Optimizing BP Networks by Means of Genetic Algorithms in Quality of Laser Milling

Artificial neural networks were introduced in the area of laser milling. The prediction model of surface quality in laser milling parts, including the width, depth of cladding layer, was proposed based on the back propagation (BP) neural networks. The model combined the global optimization searching performance of the genetic algorithm and the localization of the back propagation (BP) neural networks. Five technical parameters were selected to test the reliability of the model. The simulation and experimental results show that the evolutionary neural network based on genetic algorithm can effectively overcome the problem of falling into local minimum point. This method can get higher accuracy of prediction. It improves the measurement precision with the maximum relative error 2. 21% between the predicted content and the real value.

Download Full-text

Quality Prediction of Laser Cladding Based on Evolutionary Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.44-47.1012 ◽

2010 ◽

Vol 44-47 ◽

pp. 1012-1017

Author(s):

Zhao Mei Xu ◽

Hai Bing Wu ◽

Zong Hai Hong

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Neural Networks ◽

Laser Cladding ◽

Back Propagation ◽

Maximum Relative Error ◽

Technical Parameters ◽

Evolutionary Neural Network ◽

Real Value ◽

Accuracy Of Prediction

Artificial neural networks were introduced in the area of laser cladding forming. The prediction model of surface quality in laser cladding parts, including the width, depth of cladding layer and dilution rate, was proposed based on the improved learned arithmetic. The model combined the global optimization searching performance of the genetic algorithm and localization of the back propagation(BP) neural networks. Five technical parameters were selected to test the reliability of the mode. The simulation and experimental results show that the evolutionary neural network based on genetic algorithm can effectively overcome the problem of falling into local minimum point. This method can get higher accuracy of prediction. It improves the measurement precision with the maximum relative error 2.14% between the predicted content and the real value.

Download Full-text

Improved Artificial BP Neural Networks and Genetic Algorithm Used to Predict the Purity of the Artificial Synthetic Hydrotalcite

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.280-283.495 ◽

2007 ◽

Vol 280-283 ◽

pp. 495-498

Author(s):

Qiang Luo ◽

Qing Li Ren

Keyword(s):

Genetic Algorithm ◽

Neural Networks ◽

Prediction Model ◽

Process Parameters ◽

Learning Algorithm ◽

Back Propagation ◽

Raw Material ◽

Algorithm Analysis ◽

Neural Net ◽

Bp Neural Networks

A prediction model for purity of the artificial synthetic hydrotalcite under varied process parameters based on improved artificial back-propagation (BP) neural networks is developed. And the non-linear relationship between the hydrotalcite purity and the raw material adding amount of NaOH, MgCl2 and AlCl3 was established based on BP learning algorithm analysis and convergence improvement. The hydrotalcite purity can be predicted by means of the trained neural net. Thus, by virtue of the prediction model, the future hydrotalcite purity can be evaluated under random complicated raw material amounts. Moreover, the best processing technology is optimized using the genetic algorithm.

Download Full-text

Application Research of Adaptive Control Techniques in the Hydraulic Torque Converter's Buffer Locking Process

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.588-589.1495 ◽

2012 ◽

Vol 588-589 ◽

pp. 1495-1498

Author(s):

Yi Jin ◽

Wei Ping Liu ◽

Xi Xia Liu

Keyword(s):

Genetic Algorithm ◽

Neural Networks ◽

Adaptive Control ◽

Back Propagation ◽

Torque Converter ◽

Bp Neural Networks ◽

Control Techniques ◽

Control Precision ◽

The Neural Network ◽

Hydraulic Torque Converter

When hydraulic torque converter is applied in hydraulic transmission-vehicle, control precision in buffer locking process of hydraulic torque converter was easily disturbed by friction plate's abrasion, changed buffer slope and other factors, which accordingly caused Impact to transmission system of vehicle. In this paper, adaptive control techniques was applied in buffer locking process as a solution to improve control precision, on basis of Back Propagation (BP) Neural Networks and Genetic Algorithm (GA). In the research, the BP Neural Networks and PID control algorithm was designed to control buffer locking process and Genetic Algorithm was applied to optimize the neural network parameters. Based on AMEsim and Matlab/simulink, joint simulation was carried out. The simulation result shows that Adaptive Control Techniques based on GA-BP can control the locking process fast and accurately.

Download Full-text