多层次信息融合在铁谱图像磨粒识别中的应用

针对铁谱图像磨粒识别中异类信息综合利用率较低的问题, 提出多层次信息融合的铁谱图像磨粒识别方法。首先, 在铁谱图像二值化分割的基础上进行二值滤波, 结合彩色铁谱图的R、G、B三分量, 实现铁谱图像的彩色滤波。其次, 以实际采集的磨粒图像样本为例, 提取滤波后二值图像的形态特征, 以及滤波后彩色图像的颜色特征; 在特征层利用PCA对异类特征进行维数约简, 并结合SVM和k-fold交叉验证, 实现形态特征和颜色特征的特征层融合; 在决策层将异类特征的SVM概率输出结果作为D-S证据理论的基本概率分配函数, 实现形态特征和颜色特征的决策层融合。通过与形态学滤波结果对比, 验证了本文提出滤波方法的优越性; 其次, 不同层次的信息融合结果表明, 与单独使用颜色特征和形态特征相比, 异类信息融合后可实现优势互补, 有效提高故障磨粒的识别准确率。

Abstract

Aiming at the insufficient utilization of the heterogeneous information in wear particle recognition of ferrographic images, a method for wear particle recognition based on multi-level information fusion was proposed. First, the binary filtering was conducted for the binary segmented ferrograhpic image, and the red, green and blue components of color ferrographic images were extracted to obtain the color filtered ferrographic images. Then, the experimental ferrographic images were collected as processing objects, the morphological features and color features of ferrographic imagesare were extracted from filtered binary images and filtered color images, respectively. PCA was utilized to reduce dimensions, and k-fold cross-validation and Support Vector Machine were combined to fuse different information in feature-level. The probabilistic output of SVM was used as the basic probability assignment of D-S information fusion, and the morphological information and color information were fused in decision-level. The superiority of proposed filtering method was demonstrated by comparing with the morphological filtering results. In addition, the multi-level information fusion results show that, compared with the use of color features and morphological features alone, the fusion of heterogeneous information can achieve complementary advantages and effectively improve the recognition accuracy of the fault wear particles.

参考文献

[1] WU J, MAO J, CAO W,et al.. Characterization of wear-debris group in on-line visual ferrographic images［J］. Proceedings of the Institution of Mechanical Tribology Engineers, Part J: Journal of Engineering. 2014; 228(11):1298-1307.

[2] 张云强, 张培林. 基于半监督局部保持投影的磨粒图像特征降维［J］.中南大学学报(自然科学版), 2015(8):2937-2943.

ZHANG Y Q, ZHANG P L. Feature dimensionality reduction of wear particle images based onsemi-supervised locality preserving projection［J］. Journal of Central South University (Science and Technology), 2015(8):2937-2943. (in Chinese)

[3] XU B, WEN G, ZHANG Z, et al.. Genetic programming-based classification of ferrograph wear particles［C］. International Conference on Ubiquitous Robots and Ambient Intelligence. IEEE, 2016:842-847.

[4] YUAN W, CHIN KS, HUA M,et al.. Shape classification of wear particles by image boundary analysis using machine learning algorithms［J］. Mechanical Systems and Signal Processing.2016; 72-73:346-358.

[5] 张云强, 张培林, 任国全. 简化PCNN在磨粒图像颜色特征提取中的应用［J］. 内燃机工程, 2013, 34(5):69-75.

ZHANG Y Q, ZHANG P L, REN G Q. Application of simplified PCNN in color feature extraction for wear particle images ［J］. Chinese Internal Combustion Engine Engineering, 2013, 34 (5):69-75. (in Chinese)

[6] 杜兴, 张荣庆.基于色彩和纹理特征融合的模糊人脸识别方法［J］. 红外与激光工程, 2014, 43(12): 4192-4197.

DU X, ZHANG R Q. Fusing color and texture features for blurred face recognition ［J］. Infrared and Laser Engineering, 2014, 43(12): 4192-4197. (in Chinese)

[7] XU B, WEN G, ZHANG Z, et al.. Wear particle classification using genetic programming evolved features［J］. Lubrication Science. 2018,1-18.

[8] 马立, 徐次雄, 欧阳航空, 等.基于信息融合实现的激光陀螺调腔检测［J］.光学精密工程,2012, 20(2):1134-1140.

MA L, XU C X, OUYANG H K, et al.. Detection of laser gyro cavity adjustment using information fusion ［J］. Opt. Precision Eng., 2012, 20(2):1134-1140. (in Chinese)

[9] 温广瑞, 徐斌, 张志芬, 等.基于差商的油液监测铁谱图像自适应分割［J］.光学精密工程,2017, 25 (5) :1322-1330.

WEN G R, XU B, ZHANG ZH F, et al.. Adaptive Segmentation Based on Difference Quotient of Ferrographic Images for Oil Monitoring ［J］. Opt. Precision Eng, 2017, 25(5):1322-1330. (in Chinese)

[10] WANG J, WANG X. A wear particle identification method by combining principal component analysis and grey relational analysis［J］. Wear, 2013:304(1-2):96-102.

[11] 刘李, 傅俏燕, 史婷婷,等. MODIS的HJ-1 B红外通道星上定标系数交叉验证［J］. 红外与激光工程, 2014, 43(11):3638-3645.

LIU L, FU Q Y, SHI T T. Cross-validation of HJ-1B infrared channels onboard calibration coefficients using MODIS ［J］. Infrared and LaserEngineering, 2014, 43(11):3638-3645. (in Chinese)

[12] 雷蕾, 王晓丹.结合SVM与DS 证据理论的信息融合分类方法［J］.计算机工程与应用,2013,49(11):114-117.

LEI L, WANG X D, MEI CH. Approach of information fusion and classification by SVM and DS evidence theory ［J］. Computer Engineering and Applications, 2013, 49(11):114-117. (in Chinese)

[13] 徐文晴,王敏. 基于自适应形态学滤波的红外小目标检测算法［J］. 激光与红外, 2017, 47(1):108-113.

XU W Q, WANG M. Infrared small target detection algorithm based on adaptive morphology filter ［J］. Laser& Infrared, 2017, 47(1):108-113.(in Chinese)

[14] 权文, 王晓丹, 王坚.基于SVM 概率输出与证据理论的多分类方法［J］.计算机工程,2012,38(5):167-169.

QUAN W, WANG X D, WANG J. Multi-class classification method based on SVM probability output and evidence theory ［J］. Computer Engineering,2012, 38(5):167-169. (in Chinese)

[15] 弓鹏伟, 费燕琼, 宋立博.基于多传感器信息融合的轮履混合移动机器人路况识别方法［J］. 上海交通大学学报, 2017, 51(4):398-402.

GONG P W,FEI Y J, SONG L B. Road recognition method of wheel-tracked robot based on multi-sensor information fusion ［J］. Journal of Shanghai Jiaotong University, 2017, 51(4):398-402. (in Chinese)

徐斌, 温广瑞, 苏宇, 张志芬, 陈峰, 孙耀宁. 多层次信息融合在铁谱图像磨粒识别中的应用[J]. 光学精密工程, 2018, 26(6): 1551. XU Bin, WEN Guang-rui, SU Yu, ZHANG Zhi-fen, CHEN Feng, SUN Yao-ning. Application of multi-level information fusion for wear particle recognition of ferrographic images[J]. Optics and Precision Engineering, 2018, 26(6): 1551.

多层次信息融合在铁谱图像磨粒识别中的应用

关于本站 Cookie 的使用提示

全站搜索

多层次信息融合在铁谱图像磨粒识别中的应用

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索