摘要
电阻点焊质量在线监控是汽车装配生产中亟待解决的问题。电阻焊过程中
电流、电压信号既反映输入能量,又反映熔核形成过程接头阻抗的动态变化。
影响焊接质量的各种随机因素,均直接或间接地体现在电流、电压等信号的变
化中。但由于影响因素的不确定性、非线性和相互耦合,故不能直观地从波形
中加以观测。因此,本课题以电阻点焊质量在线监控为目的,电流、电压等焊接
动态信号为对象,用现代信号分析方法研究信号的时频特征,提取信号中隐含
的信息。通过建立人工神经网络模型来预测点焊接头熔核尺寸。论文工作主要
包括以下内容:
研制了以KS2062型A/D卡为核心的数据采集系统,对点焊焊接过程中的
电压、电流等信号进行同步采集,采集系统软件由C++语言编写,能够显示信
号波形,并进行预处理。利用时域、频域、小波等多种方法对电流、电压等信
号进行分析,研究信号特征及其与电阻点焊过程的相关性。从信号分析角度丰
富对焊接过程的认识,为焊接缺陷在线识别和质量分类奠定基础。初步分析认
为,电流、电压信号波形以及接头动态电阻、加热功率的变化与熔核形态密切
相关,可用于电阻点焊接头质量的在线监控。电压、电流信号在频域里的变化
特征不明显,因此信号特征重点放在时域中分析和提取。
采用归一化处理后的周波参数时间序列构造网络输入向量,尝试两种不同
的网络对点焊接头熔核尺寸进行预测。对普通BP算法运算速度慢等缺点提出
分析并提出了相应的改善方法,大大提高了模型的运算速度和精度,较好的预
测了熔核尺寸。RBF网络是一种通过改变神经元非线性变换函数的参数以实现
非线性映射,从而大大加快学习速度并避免局部极小问题。另一方面,该网络
运用了多变量插值的径向基函数方法,使网络能实现高维空间的分类。因此,
RBF网络在焊接质量在线监控方面具有应用价值。
The on-line quality monitoring of spot welding is desiderated in automobile assembly process. In the process of resistance welding, the signals of voltage and current reflect both the input energy and the dynamic variation for joint impedance of forming the nugget. The random influence factors of welding quality must be present in the variety of welding signals directly or indirectly, but can't be observed simply because of its indetermination, non-linearity and coupling with each other. Purposed on on-line monitoring and controlling of resistance spot welding quality,the modern analysis methods of signals were adopted to analyse the characteristcs of dynamic welding current and voltage, and picked up the informations in them. Artificial Neural Networks(ANN) were used to predict the nugget sizes of resistance spot welder. The work was done as follows.
A signal collection system was developed with KS2062. The welding voltage and current were measured synchronously, which carried out displaying and presetting with the C+ +. Time-domain, frequency-domain and wavelet were used to analyse current, voltage, displacement signals in this thesis in order to research the relativity between the character of signals and the process of resistance spot welding. Enriched the recongition of the process of welding by the point of view signal analysis, the basic will be established for welding defect on-line identifying and quality classifying. It is concluded that the waveform of current, voltage signals and the variation of dynamic resistance, power of joint have related to nugget formation closely, so they can be used for on-line monitoring and controlling of joint quality of resistance spot welding. Because the variation of the signals of voltage and current is not obvious in frequency domain, the signal characters were stressly analysed and picked up in time domain.
The two different neural networks were used to predict the nugget sizes of resistance spot welder, in which the input vectors were constructed by the time sequences of cycle parameters normalized. The common BP Network was analysed. The effective methods were advanced to improve the rapidity and accuracy of the model, which have predicted nugget sizes availably. The Radial Basis Function (RBF) neutral network is a non-linear map by altering the parameters of non-linear activation functions of neuron so that it can improve the rapidity of networks and avoid the local minimality. On the other hand, the RBF neutral network can realize the classification of multi-dimension because it adopts the multivariate interpolation way based on the Radial Basis Functions. Therefore, the RBF neutral network will act a significant part in on-line monitoring and controlling of welding quality.
引文
1. 中国机械工程学会焊接学会电阻焊(Ⅲ)专业委员会.电阻焊理论与实践.北京:机械 工业出版社,1994:319-398
2. A.GLivshits. Universal Quality Assurance Method for Resistance Spot Welding Based on Dynamic Resistance. Welding Journal, 1997. 76(5) :383s-390s
3. 李树槐.点焊质量动态电阻阈值法自适应控制的研究.第六届全国焊接学术会议论文 集.西安:1990. H-Ⅲ b-0 14-90:139-143
4. 赵熹华.压力焊.机械工业出版社,1988:28-40
5. Jorn Burmeister et al. Automated Quality Assessment in Alternating Current Resistance Spot Welding by Fuzzy Classification. S.&S. 1994. (6) :E103-E106
6. 方婉莹.电阻焊理论与实践.机械工业出版社,1994. 1:291-397
7. 刘森.特种焊接工基本技术.金盾出版社,1998. 9:135-142
8. 耿正,高洪明.电阻焊设备及控制的研究进展.北京:第八次全国焊接会议论文集(1) . 北京:机械工业出版社,1997:1 69-1 75
9. 支楠,张旭明等.点焊恒流控制中电流检测系统的研究.电焊机.2001. (5) :15-17
10. 申哲.全桥式逆变直流点焊电源的研制及其焊接质量的控制.清华人学博士学位论 文.1991
11. 王笑川.电阻点焊临界电极电压法质量监控器的研究.焊接技术,1994. (1) :22-24
12. 唐廷乾.电阻点焊时用电极间电压监控焊接质量.焊接技术,1992(1) :8-13
13. A De, O P Gupta,L Dorn. An experimental study of resistance spot welding in 1mm thick sheet of low carbon steel. Proceedings of the Institution of Mechanical Engineers. 1996,210,4
14. 马凯等.动态电阻点焊监控系统多参数分时段的监控算法.接学报,2002. (1) :63-64
15. 吴林,陈善本.智能化焊接技术.国防工业出版社,2001. 5:149-191
16. 黄德智等.利用点焊过程中的动态电阻检测车身焊点质量.焊接,2003. (3) :9-13
17. Robert W.Messler,etc.An intelligent control system for resistance spot welding using a neural network and fuzzy logic.1995. 1757-1763
18. 常云龙,黄石生等.热膨胀电极位移法用于机器人点焊过程的研究.机器人,1999. (2) : 134-138
19. H Tang, W Hou, S J Hu. Forging force in resistance spot welding. Proceedings of the Institution of Mechanical Engineers. 2002,216,7
20. 胡德安等.电阻点焊热膨胀电极位移微机检测系统.电子与自动化,1997. (1) :10-13
21. 曹彪等.点焊过程热膨胀变形分析.焊接学报.1995. (6) :94-99
22. 刘效方.点焊质量电极位移法检测模型的设计.电焊机,1987. (3) :11-14
23. 姜以宏等.光栅测热膨胀位移点焊质量实时控制装置研制.全国焊接年会论文集 (7) ,1990:37-41
24. 黄明泰.铝合金点焊脉冲超声检测的研究.焊接研究与生产,1994,4(3) :1-5
25. Wei Li. Monitoring and diagnosis of resistance spot welding process. Degree of doctor of philosophy in the university of Michigan, 1999
26. MansourTM,吴明复译.薄板钢点焊超声波检测.无损探伤,1992. (5) :28-34
27. 杨思乾等.LY12铝合金焊点射线检测时的环形影象与熔核直径及热影响区组织的关 系.无损探伤,1994. (1) :17-19
28. 邓云生等.LY12 铝合金点焊区合金成分对X射线透照图象的影响.无损检 测,1991. 18(1) :1-5
29. 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
30. Mei Kobayashi, Listening for Defects: Wavelet-Based Acoustical Signal Processing in Japan. SIAM News, 1996. 3
31. 胡光锐.信号与系统.上海:上海交通大学出版社,1986
32. 印勇.随机信号分析.北京:中国物资出版社 1996
33. 沈凤麟,钱玉美 编著.陈宗(?) 审定.信号统计分析基础.合肥:中国科学技术大学出 版社,1989
34. S.W.Simpson. Information Processing in Welding: Welding sinatures and applications in industry. Welding in the world, Vol.43 1999. 7-8 No.4
35. 俞建容等.CO2弧焊特征参数的检测分析系统.第三届计算机在焊接中的应用技术交流 会论文集,2001. 11
36. 陈永彬.语音信号处理.上海:上海交通大学出版社,1984
37. 韩国明,云绍辉,李俊岳.熔滴过渡类型光谱信号自动识别软件系统[J]焊接学 报,2001,22(1) 19-23
38. 罗震,单平等.基于小波包分析的铝合金点焊飞溅研究.天津大学学报,2002,9
39. 罗震,胡绳菘等.用时频分析法研究铝合金电阻点焊过程中的声音信号,焊接学报, 2004. 25(1) 7-15
40. 赵纪元,何正嘉,孟庆丰,程正兴.小波包-自回归分析在振动诊断中的应用.振动工 程学报,1995. 3
41. 李迪等.基于电弧传感的GMAW过程焊缝缺陷识别方法.焊接学报,2000. 2
42. M. Hao, K.A. Osman. Developments in characterization of resistance spot welding of aluminum. Welding Journal, 1992. 75(5) :283s-324s
43. Y Cho, Y Kim, S Ree. Development of a quality estimation model using multivariate analysis during resistance spot welding. Proceedings of the Institution of Mechanical Engineers. 2001,215,11
44. 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.
45. 顾春艳等.一种采用恒压法的电阻点焊控制器.北方交通大学,2000. (1) :102-105
46. 尹孝辉等.点焊质量监控技术的发展与现状.焊接,2002. (2) :5-10
47. Hao M, Osman K A. Developments in characterization of resistance spot welding of aluminum[J]. Welding Journal, 1996(1) :52-56
48. S.R.Lee, Y J Choo, T Y Lee. A quality assurance technique for resistance spot welding using a neuro-fuzzy algorithm. Journal of manufacturing systems. 2001,20,5
49. 张乃尧,阎平凡. 神经网络与模糊控制[M].北京:清华大学出版社,2002.
50. 李士勇.模糊控制·神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社, 1996.
51. 张忠典,李严,何幸平等.人工神经元网络法估测点焊接头力学性能[J].焊接学报, 1997,18(1) :1-4.
52. 方平,谭义明,吴禄等.人工神经网络技术在点焊质量控制中的应用研究[J].航空学 报,2000,21(1) :94-95.
53. Osman K A, Higginson M, Kelly H R, et al. Monitoring of resistance spot welding using multi-layer perceptrons[J]. Artificial Neural Networks in Engineering-proceeding
(ANNIE’94) ,1994,(4) :1109-1114.
54. Arata Yoshiaki. Vibration analysis of base metal during welding, Transaction of JWRI,1981. 9
55. 刚铁,吴林.焊接缺陷的智能化模式识别与诊断.第九次全国焊接会议论文集,第1册, 哈尔滨:黑龙江人民出版社,1999:627-634
56. 刘文焕,王克争等.人工神经网络控制在焊接中的研究应用.电焊机,1997. 5
57. 陈强,王耀文,孙久文,孙振国.脉冲等离子焊接小孔效应的检测及控制,第十次全 国焊接会议论文集, 2-322
58. 王耀文,陈强,孙振国,孙久文,王海燕,等离子弧焊接穿孔行为的声信号传感,机 械工程学报,2001. 1
59. Jacques de Villiers. Back-propagation Neural Networks with One and Two Hidden Layers[J]. IEEE Trans on Neural Networks, 1992, 4 (1) :136-144.
60. 王宸煜,赵熹华等.基于人工神经网络的点焊工艺参数选择和质量预测.吉林工业大 学自然科学学报,1999. 29(1) :12-15
61. Thornton BY P H. Contact resistance in spot welding[J]. Welding Journal, 1996, 76(5) :402s-411s.
62. 邹积岩.罗哥夫斯基线圈测量电流的仿真计算及实验研究.电工技术学报,2001, 16(1) :81-84.
63. 樊宽军.微秒级电脉冲的测量.核技术,1999,22(8) :469-473.
64. 郭晓华,叶妙元,徐雁,朱明钧,张庆,廖京生,胡爱华.用于110Kv变压器的空心 线圈电流传感器研究.高压电器,2002. 6(3) :23-25
65. 王锡凡.电力工程基础.西安:西安交通大学出版社,1998
66. 翟小社,王颖,林莘.基于Rogowski线圈电流传感器的研制.高压电器,2002. 6(3) : 19-20
67. 樊宽军.微秒级电脉冲的测量.核技术,1999. 22(8) :469-473
68. 李海燕.毫秒级罗哥夫斯基线圈的研制.西安交通大学论文,1986
69. 马乃祥,周佩白.电磁干扰的预防.华东电力,1999. 2 7(11) :47-50
70. 冉启文.小波分析方法及其应用.哈尔滨:哈尔滨工业大学出版社,1995
71. 陈继东.小波分析应用于在线监测中的信噪分离的研究.电网技术,1999. 11
72. 杨福生.小波变换的工程分析与应用.北京:科学出版社,1999
73. 程正兴.小波分析算法及应用.西安:西安交通大学出版社,1998
74. A.Wiedand and R.Leighten. Geometric Analysis of Neural Network Capacity.in Pro.IEEE First IJCNN.1987. 1:385-392
75. B.Irie and S.Miyake. Capacity of Three-layered Perceptrons.in Pro. IEEE First IJCNN.1988. 1:641-648
76. S.M.Carroll and W.Dickinson. Construction of Neural Nets Using Random transform. in Pro.IEEE IJCNN. 1989. 1:607-611
77. K I.Funahashi. On the Approximate Realieation of Continuous Mapping by Neural Networks.Inter.Conf.NN. 1989. 2: 11-13
78. R.Hecht-Nielsen. Theory of the Backpropagation. Proc.lEEE IJCNN. 1989. 1:593-605
79. 闻新,周露,王丹力.MATLAB神经网络应用设计.科学出版社,2000. 9,212-232
80. 孙增圻等.智能控制理论与技术.清华大学出版社,1997. 4
81. Powell M J D. Radial basis functions for multivariate interpolation[A]. In: Mason J M, Cox M,eds. Algorithms for Approximation[C]. New York: Springer, 1985. 143-167.
82. Haykin S. Neural Networks: A Comprehensive Foundation[D]. Second edition. Beijing: Tsinghua University Press, 2001. 256-317.
83. 史忠植.知识发现[M].北京:清华大学出版社,2002
84. Chen S, Billing S A. Neural networks for nonlinear dynamic system modeling and identification[J]. Int. J Control. 1992, 56(2) :319-346.
85. 边肇祺,张学工等.模式识别.北京:清华大学出版社,2000.