基于卷积神经网络的柴油机失火故障实时诊断

doi:10.13229/j.cnki.jdxbgxb20210777

摘要/Abstract

摘要：

针对发动机的失火故障，提出了一种基于卷积神经网络（CNN）的失火诊断方法，构建了基于STM32单片机的柴油机失火故障实时诊断系统。通过STM32CubeMX软件将柴油机失火故障诊断的卷积神经网络写入到单片机中，在试验过程中利用单片机的定时器输入捕获功能采集柴油机的转速信号，且将上止点信号作为转速采集的触发信号，将采集到的转速进行预处理作为卷积神经网络的输入。通过柴油机台架试验证明，所建立的柴油机失火实时诊断系统在较宽的转速与负荷工况下有较高的诊断准确率。

关键词: 柴油机, 失火故障诊断, 卷积神经网络, STM32单片机

Abstract:

Aiming at diagnosing the misfire fault of engine， a method of misfire diagnosis based on convolutional neural network（CNN） is proposed. The real-time diagnosis system for misfire fault detection of diesel engine is constructed based on STM32 single chip microcomputer. The convolutional neural network for misfire fault diagnosis of diesel engine is written in Microcontroller Unit（MCU） based on STM32CubeMX software. In the experiment the speed signal is collected by using the timer input capture function of single chip microcomputer， and the top dead center signal works as the trigger signal for speed acquisition. The collected speed data is preprocessed and then used as the input of CNN. The test results in the diesel engine bench show that the real-time misfire diagnosis system has high diagnostic accuracy under wide range of speed and load conditions.

Key words: diesel engine, misfire diagnosis, convolutional neural network, STM32 single chip microcomputer

中图分类号:

TK428

高文志,王彦军,王欣伟,张攀,李勇,董阳. 基于卷积神经网络的柴油机失火故障实时诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 417-424.

Wen-zhi GAO,Yan-jun WANG,Xin-wei WANG,Pan ZHANG,Yong LI,Yang DONG. Real⁃time diagnosis for misfire fault of diesel engine based on convolutional neural network[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 417-424.

图/表 8

图1

表1

表2

图2

图3

表3

图4

表4

参考文献 27

1	王银辉, 黄开胜, 林志华, 等. 发动机多缸随机失火诊断算法研究[J]. 内燃机工程, 2012, 33(1): 18-21, 26.
	Wang Yin-hui, Huang Kai-sheng, Lin Zhi-hua, et al. Study of engine multi-cylinder random misfire detection[J]. Chinese Internal Combustion Engine Engineering, 2012, 33(1): 18-21, 26.
2	郑太雄, 张瑜, 李永福. 汽车发动机失火故障诊断方法研究综述[J]. 自动化学报, 2017, 43(4): 509-527.
	Zheng Tai-xiong, Zhang Yu, Li Yong-fu, Misfire fault diagnosis of automobile engine: a review[J]. Acta Automatica Sinica, 2017, 43(4): 509-527.
3	王德军, 吕志超, 王启明, 等. 基于卡尔曼转速观测器时频变换的失火故障诊断[J]. 吉林大学学报: 工学版, 2019, 49(1): 209-220.
	Wang De-jun, Lv Zhi-chao,Wang Qi-ming, et al. Misfire detection based on time-frequency transform of kalman speed observer[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(1): 209-220.
4	王德军, 吕志超, 王启明, 等. 基于汽缸压力辨识的发动机失火故障诊断[J]. 吉林大学学报: 工学版, 2017, 47(1): 917-923.
	Wang De-jun, Lv Zhi-chao, Wang Qi-ming, et al. Engine misfire fault diagnosis based on cylinder pressure identification[J]. Journal of Jilin University(Engineering and Technology Edition), 2017, 47(1): 917-923.
5	Wu Z J, Sanjeev M N. DSP applications in engine control and onboard diagnostics: enabling greener automobiles[J]. IEEE Signal Processing Magazine, 2017, 34(2): 70-81.
6	Xia Z C, Ma X P, Wu H T, et al. Combined frequency domain analysis and fuzzy logic for engine misfire diagnosis[C]∥SAE Technical Paper, 2015-01-0207.
7	刘健康, 高文志, 张攀, 等. 基于改进段角加速度和神经网络的柴油机失火诊断研究[J]. 内燃机工程, 2019, 40(1): 79-85.
	Liu Jian-kang, Gao Wen-zhi, Zhang Pan, et al. Diagnosis of misfire fault of diesel engine based on segment angular acceleration and neural network[J]. Chinese Internal Combustion Engine Engineering, 2019, 40(1): 79-85.
8	Siegfried H, Martin K, Stefan J. Combustion torque estimation and misfire detection for calibration of combustion engines by parametric Kalman filtering[J]. IEEE Transactions on Industrial Electronics, 2012, 59(11): 4326-4337.
9	Gu C, Qiao X Y, Li H Y, et al. Misfire fault diagnosis method for diesel engine based on MEMD and dispersion entropy[J]. Shock and Vibration, 2021(5): 9213697.
10	李卫星, 陶建峰, 覃程锦, 等. 同步压缩小波与极限梯度提升树融合的柴油机失火故障诊断[J]. 西安交通大学学报, 2019, 53(2): 47-54.
	Li Wei-xing, Tao Jian-feng, Qin Cheng-jin, et al. A diagnostic method for diesel engine misfire based on integrating of Synchro-Squeezed wavelet transform and XGBoost[J]. Journal of Xi'an Jiaotong University, 2019, 53(2): 47-54.
11	贾继德, 任刚, 梅检民, 等. 基于变分模态分解和交叉小波变换的柴油机失火故障诊断[J]. 内燃机工程,2020, 41(1): 57-63.
	Jia Ji-de, Ren Gang, Mei Jian-min, et al. Fault diagnosis of diesel engine misfire based on VMD and XWT[J]. Chinese Internal Combustion Engine Engineering, 2020, 41(1): 57-63.
12	樊新海, 安钢, 张传清, 等. 基于排气噪声EMD的柴油机失火故障诊断[J]. 内燃机工程, 2010, 31(1): 78-81.
	Fan Xin-hai, An Gang, Zhang Chuan-qing, et al. Misfire fault diagnosis for diesel engine based on EMD of exhaust noise[J]. Chinese Internal Combustion Engine Engineering, 2010, 31(1): 78-81.
13	Sneha S, Potala S, Mohanty A R. An improved method of detecting engine misfire by sound quality metrics of radiated sound[J]. Proceedings of the Institution of Mechanical Engineers Part D-Journal of Automobile Engineering, 2019, 233(12): 3112-3124.
14	Lu D, Dou W J. Fault diagnosis of engine misfire based on genetic optimized support vector machine[C]∥IEEE Proceedings of 2011 6th International Forum on Strategic Technology, Harbin, 2011: 250-253.
15	毕晓君, 柳长源, 卢迪. 基于PSO-RVM算法的发动机故障诊断[J]. 哈尔滨工程大学学报, 2014, 35(2): 245-249.
	Bi Xiao-jun, Liu Chang-yuan, Lu Di. Engine fault diagnosis method based on PSO-RVM algorihm[J]. Journal of Harbin Engineering University, 2014, 35(2): 245-249.
16	院老虎, 连冬杉, 张亮, 等. 基于密集连接卷积网络和支持向量机的飞行器机械部件故障诊断[J]. 吉林大学学报: 工学版, 2021, 51(5): 1635-1641.
	Yuan Lao-hu, Lian Dong-shan, Zhang Liang,et al. Fault diagnosis of key mechanical components of aircraft based on DenseNet and SVM[J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1635-1641.
17	Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
18	Ding X X, He Q B, Energy-fluctuated multiscale feature learning with deep ConvNet for intelligent spindle bearing fault diagnosis[J]. IEEE Transactions on Instrumentation&Measurement, 2017, 66(8): 1926-1935.
19	Qin C J, Jin Y R, Tao J F, et al. A deep twin convolutional neural networks with multi-domain inputs for strongly noisy diesel engine misfire detection[J]. Measurement, 2021, 180: 109548.
20	Janssens O, Slavkovikj V, Vervisch B, et al. Convolutional neural network based fault detection for rotating machinery[J]. Journal of Sound and Vibration, 2016, 377: 331-345.
21	张康, 陶建峰, 覃程锦, 等.随机丢弃和批标准化的深度卷积神经网络柴油机失火故障诊断[J]. 西安交通大学学报, 2019, 53(8): 159-166.
	Zhang Kang, Tao Jian-feng, Qin Cheng-jin, et al. Diesel engine misfire diagnosis with deep convolutional neural network using dropout and batch normalization[J]. Journal of Xi'an Jiaotong University, 2019, 53(8): 159-166.
22	张根保, 李浩, 冉琰, 等. 一种用于轴承故障诊断的迁移学习模型[J]. 吉林大学学报: 工学版, 2020, 50(5): 1617-1626.
	Zhang Gen-bao, Li Hao, Ran Yan, et al. A transfer learning model for bearing fault diagnosis[J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(5): 1617-1626.
23	Feng J, Yao Y, Lu S X, et al. Domain knowledge-based Deep-Broad learning framework for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 68(4): 3454-3464.
24	张鹏, 孔峰, 王忠, 等. 车载诊断系统失火诊断策略的研究[J]. 汽车技术, 2007(9): 20-23.
	Zhang Peng, Kong Feng, Wang Zhong, et al. Study on misfire diagnosis strategy of on-board diagnostic system[J]. Automobile Technology, 2007(9): 20-23.
25	陆红雨. 轻型汽油车OBD(车载诊断)型式认证试验研究[D]. 长春: 吉林大学汽车工程学院, 2007.
	Lu Hong-yu. Study on OBD(on-board diagnostic) type approval test for light-duty gasoline vehicle[D]. Changchun: College of Automotive Engineering, Jilin University, 2007.
26	Wu P L, Nie X Y, Xie G. Multi-sensor signal fusion for a compound fault diagnosis method with strong generalization and noise-tolerant performance[J]. Measurement Science and Technology, 2021, 32(3): 1-16.
27	胡晓依, 荆云建, 宋志坤, 等. 基于CNN-SVM的深度卷积神经网络轴承故障识别研究[J]. 振动与冲击, 2019, 38(18): 173-178.
	Hu Xiao-yi, Jing Yun-jian, Song Zhi-kun, et al. Bearing fault identification by using deep convolution neural networks based on CNN-SVM[J]. Journal of Vibration and Shock, 2019, 38(18): 173-178.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

序号	神经网络层	核尺寸	核数量	步长	激活函数	补零	输出规模
1	输入层	/	/	/	/	/
2	卷积层C1	6×2	16	1×1	Relu	SAME
3	池化层S1	3×2	16	3×2	/	SAME
4	卷积层C2	6×2	32	1×1	Relu	SAME
5	池化层S2	2×2	32	2×2	/	SAME
6	平铺层	/	/	/	/	/	1280
7	全连接层	1	1	/	Relu	/	60
8	输出层	1	1	/	Softmax	/	7

发动机参数	数值
气缸数	6
气缸的布置形式	立式直列
缸径/mm	102
行程/mm	118
总排量/L	5.8
压缩比	17.5
发火顺序	1-5-3-6-2-4
转速范围/（r·min^-1）	800~2200
标定功率/kW	85

负载/（N·m）	转速/（r·min^-1）	准确率/%
空载	1000	99.61
空载	1800	99.77
150	1000	99.50
	1400	99.85
	1800	99.77
300	1000	99.83
300	1800	99.91

负荷/（N·m）	转速/（r·min^-1）
负荷/（N·m）	900	1500	1900
空载	99.29	100.00	99.29
75	100.00	100.00	99.29
150	100.00	100.00	100.00
300	100.00	100.00	100.00

[1]	张龙,徐天鹏,王朝兵,易剑昱,甄灿壮. 基于卷积门控循环网络的齿轮箱故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 368-376.
[2]	段亮,宋春元,刘超,魏苇,吕成吉. 基于机器学习的高速列车轴承温度状态识别[J]. 吉林大学学报(工学版), 2022, 52(1): 53-62.
[3]	钟辉,康恒,吕颖达,李振建,李红,欧阳若川. 基于注意力卷积神经网络的图像篡改定位算法[J]. 吉林大学学报(工学版), 2021, 51(5): 1838-1844.
[4]	王德兴,吴若有,袁红春,宫鹏,王越. 基于多尺度注意力融合和卷积神经网络的水下图像恢复[J]. 吉林大学学报(工学版), 2021, 51(4): 1396-1404.
[5]	王忠,李游,张美娟,刘帅,李瑞娜,赵怀北. 柴油机排气阶段颗粒碰撞过程动力学特征分析[J]. 吉林大学学报(工学版), 2021, 51(1): 39-48.
[6]	王柯俨,王迪,赵熹,陈静怡,李云松. 基于卷积神经网络的联合估计图像去雾算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1771-1777.
[7]	刘国华,周文斌. 基于卷积神经网络的脉搏波时频域特征混叠分类[J]. 吉林大学学报(工学版), 2020, 50(5): 1818-1825.
[8]	李志军,杨楚皙,刘丹,孙大洋. 基于深度卷积神经网络的信息流增强图像压缩方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1788-1795.
[9]	谌华,郭伟,闫敬文,卓文浩,吴良斌. 基于深度学习的SAR图像道路识别新方法[J]. 吉林大学学报(工学版), 2020, 50(5): 1778-1787.
[10]	车翔玖,董有政. 基于多尺度信息融合的图像识别改进算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1747-1754.
[11]	王建,许鑫,顾晗,张多军,刘胜吉. 基于排气热管理的柴油机氧化催化器升温特性[J]. 吉林大学学报(工学版), 2020, 50(2): 408-416.
[12]	马子骥,卢浩,董艳茹. 双通道单图像超分辨率卷积神经网络[J]. 吉林大学学报(工学版), 2019, 49(6): 2089-2097.
[13]	车翔玖,刘华罗,邵庆彬. 基于Fast RCNN改进的布匹瑕疵识别算法[J]. 吉林大学学报(工学版), 2019, 49(6): 2038-2044.
[14]	刘长铖,刘忠长,田径,许允,杨泽宇. 重型增压柴油机燃烧过程中的缸内㶲损失[J]. 吉林大学学报(工学版), 2019, 49(6): 1911-1919.
[15]	周柚,杨森,李大琳,吴春国,王岩,王康平. 基于现场可编程门电路的人脸检测识别加速平台[J]. 吉林大学学报(工学版), 2019, 49(6): 2051-2057.