Use ANN to Solve Function Regression Problem in Manufacturing

Abstract:

Engineers often meet function regression problems in manufacturing. In this work, we use artifical neural network to solve this problem. We choose a typical function as the target function. Since the input value of the function is continuous, the output of the regression model should also have a continuous value range. We implement the feed forward neural network with back propagation learning algorithm, investigate different network parameters, and compare several different training algorithms. The performance assessment based on the test dataset is also discussed.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 3119-3122
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.3119
• Online since: December 2010
• Authors: Qi Fan, Chang Jie Zhu, Bao Hua Wang, Jian Yu Xiao
• Keywords: Artificial Neural Network (ANN), Back Propagation, Feed Forward Neural Network, Function Regression

References

[1] HArtificial neural networks. California Inst. of Technol. Circuits and Devices Magazine: 2002(06).

[2] MH Hassoun. Fundamentals of artificial neural networks. 1995 - books. google. com.

[3] AK Jain, J Mao, KM Mohiuddin. Artificial neural networks: A tutorial. Computer, 1996 - ieeexplore. ieee. org.