基于IDRSN-BiLSTM的铣削加工表面粗糙度预测方法

被引：1

作者：

陈佳琳 ^{[1
]}

尚志武 ^{[1
]}

张雷 ^{[2
,3
]}

机构：

[1] 天津工业大学天津市现代机电装备技术重点实验室

[2] 天津商业大学机械工程学院

[3] 天津市天森智能设备有限公司

来源：

仪器仪表学报 | 2024年 / 45卷 / 04期

基金：

天津市自然科学基金;

关键词：

粗糙度预测; 深度残差收缩网络; Inception模块; 自适应特征提取; 双向长短时记忆网络;

D O I：

暂无

中图分类号：

TG54 [铣削加工及铣床]; TG84 [表面光洁度（表面粗糙度）的测量及其量仪];

学科分类号：

摘要：

针对传统的表面粗糙度预测方法过度依赖人工提取特征以及预测精度较低的问题,提出一种基于Inception模块改进的深度残差收缩网络(IDRSN)和双向长短时记忆网络(BiLSTM)的表面粗糙度预测方法。首先,利用深度残差收缩网络(DRSN)中软阈值化结构和注意力机制对输入信号进行降噪处理。其次,引入Inception模块构建IDRSN以提升网络的多尺度信息获取能力,实现自适应多尺度特征提取。然后,引入反向长短期记忆(LSTM)构建BiLSTM预测网络,利用正反两个LSTM提高网络捕捉历史和未来完整信息的能力。最后,进行实验验证,分别对比IDRSN、DRSN、BiLSTM和人工提取特征4种方法的提取特征效果,以及BiLSTM、卷积神经网络(CNN)、DRSN和CNN-LSTM 4种表面粗糙度预测模型的预测精度。结果表明所提方法具有较高的预测精度,为铣削加工表面粗糙度预测奠定了方法基础。

引用

页码：27 / 36

页数：10

共 28 条

[1] 基于DRSN和优化BiLSTM的轴承剩余寿命预测方法..文井辉;伍荣森;李帅永;等;.计算机集成制造系统.2024,
[2] A Hybrid Attention-Based Paralleled Deep Learning model for tool wear prediction.[J].Duan Jian;Zhang Xi;Shi Tielin.Expert Systems With Applications.2023,
[3] A fault diagnosis method of rolling bearing based on improved deep residual shrinkage networks.[J].Tong Jinyu;Tang Shiyu;Wu Yi;Pan Haiyang;Zheng Jinde.Measurement.2023,
[4] A robust VRF fault diagnosis method based on ensemble BiLSTM with attention mechanism: Considering uncertainties and generalization.[J].Han Linzhi;Deng Yuping;Chen Huanxin;Wei Gou;KaiSheng ;Shi Jingfeng.Energy & Buildings.2022,
[5] Surface roughness prediction and optimization in the REMF process using an integrated DBN-GA approach
Lee, Jung-Hee
Seo, Yun-Su
Kwak, Jae-Seob
[J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2022, 121 (9-10): : 5931 - 5942
[6] GMA-DRSNs: A novel fault diagnosis method with global multi-attention deep residual shrinkage networks.[J].Zhang Zhijin;Chen Lei;Zhang Chunlei;Shi Huaitao;Li He.Measurement.2022,
[7] Intelligent tool wear monitoring and multi-step prediction based on deep learning model.[J].Cheng Minghui;Jiao Li;Yan Pei;Jiang Hongsen;Wang Ruibin;Qiu Tianyang;Wang Xibin.Journal of Manufacturing Systems.2022,
[8] Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer.[J].Yang Jingli;Gao Tianyu;Jiang Shouda;Li Shijie;Tang Qing.Shock and Vibration.2020,
[9] On-line prediction of ultrasonic elliptical vibration cutting surface roughness of tungsten heavy alloy based on deep learning.[J].Yanan Pan;Renke Kang;Zhigang Dong;Wenhao Du;Sen Yin;Yan Bao.Journal of Intelligent Manufacturing.2020, 3
[10] Prediction and Optimization of Surface Roughness in a Turning Process Using the ANFIS-QPSO Method
Alajmi, Mahdi S.
Almeshal, Abdullah M.
[J]. MATERIALS, 2020, 13 (13) : 1 - 23

← 1 2 3 →