Abnormality Diagnosis Method for Manufacturing Process Based on Bayesian Network

doi:10.7652/xjtuxb201808002

您当前的位置：

首页 >

文章列表页 >

Abnormality Diagnosis Method for Manufacturing Process Based on Bayesian Network

更新时间：2025-07-09

- Abnormality Diagnosis Method for Manufacturing Process Based on Bayesian Network
- Vol. 52, Issue 8, Pages: 9-14(2018)
- 作者机构：
  
  西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201808002
  CLC： TH16
- Online First：10 August 2018，
  
  Published：2018
- 稿件说明：
移动端阅览
Abnormality Diagnosis Method for Manufacturing Process Based on Bayesian Network[J]. 2018, 52(8): 9-14.
DOI：

Abnormality Diagnosis Method for Manufacturing Process Based on Bayesian Network[J]. 2018, 52(8): 9-14. DOI： 10.7652/xjtuxb201808002.

摘要

针对制造过程异常原因复杂、基于传统控制图诊断分析困难等问题

提出了一种采用贝叶斯网络的制造过程异常诊断方法。利用过程异常诊断的先验知识

结合需要诊断的异常特征

构建基于贝叶斯网络的制造过程异常诊断模型。首先提取控制图异常征兆特征

建立贝叶斯网络的异常征兆节点和异常原因节点并进行关联; 然后利用先验知识确定贝叶斯网络中的先验概率

建立贝叶斯网络诊断模型; 最后根据控制图异常特征

利用诊断模型推理异常发生的原因。以汽轮机转子叶轮制造为例进行了诊断

验证了采用贝叶斯网络作为制造过程诊断方法的可行性。

Abstract

Based on Bayesian network

a new method was proposed to diagnose manufacturing process abnormalities

which may be caused by multiple complex reasons. Using the prior knowledge of historical process abnormality diagnosis results

in combination with the abnormal characteristics of present process

the Bayesian network was constructed and the characteristics of the abnormal symptom of the control chart were extracted

the abnormal symptom nodes and the abnormal reason nodes of the Bayesian network were established and correlated. Then the prior distribution in Bayesian network was determined by prior knowledge

and the Bayesian network diagnosis model was determined. According to the abnormal characteristics of the control chart

the reason why the abnormality occurs was diagnosed with the proposed diagnostic model. A turbine impeller manufacturing process was diagnosed

and result validates the feasibility of the proposed method.

关键词

Keywords

references

苏秦. 质量管理与可靠性 [M]. 北京: 机械工业出版社, 2006: 1-4.

张公绪, 孙静. 两种质量多元诊断理论应用实例 [J]. 中国质量, 2002(8): 30-33.

ZHANG Gongxu, SUN Jing. A case study of the multivariate diagnostic theory with two kinds of quality [J]. China Quality, 2002(8): 30-33.

卓德保, 徐济超. 质量诊断技术及其应用综述 [J]. 系统工程学报, 2008, 23(3): 338-346.

ZHUO Debao, XU Jichao. Survey of techniques and applications on quality diagnosis [J]. Journal of Systems Engineering, 2008, 23(3): 338-346.

程志强. 基于智能方法的产品制造过程质量诊断 [D]. 南京: 南京理工大学, 2011: 4-6.

APLEY D W, LEE H Y. Simultaneous identification of premodeled and unmodeled variation patterns [J]. Journal of Quality Technology, 2010, 42(1): 36-51.

赵永满. 多元过程监控与异常诊断研究 [D]. 天津: 天津大学, 2012: 6-8.

程红军. 基于神经网络的多元质量控制与诊断技术研究 [D]. 天津: 天津大学, 2008: 17-45.

ATASHGAR K. Monitoring multivariate environments using artificial neural network approach: an overview [J]. Scientia Kanica, 2015, 22(6): 2527-2547.

SALEHI M, KAZEMZADEH R B, SALMASNIA A. On line detection of mean and variance shift using neural networks and support vector machine in multivariate processes [J]. Applied Soft Computing, 2012, 12(9): 2973-2984.

项前, 徐兰, 刘彬, 等. 基于粗糙集与支持向量机的加工过程异常检测 [J]. 计算机集成制造系统, 2015, 21(9): 2467-2474.

XIANG Qian, XU Lan, LIU Bin, et al. Processing anomaly detection based on rough set and support vector machine [J]. Computer Integrated Manufacturing Systems, 2015, 21(9): 2467-2474.

肖承杭. 基于决策树的多元过程控制与异常识别方法研究 [D]. 天津: 天津大学, 2012: 29-41.

黄影平. 贝叶斯网络发展及其应用综述 [J]. 北京理工大学学报, 2013, 33(12): 1211-1219.

HUANG Yingping. Survey on Bayesian network development and application [J]. Transactions of Beijing Institute of Technology, 2013, 33(12): 1211-1219.

CAI Baoping, HUA Lei, XIE Min. Bayesian networks in fault diagnosis [J]. IEEE Transactions on Industrial Informatics, 2017, 13(5): 2227-2240.

LIN S, CHEN X, WANG Q. Fault diagnosis model based on Bayesian network considering information uncertainty and its application in traction power supply system [J]. IEEJ Transactions on Electrical and Electronic Engineering, 2018, 13(5): 671-680.

罗孝辉, 童晓阳. 计及可信度的变结构贝叶斯网络电网故障诊断 [J]. 电网技术, 2015, 39(9): 2658-2664.

LUO Xiaohui, TONG Xiaoyang. Structure-variable Bayesian network for power system fault diagnosis considering credibility [J]. Power System Technology, 2015, 39(9): 2658-2664.

BI Z, LI C M, LI X J, et al. Research on fault diagnosis for pumping station based on T-S fuzzy fault tree and Bayesian network [J]. Journal of Electrical Computer Engineering, 2017, 2017(11): 1-7.

梁潇, 王海峰, 郭进, 等. 基于贝叶斯网络的列控车载设备故障诊断方法 [J]. 铁道学报, 2017, 39(8): 93-100.

LIANG Xiao, WANG Haifeng, GUO Jin, et al. Bayesian network based fault diagnosis method for on-board equipment of train control system [J]. Journal of the China Railway Society, 2017, 39(8): 93-100.

曹杰. 贝叶斯网络结构学习与应用研究 [D]. 合肥: 中国科学技术大学, 2017: 11-14.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Diffusion Characteristics and Influencing Factors in Case of Hydrogen Leakage from Fuel Cell Vehicles Running in Tunnels

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Sensitivity Analysis of Foil Geometrical Parameters for the Third-Generation CO2 Gas Foil Bearings Based on Design of Experiments Method

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Related Author

No data

Related Institution

No data

⁰