A Pipeline Leak Detection and Localization Approach Based on Ensemble TL1DCNN

Zhou, Mengfei; Yang, Yanhui; Xu, Yinze; Hu, Yinchao; Cai, Yijun; Lin, Junjie; Pan, Haitian

doi:10.1109/access.2021.3068292

Cited by 34 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Existing Methods To Identify Inefficienciesmentioning

confidence: 99%

“…Most of these use mass/volume balances, deep learning, or cross-correlation with available data to locate the inefficiencies [15]. Hardware-based methods normally require equipment to locate and identify the inefficiencies [14], [15]. The hardware that is used can be optical fibre, hydrophones, radar systems, and more; however, such equipment can be quite expensive to acquire and/or install.…”

Section: Existing Methods To Identify Inefficienciesmentioning

confidence: 99%

See 1 more Smart Citation

Using Zero-Waste Baselines to Identify Compressed Air System Inefficiencies in Deep-Level Mines

Merwe

Gous

Schutte

2022

SAJIE

View full text Add to dashboard Cite

Inefficient compressed air systems in deep-level mines deteriorate energy performance and increase operational costs. Leaks, wastages, and misuse are common inefficiencies that necessitate an oversupply of compressed air. It is therefore important to identify where the opportunities for improvement are located. Underground mining equipment can be used to develop a zero-waste compressed air demand profile. This profile can then be simulated for the entire operation to determine a theoretical baseline. Noticeable inefficiencies are then identified by comparing the actual data with the zero-waste baselines. The results of this study showed that the surface operations oversupply compressed air by 15% (10 kg/s of air) per day. This requires an additional 80 MWh of electricity (14.5% of the total) and costs approximately R91 000 per day. The comparison with the zero-waste baselines showed that 7.9 kg/s of air is wasted at the underground levels during drilling periods, highlighting the areas that require mitigation projects to improve the performance while decreasing costs and wastages. Keywords zero-waste baseline; compressed air; deep-level mine

show abstract

Section: Existing Methods To Identify Inefficienciesmentioning

confidence: 99%

Section: Existing Methods To Identify Inefficienciesmentioning

confidence: 99%

Using Zero-Waste Baselines to Identify Compressed Air System Inefficiencies in Deep-Level Mines

Merwe

Gous

Schutte

2022

SAJIE

View full text Add to dashboard Cite

show abstract

“…Moreover, the ensemble model approach also results in performance advantages due to optimal parameter selection using various combination strategies, batch sizes, epochs, learning rates, etc. 94 The TL1DCNN model proposed by Wang et al was trained on a small data set, resulting in highperformance pipeline leak localization and detection. The system utilized a fiber Bragg grating (FBG) sensor that monitored internal corrosion and pipeline leakage.…”

Section: Effectiveness Of Ldms and Llms Against Possible Leakagementioning

confidence: 99%

Degradation mechanisms associated with metal pipes and the effective impact of LDMs and LLMs in water transport and distribution

Agala

Khan

Starr

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The effective operation of water management systems is contingent upon leak localization and detection – a common problem that is more acute in large networks. This paper reviews the salient literature in this context and demonstrates the effectiveness of leakage location methods (LLMs) and leakage detection methods (LDMs). Although there is a significant amount of literature that discusses leakage localization and detection technologies, an academic lacuna still exists concerning the linkage between degradation mechanisms and LDMs and do not cover or connect past efforts from the start of a degradation mechanism that leads to changes in the mechanical strength (such as a reduction in fracture toughness) of pipes and results in crack propagation and leakage. This review focuses on these issues in the context of degradation mechanisms and common detection methods.

show abstract

“…CNNs have proved to be vital in leak detection and fault diagnosis [22]. A CNN can extract leak-related discriminant information from acoustic images and can utilize it for pipeline state classification [23][24][25][26][27]. For intelligent fault detection, Jiao et al used a residual joint adaptation adversarial network [28] and a deep coupled dense convolutional network [29], which are very interesting and are considered for future research on leak detection.…”

Section: Introductionmentioning

confidence: 99%

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

Ahmad

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

A Pipeline Leak Detection and Localization Approach Based on Ensemble TL1DCNN

Cited by 34 publications

References 43 publications

Using Zero-Waste Baselines to Identify Compressed Air System Inefficiencies in Deep-Level Mines

Using Zero-Waste Baselines to Identify Compressed Air System Inefficiencies in Deep-Level Mines

Degradation mechanisms associated with metal pipes and the effective impact of LDMs and LLMs in water transport and distribution

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

Contact Info

Product

Resources

About