water Networks

“…Related approaches of acoustic leak detection are mostly based on cross-correlation (Muggleton and Brennan, 2004;Gao et al, 2017), wavelet transforms (Ni and Iwamoto, 2002;Ting et al, 2019), Support-Vector-Machines (Kang et al, 2017;Cody et al, 2017) or neural networks (Kang et al, 2017;Chuang et al, 2019;Cody et al, 2020). Other methods combine acoustic data with additional sensory measurements (Stoianov et al, 2007).…”