基于小波包信包提取的空调制冷压缩机怠速噪声诊断算法

doi:10.13229/j.cnki.jdxbgxb.20220213

摘要/Abstract

摘要：

针对车辆空调制冷压缩机怠速噪声具有随机性和不确定性，其诊断难度较大的问题，为了及时发现压缩机的异常并提供更加舒适的开车、乘车环境，提出一种基于小波包信包提取的空调制冷压缩机怠速噪声诊断算法。先利用小波包信包提取空调制冷压缩机怠速噪声信号特征，再通过支持向量机（SVM）将空调制冷压缩机怠速噪声信号特征分类，最后根据噪声信号特征分类结果实现空调制冷压缩机怠速噪声的诊断。实验结果表明，本文方法获取的空调制冷压缩机怠速噪声幅值更接近实际怠速噪声幅值，ROC曲线的面积较大，说明该算法对压缩机怠速噪声的诊断结果具有理想的精确度。

关键词: 空调制冷压缩机, 怠速噪声, 小波包信包, 特征提取, 支持向量机

Abstract:

When the vehicle is idling， the large noise of the air conditioning refrigeration compressor is the low-frequency abnormal noise of the compressor. The idle noise of air conditioning refrigeration compressor has randomness and uncertainty， so its diagnosis is difficult. In order to find the compressor abnormality in time and provide a more comfortable driving and riding environment， the idle noise diagnosis algorithm of air conditioning refrigeration compressor based on wavelet packet extraction is studied. The characteristics of idle noise signal of air-conditioning refrigeration compressor are extracted by wavelet packet， and then the characteristics of idle noise signal of air-conditioning refrigeration compressor are classified by support vector machine （SVM）. According to the classification results of noise signal characteristics， the diagnosis of idle speed noise of air conditioning refrigeration compressor is realized. The experimental results show that the idle noise amplitude of air conditioning refrigeration compressor obtained by the proposed method is closer to the actual idle noise amplitude， and the area of ROC curve is large， which shows that the research algorithm has ideal accuracy for the diagnosis result of compressor idle noise.

Key words: air conditioning refrigeration compressor, idle noise, wavelet envelope, feature extraction, support vector machine

中图分类号:

U463.8

龙恩深,班光泽. 基于小波包信包提取的空调制冷压缩机怠速噪声诊断算法[J]. 吉林大学学报(工学版), 2023, 53(7): 1929-1934.

En-shen LONG,Guang-ze BAN. Idle noise diagnosis algorithm of air-conditioning refrigeration compressor based on wavelet packet extraction[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1929-1934.

图/表 6

图1

图2

图3

表1

图4

图5

参考文献 10

1	陶宏, 张婷, 吴生礼, 等. 油循环率对电动汽车空调压缩机性能的影响[J]. 制冷学报,2021,42(6):140-145.
	Tao Hong, Zhang Ting, Wu Sheng-li, et al. Effect of oil circulation rate on the performance of compressor in electric vehicle air-conditioning[J]. Journal of Refrigeration, 2021, 42(6): 140-145.
2	吴小莉, 郑艺峰.基于K近邻算法的噪声种类识别和强度估计[J].计算机应用, 2020, 40(1): 264-270.
	Wu Xiao-li, Zheng Yi-feng. Noise type recognition and intensity estimation based on K-nearest neighbors algorithm[J]. Journal of Computer Applications, 2020, 40(1): 264-270.
3	吴飞, 余神志, 刘苏行, 等.车用制动空气压缩机结构辐射噪声特性研究[J].声学技术, 2021, 40(2): 228-233.
	Wu Fei, Yu Shen-zhi, Liu Su-xing, et al. Simulation and experimental study on the radiation noise characteristics of air compressor structure of vehicle brake[J]. Technical Acoustics, 2021, 40(2): 228-233.
4	李天宇, 蒋伟康, 王海军.滚动转子压缩机排气流噪声数值计算与机理分析[J]. 流体机械, 2021, 49(6): 15-21.
	Li Tian-yu, Jiang Wei-kang, Wang Hai-jun. Numerical computation and mechanism analysis of the aerodynamic noise of rolling piston compressor during exhaust process[J]. Fluid Machinery, 2021, 49(6): 15-21.
5	彭珍瑞, 曹明明, 刘满东.基于加速度频响函数小波分解的模型修正方法[J]. 航空学报, 2020, 41(7): 181-191.
	Peng Zhen-rui, Cao Ming-ming, Liu Man-dong. Model updating method based on wavelet decomposition of acceleration frequency response function[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41(7): 181-191.
6	童力, 刘翰柔, 胡松涛, 等.听觉诱发电位信号分析中小波基函数的确定[J].科学技术与工程, 2021, 21(2): 473-479.
	Tong Li, Liu Han-rou, Hu Song-tao, et al. Determination of wavelet basis function in auditory evoked potential signal analysis[J]. Science Technology and Engineering, 2021, 21(2): 473-479.
7	洪亮, 严世榕. 新能源汽车低频振动噪声传递路径模拟方法[J]. 计算机仿真, 2021, 38(1): 102-106.
	Hong Liang, Yan Shi-rong. Simulation method of low frequency vibration and noise transfer path of new energy vehicles[J]. Computer Simulation, 2021, 38(1): 102-106.
8	刘竞, 郭忠文, 孙中卫, 等. 采用分而治之策略的快速多标签支持向量机分类算法研究[J].中国海洋大学学报: 自然科学版, 2020, 50(12): 160-166.
	Liu Jing, Guo Zhong-wen, Sun Zhong-wei, et al. Research on fast multi-label svm classification algorithm using divide-and-conquer strategy[J]. Periodical of Ocean University of China, 2020, 50(12): 160-166.
9	王俊霞, 申倩影, 王川龙.符号矩阵填充的修正增广拉格朗日乘子算法[J].工程数学学报, 2021, 38(3): 343-352.
	Wang Jun-xia, Shen Qian-ying, Wang Chuan-long. The augmented lagrange multiplier algorithm for sign matrix completion[J]. Chinese Journal of Engineering Mathematics, 2021, 38(3): 343-352.
10	李正平, 白倩倩.一种对称无向图的同构判定算法[J]. 合肥工业大学学报: 自然科学版, 2021, 44(3): 332-336.
	Li Zheng-ping, Bai Qian-qian. An isomorphism identification algorithm for symmetric undirected graphs[J]. Journal of Hefei University of Technology(Natural Science), 2021, 44(3): 332-336.

相关文章 15

[1]	白琳,刘林军,李轩昂,吴沙,刘汝庆. 基于自监督学习的单目图像深度估计算法[J]. 吉林大学学报(工学版), 2023, 53(4): 1139-1145.
[2]	吴剑,许斌. 基于CEEMDAN理论的堆积层滑坡位移区间预测模型及仿真[J]. 吉林大学学报(工学版), 2023, 53(2): 562-568.
[3]	王奎洋,何仁. 基于支持向量机的制动意图识别方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1770-1776.
[4]	周怡娜,董宏丽,张勇,路敬祎. 基于VMD去噪和散布熵的管道信号特征提取方法[J]. 吉林大学学报(工学版), 2022, 52(4): 959-969.
[5]	罗巍,卢博,陈菲,马腾. 基于PSO-SVM及时序环节的数控刀架故障诊断方法[J]. 吉林大学学报(工学版), 2022, 52(2): 392-399.
[6]	李国发,王彦博,何佳龙,王继利. 机电装备健康状态评估研究进展及发展趋势[J]. 吉林大学学报(工学版), 2022, 52(2): 267-279.
[7]	陈晓雷,孙永峰,李策,林冬梅. 基于卷积神经网络和双向长短期记忆的稳定抗噪声滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(2): 296-309.
[8]	杜先君,贾亮亮. 基于优化堆叠降噪自编码器的滚动轴承故障诊断[J]. 吉林大学学报(工学版), 2022, 52(12): 2827-2838.
[9]	戴礼灿,代翔,崔莹,魏永超. 基于深度集成学习的社交网络异常数据挖掘算法[J]. 吉林大学学报(工学版), 2022, 52(11): 2712-2717.
[10]	欧阳宁,李祖锋,林乐平. 基于多层次空⁃谱融合网络的高光谱图像分类[J]. 吉林大学学报(工学版), 2022, 52(10): 2438-2446.
[11]	黎才茂,陈少凡,林成蓉,候玉权,李浩. 基于循环知识图谱的虚拟社区知识动态推荐方法[J]. 吉林大学学报(工学版), 2022, 52(10): 2385-2390.
[12]	刘桂霞,裴志尧,宋佳智. 基于深度学习的蛋白质⁃ATP结合位点预测[J]. 吉林大学学报(工学版), 2022, 52(1): 187-194.
[13]	许鸿奎,姜彤彤,李鑫,姜斌祥,王永雷. 结合降噪自编码与极限学习机的LTE上行干扰分析[J]. 吉林大学学报(工学版), 2022, 52(1): 195-203.
[14]	刘远红,郭攀攀,张彦生,李鑫. 基于黎曼流形的稀疏图保持投影的特征提取[J]. 吉林大学学报(工学版), 2021, 51(6): 2268-2279.
[15]	侯春萍,赵春月,王致芃,田海瑞. 基于有效异常样本构造的视频异常检测算法[J]. 吉林大学学报(工学版), 2021, 51(5): 1823-1829.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

压缩机编号	制冷剂	气缸容积/cm³	制冷量/W	输入功率/W	电机类型	油的粘度
1#	R12	5.6	132	120	YUR	32
2#	R134a	5.8	55	75	RSIR	22
3#	R12	5.9	137	134	RSCR	35