{"title":"Data driven prognostics using a Kalman filter ensemble of neural network models","authors":"Leto Peel","doi":"10.1109/PHM.2008.4711423","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711423","url":null,"abstract":"This paper details the winning method in the IEEE GOLD category of the PHM psila08 Data Challenge. The task was to estimate the remaining useable life left of an unspecified complex system using a purely data driven approach. The method involves the construction of Multi-Layer Perceptron and Radial Basis Function networks for regression. A suitable selection of these networks has been successfully combined in an ensemble using a Kalman filter. The Kalman filter provides a mechanism for fusing multiple neural network model predictions over time. The essential initial stages of pre-processing and data exploration are also discussed.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131446266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Maxima-SPRT methodology for health monitoring of contact resistance in IC sockets","authors":"Leoncio D. Lopez, Michael Pecht","doi":"10.1109/PHM.2008.4711465","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711465","url":null,"abstract":"The evaluation of integrated circuit sockets for quality, reliability, and/or prognostic applications is performed with accelerated tests and stress conditions that are defined by industry standards. These methods typically use threshold values to detect degradation and failures of the electrical interconnect. However, this approach does not consider the physics of failure of the component under test and is not sensitive enough to detect small changes in behavior. This paper presents a physics of failure based methodology that, combined with a sequential probability ratio test, overcomes the issues of the traditional approach. This new approach, called Maxima-SPRT, enables early detection of degradation and provides the information needed for the successful implementation of prognostic tools. The method is validated using an elastomer socket, a daisy chain package, and a test board assembly.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131621344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Aircraft AC generators: Hybrid system modeling and simulation","authors":"A. Tantawy, X. Koutsoukos, G. Biswas","doi":"10.1109/PHM.2008.4711420","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711420","url":null,"abstract":"Integrated drive generators (IDGs) are the main source of electrical power for a number of critical systems in aircraft. Fast and accurate fault detection and isolation is a necessary component for safe and reliable operation of the IDG and the aircraft. IDGs are complex systems, and a majority of the existing fault detection and isolation techniques are based on signal analysis and heuristic methods derived from experience. Model-based fault diagnosis techniques are hypothesized to be more general and powerful in designing detection and isolation schemes, but building sufficiently accurate models of complex IDGs is a difficult task. dq0 models have been developed for design and control of generators, but these models are not suitable for fault situations, where the generator may become unbalanced. In this paper, we present a hybrid phase-domain model for the aircraft generator that accurately represents both nominal and parametric faulty behaviors. We present the details of the hybrid modeling approach and simulation results of nominal operation and fault behaviors associated with parametric faults in the aircraft generator. The simulation results show that the developed model is capable of accurately capturing the generator dynamics under a variety of normal and faulty configurations.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116935535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The analysis of Return on Investment for PHM applied to electronic systems","authors":"K. Feldman, P. Sandborn, T. Jazouli","doi":"10.1109/PHM.2008.4711415","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711415","url":null,"abstract":"Prognostics and Health Management (PHM) provides an opportunity for lowering sustainment costs, improving maintenance decision-making, and providing product usage feedback into the product design and validation process. However, support for PHM is predicated on the articulation of clear business cases that quantify the expected cost and benefit of its implementation. The realization of PHM requires implementation at different levels of scale and complexity. The maturity, robustness, and applicability of the underlying predictive algorithms impact the overall efficacy of PHM within an enterprise. The utility of PHM to inform decision-makers within tight scheduling constraints and under different operational profiles likewise affects the cost avoidance that can be realized. This paper discusses the calculation of Return on Investment (ROI) for PHM activities and presents a case study conducted using a stochastic discrete event simulation model to determine the potential ROI offered by electronics PHM. The case study of a multifunctional display in a Boeing 737 compared the life cycle costs of a system employing unscheduled maintenance to the same system using a precursor to failure PHM approach.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115315033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Roger K. Youree, J. Yalowitz, Aaron Corder, Teng K. Ooi
{"title":"A multivariate statistical analysis technique for on-line fault prediction","authors":"Roger K. Youree, J. Yalowitz, Aaron Corder, Teng K. Ooi","doi":"10.1109/PHM.2008.4711447","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711447","url":null,"abstract":"This paper describes a generalized multivariate statistical analysis technique for prediction of impending failures in electronic and electromechanical equipment. This data-driven prognostic technique is useful in health-monitoring situations where equipment physical models are unavailable or of limited fidelity. Statistical analysis algorithms, integrated into a predictive fault detection (PFD) statistical analysis engine, operate on heterogeneous streams of data from sensors that monitor selected equipment structural and functional parameters. The statistical analysis engine processes input data in two stages - similarity testing followed by trend determination. The input stage algorithm extracts multidimensional feature data samples from the arriving sensor data streams. It then performs statistical comparisons of the feature data samples to corresponding feature patterns from equipment considered to be in nominal operating condition. The nominal-condition data may be obtained from equipment specifications, or it may be derived in situ from the sensor data streams. The algorithm maintains a set of scalar similarity metrics for the equipment being monitored, which it periodically compares with pre-computed thresholds. The thresholds may be adaptive, with values typically functions of the amount and variability of the feature data. The trend determination stage is triggered when a threshold value is exceeded. The trend determination algorithm projects trends of feature data from the similarity analysis onto the future. The automatic data trending computation for a given feature is performed by statistically analyzing a window of the feature data. This analysis addresses a collection of different characteristics of a well-fitting trend, which are then fused into a single trend result per data window. The statistical analysis engine applies the trending results to determine the most probable trend, which in the PFD context is related to the requirements for scheduling of equipment maintenance actions.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"603 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Standardizing research methods for prognostics","authors":"S. Uckun, Kai Goebel, Peter J. F. Lucas","doi":"10.1109/PHM.2008.4711437","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711437","url":null,"abstract":"Prognostics and health management (PHM) is a maturing system engineering discipline. As with most maturing disciplines, PHM does not yet have a universally accepted research methodology. As a result, most component life estimation efforts are based on ad-hoc experimental methods that lack statistical rigor. In this paper, we provide a critical review of current research methods in PHM and contrast these methods with standard research approaches in a more established discipline (medicine). We summarize the developmental steps required for PHM to reach full maturity and to generate actionable results with true business impact.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129977431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Kurtoglu, S.B. Johnson, E. Barszcz, J. Johnson, P. Robinson
{"title":"Integrating system health management into the early design of aerospace systems using Functional Fault Analysis","authors":"T. Kurtoglu, S.B. Johnson, E. Barszcz, J. Johnson, P. Robinson","doi":"10.1109/PHM.2008.4711425","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711425","url":null,"abstract":"This paper introduces a systematic design methodology, namely the functional fault analysis (FFA), developed with the goal of integrating SHM into early design of aerospace systems. The basis for the FFA methodology is a high-level, functional model of a system that captures the physical architecture, including the physical connectivity of energy, material, and data flows within the system. The model also contains all sensory information, failure modes associated with each component of the system, the propagation of the effects of these failure modes, and the characteristic timing by which fault effects propagate along the modeled physical paths. Using this integrated model, the designers and system analysts can assess the sensor suitepsilas diagnostic functionality and analyze the ldquoracerdquo between the propagation of fault effects and the fault detection isolation and response (FDIR) mechanisms designed to compensate and respond to them. The Ares I Crew Launch Vehicle has been introduced as a case example to illustrate the use of the Functional Fault Analysis (FFA) methodology during system design.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115027686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prognostic algorithm categorization with PHM Challenge application","authors":"J. Coble, J. Hines","doi":"10.1109/PHM.2008.4711456","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711456","url":null,"abstract":"Prognostic algorithms can be divided into three major categories. The most basic methods model the component or system reliability using failure time data and conventional models such as the Weibull. When information pertaining to the operating condition and environmental stressors are available, stress-based techniques can be used. The third type of prognostics is termed effects-based. It is truly an individual based prognostics because it uses information as to how the individual component is affected by the usage condition. This paper presents a summary of the three prognostic types and describes the ongoing development of a Matlab-based set of tools to facilitate prognostic model development. The application of models of each type is illustrated with the PHM Challenge data set. The paper shows the advantages of identifying a degradation parameter to provide for the use of effects-based prognostics.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129482220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Co-located triangulation for damage position identification from a single SHM node","authors":"S. Kessler, A. Raghavan","doi":"10.1109/PHM.2008.4711440","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711440","url":null,"abstract":"A fundamental limitation for current Structural Health Monitoring (SHM) systems is the need for distributed synchronous sensors to determine precise damage location using traditional triangulation methods. Accuracy is dictated by sensor density (quantity and proximity), which drives complexity, weight and cost to resolve reliable position. This paper introduces a patent-pending real-time method to predict accurate damage location from a single SHM node. This co-located triangulation method consists of novel sensors, algorithms and hardware to achieve a significantly more efficient means of localizing damage. Results are presented for proof-of-concept experiments on an aluminum plate using guided waves, as well as theoretical accuracy and limitations for the method. Finally, a description of a prototype under development is presented. SHM technology will be critical to reducing the overall cost of ownership for air and spacecraft, and the present research could play an important role in implementing such a system feasibly, practically and efficiently.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P. Lall, C. Bhat, M. Hande, V. More, R. Vaidya, R. Pandher, J. Suhling, K. Goebel
{"title":"Latent damage assessment and prognostication of residual life in airborne lead-free electronics under thermo-mechanical loads","authors":"P. Lall, C. Bhat, M. Hande, V. More, R. Vaidya, R. Pandher, J. Suhling, K. Goebel","doi":"10.1109/PHM.2008.4711444","DOIUrl":"https://doi.org/10.1109/PHM.2008.4711444","url":null,"abstract":"Aerospace-electronic systems usually face a very harsh environment, requiring them to survive the high strain rates, e.g. during launch and re-entry and thermal environments including extreme low and high temperatures. Traditional health monitoring methodologies have relied on reactive methods of failure detection often providing little or no insight into the remaining useful life of the system. In this paper, a mathematical approach for interrogation of system state under cyclic thermo-mechanical stresses has been developed for 6-different leadfree solder alloy systems. Data has been collected for leading indicators of failure for alloy systems including, Sn3Ag0.5Cu, Sn3Ag0.7Cu, Sn1Ag0.5Cu, Sn0.3Ag0.5Cu0.1Bi, Sn0.2Ag0.5Cu0.1Bi0.1Ni, 96.5Sn3.5Ag second-level interconnects under the application of cyclic thermo-mechanical loads. Methodology presented resides in the pre-failure space of the system in which no macro-indicators such as cracks or delamination exist. Systems subjected to thermo-mechanical damage have been interrogated for system state and the computed damage state correlated with known imposed damage. The approach involves the use of condition monitoring devices which can be interrogated for damage proxies at finite time-intervals. Interrogation techniques are based on derivation of damage proxies, and system prior damage based non-linear least-squares methods including the Levenberg-Marquardt Algorithm. The systempsilas residual life is computed based on residual-life computation algorithms.","PeriodicalId":377635,"journal":{"name":"2008 International Conference on Prognostics and Health Management","volume":"188 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114017012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}