建立点焊质量神经网络监测模型时作用函数的选取
Selection of Action Function When Establishing the Neural Network Monitoring Model on Quality of Spot Welding
-
摘要: 多层前向神经网络是最常用、最流行的神经网络模型,其逼近能力和训练算法是其应用的关键。误差反传算法(BP)以诸多的优点而成为多层前向神经网络训练的首选算法,但却存在收敛速度慢的缺点。研究发现,"假饱和"是导致BP算法收敛缓慢的主要原因之一,也是减小点焊质量监测模型误差的主要障碍。为了减少BP算法学习过程中出现"假饱和"的可能性、加快学习速度,提出了选取神经元作用函数类型的原则。
-
关键词:
- 点焊质量 /
- 监测模型 /
- 神经元网络 /
- 误差反传(BP)算法 /
- 作用函数
Abstract: Multilayer feedforward neural network is the most popular network model,and the approach ability and training algorithm are the key of its application. The Back-propagation algorithm is the first choice algo rithm to multilayer feedforward neural network because of its many merits, but its convergence rate is slow, which is its shortcoming. This article found that "false saturation" is one of the main reasons which causes BP algorith's convergence slow and is also the main obstruction to decrease the error of quality monitoring model for spot welding. In order to reduce the appearance possibility of "false saturation" in the learning process of BP algorithm and accelerate learning rate, this article puts forward the principle about selecting the type of neural action function.-
Keywords:
- quality of spot welding /
- monitoring model /
- neural network /
- HP algorithm /
- action function
-
-
期刊类型引用(7)
1. 于江，杜荣茂，范彦龙，葛福琛，余果，张洪涛，杨涛. 冷喷涂Cu涂层辅助铝/钢异种金属电阻热扩散连接工艺分析. 焊接学报. 2024(12): 36-44 . 
本站查看
2. 肖勇，程钊，周建军，张建，罗丹，李明雨. 铝合金表面电弧喷涂Ag基涂层及其低温钎焊行为. 焊接学报. 2022(12): 27-34+114 . 本站查看
3. 徐杰，王田. 焊接电流对镁合金/不锈钢电阻点焊接头的影响. 热加工工艺. 2019(01): 214-216 . 百度学术
4. 李文亚，曹聪聪，杨夏炜，徐雅欣. 冷喷涂复合加工制造技术及其应用. 材料工程. 2019(11): 53-63 . 百度学术
5. 张梦清，乔玉林，张仲，张伟，于鹤龙. 铜合金表面冷喷涂纯Cu/Cu基复合涂层的结构与性能. 科技经济导刊. 2019(31): 34+36 . 百度学术
6. 汤贵庭. 镁/钢异种金属电阻点焊工艺研究. 热加工工艺. 2018(15): 225-228 . 百度学术
7. 贾林，栗卓新，李红，Wolfgang Tillmann. 中间层对可伐合金4J29/钼组玻璃DM308激光焊接接头结合性能的影响. 焊接学报. 2018(11): 33-38+130 . 本站查看
其他类型引用(7)
计量
- 文章访问数: 215
- HTML全文浏览量: 2
- PDF下载量: 69
- 被引次数: 14
下载:
