Limits...
A monotonic degradation assessment index of rolling bearings using fuzzy support vector data description and running time.

Shen Z, He Z, Chen X, Sun C, Liu Z - Sensors (Basel) (2012)

Bottom Line: DSI inherits all advantages of ε⁻ and overcomes its disadvantage.A run-to-failure test is carried out to validate the performance of the proposed method.The results show that DSI reflects the growth of the damages with running time perfectly.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China. zjshen.2007@stu.xjtu.edu.cn

ABSTRACT
Performance degradation assessment based on condition monitoring plays an important role in ensuring reliable operation of equipment, reducing production downtime and saving maintenance costs, yet performance degradation has strong fuzziness, and the dynamic information is random and fuzzy, making it a challenge how to assess the fuzzy bearing performance degradation. This study proposes a monotonic degradation assessment index of rolling bearings using fuzzy support vector data description (FSVDD) and running time. FSVDD constructs the fuzzy-monitoring coefficient ε⁻ which is sensitive to the initial defect and stably increases as faults develop. Moreover, the parameter ε⁻ describes the accelerating relationships between the damage development and running time. However, the index ε⁻ with an oscillating trend disagrees with the irreversible damage development. The running time is introduced to form a monotonic index, namely damage severity index (DSI). DSI inherits all advantages of ε⁻ and overcomes its disadvantage. A run-to-failure test is carried out to validate the performance of the proposed method. The results show that DSI reflects the growth of the damages with running time perfectly.

No MeSH data available.


Related in: MedlinePlus

Four time-domain features of test 1 failure bearing: (a) RMS during the whole life; (b) local enlargement of RMS; (c) SRA during the whole life; (d) local enlargement of SRA; (e) AAV during the whole life; (f) local enlargement of AAV; (g) Kurtosis factor during the whole life; (h) local enlargement of Kurtosis factor.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3472819&req=5

f5-sensors-12-10109: Four time-domain features of test 1 failure bearing: (a) RMS during the whole life; (b) local enlargement of RMS; (c) SRA during the whole life; (d) local enlargement of SRA; (e) AAV during the whole life; (f) local enlargement of AAV; (g) Kurtosis factor during the whole life; (h) local enlargement of Kurtosis factor.

Mentions: Firstly, the original time-domain features are researched. Three stability features, such as RMS, square-root amplitude (SRA), absolute average values (AAV), and one sensitive feature as Kurtosis factor of three bearings are listed in Figures 5–7. In each Figure, the right subgraph is the local enlargement of the left subgraph to describe the variance of each feature in degradation period more distinctly. These figures at least tell us the following: (1) The normal periods usually are obviously longer than the degradation period which is verified in reference [36]. (2) In the normal period, the three stability features have placid trends while they grow continuously with the development of faults in the degradation period, but there is not an obvious impulse for each stability feature when the initial defect occurs. Three features of test 2 failure bearing have large changes at 7,600 min. It could be resulted from a dismounting and reinstallation. (3) Kurtosis factor is bumping up when the incipient fault appears, but its subsequent behaviors are bad. Kurtosis factor could be used to roughly discriminate the initial defect times, that is, the beginning moments of degradation, which are 10,000min, 10,710 min and 3,075 min, respectively. However, the beginning moments of degradation may be unfaithful because of the randomness of Kurtosis factor, especially when the impulse in Kurtosis factor is very weak, such as in the test 3 failure bearing. (4) The same feature for different bearings varies greatly because of the individual differences, even though at the same period. For examples, RMS of test 1 failure bearing is clearly less than that of tests 2 and 3 failure bearings at the normal period. (5) The overall trend of the original features is fuzzy, while their every point has the strong randomness. Therefore, none of the original features are suitable to assess the performance degradation over the whole lifetime.


A monotonic degradation assessment index of rolling bearings using fuzzy support vector data description and running time.

Shen Z, He Z, Chen X, Sun C, Liu Z - Sensors (Basel) (2012)

Four time-domain features of test 1 failure bearing: (a) RMS during the whole life; (b) local enlargement of RMS; (c) SRA during the whole life; (d) local enlargement of SRA; (e) AAV during the whole life; (f) local enlargement of AAV; (g) Kurtosis factor during the whole life; (h) local enlargement of Kurtosis factor.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3472819&req=5

f5-sensors-12-10109: Four time-domain features of test 1 failure bearing: (a) RMS during the whole life; (b) local enlargement of RMS; (c) SRA during the whole life; (d) local enlargement of SRA; (e) AAV during the whole life; (f) local enlargement of AAV; (g) Kurtosis factor during the whole life; (h) local enlargement of Kurtosis factor.
Mentions: Firstly, the original time-domain features are researched. Three stability features, such as RMS, square-root amplitude (SRA), absolute average values (AAV), and one sensitive feature as Kurtosis factor of three bearings are listed in Figures 5–7. In each Figure, the right subgraph is the local enlargement of the left subgraph to describe the variance of each feature in degradation period more distinctly. These figures at least tell us the following: (1) The normal periods usually are obviously longer than the degradation period which is verified in reference [36]. (2) In the normal period, the three stability features have placid trends while they grow continuously with the development of faults in the degradation period, but there is not an obvious impulse for each stability feature when the initial defect occurs. Three features of test 2 failure bearing have large changes at 7,600 min. It could be resulted from a dismounting and reinstallation. (3) Kurtosis factor is bumping up when the incipient fault appears, but its subsequent behaviors are bad. Kurtosis factor could be used to roughly discriminate the initial defect times, that is, the beginning moments of degradation, which are 10,000min, 10,710 min and 3,075 min, respectively. However, the beginning moments of degradation may be unfaithful because of the randomness of Kurtosis factor, especially when the impulse in Kurtosis factor is very weak, such as in the test 3 failure bearing. (4) The same feature for different bearings varies greatly because of the individual differences, even though at the same period. For examples, RMS of test 1 failure bearing is clearly less than that of tests 2 and 3 failure bearings at the normal period. (5) The overall trend of the original features is fuzzy, while their every point has the strong randomness. Therefore, none of the original features are suitable to assess the performance degradation over the whole lifetime.

Bottom Line: DSI inherits all advantages of ε⁻ and overcomes its disadvantage.A run-to-failure test is carried out to validate the performance of the proposed method.The results show that DSI reflects the growth of the damages with running time perfectly.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China. zjshen.2007@stu.xjtu.edu.cn

ABSTRACT
Performance degradation assessment based on condition monitoring plays an important role in ensuring reliable operation of equipment, reducing production downtime and saving maintenance costs, yet performance degradation has strong fuzziness, and the dynamic information is random and fuzzy, making it a challenge how to assess the fuzzy bearing performance degradation. This study proposes a monotonic degradation assessment index of rolling bearings using fuzzy support vector data description (FSVDD) and running time. FSVDD constructs the fuzzy-monitoring coefficient ε⁻ which is sensitive to the initial defect and stably increases as faults develop. Moreover, the parameter ε⁻ describes the accelerating relationships between the damage development and running time. However, the index ε⁻ with an oscillating trend disagrees with the irreversible damage development. The running time is introduced to form a monotonic index, namely damage severity index (DSI). DSI inherits all advantages of ε⁻ and overcomes its disadvantage. A run-to-failure test is carried out to validate the performance of the proposed method. The results show that DSI reflects the growth of the damages with running time perfectly.

No MeSH data available.


Related in: MedlinePlus