Planning preventive maintenance (PM) actions for a fleet of repairable systems is not simple due to their complex dependent structure and variability among systems. An optimal PM policy can be established by considering a tradeoff between system reliability and maintenance costs over the lifespan of repairable systems. In this paper, we propose age-reduced nonhomogeneous Poisson process (NHPP) models for doubly-censored (left- and right-censored) or bathtub-shaped recurrent failure data from multiple repairable systems. We apply modeling frameworks of mixed-effects and frailty to the proportional age-reduced NHPP model, of which parameters are estimated by the maximum likelihood (ML) method, except for the improvement factor that is assumed to be known. The proposed models explicitly involve between-system variation through random-effects or frailty, along with a common baseline for all the systems through fixed-effects for non-normal data. Given the estimates for the proposed models, we derive the optimal aperiodic PM policy by considering whole population of repairable systems rather than a single system to reflect practical environments where the PM executes imperfect repairs on same-typed systems following the same schedule in a lump. The optimal policy aims at determining irregular PM check-points and useful lifetime with the objective of minimizing the expected total maintenance cost per unit of time. Analytical results of two real-world examples show prominent applications of the proposed models and methods to doubly-censored or bathtub-shaped failure patterns from a fleet of repairable systems for the purpose of reliability prediction and maintenance optimization.

In some practical circumstances, data are recorded after the systems have begun operations, and data collection is stopped at a predetermined time or after a predetermined number of failures. In such circumstances, incompleteness of various types exists in the aspect of the missing number of failures and their occurrence times beyond the duration of the pilot study. Additionally, multiple repairable systems may present system-to-system variability caused by differences in the operating environments or working loads of individual systems. With respect to left-truncated and right-censored recurrent failure data from multiple repairable systems, we propose a reliability model based on a proportional intensity model with frailty. The frailty model explicitly models unobserved heterogeneity among systems. Covariates incorporated into the proportional intensity model additionally account for the heterogeneity between different operating conditions. To estimate the model parameters for the left-truncated and right-censored recurrent failure data, a Monte Carlo expectation maximization algorithm is proposed. Details of the estimation of the model parameters and the construction of their confidence intervals are examined. A real-world example and simulation studies under various scenarios show prominent applications of the proportional intensity model with frailty to left-truncated and right-censored multiple repairable systems for reliability prediction.

The nonhomogeneous Poisson process (NHPP) has become a useful approach for modeling failure patterns of recurrent failure data revealed by minimal repairs from an individual repairable system. This work investigates complex repairable artillery systems that include several failure modes. We propose a superposed log-linear process (S-LLP) based on a mixture of nonhomogeneous Poisson processes in a minimal repair model. This allows for a bathtub-shaped failure intensity that models artillery data better than currently used methods. The method of maximum likelihood is used to estimate model parameters and construct confidence intervals for the cumulative intensity of the S-LLP. Additionally, for multiple repairable systems presenting system-to-system variability, we apply the mixed-effects models to recurrent failure data with bathtub-shaped failure intensity, based on the superposed Poisson process models including S-LLP. The mixed-effects models explicitly involve between-system variation through random-effects, along with a common baseline for all the systems through fixed-effects. Details on estimation of the parameters of the mixed-effects superposed Poisson process models and construction of their confidence intervals are examined in this work. An applicative example of multiple artillery systems shows prominent proof of the mixed-effects superposed Poisson process models for the purpose of reliability analysis.

The nonhomogeneous Poisson process (NHPP) has become a useful approach for modeling failure patterns of recurrent failure data revealed by minimal repairs from an individual repairable system. Sometimes, multiple repairable systems may present system-to-system variability owing to operation environments or working intensities of individual systems. In this paper, we go over the application of generalized mixed-effects models to recurrent failure data from multiple repairable systems based on the NHPP. The generalized mixed-effects models explicitly involve between-system variation through randomeffects, along with a common baseline for all the systems through fixed-effects for non-normal data. Details on estimation of the parameters of the mixed-effects NHPP models and construction of their confidence intervals are examined. An applicative example shows prominent proof of the mixed-effects NHPP models for the purpose of reliability analysis.

Purpose: The objective of this study was to predict the lifetime of a rubber O-ring in contact with fuel in cases involving a heterogeneous degradation pattern.BRMethods: We introduced a change-point regression model to detect the point at which the degradation rate changed. The data after the change-point were processed using the exponential degradation model to predict the B_p lifetime.BRResults: The prediction results were used to evaluated the superiority of different fuel types, and the results were noted to be in agreement with those presented in literature. BRConclusion: The rubber O-ring in contact with JET A-1 fuel corresponded to a more stable compression set degradation pattern and exhibited a larger lifetime compared to those of BIOJET fuel.

Purpose: Yield and quality problems can be caused by clustering defects in display manufacturing processes. This article proposes a detection method for clustering defects in thin film transistor(TFT) processes of a display.BRMethods: A detection method for display defects was used to solve an imbalanced data problem. We introduce α-index derived from a negative binomial yield model, as one of the cluster indices.BRResults: We applied the proposed method to detect data collected from the TFT processes of the display. We compared the detection accuracy of the α-index. The application results show that the detection accuracy of clustering defects was 92.11%.BRConclusion: In this article, the α-index as a cluster index is proposed to detect the clustering defects in TFT processes. The proposed method provides the best detection accuracy of the defect data in TFT processes.

A condition-based maintenance (CBM) has been widely employed to reduce maintenance cost by predicting the health status of many complex systems in prognostics and health management (PHM) framework. Recently, multivariate control charts used in statistical process control (SPC) have been actively introduced as monitoring technology. In this paper, we propose a condition monitoring scheme to monitor the health status of the system of interest. In our condition monitoring scheme, we first define reference data set using one-class support vector machine (OC-SVM) to construct the control limit of multivariate control charts in phase I. Then, parametric control chart or non-parametric control chart is selected according to the results from multivariate normality tests. The proposed condition monitoring scheme is applied to sensor data of two anemometers to evaluate the performance of fault detection power.

Accelerated life tests (ALTs) have been used to assess reliability of one-shot devices in a short time. Due to destructive characteristics of one-shot devices, lifetime data of the devices is incomplete and enough number of failures or even no failures may be not secured in ALT. In such situations, Baysian methods incorporating prior information into the parameters provide useful inference on the reliability of one-shot devices. In this paper, we propose a modeling approach to predict functional reliability of pin pullers as a kind of one-shot devices, mainly in a Bayesian framework. We introduce three different priors to the parameters of the Weibull distribution or reliability function. Sress-strength relationships of key components in pin pullers are employed to the scale and shape parameters via three prior densities. The proposed methods are illustrated with a variety of simulation studies. The simulation works are performed using the Gibbs sampling technique to generate MCMC samples to obtain Bayesian estimates of the Weibull parameters. The Bayesian estimates from the three priors tend to approach to true parameter values as sample size increases.

Purpose: This paper presents a lifetime prediction method for a rubber O-ring in contact with fuel. The method involves the accelerated destructive degradation test in which different types of fuel are considered for a given type of rubber O-ring.BRMethods: For the prediction of the lifetime of a rubber O-ring by considering the fuel type, a multilevel accelerated degradation model is proposed under the assumption that the activation energy of the Arrhenius model is constant for O-rings of the same type. A Monte-Carlo simulation was performed to predict the lifetime distribution of a rubber O-ring at use condition from an estimated accelerated degradation test model.BRResults: Lifetime predictions are presented for three types of rubber O-rings in contact with two types of fuel samples when the activation energy of the acceleration model is a common parameter for a given type of O-ring.BRConclusion: It was found that an FKM rubber O-ring and a synthetic fuel sample (ADF S-1), with which the O-ring was in contact, was the best combination for long-term storage reliability.

* 이 논문은 2018년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(No. 2018R1D1A1A09083149). 본 연구는 한국전력공사의 2017년 선정 기초연구개발 과제 연구비에 의해 지원되었음(과제번호: R18XA06-46).

Reliability demonstration tests (RDTs) have been widely adopted to verify reliability requirements of manufacturing products. In practice, due to the limited resource and tight development schedule for new products, it is preferable to determine the decision variables including the termination time and the sample size for the RDT in advance. Existing degradation models often fail to capture the nonlinear degradation characteristics of testing items with complicated degradation mechanisms. This paper proposes a reliability demonstration method using an accelerated degradation test (ADT) in the context of a nonlinear random-coefficients model. First, we present the capabilities of the proposed ADT model to degradation data. Then, the cost-effective RDT plan is derived based on two types of decision risks and reliability requirements from both producers and customers, while meeting certain testing time constraints. The proposed method is illustrated using two practical examples. Finally, sensitivity analysis is provided to evaluate the robustness of the proposed RDT plan using ADT data.

Purpose: Accelerated degradation tests can be effective in assessing product reliability when degradation leading to failure can be observed. This article proposes an accelerated degradation test model for highly reliable solid state drives (SSDs).BR Methods: We suggest a nonlinear mixed-effects (NLME) model to degradation data for SSDs. A Monte Carlo simulation is used to estimate lifetime distribution in accelerated degradation testing data. This simulation is performed by generating random samples from the assumed NLME model.BR Conclusion: We apply the proposed method to degradation data collected from SSDs. The derived power model is shown to be much better at fitting the degradation data than other existing models. Finally, the Monte Carlo simulation based on the NLME model provides reasonable results in lifetime estimation.

Harsh noises come from air-conditioning units are chronic complaining issues to their users. Individual perceptions of noise levels have been generally quantified by means of subjective evaluation such as a jury test. This article proposes a classification approach to acoustic noise signals using a wavelet spectrum analysis. We derive energy spectrums of noise signals using a discrete wavelet transform at pre-specified window length. The energy spectrums are a linear form and represented by a Hurst parameter as an informative summary of long-range dependent signal data. The Hurst parameter controls the self-similarity scaling as well as the degree of long-range dependence. We estimate the Hurst parameter through the least squares regression of sample energy against a resolution level in the wavelet spectral domain. In the context of multi-class classification problem, the classification of noise signals is performed by a nonlinear support vector machine (SVM) for parameter estimates of linear energy profiles containing the Hurst parameter. In an application example of air-conditioner noise signals, empirical results show that the proposed method offers the higher level of accuracy in acoustic noise sound classification.

The requirements for timely information on the reliability of product components and materials facilitate the use of accelerated degradation test (ADT). The ADT approach supports the experimenter in drawing quick inference on the lifetime distribution of testing units at normal use condition. This paper provides an Excel add-in program (called RExADT) for analysis of ADT data. RExADT is designed to support two popular ADT approaches: single-stage and two-stage approach. RExADT is implemented in Visual Basic for Applications (VBA) and R based on the R-EXCEL environment. RExADT is expected to help the users with diverse backgrounds perform the ADT analysis conveniently with a familiar graphical user interface in Excel.

In financial distress analysis, the diagnosis of firms at risk for bankruptcy is crucial in preparing to hedge against any financial damage the at-risk firms stand to inflict. Some pre-alarm signals that indicate a potential financial crisis exist when a firm faces a default risk. Early studies on corporate bankruptcy prediction include parametric and nonparametric approaches, such as artificial intelligence (AI), for detecting pre-alarm signals. Among nonparametric techniques, the methods involving support vector machine (SVM) have shown potential in predicting corporate bankruptcy. We propose a hybrid method that combines data depths and nonlinear SVM for the prediction of corporate bankruptcy. We employed data depth functions to condense multivariate financial data with nonlinear and non-normal characteristics into one-dimensional space. The SVM method was introduced to classify the data points on a depth versus depth plot (DD-plot). Based on data set that records failed and non-failed manufacturing firms in Korea over 10 years, the empirical results demonstrated that the proposed method offers a higher level of accuracy in corporate bankruptcy prediction than existing methods. The proposed method is expected to provide a guidance in corporate investing for investors or other interested parties.

Purpose: This study analyzes automobile quality review data to develop alternative analytical method of informal data.Existing methods to analyze informal data are based mainly on the frequency of informal data, however, this research tries to use correlation information of each informal data.Method: After sentimental analysis to acquire the user information for automobile products, three classification methods, that is, naïve Bayes, random forest, and support vector machine, were employed to accurately classify the informal user opinions with respect to automobile qualities.Additionally, Word2vec was applied to discover correlated information about informal data.Result: As applicative results of three classification methods, random forest method shows most effective results compared to the other classification methods.Word2vec method manages to discover closest relevant data with automobile components. Conclusion:The proposed method shows its effectiveness in terms of accuracy and sensitivity on the analysis of informal quality data, however, only two sentiments (positive or negative) can be categorized due to human errors.Further studies are required to derive more sentiments to accurately classify informal quality data.Word2vec method also shows comparative results to discover the relevance of components precisely.

Condition-based maintenance (CBM) is designed to take maintenance actions only when there is an imminent evidence of failure for a monitoring system. The parameters indicating health status of the system are continuously monitored in CBM. This article proposes a condition monitoring scheme based on energy profiles generated from wavelet spectrum analysis. The energy of time series is represented by a wavelet spectrum in scale representations of signals. After deriving wavelet spectrums using a discrete wavelet transform at pre-specified windows, we aim to monitor the system based on multivariate T-2 chart for the parameters in the linear energy profiles. The monitoring scheme is applied to temperature signals measured from a steam turbine generator. The proposed T-2 chart based on the energy profiles shows a potential in early detecting the abnormality of a monitoring system which is not clearly detectable in original time scales. (C) 2017 Elsevier Ltd. All rights reserved.

To generate mechanical movements in one-shot devices such as missiles and space launch vehicles, pyrotechnic mechanical device(PMD) such as pin pullers using pyrotechnic charge has been widely used. Reliability prediction of pin pullers is crucial to successfully execute target missions for the one-shot devices. Because the pin pullers require destructive tests to evaluate their reliability, one would need about 3,000 samples of success to guarantee a reliability of 99.9 % with a confidence level of 95 %. This paper suggests the application of a probit model using the charge amount as a functional parameter for estimation of functional reliability of pin puller. To guarantee target reliability, we propose estimation methods of the lower bound of functional reliability by applying the probit model. Given lower bound of functional reliability, we quantitatively show that the optimum amount of charge increases as the number of samples decreases. Along with a variety of simulations the validity of our new model via real test results is confirmed.