大功率碟型激光焊金属蒸汽图像动态特征分析
|
摘要
大功率激光器的出现,开辟了激光焊接新领域,推动了以匙孔效应为理论基础的深熔焊接的发展。作为大功率深熔焊遇到的关键问题之一,光致等离子体的研究受到越来越多的关注。近十几年的研究主要集中在等离子体信息在线监测、特征分析以及控制等方面。虽然已经实现了一定程度的激光焊接自动化,但是由于激光焊接过程是一个非线性、时变和易受干扰的多变量强耦合复杂过程,导致设备的复杂化和检测的困难化,极大地限制了激光焊接的自动化程度与推广进程。
大功率碟型激光焊接过程中形成的等离子体以金属蒸汽为主,金属蒸汽图像的各种特征参数随着激光焊接状态的不同而变化。本文通过高速摄影技术获取大功率碟型激光焊接过程金属蒸汽等离子体的瞬态信息,提出了金属蒸汽彩色图像聚类分割算法以提取光致金属蒸汽的面积、高度、亮度、摆角以及飞溅颗粒的面积等特征参数,结合对焊接样品的检测分析,探索了金属蒸汽图像特征与激光焊接加工质量之间的关系和规律。利用人工神经网络分别建立了基于BP神经网络和RBF神经网络的焊缝宽度预测模型,并将支持向量回归算法引入到焊缝宽度预测模型中,提出了基于支持向量回归的焊缝宽度预测建模方法。通过这一系列的研究工作,取得了如下主要研究成果：
1、探究并分析大功率碟型激光焊接过程金属蒸汽监测试验系统
试验系统主要由激光加工设备和带组合滤光片的高速摄像机组成。设计了10kW的平板堆焊焊接试验方案：在选取不同的焊接速度,且保持其他焊接参数不变的情况下,进行了多组试验,得到了相关金属蒸汽图像数据。
2、提出了金属蒸汽彩色图像聚类分割算法
金属蒸汽的彩色图像比灰度图像蕴含着更为丰富的信息,本文提出了两种基于彩色空间的聚类分割算法,实现了在不同彩色空间中直接对光致金属蒸汽图像进行分割。
(1)针对传统的K-means聚类分割算法在处理光致金属蒸汽图像时,时间复杂度很高,分类性能较差,提出了一种改进的K-means聚类分割算法：引入距离参数d,增强类内中各样本的聚合程度,从而提高分割精度；减少样本集中包含的样本数量,在处理样本集中的样本时,先将背景区域样本过滤,再对前景区域的样本进行分类,从而降低时间复杂度。试验结果表明,改进的K-means聚类分割算法在RGB颜色空间和HSI颜色空间都能有效地提高分割精度,降低时间复杂度。
(2)改进的K-means聚类分割算法的时间复杂度仍然偏高,且初始聚类中心的选择对于聚类结果有较大的影响,因此,引入基于最小错误概率判决准则的概率聚类算法,采用Bayers分类决策模型,将样本X分配到使后验概率最大的聚类中。在概率聚类算法中,类条件概率密度函数定义为样本X到该类聚类中心之间距离的倒数。试验结果表明,两种聚类算法的分割精度相近,但是基于最小错误概率判决准则的概率聚类算法大幅降低了时间复杂度。
3、提取与分析光致金属蒸汽图像特征与焊缝特征
本文定义了光致金属蒸汽图像的各种特征信息(包括金属蒸汽面积、高度、亮度、质心、摆角和飞溅颗粒面积),将其与实际样品的焊接质量(包括焊缝表面特征、熔深、熔宽和深宽比等)进行对比,以期找出光致金属蒸汽图像特征与激光焊接质量之间的联系。这些非线性的特征信息,在很大程度上可以反映出焊接质量的变化,从而反映出焊接过程的稳定性变化情况,为焊接过程的可监控性提供了新的思路。
4、建立基于金属蒸汽图像特征的焊缝宽度预测模型
(1)利用人工神经网络建立焊缝宽度预测模型
现有预测模型中的输入信号(如焊接电流、焊接速度、熔池附近温度)对于焊接过程往往呈现一维性,丢失了信号的空间分布信息,降低了焊接性能预测的可靠性。文中分别建立了基于BP神经网络和基于RBF神经网络的焊缝宽度预测模型,输入为由金属蒸汽图像特征组成的7维特征向量,分别是金属蒸汽面积平均值及其方差、飞溅面积平均值及其方差、金属蒸汽摆角平均值及其方差以及前一个样本的焊缝宽度输出；输出为模型预测的焊缝宽度。试验结果表明,BP模型在焊缝宽度预测方面优于RBF模型,较适合于激光焊接过程中的应用。
(2)引入支持向量回归算法,提出了基于支持向量回归的焊缝宽度预测建模方法
人工神经网络不稳定,过分依赖学习样本,并且大功率碟型激光焊接过程中获取的样本数量有限,本文引入支持向量机方法,建立了基于支持向量回归的焊缝宽度预测模型。该模型的输入层和输出层的设计与BP神经网络模型的输入层和输出层的设计一样。试验结果表明,支持向量机在非线性回归方而的泛化能力强于BP网络,很适合大功率碟型激光焊接过程的样本训练和预测。
The emergence of high-power lasers opened up a new field of laser welding and promoted the development of deep penetration welding based on the keyhole effect. As one of the key issues encountered in high-power deep penetration, laser-induced plasma phenomena has received a lot of attention lately. Over the last decade, the study mainly focused on the on-line monitoring of plasma information, the analysis of its feature, and the control of it. Although a limited degree of automation of laser welding has been achieved in a few laser-processing fields, laser welding process is a complex process with multi-variable, which is non-linear, time-varying and vulnerable to interference. These result in the difficulties in detection and the complexity of the equipment, and greatly limit the automation and promotion of laser welding.
The plasma formed in the high-power disk laser welding process mainly consisted of metal vapor, and characteristics of laser-induced metal vapor image varied with the different state of laser welding. This paper achieved the transient information of the metal vapor during high-power disk laser welding process by high-speed photography, developed color space clustering segmentation algorithms based on metal vapor image to extract the characteristics, including the metal vapor area, height, intensity, swing angle and the spatters area, combined modern detection analysis means of welding samples, and analyzed the relationship between the metal vapor characteristics and the laser welding process quality. Two welded seam width prediction models based on BP and RBF were established respectively. Moreover, a support vector regression algorithm was introduced to predicting the welded seam width, establishing a welded seam width prediction model based on support vector regression. Through these studies, the main achievements are obtained as following:
1. Exploration and analysis of metal vapor monitoring experimental system during the high-power disk laser welding process
The experimental system was composed of the laser processing equipment and a high-speed camera with a combination filter. A scheme for10kW bead-on-plate disk laser welding was designed. We carried out several groups of experiment at different welding speed, while other welding parameters maintained the same, and got corresponding image sequences.
2. The proposing of color space clustering segmentation algorithm based on metal vapor image
Metal vapor color images contained more information than the gray images. Two clustering image segmentation algorithm based on color space were proposed in the paper, achieving the segmentation of the metal vapor image in color space directly.
(1) Because the traditional clustering segmentation algorithm based on K-means was of high time complexity and poor classification performance when processing the metal vapor images, an improved segmentation algorithm based on K-means was proposed. On the one hand, introduce of the distance parameter d to enhance the cohesion of each sample within a class, in order to improve the accuracy of segmentation. On the other hand, reduce the number of samples. When processing samples, first filter the samples which were in the background region, and then classify the samples in foreground region, in order to reduce the time complexity. The experimental results showed that the improved segmentation algorithm can effectively improve the accuracy of segmentation, and decrease the time complexity.
(2) However, the time complexity of the improved segmentation algorithm based on K-means was still high, and the selection of the initial cluster centers greatly impacted on the clustering results. Therefore, a probabilistic clustering method based on minimum error probability criterion was applied. It adopted Bayers model, which assigned the sample X to the cluster of the largest posterior probability. In the algorithm, the class conditional probability density function was defined as the reciprocal of the distance between sample X and the cluster center. The experimental results showed that the accuracy of segmentation of both algorithms were high, but the probability clustering method greatly decreased the time complexity.
3. Extraction and analysis of the characteristics of the laser-induced metal vapor image and the welded seam
Characteristics of the laser-induced metal vapor image, including the area, height, intensity, centroid, swing angle of metal vapor and the area of spatters, were extracted. These characteristics were analyzed combined with the welding quality, including the surface characteristics of the weld seam, the bead width, the weld penetration and the depth-to-width ratio, in order to find the relationship between the laser-induced metal vapor and the welding quality. The changes of the welding quality can be reflected by these nonlinear factors together, which reflected the stability of the welding process, and provided a new way of online monitoring of welding process.
4. The establishment of welded seam width prediction models based on metal vapor image features
(1) The establishment of welded seam width prediction models based on artificial neural networks
The input signals in the existing models, such as welding current, temperature near the molten pool, welding speed, presented one-dimensional for the welding process, and lost the spatial distribution information of the signals, which reduced the reliability of the welding quality prediction. Welded seam width prediction models based on BP and RBF were established respectively. The input layer was a7-dimension feature vector composed of metal vapor image features, including the average area value of metal vapor and its variance, the average area value of spatters and its variance, the average swing angle value of metal vapor and its variance, and the welded seam width output of the previous sample. The output layer is the welded seam width. The experimental results showed that the model based on BP was better than the model based on RBF, and was suitable for the laser welding process.
(2) The introduction of support vector regression algorithm to establish a welded seam width prediction model based on support vector regression
Neural network was instable, over reliant on the learning samples, and the numbers of samples obtained in the laser welding process were limited. The support vector machine method was introduced in the paper, establishing a welded seam width prediction model based on support vector regression. The experimental results showed that the support vector machine's generalization ability is stronger than BP network in nonlinear regression, and the support vector machine method is suitable for high-power disk laser welding process.
大功率碟型激光焊接过程中形成的等离子体以金属蒸汽为主,金属蒸汽图像的各种特征参数随着激光焊接状态的不同而变化。本文通过高速摄影技术获取大功率碟型激光焊接过程金属蒸汽等离子体的瞬态信息,提出了金属蒸汽彩色图像聚类分割算法以提取光致金属蒸汽的面积、高度、亮度、摆角以及飞溅颗粒的面积等特征参数,结合对焊接样品的检测分析,探索了金属蒸汽图像特征与激光焊接加工质量之间的关系和规律。利用人工神经网络分别建立了基于BP神经网络和RBF神经网络的焊缝宽度预测模型,并将支持向量回归算法引入到焊缝宽度预测模型中,提出了基于支持向量回归的焊缝宽度预测建模方法。通过这一系列的研究工作,取得了如下主要研究成果：
1、探究并分析大功率碟型激光焊接过程金属蒸汽监测试验系统
试验系统主要由激光加工设备和带组合滤光片的高速摄像机组成。设计了10kW的平板堆焊焊接试验方案：在选取不同的焊接速度,且保持其他焊接参数不变的情况下,进行了多组试验,得到了相关金属蒸汽图像数据。
2、提出了金属蒸汽彩色图像聚类分割算法
金属蒸汽的彩色图像比灰度图像蕴含着更为丰富的信息,本文提出了两种基于彩色空间的聚类分割算法,实现了在不同彩色空间中直接对光致金属蒸汽图像进行分割。
(1)针对传统的K-means聚类分割算法在处理光致金属蒸汽图像时,时间复杂度很高,分类性能较差,提出了一种改进的K-means聚类分割算法：引入距离参数d,增强类内中各样本的聚合程度,从而提高分割精度；减少样本集中包含的样本数量,在处理样本集中的样本时,先将背景区域样本过滤,再对前景区域的样本进行分类,从而降低时间复杂度。试验结果表明,改进的K-means聚类分割算法在RGB颜色空间和HSI颜色空间都能有效地提高分割精度,降低时间复杂度。
(2)改进的K-means聚类分割算法的时间复杂度仍然偏高,且初始聚类中心的选择对于聚类结果有较大的影响,因此,引入基于最小错误概率判决准则的概率聚类算法,采用Bayers分类决策模型,将样本X分配到使后验概率最大的聚类中。在概率聚类算法中,类条件概率密度函数定义为样本X到该类聚类中心之间距离的倒数。试验结果表明,两种聚类算法的分割精度相近,但是基于最小错误概率判决准则的概率聚类算法大幅降低了时间复杂度。
3、提取与分析光致金属蒸汽图像特征与焊缝特征
本文定义了光致金属蒸汽图像的各种特征信息(包括金属蒸汽面积、高度、亮度、质心、摆角和飞溅颗粒面积),将其与实际样品的焊接质量(包括焊缝表面特征、熔深、熔宽和深宽比等)进行对比,以期找出光致金属蒸汽图像特征与激光焊接质量之间的联系。这些非线性的特征信息,在很大程度上可以反映出焊接质量的变化,从而反映出焊接过程的稳定性变化情况,为焊接过程的可监控性提供了新的思路。
4、建立基于金属蒸汽图像特征的焊缝宽度预测模型
(1)利用人工神经网络建立焊缝宽度预测模型
现有预测模型中的输入信号(如焊接电流、焊接速度、熔池附近温度)对于焊接过程往往呈现一维性,丢失了信号的空间分布信息,降低了焊接性能预测的可靠性。文中分别建立了基于BP神经网络和基于RBF神经网络的焊缝宽度预测模型,输入为由金属蒸汽图像特征组成的7维特征向量,分别是金属蒸汽面积平均值及其方差、飞溅面积平均值及其方差、金属蒸汽摆角平均值及其方差以及前一个样本的焊缝宽度输出；输出为模型预测的焊缝宽度。试验结果表明,BP模型在焊缝宽度预测方面优于RBF模型,较适合于激光焊接过程中的应用。
(2)引入支持向量回归算法,提出了基于支持向量回归的焊缝宽度预测建模方法
人工神经网络不稳定,过分依赖学习样本,并且大功率碟型激光焊接过程中获取的样本数量有限,本文引入支持向量机方法,建立了基于支持向量回归的焊缝宽度预测模型。该模型的输入层和输出层的设计与BP神经网络模型的输入层和输出层的设计一样。试验结果表明,支持向量机在非线性回归方而的泛化能力强于BP网络,很适合大功率碟型激光焊接过程的样本训练和预测。
The emergence of high-power lasers opened up a new field of laser welding and promoted the development of deep penetration welding based on the keyhole effect. As one of the key issues encountered in high-power deep penetration, laser-induced plasma phenomena has received a lot of attention lately. Over the last decade, the study mainly focused on the on-line monitoring of plasma information, the analysis of its feature, and the control of it. Although a limited degree of automation of laser welding has been achieved in a few laser-processing fields, laser welding process is a complex process with multi-variable, which is non-linear, time-varying and vulnerable to interference. These result in the difficulties in detection and the complexity of the equipment, and greatly limit the automation and promotion of laser welding.
The plasma formed in the high-power disk laser welding process mainly consisted of metal vapor, and characteristics of laser-induced metal vapor image varied with the different state of laser welding. This paper achieved the transient information of the metal vapor during high-power disk laser welding process by high-speed photography, developed color space clustering segmentation algorithms based on metal vapor image to extract the characteristics, including the metal vapor area, height, intensity, swing angle and the spatters area, combined modern detection analysis means of welding samples, and analyzed the relationship between the metal vapor characteristics and the laser welding process quality. Two welded seam width prediction models based on BP and RBF were established respectively. Moreover, a support vector regression algorithm was introduced to predicting the welded seam width, establishing a welded seam width prediction model based on support vector regression. Through these studies, the main achievements are obtained as following:
1. Exploration and analysis of metal vapor monitoring experimental system during the high-power disk laser welding process
The experimental system was composed of the laser processing equipment and a high-speed camera with a combination filter. A scheme for10kW bead-on-plate disk laser welding was designed. We carried out several groups of experiment at different welding speed, while other welding parameters maintained the same, and got corresponding image sequences.
2. The proposing of color space clustering segmentation algorithm based on metal vapor image
Metal vapor color images contained more information than the gray images. Two clustering image segmentation algorithm based on color space were proposed in the paper, achieving the segmentation of the metal vapor image in color space directly.
(1) Because the traditional clustering segmentation algorithm based on K-means was of high time complexity and poor classification performance when processing the metal vapor images, an improved segmentation algorithm based on K-means was proposed. On the one hand, introduce of the distance parameter d to enhance the cohesion of each sample within a class, in order to improve the accuracy of segmentation. On the other hand, reduce the number of samples. When processing samples, first filter the samples which were in the background region, and then classify the samples in foreground region, in order to reduce the time complexity. The experimental results showed that the improved segmentation algorithm can effectively improve the accuracy of segmentation, and decrease the time complexity.
(2) However, the time complexity of the improved segmentation algorithm based on K-means was still high, and the selection of the initial cluster centers greatly impacted on the clustering results. Therefore, a probabilistic clustering method based on minimum error probability criterion was applied. It adopted Bayers model, which assigned the sample X to the cluster of the largest posterior probability. In the algorithm, the class conditional probability density function was defined as the reciprocal of the distance between sample X and the cluster center. The experimental results showed that the accuracy of segmentation of both algorithms were high, but the probability clustering method greatly decreased the time complexity.
3. Extraction and analysis of the characteristics of the laser-induced metal vapor image and the welded seam
Characteristics of the laser-induced metal vapor image, including the area, height, intensity, centroid, swing angle of metal vapor and the area of spatters, were extracted. These characteristics were analyzed combined with the welding quality, including the surface characteristics of the weld seam, the bead width, the weld penetration and the depth-to-width ratio, in order to find the relationship between the laser-induced metal vapor and the welding quality. The changes of the welding quality can be reflected by these nonlinear factors together, which reflected the stability of the welding process, and provided a new way of online monitoring of welding process.
4. The establishment of welded seam width prediction models based on metal vapor image features
(1) The establishment of welded seam width prediction models based on artificial neural networks
The input signals in the existing models, such as welding current, temperature near the molten pool, welding speed, presented one-dimensional for the welding process, and lost the spatial distribution information of the signals, which reduced the reliability of the welding quality prediction. Welded seam width prediction models based on BP and RBF were established respectively. The input layer was a7-dimension feature vector composed of metal vapor image features, including the average area value of metal vapor and its variance, the average area value of spatters and its variance, the average swing angle value of metal vapor and its variance, and the welded seam width output of the previous sample. The output layer is the welded seam width. The experimental results showed that the model based on BP was better than the model based on RBF, and was suitable for the laser welding process.
(2) The introduction of support vector regression algorithm to establish a welded seam width prediction model based on support vector regression
Neural network was instable, over reliant on the learning samples, and the numbers of samples obtained in the laser welding process were limited. The support vector machine method was introduced in the paper, establishing a welded seam width prediction model based on support vector regression. The experimental results showed that the support vector machine's generalization ability is stronger than BP network in nonlinear regression, and the support vector machine method is suitable for high-power disk laser welding process.
引文
[1]张永康.激光加工技术[M].北京：化学工业出版社工业装备与信息工程出版社,2004.
[2]W. M. Steen. Laser Material Processing[M]. London:Springer-Verlag London Limited, 2003.
[3]Y. B. Chen, Z. L. Lei, L. Q. Li, et al. Experimental study on welding characteristics of CO2 laser TIG hybrid welding proeess[J]. Science and Technology of Welding and Joining,2006, 11(4):403-411.
[4]M. Gao, X. Y. Zeng, Q. W. Hu. Effects of welding parameters on melting energy of CO2 laser-GMA hybrid welding[J]. Science and Technology of Welding and Joining, 2006, 11(5):517-522.
[5]陈彦宾.现代激光焊接技术[M].北京：科学出版社,2005.
[6]刘金合.高能密度焊[M].西安：西北工业大学出版社,1995.
[7]http://www.laserfair.com/a/hj/20111104/10085.html[EB/OL].
[8]葛袁静,张广秋,陈强.等离子体科学技术及其在工业中的应用[M].北京：中国轻工业出版社,2011.
[9]赵青,刘述章,童洪辉.等离子体技术及应用[M].长沙：国防工业出版社,2009.
[10]M. Aden, E. W. Kreutz, A. Voss. Laser-induced plasma formation during pulsed laser deposition[J]. Journal of Physics. D:Applied Physics,1993(26):1545-1553.
[11]L. Li, D. J. Brookfield, W.M. Steen. Plasma charge sensor for in-process, non-contact monitoring of the laser welding process[J]. Measurement Science and Technology, 1996,7(4):615-626.
[12]郑春开.等离子体物理[M].北京：北京大学出版社,2009.
[13]T. Sibillano, A. Ancona, V. Berardi, et al. A study of the shielding gas influence on the laser beam welding of AA5083 aluminium alloys by in-process spectroscopic investigation [J]. Optics and Lasers in Engineering,2006,44(10):1039-1051.
[14]T. Sibillano, A. Ancona, V. Berardi, et al. Correlation analysis in laser welding plasma[J]. Optics Communications,2005,251(1-3):139-148.
[15]T. Sibillano, A. Ancona, V. Berardi, et al. Optical detection of conduction/keyhole mode transition in laser welding[J]. Journal of Materials Processing Technology,2007, 191(1):364-367.
[16]T. Sibillano, A. Ancona, V. Berardi, et al. Real-time monitoring of laser welding by correlation analysis:The case of AA5083[J]. Optics and Lasers in Engineering,2007, 45(10):1005-1009.
[17]G. H. Li, Y. Cai, Y. X. Wu. Stability information in plasma image of high-power CO2 laser welding[J]. Optics and Lasers in Engineering,2009,47(9):990-994.
[18]M. Gao, X. Y. Zeng, Q. W. Hu. Effects of gas shielding parameters on weld penetration of CO2 laser-TIG hybrid welding[J]. Journal of Materials Processing Technology,2007, 184(1-3):177-183.
[19]M. Hamadou, R. Fabbro, G. Caillibotte. Effect of gas shielding delivery mode on high power CO2 laser welding[C]. Proceedings of ICALEO 2004, LaserWelding and Brazing,2004,10:171-180.
[20]L. M. Liu, G. Song, M. L. Zhu. Low-Power Laser/Arc Hybrid Welding Behavior in AZ-Based Mg Alloys[J]. Metallurgical and Materials Transactions A,2008, 39(7):1702-1711.
[21]H. Wang, Y. W. Shi, S. L. Gong, et al. Effect of assist gas flow on the gas shielding during laser deep penetration welding[J]. Journal of Materials Processing Technology, 2007,184(1-3):379-385.
[22]J. W. Kwon, O. Kwon, Y. G. Jang, et al. Development of neural network based plasma monitoring system for laser welding quality analysis[C]. Proceedings of the IEEE Region 10 Conference,1999(1):678-681.
[23]王春明,胡伦骥,胡席远.非穿透激光焊等离子体光信号与熔深的关系[J].激光技术,2006,30(1)：23-26.
[24]王春明,余福林,段爱琴.非穿透激光深熔焊熔深与等离子体光信号的关系[J].焊接学报,2002,23(5)：45-48.
[25]高向东,龙观富,汪润林等人.大功率盘型激光焊飞溅特征分析[J].物理学报,2012,61(9)：098103-1-8.
[26]高向东,汪润林,龙观富等人.盘型激光焊金属蒸汽特征色调-色饱和度-亮度分析法研究[J].物理学报,2012,61(14)：148103-8.
[27]祁俊峰,丁鹏,张冬云.工艺参数对铝合金C02激光焊接光致等离子体温度的影响[J].焊接学报,2008,29(6)：97-100.
[28]刘金合,朱石刚.C02激光焊接等离子体高速摄影照片图像处理[J].应用激光,2002,22(3)：342-344.
[29]陈根余,赵智,张屹等.激光焊接等离子体温度场测量及数据处理[J].中国激光, 2008,35(11)：1778-1782.
[30]刘博生,王睿,段爱琴.激光深熔焊等离子光焰图像信息提取的研究[J].影像技术,2006,(1)：24-27.
[31]赵良磊,唐卓,李国华.等离子体在大功率激光深熔焊中的作用及其影响因素的分析[J].应用激光,2007,27(5)：357-361.
[32]H. Luo, H. Zeng, L. J. Hu, et al. Application of artificial neural network in laser welding defect diagnosis[J]. Journal of Materials Processing Technology,2005, 170(1-2):403-411.
[33]刘京雷,陈彦宾,徐庆鸿.激光焊接声信号与熔深的相关性[J].焊接学报,2006,27(1)：72-75.
[34]Z. Y. Li, W. Wang, X. Y. Wang, et al. A study of the radiation of a Nd:YAG laser-MIG hybrid plasma[J]. Optics and Laser Technology,2010,42(1):132-140.
[35]姜平,陈武柱.激光焊接时等离子体电流的产生机制及其数学模型[J].中国激光,2002,29(5)：471-474.
[36]N. Seto, S. J. Katayama, M. Mizutanit, et al. Relationship between plasma and keyhole behavior during CO2 laser welding[C]. Proceeding of SPIE:High-Power Lasers Manufacturing,2000(3888):61-68.
[37]陈明,马跃洲,陈光.X射线线阵实时成像焊缝缺陷检测方法[J].焊接学报,2007,28(6)：81-84.
[38]M. Zhou, W. Z. Liu, L. Wan. Multi-information Fusion and Identification System for Laser Welding[C]. Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks,2009(5551):986-992.
[39]H, Park, S. Rhee, D. Kim. A fuzzy pattern recognition based system for monitoring laser weld quality[J]. Measurement Science and Technology,2001,12(8):1381-1324.
[40]H. Park, S. Rhee. Real time estimation of CO2 laser weld quality for automotive industry[J]. Optical & Laser Technology,2002,34(2):134-142.
[41]S. S. Rodil, R. A. Gomez, J. M. Bernardez, et al. Laser welding defects detection in automotive industry based on radiation and spectroscopical measurements[J]. International Journal of Advanced Manufacturing Technology,2010,49(1-4):133-145.
[42]段爱琴,陈俐,王亚军.CO2激光焊接不锈钢光致等离子体动态特性分析[J].焊接学报,2005,26(11)：17-20.
[43]骆红,胡伦骥,黄树槐等.激光焊接过程中小孔行为对光、声的影响[J].中国机械工程,1998,9(11)：84-85.
[44]G. Tani, A. Ascari, G. Campana, et al. A study on shielding gas contamination in laser welding of non-ferrous alloys[J]. Applied Surface Science,2007,254(4):904-907.
[45]G. Tani, L. Tomesani, G. Campana, et al. Evaluation of molten pool geometry with induced plasma plume absorption in laser-material interaction zone[J]. International Journal of Machine Tools & Manufacture,2007,47(6):971-977.
[46]U. Stute, R. Kling, J. Hermsdorf. Interaction between Electrical Arc and Nd:YAG Laser Radiation[J]. Annals of the CIRP:Manufacturing Technology,2007, 56(1):197-200.
[47]J. Mark, F. A. Hamprecht. Principal Component Imagery for the Quality Monitoring of Dynamic Laser Welding Processes[J]. IEEE Transactions on Industrial Electronics, 2009,56(4):1307-1313.
[48]Z. G. Gao, Y. X. Wu, J. Huang. Analysis of weld pool dynamic during stationary laser-MIG hybrid welding[J]. International Journal of Advanced Manufacturing Technology,2009,44(9-10):870-879.
[49]D. Naso, B. Turchiano, P. Pantaleo. A fuzzy-logic based optical sensor for online weld defect-detection[J]. IEEE Transactions on Industrial Information,2009, 1(4):259-273.
[50]C. Bertrand, O. Laplanche, J. P. Rocca, et al. Effect of the combination of different welding parameters on melting characteristics of grade 1 titanium with a pulsed Nd-Yag laser[J]. Lasers in Medical Science,2007,22(4):237-244.
[51]M. Farid, P. A. Molian. High-brightness laser welding of thin-sheet 316 stainless steel[J]. Journal of Materials Science,2000,35(15):3817-3826.
[52]Y. M. Zhang, S. B. Zhang, Y. C. Liu. A plasma cloud charge sensor for pulse keyhole process control[J]. Measurment Science & Technology,2001,12(8):1365-1370.
[53]胡昌奎,陈培锋,黄涛.激光深熔焊接光致等离子体行为及控制技术[J].中国激光,2003,24(5)：78-80.
[54]游德勇,高向东.激光焊接技术的研究现状与展望[J].焊接技术,2008,37(4)：5-9.
[55]齐秀滨.激光焊接过程视觉传感技术的发展现状[J].焊接学报,2008,29(2)：108-112.
[56]曾浩,周祖德,陈幼平.激光焊接质量实时检测和控制的进展[J].激光杂志,2000,21(1)：2-5.
[57]刘锟,刘金合,周畅.激光深熔焊接光致等离子体的控制[J].热加工工艺,2007,36(23)：86-88.
[58]高世一,吴瑞珉,陈卫东.激光焊接过程监测及焊缝质量检测技术研究现状[J].世界钢铁,2010,(3)：51-54.
[59]C. Kim, J. Kim, H. Lim, et al. Investigation of laser remote welding using disc laser[J]. Journal of Materials Processing Technology,2008,201:521-525.
[60]何煦辉.碟片激光器及其在工业中的应用[J].激光与光电子学进展,2009,46(7)：64-66.
[61]http://www.cn.trumpf.com/produkte/lasertechnik/laser-und-lasersysteme-fuer-die-mate rialbearbeitung/festkoerperlaser/scheibenlaser/trudisk.html[EB/OL].
[62]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报,2001,46(3)：178-190.
[63]章毓晋.图像处理和分析教程[M].北京：人民邮电出版社,2009.
[64]V. R. Chary, D. R. Lakshmi, K. V. N. Sunitha. Feature extraction methods for color image similarity[J]. Advanced Computing:An International Journal,2012, 3(2):147-157.
[65]T. Q. Chen, Y. Lu. Color image segmentation—An innovative approach[J]. Pattern Recognition,2002,35(2):395-405.
[66]D. H. Cheng, X. H. Jiang, Y. Sun, et al. Color image segmentation:advances and prospects[J]. Pattern Recognition,2001,34 (12):2259-2281.
[67]R. C. Gonzalez, R. E. Woods, S. L. Eddins. Digital Image Processing Using Matlab[M]. New Jersey:Pearson Education,2004.
[68]L. Bonsiepen, W. Coy. Stable segmentation using color information[C]. Proc.4th Int. Conference on Computer Analysis of Image and Patterns,1991:77-84.
[69]S. A, Underwood, J. K. Aggarwal. Interactive computer analysis of aerial color infrared photographs [J]. Computer Graphics and Image Processing,1977,6 (1):1-24.
[70]李冠林,马占鸿,黄冲等.基于K_means硬聚类算法的葡萄病害彩色图像分割方法[J].农业工程学报,2010,26(2)：32-36.
[71]X. Y. Wang, X. J. Zhang, H. Y. Yang, et al. A pixel-based color image segmentation using support vector machine and fuzzy C-means[J]. Neural Networks,2012, 33:148-159.
[72]S. A. Naji, R. Zainuddin, H. A. Jalab. Skin segmentation based on multi pixel color clustering models[J]. Digital Signal Processing,2012,22(6):933-940.
[73]F. Y. Shih, S. X. Cheng. Automatic seeded region growing for color image segmentation[J]. Image & Vision Computing,2005,23(10):877-886.
[74]C. C. Kang, W. J. Wang, C. H. Kang. Image segmentation with complicated background by using seeded region growing[J]. International Journal of Electronics and Communications,2012,66(9):767-771.
[75]K. L. Chung, W. J. Yang, W. M. Yan. Efficient edge-preserving algorithm for color contrast enhancement with application to color image segmentation[J]. Journal of Visual Communication and Image Representation,2008,19(5):299-310.
[76]H. Z. Wang, J. Oliensisb. Generalizing edge detection to contour detection for image segmentation[J]. Computer Vision and Image Understanding,2010,114(7):731-744.
[77]黄玉明,徐光祐,叶培建.基于物理模型的彩色图像分割[J].自动化学报,1992,18(4)：421-428.
[78]A. Kochan, M. Abidi. Digital Color Image Processing[M]. New York:Wiley,2009.
[79]W. K. Pratt. Digital Image Processing[M]. New York:Wiley,2007.
[80]H. D. Cheng, X. H. Jiang, Y. Sun, et al. Color image segmentation advances and prospects[J]. Pattern Recognition,2001,34(12):2259-2281.
[81]J. Gauch, C. W. Hsia. A comparison of three color image segmentation algorithm in four color spaces[C]. SPIE Visual Communications and Image Processing, 1992(1818):1168-1181.
[82]林开颜,吴军辉,徐立鸿.彩色图像分割方法综述[J].中国图象图形学报,2005,10(1)：1-10.
[83]M. Taghizadeh, A. A. Gowen, C. P. O'Donnell. Comparison of hyperspectral imaging with conventional RGB imaging for quality evaluation of Agaricus bisporus mushrooms[J]. Biosystems Engineering,2011,108(2):191-194.
[84]陆启韶,周梦,高宗升.现代数学基础(第二版)[M].北京：北京航空航天大学出版社,2005.
[85]李贵俊,刘正熙,游志胜等.一种基于色差和彩色归一化的车身颜色识别算法[J].计算机应用,2004,24(9)：47-49.
[86]田杰,吕建新,周晓娟等.位图的图像处理技术[J].现代电子技术,2001,(9)：28-30.
[87]贾秋菊,王小铭.一种动态切分的颜色量化算法[J].华南师范大学学报(自然科学版),2005,(1)：46-49.
[88]D. Androutsos, A. N. Venetsanopoulos, K. N. Plataniotis. Novel vector-based approach to color image retrieval using a vector angular-based distance measure[J]. Computer vision and image understanding,1999,75(1):46-58.
[89]D. Androutsos, A. N. Venetsanopoulos, K. N. Plataniotis. Vector angular distance measure for indexing and retrieval of color[C]. SPIE,1999(3656):604-612.
[90]D. C. Tseng, C. H. Chang. Color segmentation using perceptual attributes[C]. Proc. 11th Int. Conference on Pattern Recognition,1992(3):228-231.
[91]汪增福.模式识别[M].合肥：中国科学技术大学出版社,2010.
[92]边肇棋,张学工.模式识别(第二版)[M].北京：清华大学出版社,2007.
[93]盛立东.模式识别导论[M].北京：北京邮电大学出版社,2010.
[94]S. Theodoridis, K. Koutroumbas. Pattern Recognition(Third Edition)[M]. Amsterdam: Elsevier,2006.
[95]K. N. Plataniotis, A. N. Venetsanopoulos. Color image processing and applications[M]. Berlin:Springer,2000.
[96]S. Beyer, K. Behler, G. Herziger. Influence of laser beam polarization in welding[C]. Industrial Laser Annual Hand-book. Tulsa:Penwell Books,1990:157-160.
[97]W. Chen, P.Ackerson, P. Molian. CO2 laser welding of galvanized steel sheets using vent holes[J]. Materials & Design,2009,30(2):245-251.
[98]Y. Kawahito, N. Matsumoto, M. Mizutani, S. Katayama. Characterisation of plasma induced during high power fibre laser welding of stainless steel[J]. Science and Technology of Welding and Joining,2008,13(8):744-748.
[99]T. M. Mitchell. Machine Learning[M]. New York:McGraw-Hill,1997.
[100]E. Mjolsness, D. Decoste. Machine learning for science:State of the art and future prospects[J]. Science,2001,293(5537):2051-2055.
[101]V. Cherkassky, F. Mulier. Vapnik-Chervonenkis(VC) learning theory and its applications[J]. IEEE Transactions on Neural Networks,1999,10(5):985-987.
[102]张青贵.人工神经网络导论[M].北京：中国水利水电出版社,2004.
[103]史忠植.神经网络[M].北京：高等教育出版社,2009.
[104]S. Haykin.神经网络原理[M].北京：机械工业出版社,2004.
[105]S. Haykin. Neural Networks and Learning Machines, Third Edition[M]. New Jersey: Pearson Education,2008.
[106]S. Kumar. Neural Networks(影印版)[M].北京：清华大学出版社,2006.
[107]赵熹华,王宸煜,张若冰等.点焊工艺设计智能混合系统研究[J].焊接,2000,11(3)：11-13.
[108]罗怡,伍光凤,李春天.C02焊接工艺参数优化的人工神经网络设计[J].热加工工艺,2008,37(5)：93-95.
[109]董志波,魏艳红,占小红等.遗传算法与神经网络结合优化焊接接头力学性能预测模型[J].焊接学报,2007,28(12)：69-72.
[110]于秀萍,孙华,赵希人等.基于人工神经网络的焊缝宽度预测[J].焊接学报,2005,26(5)：17-19.
[111]张永志,董俊慧,张艳飞等.基于径向基神经网络焊接接头力学性能预测[J].焊接学报,2008,29(7)：81-84.
[112]方平,张勇,谭义明.人工神经网络电阻点焊质量监测模型的研究[J].机械科学与技术,2000,19(1)：130-132.
[113]C. C. Sheng, C. H. Li. A fuzzy radial basis function neural network for predicting multiple quality characteristics of plasma arc welding[C]. IFSA World Congress and 20th NAFIPS International Conference,2001:2812-2818.
[114]韩力群.人工神经网络教程[M].北京：北京邮电大学出版社,2006.
[115]张雨浓,杨逸文,李巍.神经网络权值直接确定法[M].广州：中山大学出版社,2010.
[116]V. N. Vapnik, S. E. Golowich, A. J. Smola. Support vector method for function approximation, regression estimation and signal processing[J]. In Advances in Neural Information Processing Systems,1996,9:281-287.
[117]J. Christopher, C. Burges. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery,1998,2(2):1-43.
[118]X. X. Huang, S. B. Chen. SVM-based fuzzy modeling for the arc welding process[J]. Materials Science and Engineering:A,2006,427(1-2):181-187.
[119]D. H. Lim, I. H. Bae, M. G. Na, et al. Prediction of residual stress in the welding zone of dissimilar metals using data-based models and uncertainty analysis[J]. Nuclear Engineering and Design,2008,240(10):2555-2564.
[120]M. G. Na, J. W. Kim, D. H. Lim, et al. Residual stress prediction of dissimilar metals welding at NPPs using support vector regression[J]. Nuclear Engineering and Design, 2008,238(7):1503-1510.
[121]张朴,万磊,孔力.基于支持向量机的激光焊接过程质量监测[J].华中科技大学学报(自然科学版),2007,35(7)：62-63.
[122]张晓光,肖应明,任世锦等.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报(自然科学版),2005,(5)：644-648.
[123]阎威武,常俊林,邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究[J].控制与决策,2004,19(5)：525-528.
[124]N. Cristianini. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge:MIT Press,1999.
[125]M. Aizerman, E. Braverman, L. Rozonoer. Theoretical foundations of the potential function method in pattern recognition learning[J]. Automation and Remote Control, 1964,25:821-837.
[126]T. Poggio, F. Girosi. Networks for approximation and learning[C]. Proceedings of the IEEE,1990,78(9):1481-1497.
[127]B. Scholkopf, C. Burges, A. J. Smola. Advances in Kernel Methods-Support Vector Learning [M]. Cambridge:MIT Press,1999.
[128]S. Amari, S.Wu. Improving support vetor machine classifiers by modifying kernel functions[J]. Neural Networks,1999,12(6):783-789.
[129]T. S. Jaakkola, D. Haussler. Exploiting generative models in discriminative classifiers[C]. In Proc. of Tenth Conference on Advances in Neural Information Processing Systems, MIT Press,1998:487-493.
[130]V. N. Vapnik. The nature of statistical learning theory[M]. New York:Springer-Verlag, 1995.
[131]V. N. Vapnik. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks,1999,10(5):988-999.
[132]V. Cherkassky, M. Yunqian. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Networks,2004,17(1):113-126.
[133]A. Smola, N. Murata, B. Scholkopf, et al. Asymptotically optimal choice of ε-loss for support vector machines[C]. Proceedings of the 8th International Conference on Artificial Neural Networks, Perspectives in Neural Computing,1998:105-110.
[134]J. T. Kwok. Linear dependency between ε and the input noise in s-support vector regression[C]. ICANN2001,2001:405-410.
[135]B. Samanta, K. R. Al-Balushi, S. A. Al-Araimi. Artificial neural networks and support vetor machines with genetic algorithm for bearing fault detection[J]. Engineering Applications of Artificial Intelligence,2003,16(7,8):657-665.
[136]B. Baesens, S. Viaene, T. V. Gestel, et al. An empirical assessment of kernel type performance for least squares support vector machine classifiers[C]. Proceedings of 4th Int Conf on Knowledge-based Intelligent Engineering Systems and Allied Technologies. Brighton, UK:IEEE,2000(1):313-316.
[137]王兴玲,李占斌.基于网格搜索的支持向量机核函数参数的确定[J].中国海洋大学学报,2005,5：859-862.
[138]S. Keerthi. Efficient tuning of SVM hyperparameters using margin bound and iterative algorithms[J]. IEEE Trans On Neural Networks,2002,13(5):1225-1229.
[139]O. Chapelle, V. Vapnik, O. Bacsquest, et al. Choosing multiple parameters for support vector machines[J]. Machine Learning,2002,46(1):131-159.
[140]S. W. Lin, K. C. Ying, S. C. Chen, et al. Particle swarm optimization for Parameter determination and feature selection of support vector machines[J]. Expert Systems with Applications,2008,35:1817-1824.
[141]邓乃扬,田英杰.支持向量机——理论、算法与拓展[M].北京：科学出版社,2009.
[2]W. M. Steen. Laser Material Processing[M]. London:Springer-Verlag London Limited, 2003.
[3]Y. B. Chen, Z. L. Lei, L. Q. Li, et al. Experimental study on welding characteristics of CO2 laser TIG hybrid welding proeess[J]. Science and Technology of Welding and Joining,2006, 11(4):403-411.
[4]M. Gao, X. Y. Zeng, Q. W. Hu. Effects of welding parameters on melting energy of CO2 laser-GMA hybrid welding[J]. Science and Technology of Welding and Joining, 2006, 11(5):517-522.
[5]陈彦宾.现代激光焊接技术[M].北京：科学出版社,2005.
[6]刘金合.高能密度焊[M].西安：西北工业大学出版社,1995.
[7]http://www.laserfair.com/a/hj/20111104/10085.html[EB/OL].
[8]葛袁静,张广秋,陈强.等离子体科学技术及其在工业中的应用[M].北京：中国轻工业出版社,2011.
[9]赵青,刘述章,童洪辉.等离子体技术及应用[M].长沙：国防工业出版社,2009.
[10]M. Aden, E. W. Kreutz, A. Voss. Laser-induced plasma formation during pulsed laser deposition[J]. Journal of Physics. D:Applied Physics,1993(26):1545-1553.
[11]L. Li, D. J. Brookfield, W.M. Steen. Plasma charge sensor for in-process, non-contact monitoring of the laser welding process[J]. Measurement Science and Technology, 1996,7(4):615-626.
[12]郑春开.等离子体物理[M].北京：北京大学出版社,2009.
[13]T. Sibillano, A. Ancona, V. Berardi, et al. A study of the shielding gas influence on the laser beam welding of AA5083 aluminium alloys by in-process spectroscopic investigation [J]. Optics and Lasers in Engineering,2006,44(10):1039-1051.
[14]T. Sibillano, A. Ancona, V. Berardi, et al. Correlation analysis in laser welding plasma[J]. Optics Communications,2005,251(1-3):139-148.
[15]T. Sibillano, A. Ancona, V. Berardi, et al. Optical detection of conduction/keyhole mode transition in laser welding[J]. Journal of Materials Processing Technology,2007, 191(1):364-367.
[16]T. Sibillano, A. Ancona, V. Berardi, et al. Real-time monitoring of laser welding by correlation analysis:The case of AA5083[J]. Optics and Lasers in Engineering,2007, 45(10):1005-1009.
[17]G. H. Li, Y. Cai, Y. X. Wu. Stability information in plasma image of high-power CO2 laser welding[J]. Optics and Lasers in Engineering,2009,47(9):990-994.
[18]M. Gao, X. Y. Zeng, Q. W. Hu. Effects of gas shielding parameters on weld penetration of CO2 laser-TIG hybrid welding[J]. Journal of Materials Processing Technology,2007, 184(1-3):177-183.
[19]M. Hamadou, R. Fabbro, G. Caillibotte. Effect of gas shielding delivery mode on high power CO2 laser welding[C]. Proceedings of ICALEO 2004, LaserWelding and Brazing,2004,10:171-180.
[20]L. M. Liu, G. Song, M. L. Zhu. Low-Power Laser/Arc Hybrid Welding Behavior in AZ-Based Mg Alloys[J]. Metallurgical and Materials Transactions A,2008, 39(7):1702-1711.
[21]H. Wang, Y. W. Shi, S. L. Gong, et al. Effect of assist gas flow on the gas shielding during laser deep penetration welding[J]. Journal of Materials Processing Technology, 2007,184(1-3):379-385.
[22]J. W. Kwon, O. Kwon, Y. G. Jang, et al. Development of neural network based plasma monitoring system for laser welding quality analysis[C]. Proceedings of the IEEE Region 10 Conference,1999(1):678-681.
[23]王春明,胡伦骥,胡席远.非穿透激光焊等离子体光信号与熔深的关系[J].激光技术,2006,30(1)：23-26.
[24]王春明,余福林,段爱琴.非穿透激光深熔焊熔深与等离子体光信号的关系[J].焊接学报,2002,23(5)：45-48.
[25]高向东,龙观富,汪润林等人.大功率盘型激光焊飞溅特征分析[J].物理学报,2012,61(9)：098103-1-8.
[26]高向东,汪润林,龙观富等人.盘型激光焊金属蒸汽特征色调-色饱和度-亮度分析法研究[J].物理学报,2012,61(14)：148103-8.
[27]祁俊峰,丁鹏,张冬云.工艺参数对铝合金C02激光焊接光致等离子体温度的影响[J].焊接学报,2008,29(6)：97-100.
[28]刘金合,朱石刚.C02激光焊接等离子体高速摄影照片图像处理[J].应用激光,2002,22(3)：342-344.
[29]陈根余,赵智,张屹等.激光焊接等离子体温度场测量及数据处理[J].中国激光, 2008,35(11)：1778-1782.
[30]刘博生,王睿,段爱琴.激光深熔焊等离子光焰图像信息提取的研究[J].影像技术,2006,(1)：24-27.
[31]赵良磊,唐卓,李国华.等离子体在大功率激光深熔焊中的作用及其影响因素的分析[J].应用激光,2007,27(5)：357-361.
[32]H. Luo, H. Zeng, L. J. Hu, et al. Application of artificial neural network in laser welding defect diagnosis[J]. Journal of Materials Processing Technology,2005, 170(1-2):403-411.
[33]刘京雷,陈彦宾,徐庆鸿.激光焊接声信号与熔深的相关性[J].焊接学报,2006,27(1)：72-75.
[34]Z. Y. Li, W. Wang, X. Y. Wang, et al. A study of the radiation of a Nd:YAG laser-MIG hybrid plasma[J]. Optics and Laser Technology,2010,42(1):132-140.
[35]姜平,陈武柱.激光焊接时等离子体电流的产生机制及其数学模型[J].中国激光,2002,29(5)：471-474.
[36]N. Seto, S. J. Katayama, M. Mizutanit, et al. Relationship between plasma and keyhole behavior during CO2 laser welding[C]. Proceeding of SPIE:High-Power Lasers Manufacturing,2000(3888):61-68.
[37]陈明,马跃洲,陈光.X射线线阵实时成像焊缝缺陷检测方法[J].焊接学报,2007,28(6)：81-84.
[38]M. Zhou, W. Z. Liu, L. Wan. Multi-information Fusion and Identification System for Laser Welding[C]. Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks,2009(5551):986-992.
[39]H, Park, S. Rhee, D. Kim. A fuzzy pattern recognition based system for monitoring laser weld quality[J]. Measurement Science and Technology,2001,12(8):1381-1324.
[40]H. Park, S. Rhee. Real time estimation of CO2 laser weld quality for automotive industry[J]. Optical & Laser Technology,2002,34(2):134-142.
[41]S. S. Rodil, R. A. Gomez, J. M. Bernardez, et al. Laser welding defects detection in automotive industry based on radiation and spectroscopical measurements[J]. International Journal of Advanced Manufacturing Technology,2010,49(1-4):133-145.
[42]段爱琴,陈俐,王亚军.CO2激光焊接不锈钢光致等离子体动态特性分析[J].焊接学报,2005,26(11)：17-20.
[43]骆红,胡伦骥,黄树槐等.激光焊接过程中小孔行为对光、声的影响[J].中国机械工程,1998,9(11)：84-85.
[44]G. Tani, A. Ascari, G. Campana, et al. A study on shielding gas contamination in laser welding of non-ferrous alloys[J]. Applied Surface Science,2007,254(4):904-907.
[45]G. Tani, L. Tomesani, G. Campana, et al. Evaluation of molten pool geometry with induced plasma plume absorption in laser-material interaction zone[J]. International Journal of Machine Tools & Manufacture,2007,47(6):971-977.
[46]U. Stute, R. Kling, J. Hermsdorf. Interaction between Electrical Arc and Nd:YAG Laser Radiation[J]. Annals of the CIRP:Manufacturing Technology,2007, 56(1):197-200.
[47]J. Mark, F. A. Hamprecht. Principal Component Imagery for the Quality Monitoring of Dynamic Laser Welding Processes[J]. IEEE Transactions on Industrial Electronics, 2009,56(4):1307-1313.
[48]Z. G. Gao, Y. X. Wu, J. Huang. Analysis of weld pool dynamic during stationary laser-MIG hybrid welding[J]. International Journal of Advanced Manufacturing Technology,2009,44(9-10):870-879.
[49]D. Naso, B. Turchiano, P. Pantaleo. A fuzzy-logic based optical sensor for online weld defect-detection[J]. IEEE Transactions on Industrial Information,2009, 1(4):259-273.
[50]C. Bertrand, O. Laplanche, J. P. Rocca, et al. Effect of the combination of different welding parameters on melting characteristics of grade 1 titanium with a pulsed Nd-Yag laser[J]. Lasers in Medical Science,2007,22(4):237-244.
[51]M. Farid, P. A. Molian. High-brightness laser welding of thin-sheet 316 stainless steel[J]. Journal of Materials Science,2000,35(15):3817-3826.
[52]Y. M. Zhang, S. B. Zhang, Y. C. Liu. A plasma cloud charge sensor for pulse keyhole process control[J]. Measurment Science & Technology,2001,12(8):1365-1370.
[53]胡昌奎,陈培锋,黄涛.激光深熔焊接光致等离子体行为及控制技术[J].中国激光,2003,24(5)：78-80.
[54]游德勇,高向东.激光焊接技术的研究现状与展望[J].焊接技术,2008,37(4)：5-9.
[55]齐秀滨.激光焊接过程视觉传感技术的发展现状[J].焊接学报,2008,29(2)：108-112.
[56]曾浩,周祖德,陈幼平.激光焊接质量实时检测和控制的进展[J].激光杂志,2000,21(1)：2-5.
[57]刘锟,刘金合,周畅.激光深熔焊接光致等离子体的控制[J].热加工工艺,2007,36(23)：86-88.
[58]高世一,吴瑞珉,陈卫东.激光焊接过程监测及焊缝质量检测技术研究现状[J].世界钢铁,2010,(3)：51-54.
[59]C. Kim, J. Kim, H. Lim, et al. Investigation of laser remote welding using disc laser[J]. Journal of Materials Processing Technology,2008,201:521-525.
[60]何煦辉.碟片激光器及其在工业中的应用[J].激光与光电子学进展,2009,46(7)：64-66.
[61]http://www.cn.trumpf.com/produkte/lasertechnik/laser-und-lasersysteme-fuer-die-mate rialbearbeitung/festkoerperlaser/scheibenlaser/trudisk.html[EB/OL].
[62]陶霖密,徐光佑.机器视觉中的颜色问题及应用[J].科学通报,2001,46(3)：178-190.
[63]章毓晋.图像处理和分析教程[M].北京：人民邮电出版社,2009.
[64]V. R. Chary, D. R. Lakshmi, K. V. N. Sunitha. Feature extraction methods for color image similarity[J]. Advanced Computing:An International Journal,2012, 3(2):147-157.
[65]T. Q. Chen, Y. Lu. Color image segmentation—An innovative approach[J]. Pattern Recognition,2002,35(2):395-405.
[66]D. H. Cheng, X. H. Jiang, Y. Sun, et al. Color image segmentation:advances and prospects[J]. Pattern Recognition,2001,34 (12):2259-2281.
[67]R. C. Gonzalez, R. E. Woods, S. L. Eddins. Digital Image Processing Using Matlab[M]. New Jersey:Pearson Education,2004.
[68]L. Bonsiepen, W. Coy. Stable segmentation using color information[C]. Proc.4th Int. Conference on Computer Analysis of Image and Patterns,1991:77-84.
[69]S. A, Underwood, J. K. Aggarwal. Interactive computer analysis of aerial color infrared photographs [J]. Computer Graphics and Image Processing,1977,6 (1):1-24.
[70]李冠林,马占鸿,黄冲等.基于K_means硬聚类算法的葡萄病害彩色图像分割方法[J].农业工程学报,2010,26(2)：32-36.
[71]X. Y. Wang, X. J. Zhang, H. Y. Yang, et al. A pixel-based color image segmentation using support vector machine and fuzzy C-means[J]. Neural Networks,2012, 33:148-159.
[72]S. A. Naji, R. Zainuddin, H. A. Jalab. Skin segmentation based on multi pixel color clustering models[J]. Digital Signal Processing,2012,22(6):933-940.
[73]F. Y. Shih, S. X. Cheng. Automatic seeded region growing for color image segmentation[J]. Image & Vision Computing,2005,23(10):877-886.
[74]C. C. Kang, W. J. Wang, C. H. Kang. Image segmentation with complicated background by using seeded region growing[J]. International Journal of Electronics and Communications,2012,66(9):767-771.
[75]K. L. Chung, W. J. Yang, W. M. Yan. Efficient edge-preserving algorithm for color contrast enhancement with application to color image segmentation[J]. Journal of Visual Communication and Image Representation,2008,19(5):299-310.
[76]H. Z. Wang, J. Oliensisb. Generalizing edge detection to contour detection for image segmentation[J]. Computer Vision and Image Understanding,2010,114(7):731-744.
[77]黄玉明,徐光祐,叶培建.基于物理模型的彩色图像分割[J].自动化学报,1992,18(4)：421-428.
[78]A. Kochan, M. Abidi. Digital Color Image Processing[M]. New York:Wiley,2009.
[79]W. K. Pratt. Digital Image Processing[M]. New York:Wiley,2007.
[80]H. D. Cheng, X. H. Jiang, Y. Sun, et al. Color image segmentation advances and prospects[J]. Pattern Recognition,2001,34(12):2259-2281.
[81]J. Gauch, C. W. Hsia. A comparison of three color image segmentation algorithm in four color spaces[C]. SPIE Visual Communications and Image Processing, 1992(1818):1168-1181.
[82]林开颜,吴军辉,徐立鸿.彩色图像分割方法综述[J].中国图象图形学报,2005,10(1)：1-10.
[83]M. Taghizadeh, A. A. Gowen, C. P. O'Donnell. Comparison of hyperspectral imaging with conventional RGB imaging for quality evaluation of Agaricus bisporus mushrooms[J]. Biosystems Engineering,2011,108(2):191-194.
[84]陆启韶,周梦,高宗升.现代数学基础(第二版)[M].北京：北京航空航天大学出版社,2005.
[85]李贵俊,刘正熙,游志胜等.一种基于色差和彩色归一化的车身颜色识别算法[J].计算机应用,2004,24(9)：47-49.
[86]田杰,吕建新,周晓娟等.位图的图像处理技术[J].现代电子技术,2001,(9)：28-30.
[87]贾秋菊,王小铭.一种动态切分的颜色量化算法[J].华南师范大学学报(自然科学版),2005,(1)：46-49.
[88]D. Androutsos, A. N. Venetsanopoulos, K. N. Plataniotis. Novel vector-based approach to color image retrieval using a vector angular-based distance measure[J]. Computer vision and image understanding,1999,75(1):46-58.
[89]D. Androutsos, A. N. Venetsanopoulos, K. N. Plataniotis. Vector angular distance measure for indexing and retrieval of color[C]. SPIE,1999(3656):604-612.
[90]D. C. Tseng, C. H. Chang. Color segmentation using perceptual attributes[C]. Proc. 11th Int. Conference on Pattern Recognition,1992(3):228-231.
[91]汪增福.模式识别[M].合肥：中国科学技术大学出版社,2010.
[92]边肇棋,张学工.模式识别(第二版)[M].北京：清华大学出版社,2007.
[93]盛立东.模式识别导论[M].北京：北京邮电大学出版社,2010.
[94]S. Theodoridis, K. Koutroumbas. Pattern Recognition(Third Edition)[M]. Amsterdam: Elsevier,2006.
[95]K. N. Plataniotis, A. N. Venetsanopoulos. Color image processing and applications[M]. Berlin:Springer,2000.
[96]S. Beyer, K. Behler, G. Herziger. Influence of laser beam polarization in welding[C]. Industrial Laser Annual Hand-book. Tulsa:Penwell Books,1990:157-160.
[97]W. Chen, P.Ackerson, P. Molian. CO2 laser welding of galvanized steel sheets using vent holes[J]. Materials & Design,2009,30(2):245-251.
[98]Y. Kawahito, N. Matsumoto, M. Mizutani, S. Katayama. Characterisation of plasma induced during high power fibre laser welding of stainless steel[J]. Science and Technology of Welding and Joining,2008,13(8):744-748.
[99]T. M. Mitchell. Machine Learning[M]. New York:McGraw-Hill,1997.
[100]E. Mjolsness, D. Decoste. Machine learning for science:State of the art and future prospects[J]. Science,2001,293(5537):2051-2055.
[101]V. Cherkassky, F. Mulier. Vapnik-Chervonenkis(VC) learning theory and its applications[J]. IEEE Transactions on Neural Networks,1999,10(5):985-987.
[102]张青贵.人工神经网络导论[M].北京：中国水利水电出版社,2004.
[103]史忠植.神经网络[M].北京：高等教育出版社,2009.
[104]S. Haykin.神经网络原理[M].北京：机械工业出版社,2004.
[105]S. Haykin. Neural Networks and Learning Machines, Third Edition[M]. New Jersey: Pearson Education,2008.
[106]S. Kumar. Neural Networks(影印版)[M].北京：清华大学出版社,2006.
[107]赵熹华,王宸煜,张若冰等.点焊工艺设计智能混合系统研究[J].焊接,2000,11(3)：11-13.
[108]罗怡,伍光凤,李春天.C02焊接工艺参数优化的人工神经网络设计[J].热加工工艺,2008,37(5)：93-95.
[109]董志波,魏艳红,占小红等.遗传算法与神经网络结合优化焊接接头力学性能预测模型[J].焊接学报,2007,28(12)：69-72.
[110]于秀萍,孙华,赵希人等.基于人工神经网络的焊缝宽度预测[J].焊接学报,2005,26(5)：17-19.
[111]张永志,董俊慧,张艳飞等.基于径向基神经网络焊接接头力学性能预测[J].焊接学报,2008,29(7)：81-84.
[112]方平,张勇,谭义明.人工神经网络电阻点焊质量监测模型的研究[J].机械科学与技术,2000,19(1)：130-132.
[113]C. C. Sheng, C. H. Li. A fuzzy radial basis function neural network for predicting multiple quality characteristics of plasma arc welding[C]. IFSA World Congress and 20th NAFIPS International Conference,2001:2812-2818.
[114]韩力群.人工神经网络教程[M].北京：北京邮电大学出版社,2006.
[115]张雨浓,杨逸文,李巍.神经网络权值直接确定法[M].广州：中山大学出版社,2010.
[116]V. N. Vapnik, S. E. Golowich, A. J. Smola. Support vector method for function approximation, regression estimation and signal processing[J]. In Advances in Neural Information Processing Systems,1996,9:281-287.
[117]J. Christopher, C. Burges. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery,1998,2(2):1-43.
[118]X. X. Huang, S. B. Chen. SVM-based fuzzy modeling for the arc welding process[J]. Materials Science and Engineering:A,2006,427(1-2):181-187.
[119]D. H. Lim, I. H. Bae, M. G. Na, et al. Prediction of residual stress in the welding zone of dissimilar metals using data-based models and uncertainty analysis[J]. Nuclear Engineering and Design,2008,240(10):2555-2564.
[120]M. G. Na, J. W. Kim, D. H. Lim, et al. Residual stress prediction of dissimilar metals welding at NPPs using support vector regression[J]. Nuclear Engineering and Design, 2008,238(7):1503-1510.
[121]张朴,万磊,孔力.基于支持向量机的激光焊接过程质量监测[J].华中科技大学学报(自然科学版),2007,35(7)：62-63.
[122]张晓光,肖应明,任世锦等.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报(自然科学版),2005,(5)：644-648.
[123]阎威武,常俊林,邵惠鹤.一种贝叶斯证据框架下支持向量机建模方法的研究[J].控制与决策,2004,19(5)：525-528.
[124]N. Cristianini. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge:MIT Press,1999.
[125]M. Aizerman, E. Braverman, L. Rozonoer. Theoretical foundations of the potential function method in pattern recognition learning[J]. Automation and Remote Control, 1964,25:821-837.
[126]T. Poggio, F. Girosi. Networks for approximation and learning[C]. Proceedings of the IEEE,1990,78(9):1481-1497.
[127]B. Scholkopf, C. Burges, A. J. Smola. Advances in Kernel Methods-Support Vector Learning [M]. Cambridge:MIT Press,1999.
[128]S. Amari, S.Wu. Improving support vetor machine classifiers by modifying kernel functions[J]. Neural Networks,1999,12(6):783-789.
[129]T. S. Jaakkola, D. Haussler. Exploiting generative models in discriminative classifiers[C]. In Proc. of Tenth Conference on Advances in Neural Information Processing Systems, MIT Press,1998:487-493.
[130]V. N. Vapnik. The nature of statistical learning theory[M]. New York:Springer-Verlag, 1995.
[131]V. N. Vapnik. An overview of statistical learning theory[J]. IEEE Transactions on Neural Networks,1999,10(5):988-999.
[132]V. Cherkassky, M. Yunqian. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Networks,2004,17(1):113-126.
[133]A. Smola, N. Murata, B. Scholkopf, et al. Asymptotically optimal choice of ε-loss for support vector machines[C]. Proceedings of the 8th International Conference on Artificial Neural Networks, Perspectives in Neural Computing,1998:105-110.
[134]J. T. Kwok. Linear dependency between ε and the input noise in s-support vector regression[C]. ICANN2001,2001:405-410.
[135]B. Samanta, K. R. Al-Balushi, S. A. Al-Araimi. Artificial neural networks and support vetor machines with genetic algorithm for bearing fault detection[J]. Engineering Applications of Artificial Intelligence,2003,16(7,8):657-665.
[136]B. Baesens, S. Viaene, T. V. Gestel, et al. An empirical assessment of kernel type performance for least squares support vector machine classifiers[C]. Proceedings of 4th Int Conf on Knowledge-based Intelligent Engineering Systems and Allied Technologies. Brighton, UK:IEEE,2000(1):313-316.
[137]王兴玲,李占斌.基于网格搜索的支持向量机核函数参数的确定[J].中国海洋大学学报,2005,5：859-862.
[138]S. Keerthi. Efficient tuning of SVM hyperparameters using margin bound and iterative algorithms[J]. IEEE Trans On Neural Networks,2002,13(5):1225-1229.
[139]O. Chapelle, V. Vapnik, O. Bacsquest, et al. Choosing multiple parameters for support vector machines[J]. Machine Learning,2002,46(1):131-159.
[140]S. W. Lin, K. C. Ying, S. C. Chen, et al. Particle swarm optimization for Parameter determination and feature selection of support vector machines[J]. Expert Systems with Applications,2008,35:1817-1824.
[141]邓乃扬,田英杰.支持向量机——理论、算法与拓展[M].北京：科学出版社,2009.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |