变间隙铝合金脉冲GTAW熔池视觉特征获取及其智能控制研究
|
摘要
在铝合金填丝脉冲GTAW自动化过程中,保证焊缝稳定成形的有效方式是实时获取焊接过程熔透信息并采用合理的控制策略形成闭环控制。由于铝合金材料的特殊性,其过程传感及控制策略的选择始终是实现自动化焊接过程的瓶颈。此外,间隙是影响铝合金焊缝成形的重要因素,由于机械加工、装卡精度和热变性等原因,在焊接过程中很难有效避免,因此,本文将间隙作为一个重要参数,对变间隙铝合金填丝脉冲GTAW过程视觉传感及智能控制问题进行了系统深入探讨。
根据铝合金填丝脉冲GTAW过程控制系统信息获取需要,设计了多光路同时同幅传感系统,实现了从熔池正前方、斜后方和斜下方等三个方向同时同幅获取熔池图像,为研究熔池正反面几何形状关系提供了有利工具。
结合铝合金填丝脉冲GTAW电弧特点,在对电弧弧光机理进行分析和实验基础上,提出了基于窄带复合滤光的滤光系统,为三条光路分别选择了不同的滤光片、减光片,以电弧光作为照明光源,在多种工艺条件下,分析了取像时刻、取像基值电流、基值峰值对视觉传感效果的影响,最终确定了兼顾焊接工艺和视觉传感的熔池图像采集方案,获得了清晰、稳定的铝合金熔池图像。在实验的基础上,本文在线采集了正常焊缝成形时图像以及四种宏观焊接缺陷情况下的图像,并分别对这些存在焊接缺陷的图像特点进行了总结。
焊接过程视觉传感是为了实时准确的提取表征熔池形状和大小的特征信息。经过分析熔透变化过程中熔池形状变化特点,定义了熔池正背面宽度、正面半长、正面余高、间隙及焊缝位置对焊接熔池形状及运动方向进行了描述。针对斜后方熔池图像特点,结合小波分析及Canny算子两者优点,提取了熔池边缘信息,经去噪、标定校正后,采用分段多项式拟合的方法对熔池边缘进行了恢复,提取到熔池宽度及半长。采用了退化恢复、阈值分割、去噪、细化及Hough变换等图像处理算法,提取了熔池前端间隙和方向信息。采用了去噪、二值化处理、边缘提取等图像处理算法,提取了背面熔池宽度信息。
在不干扰正常图像处理流程的前提下,进一步开发了焊缝宏观缺陷在线检测图像处理方法,定义了各种焊接缺陷特征评价函数。对偏丝缺陷图像,由于焊丝只能出现在熔池一侧,通过对比熔池两侧灰度变化可以进行判断;对错边缺陷图像,其斜后方熔池边缘标定后,其头部上下两侧最前端边缘点横坐标出现明显错位,通过比较该区域上下两部分横坐标统计平均值可以判断缺陷是否存在;对焊漏缺陷图像,其正面图像焊漏处灰度值明显偏小,通过检验固定区域灰度平均值可以判断缺陷是否存在;对未焊透缺陷图像,其背面熔宽可以直接反映。
为了从控制角度研究铝合金GTAW过程中熔池特征参数与焊接工艺参数之间的动态关系,本文采用经典阶跃响应激励系统,分别建立了峰值电流、送丝速度、间隙,焊接速度与熔池几何形状参数间的单入单出经典传递函数模型,深入分析了焊接规范参数与熔池几何形状参数之间的关系,从理论上描述了系统地动态性能及稳态性能,为进一步地焊接过程实时控制奠定了基础,证明了焊接过程存在非线性、强耦合和时滞等复杂特点,简单的数学模型难以对其精确描述。
为了建立焊接过程动态模型,在合理的焊接规范下,确定了焊接电流、送丝速度、间隙随机变化范围,在以上三个变量同时随机变化的条件下,进行随机实焊试验,提取到熔池正背面几何形状参数。对其进行数据拓展和去噪处理后,采用RBF神经网络模型,分别建立了熔池正面宽度和半长预测模型,熔池背面宽度及正面高度预测模型。利用以上两模型,对不同规范下熔池形状动态变化过程进行了离线仿真,仿真结果与实际焊接过程人工经验基本一致,进一步证明了前述动态模型的正确性与可行性。
结合工件尺寸、坡口形式及工艺条件,详细分析了工艺及焊缝成形特征,并进行了单入单出控制器设计及实验,其中,间隙处于[0, 0.5mm]时被看作系统干扰,实验中间隙值为0.3mm。为了比较不同控制器性能,首先设计了经典位置式PID控制器,仿真结果及实焊控制实验表明,针对不同系统期望值和初始参数,固定参数的PID控制器无法适应焊接过程的非线性、变参数特征。针对固定参数PID控制器的不足,进一步设计了参数在线自调整的MS-PSD控制器,仿真结果及实焊控制实验表明,参数在线自适应调整MS-PSD控制器对变散热条件或小间隙工件背面熔宽均可以实现较好的控制效果。
针对传统智能控制器的局限,从兼顾控制器智能特性及可理解性角度,本文引入RS理论,经过对样本数据进行数据拓展、去噪、离散化预处理、条件属性约简、条件属性值约简、规则约简等过程,设计了单入单出RS控制器,并进行了仿真,变散热及小间隙工件实焊实验结果均表明,对于背面熔宽,该控制器可以获得较好控制效果。
同时,以上实验也表明,以背面熔宽作为输出的单入单出控制系统中,熔池正面几何参数处于开环状态,尤其在有间隙时,熔池表面下塌严重,成形受到影响。
为同时控制熔池背面熔宽和正面余高,在单入单出RS控制器基础上,设计了双入双出RS及MS-PSD复合控制器,其中焊接电流用来控制背面熔宽,送丝速度用来控制正面余高,并进行了仿真,变散热及小间隙工件实焊实验结果表明,在间隙处于[0,0.5mm]区间时,对于背面熔宽和正面余高,该控制器均可以获得较好控制效果。
实践经验表明:在本文无衬垫4mm厚开坡口铝合金GTAW中,间隙大于1.5mm时,焊件废品率明显提高,该工艺方法无法保证稳定成形,故大间隙焊接控制实验中,要求间隙小于1.5mm。
在分析了理想状态下间隙值与送丝量之间的数量关系后,结合经验和工件坡口形式,提出了实际焊接过程中有间隙时送丝增量补偿公式,进一步设计了基于参数预置前馈的RS和MS-PSD复合控制器,间隙渐变和间隙突变两种工件实焊实验表明,该控制器可以在大间隙条件下实现良好焊缝成形。其中间隙渐变时,焊道正背面成形均匀,而间隙突变时,在突变处焊道成形要差于其他部位。总体说来,在间隙大范围变化条件下,该前馈复合控制器可以对熔池正背面成形进行有效控制,当间隙为0时,该控制器等同于前文中RS及MS-PSD复合控制器。
In aluminum alloy pulsed gas tungsten arc welding (GTAW) process, both real-time penetration information and well controller are important for stable weld shape closed-controlling. Because aluminum alloy is special, the welding process information sensing and control algorithm are still bottlenecks in automatic welding. Moreover, gap is inevitable in welding process while it effects on weld shape seriously. So systematic research is done in aluminum alloy pulsed GTAW process information sensing and intelligent control.
According to the requirements of aluminum alloy the GTAW control system, multi-light-route visual sensing subsystem is designed to catch weld pool image from top-back, top-front and back directions simultaneous. The sensor provides powerful tools for the investigation of the relation between the top and the back weld pool parameter.
Narrowband multiple filter technology is developed after analysis on the are sensing mechanism and experiments in aluminum alloy GTAW process. Dirrent ultra-red filter glass and neural density filter glass are selected for the three light-routes, separately. The effects from obtaining images time, base level current, peak level current on visual sensing are studied carefully under several technical conditions. Lastly, the clearly and stable aluminum alloy weld pool images are obtained while the welding technics and visual sensing parameters are confirmed. Based on the experiments, general weld pool image and four weld pool defects images are collected. Extensively, the defects characters are summarized, separately.
Combined with welding pool variation in different penetration, several parameters about weld pool geometry and welding directions are defined. For top-back image, wavelet transform and Canny operator advantages are used to get weld pool edge points. After noise removing and calibration, subsection polynomial curve fitting method are used to recove the whole weld pool edge. For the top-front image, degrade recover, automatic threshold segmentation, noise removing, thinning and Hough transform are used to computing gap size and welding direction. For the back image, algorithm including noise removing, automatic threshold segmentation, edge detection is used to recover the whole back contour of the weld pool. From these recoved whole weld pool edge and the weld pool parameters’definitions, the values of the parameters can be computed.
Not interface with the above image processing flow, weld pool defect can be inspected on-line by the image processing software and these defects character evaluation functions are defined for them. For weld wire misdirection image, it can be judged by comparing with the gray value difference of two sides of the weld pool because wire only appears on one side each time. For misalignment image,there are obvious misalignment of its abscissa value in the front up and down part of the pool edge after calibration. So the different of the average gray values in the up and down sides separately may be used to judge the defect. For burning through image, its back image is quite bright. It means the average gray value of the special region may show if there is burning through. For incomplete penetration, its back wide of the weld pool is the best direct paramenters.
To study the dynamic relation between weld pool characters and weld technics parameters, several single input and single output transfer function models are established through step response identification experiments. The inputs include peak current, wire feeding rate, gap size, weld speed. And the outputs are weld pool parameters. By analyzing effects of welding parameters on weld shaping, it s discovered that arc welding is characterized as multi-variables, strong coupling, nonlinear, time varying. The simple conventional models are not enough to describe the complex system.
To establish the welding process dynamic models, the appropriate arrangements of welding current, wire feeding rate, gap are determined. Stochastic experiments are done to extract the shape parameters of weld pool when the three welding parameters are stochastic variable. After data extension and noise removing, two prediction models are constructed by using RBF neural net. The models are and predictions model , and predictions model . Through these two models, offline simulation experiments are applied to analyze the dynamic process of weld pool shape. The simulation result agrees to the actual manual experiments. It proves that the two models are right and feasible.
For the workpiece shape, groove shape and technics conditions provided for the experiments, the characters of the technics and weld shaping are analyzed carefully. Also SISO control experiments are carried out. Here gap size in [0, 0.5mm] is regarded as disturbance and set as 0.3mm. To compare with the capability of different controller, PID controller and MS-PSD controller are designed, separately. Simulations and welding experiments proved that, PID controller works not well when varied heat-sink and varied gap appears. For the shortcomings of PID, MS-PSD is designed to obtain better weld quality. It can adjust its parameters on-line by itself. Simulation and welding experiments proved that, MS-PSD controller can ensure both varied heat-sink and varied gap workpieces welding process stable. At the same time, the experiments also show that the topside of the weld pool is not in control. The topside surface sinks severely, which effects on weld shape.
Avoiding the limitation of traditional intelligent controller, rough set (RS) theory is introduced into welding process control considering both intelligence and comprehension. After data extension, noise removing, data discrete preprocessing, attribute reduction, attribute value reduction and rule reduction, SISO RS controller is designed. Simulation and welding experiments proved that, the control result is acceptable for back width of varied heat-sink or varied gap workpiece.
To control both top-front width and back with of the weld pool, double inputs and double outputs RS&MS-PSD multi-controller is designed. In this controller, wire feeding rate is used to control back width and weld current is used to control top-back width. Simulation and welding experiments proved that: the controller can insure weld shape from both sides of the weld pool. Moreover, topside height is also better than ever since wire feed rate is adjusted.
Welding experience shows that: weld defection increases quickly when gap size is greater than 1.5mm in aluminum alloy GTAW with groove but no backing. The welding technics can not ensure stable welding shaping. So the gap size arrangement is confirmed as [0,1.5mm].
After analyzing the relation between gap size and wire feeding rate under idea state, a wire compensation formula based on experience and workpiece groove style is raised up when there is big gap in real welding process. Extensively, new RS&MS-PSD controller with parameter preset is designed. Two types of workpieces with different big gap are provided to check the validation of the controller. When gap changes gradually, the controller is effected on both sides of the weld zone. The welding shaping is uniform. When gap changes suddenly, the shaping in the position where gap just appears is worse than elsewhere. For those big gap workpiece, the multi-controller with parameter preset can ensure both sides shaping of the weld zone. When gap is 0, the controller equals to the RS&MS-PSD multi-controller.
根据铝合金填丝脉冲GTAW过程控制系统信息获取需要,设计了多光路同时同幅传感系统,实现了从熔池正前方、斜后方和斜下方等三个方向同时同幅获取熔池图像,为研究熔池正反面几何形状关系提供了有利工具。
结合铝合金填丝脉冲GTAW电弧特点,在对电弧弧光机理进行分析和实验基础上,提出了基于窄带复合滤光的滤光系统,为三条光路分别选择了不同的滤光片、减光片,以电弧光作为照明光源,在多种工艺条件下,分析了取像时刻、取像基值电流、基值峰值对视觉传感效果的影响,最终确定了兼顾焊接工艺和视觉传感的熔池图像采集方案,获得了清晰、稳定的铝合金熔池图像。在实验的基础上,本文在线采集了正常焊缝成形时图像以及四种宏观焊接缺陷情况下的图像,并分别对这些存在焊接缺陷的图像特点进行了总结。
焊接过程视觉传感是为了实时准确的提取表征熔池形状和大小的特征信息。经过分析熔透变化过程中熔池形状变化特点,定义了熔池正背面宽度、正面半长、正面余高、间隙及焊缝位置对焊接熔池形状及运动方向进行了描述。针对斜后方熔池图像特点,结合小波分析及Canny算子两者优点,提取了熔池边缘信息,经去噪、标定校正后,采用分段多项式拟合的方法对熔池边缘进行了恢复,提取到熔池宽度及半长。采用了退化恢复、阈值分割、去噪、细化及Hough变换等图像处理算法,提取了熔池前端间隙和方向信息。采用了去噪、二值化处理、边缘提取等图像处理算法,提取了背面熔池宽度信息。
在不干扰正常图像处理流程的前提下,进一步开发了焊缝宏观缺陷在线检测图像处理方法,定义了各种焊接缺陷特征评价函数。对偏丝缺陷图像,由于焊丝只能出现在熔池一侧,通过对比熔池两侧灰度变化可以进行判断;对错边缺陷图像,其斜后方熔池边缘标定后,其头部上下两侧最前端边缘点横坐标出现明显错位,通过比较该区域上下两部分横坐标统计平均值可以判断缺陷是否存在;对焊漏缺陷图像,其正面图像焊漏处灰度值明显偏小,通过检验固定区域灰度平均值可以判断缺陷是否存在;对未焊透缺陷图像,其背面熔宽可以直接反映。
为了从控制角度研究铝合金GTAW过程中熔池特征参数与焊接工艺参数之间的动态关系,本文采用经典阶跃响应激励系统,分别建立了峰值电流、送丝速度、间隙,焊接速度与熔池几何形状参数间的单入单出经典传递函数模型,深入分析了焊接规范参数与熔池几何形状参数之间的关系,从理论上描述了系统地动态性能及稳态性能,为进一步地焊接过程实时控制奠定了基础,证明了焊接过程存在非线性、强耦合和时滞等复杂特点,简单的数学模型难以对其精确描述。
为了建立焊接过程动态模型,在合理的焊接规范下,确定了焊接电流、送丝速度、间隙随机变化范围,在以上三个变量同时随机变化的条件下,进行随机实焊试验,提取到熔池正背面几何形状参数。对其进行数据拓展和去噪处理后,采用RBF神经网络模型,分别建立了熔池正面宽度和半长预测模型,熔池背面宽度及正面高度预测模型。利用以上两模型,对不同规范下熔池形状动态变化过程进行了离线仿真,仿真结果与实际焊接过程人工经验基本一致,进一步证明了前述动态模型的正确性与可行性。
结合工件尺寸、坡口形式及工艺条件,详细分析了工艺及焊缝成形特征,并进行了单入单出控制器设计及实验,其中,间隙处于[0, 0.5mm]时被看作系统干扰,实验中间隙值为0.3mm。为了比较不同控制器性能,首先设计了经典位置式PID控制器,仿真结果及实焊控制实验表明,针对不同系统期望值和初始参数,固定参数的PID控制器无法适应焊接过程的非线性、变参数特征。针对固定参数PID控制器的不足,进一步设计了参数在线自调整的MS-PSD控制器,仿真结果及实焊控制实验表明,参数在线自适应调整MS-PSD控制器对变散热条件或小间隙工件背面熔宽均可以实现较好的控制效果。
针对传统智能控制器的局限,从兼顾控制器智能特性及可理解性角度,本文引入RS理论,经过对样本数据进行数据拓展、去噪、离散化预处理、条件属性约简、条件属性值约简、规则约简等过程,设计了单入单出RS控制器,并进行了仿真,变散热及小间隙工件实焊实验结果均表明,对于背面熔宽,该控制器可以获得较好控制效果。
同时,以上实验也表明,以背面熔宽作为输出的单入单出控制系统中,熔池正面几何参数处于开环状态,尤其在有间隙时,熔池表面下塌严重,成形受到影响。
为同时控制熔池背面熔宽和正面余高,在单入单出RS控制器基础上,设计了双入双出RS及MS-PSD复合控制器,其中焊接电流用来控制背面熔宽,送丝速度用来控制正面余高,并进行了仿真,变散热及小间隙工件实焊实验结果表明,在间隙处于[0,0.5mm]区间时,对于背面熔宽和正面余高,该控制器均可以获得较好控制效果。
实践经验表明:在本文无衬垫4mm厚开坡口铝合金GTAW中,间隙大于1.5mm时,焊件废品率明显提高,该工艺方法无法保证稳定成形,故大间隙焊接控制实验中,要求间隙小于1.5mm。
在分析了理想状态下间隙值与送丝量之间的数量关系后,结合经验和工件坡口形式,提出了实际焊接过程中有间隙时送丝增量补偿公式,进一步设计了基于参数预置前馈的RS和MS-PSD复合控制器,间隙渐变和间隙突变两种工件实焊实验表明,该控制器可以在大间隙条件下实现良好焊缝成形。其中间隙渐变时,焊道正背面成形均匀,而间隙突变时,在突变处焊道成形要差于其他部位。总体说来,在间隙大范围变化条件下,该前馈复合控制器可以对熔池正背面成形进行有效控制,当间隙为0时,该控制器等同于前文中RS及MS-PSD复合控制器。
In aluminum alloy pulsed gas tungsten arc welding (GTAW) process, both real-time penetration information and well controller are important for stable weld shape closed-controlling. Because aluminum alloy is special, the welding process information sensing and control algorithm are still bottlenecks in automatic welding. Moreover, gap is inevitable in welding process while it effects on weld shape seriously. So systematic research is done in aluminum alloy pulsed GTAW process information sensing and intelligent control.
According to the requirements of aluminum alloy the GTAW control system, multi-light-route visual sensing subsystem is designed to catch weld pool image from top-back, top-front and back directions simultaneous. The sensor provides powerful tools for the investigation of the relation between the top and the back weld pool parameter.
Narrowband multiple filter technology is developed after analysis on the are sensing mechanism and experiments in aluminum alloy GTAW process. Dirrent ultra-red filter glass and neural density filter glass are selected for the three light-routes, separately. The effects from obtaining images time, base level current, peak level current on visual sensing are studied carefully under several technical conditions. Lastly, the clearly and stable aluminum alloy weld pool images are obtained while the welding technics and visual sensing parameters are confirmed. Based on the experiments, general weld pool image and four weld pool defects images are collected. Extensively, the defects characters are summarized, separately.
Combined with welding pool variation in different penetration, several parameters about weld pool geometry and welding directions are defined. For top-back image, wavelet transform and Canny operator advantages are used to get weld pool edge points. After noise removing and calibration, subsection polynomial curve fitting method are used to recove the whole weld pool edge. For the top-front image, degrade recover, automatic threshold segmentation, noise removing, thinning and Hough transform are used to computing gap size and welding direction. For the back image, algorithm including noise removing, automatic threshold segmentation, edge detection is used to recover the whole back contour of the weld pool. From these recoved whole weld pool edge and the weld pool parameters’definitions, the values of the parameters can be computed.
Not interface with the above image processing flow, weld pool defect can be inspected on-line by the image processing software and these defects character evaluation functions are defined for them. For weld wire misdirection image, it can be judged by comparing with the gray value difference of two sides of the weld pool because wire only appears on one side each time. For misalignment image,there are obvious misalignment of its abscissa value in the front up and down part of the pool edge after calibration. So the different of the average gray values in the up and down sides separately may be used to judge the defect. For burning through image, its back image is quite bright. It means the average gray value of the special region may show if there is burning through. For incomplete penetration, its back wide of the weld pool is the best direct paramenters.
To study the dynamic relation between weld pool characters and weld technics parameters, several single input and single output transfer function models are established through step response identification experiments. The inputs include peak current, wire feeding rate, gap size, weld speed. And the outputs are weld pool parameters. By analyzing effects of welding parameters on weld shaping, it s discovered that arc welding is characterized as multi-variables, strong coupling, nonlinear, time varying. The simple conventional models are not enough to describe the complex system.
To establish the welding process dynamic models, the appropriate arrangements of welding current, wire feeding rate, gap are determined. Stochastic experiments are done to extract the shape parameters of weld pool when the three welding parameters are stochastic variable. After data extension and noise removing, two prediction models are constructed by using RBF neural net. The models are and predictions model , and predictions model . Through these two models, offline simulation experiments are applied to analyze the dynamic process of weld pool shape. The simulation result agrees to the actual manual experiments. It proves that the two models are right and feasible.
For the workpiece shape, groove shape and technics conditions provided for the experiments, the characters of the technics and weld shaping are analyzed carefully. Also SISO control experiments are carried out. Here gap size in [0, 0.5mm] is regarded as disturbance and set as 0.3mm. To compare with the capability of different controller, PID controller and MS-PSD controller are designed, separately. Simulations and welding experiments proved that, PID controller works not well when varied heat-sink and varied gap appears. For the shortcomings of PID, MS-PSD is designed to obtain better weld quality. It can adjust its parameters on-line by itself. Simulation and welding experiments proved that, MS-PSD controller can ensure both varied heat-sink and varied gap workpieces welding process stable. At the same time, the experiments also show that the topside of the weld pool is not in control. The topside surface sinks severely, which effects on weld shape.
Avoiding the limitation of traditional intelligent controller, rough set (RS) theory is introduced into welding process control considering both intelligence and comprehension. After data extension, noise removing, data discrete preprocessing, attribute reduction, attribute value reduction and rule reduction, SISO RS controller is designed. Simulation and welding experiments proved that, the control result is acceptable for back width of varied heat-sink or varied gap workpiece.
To control both top-front width and back with of the weld pool, double inputs and double outputs RS&MS-PSD multi-controller is designed. In this controller, wire feeding rate is used to control back width and weld current is used to control top-back width. Simulation and welding experiments proved that: the controller can insure weld shape from both sides of the weld pool. Moreover, topside height is also better than ever since wire feed rate is adjusted.
Welding experience shows that: weld defection increases quickly when gap size is greater than 1.5mm in aluminum alloy GTAW with groove but no backing. The welding technics can not ensure stable welding shaping. So the gap size arrangement is confirmed as [0,1.5mm].
After analyzing the relation between gap size and wire feeding rate under idea state, a wire compensation formula based on experience and workpiece groove style is raised up when there is big gap in real welding process. Extensively, new RS&MS-PSD controller with parameter preset is designed. Two types of workpieces with different big gap are provided to check the validation of the controller. When gap changes gradually, the controller is effected on both sides of the weld zone. The welding shaping is uniform. When gap changes suddenly, the shaping in the position where gap just appears is worse than elsewhere. For those big gap workpiece, the multi-controller with parameter preset can ensure both sides shaping of the weld zone. When gap is 0, the controller equals to the RS&MS-PSD multi-controller.
引文
1.斯重遥,周振丰,钱乙余等,焊接手册(第二卷),北京,机械工业出版社,1992,503-509.
2. H. C. Wikle, S. Kottilingam, R. H. Zee, and B. A. Chin, Infrared sensing techniques for penetration depth control of the submerged arc welding process. Journal of materials processing technology. 2001,vol.113:228-233.
3. J. P. Boillot and G. Begin,Adaptive Welding by Fiber Optic Thermographic Sensing: an Analysis of Thermal and Instrumental Considerations. Welding Journal. 1985, Vol. 64(7): 31-37.
4. George,M. Graham and I. Charles, Automated system for laser ultrasonic sensing of weld penetration. Journal of Nuclear Materials, 1998:711-721.
5. R. Fenn,Ultrasonic Monitoring and Control During Arc Welding,Welding Journal. 1985, Vol.64(9): 18-24.
6. N. M. Carlson and J. A. Johnson,Ultrasonic Sensing of Weld Pool Penetration. Welding Journal. 1988, Vol. 67(11): 239-246.
7. M. Futamata, Application of arc sound for detection of welding process, Quarterty journal of the Japan welding society, 1983,1(1):11-14.
8. R. J. Renwick, Real-time control of GAT weld size by controlling pool oscillation frequency, CWR technical report, June 1983.
9. R. J. Renwick, Experimental investigation of GAT weld pool oscillation, Welding journal, 1983, 62(2):29-34.
10.耿正,铝合金TIG焊电弧传感熔池自激振荡法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
11.吴林,董德祥,陈定华,固定点状态下TIG焊接熔深信号的检测及分析,焊接学报,1986, Vol.7(2):64-71.
12.陈善本.焊接智能化技术现状与发展.第十次全国焊接会议论文集.黑龙江人民出版社,2001:84~96
13. D.S. Nagesh. Prediction of Weld Bead Geometry and Penetration in Shielded Metal-arc Welding Using Artificial Neural Networks. Journal of Materials Processing Technology. 2002,123(2):303~312
14. Li Di, T. Srikanthanb, R.S. Chandelc. Neural-network-based Self-organized Fuzzy Logic Control for Arc Welding. Engineering Applications of Artificial Intelligence. 2001,14:115~124
15.周振丰,张文钺,焊接冶金与金属焊接性,北京,机械工业出版社,1988.
16. Hirokazu Nomura. Sensor and Control System in Arc Welding. Chapman & Hall. 1994:3~5
17. M. Ushio and W. Mao, Sensors for Arc Welding: Advantages and Limitations. Transactions of JWRI. 1994,23(2):135~141
18. A. E. Bentley and S. J. Marberger,Arc Welding Penetration Control Using Quantitative Feedback Theory,Welding Journal,1992, Vol. 71(11): 397-405.
19.张裕明,TIG焊熔透正面视觉自适应控制的研究[博士学位论文],哈尔滨,哈尔滨工业大学,1990.
20.张裕明,吴林,TIG焊熔透正面监测量的确定,焊接学报,1991,Vol.12(1):39-45.
21. H.S. Song, Y.M. Zhang, Three-dimentional reconstruction of specular surface for a gas tungsten are weld pool, Measurement Science and Technology, 2007, Vol.18: 3751-3767.
22. H.S. Song, Y.M. Zhang, Image processing for measurement of three-dimensional GTA weld pool surface, Welding Journal, 2007, Vol. 86(10): 323-330.
23. R. Kovacevic and Y. M. Zhang,Real-Time Image Processing for Monitoring of Free Weld Pool Surface,Journal of Manufacturing Science and Engineering. 1997,Vol. 119(5): 161-169.
24. H.S. Song, Y.M. Zhang, Measurement and analysis of three-dimensional specular gas tungsten arc weld pool surface, Welding Journal, 2008, Vol. 87(4): 85- 95.
25. Y. M. Zhang, M. Beardsley and R. Kovacevic, Real-time Image Processing for 3D Measurement of Weld Pool Surface,Manufacturing Science and Engineering. 1994,PED-vol. 68(1): 255-262.
26.张远鹏,董海,周文灵.计算机图像处理技术基础,北京,北京大学出版社.1996.
27. R. J. Beatlie,S. K. Cheng,P. S. Logue,The Use of Vision Sensors in Multi-pass Welding Applications. Welding Journal,1988, Vol.67(11):28-33.
28. C. G. Morgan,J. S. Bromley,P. G. Davey,Visual Guidance Techniques for Robot Arc Welding,Proceeding of 3rd International Conference on Robot Vision and Sensory Controls, 1983: 615-619.
29. G.Agapiou, C.Kasiouras, A.A.Serafeintides, A detailed analysis of the MIG spectrum for the development of laser-based seam tracking sensors, Optics& Laser Technology,1999,31:157-161.
30. Jae seon Kim, Young Tak Son, Hyung Suck Cho and Kwang ii Koh, A robust visual seam tracking system for arc welding, Mechatronics, 1996, 6(2):141-163.
31. J.E. Agapakis, J. Bolstad. Vision Sensing and Processing System for Monitoring and Control of Welding and Other High Luminosity Processes. International Robots&Vision Automation Conference, 1991:23~29
32. S. Nakata, J. Huang, Y. Tsuruha. Visual Sensing System for In-Process Control of Arc Welding Process. Welding International. 1988, (12):1086~1090
33. R. Kovacevic, Y.M. Zhang. Three-dimension Measurement of Weld Pool Surface. Proceedings of the International Conference on Modeling and Control of Joining Processeses, Oriando, Florida, USA, 1993:600~607
34. R.W. Richardson, D.A. Gutow. Coaxial Arc Weld Pool Viewing for Process Monitoring and Control. Welding Journal. 1984,63(3):43~50
35. D. Brzakovic, D.T. Khani. Weld Pool Edge Detection for Automated Control of Welding. IEEE Transactions on Robotics and Automation. 1991,7(3):397~403
36. K. Oshima, M. Morita. Observation and Digital Control of the Molten Pool in Pulsed MIG Welding. Welding International. 1988, (3):234~240
37. K. Oshima, M. Morita. Sensing and Digital Control of Weld Pool in Pulsed MIG Welding. Transactions of the Japan Welding Society. 1992,23(4):36~42
38.王克争,大岛健司. MIG焊接熔池的图象处理和数字控制系统.清华大学学报. 1990,30(2):22~29
39.陈武柱,井上胜敬.图象处理在窄间隙MIG/MAG焊在线检测中的应用.焊接学报. 1988,9(4):247~253
40.肖强.焊接机器人视觉系统.焊接. 1992, (4):7~10
41.宋永伦.弧焊区图象信息的光谱传感技术.焊接学报. 1992,13(2): 127~132
42.黄石生. TIG焊熔宽的自整定PID闭环控制系统的研究.电焊机. 1993, (5): 6~11
43.刘玉池.计算机视觉脉冲TIG焊正面实时检测与熔宽控制的研究.哈尔滨工业大学硕士学位论文. 1994
44.黄斌.脉冲TIG焊熔池系统的智能控制研究.哈尔滨工业大学硕士学位论文. 1995
45.李鹏九.焊接过程弧光传感的应用基础研究.哈尔滨工业大学博士学位论文. 1997
46.娄亚军,戴明,陈善本.脉冲TIG焊正反面熔池同时同幅图象传感.机器人. 1997,19(1):59~63
47.赵冬斌.由单目图象获得表面高度算法的分析和实现.计算机学报. 2000, 23(2):147~152
48. K. A. Pietrzak, S. M. Packer,Vision-Based Weld Pool Width Control. ASME Journal of Engineering for Industry,1994, 116(2):86-92
49.刘晓东,变间隙对接脉冲GTAW视觉传感与神经网络建模研究[硕士学位论文],哈尔滨,哈尔滨工业大学,2001。
50. G. J. Zhang, S. B. Chen, L. Wu, Intelligent control of pulsed GTAW with filler metal, Welding Journal, 2005, 84 (1): 9-16.
51.王建军,铝合金脉冲TIG焊熔池动态特征的视觉信息获取与自适应控制[博士学位论文],上海,上海交通大学,2003
52. K.Y. Bae, T.H. Lee, K.C. Ahn. An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe, Journal of Materials Processing Technology,2002, 120: 458-465.
53. Y.M. Zhang, L. Li, R. Kovacevic. Monitoring of Weld Pool Appearance for Penetration Control.4th International Conference on Trends in Welding Research, Gatlinburg, Tennessee, USA, 1995:30~35
54. E.W. Kim, C. Allemand and T.W. Eagar. Visible Light Emissions during Gas Tungsten Arc Welding and Its Application to Weld Image Improvement. Welding Journal. 1987,66(12):369s~377s
55.赵冬斌,基于三维视觉传感的填丝脉冲GTAW熔池形状动态智能控制[博士学位论文],哈尔滨,哈尔滨工业大学,2000.
56. Laiping Li, Shanben Chen, Tao Lin, The modeling of welding pool surface reflectance of aluminum alloy pulse GTAW, Materials Science and Engineering: A, 394(2005): 320~326
57. L. P. Li, S.B.Chen, and T.Lin, The Light Intensity Analysis of Passive Visual Sensing System in GTAW. The international journal of advanced manufacturing technology, UK, 2005.1
58. Laiping Li, Shanben Chen, Tao Lin, 3D Vision Technology and its applications in Welding, The Eighth International conference on Control, Automation, Robotics and Vision, ICARCV 2004, Kunming, China, 6-9,December, 2004, 190~198.
59.李来平,脉冲GTAW熔池表面反射图建模与高度计算的研究[博士学位论文],上海,上海交通大学,2005
60. Quanying Du, Shanben Chen and Tao Lin, Inspection on Shape of Weld Based on Shape from Shading. The International Journal of Advanced Manufacturing Technology, 2006, Vol.27:667-671.
61. QuanYing Du, ShanBen Chen and Tao Lin, An Application of Shape from Shading. ICARCV 2004 - Proceedings of the 8th International Conference on Control, Automation, Robotics and Vision, 2004, 184-189.
62.杜全营,填丝脉冲GTAW熔池三维特征实时提取与智能控制[博士学位论文],上海,上海交通大学,2006
63.鄢景华,自动控制原理,哈尔滨工业大学出版社,1996.
64.胡德文,非线性与多变量系统相关辨识,国防科技大学出版社,2001.
65. Kou and Y. H. Wang , Weld Pool Convection and Its Effect , Welding Journal. 1986, Vol.65(3):63-70.
66.曹振宁,TIG/MIG焊接熔透熔池流场与热场的数值分析[博士学位论文],哈尔滨,哈尔滨工业大学工学,1993.
67. D. J. Kotecki, Mechanism of ripple formation during weld solidification, Welding journal, 1972, Vol.51(8):386-394.
68. Q. L. Wang,Detection of the weld full prentration signals of a traveling arc in GTAW process, proceedings of IIW Asian pacific regional welding congress, 1988, Hobart.
69.杨春利,薄钢板TIG焊电弧传感熔池谐振法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
70.耿正,铝合金TIG焊电弧传感熔池自激振荡法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
71.王其隆,张九海,杨春利,快速行走TIG焊接时熔透信号的提取及分析,焊接学报,1992,Vol.11(3): 175-179.
72. J. F. Kotnik, The control and analysis of full-peneteration plused-GAT welds using weld pool oscillation sensing, Masters thesis, 1986.
73. S. B. Chen, L. Wu, and Q. L. Wang, etc, Self-learning Fuzzy Neural Network and Computer Vision for Control of Pulsed GTAW. Welding Journal. 1997, Vol.76(5): 201-209.
74. S. B. Chen, L. Wu and Q. L. Wang, Self-learning Fuzzy Neural Networks for Control of Uncertain Systems with Time Delay. IEEE Transactions on System, Man, and Cybernetics-Part B: Cybernetics. 1997, Vol .27(1):142-148.
75.陈善本,吴林,王其隆,人工神经网络及其在焊接控制中的展望,哈尔滨工业大学学报,1994,26(1):20-26
76.黄石生,李迪,焊接过程的神经网络建模及控制的研究,机械工程学报,1994,30(3):24-29.
77. Y. J. Lou, S. B. Chen and L. Wu,Neuron PSD Control Based on Sensing Image of Weld Pool During Pulsed GTAW. Proceedings of International Conference on Manufacturing Science, Wuhan, P.R.China, 10-12, June, 1998.
78. Yajun Lou, Shanben Chen and Lin Wu, Monitoring of Weld Joint Penetration Based on Sensing Double-side Vision Images of Weld Pool,Journal of Harbin Institute of Technology, 1998, vol.7(11):22-27.
79. Y.S. Tarng. Modeling, Optimization and Classification of Weld Quality in Tungsten Inert Gas Welding, International Journal of Machine Tools & Manufacture, 1999,39:1427-1438.
80. S.C. Juang, Y.S. Tarng, A Comparison between the Back-propagation and Counter-propagation Networks in the Modeling of the TIG Welding Process, Journal of Materials Processing Technology, 1998,75:54-62.
81. Billy Chan, Modeling Gas Metal Arc Weld Geometry Using Artificial Neural Network Technology, Canadian Metallurgical Quarterly, 1999,38(1): 43-51.
82. George E. Cook, Weld Modeling and Control Using Artificial Neural Networks, IEEE Transactions on Industry Applications, 1995,31(6): 1484-1491.
83. Jengywan Jeng, Prediction of Laser Butt Joint Welding Parameters Using Back Propagation and Learning Vector Quantization Networks, Journal of Materials Processing Technology, 2000,99:207-218.
84. Yasuo Suga, Measurement of Molten Pool Shape and Penetration Control Applying Neural Network in TIG Welding of Thin Steel Plates, ISIJ international, 1999,39(10):1075-1080.
85. Kovacevic, Y.M. Zhang, and L. Li, Monitoring of Weld Penetration Based on Weld Pool Geometrical Appearance, Welding Journal, 1996,75(10):317-328.
86.李迪,用人工神经元网络技术对焊接质量的智能控制,华南理工大学博士学位论文, 1993.
87.李迪,黄石生,宋永伦,用神经元网络技术对焊缝质量的直接控制,第七届全国焊接学术会议论文集(第3分册),H-XX-001-93.
88.娄亚军,基于熔池图像传感的脉冲GTAW动态过程智能控制,哈尔滨工业大学博士学位论文.1998.
89.张广军,视觉传感的变间隙填丝脉冲GTAW对接焊缝成形智能控制,哈尔滨工业大学博士学位论文,2002.
90. Wang B., Chen S. B., Wang J. J., Rough set based knowledge modeling for the aluminum alloy pulsed gtaw process, The International Journal of Advanced Manufacturing Technology, 2005, 25 (9), 902-908.
91.黎文航,基于变精度粗糙集理论的焊接动态过程知识建模方法研究[博士学位论文],上海,上海交通大学,2007.
92.李士勇.模糊控制、神经控制和智能控制论.哈尔滨工业大学出版社. 1996,8:1~7
93. Charalabos Doumanidis. Multivariable Adaptive Control of the Bead Profile Geometry in Gas Metal Arc Welding with Thermal Scanning. International Journal of Pressure Vessels and Piping. 2002,79:251~262
94. Y.M. Zhang. Adaptive Control of Full Penetration Gas Tungsten Arc Welding. IEEE Transactions on Control System Technology. 1996,4(4): 394~403
95.赵彭生,萧波.焊接过程的自动控制(概况与趋势).焊接技术. 1993,(2):37~40
96. Akira Hirai. Sensing and Control of Weld Pool by Fuzzy-Neural Network in Robotic Welding System. The 27th Annual Conference of the IEEE Industrial Electronics Society. 2001,238~242
97. Mary A. Austin. Real-Time Multi-Processing Fuzzy Logic Adaptive Control Gas Tungsten Arc Welding System. The IEEE Proceedings of the 4th WPDRTS. 1996:139~142
98. Andre Bigand. Arc Welding Fuzzy Control Using Neural Net Supervisor. IEEE. 1996:2003~2006
99. Y.M. Zhang. Neuro-fuzzy Model Based Control of Weld Fusion Zone Geometry. The Proceedings of the American Control Conference. 1997,6: 2483~2487
100. K.J. Hunt. Neural Networks for Control System: A Survey. Automatica. 1992.28(6):1083~1112
101. Bob Irving. Neural Networks Are Paying Off on the Production Line. Welding Journal. 1997,76(10):59~64.
102. S.S. Huang, D. Li. Weld Quality Control by Neural Network. Welding in the Word. 1994,34:359~363
103. Y. Kaneke, T. Iisaka and K. Oshima. Neuro-fuzzy Control of the Weld Pool in Pulsed MIG Welding. Welding International. 1995,9(3):191~196
104. T.G. Lim,H.S. Cho.Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks.Journal of Systems and Control Engineering.1993,207(1):15~26
105. Jay F. Tu, N.L. Dishore. On-line Estimation of Laser Weld Penetration. ASME Journal of dynamic Systems, Measurement, and Control. 1997, 119:791~801
106. J.W. Kim,S.J. Na.A Self-organizing Fuzzy Control Approach to Arc Sensor for Weld Joint Tracking in Gas Metal Arc Welding of Butt Joints. Welding Journal. 1993,72(1):60s~66s
107. S.B. Chen, L. Wu, Q.L. Wang and Y.C. Liu. Self-learning Fuzzy Neural Network and Computer Vision for Control of Pulsed GTAW. Welding Journal. 1997,76(5):201s~209s
108. S.B. Chen, L. Wu, Q.L. Wang. Self-learning Fuzzy Neural Networks for Control of Uncertain Systems with Time Delay. IEEE Transactions on System, Man, and Cybernetics-Part B: Cybernetics. 1997,27(1):142~148
109. D.A. Hartman. Intelligent Control in Arc Welding. Intelligent Engineering Systems Through Artificial Neural Networks, ASME. 1999:715~725
110.黄石生,贺剑峰,宋永伦.钨极氩弧焊焊缝熔宽模糊控制系统设计.焊接学报. 1996,17(2):94~98
111. Y. Suga. Application of Neural Network to Visual Sensing of Weld Line and Automatic Tracking in Robot Welding. Welding in the World. 1994,34: 275~282
112. Kristinn Andersen. Artificial Neural Networks Applied to Arc Welding Process Modeling and Control. IEEE Transactions on Industry Applications. 1990,26(5):824~830
113. Xiangdong Gao, Shisheng Huang. Fuzzy Neural Networks for Control of Penetration Depth during GTAW. China Welding. 2000,1:1~8
114.刘中华,视觉传感VPPAW焊缝成形实时控制系统[博士学位论文],哈尔滨,哈尔滨工业大学,2001.
115. Zhonghua Liu and Qilong Wang, Process control based on double-side sensing of the keyhole in the VPPA welding. Journal of material technology and processing, Elsevier science, 2001, 115(2):373-379.
116. J.J. Wang, T. Lin, S.B. Chen, Obtaining weld pool vision information during aluminium alloy TIG welding, International Journal of Advanced Manufacturing Technology, 2005, 26(3): 219-227.
117.张淑荣,焊接过程粗糙集建模中推理方法的研究[硕士学位论文],上海,上海交通大学, 2004.
118.王惠钧,图像传感变极性等离子弧焊缝稳定成形闭环控制[博士学位论文],哈尔滨,哈尔滨工业大学,1998,19-23.
119.贾云得,机器视觉,北京,科学出版社,2000: 12-15.
120.成礼智,王红霞,罗永,小波的理论与应用,北京,科学出版社,2004: 303-305.
121. B.M. Sadler, A. Swami, Analysis of multiscale products for step detection and estimation[J]. IEEE Trans. Information Theory . 1999, (45): 1043–1051.
122. Lei Zhang, Paul Bao, Edge detection by scale multiplication in wavelet domain. Patten Recognition letters, 2002, Vol. 23: 1771-1784.
123. D. Brzakovic, D. T. Khani, B. Awad, A vision system for monitoring weld pool. Proceeding of the 1992 IEEE International Conference on robotics and automation Nico, France, 1992: 1609-1614.
124. Y.M.Zhang, L.Li, R.Kovacevic. Dynamic estimation of full penetration using geometry of adjacent weld pools. ASME Journal of Manufacturing Science and Engineering, 1997,Vol. 119(11): 631-643.
125.何斌等,数字图像处理,人民邮电出版社,2002年第二版.
126.林尚扬,陈善本,李成桐,焊接机器人机器应用,北京,机械工业出版社, 2000: 145-148.
127.薛定宇,控制系统计算机辅助设计,北京,清华大学出版社,1996.
128.飞思科技产品研发中心,Matlab 6.5辅助神经网络分析与设计,北京,电子工业出版社,2003,72-74.
129.徐丽娜,神经网络控制,哈尔滨,哈尔滨工业大学出版社,1998.
130. Simon Haykin,神经网络原理,北京,机械工业出版社,2003.
131.方崇智,萧德云,北京,清华大学出版社,1988.
132.候媛彬,汪梅,王立琦,系统辨识及其Matlab仿真,北京,科学出版社,2004.
133.石纯一,王家钦,数理逻辑与集合论,北京:清华大学出版社, 2000.
134.马振华,离散数学导引,北京,清华大学出版社, 1993.
135. C. E. Shannon, A mathematical theory of communication, bell syst, Tech. J, 1948, 27 (3), 379–423.
136. J. R. Quinlan, Induction of decision trees, Machine Learning, 1986, 1 (1), 81-106.
137. J. G. Bazan, A..Skowron, P. Synak, Dynamic reducts as a tool for extracting laws from decisions tables, Proceedings of the 8th International Symposium on Methodologies for Intelligent Systems, 1994, 346-355.
138. J. Bazan, A comparison of dynamic and non-dynamic rough set methods for extracting laws from decision tables, Rough Sets in Knowledge Discovery, 1998, 1, 321–365
2. H. C. Wikle, S. Kottilingam, R. H. Zee, and B. A. Chin, Infrared sensing techniques for penetration depth control of the submerged arc welding process. Journal of materials processing technology. 2001,vol.113:228-233.
3. J. P. Boillot and G. Begin,Adaptive Welding by Fiber Optic Thermographic Sensing: an Analysis of Thermal and Instrumental Considerations. Welding Journal. 1985, Vol. 64(7): 31-37.
4. George,M. Graham and I. Charles, Automated system for laser ultrasonic sensing of weld penetration. Journal of Nuclear Materials, 1998:711-721.
5. R. Fenn,Ultrasonic Monitoring and Control During Arc Welding,Welding Journal. 1985, Vol.64(9): 18-24.
6. N. M. Carlson and J. A. Johnson,Ultrasonic Sensing of Weld Pool Penetration. Welding Journal. 1988, Vol. 67(11): 239-246.
7. M. Futamata, Application of arc sound for detection of welding process, Quarterty journal of the Japan welding society, 1983,1(1):11-14.
8. R. J. Renwick, Real-time control of GAT weld size by controlling pool oscillation frequency, CWR technical report, June 1983.
9. R. J. Renwick, Experimental investigation of GAT weld pool oscillation, Welding journal, 1983, 62(2):29-34.
10.耿正,铝合金TIG焊电弧传感熔池自激振荡法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
11.吴林,董德祥,陈定华,固定点状态下TIG焊接熔深信号的检测及分析,焊接学报,1986, Vol.7(2):64-71.
12.陈善本.焊接智能化技术现状与发展.第十次全国焊接会议论文集.黑龙江人民出版社,2001:84~96
13. D.S. Nagesh. Prediction of Weld Bead Geometry and Penetration in Shielded Metal-arc Welding Using Artificial Neural Networks. Journal of Materials Processing Technology. 2002,123(2):303~312
14. Li Di, T. Srikanthanb, R.S. Chandelc. Neural-network-based Self-organized Fuzzy Logic Control for Arc Welding. Engineering Applications of Artificial Intelligence. 2001,14:115~124
15.周振丰,张文钺,焊接冶金与金属焊接性,北京,机械工业出版社,1988.
16. Hirokazu Nomura. Sensor and Control System in Arc Welding. Chapman & Hall. 1994:3~5
17. M. Ushio and W. Mao, Sensors for Arc Welding: Advantages and Limitations. Transactions of JWRI. 1994,23(2):135~141
18. A. E. Bentley and S. J. Marberger,Arc Welding Penetration Control Using Quantitative Feedback Theory,Welding Journal,1992, Vol. 71(11): 397-405.
19.张裕明,TIG焊熔透正面视觉自适应控制的研究[博士学位论文],哈尔滨,哈尔滨工业大学,1990.
20.张裕明,吴林,TIG焊熔透正面监测量的确定,焊接学报,1991,Vol.12(1):39-45.
21. H.S. Song, Y.M. Zhang, Three-dimentional reconstruction of specular surface for a gas tungsten are weld pool, Measurement Science and Technology, 2007, Vol.18: 3751-3767.
22. H.S. Song, Y.M. Zhang, Image processing for measurement of three-dimensional GTA weld pool surface, Welding Journal, 2007, Vol. 86(10): 323-330.
23. R. Kovacevic and Y. M. Zhang,Real-Time Image Processing for Monitoring of Free Weld Pool Surface,Journal of Manufacturing Science and Engineering. 1997,Vol. 119(5): 161-169.
24. H.S. Song, Y.M. Zhang, Measurement and analysis of three-dimensional specular gas tungsten arc weld pool surface, Welding Journal, 2008, Vol. 87(4): 85- 95.
25. Y. M. Zhang, M. Beardsley and R. Kovacevic, Real-time Image Processing for 3D Measurement of Weld Pool Surface,Manufacturing Science and Engineering. 1994,PED-vol. 68(1): 255-262.
26.张远鹏,董海,周文灵.计算机图像处理技术基础,北京,北京大学出版社.1996.
27. R. J. Beatlie,S. K. Cheng,P. S. Logue,The Use of Vision Sensors in Multi-pass Welding Applications. Welding Journal,1988, Vol.67(11):28-33.
28. C. G. Morgan,J. S. Bromley,P. G. Davey,Visual Guidance Techniques for Robot Arc Welding,Proceeding of 3rd International Conference on Robot Vision and Sensory Controls, 1983: 615-619.
29. G.Agapiou, C.Kasiouras, A.A.Serafeintides, A detailed analysis of the MIG spectrum for the development of laser-based seam tracking sensors, Optics& Laser Technology,1999,31:157-161.
30. Jae seon Kim, Young Tak Son, Hyung Suck Cho and Kwang ii Koh, A robust visual seam tracking system for arc welding, Mechatronics, 1996, 6(2):141-163.
31. J.E. Agapakis, J. Bolstad. Vision Sensing and Processing System for Monitoring and Control of Welding and Other High Luminosity Processes. International Robots&Vision Automation Conference, 1991:23~29
32. S. Nakata, J. Huang, Y. Tsuruha. Visual Sensing System for In-Process Control of Arc Welding Process. Welding International. 1988, (12):1086~1090
33. R. Kovacevic, Y.M. Zhang. Three-dimension Measurement of Weld Pool Surface. Proceedings of the International Conference on Modeling and Control of Joining Processeses, Oriando, Florida, USA, 1993:600~607
34. R.W. Richardson, D.A. Gutow. Coaxial Arc Weld Pool Viewing for Process Monitoring and Control. Welding Journal. 1984,63(3):43~50
35. D. Brzakovic, D.T. Khani. Weld Pool Edge Detection for Automated Control of Welding. IEEE Transactions on Robotics and Automation. 1991,7(3):397~403
36. K. Oshima, M. Morita. Observation and Digital Control of the Molten Pool in Pulsed MIG Welding. Welding International. 1988, (3):234~240
37. K. Oshima, M. Morita. Sensing and Digital Control of Weld Pool in Pulsed MIG Welding. Transactions of the Japan Welding Society. 1992,23(4):36~42
38.王克争,大岛健司. MIG焊接熔池的图象处理和数字控制系统.清华大学学报. 1990,30(2):22~29
39.陈武柱,井上胜敬.图象处理在窄间隙MIG/MAG焊在线检测中的应用.焊接学报. 1988,9(4):247~253
40.肖强.焊接机器人视觉系统.焊接. 1992, (4):7~10
41.宋永伦.弧焊区图象信息的光谱传感技术.焊接学报. 1992,13(2): 127~132
42.黄石生. TIG焊熔宽的自整定PID闭环控制系统的研究.电焊机. 1993, (5): 6~11
43.刘玉池.计算机视觉脉冲TIG焊正面实时检测与熔宽控制的研究.哈尔滨工业大学硕士学位论文. 1994
44.黄斌.脉冲TIG焊熔池系统的智能控制研究.哈尔滨工业大学硕士学位论文. 1995
45.李鹏九.焊接过程弧光传感的应用基础研究.哈尔滨工业大学博士学位论文. 1997
46.娄亚军,戴明,陈善本.脉冲TIG焊正反面熔池同时同幅图象传感.机器人. 1997,19(1):59~63
47.赵冬斌.由单目图象获得表面高度算法的分析和实现.计算机学报. 2000, 23(2):147~152
48. K. A. Pietrzak, S. M. Packer,Vision-Based Weld Pool Width Control. ASME Journal of Engineering for Industry,1994, 116(2):86-92
49.刘晓东,变间隙对接脉冲GTAW视觉传感与神经网络建模研究[硕士学位论文],哈尔滨,哈尔滨工业大学,2001。
50. G. J. Zhang, S. B. Chen, L. Wu, Intelligent control of pulsed GTAW with filler metal, Welding Journal, 2005, 84 (1): 9-16.
51.王建军,铝合金脉冲TIG焊熔池动态特征的视觉信息获取与自适应控制[博士学位论文],上海,上海交通大学,2003
52. K.Y. Bae, T.H. Lee, K.C. Ahn. An optical sensing system for seam tracking and weld pool control in gas metal arc welding of steel pipe, Journal of Materials Processing Technology,2002, 120: 458-465.
53. Y.M. Zhang, L. Li, R. Kovacevic. Monitoring of Weld Pool Appearance for Penetration Control.4th International Conference on Trends in Welding Research, Gatlinburg, Tennessee, USA, 1995:30~35
54. E.W. Kim, C. Allemand and T.W. Eagar. Visible Light Emissions during Gas Tungsten Arc Welding and Its Application to Weld Image Improvement. Welding Journal. 1987,66(12):369s~377s
55.赵冬斌,基于三维视觉传感的填丝脉冲GTAW熔池形状动态智能控制[博士学位论文],哈尔滨,哈尔滨工业大学,2000.
56. Laiping Li, Shanben Chen, Tao Lin, The modeling of welding pool surface reflectance of aluminum alloy pulse GTAW, Materials Science and Engineering: A, 394(2005): 320~326
57. L. P. Li, S.B.Chen, and T.Lin, The Light Intensity Analysis of Passive Visual Sensing System in GTAW. The international journal of advanced manufacturing technology, UK, 2005.1
58. Laiping Li, Shanben Chen, Tao Lin, 3D Vision Technology and its applications in Welding, The Eighth International conference on Control, Automation, Robotics and Vision, ICARCV 2004, Kunming, China, 6-9,December, 2004, 190~198.
59.李来平,脉冲GTAW熔池表面反射图建模与高度计算的研究[博士学位论文],上海,上海交通大学,2005
60. Quanying Du, Shanben Chen and Tao Lin, Inspection on Shape of Weld Based on Shape from Shading. The International Journal of Advanced Manufacturing Technology, 2006, Vol.27:667-671.
61. QuanYing Du, ShanBen Chen and Tao Lin, An Application of Shape from Shading. ICARCV 2004 - Proceedings of the 8th International Conference on Control, Automation, Robotics and Vision, 2004, 184-189.
62.杜全营,填丝脉冲GTAW熔池三维特征实时提取与智能控制[博士学位论文],上海,上海交通大学,2006
63.鄢景华,自动控制原理,哈尔滨工业大学出版社,1996.
64.胡德文,非线性与多变量系统相关辨识,国防科技大学出版社,2001.
65. Kou and Y. H. Wang , Weld Pool Convection and Its Effect , Welding Journal. 1986, Vol.65(3):63-70.
66.曹振宁,TIG/MIG焊接熔透熔池流场与热场的数值分析[博士学位论文],哈尔滨,哈尔滨工业大学工学,1993.
67. D. J. Kotecki, Mechanism of ripple formation during weld solidification, Welding journal, 1972, Vol.51(8):386-394.
68. Q. L. Wang,Detection of the weld full prentration signals of a traveling arc in GTAW process, proceedings of IIW Asian pacific regional welding congress, 1988, Hobart.
69.杨春利,薄钢板TIG焊电弧传感熔池谐振法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
70.耿正,铝合金TIG焊电弧传感熔池自激振荡法熔透实时控制[博士学位论文],哈尔滨,哈尔滨工业大学,1991.
71.王其隆,张九海,杨春利,快速行走TIG焊接时熔透信号的提取及分析,焊接学报,1992,Vol.11(3): 175-179.
72. J. F. Kotnik, The control and analysis of full-peneteration plused-GAT welds using weld pool oscillation sensing, Masters thesis, 1986.
73. S. B. Chen, L. Wu, and Q. L. Wang, etc, Self-learning Fuzzy Neural Network and Computer Vision for Control of Pulsed GTAW. Welding Journal. 1997, Vol.76(5): 201-209.
74. S. B. Chen, L. Wu and Q. L. Wang, Self-learning Fuzzy Neural Networks for Control of Uncertain Systems with Time Delay. IEEE Transactions on System, Man, and Cybernetics-Part B: Cybernetics. 1997, Vol .27(1):142-148.
75.陈善本,吴林,王其隆,人工神经网络及其在焊接控制中的展望,哈尔滨工业大学学报,1994,26(1):20-26
76.黄石生,李迪,焊接过程的神经网络建模及控制的研究,机械工程学报,1994,30(3):24-29.
77. Y. J. Lou, S. B. Chen and L. Wu,Neuron PSD Control Based on Sensing Image of Weld Pool During Pulsed GTAW. Proceedings of International Conference on Manufacturing Science, Wuhan, P.R.China, 10-12, June, 1998.
78. Yajun Lou, Shanben Chen and Lin Wu, Monitoring of Weld Joint Penetration Based on Sensing Double-side Vision Images of Weld Pool,Journal of Harbin Institute of Technology, 1998, vol.7(11):22-27.
79. Y.S. Tarng. Modeling, Optimization and Classification of Weld Quality in Tungsten Inert Gas Welding, International Journal of Machine Tools & Manufacture, 1999,39:1427-1438.
80. S.C. Juang, Y.S. Tarng, A Comparison between the Back-propagation and Counter-propagation Networks in the Modeling of the TIG Welding Process, Journal of Materials Processing Technology, 1998,75:54-62.
81. Billy Chan, Modeling Gas Metal Arc Weld Geometry Using Artificial Neural Network Technology, Canadian Metallurgical Quarterly, 1999,38(1): 43-51.
82. George E. Cook, Weld Modeling and Control Using Artificial Neural Networks, IEEE Transactions on Industry Applications, 1995,31(6): 1484-1491.
83. Jengywan Jeng, Prediction of Laser Butt Joint Welding Parameters Using Back Propagation and Learning Vector Quantization Networks, Journal of Materials Processing Technology, 2000,99:207-218.
84. Yasuo Suga, Measurement of Molten Pool Shape and Penetration Control Applying Neural Network in TIG Welding of Thin Steel Plates, ISIJ international, 1999,39(10):1075-1080.
85. Kovacevic, Y.M. Zhang, and L. Li, Monitoring of Weld Penetration Based on Weld Pool Geometrical Appearance, Welding Journal, 1996,75(10):317-328.
86.李迪,用人工神经元网络技术对焊接质量的智能控制,华南理工大学博士学位论文, 1993.
87.李迪,黄石生,宋永伦,用神经元网络技术对焊缝质量的直接控制,第七届全国焊接学术会议论文集(第3分册),H-XX-001-93.
88.娄亚军,基于熔池图像传感的脉冲GTAW动态过程智能控制,哈尔滨工业大学博士学位论文.1998.
89.张广军,视觉传感的变间隙填丝脉冲GTAW对接焊缝成形智能控制,哈尔滨工业大学博士学位论文,2002.
90. Wang B., Chen S. B., Wang J. J., Rough set based knowledge modeling for the aluminum alloy pulsed gtaw process, The International Journal of Advanced Manufacturing Technology, 2005, 25 (9), 902-908.
91.黎文航,基于变精度粗糙集理论的焊接动态过程知识建模方法研究[博士学位论文],上海,上海交通大学,2007.
92.李士勇.模糊控制、神经控制和智能控制论.哈尔滨工业大学出版社. 1996,8:1~7
93. Charalabos Doumanidis. Multivariable Adaptive Control of the Bead Profile Geometry in Gas Metal Arc Welding with Thermal Scanning. International Journal of Pressure Vessels and Piping. 2002,79:251~262
94. Y.M. Zhang. Adaptive Control of Full Penetration Gas Tungsten Arc Welding. IEEE Transactions on Control System Technology. 1996,4(4): 394~403
95.赵彭生,萧波.焊接过程的自动控制(概况与趋势).焊接技术. 1993,(2):37~40
96. Akira Hirai. Sensing and Control of Weld Pool by Fuzzy-Neural Network in Robotic Welding System. The 27th Annual Conference of the IEEE Industrial Electronics Society. 2001,238~242
97. Mary A. Austin. Real-Time Multi-Processing Fuzzy Logic Adaptive Control Gas Tungsten Arc Welding System. The IEEE Proceedings of the 4th WPDRTS. 1996:139~142
98. Andre Bigand. Arc Welding Fuzzy Control Using Neural Net Supervisor. IEEE. 1996:2003~2006
99. Y.M. Zhang. Neuro-fuzzy Model Based Control of Weld Fusion Zone Geometry. The Proceedings of the American Control Conference. 1997,6: 2483~2487
100. K.J. Hunt. Neural Networks for Control System: A Survey. Automatica. 1992.28(6):1083~1112
101. Bob Irving. Neural Networks Are Paying Off on the Production Line. Welding Journal. 1997,76(10):59~64.
102. S.S. Huang, D. Li. Weld Quality Control by Neural Network. Welding in the Word. 1994,34:359~363
103. Y. Kaneke, T. Iisaka and K. Oshima. Neuro-fuzzy Control of the Weld Pool in Pulsed MIG Welding. Welding International. 1995,9(3):191~196
104. T.G. Lim,H.S. Cho.Estimation of Weld Pool Sizes in GMA Welding Process Using Neural Networks.Journal of Systems and Control Engineering.1993,207(1):15~26
105. Jay F. Tu, N.L. Dishore. On-line Estimation of Laser Weld Penetration. ASME Journal of dynamic Systems, Measurement, and Control. 1997, 119:791~801
106. J.W. Kim,S.J. Na.A Self-organizing Fuzzy Control Approach to Arc Sensor for Weld Joint Tracking in Gas Metal Arc Welding of Butt Joints. Welding Journal. 1993,72(1):60s~66s
107. S.B. Chen, L. Wu, Q.L. Wang and Y.C. Liu. Self-learning Fuzzy Neural Network and Computer Vision for Control of Pulsed GTAW. Welding Journal. 1997,76(5):201s~209s
108. S.B. Chen, L. Wu, Q.L. Wang. Self-learning Fuzzy Neural Networks for Control of Uncertain Systems with Time Delay. IEEE Transactions on System, Man, and Cybernetics-Part B: Cybernetics. 1997,27(1):142~148
109. D.A. Hartman. Intelligent Control in Arc Welding. Intelligent Engineering Systems Through Artificial Neural Networks, ASME. 1999:715~725
110.黄石生,贺剑峰,宋永伦.钨极氩弧焊焊缝熔宽模糊控制系统设计.焊接学报. 1996,17(2):94~98
111. Y. Suga. Application of Neural Network to Visual Sensing of Weld Line and Automatic Tracking in Robot Welding. Welding in the World. 1994,34: 275~282
112. Kristinn Andersen. Artificial Neural Networks Applied to Arc Welding Process Modeling and Control. IEEE Transactions on Industry Applications. 1990,26(5):824~830
113. Xiangdong Gao, Shisheng Huang. Fuzzy Neural Networks for Control of Penetration Depth during GTAW. China Welding. 2000,1:1~8
114.刘中华,视觉传感VPPAW焊缝成形实时控制系统[博士学位论文],哈尔滨,哈尔滨工业大学,2001.
115. Zhonghua Liu and Qilong Wang, Process control based on double-side sensing of the keyhole in the VPPA welding. Journal of material technology and processing, Elsevier science, 2001, 115(2):373-379.
116. J.J. Wang, T. Lin, S.B. Chen, Obtaining weld pool vision information during aluminium alloy TIG welding, International Journal of Advanced Manufacturing Technology, 2005, 26(3): 219-227.
117.张淑荣,焊接过程粗糙集建模中推理方法的研究[硕士学位论文],上海,上海交通大学, 2004.
118.王惠钧,图像传感变极性等离子弧焊缝稳定成形闭环控制[博士学位论文],哈尔滨,哈尔滨工业大学,1998,19-23.
119.贾云得,机器视觉,北京,科学出版社,2000: 12-15.
120.成礼智,王红霞,罗永,小波的理论与应用,北京,科学出版社,2004: 303-305.
121. B.M. Sadler, A. Swami, Analysis of multiscale products for step detection and estimation[J]. IEEE Trans. Information Theory . 1999, (45): 1043–1051.
122. Lei Zhang, Paul Bao, Edge detection by scale multiplication in wavelet domain. Patten Recognition letters, 2002, Vol. 23: 1771-1784.
123. D. Brzakovic, D. T. Khani, B. Awad, A vision system for monitoring weld pool. Proceeding of the 1992 IEEE International Conference on robotics and automation Nico, France, 1992: 1609-1614.
124. Y.M.Zhang, L.Li, R.Kovacevic. Dynamic estimation of full penetration using geometry of adjacent weld pools. ASME Journal of Manufacturing Science and Engineering, 1997,Vol. 119(11): 631-643.
125.何斌等,数字图像处理,人民邮电出版社,2002年第二版.
126.林尚扬,陈善本,李成桐,焊接机器人机器应用,北京,机械工业出版社, 2000: 145-148.
127.薛定宇,控制系统计算机辅助设计,北京,清华大学出版社,1996.
128.飞思科技产品研发中心,Matlab 6.5辅助神经网络分析与设计,北京,电子工业出版社,2003,72-74.
129.徐丽娜,神经网络控制,哈尔滨,哈尔滨工业大学出版社,1998.
130. Simon Haykin,神经网络原理,北京,机械工业出版社,2003.
131.方崇智,萧德云,北京,清华大学出版社,1988.
132.候媛彬,汪梅,王立琦,系统辨识及其Matlab仿真,北京,科学出版社,2004.
133.石纯一,王家钦,数理逻辑与集合论,北京:清华大学出版社, 2000.
134.马振华,离散数学导引,北京,清华大学出版社, 1993.
135. C. E. Shannon, A mathematical theory of communication, bell syst, Tech. J, 1948, 27 (3), 379–423.
136. J. R. Quinlan, Induction of decision trees, Machine Learning, 1986, 1 (1), 81-106.
137. J. G. Bazan, A..Skowron, P. Synak, Dynamic reducts as a tool for extracting laws from decisions tables, Proceedings of the 8th International Symposium on Methodologies for Intelligent Systems, 1994, 346-355.
138. J. Bazan, A comparison of dynamic and non-dynamic rough set methods for extracting laws from decision tables, Rough Sets in Knowledge Discovery, 1998, 1, 321–365