激光技术2001，Vol.25Issue(1)：1-6,6.
激光冲击区表面质量的人工神经网络研究
Study of the surface qualities of laser shock-processing zones using an artificial neural network
摘要
Abstract
A lot of experiments have shown that there is an obvious relationbetween surface qualities of specimen after laser shock-processing（LSP） and its fatigue life．Consequently，the LSP effects can be evaluated by surface qualities in LSP areas．In this paper，an artificial neural network（ANN） is utilized to study the surface qualities of specimen a fter LSP．Based on the data obtained in t he experiment，an ANN is established．The trained ANN could acquire the relations between surface qualities and laser parm eters．From the verification of aluminium alloy 2024-T62，it is proved that the neural network can successfully predict the surface quality grades of specimen after LSP，and easily determine the laser parameters under different production cond itions．The research and experimental res ults show that the ANN has not only the accuracy and good stability，but also theintelligent improving control ability during process．关键词
激光冲击处理/表面质量/神经网络分类
信息技术与安全科学引用本文复制引用
於自岚,高传玉,曾丹勇,杨继昌,张永康..激光冲击区表面质量的人工神经网络研究[J].激光技术,2001,25(1):1-6,6.基金项目
江苏省应用基金 （）
