Neurofuzzy modelling of the reflow thermal profile for surface mount assembly

Troubleshooting and production set-up time are often the major contributors for productivity loss in surface mount assembly. The solder reflow process is one of the least understood process segments. The research proposes a neurofuzzy reflow thermal profile control system for a convection oven. An incompatible temperature profile can result in a poor soldering quality and reduced system throughput. This paper proposes a neurofuzzy-based solder reflow thermal profile control system that responds to facilitate the production set-up process. The model is trained and constructed using data from both an experimental design and from historical production records. Customized computer code is used to generate a user-friendly human–machine interface and to link between neurofuzzy-reasoning rules and reflow oven set-up parameters for thermal profile planning and control. Empirical results illustrate the effectiveness and efficiency of the proposed system to solve a practical application.

[1]  J. Lau,et al.  Solder Joint Reliability of BGA, CSP, Flip Chip, and Fine Pitch SMT Assemblies , 1996 .

[2]  Wenhua Wang,et al.  Intelligent materials processing by hyperspace data mining , 2000 .

[3]  Michael J. Shaw,et al.  Knowledge management and data mining for marketing , 2001, Decis. Support Syst..

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  M. F. Franklin.  Constructing Tables of Minimum Aberration pn-m Designs , 1984 .

[6]  Harpreet Singh,et al.  A neuro fuzzy logic approach to material processing , 1999, IEEE Trans. Syst. Man Cybern. Part C.

[7]  Krishnaswami Srihari,et al.  A profile identification system for surface mount printed circuit board assembly , 1997 .

[8]  I. K. Hui,et al.  Wetting Analysis of Leadless Chips in Surface Mount Technology , 2000 .

[9]  Paul Conway,et al.  Effective modeling of the reflow soldering process: use of a modeling tool for product and process design , 1998 .

[10]  Narasimha Bolloju.  Decision model formulation of subjective classification problem-solving knowledge using a neuro-fuzzy classifier and its effectiveness , 1999, Int. J. Approx. Reason..

[11]  Clyde F. Coombs,et al.  Printed Circuits Handbook , 2007 .

[12]  David W. Coit,et al.  Neural network open loop control system for wave soldering , 2002 .

[13]  Ahmad Lotfi,et al.  Learning fuzzy inference systems using an adaptive membership function scheme , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[14]  Ronald J. Patton,et al.  A study on neuro-fuzzy systems for fault diagnosis , 2000, Int. J. Syst. Sci..

[15]  David W. Coit,et al.  STATIC NEURAL NETWORK PROCESS MODELS : CONSIDERATIONS AND CASE STUDIES , 1998 .

[16]  Ahmad Lotfi,et al.  Industrial Application of Fuzzy Systems: Adaptive Fuzzy Control od Solder Paste Stencil Printing , 1998, Inf. Sci..

[17]  N. Lee,et al.  Optimizing the reflow profile via defect mechanism analysis , 1999 .

[18]  Francis K. H. Lau,et al.  A hierarchical evaluation of the solder paste printing process , 1997 .

[19]  Howard H. Manko,et al.  Soldering handbook for printed circuits and surface mounting : design, materials, processes, equipment, trouble-shooting, quality, economy, and line management , 1986 .

[20]  Paul Conway,et al.  A modelling tool for the thermal optimisation of the reflow soldering of printed circuit assemblies , 1998 .

[21]  Jing-Chung Shen,et al.  Fuzzy neural networks for tuning PID controller for plants with underdamped responses , 2001, IEEE Trans. Fuzzy Syst..