| Citation: | Liu Na, Xu Yinze, Hu Chunming, et al. Knock intensity identification of piston aviation kerosene engine based on dual-domain feature analysis[J]. Journal of Aerospace Power, 2026, 41（9）：20250133 doi: 10.13224/j.cnki.jasp.20250133
|
To improve the accuracy of recognizing knock intensity in aviation kerosene piston engines, a dedicated test bench was built, combustion tests were conducted, and cylinder pressure signals under various operating conditions were collected to extract knock information. Wavelet packet transform was applied to decompose the pressure signals, and energy entropy analysis was used to identify sub-band components effectively characterizing knock levels. The knock feature sub-band for this engine was found to be concentrated within the 7.5—18.75 kHz range. Knock information within this band was reconstructed, and 22 knock feature indicators were extracted from the time and frequency domains, forming a bi-domain knock feature image. To accurately identify and analyze knock intensity, both a multilayer perceptron (MLP) model and a convolutional neural network (CNN) model were developed. These models used the dual-domain knock feature indicators and images as input parameters and were validated under four different operating conditions. The results demonstrated high recognition accuracy for both models, with the CNN model achieving an average accuracy of 93.46%, surpassing the MLP model’s 88.50% by 4.96%. This highlighted the CNN model’s superior accuracy and generalization capability for knock intensity recognition in aviation kerosene engines.
| [1] |
王宝义. 我国低空经济的技术经济范式分析与发展对策[J]. 中国流通经济, 2024, 38(9): 14-26. Wang Baoyi. The technological and economic paradigm analysis and countermeasures for developing low altitude economy in China[J]. China Business and Market, 2024, 38(9): 14-26. (in Chinese doi: 10.14089/j.cnki.cn11-3664/f.2024.09.002
Wang Baoyi. The technological and economic paradigm analysis and countermeasures for developing low altitude economy in China[J]. China Business and Market, 2024, 38(9): 14-26. (in Chinese) doi: 10.14089/j.cnki.cn11-3664/f.2024.09.002
|
| [2] |
张红兴. 对置活塞二冲程内燃机用于无人机的研究[D]. 哈尔滨: 哈尔滨工业大学, 2018. Zhang Hongxing. Study on an opposed piston two stroke internal combustion engine for unmanned aerial vehicle[D]. Harbin: Harbin Institute of Technology, 2018. (in Chinese
Zhang Hongxing. Study on an opposed piston two stroke internal combustion engine for unmanned aerial vehicle[D]. Harbin: Harbin Institute of Technology, 2018. (in Chinese)
|
| [3] |
胡强, 余双, 史开源, 等. 浅谈航空重油活塞式发动机[J]. 航空动力, 2020(5): 32-35. Hu Qiang, Yu Shuang, Shi Kaiyuan, et al. Discussion on the aviation heavy fuel piston engines[J]. Aerospace Power, 2020(5): 32-35. (in Chinese
Hu Qiang, Yu Shuang, Shi Kaiyuan, et al. Discussion on the aviation heavy fuel piston engines[J]. Aerospace Power, 2020(5): 32-35. (in Chinese)
|
| [4] |
Ding Shuiting, Ma Qinglin, Qiu Tian, et al. An engine-level safety assessment approach of sustainable aviation fuel based on a multi-fidelity aerodynamic model[J]. Sustainability, 2024, 16(9): 3814. doi: 10.3390/su16093814
|
| [5] |
Napolitano P, Jimenez I, Pla B, et al. Knock recognition based on vibration signal and Wiebe function in a heavy-duty spark ignited engine fueled with Methane[J]. Fuel, 2022, 315: 122957. doi: 10.1016/j.fuel.2021.122957
|
| [6] |
周浩. 直喷发动机的爆震分析研究[D]. 天津: 天津大学, 2014. Zhou Hao. Investigation on knock analysis of direct injection engine[D]. Tianjin: Tianjin University, 2014. (in Chinese
Zhou Hao. Investigation on knock analysis of direct injection engine[D]. Tianjin: Tianjin University, 2014. (in Chinese)
|
| [7] |
Pla B, De La Morena J, Bares P, et al. An unsupervised machine learning technique to identify knock from a knock signal time-frequency analysis[J]. Measurement, 2023, 211: 112669. doi: 10.1016/j.measurement.2023.112669
|
| [8] |
Borg J M, Cheok K C, Saikalis G, et al. Wavelet-based knock detection with fuzzy logic[C]//2005 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications. Piscataway, US: IEEE, 2005: 26-31.
|
| [9] |
李宁, 周瑞. 基于非线性小波变换的汽油机爆震强度识别[J]. 内燃机学报, 2018, 36(1): 83-89. Li Ning, Zhou Rui. Knock intensity identification for a gasoline engine based on nonlinear wavelet transform[J]. Transactions of Csice, 2018, 36(1): 83-89. (in Chinese doi: 10.16236/j.cnki.nrjxb.201801011
Li Ning, Zhou Rui. Knock intensity identification for a gasoline engine based on nonlinear wavelet transform[J]. Transactions of Csice, 2018, 36(1): 83-89. (in Chinese) doi: 10.16236/j.cnki.nrjxb.201801011
|
| [10] |
孙久岭. 天然气发动机爆震燃烧特性及识别算法研究[D]. 北京: 北京交通大学, 2022. Sun Jiuling. Research on knock combustion characteristics and identification algorithm of natural gas engine[D]. Beijing: Beijing Jiaotong University, 2022. (in Chinese
Sun Jiuling. Research on knock combustion characteristics and identification algorithm of natural gas engine[D]. Beijing: Beijing Jiaotong University, 2022. (in Chinese)
|
| [11] |
Kefalas A, Ofner A B, Pirker G, et al. Detection of knocking combustion using the continuous wavelet transformation and a convolutional neural network[J]. Energies, 2021, 14(2): 439. doi: 10.3390/en14020439
|
| [12] |
Hosseini M, Chitsaz I. Knock probability determination employing convolutional neural network and IGTD algorithm[J]. Energy, 2023, 284: 129282. doi: 10.1016/j.energy.2023.129282
|
| [13] |
Pla B N, Bares P, Jiménez I, et al. A fuzzy logic map-based knock control for spark ignition engines[J]. Applied Energy, 2020, 280: 116036. doi: 10.1016/j.apenergy.2020.116036
|
| [14] |
杨建国, 刘晓峰, 林波. 基于DWT的汽油机爆震特征提取及爆震强度的判定[J]. 内燃机学报, 2003, 21(3): 233-238. Yang Jianguo, Liu Xiaofeng, Lin Bo. DWT based knock detection and knock intensity judgment for a gasoline engine[J]. Transactions of Csice, 2003, 21(3): 233-238. (in Chinese doi: 10.3321/j.issn:1000-0909.2003.03.008
Yang Jianguo, Liu Xiaofeng, Lin Bo. DWT based knock detection and knock intensity judgment for a gasoline engine[J]. Transactions of Csice, 2003, 21(3): 233-238. (in Chinese) doi: 10.3321/j.issn:1000-0909.2003.03.008
|
| [15] |
Molinaro F, Castanie F, Denjean A. Knocking recognition in engine vibration signal using the wavelet transform[C]//Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis. Piscataway, US: IEEE, 1992: 353-356.
|
| [16] |
薛劲梓, 胡春明, 刘娜, 等. 基于小波包能熵谱的爆震特征频带及强度分析[J]. 中南大学学报(自然科学版), 2022, 53(6): 2092-2101. Xue Jinzi, Hu Chunming, Liu Na, et al. Frequency band and intensity analysis of knock characteristics based on wavelet packet energy entropy spectrum[J]. Journal of Central South University (Science and Technology), 2022, 53(6): 2092-2101. (in Chinese doi: 10.11817/j.issn.1672-7207.2022.06.011
Xue Jinzi, Hu Chunming, Liu Na, et al. Frequency band and intensity analysis of knock characteristics based on wavelet packet energy entropy spectrum[J]. Journal of Central South University (Science and Technology), 2022, 53(6): 2092-2101. (in Chinese) doi: 10.11817/j.issn.1672-7207.2022.06.011
|
| [17] |
Naber J, Blough J R, Frankowski D, et al. Analysis of combustion knock metrics in spark-ignition engines[R]. Detroit, US: Sae World Congress and Exhibition, 2006.
|
| [18] |
盛敬, 魏民祥, 刘锐. 基于经验模态分解的煤油发动机爆震因子计算[J]. 内燃机工程, 2013, 34(5): 29-32, 37. Sheng Jing, Wei Minxiang, Liu Rui. Research on knocking factor calculating method based on empirical mode decomposition algorithm for kerosene engine[J]. Chinese Internal Combustion Engine Engineering, 2013, 34(5): 29-32, 37. (in Chinese doi: 10.13949/j.cnki.nrjgc.2013.05.009
Sheng Jing, Wei Minxiang, Liu Rui. Research on knocking factor calculating method based on empirical mode decomposition algorithm for kerosene engine[J]. Chinese Internal Combustion Engine Engineering, 2013, 34(5): 29-32, 37. (in Chinese) doi: 10.13949/j.cnki.nrjgc.2013.05.009
|
| [19] |
张德丰. MATLAB小波分析[M]. 北京: 机械工业出版社, 2009.
|
| [20] |
Pan Yue, Zhang Limao, Wu Xianguo, et al. Structural health monitoring and assessment using wavelet packet energy spectrum[J]. Safety Science, 2019, 120: 652-665. doi: 10.1016/j.ssci.2019.08.015
|
| [21] |
Hudson C, Gao X, Stone R. Knock measurement for fuel evaluation in spark ignition engines[J]. Fuel, 2001, 80(3): 395-407. doi: 10.1016/S0016-2361(00)00080-6
|
| [22] |
何正友, 蔡玉梅, 钱清泉. 小波熵理论及其在电力系统故障检测中的应用研究[J]. 中国电机工程学报, 2005, 25(5): 38-43. He Zhengyou, Cai Yumei, Qian Qingquan. A study of wavelet entropy theory and its application in electric power system fault detection[J]. Proceedings of the CSEE, 2005, 25(5): 38-43. (in Chinese doi: 10.3321/j.issn:0258-8013.2005.05.007
He Zhengyou, Cai Yumei, Qian Qingquan. A study of wavelet entropy theory and its application in electric power system fault detection[J]. Proceedings of the CSEE, 2005, 25(5): 38-43. (in Chinese) doi: 10.3321/j.issn:0258-8013.2005.05.007
|
| [23] |
张炜博. 基于时频分析与非线性熵的水电机组智能故障诊断与状态趋势预测研究[D]. 武汉: 华中科技大学, 2019. Zhang Weibo. Study on intelligent fault diagnosis and state tendency prediction of hydroelectric generator units based on time-frequency analysis and nonlinear entropy[D]. Wuhan: Huazhong University of Science and Technology, 2019. (in Chinese
Zhang Weibo. Study on intelligent fault diagnosis and state tendency prediction of hydroelectric generator units based on time-frequency analysis and nonlinear entropy[D]. Wuhan: Huazhong University of Science and Technology, 2019. (in Chinese)
|
| [24] |
Donahue J, Jia Y, Vinyals O, et al. DeCAF: a deep convolutional activation feature for generic visual recognition[R]. Beijing: 31st International Conference on Machine Learning, 2014.
|
| [25] |
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90. doi: 10.1145/3065386
|
| [26] |
吴正文. 卷积神经网络在图像分类中的应用研究[D]. 成都: 电子科技大学, 2015. Wu Zhengwen. Application research of convolution neural network in image classification[D]. Chengdu: University of Electronic Science and Technology of China, 2015. (in Chinese
Wu Zhengwen. Application research of convolution neural network in image classification[D]. Chengdu: University of Electronic Science and Technology of China, 2015. (in Chinese)
|
| [27] |
周志华. 机器学习[M]. 北京: 清华大学出版社, 2016.
|
DownLoad:
