A comprehensive investigation of LSTM-CNN deep learning model for fast detection of combustion instability. (1st November 2021)

• Record Type: Journal Article
• Authors: Lyu, Zengyi; Jia, Xiaowei; Yang, Yao; Hu, Keqi; Zhang, Feifei; Wang, Gaofeng
• Is Part Of: Fuel. Volume 303(2021)
• Publication Date: 2021-11-01
• Subjects: Premixed swirling flame -- Combustion instability -- Deep learning -- Convolutional neural network -- LSTM; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2021.121300
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: A data-driven model is used to detect combustion instability based on deep learning. Model can correctly identify flame images in real-time. Features extracted by the model reflect the underlying links between flame images and their stabilities. Abstract: In this paper, we propose a deep learning model to detect combustion instability using high-speed flame image sequences. The detection model combines Convolutional Neural Network (CNN) and Long Short-Term Memory network (LSTM) to learn both spatial features and temporal correlations from high-speed images, and then outputs combustion instability detection results. We also visualize the extracted spatial features and their temporal evolution to interpret the detection process of model. In addition, we discuss the effect of different complexity of CNN layers and different amounts of training data on model performance. The proposed method achieves superior performance under various combustion conditions in swirl chamber with high accuracy and a short processing time about 1.23 ms per frame. Hence, we show that the proposed deep learning model is a promising detection tool for combustion instability under various combustion conditions.