上海交通大学学报

上海交通大学学报 >

2019 , Vol. 53 >Issue 7: 838 - 843

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2019.07.010

学报（中文）

基于稀疏自编码神经网络的产品再设计模块识别方法

展开
  • 1. 上海交通大学 机械与动力工程学院， 上海 200240； 2. 中国矿业大学 矿业工程学院， 江苏 徐州 221116
马斌彬（1993-），男，浙江省宁波市人，硕士生，研究方向为产品再设计，E-mail: mabinbin@sjtu.edu.cn.

网络出版日期: 2019-08-02

基金资助

国家自然科学基金项目（51875345，51475290，51075261，51505480）

收起

Identification of Product Redesign Modules Based on Neural Network of Sparse Auto-Encoder

Expand
  • 1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; 2. School of Mines, China University of Mining and Technology, Xuzhou 221116, Jiangsu, China

Online published: 2019-08-02

Fold

摘要

提出了基于性能时变数据分析的再设计模块识别方法.利用产品在健康状态下的性能时变数据构建无监督学习的稀疏自编码神经网络(SAENN)模型，以用于健康状态下产品性能数据的特征提取以及产品功能退化程度的评估；将产品在健康状态下的性能数据用于训练SAENN模型，使用运行期间的性能时变数据更新产品的状态特征，以反映功能的退化过程；通过对比功能间的退化差异来识别需要再设计模块；同时，以某制造企业水平定向钻产品再设计功能模块的识别为例验证了所提方法的可行性.结果表明，所提出的再设计模块识别方法具有较好的准确性，能够识别需改进的功能模块，识别结果可作为产品再设计的依据.

关键词： 产品再设计； 模块识别； 性能时变数据； 稀疏自编码神经网络； 功能退化

本文引用格式

马斌彬，马红占，褚学宁，李玉鹏 . 基于稀疏自编码神经网络的产品再设计模块识别方法[J]. 上海交通大学学报, 2019 , 53(7) : 838 -843 . DOI: 10.16183/j.cnki.jsjtu.2019.07.010

Abstract

This paper presents a redesign-module identification method based on time-varying product usage data. The method is conducted in three steps：Building a model based on sparse auto-encoder (SAE) neural network using performance feature data from the product health state; Assessing functional performance degradation by using the data during the actual operation; Identifying the redesign module by comparing the difference in functional degradation. Then, a case study of horizontal directional drilling redesign module identification is presented to illustrate feasibility of the proposed method. The result shows the effectiveness of proposed method so that it can identify the weak function modules, while the identified result can provide support for redesign decision-making.

Key words： This paper presents a redesign-module identification method based on time-varying product usage data. The method is conducted in three steps：Building a model based on sparse auto-encoder (SAE) neural network using performance feature data from the product health state; Assessing functional performance degradation by using the data during the actual operation; Identifying the redesign module by comparing the difference in functional degradation. Then, a case study of horizontal directional drilling redesign module identification is presented to illustrate feasibility of the proposed method. The result shows the effectiveness of proposed method so that it can identify the weak function modules, while the identified result can provide support for redesign decision-making.

参考文献

［1］周鹏辉, 马红占, 陈东萍, 等. 基于模糊随机故障模式与影响分析的产品再设计模块识别［J］. 上海交通大学学报, 2017, 51(10): 1189-1195. ZHOU Penghui, MA Hongzhan, CHEN Dongping, et al. Identification of product redesign modules based on fuzzy random failure mode and effects analysis［J］. Journal of Shanghai Jiao Tong University, 2017, 51(10): 1189-1195. ［2］FRANCESCO Z, ROBERTO G. ANP/RPN: A multi criteria evaluation of the risk priority number［J］. Quality and Reliability Engineering International, 2012, 28(1): 85-104. ［3］全睿, 全书海, 黄亮, 等. 基于模糊故障树的燃料电池发动机氢安全［J］. 上海交通大学学报, 2010, 44(7): 951-956. QUAN Rui, QUAN Shuhai, HUANG Liang, et al. Study on hydrogen safety of fuel cell engine based on fuzzy fault tree［J］. Journal of Shanghai Jiao Tong University, 2010, 44(7): 951-956. ［4］DELANEY K D, PHELAN P. Design improvement using process capability data［J］. Journal of Materials Processing Technology, 2009, 209(1): 619-624. ［5］SHIN J H, KIRITSIS D, XIROUCHAKIS P. Design modification supporting method based on product usage data in closed-loop PLM［J］. International Journal of Computer Integrated Manufacturing, 2015, 28(6): 551-568. ［6］MA H Z, CHU X N, LYU G L, et al. An integra-ted approach for design improvement based on analysis of time-dependent product usage data［J］. Journal of Mechanical Design, 2017, 139(11): 111401-1-13. ［7］杜勉, 易俊, 郭剑波, 等. 神经网络技术在风电机组SCADA数据分析中的应用研究［J］. 电网技术, 2018, 42(7): 2200-2205. DU Mian, YI Jun, GUO Jianbo, et al. Research on the application of neural networks on wind turbine SCADA data analysis［J］. Power System Technology, 2018, 42(7): 2200-2205. ［8］王鲁昆, 唐功夫, 张健, 等. 连续时变自编码机在人体行为识别中的应用［J］. 上海交通大学学报, 2016, 50(7): 1065-1070. WANG Lukun, TANG Gongfu, ZHANG Jian, et al. Human behavior recognition using continuous time-varying autoencoder［J］. Journal of Shanghai Jiao Tong University, 2016, 50(7): 1065-1070. ［9］DENG J, ZHANG Z X, MARCHI E, et al. Sparse autoencoder-based feature transfer learning for speech emotion recognition［C］//Proceedings of Humaine Association Conference on Affective Computing and Intelligent Interaction. New York, USA: ACM Press, 2013: 511-516. ［10］PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: Machine learning in python［J］. Journal of Machine Learning Research, 2012, 12: 2825-2830. ［11］KINGMA D, BA J. Adam: A method for stochastic optimization ［EB/OL］. ［2017-11-09］. http://www.oalib.com/paper/4068193.XG5Cw6FJhtA.
Options
文章导航

/

〈 〉