Journal
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
Volume 87, Issue 9-12, Pages 2943-2950Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00170-016-8649-6
Keywords
Laser brazing; Bead geometry; Prediction; Optimization; ELM; GA
Funding
- National Basic Research Program of China (973 Program) [2014CB046703]
- Fundamental Research Funds for the Central Universities (HUST) [2014QN016]
Ask authors/readers for more resources
Welding parameters play a significant role in determining the bead geometry and hence the quality of the weld joint. To further improve prediction accuracy and optimization quality of laser brazing, the published experiment results are utilized to build a prediction model of top and bottom width of weld bead and further establish an optimization model by a novel hybrid extreme learning machine and genetic algorithm method. Firstly, about two-third experiment results are used to train the extreme learning machine network for suitable weights, and then the rest one-third experiments are selected as a test set to illustrate the validity and reliability of the prediction network. Then, by regarding the prediction values from the extreme learning machine as the fitness values of genetic algorithm, optimal results of the inputs and outputs are obtained through the procedure of selection, crossover, and mutation. Eventually, the final optimization results are confirmed by verification experiments. Meanwhile, the hybrid model is more accurate and stable than that using back propagation neural network and genetic algorithm. In the whole, the proposed method in this paper is an effective and accurate way for optimizing laser brazing welding parameters and guiding the actual welding process.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available