A data-driven approach using machine learning for early detection of the lean blowout

Hasti, Veeraraghava Raju; Navarkar, Abhishek; Gore, Jay P.

doi:10.1016/j.egyai.2021.100099

Cited by 20 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 7, Figure 8, and Figure 11 show that, although the parameters of the ANN had been optimized, there was discrepancy between the predicted b ij and the actual values. Some scholars have adopted intelligence algorithms such as the random forest 57,58 and SVM 59,60 in the training of data-driven models. However, their studies did not address indoor airflows.…”

Section: Test Casesmentioning

confidence: 99%

Application of data‐driven RANS model in simulating indoor airflow

Chen

Liu

et al. 2022

Indoor Air

View full text Add to dashboard Cite

The indoor environment has a significant impact on our wellbeing. Accurate prediction of the indoor air distribution can help to create a good indoor environment. Reynolds‐averaged Navier–Stokes (RANS) models are commonly used for indoor airflow prediction. However, the Boussinesq hypothesis used in the RANS model fails to account for indoor anisotropic flows. To solve this problem, this study developed a data‐driven RANS model by using a nonlinear model from the literature. An artificial neural network (ANN) was used to determine the coefficients of high‐order terms. Three typical indoor airflows were selected as the training set to develop the model. Four other cases were used as testing sets to verify the generalizability of the model. The results show that the data‐driven model can better predict the distributions of air velocity, temperature, and turbulent kinetic energy for the indoor anisotropic flows than the original RANS model. This is because the nonlinear terms are accurately simulated by the ANN. This investigation concluded that the data‐driven model can correctly predict indoor anisotropic flows and has reasonably good generalizability.

show abstract

Section: Test Casesmentioning

confidence: 99%

Application of data‐driven RANS model in simulating indoor airflow

Chen

Liu

et al. 2022

Indoor Air

View full text Add to dashboard Cite

show abstract

“…However, limited studies are available in the literature. A study by [110] implemented machine learning using a Support Vector Machine to early detect the LBO. The model successfully predicted the LBO approximately 20 ms before the event.…”

Section: Prediction Techniques Of Lean Blowoutmentioning

confidence: 99%

Dry-Low Emission Gas Turbine Technology: Recent Trends and Challenges

et al. 2022

View full text Add to dashboard Cite

Dry-low emission (DLE) is one of the cleanest combustion types used in a gas turbine. DLE gas turbines have become popular due to their ability to reduce emissions by operating in lean-burn operation. However, this technology leads to challenges that sometimes interrupt regular operations. Therefore, this paper extensively reviews the development of the DLE gas turbine and its challenges. Numerous online publications from various databases, including IEEE Xplore, Scopus, and Web of Science, are compiled to describe the evolution of gas turbine technology based on emissions, fuel flexibility, and drawbacks. Various gas turbine models, including physical and black box models, are further discussed in detail. Working principles, fuel staging mechanisms, and advantages of DLE gas turbines followed by common faults that lead to gas turbine tripping are specifically discussed. A detailed evaluation of lean blow-out (LBO) as the major fault is subsequently highlighted, followed by the current methods in LBO prediction. The literature confirms that the DLE gas turbine has the most profitable features against other clean combustion methods. Simulation using Rowen’s model significantly imitates the actual behavior of the DLE gas turbine that can be used to develop a control strategy to maintain combustion stability. Lastly, the data-driven LBO prediction method helps minimize the flame’s probability of a blow-out.

show abstract

“…Other potential features need to be explored further. Hasti et al [22] proposed a data-driven method based on support vector machine (SVM) to identify the critical flame location of the LBO flame. The temperature and OH mass fraction from the large eddy simulation were used as training data to establish the machine learning model.…”

Section: Introductionmentioning

confidence: 99%

A Neural Network-Based Flame Structure Feature Extraction Method for the Lean Blowout Recognition

Yan,

Cao,

Peng

et al. 2024

Aerospace

View full text Add to dashboard Cite

A flame’s structural feature is a crucial parameter required to comprehensively understand the interaction between turbulence and flames. The generation and evolution processes of the structure feature have rarely been investigated in lean blowout (LBO) flame instability states. Hence, to understand the precursor features of the LBO flame, this work employed high-speed OH-PLIF measurements to acquire time-series LBO flame images and developed a novel feature extraction method based on a deep neural network to quantify the LBO features in real time. Meanwhile, we proposed a deep neural network segmentation method based on a tri-map called the Fire-MatteFormer, and conducted a statistical analysis on flame surface features, primarily holes. The statistical analysis results determined the relationship between the life cycle of holes (from generation to disappearance) and their area, perimeter, and total number. The trained Fire-MatteFormer model was found to represent a viable method for determining flame features in the detection of incipient LBO instability conditions. Overall, the model shows significant promise in ascertaining local flame structure features.

show abstract

A data-driven approach using machine learning for early detection of the lean blowout

Cited by 20 publications

References 32 publications

Application of data‐driven RANS model in simulating indoor airflow

Application of data‐driven RANS model in simulating indoor airflow

Dry-Low Emission Gas Turbine Technology: Recent Trends and Challenges

A Neural Network-Based Flame Structure Feature Extraction Method for the Lean Blowout Recognition

Contact Info

Product

Resources

About