No Access

SIMULATION AND DESIGN OF A CONSTANT-CURRENT-CONTROLLED SPOT WELDING INVERTER WITH THE FUZZY NEURAL NETWORK

YONG ZHANG

Shaanxi Key Laboratory of Friction Welding Technologies, Northwestern Polytechnical University, Xi'an, 710072, China

Search for more papers by this author

HUA BAI

Department of Electrical and Computer Engineering, Kettering University, Flint, Michigan, 48504, USA

Search for more papers by this author

YONGQING CAI

Shaanxi Key Laboratory of Friction Welding Technologies, Northwestern Polytechnical University, Xi'an, 710072, China

Search for more papers by this author

TIEJUN MA

Shaanxi Key Laboratory of Friction Welding Technologies, Northwestern Polytechnical University, Xi'an, 710072, China

Search for more papers by this author

, and

HONGXIA XIE

Shaanxi Key Laboratory of Friction Welding Technologies, Northwestern Polytechnical University, Xi'an, 710072, China

Search for more papers by this author

https://doi.org/10.1142/S0218126611007621Cited by:0 (Source: Crossref)

Abstract

Resistance spot welding is a major metal connecting method in vehicle and other domestic electronic domains. Among all the welding techniques, the spot welding inverter is an important direction at the present time. The high nonlinearity and strongly coupled multiple parameters in the resistance spot welding process challenge the classical control theory based on some specific conditions and ideal assumptions, which in real practice obstacle the high-quality welding. This paper put the fuzzy neural network into a constant-current-controlled spot welding inverter, where the welding current peak and its variation are adopted as the input parameters and the duty ratio of the switches is regarded as the output. Eventually a five-layer feed-forward network was constructed, back propagation (BP) algorithm was applied to revise the adjustable parameters in the network, and a mathematical model was established to obtain the training samples serving for the network. The ultimate precision could reach 1.75%, the relative control error is 2.28% with strong external disturbances, the overmodulation is 3.35%, and the total modulating period is seven switching period, which indicated that the proposed algorithm has good performance.

This paper was recommended by Regional Editor Krishna Shenai.

Keywords:

References

M. El-Banna, D. Filev and R. B. Chinnam, Intelligent constant current control for resistance spot welding, IEEE Int. Conf. Fuzzy Systems pp. 1570–1577. Google Scholar
W. Qinget al., Weld. Join. 3, 7 (2000). Web of Science, Google Scholar
M. J. Karagoulis, Weld. J. 7, 27 (1994). Web of Science, Google Scholar
R. W. Messler Jr., M. Jou and C. J. Li, An intelligent control system for resistance spot welding using a neural network and fuzzy logic, Industry Appl. Conf. Record IEEE2 (1995) pp. 1757–1763. Google Scholar
L. Renhou , Intelligent Control Theory and Method ( Xidian University Press , Xi'an , 1999 ) . Google Scholar
L. Hua, Application of fuzzy control technology in constant-current-controlled AC spot welding, Dissertation submitted to Nanchang Institute of Aeronautical Technology (1990) . Google Scholar
M. A. Javed and S. A. C. Sanders, Neural networks based learning and adaptive control for manufacturing systems, Intelligent Robots and Systems, Intelligence for Mechanical Systems, Proceedings IROS, IEEE/RSJ Int. Workshop1 (1991) pp. 242–246. Google Scholar
S. Hu, China Mech. Eng. 8, 24 (1997). Google Scholar
L. P. Khoo and H. Y. Young, Int. J. Prod. Res. 33, 2023 (1995), DOI: 10.1080/00207549508904796. Crossref, Web of Science, Google Scholar
X. Chen, K. Araki and T. Mizuno, Modeling and fuzzy control of the resistance spot welding process, Proc. 36th SICE Ann. Conf., International Session Papers (1997), 989–994 . Google Scholar
J. Shriver, H. Peng and S. J. Hu, Control of resistance spot welding, Am. Control Conf. Proc.1 (1999) pp. 187–191. Google Scholar
J. D. Brown and M. G. Rodd, Iron Making Steel Making 25, 199 (1998). Web of Science, Google Scholar
F. Pinget al., Chin. J. Aeronautics 1, 94 (2000). Google Scholar
H. Zhu and W. Liang, J. LuoYang Instit. Technol. 3, 17 (2001). Google Scholar
Y. Cho and S. Rhee, IEEE Trans. Instrum. Meas. 53, 330 (2004), DOI: 10.1109/TIM.2003.822713. Crossref, Web of Science, Google Scholar
Y. Wu, H. Serizawa and H. Murakawa, Trans. JWRI 32, 277 (2003). Web of Science, Google Scholar
X. Wuet al., Weld. Join. 3, 19 (2001). Web of Science, Google Scholar
K. Zhang, F. Qian and M. Liu, Inform. Control 32, 431 (2003). Google Scholar
S. R. Leeet al., J. Manufact. Syst. 20, 320 (2001). Crossref, Web of Science, Google Scholar
P. Fang, Study on intelligent control system of resistance spot welding based on DSP, Dissertation submitted to South China University of Technology (2002) . Google Scholar
Z. Linet al., Study on real-time measurement of nugget diameter for resistance spot welding using a neuro-fuzzy algorithm, Instrumentation and Measurement Technology Conf. IMTC 04, Proc. 21st IEEE3 (2004) pp. 2230–2233. Google Scholar
A. Prateepasen, P. Kaewtrakulpong and C. Jirarungsatean, Classification of DC micro spot welding quality using fuzzy ARTMAP on acoustic emission monitoring, 2004 IEEE Region 10 Conf. D (2004) pp. 649–652. Google Scholar
S. Huang and W. Yu, Elect. Welding Mach. 3, 29 (2000). Google Scholar
N. Zhang and P. Yan , Artificial Neural Networks and Fuzzy Control ( TsingHua University Press , Beijing , 1998 ) . Google Scholar
X. Wu, Soft-switching spot welding inverter power and digital microcomputer control system, Dissertation submitted to South China University of Technology (2002) . Google Scholar
Y. Zhang, Study on soft-switching and fuzzy neural network control for spot welding inverter power, Dissertation submitted to Northwestern Polytechnical University (2006) . Google Scholar