Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925796
B. Haan
The notional bathtub curve is often cited to describe how a device's failure rate may change with age. Modeling the bathtub curve or other undulating function to capture the reliability-centric phases of life can be accomplished using the mixed-Weibull distribution. Unfortunately, fitting failure data directly to the mixed-Weibull distribution typically requires an assumption of the number of subpopulations within the distribution and difficult computations that often end in the utilization of complex algorithms. The fitting approach described in this paper provides a tactic that can perform the fit without assuming a set number of subpopulations and can be implemented in a basic spreadsheet. This paper begins with a brief examination of a common mixed-Weibull form. It is observed that the likelihood function of this form implicitly handles the data in aggregate - ironically not a mixture. This can be addressed with a modest adjustment but at the cost of greatly increasing the number of parameters that must be considered to fit the distribution. Two separate derivations of the introduced approach are outlined. The first originates within an Artificial-Life framework used for constructing reliability models. Processes within this framework are taken to a conceptual limit. Addressing computational time issues that result yields the presented approach. Because the Artificial-Life Framework tactic is still largely unproven a second derivation based on the well established k-means clustering algorithm is provided as an alternate. Because k-means clustering algorithms are well known, their behavior provides predictions into the behavior of the approach being introduced. The mechanics of the approach are outlined and detailed using sample data. One simple sample set demonstrates the mechanics while a second, more contextually rich set of data illustrates a more realistic application and behavior of the approach. In each, individual reliability data are classified and subpopulations emerge to quickly estimate parameters for a mixed-Weibull distribution. Performance characteristics are noted to be very similar to the k-means algorithm. Termination requires little iteration so even very complex mixtures can be assessed quickly. As predicted by its k-means derivation the approach is mildly chaotic so multiple trials may yield better solutions. Fortunately speed and ease of implementation accommodates for this shortcoming. Additionally, repeated application of the method on a set of data is shown to yield a discrete probabilistic estimate of the number of subpopulations contained within a dataset. The approach is found to be a convenient addition to the reliability analyst's toolbox.
{"title":"A simple classification approach to build a bathtub","authors":"B. Haan","doi":"10.1109/RAMS.2008.4925796","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925796","url":null,"abstract":"The notional bathtub curve is often cited to describe how a device's failure rate may change with age. Modeling the bathtub curve or other undulating function to capture the reliability-centric phases of life can be accomplished using the mixed-Weibull distribution. Unfortunately, fitting failure data directly to the mixed-Weibull distribution typically requires an assumption of the number of subpopulations within the distribution and difficult computations that often end in the utilization of complex algorithms. The fitting approach described in this paper provides a tactic that can perform the fit without assuming a set number of subpopulations and can be implemented in a basic spreadsheet. This paper begins with a brief examination of a common mixed-Weibull form. It is observed that the likelihood function of this form implicitly handles the data in aggregate - ironically not a mixture. This can be addressed with a modest adjustment but at the cost of greatly increasing the number of parameters that must be considered to fit the distribution. Two separate derivations of the introduced approach are outlined. The first originates within an Artificial-Life framework used for constructing reliability models. Processes within this framework are taken to a conceptual limit. Addressing computational time issues that result yields the presented approach. Because the Artificial-Life Framework tactic is still largely unproven a second derivation based on the well established k-means clustering algorithm is provided as an alternate. Because k-means clustering algorithms are well known, their behavior provides predictions into the behavior of the approach being introduced. The mechanics of the approach are outlined and detailed using sample data. One simple sample set demonstrates the mechanics while a second, more contextually rich set of data illustrates a more realistic application and behavior of the approach. In each, individual reliability data are classified and subpopulations emerge to quickly estimate parameters for a mixed-Weibull distribution. Performance characteristics are noted to be very similar to the k-means algorithm. Termination requires little iteration so even very complex mixtures can be assessed quickly. As predicted by its k-means derivation the approach is mildly chaotic so multiple trials may yield better solutions. Fortunately speed and ease of implementation accommodates for this shortcoming. Additionally, repeated application of the method on a set of data is shown to yield a discrete probabilistic estimate of the number of subpopulations contained within a dataset. The approach is found to be a convenient addition to the reliability analyst's toolbox.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124963148","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925766
M. Hamada, G. Jarrell
The overall objective of design for reliability is to ensure that the final product will be economically reliable. This means that the product's observed reliability has been established with consideration of life cycle costs. These costs include the acquisition cost, scheduled maintenance cost, unscheduled maintenance cost and the cost of failures. Cessna Aircraft Company has developed a model that is used to track the performance of each component, not only based on historical field history, but based on what matters most to the customers, the life cycle cost. This very simple model enables the design and procurement teams to evaluate options, prioritize resources and provides feedback very quickly to the design team during the design process as to which issues need to be addressed first.
{"title":"World-class supply chain reliability in general aviation","authors":"M. Hamada, G. Jarrell","doi":"10.1109/RAMS.2008.4925766","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925766","url":null,"abstract":"The overall objective of design for reliability is to ensure that the final product will be economically reliable. This means that the product's observed reliability has been established with consideration of life cycle costs. These costs include the acquisition cost, scheduled maintenance cost, unscheduled maintenance cost and the cost of failures. Cessna Aircraft Company has developed a model that is used to track the performance of each component, not only based on historical field history, but based on what matters most to the customers, the life cycle cost. This very simple model enables the design and procurement teams to evaluate options, prioritize resources and provides feedback very quickly to the design team during the design process as to which issues need to be addressed first.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131775984","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925812
P. Dersin, A. Peronne, C. Arroum
Operators of complex systems, such as are found in aerospace, electric power networks, automated manufacturing, or the railways industry, impose ever more stringent availability performance constraints. At the same time, increasing attention is being paid to life-cycle cost (LCC). ALSTOM Transport Information Solutions' URBALIS automated mass transit system is confronted with this situation. This has led the RAM Department to investigating some key factors which impact availability and LCC, in order to provide designers and maintainers with guidelines for reaching availability targets at lowest cost. Redundancy needs to be managed: in particular it is crucial to be able to detect a partial loss of redundancy before the function is completely lost. This is where testability and maintenance policy come into play. In a first model, constant failure rate and perfect maintenance are assumed and Markov modelling is used. In order to contemplate the non-constant failure rate case, as well as the deterministic aspect of scheduled maintenance inspections, simulations are then run with Petri nets. Imperfect maintenance models (based on Kijima's virtual age) are also considered so that the impact of maintenance-related ageing can be taken into account. .Recommendations are thus formulated depending on relative unit costs of investment, corrective and preventive maintenance, and sensitivity analyses of system availability are performed with respect to failure rate, test coverage rate as well as percentage of perfect maintenance.
{"title":"Selecting test and maintenance strategies to achieve availability target with lowest life-cycle cost","authors":"P. Dersin, A. Peronne, C. Arroum","doi":"10.1109/RAMS.2008.4925812","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925812","url":null,"abstract":"Operators of complex systems, such as are found in aerospace, electric power networks, automated manufacturing, or the railways industry, impose ever more stringent availability performance constraints. At the same time, increasing attention is being paid to life-cycle cost (LCC). ALSTOM Transport Information Solutions' URBALIS automated mass transit system is confronted with this situation. This has led the RAM Department to investigating some key factors which impact availability and LCC, in order to provide designers and maintainers with guidelines for reaching availability targets at lowest cost. Redundancy needs to be managed: in particular it is crucial to be able to detect a partial loss of redundancy before the function is completely lost. This is where testability and maintenance policy come into play. In a first model, constant failure rate and perfect maintenance are assumed and Markov modelling is used. In order to contemplate the non-constant failure rate case, as well as the deterministic aspect of scheduled maintenance inspections, simulations are then run with Petri nets. Imperfect maintenance models (based on Kijima's virtual age) are also considered so that the impact of maintenance-related ageing can be taken into account. .Recommendations are thus formulated depending on relative unit costs of investment, corrective and preventive maintenance, and sensitivity analyses of system availability are performed with respect to failure rate, test coverage rate as well as percentage of perfect maintenance.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128259569","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925826
Jianxiong Chen, Wenzhen Yan
This paper devotes to the fatigue damage analysis of a solenoid tube under vibration-induced fatigue stresses and is concerned with the estimation of tube reliability from variable amplitude stress histories in the time domain. The complete procedure of reliability assessments for the tube fatigue failure has been presented in this paper. The fatigue strength of the tube material was represented by the S-N curve with variable slope when plotted on paper with logarithmic scales and with variable statistical spread. The maximum fatigue stresses at the stress raiser were obtained from the measured nominal stresses with strain gauges and the stress concentration factor determined by finite element method. Rainflow cycle counting method was used to reduce complex variable amplitude stress history into blocks of constant amplitude loads. The fatigue damage accumulated from these constant amplitude blocks was calculated individually and summed using Miner's rule to obtain the total accumulative fatigue damage. The reliability was estimated as a function of field service usages based on the estimated total cumulative fatigue damage. Iterative numerical calculation processes were developed to solve nonlinear equations. The success of any fatigue analysis procedure depends largely on the availability of reasonably reliable material fatigue properties. The estimation of the material fatigue strength is usually a very important and difficult part of reliability analysis for fatigue failures. If sufficient fatigue test data is available, the S-N curves modeled in this paper can be mathematically determined by maximum likelihood algorithm. However, in reality, the fatigue data often are inadequate, and this is the case in the analysis presented in this paper. This paper presents the techniques that could be useful to estimate the fatigue strength with all available sources of information when no sufficient fatigue data is available.
{"title":"Reliability assessments of vibration-induced tube fatigue failure","authors":"Jianxiong Chen, Wenzhen Yan","doi":"10.1109/RAMS.2008.4925826","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925826","url":null,"abstract":"This paper devotes to the fatigue damage analysis of a solenoid tube under vibration-induced fatigue stresses and is concerned with the estimation of tube reliability from variable amplitude stress histories in the time domain. The complete procedure of reliability assessments for the tube fatigue failure has been presented in this paper. The fatigue strength of the tube material was represented by the S-N curve with variable slope when plotted on paper with logarithmic scales and with variable statistical spread. The maximum fatigue stresses at the stress raiser were obtained from the measured nominal stresses with strain gauges and the stress concentration factor determined by finite element method. Rainflow cycle counting method was used to reduce complex variable amplitude stress history into blocks of constant amplitude loads. The fatigue damage accumulated from these constant amplitude blocks was calculated individually and summed using Miner's rule to obtain the total accumulative fatigue damage. The reliability was estimated as a function of field service usages based on the estimated total cumulative fatigue damage. Iterative numerical calculation processes were developed to solve nonlinear equations. The success of any fatigue analysis procedure depends largely on the availability of reasonably reliable material fatigue properties. The estimation of the material fatigue strength is usually a very important and difficult part of reliability analysis for fatigue failures. If sufficient fatigue test data is available, the S-N curves modeled in this paper can be mathematically determined by maximum likelihood algorithm. However, in reality, the fatigue data often are inadequate, and this is the case in the analysis presented in this paper. This paper presents the techniques that could be useful to estimate the fatigue strength with all available sources of information when no sufficient fatigue data is available.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128366569","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925782
J. Acevedo, A. Paz, S. Fernandez-Gomez, M. Soria
Our research has been focused in the past years on the development of efficient fast battery chargers of application to electrical vehicles. One of the challenges that we are facing is selecting adequate sensing components to accurately monitor the charging process, due to the harsh environment in the batteries that use an electrolyte with sulfuric acid (H2SO4) at an elevated temperature during the charge process. The sensor must be able to measure the electrolyte density at different places within the battery -density varies with location. The accuracy of the density readout must be maintained through the useful life of the vehicle. In this paper we review our current line of research in fast battery charges as it pertains to their reliability. We present our results on accelerated tests using plastic fiber optics as sensing elements for electrolyte density. The test duration was over one calendar year (9,552 hours) using a sensor with four optical fibers. Three of the optical fibers are used to measure density, and the fourth one as a reference to account for common-mode variation. The charge level of the battery can be derived from this density measurement, as well as the overall health of the battery. For the test, the electrolyte acid density was set to 35%, and the temperature to 70 degrees Celsius. An electronic system for emission and detection of light collected data periodically to assess the transmission loss in the fibers as they aged.
{"title":"Life testing of plastic optical fibers for lead-acid battery fast charge equipment","authors":"J. Acevedo, A. Paz, S. Fernandez-Gomez, M. Soria","doi":"10.1109/RAMS.2008.4925782","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925782","url":null,"abstract":"Our research has been focused in the past years on the development of efficient fast battery chargers of application to electrical vehicles. One of the challenges that we are facing is selecting adequate sensing components to accurately monitor the charging process, due to the harsh environment in the batteries that use an electrolyte with sulfuric acid (H2SO4) at an elevated temperature during the charge process. The sensor must be able to measure the electrolyte density at different places within the battery -density varies with location. The accuracy of the density readout must be maintained through the useful life of the vehicle. In this paper we review our current line of research in fast battery charges as it pertains to their reliability. We present our results on accelerated tests using plastic fiber optics as sensing elements for electrolyte density. The test duration was over one calendar year (9,552 hours) using a sensor with four optical fibers. Three of the optical fibers are used to measure density, and the fourth one as a reference to account for common-mode variation. The charge level of the battery can be derived from this density measurement, as well as the overall health of the battery. For the test, the electrolyte acid density was set to 35%, and the temperature to 70 degrees Celsius. An electronic system for emission and detection of light collected data periodically to assess the transmission loss in the fibers as they aged.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130464827","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925778
S.W. Yates
A Bayesian approach to reliability demonstration has been developed by the Australian Department of Defence (Defence) and documented in a handbook. Flexibility was provided to address reliability demonstration requirements relating to probability of success and mean time between failure under both the exponential and Weibull distributions. The handbook was based largely on prior work documented and with the majority of the new work dedicated to ensuring the approach could be practically applied in a contractual environment. The prior work approached the Bayesian reliability demonstration issue through the weighted likelihood form of Bayes' Theorem and incorporated a sequential testing methodology based on the probability of achieving the requirement after each testing phase. An eight step process was developed, consisting of determination of applicability, specification of constraints, determination of weights, construction of the prior, determination of evidence required, testing of the prior, testing and updating and reliability estimation. No pilot project for the handbook had been identified at the time of writing, but the existence of a Bayesian reliability demonstration activity outside of the handbook was noted. It was hoped that this would lead to increased acceptance of Bayesian techniques and postulated that these would eventually become the preferred method of reliability demonstration for Defence.
{"title":"Australian defence standard for Bayesian reliability demonstration","authors":"S.W. Yates","doi":"10.1109/RAMS.2008.4925778","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925778","url":null,"abstract":"A Bayesian approach to reliability demonstration has been developed by the Australian Department of Defence (Defence) and documented in a handbook. Flexibility was provided to address reliability demonstration requirements relating to probability of success and mean time between failure under both the exponential and Weibull distributions. The handbook was based largely on prior work documented and with the majority of the new work dedicated to ensuring the approach could be practically applied in a contractual environment. The prior work approached the Bayesian reliability demonstration issue through the weighted likelihood form of Bayes' Theorem and incorporated a sequential testing methodology based on the probability of achieving the requirement after each testing phase. An eight step process was developed, consisting of determination of applicability, specification of constraints, determination of weights, construction of the prior, determination of evidence required, testing of the prior, testing and updating and reliability estimation. No pilot project for the handbook had been identified at the time of writing, but the existence of a Bayesian reliability demonstration activity outside of the handbook was noted. It was hoped that this would lead to increased acceptance of Bayesian techniques and postulated that these would eventually become the preferred method of reliability demonstration for Defence.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134115589","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925803
D. H. Rose
A Federal Highway Administration study published in 2001 indicated that corrosion costs the US economy $276B/year, or 3.1% of the U.S. gross domestic product (GDP). This study was based upon an analysis of twenty-six individual sectors of the US economy. In response to the conclusions, Congress directed the DOD, one of the sectors examined in the study, to implement a focused, Department wide program to address the problem. Congress later directed DOD to sponsor the National Research Council to investigate the curricula at our Nation's institutes of higher learning and make recommendations to improve the corrosion education that undergraduate engineering students receive. Improving engineering education will help reduce the cost of corrosion. Taking full advantage of improved skills, however, while enabling the current workforce to effectively help in the fight, will require the development, promotion, and institutionalization of practical corrosion analysis tools. To ensure that potential cost reductions are maximized, the discipline employing these proposed tools must currently play an active role in product design and sustainment, and the tools must be integrated into currently accepted practices. Since reliability engineers routinely work with designers, maintainers, and other specialties that support the entire product life-cycle, they possess an understanding of system-level design and aging far exceeding that possessed by designers and most, if not all, other engineering disciplines. This perspective, if appropriately focused towards corrosion, provides the opportunity for the reliability community to evolve and improve its current analytical processes, thus helping break down the barriers that have long impeded the implementation of effective corrosion prevention and control (CP&C) practices.
{"title":"Reducing corrosion costs through reliability centered design","authors":"D. H. Rose","doi":"10.1109/RAMS.2008.4925803","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925803","url":null,"abstract":"A Federal Highway Administration study published in 2001 indicated that corrosion costs the US economy $276B/year, or 3.1% of the U.S. gross domestic product (GDP). This study was based upon an analysis of twenty-six individual sectors of the US economy. In response to the conclusions, Congress directed the DOD, one of the sectors examined in the study, to implement a focused, Department wide program to address the problem. Congress later directed DOD to sponsor the National Research Council to investigate the curricula at our Nation's institutes of higher learning and make recommendations to improve the corrosion education that undergraduate engineering students receive. Improving engineering education will help reduce the cost of corrosion. Taking full advantage of improved skills, however, while enabling the current workforce to effectively help in the fight, will require the development, promotion, and institutionalization of practical corrosion analysis tools. To ensure that potential cost reductions are maximized, the discipline employing these proposed tools must currently play an active role in product design and sustainment, and the tools must be integrated into currently accepted practices. Since reliability engineers routinely work with designers, maintainers, and other specialties that support the entire product life-cycle, they possess an understanding of system-level design and aging far exceeding that possessed by designers and most, if not all, other engineering disciplines. This perspective, if appropriately focused towards corrosion, provides the opportunity for the reliability community to evolve and improve its current analytical processes, thus helping break down the barriers that have long impeded the implementation of effective corrosion prevention and control (CP&C) practices.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114978312","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925824
C. Constantinescu
A significant amount of research has been aimed at analyzing the effects of high energy particles on semiconductor devices. However, less attention has been given to the intermittent faults. Field collected data and failure analysis results presented in this paper clearly show intermittent faults are a major source of errors in modern integrated circuits. The root cause for these faults ranges from manufacturing residuals to oxide breakdown. Burstiness and high error rates are specific manifestations of the intermittent faults. They may be activated and deactivated by voltage, frequency, and operating temperature variations. The aggressive scaling of semiconductor devices and the higher circuit complexity are expected to increase the likelihood of occurrence of the intermittent faults, despite the extensive use of fault avoidance techniques. Herein we discuss the effectiveness of several fault tolerant approaches, taking into consideration the specifics of the errors generated by intermittent faults. Several solutions, previously proposed for handling particle induced soft errors, are exclusively based on software and too slow for handling large bursts of errors. As a result, hardware implemented fault tolerant techniques, such as error detecting and correcting codes, self checking, and hardware implemented instruction retry, are necessary for mitigating the impact of the intermittent faults, both in the case of microprocessors, and other complex integrated circuits.
{"title":"Intermittent faults and effects on reliability of integrated circuits","authors":"C. Constantinescu","doi":"10.1109/RAMS.2008.4925824","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925824","url":null,"abstract":"A significant amount of research has been aimed at analyzing the effects of high energy particles on semiconductor devices. However, less attention has been given to the intermittent faults. Field collected data and failure analysis results presented in this paper clearly show intermittent faults are a major source of errors in modern integrated circuits. The root cause for these faults ranges from manufacturing residuals to oxide breakdown. Burstiness and high error rates are specific manifestations of the intermittent faults. They may be activated and deactivated by voltage, frequency, and operating temperature variations. The aggressive scaling of semiconductor devices and the higher circuit complexity are expected to increase the likelihood of occurrence of the intermittent faults, despite the extensive use of fault avoidance techniques. Herein we discuss the effectiveness of several fault tolerant approaches, taking into consideration the specifics of the errors generated by intermittent faults. Several solutions, previously proposed for handling particle induced soft errors, are exclusively based on software and too slow for handling large bursts of errors. As a result, hardware implemented fault tolerant techniques, such as error detecting and correcting codes, self checking, and hardware implemented instruction retry, are necessary for mitigating the impact of the intermittent faults, both in the case of microprocessors, and other complex integrated circuits.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132130359","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925788
J. Gyekenyesi, B. Strack, E. Zampino, S. Pai
The reliability of a simple turbomachinery model was calculated to demonstrate the application of a newly developing system integration tool, Probabilistic Design and Analysis Framework(PRODAF), along with efficient probabilistic methods using a response surface method. The model represents a system consisting of hypothetical turbine components. The parts include a blade, disk, and shaft with an applied angular velocity. All the components were modeled with the properties of the nickel alloy, Inconel 718. A response surface was calculated for the system of components to improve probabilistic computational efficiency. In addition, a fast probability integration method, Advanced First Order Reliability Method (AFORM), was used for the probabilistic analysis in order to provide an efficient analysis as possible. Geometric dimensions, the applied load, and material yield strength were varied for this study. The probability of failure was determined using the maximum first principal stress response and the material yield strength. A simple G function using the difference between strength and loading stress was used to determine failure limits. The probabilistic sensitivity of the failure response relative to the individual variables was determined also with material yield strength having the greatest influence. The model was recreated with every iteration of the probabilistic analysis in order to vary the geometry. As a result, the response surface method has a significant impact on improving computational efficiency and enabling reliability analysis with rapid turnaround.
{"title":"System reliability analysis with the response surface method","authors":"J. Gyekenyesi, B. Strack, E. Zampino, S. Pai","doi":"10.1109/RAMS.2008.4925788","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925788","url":null,"abstract":"The reliability of a simple turbomachinery model was calculated to demonstrate the application of a newly developing system integration tool, Probabilistic Design and Analysis Framework(PRODAF), along with efficient probabilistic methods using a response surface method. The model represents a system consisting of hypothetical turbine components. The parts include a blade, disk, and shaft with an applied angular velocity. All the components were modeled with the properties of the nickel alloy, Inconel 718. A response surface was calculated for the system of components to improve probabilistic computational efficiency. In addition, a fast probability integration method, Advanced First Order Reliability Method (AFORM), was used for the probabilistic analysis in order to provide an efficient analysis as possible. Geometric dimensions, the applied load, and material yield strength were varied for this study. The probability of failure was determined using the maximum first principal stress response and the material yield strength. A simple G function using the difference between strength and loading stress was used to determine failure limits. The probabilistic sensitivity of the failure response relative to the individual variables was determined also with material yield strength having the greatest influence. The model was recreated with every iteration of the probabilistic analysis in order to vary the geometry. As a result, the response surface method has a significant impact on improving computational efficiency and enabling reliability analysis with rapid turnaround.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127278179","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}
Pub Date : 2008-01-28DOI: 10.1109/RAMS.2008.4925817
Yu Liu, Hongzhong Huang, H. Pham
This paper introduces a proposed model to evaluate the reliability of multi-component degradation systems suffering two kinds of competing failure causes: internal degradation process and damage from external random shocks. The internal degradation is expressed as a random process with respect to working time, and a geometric process is employed to describe cumulative damage caused by external random shocks. In our proposed model, the system is assumed to be failed when internal degradation or cumulative damage from random shocks exceed random life thresholds. The reliability expression is derived when the random life threshold and degradation process are considered to follow a Weibull distribution. A studied case of series-parallel system is presented to illustrate the proposed model, and a numerical algorithm is provided to simplify the calculating process based on normal approximation and assess the system reliability. Finally, Monte Carlo simulation method is employed to verify the model and algorithms.
{"title":"Reliability evaluation of systems with degradation and random shocks","authors":"Yu Liu, Hongzhong Huang, H. Pham","doi":"10.1109/RAMS.2008.4925817","DOIUrl":"https://doi.org/10.1109/RAMS.2008.4925817","url":null,"abstract":"This paper introduces a proposed model to evaluate the reliability of multi-component degradation systems suffering two kinds of competing failure causes: internal degradation process and damage from external random shocks. The internal degradation is expressed as a random process with respect to working time, and a geometric process is employed to describe cumulative damage caused by external random shocks. In our proposed model, the system is assumed to be failed when internal degradation or cumulative damage from random shocks exceed random life thresholds. The reliability expression is derived when the random life threshold and degradation process are considered to follow a Weibull distribution. A studied case of series-parallel system is presented to illustrate the proposed model, and a numerical algorithm is provided to simplify the calculating process based on normal approximation and assess the system reliability. Finally, Monte Carlo simulation method is employed to verify the model and algorithms.","PeriodicalId":143940,"journal":{"name":"2008 Annual Reliability and Maintainability Symposium","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128957586","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：