Wear-out Failure Diagnosis of Planetary Gear Tooth Surface based on SIFT_BoW and HIK_SVM
-
摘要: 行星轮齿面磨损故障信号具有特征薄弱、特征量少等缺点,对其进行故障特征识别较为困难。本文中提出一种新的方法:首先,将原始振动加速度信号幅值作为像素点构造灰度图像,检测灰度图像的特征点并对检测出的特征点向量描述;然后将灰度图像的特征描述向量聚类,构建词袋模型;最后用直方图相交核支持向量机算法对其进行分类。该方法不但不需要对原始信号模态分解和降噪处理,还可以提取出大量的信号特征,提高了故障特征识别的效率和准确率。对正常轮齿、2个齿面磨损和3个齿面磨损故障进行了诊断实验,准确率高达98.55%,实验结果验证了所提方法的有效性。Abstract: The vibration signal of planetary gear tooth surface wear-out failure has some disadvantages such as weak feature and little feature quantity. Therefore, it is difficult to identify the wear-out failure feature of planetary gear tooth surface. In order to solve this problem, a new fault diagnosis method is put forward. Firstly, the amplitude of the original vibration acceleration signal is used as pixels to construct a gray-scale image, and the feature points of the gray-scale image are detected and the detected feature point vectors are described. Then, the feature description vectors of the gray-scale image are clustered to construct a bag of words model. Finally, the histogram intersection kernel support vector machine algorithm is used to classify the gray-scale image. This method not only does not need to decompose the original signal and reduce the signal noise, but also can extract a large number of signal features, and improve the efficiency and accuracy of fault feature detection. Experiments were carried out to diagnose the normal gear teeth, fault gears with two tooth surfaces wear and three tooth surfaces wear, and the diagnosis accuracy was up to 98.55%. Experimental results show that the proposed method is effective.
-
Key words:
- planetary gear /
- tooth surfaces wear /
- feature detection /
- vibration acceleration /
- fault diagnosis /
- pixels /
- support vector machine /
- algorithm /
- experiment /
- words bag model
-
表 1 行星齿轮机构齿轮参数
名称 齿数Z 模数m 压力角α 齿宽b 行星轮 27 2 mm 20° 30 mm 太阳轮 18 2 mm 20° 30 mm 齿圈 72 2 mm 20° 30 mm 表 2 3种工况下的故障识别率
故障名称 总个数 正确识别个数 识别率 正常 23 23 100% 2个齿面磨损 23 22 95.65% 3个齿面磨损 23 23 100% -
[1] 郝如江, 安雪君, 史云林.基于EMD和CICA的单通道盲源分离方法用于齿轮箱混合故障诊断研究[J].振动与冲击, 2019, 38(8):225-231, 262 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201908034Hao R J, An X J, Shi Y L. Single-channel blind source separation based on EMD and CICA and its application to gearbox multi-fault diagnosis[J]. Journal of Vibration and Shock, 2019, 38(8):225-231, 262(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201908034 [2] Yu J, Xu Y G, Liu K. Planetary gear fault diagnosis using stacked denoising autoencoder and gated recurrent unit neural network under noisy environment and time-varying rotational speed conditions[J]. Measurement Science and Technology, 2019, 30(9):095003 doi: 10.1088/1361-6501/ab1da0 [3] Li Y Z, Ding K, He G L, et al. Vibration modulation sidebands mechanisms of equally-spaced planetary gear train with a floating sun gear[J]. Mechanical Systems and Signal Processing, 2019, 129:70-90 doi: 10.1016/j.ymssp.2019.04.026 [4] Zheng H, Cheng G, Li Y, et al. A new fault diagnosis method for planetary gear based on image feature extraction and bag-of-words model[J]. Measurement, 2019, 145:1-13 doi: 10.1016/j.measurement.2019.05.046 [5] 张星辉, 康建设, 赵劲松, 等.基于CDA和MoG-BBN的齿轮磨损状态识别研究[J].振动与冲击, 2014, 33(4):70-76, 106 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201404014Zhang X H, Kang J S, Zhao J S, et al. Wear level identification of gears based on CDA and MOG-BBN[J]. Journal of Vibration and Shock, 2014, 33(4):70-76, 106(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdycj201404014 [6] 陈庆.基于LCD基本尺度熵的齿轮故障RVM识别[J].机械强度, 2019, 41(4):828-832 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxqd201904010Chen Q. Gear fault identification of RVM based on LCD base-scale entropy[J]. Journal of Mechanical Strength, 2019, 41(4):828-832(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxqd201904010 [7] 姜宏, 章翔峰, 张小栋.双矢时域齿轮早期微弱故障特征增强及应用[J].振动、测试与诊断, 2018, 38(6):1161-1168, 1291 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdcsyzd201806012Jiang H, Zhang X F, Zhang X D. Gear early weak fault feature enhancement in dual vector time-time domain[J]. Journal of Vibration, Measurement & Diagnosis, 2018, 38(6):1161-1168, 1291(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdcsyzd201806012 [8] Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6d7f4db9dae5b32514309ee242a50f4b [9] 郑永斌, 黄新生, 丰松江.SIFT和旋转不变LBP相结合的图像匹配算法[J].计算机辅助设计与图形学学报, 2010, 22(2):286-292 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201002015Zheng Y B, Huang X S, Feng S J. An image matching algorithm based on combination of SIFT and the rotation invariant LBP[J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(2):286-292(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjfzsjytxxxb201002015 [10] 王晓华, 傅卫平, 梁元月.提高SIFT特征匹配效率的方法研究[J].机械科学与技术, 2009, 28(9):1252-1255, 1260 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxkxyjs200909030Wang X H, Fu W P, Liang Y Y. A method for improving SIFT feature matching efficiency[J]. Mechanical Science and Technology for Aerospace Engineering, 2009, 28(9):1252-1255, 1260(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jxkxyjs200909030 [11] Csurka G, Dance C R, Fan LX, et al. Visual categorization with bags of keypoints[C]//ECCV'04 Workshop on Statistical Learning in Computer Vision. Prague, Czech: 2004: 59-74 [12] Steinley D. K-means clustering:a half-century synthesis[J]. British Journal of Mathematical and Statistical Psychology, 2006, 59(1):1-34 [13] Swain M J, Ballard D H. Color indexing[J]. International Journal of Computer Vision, 1991, 7(1):11-32 http://www.tandfonline.com/servlet/linkout?suffix=CIT0005&dbid=16&doi=10.1080%2F03602550701866808&key=10.1007%2FBF00130487 [14] Wu J X. Efficient HIK SVM learning for image classification[J]. IEEE Transactions on Image Processing, 2012, 21(10):4442-4453 doi: 10.1109/TIP.2012.2207392 [15] 史东承, 贾令尧, 梁超, 等.基于图像空间金字塔SURF-BoW的步态识别[J].计算机工程, 2017, 43(9):270-275 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc201709047Shi D C, Jia L Y, Liang C, et al. Gait recognition based on SURF-BoW of image space pyramid[J]. Computer Engineering, 2017, 43(9):270-275(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=jsjgc201709047