BP Neural Network's Application in Glass Fiber Textile Machine Parameter Tuning

• Published in: 2011 Fourth International Conference on Information and Computing pp. 436 - 439
• Main Authors: Zhang Lihong, Chen Shuqian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-04-2011
• Subjects: Artificial neural networks; Control systems; Glass; Glass fiber textile machine; neural network; Neurons; Optical fiber networks; parameter tuning; PID; Textiles; Tuning
• ISBN: 9781612846880; 1612846882
• ISSN: 2160-7443
• DOI: 10.1109/ICIC.2011.5

Glass fiber textile machine is a major producer machine of glass fiber cloth. Textile machines of take-up system adopts non-axis volume cloth method in production, with the increase of fiber cloth, curls the cloth drive shaft's pressure also becomes bigger, thus causes to receive cloth motor speed PID control to be even more difficult, and would cause the pulling force oversized textile fiber cloth break frequently or cannot receive the cloth promptly or twine drive shaft. Three layers of BP neural network model can dynamically adjust the parameters of hidden layer through self-learning, hidden layer units, respectively as the proportion of PID (P) unit, integral (I) unit and differential (D) unit, so as to realize the PID parameters on-line tuning, to improve real-time of t receive the cloth motor speed PID controller, improved the stability of the system, and achieve a better control effect.