Academia.eduAcademia.edu

Outline

Title
Introduction
Sensing and Data Processing
Conclusions
References

Data Mining in Systems Health Management

Profile image of Kai GoebelKai Goebel

2010

Related papers

Fault Prognostics Using Logical Analysis of Data and Non-Parametric Reliability Estimation Methods
Ahmed Ragab

2014

Estimating the remaining useful life (RUL) for a system working under different operating conditions represents a big challenge to the researchers in the condition-based maintenance (CBM) domain. The reason is that the relationship between the covariates that represent those operating conditions and the RUL is not fully understood in many practical cases, due to the high degree of correlation between such covariates, and their dependence on time. It is also difficult or even impossible for the experts to acquire and accumulate the knowledge from a complex system, where the failure of the system is regarded as the result of interaction and competition between several failure modes. This thesis presents systematic CBM prognostic methodologies based on a pattern-based machine learning and knowledge discovery approach called Logical Analysis of Data (LAD). The proposed methodologies comprise different implementations of the LAD approach combined with nonparametric reliability estimation methods. The objective of these methodologies is to predict the RUL of the monitored system while considering the analysis of single or multiple failure modes. Three different methodologies are presented; two deal with single failure mode and one deals with multiple failure modes. The two methodologies for single mode prognostics differ in the way of representing the data. The prognostic methodologies in this doctoral research have been tested and validated based on a set of widely known tests. In these tests, the methodologies were compared to well-known prognostic techniques; the proportional hazards model (PHM), artificial neural networks (ANNs) and support vector machines (SVMs). Two datasets were used to illustrate the performance of the three methodologies: the turbofan engine dataset that is available at NASA prognostic data repository, and another dataset collected from a real application in the industry. The results of these comparisons indicate that each of the proposed methodologies provides an accurate prediction for the RUL of the monitored system. This doctoral research concludes that the LAD approach has attractive merits and advantages that add benefits to the field of prognostics. It is capable of dealing with the CBM data that are correlated and time-varying. Another advantage is its generation of an interpretable knowledge that is beneficial to the maintenance personnel. vii

View PDFchevron_right
Impact of Prognostic Uncertainty in System Health Monitoring
Jason Freels

2020

Across many industries, systems are exceeding their intended design lives, whether they are ships, bridges or military aircraft. As a result failure rates can increase and unanticipated wear or failure conditions can arise. Health monitoring research and application has the potential to more safely lengthen the service life of a range of systems through utilization of sensor data and knowledge of failure mechanisms to predict component life remaining. A further benefit of health monitoring when combined across an entire platform is system health management. System health management is an enabler of condition based maintenance, which allows repair or replacement based on material condition, not a set time. Replacement of components based on condition can enable cost savings through fewer parts being used and the associated maintenance costs. The goal of this research is to show the management of system health can provide savings in maintenance and logistics cost while increasing vehi...

View PDFchevron_right
Prognostics Health Management of Electronic Systems Under Mechanical Shock and Vibration Using Kalman Filter Models and Metrics
Kai Goebel

IEEE Transactions on Industrial Electronics, 2012

View PDFchevron_right
Comparative case study of life usage and data-driven prognostics techniques using aircraft fault messages
Cairo L. Nascimento Jr.

Computers in Industry, 2017

Prognostics are a key activity in repair and maintenance operations. A recent approach to condition-based maintenance is the data-driven approach. This approach has been mostly based on past failure time measures, and sensed measurements of component degradation to derive estimates of the remaining useful life of equipment. An alternative source of data, rarely used in these models, is the stream of automatic messages derived from diagnostics systems, which consist of fault codes indicating abnormal events or deviations from optimal operation. Despite the richness and concise nature of these messages, their difficult interpretation poses significant challenges to its use in prognostics. This paper aims to show that data-driven prognostics based on this type of messages can be better suited to maintenance than time-based approaches. We illustrate this comparison with an industrial case study involving the removal times of a bleed valve from the aircraft air management system. Our experimental results reveal a significant accuracy improvement over the contrasting time-based models. We also establish the contribution to this improvement of the data-driven methods and message-related predictors.

View PDFchevron_right
Data-Driven Based Fault Prognosis for Industrial Systems: A Concise Overview
IEEE/CAA J. Autom. Sinica

IEEE/CAA Journal of Automatica Sinica, 2020

Fault prognosis is mainly referred to the estimation of the operating time before a failure occurs, which is vital for ensuring the stability, safety and long lifetime of degrading industrial systems. According to the results of fault prognosis, the maintenance strategy for underlying industrial systems can realize the conversion from passive maintenance to active maintenance. With the increased complexity and the improved automation level of industrial systems, fault prognosis techniques have become more and more indispensable. Particularly, the data-driven based prognosis approaches, which tend to find the hidden fault factors and determine the specific fault occurrence time of the system by analysing historical or real-time measurement data, gain great attention from different industrial sectors. In this context, the major task of this paper is to present a systematic overview of data-driven fault prognosis for industrial systems. Firstly, the characteristics of different prognosis methods are revealed with the data-based ones being highlighted. Moreover, based on the different data characteristics that exist in industrial systems, the corresponding fault prognosis methodologies are illustrated, with emphasis on analyses and comparisons of different prognosis methods. Finally, we reveal the current research trends and look forward to the future challenges in this field. This review is expected to serve as a tutorial and source of references for fault prognosis researchers.

View PDFchevron_right
Estimation of Health Indicators using Advanced Analytics for Prediction of Aircraft Systems Remaining Useful Lifetime
Bernardete Ribeiro

2020

A valuable asset for the improvement of aviation maintenance is the correct assessment of the aircraft systems health condition, for a more accurate planning and execution of maintenance routines. As such, the creation of a Prognostic and Health Management (PHM) system, supported by Condition Based Maintenance (CBM) can bring important benefits to the aeronautical field. The ultimate goal of a PHM system is the correct prediction of the Remaining Useful Lifetime (RUL) of a certain aircraft system, using the sensors data extracted during flights. Nevertheless, a relevant stage in the PHM pipeline concerns the estimation of the system condition, expressed by the Health Indicator (HI). The HI value reflects the health condition of a specific aircraft system, which can possibly be affected by degradation, failures or external conditions occurred during flight time. Henceforth, due to the relevancy of the HI assessment for the accuracy of the PHM model, this paper aims to propose a new f...

View PDFchevron_right
On‐line reliability estimation for individual components using statistical degradation signal models
Ratna Chinnam

Quality and Reliability Engineering International, 2002

With very few exceptions, most contemporary reliability engineering methods are geared towards estimating a population characteristic(s) of a system, subsystem or component. The information so extracted is extremely valuable for manufacturers and others that deal with product in relatively large volumes. In contrast, end users are typically more interested in the behavior of a 'particular' component used in their system to arrive at optimal component replacement or maintenance strategies leading to improved system utilization, while reducing risk and maintenance costs. The traditional approach to addressing this need is to monitor the component through degradation signals and 'classifying' the state of a component into discrete classes, say 'good', 'bad' and 'in-between' categories. In the event, one can develop effective degradation signal forecasting models and precisely define component failure in the degradation signal space, then, one can move beyond the classification approach to a more vigorous reliability estimation and forecasting scheme for the individual unit. This paper demonstrates the feasibility of such an approach using 'general' polynomial regression models for degradation signal modeling. The proposed methods allow first-order autocorrelation in the residuals as well as weighted regression. Parametric bootstrap techniques are used for calculating confidence intervals for the estimated reliability. The proposed method is evaluated on a cutting tool monitoring problem. In particular, the method is used to monitor high-speed steel drill-bits used for drilling holes in stainless-steel metal plates. A second study involves modeling and forecasting fatigue-crack-growth data from the literature. The task involved estimating and forecasting the reliability of plates expected to fail due to fatigue-crack-growth. Both studies reveal very promising results.

View PDFchevron_right
A practical approach to combine data mining and prognostics for improved predictive maintenance
Steve Vandenplas, agusmian ompusunggu
View PDFchevron_right
Unsupervised Fault Detection and Prediction of Remaining Useful Life for Online Prognostic Health Management of Mechanical Systems
Cristina Mora

Applied Sciences, 2020

Predictive maintenance allows industries to keep their production systems available as much as possible. Reducing unforeseen shutdowns to a level that is close to zero has numerous advantages, including production cost savings, a high quality level of both products and processes, and a high safety level. Studies in this field have focused on a novel approach, prognostic health management (PHM), which relies on condition monitoring (CM) for predicting the remaining useful life (RUL) of a system. However, several issues remain in its application to real industrial contexts, e.g., the difficulties in conducting tests simulating each fault condition, the dynamic nature of industrial environments, and the need to handle large amounts of data collected from machinery. In this paper, a data-driven methodology for PHM implementation is proposed, which has the following characteristics: it is unsupervised, i.e., it does not require any prior knowledge regarding fault behaviors and it does no...

View PDFchevron_right
Prognostics of Systems: Approaches and Applications
Sony Mathew

2011

Ideally, systems continue to operate reliably for a long time. But the reality is that systems fail, and the consequences can be serious. In the worst cases, lives may be lost and people may be injured; in all cases, people are adversely affected. The economic repercussions of critical system failure can be staggering. Current reliability methods cannot handle real-time changes in operational and environmental loads on a system, which can cause a system to fail in the field without warning, leading to unplanned downtime. Prognostics and health management (PHM) is an enabling discipline consisting of technologies and methods to assess the reliability of a product in its actual life cycle conditions to determine the advent of failure and mitigate system risk. The approaches adopted for conducting prognostics for a product include physics-of-failure (PoF) based approaches, including use of canaries to provide advance warning of failure, and modeling of life cycle environment stress to compute accumulated damage; data-driven methods involving monitoring and analysis of product functional parameters; and the fusion approach, which combines the PoF and data-driven techniques to provide an accurate estimate of remaining useful life. This paper describes the various approaches to prognostics and presents case studies of the implementation of different prognostic approaches.

View PDFchevron_right

References (24)

  1. A. Andrieu, C.and Doucet and Punskaya E. Sequential Monte Carlo Methods for Optimal Filtering. In Sequential Monte Carlo Methods in Practice , A. Doucet, N. De Frietas, and N. Gordon (Eds.) Springer- Verlag, NY, USA, 2001.
  2. M.S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp. A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking. IEEE Transactions on Signal Processing, 50(2), 2002.
  3. I. Dar and G. Vachtsevanos. Feature level sensor for pattern recognition using an active perception approach. In Proceedings of IS&T/SPIE's Electronic Imaging '97: Science and Technology, 1997.
  4. A. Doucet, N. de Freitas, and N. Gordon. An introduction to Sequential Monte Carlo methods. In Sequential Monte Carlo Methods in Practice , A. Doucet, N. De Frietas, and N. Gordon (Eds.) Springer-Verlag, NY, USA, 2001.
  5. A.D. Flint. A Prognostic Maintenance System Based on the Hough Trans- formation. Transactions of the Institute of Measurement and Control, 16(2):59-65, 1994.
  6. G. Hadden, P. Bergstrom, B. Bennett, G. Vachtsevanos, and J. Van Dyke. Shipboard machinery diagnostics and prognostics/condition based main- tenance: A progress report. In Proceedings of the Maintenance and Reli- ability Conference, MARCON 99, pages 73.01-73.16, 1999.
  7. G. Hadden, G. Vachtsevanos, B. Bennett, and J. Van Dyke. Machinery di- agnostics and prognostics and prognostics/condition based maintenance: A progress report, failure analysis: A foundation for diagnostics and prog- nostics development. In Proceedings of the 53rd Meeting of the society for Machinery Failure Prevention Technology, 1999.
  8. J. Keller and P. Grabill. Vibration monitoring of a uh-60a main trans- mission planetary carrier fault. In Proceedings of the 59th Annual Forum AmericanHelicopter Society, 2003.
  9. D. Kundur and D. Hatzinakos. Blind Image Deconvolution. IEEE Signal Processing Magazine, 13(3):43-46, 1996.
  10. K.A. Marko, J.V. James, T.M. Feldkamp, C.V. Puskorius, J.A. Feld- kamp, and D. Roller. pplication of neural networks to the construction of "virtual sensor and model-based diagnostics. In Proceedings of ISATA 29th International Symposium on Automotive Technology and Automa- tion, pages 133-138, 1996.
  11. C. Musso, N. Oudjane, and F. Le Gland. Improving regularized particle filters. In Sequential Monte Carlo Methods in Practice , A. Doucet, N. De Frietas, and N. Gordon (Eds.) Springer-Verlag, NY, USA, 2001.
  12. M. Orchard. On-line Fault Diagnosis and Failure Prognosis Using Par- ticle Filters. Theoretical Framework and Case Studies. VDM Verlag Dr. Mller Aktiengesellschaft and Co. KG, Saarbrcken, Germany, 2009.
  13. M. Orchard, F. Tobar, and G. Vachtsevanos. Outer Feedback Correc- tion Loops in Particle Filtering-based Prognostic Algorithms: Statistical Performance Comparison. Studies in Informatics and Control, 18(4):295- 304, 2009.
  14. M. Orchard and G. Vachtsevanos. A Particle Filtering Approach for On- Line Fault Diagnosis and Failure Prognosis. Transactions of the Institute of Measurement and Control, 31(3-4):221-246, 2009.
  15. M. Orchard, B. Wu, and G. Vachtsevanos. A particle filter framework for failure prognosis. In Proceedings of WTC2005 World Tribology Congress III, 2005.
  16. R. Patrick, M. Orchard, B. Zhang, M. Koelemay, G. Kacprzynski, A. Ferri, and G. Vachtsevanos. An integrated approach to helicopter planetary gear fault diagnosis and failure prognosis. In 42nd Annual Sys- tems Readiness Technology Conference, AUTOTESTCON 2007, 2007.
  17. T.D. Pebbles, M.A. Essawy, and S. Fein-Sabatto. An intelligent method- ology for remaining useful life estimation of mechanical components. In Proceedings of the Maintenance and Reliability Conference, MARCON 99, pages 27.01-27.09, 1999.
  18. R. Peled, S. Braun, and M. Zacksenhouse. A Blind Deconvolution Seper- ation of Multiple Sources with application to Bearing Diagnostics. Me- chanical Systems and Signal Processing, 14(3):427-442, 2000.
  19. M. Roemer, C. Byingston, G. Kacprzynski, and G. Vachtsevanos. An overview of selected prognostic technologies with reference to an inte- grated phm architecture. In Proceedings of NASA Integrated Vehicle Health Management Workshop, 2005.
  20. B.J. Rosenberg. The navy idss program: adaptive diagnostics and feed- back analysis-precursors to a fault prognostics capability. In Proceedings of the IEEE National Aerospace and Electronics Conference, NAECON, volume 3, pages 1334-1338, 1989.
  21. A. Saxena, B. Wu, and G. Vachtsevanos. Integrated diagnosis and prog- nosis architecture for fleet vehicles using dynamic case-based reasoning. In Proceedings of AUTOTESTCON 2005 Conference, 2005.
  22. B. Wu, A. Saxena, R. Patrick, and G. Vachtsevanos. Vibration monitoring for fault diagnosis of helicopter planetary gears. In Proceedings of the 16th IFAC World Congress, 2005.
  23. B. Zhang, T. Khawaja, R. Patrick, G. Vachtsevanos, M. Orchard, and A. Saxena. Application of Blind Deconvolution Denoising in Failure Prognosis. IEEE Transactions on Instrumentation and Measurement, 58(2):303-310, 2009.
  24. B. Zhang, T. Khawaja, R. Patrick, G. Vachtsevanos, M. Orchard, and A. Saxena. A Novel Blind Deconvolution De-Noising Scheme in Failure Prognosis. Transactions of the Institute of Measurement and Control, 32(1):3-30, 2010.

Related papers

Improved Dynamic Dependability Assessment Through Integration With Prognostics
Yiannis Papadopoulos

IEEE Transactions on Reliability, 2017

The use of average data for dependability assessments results in a outdated system-level dependability estimation which can lead to incorrect design decisions. With increasing availability of online data, there is room to improve traditional dependability assessment techniques. Namely, prognostics is an emerging field which provides asset-specific failure information which can be reused to improve the system level failure estimation. This paper presents a framework for prognosticsupdated dynamic dependability assessment. The dynamic behaviour comes from runtime updated information, asset interdependencies, and time-dependent system behaviour. A case study from the power generation industry is analysed and results confirm the validity of the approach for improved near real-time unavailability estimations.

View PDFchevron_right
Aircraft on-condition reliability assessment based on data-intensive analytics
Márcia Baptista

2017 IEEE Aerospace Conference, 2017

The implementation of condition-based maintenance continues to face several challenges especially in the aeronautics field. While it is true that time-based maintenance dominates the industry today, it is believed that condition monitoring could yield promising results with a better compromise on cost over effectiveness in the long run. The aim of condition-based monitoring in aeronautics is, based on the available system data (e.g., flight, event and maintenance data), to evaluate the current health state of an aircraft component and to estimate its remaining useful life. Several approaches have been studied in condition-based maintenance with the most promising being data-driven modeling. This paper proposes a comparison of a set of data-driven modeling techniques to perform prognostics on a critical component of the jet engine bleed system. The novelty of our work is twofold. First, we perform this comparative study on a real case study of a critical valve of the aircraft bleed system. Fielded data from different data sources are used in the models. To our knowledge, this is the first case study that merges data from the computer central maintenance system (fault messages), maintenance data, and flight data on a prognostics system. Second, a variety of data-driven techniques are compared from neural nets to regression support machines. The models are compared using the standard metrics of absolute, mean, and squared errors. A regressive accuracy curve is also used to compare the models along different prediction window sizes. The results show the best model comprised information from all data sources. The data that most contributed to the performance improvement was the maintenance, flight and fault data, in this order. This result comes to reinforce the notion that it is more difficult to extract quantitative information from fault events than flight data with data-driven regressive methods.

View PDFchevron_right
Reliability Meets Big Data: Opportunities and Challenges
William Meeker

Quality Engineering, 2013

Reliability field data such as that obtained from warranty claims and maintenance records have been used traditionally for such purposes as generating predictions for warranty costs and optimizing the cost of system operation and maintenance. In the current (and future) generation of many products, the nature of field reliability data is changing dramatically. In particular, products can be outfitted with sensors that can be used to capture information about how and when and under what environmental and operating conditions products are being used. Today some of that information is being used to monitor system health and interest is building to develop prognostic information systems. There are, however, many other potential applications for using such data. In this paper we review some applications where field reliability data are used and explore some of the opportunities to use modern reliability data to provide stronger statistical methods to operate and predict the performance of systems in the field. We also provide some examples of recent technical developments designed to be used in such applications and outline remaining challenges.

View PDFchevron_right
Prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation model
Michael Pecht

Mechanical Systems and Signal Processing, 2014

The objective of this study is to develop a state-space-based degradation model and associated computational techniques to reduce failure prognostics uncertainty by fusing on-line monitoring data. A key problem in failure prognostics for an individual system under actual operating conditions is uncertainty management. In this study, the various uncertainty sources in failure prognostics are analyzed, and an appropriate uncertainty quantifying and managing mechanism is proposed, accounting for both the item-to-item variability and the degradation process variability. The method is demonstrated on a crack growth data set, and the results show that the proposed prognostics method has the ability to provide a failure time prediction with less uncertainty by fusing sensor data, which are beneficial for risk assessment and optimal maintenance decision-making. (J. Sun).

View PDFchevron_right
Hybrid Monitoring for the Prognostic of the Reliability System
Jalloul Méliani, Hassani Messaoud

Quality and Reliability Engineering International, 2013

This paper aims at developing a model for the monitoring of a rotating machine. The contribution in this model is the development of the last stage of monitoring which is the prognostic; indeed, the method used takes into account the required quality criteria of the product on one hand and the state of the current system of one somewhere else on the other. The objective of this contribution is to estimate the reliability of the system in time and to plan the time of total system dysfunction. The interval constrained Petri nets are used for the modeling of an industrial example which is the centrifuge pump. I n a manufactories industry, maintenance has always been considered as a cost center and not as a contribution to the added value for the company's good. In fact, this logically means that maintenance has failed. However, this restrictive view, today, has progressively changed. It tends to develop in an approach to increase the system's life cycle. 1 Maintenance must be a means of increase of the availability to the system, 2 hence, a gain center for the company. This evolution in maintenance also has an impact on the strategies evolution that should be elaborated. Indeed, classical strategies, 3 like systematic preventive maintenance, that lead to preventive interventions cannot be compatible with this optimization need.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved