Reliability assessment of rolling bearing based on principal component analysis and Weibull proportional hazard model

Abstract Large companies are investing heavily in digitalization to be more competitive and economically viable. Hence, physical assets and maintenance operations have been digitally transformed to transmit a high volume of data, e.g., condition monitoring data. Such high-volume data can be useful to optimize maintenance operations and minimize maintenance and replacement costs. A tool to optimize maintenance using condition monitoring data is the Proportional hazard model (PHM). However, it is challenging to implement PHM for industrial complex systems that generate big data. Therefore, machine learning algorithms shall support PHM method to handle such a high volume of data. Thus, the purpose of this paper is to explore how to support PHM with Principal Component Analysis (PCA) to maintenance optimization of complex industrial systems. A case study of hydraulic power unit was purposefully selected to apply and validate the proposed analytical approach. The results show that PCA supported PHM optimizes and extends the preventive maintenance interval by 79.27% which might lead to maintenance cost reductions. This model enables PHM to handle complex systems where big data is collected.

Download Full-text

2110 Principal component analysis for reliability assessment of structural systems

The Proceedings of Design & Systems Conference ◽

10.1299/jsmedsd.2001.11.110 ◽

2001 ◽

Vol 2001.11 (0) ◽

pp. 110-111

Author(s):

Shingo NAKANISHI ◽

Hidetoshi NAKAYASU

Keyword(s):

Principal Component Analysis ◽

Reliability Assessment ◽

Principal Component ◽

Component Analysis ◽

Structural Systems

Download Full-text

Survival analysis of productive life in Brazilian holstein using a piecewise Weibull proportional hazard model

Livestock Science ◽

10.1016/j.livsci.2016.01.019 ◽

2016 ◽

Vol 185 ◽

pp. 89-96 ◽

Cited By ~ 7

Author(s):

Elisandra Lurdes Kern ◽

Jaime Araujo Cobuci ◽

Claudio Napolis Costa ◽

Vincent Ducrocq

Keyword(s):

Survival Analysis ◽

Hazard Model ◽

Proportional Hazard ◽

Proportional Hazard Model ◽

Productive Life ◽

Weibull Proportional Hazard

Download Full-text

Relationship between somatic cell score and longevity of Holstein cows in Brazil using a piecewise Weibull proportional-hazard model

Animal Production Science ◽

10.1071/an18069 ◽

2019 ◽

Vol 59 (8) ◽

pp. 1546

Author(s):

Elisandra Lurdes Kern ◽

Jaime Araujo Cobuci ◽

José Braccini Neto ◽

Darlene dos Santos Daltro

Keyword(s):

Somatic Cell ◽

Milk Production ◽

Hazard Model ◽

Somatic Cell Score ◽

Holstein Cows ◽

Independent Effect ◽

Proportional Hazard ◽

Proportional Hazard Model ◽

Weibull Proportional Hazard ◽

The Impact

The objective of the present work was to evaluate the effect of somatic cell score on the longevity of Holstein cows raised all over Brazil, using a piecewise Weibull proportional-hazard model. The following two longevity traits were defined: true longevity, number of days from first calving to culling; and functional longevity, approximated by correcting true longevity to within-herd-year production. Records on productive life of 131330 cows were used. The model included the time-independent effect of age at first calving. The other effects were time-dependent, and included the following: region by year of calving, variation in herd-size class, milk-production class by year of calving within herd, within-herd milk-production class by number of lactations, within-herd fat content, within-herd protein content, and somatic cell score (SCS). The overall mean of the somatic cell counts (SCC) was 322000 cells/mL. The highest SCC mean was found between 130 to 290 days of lactation. The SCC mean decreased over the years. Cows from Region 5 (Rio Grande do Sul) showed higher SCC means. The risk of culling was slightly higher for functional longevity than for true longevity. The impact of longevity was high in cows from first to fourth lactation with a high SCS, with the risk of culling varying from 0.90 (true longevity: second lactation and Class 2) to 1.2 (functional longevity: fourth lactation and Class 5). Cows at the fifth lactation with a lower SCS had a higher risk of culling (1.4). Including the effect of SCS class by stage of lactation in the models was not beneficial. The decrease in SCS, especially from the first to fourth lactation, can be used for indirect selection to improve the longevity of Holstein cows in Brazil.

Download Full-text

Usability evaluation and maintenance decision of the optical cable based on Weibull Proportional Hazard Model

10.1109/icvris51417.2020.00282 ◽

2020 ◽

Author(s):

Guijin Xia ◽

Xiaogang Xie ◽

Jingke Wan ◽

Weihu Zhao

Keyword(s):

Hazard Model ◽

Usability Evaluation ◽

Proportional Hazard ◽

Proportional Hazard Model ◽

Optical Cable ◽

Maintenance Decision ◽

Weibull Proportional Hazard

Download Full-text

Bearing Condition Recognition Based on Kernel Principal Component Analysis and Genetic Programming

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.397-400.1282 ◽

2013 ◽

Vol 397-400 ◽

pp. 1282-1285 ◽

Cited By ~ 1

Author(s):

Wen Bin Liu ◽

Yu Xin He ◽

Hua Qing Wang ◽

Jian Feng Yang

Keyword(s):

Principal Component Analysis ◽

Genetic Programming ◽

Principal Component ◽

Vibration Signal ◽

Rolling Bearing ◽

Component Analysis ◽

Kernel Principal Component Analysis ◽

Initial Symptom ◽

The Time Domain ◽

Condition Recognition

In order to extract the fault feature validity in early fault diagnosis, method based on kernel principal component analysis and genetic programming (GP) is presented. The time domain features of the vibration signal are extracted and the initial symptom parameters (SP) are constructed. Then the combination to the initial SPs is carried on to optimize and build composite characteristics by GP. Through kernel principal component analysis (KPCA), the nonlinear principal component of the original characteristics is produced. Finally, the nonlinear principal components are selected as the feature subspace to classify the conditions of rolling bearing. Meanwhile, the within-class and among-class distance is introduced to compare and analyze the bearing condition recognition effect by using KPCA and GP plus KPCA separately. Experimental results show that the features extracted by kernel principal component analysis and genetic programming perform better ability in identifying the working states of the rolling bearing.

Download Full-text

Rolling Bearing Reliability Assessment via Kernel Principal Component Analysis and Weibull Proportional Hazard Model

Shock and Vibration ◽

10.1155/2017/6184190 ◽

2017 ◽

Vol 2017 ◽

pp. 1-11 ◽

Cited By ~ 6

Author(s):

Fengtao Wang ◽

Xutao Chen ◽

Bosen Dun ◽

Bei Wang ◽

Dawen Yan ◽

...

Keyword(s):

Principal Component Analysis ◽

Frequency Domain ◽

Reliability Assessment ◽

Principal Component ◽

Component Analysis ◽

Performance Degradation ◽

Assessment Model ◽

Kernel Principal Component Analysis ◽

Engineering Project ◽

Time Frequency

Reliability assessment is a critical consideration in equipment engineering project. Successful reliability assessment, which is dependent on selecting features that accurately reflect performance degradation as the inputs of the assessment model, allows for the proactive maintenance of equipment. In this paper, a novel method based on kernel principal component analysis (KPCA) and Weibull proportional hazards model (WPHM) is proposed to assess the reliability of rolling bearings. A high relative feature set is constructed by selecting the effective features through extracting the time domain, frequency domain, and time-frequency domain features over the bearing’s life cycle data. The kernel principal components which can accurately reflect the performance degradation process are obtained by KPCA and then input as the covariates of WPHM to assess the reliability. An example was conducted to validate the proposed method. The differences in manufacturing, installation, and working conditions of the same type of bearings during reliability assessment are reduced after extracting relative features, which enhances the practicability and stability of the proposed method.

Download Full-text