Deep learning approach for super-knock event prediction of petrol engine with sample imbalance. (1st March 2022)

• Record Type: Journal Article
• Authors: Zhou, Zhou; Xiong, Shengwu; Chen, Yaxiong; Zhang, Chan; Cao, Yinbo
• Is Part Of: Fuel. Volume 311(2022)
• Publication Date: 2022-03-01
• Subjects: Deep learning -- Super-knock -- Triplet network -- LSTM -- Imbalance problem; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2021.122509
• Languages: English
• ISSNs: 0016-2361

Abstract

Abstract: Petrol engine becomes much smaller and has higher compression ratio due to the strict exhaust emission regulations and consumer demand for power performance. Meanwhile, the frequency of super-knock is increasing sharply at low speed of high load working region, which has great damage to engine components. Prediction of super-knock is therefore of great significance to optimize operation conditions and prolong service life. High-performance in-cylinder sensors can provide quality information for super-knock prediction, but at a price that production vehicles cannot afford. An approach that does not require additional engine sensors while having an acceptable accuracy rate is needed. Furthermore, the super-knock events are difficult to capture, making prediction task subjects to sample imbalance. In this research, a deep learning approach using only existing engine sensors was applied to address the challenge. Specifically, a two-stage model was designed: (i) Feature extraction, an LSTM based triplet network is built to extract the differential features between super-knock and normal combustion from the engine working cycles. (ii) Classification, to effectively use the extracted features and metric information from the previous stage, a modified KNN classifier is employed. The effectiveness of the proposed approach, i.e., TLSTM-KNN was evaluated and compared with other state-of-the-art methods on an actual engine-based dataset under different imbalance ratios (IR). The prediction precision and recall of super-knock event reach to 81.67% and 79.01% for the test dataset at IR=10. Even at IR=100, the precision and recall reach to 59.02% and 63.31%. The comparisons suggested that the proposed model provides better prediction performance and robustness capability compared to other traditional prediction models. Finally sensitivity analysis was used to explore the factors influencing super-knock. Highlights: A deep learning method is adopted for the super-knock prediction using existing engine sensors. The triplet-network structure is employed to address the sample imbalance problem. The prediction performance under different imbalance ratios is discussed. Sensitivity analysis is conducted to explore the factors influencing super-knock.