Locating hazardous gas leaks in the atmosphere via modified genetic, MCMC and particle swarm optimization algorithms

Ji, Wang; Zhang, Ru; Yan, Yixin; Dong, Xiaoqiang; Li, Jun Ming

doi:10.1016/j.atmosenv.2017.03.009

Cited by 28 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors for a contaminant of interest are often used with a mobile platform using a single robot or multiple robots. Multi-robot methods are typically more efficient and robust in localizing indoor sources through particle swarm optimization (PSO) [28,29], ant colony optimization (ACO) [30] and adapted algorithms [31][32][33][34].…”

Section: Introductionmentioning

confidence: 99%

An improved particle swarm optimization method for locating time-varying indoor particle sources

Feng

Cai

et al. 2019

Building and Environment

View full text Add to dashboard Cite

A B S T R A C TThe indoor transmission of airborne particles can spread disease and have health-related and even life-threatening effects on occupants, thus necessitating effective ways to locate indoor particle sources. The identification of particle sources from concentration distributions is a difficult task because particles are often released at a time-varying rate, and particle transport mechanisms are more complex than those of gas. This study proposes an improved multi-robot olfactory search method for locating two types of time-varying indoor particle sources: 1) periodic sources such as occupants' respiratory activities and 2) decaying sources such as laboratory leaky containers with hazardous chemicals. The method considers both particle concentrations and indoor air velocities by including an upwind term in the standard particle swarm optimization (PSO) algorithm, preventing robots from becoming trapped into a local optimum, which occurs when using other algorithms. We also considered two ventilation types (mixing ventilation and displacement ventilation) when particles are emitted from different source types, comprising four scenarios. For each scenario, particle concentration and air velocity were simulated using computational fluid dynamics (CFD) and then fed to the PSO algorithm for source localization. In addition, we validated the CFD approach for one scenario by comparing experimental data (e.g., velocities and particle concentrations) under laboratory settings. The results showed that the proposed method can locate the two types of particle sources within approximately 55 s, and the success rates of source localization exceeding 96%, which is a much higher level than levels achieved from the standard PSO and wind utilization II algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

An improved particle swarm optimization method for locating time-varying indoor particle sources

Feng

Cai

et al. 2019

Building and Environment

View full text Add to dashboard Cite

show abstract

“…In recent years, several leak localization techniques have been studied. These include the time difference of arrival (TDOA) technique based on basic cross correlation and generalized cross correlation [7], the array signal processing technique based on beamforming and spatial spectrum estimation [8], and the artificial intelligence technique based on neural networks, genetic algorithms or deep learning [9][10][11][12]. The TDOA technique is widely used for leak localization on pipelines for several decades, however, its localization accuracy depends significantly on the degree of signal correlation [13].…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of acoustic emission sensor arrays in different topologies for the localization of gas leakage on a flat-surface structure

Yan

Guo

2019

Sensors and Actuators A: Physical

View full text Add to dashboard Cite

show abstract

“…We intend to deal with the ongoing problem of GSL in outdoor environments. Studies so far are usually limited to using simulations or environments of specific conditions [12,16]. This is because airflow in outdoor environments is usually intermittent and unpredictable making it difficult to model.…”

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Long Short-Term Memory Neural Networks to Signals Collected from a Sensor Network for Autonomous Gas Source Localization in Outdoor Environments

Bilgera

Yamamoto

Sawano

et al. 2018

Sensors

View full text Add to dashboard Cite

Convolutional Long Short-Term Memory Neural Networks (CNN-LSTM) are a variant of recurrent neural networks (RNN) that can extract spatial features in addition to classifying or making predictions from sequential data. In this paper, we analyzed the use of CNN-LSTM for gas source localization (GSL) in outdoor environments using time series data from a gas sensor network and anemometer. CNN-LSTM is used to estimate the location of a gas source despite the challenges created from inconsistent airflow and gas distribution in outdoor environments. To train CNN-LSTM for GSL, we used temporal data taken from a 5 × 6 metal oxide semiconductor (MOX) gas sensor array, spaced 1.5 m apart, and an anemometer placed in the center of the sensor array in an open area outdoors. The output of the CNN-LSTM is one of thirty cells approximating the location of a gas source. We show that by using CNN-LSTM, we were able to determine the location of a gas source from sequential data. In addition, we compared several artificial neural network (ANN) architectures as well as trained them without wind vector data to estimate the complexity of the task. We found that ANN is a promising prospect for GSL tasks.

show abstract

Locating hazardous gas leaks in the atmosphere via modified genetic, MCMC and particle swarm optimization algorithms

Cited by 28 publications

References 38 publications

An improved particle swarm optimization method for locating time-varying indoor particle sources

An improved particle swarm optimization method for locating time-varying indoor particle sources

Performance comparison of acoustic emission sensor arrays in different topologies for the localization of gas leakage on a flat-surface structure

Application of Convolutional Long Short-Term Memory Neural Networks to Signals Collected from a Sensor Network for Autonomous Gas Source Localization in Outdoor Environments

Contact Info

Product

Resources

About