A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision

The industrial robot is a mechanized electronic device that functions as a human arm, wrist and hand. Rolling bearings are an essential part of these flexible rotation. Due to the harsh environment of the industrial robot and full-load operation, bearing faults are difficult to be diagnose and occur...

Full description

Bibliographic Details
Main Authors: Xianbin Sun, Xinming Jia
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8854188/
_version_ 1818728070264127488
author Xianbin Sun
Xinming Jia
author_facet Xianbin Sun
Xinming Jia
author_sort Xianbin Sun
collection DOAJ
description The industrial robot is a mechanized electronic device that functions as a human arm, wrist and hand. Rolling bearings are an essential part of these flexible rotation. Due to the harsh environment of the industrial robot and full-load operation, bearing faults are difficult to be diagnose and occur from time to time. In the long-term research, the author found that the traditional method based on fault characteristic frequency has at least two problems. On the one hand, some bearing parameters are not easy to obtain so that the fault characteristic frequency cannot be calculated, especially the high-precision bearing of some imported equipment. On the other hand, some bearings can calculate the fault characteristic frequency, but the fuzziness of the method is difficult to overcome. This paper introduces a new method based on experimental data-driven random fuzzy evidence acquisition and intuitionistic fuzzy sets fusion (IFSF). Firstly, this method does not need to calculate the fault characteristic frequency, by constructing and matching the fuzzy expert system and the sample to be tested. The maximum value of the vertical coordinate of the intersection point, namely the likelihood measure value, is used as the membership degree of the support proposition. Then, the essential meaning of uncertainty parameter is analyzed, the membership degree of the fuzzy set under the random set framework is transformed into the membership function of the intuitionistic fuzzy set, and the binary likelihood pair is used to represent the single likelihood measure value. Finally, the single sensor multi-feature fusion and multi-sensor information fusion are transformed into intuitionistic fuzzy set multi-attribute decision fusion. The experimental results show that the method proposed in this paper can overcome the fuzziness of the traditional method, and provides a new theoretical method for the fault diagnosis of rolling bearing, which is difficult to obtain geometric parameters.
first_indexed 2024-12-17T22:24:09Z
format Article
id doaj.art-260b7cb13fe841f4b36a304b98a5daa4
institution Directory Open Access Journal
issn 2169-3536
language English
last_indexed 2024-12-17T22:24:09Z
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj.art-260b7cb13fe841f4b36a304b98a5daa42022-12-21T21:30:23ZengIEEEIEEE Access2169-35362019-01-01714876414877010.1109/ACCESS.2019.29449748854188A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy DecisionXianbin Sun0https://orcid.org/0000-0002-2077-5757Xinming Jia1Qingdao University of Technology, Qingdao, ChinaQingdao University of Technology, Qingdao, ChinaThe industrial robot is a mechanized electronic device that functions as a human arm, wrist and hand. Rolling bearings are an essential part of these flexible rotation. Due to the harsh environment of the industrial robot and full-load operation, bearing faults are difficult to be diagnose and occur from time to time. In the long-term research, the author found that the traditional method based on fault characteristic frequency has at least two problems. On the one hand, some bearing parameters are not easy to obtain so that the fault characteristic frequency cannot be calculated, especially the high-precision bearing of some imported equipment. On the other hand, some bearings can calculate the fault characteristic frequency, but the fuzziness of the method is difficult to overcome. This paper introduces a new method based on experimental data-driven random fuzzy evidence acquisition and intuitionistic fuzzy sets fusion (IFSF). Firstly, this method does not need to calculate the fault characteristic frequency, by constructing and matching the fuzzy expert system and the sample to be tested. The maximum value of the vertical coordinate of the intersection point, namely the likelihood measure value, is used as the membership degree of the support proposition. Then, the essential meaning of uncertainty parameter is analyzed, the membership degree of the fuzzy set under the random set framework is transformed into the membership function of the intuitionistic fuzzy set, and the binary likelihood pair is used to represent the single likelihood measure value. Finally, the single sensor multi-feature fusion and multi-sensor information fusion are transformed into intuitionistic fuzzy set multi-attribute decision fusion. The experimental results show that the method proposed in this paper can overcome the fuzziness of the traditional method, and provides a new theoretical method for the fault diagnosis of rolling bearing, which is difficult to obtain geometric parameters.https://ieeexplore.ieee.org/document/8854188/Data-drivenrandom fuzzy setintuitionistic fuzzy setsdata fusion rule
spellingShingle Xianbin Sun
Xinming Jia
A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
IEEE Access
Data-driven
random fuzzy set
intuitionistic fuzzy sets
data fusion rule
title A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
title_full A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
title_fullStr A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
title_full_unstemmed A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
title_short A Fault Diagnosis Method of Industrial Robot Rolling Bearing Based on Data Driven and Random Intuitive Fuzzy Decision
title_sort fault diagnosis method of industrial robot rolling bearing based on data driven and random intuitive fuzzy decision
topic Data-driven
random fuzzy set
intuitionistic fuzzy sets
data fusion rule
url https://ieeexplore.ieee.org/document/8854188/
work_keys_str_mv AT xianbinsun afaultdiagnosismethodofindustrialrobotrollingbearingbasedondatadrivenandrandomintuitivefuzzydecision
AT xinmingjia afaultdiagnosismethodofindustrialrobotrollingbearingbasedondatadrivenandrandomintuitivefuzzydecision
AT xianbinsun faultdiagnosismethodofindustrialrobotrollingbearingbasedondatadrivenandrandomintuitivefuzzydecision
AT xinmingjia faultdiagnosismethodofindustrialrobotrollingbearingbasedondatadrivenandrandomintuitivefuzzydecision