新能源汽车电动真空泵助力制动系统故障诊断方法*

doi:10.13385/j.cnki.vacuum.2025.06.09

摘要/Abstract

摘要： 动态工况下,新能源汽车电动真空泵助力制动系统的瞬态信号具有多模态非线性耦合特性,易误判故障模态。故本研究提出了一种新的故障诊断方法。首先,通过实时监测真空泵工作时的极限真空度、抽气速率等核心参数,构建电动真空泵助力制动系统的动态特性模型,再从电流和压力两方面入手,获取该系统的运行瞬态特性,并生成连续时刻的系统运行瞬态信号;其次,为应对信号的多模态非线性耦合特性,利用小波分析理论分解瞬态信号,提取每个频段信号的能量熵特征,通过精细刻画故障特征的内在本质提高对故障特征的辨识度和区分度,并建立真空失效特征库;最后,结合ResCNN网络和XGBoost构建智能故障诊断模型,将能量熵特征输入其中,通过卷积池化运算进一步挖掘深层次代表特征,再依靠XGBoost的自动分类能力,对挖掘出的深层次特征进行高效、准确的分类,从而输出制动系统故障诊断结果。结果表明：该方法的ACC值达到了0.97,实现了对制动系统运行状态的准确描述,有效缩短真空建立时间,降低系统的压力波动和能耗。

关键词: 电动真空泵制动系统, 真空动力学, 深度学习, 真空失效, 故障诊断

Abstract: Under dynamic working conditions, the transient signal of the electric vacuum pump assisted braking system of new energy vehicles has multi-modal nonlinear coupling characteristics, which can easily lead to misjudgement of fault modes. Therefore, this study proposes a new fault diagnosis method. Firstly, by real-time monitoring of core parameters such as the maximum vacuum degree and pumping rate during the operation of the vacuum pump, a dynamic characteristic model of the electric vacuum pump assisted braking system is constructed. Secondly, starting from the aspects of current and pressure, the transient characteristics of the electric vacuum pump assisted braking system are obtained, and continuous transient signals of the system operation are generated; Then, to address the multi-modal nonlinear coupling characteristics of the signal, the transient signal is decomposed using wavelet analysis theory, and the energy entropy features of each frequency band signal are extracted. By finely characterizing the inherent nature of the fault features, the identification and discrimination of the fault features are improved, and a vacuum failure feature library is established; Finally, an intelligent fault diagnosis model is constructed by combining ResCNN network and XGBoost. Energy entropy features are input into the model, and deep level representative features are further explored through convolutional pooling operation. Then, relying on the automatic classification ability of XGBoost, the deep level features are efficiently and accurately classified to output the fault diagnosis results of the braking system. The results show that the ACC value of this method reaches 0.97, which realizes the accurate description of the running state of the braking system, effectively shortens the vacuum establishment time, and reduces the pressure fluctuation and energy consumption of the system.

Key words: electric vacuum pump braking system, vacuum dynamics, deep learning, vacuum failure, fault diagnosis

中图分类号: TB752;TP391.5

王吉欣, 胡宸琪. 新能源汽车电动真空泵助力制动系统故障诊断方法^*[J]. 真空, 2025, 62(6): 62-69.

WANG Jixin, HU Chenqi. Fault Diagnosis Method for Electric Vacuum Pump Assisted Braking System of New Energy Vehicles[J]. VACUUM, 2025, 62(6): 62-69.

参考文献

[1] ROTH A.Vacuum technology in automotive applications[J]. Vacuum, 2021, 89(3): 45-58.
[2] 刘双源,吴科瑞.电动车电机驱动传感系统集成故障诊断策略[J].机械设计与制造,2024,400(6):223-228.
[3] 张兴琦,宋杰,宋雪梅,等.基于AMESIM的电动真空泵优化匹配研究[J].南京理工大学学报,2023,47(3):397-403.
[4] 黄庆程. 基于IPSO-SVM的动态汽车衡故障诊断方法研究[J].机电工程,2024,41(12):2310-2319.
[5] 徐猛,袁细祥,石计红,等.真空泵系统引致车内结构噪声快速识别与控制[J].噪声与振动控制,2022,42(4):256-261.
[6] 洪吉超,张昕阳,徐晓明,等.基于多熵融合的动力电池故障诊断与应用研究[J].机械工程学报,2024,60(12):301-312.
[7] 孙环阳,张红光,薛明晨,等.基于小波包分解与BP神经网络的制动系统电磁阀故障诊断研究[J].铁道机车车辆,2024,44(5):39-45.
[8] 陈岩霖,孙庚,汪敏捷,等.基于MSIF-CNN的地铁车辆制动系统故障诊断方法[J].现代电子技术,2024,47(24):137-142.
[9] 钟志成,徐封杰,李超超,等.基于动态故障树的汽车系统故障诊断方法[J].电子测量技术,2023,46(14):131-137.
[10] ZHOU C, YU N, CAI G, et al.Comparison between the dynamic characteristics of electric pump fed engine and expander cycle engine[J]. Aerospace Science and Technology. 2022, 124: 107508.
[11] 范永山,杜畅通,张化一,等.Xi PAF重离子同步加速器超高真空系统设计[J].工程科学与技术,2025,57(1):339-346.
[12] 杜伟,张少伟,辛庆锋,等.电动汽车真空泵结构与性能分析[J].机械制造,2024,62(1):29-30.
[13] 闵济东,李京,胡文盛,等.基于喷射器的一回路抽真空系统研究[J].核动力工程,2023,44(S2):221-225.
[14] 李正清,韩仙虎,蔡宇宏,等.一种腰部为椭圆线的罗茨真空泵转子型线设计与分析[J].真空, 2024, 61(1):47-51.
[15] 杨乃恒. 关于真空除气使用的真空泵情况分析与讨论[J].真空,2021,58(1):29-32.
[16] BARRAU A, BONNABEL S.The invariant extended kalman filter as a stable observer[J]. IEEE Transactions on Automatic Control. 2017, 62(4): 1797-1812.
[17] 张丕显,张以忱,战春鸣,等.干式真空泵在半导体及新能源领域的应用及发展趋势[J].真空,2024,61(3):1-8.
[18] 赵前玉,于振华,李恒霖,等.基于MATLAB/GUI的真空泵抽速曲线预测计算[J].真空,2024,61(3):9-12.
[19] 郑宝山. 液环真空泵抽气量修正探讨及工程应用优化[J].化工设备与管道,2021,58(5):38-42.
[20] 侯聪闻,柳恩芬,张世强,等.电子真空助力器控制系统及方法[J].吉林大学学报(信息科学版),2022,40(1):13-19.
[21] 何天一,岳向吉,张志军,等.等螺距螺杆真空泵内气体流动的数值模拟研究[J].真空,2024,61(1):52-57.
[22] 李小金,李正清,韩仙虎,等.基于TRIZ理论的一种提升罗茨真空泵基础压力的设计方法[J].真空, 2024, 61(2):62-67.
[23] 田兴丽,孙环阳,张红光,等.城市轨道交通车辆制动系统的智能诊断与预警系统[J].城市轨道交通研究,2023,26(11):94-98.
[24] 郭媛,汪胜,李世超,等.基于高斯模糊和BP神经网络的汽车液压转向系统故障诊断[J].液压与气动,2023,47(10):70-77.
[25] 何宇新,廖长江,何新旭.基于多尺度信息熵特征的数据流快速聚类研究[J].电子设计工程,2024,32(15):41-44.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed