Failure time data of fielded systems are usually obtained from the actual users of the systems. Due to various operational preferences and/or technical obstacles, a large proportion of field data are collected as aggregate data instead of the exact failure times of individual units. The challenge of using such data is that the obtained information is more concise but less precise in comparison to using individual failure times. The most significant needs in modeling aggregate failure time data are the selection of an appropriate probability distribution and the development of a statistical inference procedure capable of handling data aggregation. Although some probability distributions, such as the Gamma and Inverse Gaussian distributions, have well-known closed-form expressions for the probability density function for aggregate data, the use of such distributions limits the applications in field reliability estimation. For reliability practitioners, it would be invaluable to use a robust approach to handle aggregate failure time data without being limited to a small number of probability distributions. This paper studies the application of phase-type (PH) distribution as a candidate for modeling aggregate failure time data. An expectation-maximization algorithm is developed to obtain the maximum likelihood estimates of model parameters, and the confidence interval for the reliability estimate is also obtained. The simulation and numerical studies show that the robust approach is quite powerful because of the high capability of PH distribution in mimicking a variety of probability distributions. In the area of reliability engineering, there is limited work on modeling aggregate data for field reliability estimation. The analytical and statistical inference methods described in this work provide a robust tool for analyzing aggregate failure time data for the first time.
more »
« less
Product Component Genealogy Modeling and Field‐failure Prediction
Many industrial products consist of multiple components that are necessary for system operation. There is an abundance of literature on modeling the lifetime of such components through competing risks models. During the life‐cycle of a product, it is common for there to be incremental design changes to improve reliability, to reduce costs, or due to changes in availability of certain part numbers. These changes can affect product reliability but are often ignored in system lifetime modeling. By incorporating this information about changes in part numbers over time (information that is readily available in most production databases), better accuracy can be achieved in predicting time to failure, thus yielding more accurate field‐failure predictions. This paper presents methods for estimating parameters and predictions for this generational model and a comparison with existing methods through the use of simulation. Our results indicate that the generational model has important practical advantages and outperforms the existing methods in predicting field failures. Copyright © 2016 John Wiley & Sons, Ltd.
more » « less- PAR ID:
- 10238153
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Quality and Reliability Engineering International
- Volume:
- 33
- Issue:
- 1
- ISSN:
- 0748-8017
- Format(s):
- Medium: X Size: p. 135-148
- Size(s):
- p. 135-148
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
This article formulates risk-based component importance measures (RCIMs) to identify critical components for a bridge subjected to earthquakes. RCIM, unlike traditional reliability-based importance measures, is well suited for complex systems like bridges as it uses a flexible system failure definition using bridge level risk consequences or performance objectives. Contrasting traditional notions of risk and reliability related to structural system failures, the RCIMs embrace a broader definition of risk which includes consequences of system failure to society and the environment. System failure is defined as exceedance of a user-defined threshold of system risk (e.g. based on cost, emissions, embodied energy, or other metrics). Our definition of system failure using global performance metrics helps relating component to system reliability explicitly and offers an alternative perspective to aggregate joint failure events of bridge components into relevant damage states. RCIM combines information about the reliability of a component and its contribution to the system performance and hence the importance measures developed offer risk mitigation indicators for decision makers as to which components may require upgrade to achieve a given performance objective. The proposed RCIMs generalize existing importance measures through analytical exploration of the entire space of system configurations with correlated component failures, while also considering multiple risk-based criteria beyond reliability. These RCIMs, demonstrated through a seismic bridge system case study, further show that as the bridge components age and the hazard intensity varies, the relative contribution of the components to system risk also shifts.
-
more » « less
The continued development of BaTiO3-based multilayer ceramic capacitors has contributed to further miniaturization by reducing the thickness of each dielectric layer for different voltage range components. MLCC designs that achieve higher volumetric capacitive efficiency must be balanced with stable properties over long operational times at higher fields and temperatures, raising concerns about their reliability. To improve the reliability and slow transient mechanisms of oxygen vacancy electromigration that drive the degradation of insulation resistance of MLCCs, we need to develop new models and improved metrologies to enhance the performance of MLCCs. This paper demonstrates how electrical characterization techniques, such as thermally stimulated depolarization current and highly accelerated life test, can be used to better understand MLCCs' degradation and assess their reliability. Also, the limitations of existing lifetime prediction models and their shortcomings of using mean time to failure in predicting the lifetime of MLCCs are discussed along with future perspectives on evaluating the reliability of MLCCs.
-
This paper develops an accurate yet interpretable machine learning framework for predicting field failures from time-series diagnostic data with application to datacenter hard disk drive failure prediction. Interpretable models are accountable: model reasoning can be verified by a domain expert for critical reliability tasks. We develop an attention-augmented recurrent neural network that visualizes the temporal information used to generate predictions; visualizations correlate with physical expectations. Finally, we propose a clustering-based method for discovering failure modes.more » « less
-
Base metal electrode (BME) multilayer ceramic capacitors (MLCCs) are widely used in aerospace, medical, military, and communication applications, emphasizing the need for high reliability. The ongoing advancements in BaTiO3-based MLCC technology have facilitated further miniaturization and improved capacitive volumetric density for both low and high voltage devices. However, concerns persist regarding infant mortality failures and long-term reliability under higher fields and temperatures. To address these concerns, a comprehensive understanding of the mechanisms underlying insulation resistance degradation is crucial. Furthermore, there is a need to develop effective screening procedures during MLCC production and improve the accuracy of mean time to failure (MTTF) predictions. This article reviews our findings on the effect of the burn-in test, a common quality control process, on the dynamics of oxygen vacancies within BME MLCCs. These findings reveal the burn-in test has a negative impact on the lifetime and reliability of BME MLCCS. Moreover, the limitations of existing lifetime prediction models for BME MLCCs are discussed, emphasizing the need for improved MTTF predictions by employing a physics-based machine learning model to overcome the existing models’ limitations. The article also discusses the new physical-based machine learning model that has been developed. While data limitations remain a challenge, the physics-based machine learning approach offers promising results for MTTF prediction in MLCCs, contributing to improved lifetime predictions. Furthermore, the article acknowledges the limitations of relying solely on MTTF to predict MLCCs’ lifetime and emphasizes the importance of developing comprehensive prediction models that predict the entire distribution of failures.more » « less
