基于电极位移曲线的点焊过程故障诊断
|
摘要
电阻点焊是一种高效、易于实现自动化的焊接方法,因而被广泛地应用于汽车制造和航空航天工业。由于电阻点焊熔核形成时间短,温度分布窄,焊接过程存在大量随机影响因素,仅通过稳定工艺参数无法完全避免焊接过程故障的产生,以及质量不合格焊点的出现。焊后检验作为质量保证体系虽必不可少,但其不具实时性。特别对于大量使用电阻焊的场合,发展一种点焊过程故障诊断和质量实时监控方法,取代或减少目前采用的焊后探伤和破坏性抽检,对提高生产率、降低成本,保证焊接质量具有重要意义。在点焊过程中,影响焊接质量的多种故障因素如工件翘曲、工件表面问题、网压波动和电极轴向错位等,均直接或间接地蕴涵在焊接电流、焊接电压、电极位移等信号的动态变化之中。本文以电极位移信号为主要信息源,通过对信号时域和波形特征分析,探索了一种基于信号实时监测和特征提取,对点焊过程故障进行在线诊断的新方法。论文工作内容包括:
1)搭建以AC6115(A/D)卡为核心的计算机数据采集系统,同步采集点焊过程中的焊接电流、焊接电压、电极位移信号,通过对上述信号的处理和分析表明:实时采集的焊接信号可以作为焊接故障分类和在线诊断的信息源。
2)针对实际生产中可能出现的故障因素,如工件翘曲、电极轴向错位、网压波动和表面问题等,将故障状态下的电极位移信号与正常焊接时的电极位移信号进行比较,结果表明各种故障因素均引起了电极位移信号的奇异性变化,造成焊点质量的变化。将这种奇异性变化作为点焊过程故障诊断的依据。
3)针对电极位移曲线,划分熔核形成的不同阶段,提取位移曲线中能描述故障状态下奇异性变化的特征参量,确定表征故障状态的电极位移特征向量集合。
4)以焊接电流、焊接时间和电极间压力为输入向量,以电极位移的特征参量上升斜率V_1、上升斜率V_2、下降斜率V_3、峰值位移S_1和结束位移S_2作为输出向量,建立了基于RBF神经网络的电极位移曲线预测模型。将预测的电极位移特征参量作为判别依据,建立了点焊过程故障分类规则。建立的这种故障分类方法,可实现点焊过程严重故障和一般故障的分类。
5)探索了一种基于案例推理的点焊过程故障诊断方法,针对几种典型的一般故障:电极轴向错位、网压波动和表面问题等,建立了基于相似优先比矩阵的案例检索模型,经有效性检验,该模型的诊断正确率为94%。
The resistance spot welding is a kind of highly efficient welding method, which is easy to realize automation. In the resitance spot welding, the time of the engendering nugget is short, and the distributing range of temperature is narrow, there are a lot of factors affect the quality, so only through stabilizing parameter of arts and crafts, which can not avoid completely producing welding faults and emergence of failed joint. It is necessary that we carry the test after welding, but it hasn't the character of real time. Especially when we using resistance spot welding, a method of welding process fault diagnosis and quality of real-time monitoring is set up to replace or reduce crack detection after welding and devastating spot test, to improve productivity and reduced cost, and to ensure quality of welding is of great significance. In welding process, the fault factors such as workpiece warping, untreated surface, voltage flunction, electrode axial misalignment and etc, which are directly and indirectly contained in the change of welding current, welding voltage and electrode displacement signals. In this paper, displacement electrode signal as the main source of information, through the analysis of time-domain and waveform characteristics, a new method, which can diagnose the faults in welding process, based on signal real-time monitoring and feature extraction is explored. The work was done as follows:
1) A data gathering system based on the core of AC6115 (A/D) card was developed, by which electrode voltage, welding current and electrode displacement signals were synchronously gathered. Through the above-mentioned signals processing and analysis show that: welding signals gathered can be used as information to classify and on-line diagnosis faults in welding process.
2) Fault factors such as workpiece warping, untreated surface, voltage flunction, electrode axial misalignment and etc, which may arise in the actual product environment, are simulated, and then compare electrode displacement signal in fault with electrode displacement signal in normal process. The preliminary analysis showed that all faults arises signals' strange change and quality change. The signals' strange change can be used to diagnosis faults in welding process.
3) Utilized the electrode displacement signals' parameter to devide the different phases of the nugget forming, and extracted characteristic parameters of electrode displacement curve, which could describe fault state of singularity changes, and by which a factor vector token as fault state could be get.
4) A prediction model based on RBF neural network is established to predict electrode displacement curve, in which the welding current, welding time and electrode pressure are as the input vectors, and the rising slope V_1, rising slope V_2, declining slope V_3, the peak displacement S_1 and the end displacement S_2 are as the output vectors. Judging by the characteristic parameters extracted, faults classification rules in welding process have established.
5) One kind of faults diagnosis method baced on case-based reasoning in welding process has probed. For several kinds' representative faults: electrode axial misalignment, voltage flunction, untreated surface and etc, a case retrieval model baced on fuzzy similar ratio is established, after validity checkout, the model diagnosis rightness rate's turn to be 94%.
1)搭建以AC6115(A/D)卡为核心的计算机数据采集系统,同步采集点焊过程中的焊接电流、焊接电压、电极位移信号,通过对上述信号的处理和分析表明:实时采集的焊接信号可以作为焊接故障分类和在线诊断的信息源。
2)针对实际生产中可能出现的故障因素,如工件翘曲、电极轴向错位、网压波动和表面问题等,将故障状态下的电极位移信号与正常焊接时的电极位移信号进行比较,结果表明各种故障因素均引起了电极位移信号的奇异性变化,造成焊点质量的变化。将这种奇异性变化作为点焊过程故障诊断的依据。
3)针对电极位移曲线,划分熔核形成的不同阶段,提取位移曲线中能描述故障状态下奇异性变化的特征参量,确定表征故障状态的电极位移特征向量集合。
4)以焊接电流、焊接时间和电极间压力为输入向量,以电极位移的特征参量上升斜率V_1、上升斜率V_2、下降斜率V_3、峰值位移S_1和结束位移S_2作为输出向量,建立了基于RBF神经网络的电极位移曲线预测模型。将预测的电极位移特征参量作为判别依据,建立了点焊过程故障分类规则。建立的这种故障分类方法,可实现点焊过程严重故障和一般故障的分类。
5)探索了一种基于案例推理的点焊过程故障诊断方法,针对几种典型的一般故障:电极轴向错位、网压波动和表面问题等,建立了基于相似优先比矩阵的案例检索模型,经有效性检验,该模型的诊断正确率为94%。
The resistance spot welding is a kind of highly efficient welding method, which is easy to realize automation. In the resitance spot welding, the time of the engendering nugget is short, and the distributing range of temperature is narrow, there are a lot of factors affect the quality, so only through stabilizing parameter of arts and crafts, which can not avoid completely producing welding faults and emergence of failed joint. It is necessary that we carry the test after welding, but it hasn't the character of real time. Especially when we using resistance spot welding, a method of welding process fault diagnosis and quality of real-time monitoring is set up to replace or reduce crack detection after welding and devastating spot test, to improve productivity and reduced cost, and to ensure quality of welding is of great significance. In welding process, the fault factors such as workpiece warping, untreated surface, voltage flunction, electrode axial misalignment and etc, which are directly and indirectly contained in the change of welding current, welding voltage and electrode displacement signals. In this paper, displacement electrode signal as the main source of information, through the analysis of time-domain and waveform characteristics, a new method, which can diagnose the faults in welding process, based on signal real-time monitoring and feature extraction is explored. The work was done as follows:
1) A data gathering system based on the core of AC6115 (A/D) card was developed, by which electrode voltage, welding current and electrode displacement signals were synchronously gathered. Through the above-mentioned signals processing and analysis show that: welding signals gathered can be used as information to classify and on-line diagnosis faults in welding process.
2) Fault factors such as workpiece warping, untreated surface, voltage flunction, electrode axial misalignment and etc, which may arise in the actual product environment, are simulated, and then compare electrode displacement signal in fault with electrode displacement signal in normal process. The preliminary analysis showed that all faults arises signals' strange change and quality change. The signals' strange change can be used to diagnosis faults in welding process.
3) Utilized the electrode displacement signals' parameter to devide the different phases of the nugget forming, and extracted characteristic parameters of electrode displacement curve, which could describe fault state of singularity changes, and by which a factor vector token as fault state could be get.
4) A prediction model based on RBF neural network is established to predict electrode displacement curve, in which the welding current, welding time and electrode pressure are as the input vectors, and the rising slope V_1, rising slope V_2, declining slope V_3, the peak displacement S_1 and the end displacement S_2 are as the output vectors. Judging by the characteristic parameters extracted, faults classification rules in welding process have established.
5) One kind of faults diagnosis method baced on case-based reasoning in welding process has probed. For several kinds' representative faults: electrode axial misalignment, voltage flunction, untreated surface and etc, a case retrieval model baced on fuzzy similar ratio is established, after validity checkout, the model diagnosis rightness rate's turn to be 94%.
引文
[1]中国机械工程学会焊接学会电阻焊(Ⅲ)专业委员会编著.电阻焊理论与实践.北京:机械工业出版社,1994:3-19-398
[2]吴林,陈善本.智能化焊接技术.北京:国防工业出版社,2000,8:120-191
[3]方婉莹.电阻焊理论与实践.北京:机械工业出版社,1994,1:291-397
[4]耿正,高洪明.电阻焊设备及控制的研究进展.见:第八次全国焊接会议论文集(1).北京:机械工业出版社,1997:169-175
[5]张延松.基于电极位移曲线的车身点焊过程故障诊断与控制方法研究:[上海交通大学博士论文].上海:上海交通大学机械与动力工程学院,2004
[6]Kaiser J G,Dunn G J and Eager T W.The effect of electrical resistance on nugget formation during spot welding.Welding Journal,1982,167s-174s
[7]Nagel G L and Lee A.A new approach to spot welding feedback control.SAE Technical Paper,1988,No.880371
[8]Holiday R,Parker J D and Williams N T.Electrode deformation when spot welding coated steels.Welding in the World,1995,35(3):23-27
[9]Holiday R,Parker J D and Williams N T.Factors affecting deformation electrode deformation when spot welding coated steels.Key Engineering Materials,1995,99:95-101
[10]Satoh T,Katayama J,Abe H,Fukuda Y,and Gohara K.Effects of mechanical properties of spot welding machine on electrode life on electrode life-2nd report-simulation test for electrode life and collision phenomenon of upper electrode,ⅡW Doc.No.Ⅲ-927-89,Helsinki.Finland,1989,9:13
[11]Satoh T,Katayama J and Okumura S.Effects of mechanical properties of spot welding machine on electrode life on electrode life for mile steel,ⅡW Doc.No.Ⅲ-912-88,1988
[12]Dorn,Lutz,Xu Ping.Influence of the mechanical properties of resistance welding machine on the quality of spot welding.Welding Research Abroad,1994,40(4):12-16
[13]Dorn,Lutz,Xu Ping.Investigations concerning the influence of the mechanical machine properties in resistance spot welding by means of a simulator.Sehweissen and S chneiden,1990,42(1):19-20
[14]Williams N T,Chilvers K and Wood K.The Relationship between machine dynamics of pedestal spot welding machines and electrode life,27p,Doc.No. Ⅲ-994-92,July,1992
[15]Howe P.The effect of spot welding machine characteristics on electrode life behavior on two welders.AWS Sheet Metal Welding Conference Ⅶ,Detroit,MI,1996
[16]Hahn O,Budde L and Hanitzsch D.Investigation on the influence of the mechanical properties of spot welding tongs on the welding process.Welding and Cutting,1990,1:6-8
[17]Tang H,Hou W,Hu S J and Zhang H.Influence of Welding Machine Mechanical Characteristics on the Resistance Spot Welding Process and Weld Quality.Welding Journal,2003,May:116s-24s
[18]Li W,Shaowei Cheng and Hu S J.Statistical Investigation on Resistance Spot Welding Quality Using a Two-State.Sliding-Level Experiment,Journal of Manufacturing Science and Engineering-Transactions of The ASME,2001,123(8):513-520
[19]Cho,S J,Hu and W Li.Resistance spot welding of aluminum and steel:a comparative experimental study.Proceedings of the institution of mechanical engineers B-Journal of Engineering Manufacture,2003,217(7):1355-1363
[20]胡敏.车身点焊装配偏差分析的建模方法研究:[上海交通大学博士学位论文].上海:上海交通大学机械与动力工程学院,2001
[21]Hao M,Osman K A,et al.Development in characteri-zation of resistance spot welding of aluminum[J].Welding Journal,1996,75(1):1-8
[22]Javed M A and Sanders SAC.Neural Network Based Learning Adaptive Control for Manufacturing System Proceeding of the 91.IEEE/RSJ,International Workshop on Intelligent Robots System,1991:242-246
[23]张忠典.基于动态电阻曲线的点焊质量多参量综合监测:[哈尔滨工业大学博士学位论文]哈尔滨:哈尔滨工业大学,1999
[24]Robert W,Messler Jr and Min Jou.An intelligent control system for resistance spot welding using a neural network and fuzzy logic.Conference Record-IAS Annual Meeting,1995.
[25]Tskums Masnori,Shinke Noboru,et al.Evaluation of function of spot-welded joint using ultrasonic inspection(nondestructive evaluation on tension shearing strength with neural network).In:Mechanics and Material Engineer,1996,39(10):626-632
[26]Brown J D,Rodd M G and Williams N T.Application of artificial intelligence techniques to resistance spot welding.Ironmaking and Steelmaking, 1998,25(3):199-204
[27]Dilthey U and Dickersbach J.Application of neural networks for quality evaluation for resistance spot welds.In:ISIJ Inr,1999,39(10):1061-1066
[28]马跃洲,种玉宝,陈剑虹等.电阻点焊熔核尺寸的RBF网络模型.兰州理工大学学报,2004,30(2):1-4
[29]张宏杰,张鹏贤,陈剑虹等.基于信号特征提取的电阻点焊质量在线监测.焊接学报,2005,26(9):52-57
[30]Lee SangRyong,Choo Yhoojun and TaeYoung.Neuro-fuzzy algorithm for quality assurance of resistance spot welding.IEEE Conference Record-IAS Annual Meeting,2000:1210-1216
[31]Lee S R and Choo Y J.A Quality Assurance Technique for Resistance Spot Welding using a Neural-Fuzzy Algorithm[J].Journal of Manufacturing System,2001,20(5):320-327
[32]程方杰,单平,廉金瑞等.铝合金连续点焊时电极烧损与焊点表面质量的变化规律.天津大学学报,2003,36(6):753-756
[33]薛海涛,宋永伦,李桓等.点焊过程工艺参数采集及缺陷信息分析.焊接学报,2004,25(8):104-106
[34]罗贤星,邓黎鹏,张晨曙等.铝合金点焊中影响因素的特征判识与熔核尺寸的评估.焊接学报,2005,26(7):37-43
[35]王亚荣,张忠典.镁合金电阻点焊接头中的缺陷.焊接学报,2006,27(7):9-12
[36]张旭强,罗爱辉,张延松等.点焊热镀锌双相高强度钢的电极磨损规律.焊接学报,2006,27(9):109-112
[37]赵欣,钱昌明,陈关龙.车身点焊接头虚焊缺陷超声快速识别.焊接学报,2006,27(11):17-20
[38]王道平,张义忠.故障智能诊断系统的理论与方法.北京:冶金工业出版社,2001,5:3-15
[39]胡昌华,许化龙.控制系统故障诊断与容错控制的分析和设计.北京:国防工业出版社,2000,7:3-7
[40]舒宁,马洪超,孙和利.模式识别的理论与方法.武汉:武汉大学出版社,2004
[41]吴大正,杨林耀,张永瑞.信号与线性系统分析.北京:高等教育出版社,1998,10
[42]胡广书.数字信号处理——理论算法与实现.北京:清华大学出版社,1997
[43]杨福生.小波变换的工程分析与应用.北京:科学出版社,1999
[44]孙如达等.点焊质量的判断及缺陷的预防.中国重汽科协获奖学术论文选编,2002～2003:164-168.
[45]王洪元,史国栋.人工神经网络技术及其应用.北京:中国石化出版社,2002
[46]飞思科技产品研发中心.神经网络理论与MATLAB7.0实现.北京:电子工业出版社,2005,12
[47]肖健华.智能模式识别方法.广州:华南理工大学出版社,2006,8
[48]舒宁,马洪超,孙和利.模式识别的理论与方法.武汉:武汉大学出版社,2004
[49]中国机械工程学会焊接学会.焊接手册第1册焊接方法及设备.北京:机械工业出版社,1992,11
[50]陈艳,张鹏.基于案例推理和故障树分析法融合的飞机故障诊断[J].自动化与仪表,2005(7),99-104
[2]吴林,陈善本.智能化焊接技术.北京:国防工业出版社,2000,8:120-191
[3]方婉莹.电阻焊理论与实践.北京:机械工业出版社,1994,1:291-397
[4]耿正,高洪明.电阻焊设备及控制的研究进展.见:第八次全国焊接会议论文集(1).北京:机械工业出版社,1997:169-175
[5]张延松.基于电极位移曲线的车身点焊过程故障诊断与控制方法研究:[上海交通大学博士论文].上海:上海交通大学机械与动力工程学院,2004
[6]Kaiser J G,Dunn G J and Eager T W.The effect of electrical resistance on nugget formation during spot welding.Welding Journal,1982,167s-174s
[7]Nagel G L and Lee A.A new approach to spot welding feedback control.SAE Technical Paper,1988,No.880371
[8]Holiday R,Parker J D and Williams N T.Electrode deformation when spot welding coated steels.Welding in the World,1995,35(3):23-27
[9]Holiday R,Parker J D and Williams N T.Factors affecting deformation electrode deformation when spot welding coated steels.Key Engineering Materials,1995,99:95-101
[10]Satoh T,Katayama J,Abe H,Fukuda Y,and Gohara K.Effects of mechanical properties of spot welding machine on electrode life on electrode life-2nd report-simulation test for electrode life and collision phenomenon of upper electrode,ⅡW Doc.No.Ⅲ-927-89,Helsinki.Finland,1989,9:13
[11]Satoh T,Katayama J and Okumura S.Effects of mechanical properties of spot welding machine on electrode life on electrode life for mile steel,ⅡW Doc.No.Ⅲ-912-88,1988
[12]Dorn,Lutz,Xu Ping.Influence of the mechanical properties of resistance welding machine on the quality of spot welding.Welding Research Abroad,1994,40(4):12-16
[13]Dorn,Lutz,Xu Ping.Investigations concerning the influence of the mechanical machine properties in resistance spot welding by means of a simulator.Sehweissen and S chneiden,1990,42(1):19-20
[14]Williams N T,Chilvers K and Wood K.The Relationship between machine dynamics of pedestal spot welding machines and electrode life,27p,Doc.No. Ⅲ-994-92,July,1992
[15]Howe P.The effect of spot welding machine characteristics on electrode life behavior on two welders.AWS Sheet Metal Welding Conference Ⅶ,Detroit,MI,1996
[16]Hahn O,Budde L and Hanitzsch D.Investigation on the influence of the mechanical properties of spot welding tongs on the welding process.Welding and Cutting,1990,1:6-8
[17]Tang H,Hou W,Hu S J and Zhang H.Influence of Welding Machine Mechanical Characteristics on the Resistance Spot Welding Process and Weld Quality.Welding Journal,2003,May:116s-24s
[18]Li W,Shaowei Cheng and Hu S J.Statistical Investigation on Resistance Spot Welding Quality Using a Two-State.Sliding-Level Experiment,Journal of Manufacturing Science and Engineering-Transactions of The ASME,2001,123(8):513-520
[19]Cho,S J,Hu and W Li.Resistance spot welding of aluminum and steel:a comparative experimental study.Proceedings of the institution of mechanical engineers B-Journal of Engineering Manufacture,2003,217(7):1355-1363
[20]胡敏.车身点焊装配偏差分析的建模方法研究:[上海交通大学博士学位论文].上海:上海交通大学机械与动力工程学院,2001
[21]Hao M,Osman K A,et al.Development in characteri-zation of resistance spot welding of aluminum[J].Welding Journal,1996,75(1):1-8
[22]Javed M A and Sanders SAC.Neural Network Based Learning Adaptive Control for Manufacturing System Proceeding of the 91.IEEE/RSJ,International Workshop on Intelligent Robots System,1991:242-246
[23]张忠典.基于动态电阻曲线的点焊质量多参量综合监测:[哈尔滨工业大学博士学位论文]哈尔滨:哈尔滨工业大学,1999
[24]Robert W,Messler Jr and Min Jou.An intelligent control system for resistance spot welding using a neural network and fuzzy logic.Conference Record-IAS Annual Meeting,1995.
[25]Tskums Masnori,Shinke Noboru,et al.Evaluation of function of spot-welded joint using ultrasonic inspection(nondestructive evaluation on tension shearing strength with neural network).In:Mechanics and Material Engineer,1996,39(10):626-632
[26]Brown J D,Rodd M G and Williams N T.Application of artificial intelligence techniques to resistance spot welding.Ironmaking and Steelmaking, 1998,25(3):199-204
[27]Dilthey U and Dickersbach J.Application of neural networks for quality evaluation for resistance spot welds.In:ISIJ Inr,1999,39(10):1061-1066
[28]马跃洲,种玉宝,陈剑虹等.电阻点焊熔核尺寸的RBF网络模型.兰州理工大学学报,2004,30(2):1-4
[29]张宏杰,张鹏贤,陈剑虹等.基于信号特征提取的电阻点焊质量在线监测.焊接学报,2005,26(9):52-57
[30]Lee SangRyong,Choo Yhoojun and TaeYoung.Neuro-fuzzy algorithm for quality assurance of resistance spot welding.IEEE Conference Record-IAS Annual Meeting,2000:1210-1216
[31]Lee S R and Choo Y J.A Quality Assurance Technique for Resistance Spot Welding using a Neural-Fuzzy Algorithm[J].Journal of Manufacturing System,2001,20(5):320-327
[32]程方杰,单平,廉金瑞等.铝合金连续点焊时电极烧损与焊点表面质量的变化规律.天津大学学报,2003,36(6):753-756
[33]薛海涛,宋永伦,李桓等.点焊过程工艺参数采集及缺陷信息分析.焊接学报,2004,25(8):104-106
[34]罗贤星,邓黎鹏,张晨曙等.铝合金点焊中影响因素的特征判识与熔核尺寸的评估.焊接学报,2005,26(7):37-43
[35]王亚荣,张忠典.镁合金电阻点焊接头中的缺陷.焊接学报,2006,27(7):9-12
[36]张旭强,罗爱辉,张延松等.点焊热镀锌双相高强度钢的电极磨损规律.焊接学报,2006,27(9):109-112
[37]赵欣,钱昌明,陈关龙.车身点焊接头虚焊缺陷超声快速识别.焊接学报,2006,27(11):17-20
[38]王道平,张义忠.故障智能诊断系统的理论与方法.北京:冶金工业出版社,2001,5:3-15
[39]胡昌华,许化龙.控制系统故障诊断与容错控制的分析和设计.北京:国防工业出版社,2000,7:3-7
[40]舒宁,马洪超,孙和利.模式识别的理论与方法.武汉:武汉大学出版社,2004
[41]吴大正,杨林耀,张永瑞.信号与线性系统分析.北京:高等教育出版社,1998,10
[42]胡广书.数字信号处理——理论算法与实现.北京:清华大学出版社,1997
[43]杨福生.小波变换的工程分析与应用.北京:科学出版社,1999
[44]孙如达等.点焊质量的判断及缺陷的预防.中国重汽科协获奖学术论文选编,2002～2003:164-168.
[45]王洪元,史国栋.人工神经网络技术及其应用.北京:中国石化出版社,2002
[46]飞思科技产品研发中心.神经网络理论与MATLAB7.0实现.北京:电子工业出版社,2005,12
[47]肖健华.智能模式识别方法.广州:华南理工大学出版社,2006,8
[48]舒宁,马洪超,孙和利.模式识别的理论与方法.武汉:武汉大学出版社,2004
[49]中国机械工程学会焊接学会.焊接手册第1册焊接方法及设备.北京:机械工业出版社,1992,11
[50]陈艳,张鹏.基于案例推理和故障树分析法融合的飞机故障诊断[J].自动化与仪表,2005(7),99-104