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

Results of degradation assessment for tests 1–3 failure bearing: (a) DSI of test 1 failure bearing during the whole life; (b) local enlargement of DSI for test 1 failure bearing; (c) DSI of test 2 failure bearing during the whole life; (d) local enlargement of DSI for test 2 failure bearing; (e) DSI of test 3 failure bearing during the whole life; (f) local enlargement of DSI for test 3 failure bearing.
© Copyright Policy
Related In: Results  -  Collection

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

f14-sensors-12-10109: Results of degradation assessment for tests 1–3 failure bearing: (a) DSI of test 1 failure bearing during the whole life; (b) local enlargement of DSI for test 1 failure bearing; (c) DSI of test 2 failure bearing during the whole life; (d) local enlargement of DSI for test 2 failure bearing; (e) DSI of test 3 failure bearing during the whole life; (f) local enlargement of DSI for test 3 failure bearing.

Mentions: Finally, a new index, DSI, is calculated as Equation (18), and Figure 14 shows the DSI and its local enlargement. The wild points of fuzzy-monitoring coefficient ε̄ should be rejected before the computation of DSI. The parameter ε̄ in Figure 12 contains lots of exceptional points. The elimination of wild points assures that DSI does not suffer from vibration randomness. DSI inherits all advantages of the fuzzy-monitoring coefficient ε̄, and overcomes its shortcomings. The monotonic index, DSI, reflects the increase of the bearing damages with running time perfectly. Sometimes DSI is jumping which means the occurrence of spalling or the emergence of new damages. On the other hand, the placid DSI implies that the running state of bearing is balanceable and no new damage occurs. The degradation beginning threshold is defined as DSI > 0 according to the monitoring coefficient ε. The initial defect occurs at the degradation beginning moment. And the confirmation of the failure threshold should consider the running state of the bearing and the synthetic performance of the whole rotary machine. In this study, the failure threshold is delimited as DSI ≤ 4 The failure moments of three bearings are 12,260 min, 11,385 min and 4,265 min, as shown in Figure 14.


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)

Results of degradation assessment for tests 1–3 failure bearing: (a) DSI of test 1 failure bearing during the whole life; (b) local enlargement of DSI for test 1 failure bearing; (c) DSI of test 2 failure bearing during the whole life; (d) local enlargement of DSI for test 2 failure bearing; (e) DSI of test 3 failure bearing during the whole life; (f) local enlargement of DSI for test 3 failure bearing.
© Copyright Policy
Related In: Results  -  Collection

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

f14-sensors-12-10109: Results of degradation assessment for tests 1–3 failure bearing: (a) DSI of test 1 failure bearing during the whole life; (b) local enlargement of DSI for test 1 failure bearing; (c) DSI of test 2 failure bearing during the whole life; (d) local enlargement of DSI for test 2 failure bearing; (e) DSI of test 3 failure bearing during the whole life; (f) local enlargement of DSI for test 3 failure bearing.
Mentions: Finally, a new index, DSI, is calculated as Equation (18), and Figure 14 shows the DSI and its local enlargement. The wild points of fuzzy-monitoring coefficient ε̄ should be rejected before the computation of DSI. The parameter ε̄ in Figure 12 contains lots of exceptional points. The elimination of wild points assures that DSI does not suffer from vibration randomness. DSI inherits all advantages of the fuzzy-monitoring coefficient ε̄, and overcomes its shortcomings. The monotonic index, DSI, reflects the increase of the bearing damages with running time perfectly. Sometimes DSI is jumping which means the occurrence of spalling or the emergence of new damages. On the other hand, the placid DSI implies that the running state of bearing is balanceable and no new damage occurs. The degradation beginning threshold is defined as DSI > 0 according to the monitoring coefficient ε. The initial defect occurs at the degradation beginning moment. And the confirmation of the failure threshold should consider the running state of the bearing and the synthetic performance of the whole rotary machine. In this study, the failure threshold is delimited as DSI ≤ 4 The failure moments of three bearings are 12,260 min, 11,385 min and 4,265 min, as shown in Figure 14.

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