[1]张宇婷,段礼祥,李兴涛,等.面向多源不确定性数据的往复压缩机决策级融合诊断方法*[J].中国安全生产科学技术,2024,20(9):112-119.[doi:10.11731/j.issn.1673-193x.2024.09.013]
ZHANG Yuting,DUAN Lixiang,LI Xingtao,et al.Decision-level fusion diagnosis method of reciprocating compressor facing multi-source uncertain data[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(9):112-119.[doi:10.11731/j.issn.1673-193x.2024.09.013]
点击复制
面向多源不确定性数据的往复压缩机决策级融合诊断方法*
ZHANG Yuting,DUAN Lixiang,LI Xingtao,et al.Decision-level fusion diagnosis method of reciprocating compressor facing multi-source uncertain data[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(9):112-119.[doi:10.11731/j.issn.1673-193x.2024.09.013]
《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]
- 卷:
- 20
- 期数:
- 2024年9期
- 页码:
- 112-119
- 栏目:
- 职业安全卫生管理与技术
- 出版日期:
- 2024-09-30
文章信息/Info
- Title:
- Decision-level fusion diagnosis method of reciprocating compressor facing multi-source uncertain data
- 文章编号:
- 1673-193X(2024)-09-0112-08
- Keywords:
- reciprocating compressor; intelligent diagnosis; uncertain data; multi-source information fusion; DS evidence theory
- 分类号:
- X937;TH17
- 文献标志码:
- A
- 摘要:
- 为解决不确定性高的数据源使多源信息融合诊断模型精度降低的问题，提出1种面向不确定性数据的往复压缩机决策融合诊断方法。构建基于GRU-AlexNet网络的初步诊断模型，得到往复压缩机各传感器信号的初始诊断结果，并引入余弦相似度与置信熵的概念构建联合指标改进传统DS证据理论，结合初步诊断结果进行多源信号决策融合诊断。研究结果表明：在对往复压缩机故障的加速度、位移、压力信号（不确定性数据）融合诊断试验中，融合诊断准确率高达99.98%，相较于单一信号源诊断结果分别提高约9.27，5.13，48.30个百分点。该方法可在较大程度上降低不确定性信息对于融合诊断结果的影响，具有良好的容错性与稳定性，可有效提高往复压缩机使用过程中各类故障识别的准确性，进而提高设备的稳定性，保证其良好工作状态。研究结果对保障相关企业安全生产、提高设备产出能力具有重要参考意义。
- Abstract:
- In order to solve the problem that the accuracy of multi-source information fusion diagnosis model is reduced due to high uncertain data sources,a decision fusion diagnosis method of reciprocating compressor facing uncertain data was proposed.A preliminary diagnosis model based on the GRU-AlexNet network was constructed to obtain the initial diagnosis results of each sensor signal of the reciprocating compressor,then the concepts of cosine similarity and confidence entropy were introduced to build a joint index to improve the traditional DS evidence theory,and the multi-source signal decision fusion diagnosis was carried out combining with the preliminary diagnosis results.The results show that in the experimental study on the acceleration,displacement,and pressure signal (uncertain data) fusion diagnosis of reciprocating compressor faults,the fusion diagnosis accuracy was 99.98%,which was 9.27,5.13,and 48.30 percentage points higher than the single signal source diagnosis results,respectively.This method greatly reduces the influence of uncertain information on the fusion diagnosis results,and has good fault tolerance and stability.It can effectively improve the accuracy of various types of fault identification,thereby improving the stability of equipment and ensuring its good working condition.It is of great significance to ensure the work safety of enterprises and improve the output capacity of equipment.
参考文献/References:
［1］CAI B P,LIU Y H,FAN Q,et al.Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network［J］.Applied Energy，2014,114:1-9.
［2］唐友福.基于广义局部频率的非线性非平稳信号故障特征提取方法研究［J］.机械工程学报,2015,51(11):176-176.
TANG Youfu.Research on fault feature extraction method of nonlinear non-stationary signal based on generalized local frequency［J］.Journal of Mechanical Engineering,2015,51(11):176-176.
［3］王威,刘畅,刘朝峰.基于多因素信息融合的城市供水安全评价系统［J］.中国安全生产科学技术,2018,14(11):180-185.
WANG Wei,LIU Chang,LIU Chaofeng.Urban water supply safety evaluation system based on multi-factor information fusion［J］.Journal of Safety Science and Technology,2018,14(11):180-185.
［4］LI S B,LIU G K,TANG X H,et al.An ensemble deep convolutional neural network model with improved D-S evidence fusion for bearing fault diagnosis［J］.Sensors,2017,17(8):1729.
［5］曹洁,郭雷雷.一种基于局部冲突分配的证据组合规则［J］.计算机应用研究,2013,30(7):2033-2035.
CAO Jie,GUO Leilei.An evidence combination rule based on local conflict allocation［J］.Applied Research of Computers,2013,30(7):2033-2035.
［6］郑日晖,岑健,陈志豪,等.基于EMD样本熵与改进DS证据理论的故障诊断方法［J］.自动化与信息工程,2020,41(2):19-26.
ZHENG Rihui,CEN Jian,CHEN Zhihao,et al.Fault diagnosis method based on EMD sample entropy and improved DS evidence Theory［J］.Automation and Information Engineering,2020,41(2):19-26.
［7］MA S J,CAI W,LIU W K,et al.A lighted deep convolutional neural network based fault diagnosis of rotating machinery［J］.Sensors,2019,19(10):2381-2385.
［8］IOFFE S,SZEGEDY C.Batch normalization accelerating deep network training by reducing internal covariate shift［C］//France:International Conference on International Conference on Machine Learning.2016:676-685.
［9］王世杰,肖萌,华国威,等.基于CNN-GRU的混凝土大坝扬压力预测模型研究［J］.中国安全生产科学技术,2023,19(7):99-105.
WANG Shijie,XIAO Meng,HUA Guowei,et al.Research on lifting pressure prediction model of concrete dam based on CNN-GRU［J］.Journal of Safety Science and Techology,2023,19(7):99-105.
［10］何少元.不确定性数据聚类算法及其并行化研究［D］.重庆:重庆邮电大学.
［11］XIAO F Y.An Improved method for combining conflicting evidences based on the similarity measure and belief function entropy［J］.International Journal of Fuzzy Systems,2018,20(4):1256-1266.
［12］DENG Y.Deng entropy:a generalized Shannon entropy to measure uncertainty［J］.Computer Science,Mathematics，2015,29(1):1-9.
［13］赵心阳,肖涵,吕勇.有界广义GMM和无阈值递归图的特征提取方法及应用［J］.机械设计与制造,2022,375(5):147-151.
ZHAO Xinyang,XIAO Han,LYU Yong.Feature extraction method and application of bounded generalized GMM and non-threshold recursive graphs［J］.Machine Design & Manufacture,2022,375(5):147-151.
［14］SHAFER G A.A mathematical theory of evidence［J］.Technometrics,1978,20(1):106.
［15］YAGER R R.On the dempster-shafer framework and new combination rules［J］.Information Sciences,1987,41(2):93-138.
［16］胡金海,高星伟,张驭,等.基于故障敏感度的证据权重计算方法及其应用［J］.振动、测试与诊断,2017,37(3):539-546.
HU Jinhai,GAO Xingwei,ZHANG Yu,et al.Evidence weight calculation method based on fault sensitivity and its application［J］.Journal of Vibration,Measurement & Diagnosis,2017,37(3):539-546.
相似文献/References:
备注/Memo
- 备注/Memo:
-
收稿日期： 2024-05-12
* 基金项目： 中国石油天然气集团有限公司科学研究与技术开发项目(ZLZX2020-05-02)
作者简介： 张宇婷，硕士研究生，主要研究方向为安全监测与智能诊断。
通信作者： 段礼祥，博士，教授，主要研究方向为状态监测、信号处理和故障诊断。
