A Novel PPA Method for Fluid Pipeline Leak Detection Based on OPELM and Bidirectional LSTM

Lei, Yang; Zhao, Qing

doi:10.1109/access.2020.3000960

Cited by 19 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(a) The identification result oscillates (especially in the transonic region) due to randomly generated structural parameters (b) When a single ELM is used to identify projectile aerodynamic parameters, it is hard to make sufficient use of the local information of the sample data and then causes overfitting To overcome the above problems and then accurately obtain the aerodynamic parameters of the projectile, a large number of documents are referenced. For problem (a), the classical idea is to apply PSO, GA, and other optimization algorithms to optimize the structural parameters of ELM [43][44][45][46][47][48][49]. However, iterative optimization increases the time complexity of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

Aerodynamic Parameter Identification of Projectile Based on Improved Extreme Learning Machine and Ensemble Learning Theory

Wang

Xia

2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

The firing accuracy of the projectile has a positive relation with aerodynamic parameters. Due to the complex dynamic characteristics of projectiles, there is an overfitting risk when a single extreme learning machine (ELM) is used to identify the aerodynamic parameters of the projectile, and the identification results oscillate transonic region. To obtain the aerodynamic parameters of the projectile accurately, an aerodynamic parameter identification model based on ensemble learning theory and ELM optimized by improved particle swarm optimization is proposed. The improved particle swarm optimization algorithm (IPSO) with an adaptive update strategy is used to optimize the weight and threshold of ELM. Combined with the ensemble learning theory, the improved ELM neural network is regarded as a weak learner to generate a strong learner. The structural parameters of the strong learner were continuously optimized through training, and an aerodynamic parameter identification model of projectile based on ensemble learning theory is obtained. The simulation results show that the introduction of the IPSO and ensemble learning theory enables the model to exhibit excellent generalization ability. The proposed identification model can accurately describe the variation of aerodynamic parameters with the Mach number.

show abstract

Section: Introductionmentioning

confidence: 99%

Aerodynamic Parameter Identification of Projectile Based on Improved Extreme Learning Machine and Ensemble Learning Theory

Wang

Xia

2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

show abstract

“…The transmission and storage of liquid or gas are widely used in the chemical, electric power, food and medical industries, as well as other fields [1,2]. The leakage will not only cause economic loss and waste of resources [3], but the toxic gas released will also cause environmental pollution, explosion, fire, etc.…”

Section: Introductionmentioning

confidence: 99%

Leak Detection and Localization in Multi-Grid Space Using Improved Gaussian Plume Model

Liu

Mao

2023

Sensors

View full text Add to dashboard Cite

Leak detection and localization of liquid or gas is of great significance to avoid potential danger and reduce the waste of resources. Leak detection and localization methods are varied and uniquely suited to specific application scenarios. The existing methods are primarily applied to conventional pressurized pipelines and open areas, and there are few methods suitable for multi-grid spaces. In this paper, a gas diffusion model applied to multi-grid space is constructed, and a method for leak detection and localization using the concentration gradient of characteristic gas is proposed according to the prediction behavior. The Gaussian plume model is selected due to its advantages of simplicity and the interpretation of gas diffusion behavior is closer to reality; the expression of the improved model is also obtained. To verify the correctness of the model and the applicability of the localization method, taking the coolant leakage in the circuit system as an example, three experiments with different source strengths were repeated. The fitting correlation coefficients between the gas concentration data of the three experiments and the model are 0.995, 0.997 and 0.997, respectively. The experimental results show that the model has a strong correlation with the real plume behavior, and it is reasonable to use the gas concentration gradient for the localization of the leak source. This study provides a reference for future research on the leak detection and localization of gas- or liquid-containing volatile substances in a complex multi-grid space.

show abstract

“…In recent years, many methods have been proposed based on artificial intelligence (AI) techniques for developing leak detection systems [2][3]. For example, Yang and Zhao [2] used an optimally pruned extreme learning machine (OPELM) to improve the accuracy of the pressure point analysis (PPA), and used bidirectional long-short term memory (BiLSTM) to construct a leak detection system [2]. Zhou et al [3] used improved spline-local mean decomposition (ISLMD) to analyze the internal pressure value of pipelines.…”

Section: Introductionmentioning

confidence: 99%

Developing and Implementing an AI-Based Leak Detection System in a Long-Distance Gas Pipeline

Wang¹,

Lin²,

Shen³

2022

Adv. technol. innov.

View full text Add to dashboard Cite

This research proposes an artificial intelligence (AI) detection model using convolutional neural networks (CNN) to automatically detect gas leaks in a long-distance pipeline. The change of gap pressure is collected when leakage occurs in the pipeline, and thereby the feature of gas leakage is extracted for building the CNN model. The gas leak patterns in the long-distance pipeline are analyzed. A pipeline detection model based on AI technology for automatically monitoring the leaks is proposed by extracting the feature of gas leakage. This model is tested by collecting gas pressure data from an existing natural gas pipeline system starting from Mailiao to Taoyuan in Taiwan. The testing result shows that the reduced model of leak detection can be used to detect the leaks from the upstream and downstream pipelines, and the AI-based pipeline leak detection system can obtain a satisfactory result.

show abstract

A Novel PPA Method for Fluid Pipeline Leak Detection Based on OPELM and Bidirectional LSTM

Cited by 19 publications

References 23 publications

Aerodynamic Parameter Identification of Projectile Based on Improved Extreme Learning Machine and Ensemble Learning Theory

Aerodynamic Parameter Identification of Projectile Based on Improved Extreme Learning Machine and Ensemble Learning Theory

Leak Detection and Localization in Multi-Grid Space Using Improved Gaussian Plume Model

Developing and Implementing an AI-Based Leak Detection System in a Long-Distance Gas Pipeline

Contact Info

Product

Resources

About