In this research, we are concerned with the modeling of optimal maintenance actions in multi-state systems with two failure types. We consider an imperfect maintenance model, that is, the impact of a preventive maintenance action is not minimal (as bad as old) and not perfect (as good as new) but lies between these boundary cases. Further, we assume that the costs of maintenance depend on the degree of repair. If a failure occurs, the system is maintained according to the failure type. Minor failures (type I) are removed through minimal repair and after major failures the system have to be replaced. Cost optimal maintenance policies for some cost functions and different discrete lifetime distributions are considered.
{"title":"Optimal Imperfect Maintenance in a Multi-state System with Two Failure Types","authors":"S. Dietrich, W. Kahle","doi":"10.1109/SMRLO.2016.47","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.47","url":null,"abstract":"In this research, we are concerned with the modeling of optimal maintenance actions in multi-state systems with two failure types. We consider an imperfect maintenance model, that is, the impact of a preventive maintenance action is not minimal (as bad as old) and not perfect (as good as new) but lies between these boundary cases. Further, we assume that the costs of maintenance depend on the degree of repair. If a failure occurs, the system is maintained according to the failure type. Minor failures (type I) are removed through minimal repair and after major failures the system have to be replaced. Cost optimal maintenance policies for some cost functions and different discrete lifetime distributions are considered.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129869085","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}
When the data on the time between failures (TBF) are available, a challenging issue is to infer the distribution of future TBFs. The existing approaches to address this issue include varying-parameter normal and Weibull distributions, where the distributional parameters are functions of the number of cumulative failures. Since the distributional parameters are extrapolated from the two fitted models of the distribution parameters, these approaches may be not robust. In this paper, we propose an improved approach. The proposed approach first estimates alpha-fractiles of time to failure from the observed data for multiple alpha values, and then fits the estimates associated with each alpha value to a three-parameter power-law model. The fitted power-law models are used to estimate the fractiles of a certain future TBF, which form an empirical distribution of the future TBF. The empirical distribution can be further fitted to a distribution model. Due to multiple fractiles are estimated, it is expected that the proposed approach is robust. The approach is illustrated by the well-known bus-motor failure data.
{"title":"Approach for Inferring Fractiles of Future Time between Failures","authors":"R. Jiang","doi":"10.1109/SMRLO.2016.55","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.55","url":null,"abstract":"When the data on the time between failures (TBF) are available, a challenging issue is to infer the distribution of future TBFs. The existing approaches to address this issue include varying-parameter normal and Weibull distributions, where the distributional parameters are functions of the number of cumulative failures. Since the distributional parameters are extrapolated from the two fitted models of the distribution parameters, these approaches may be not robust. In this paper, we propose an improved approach. The proposed approach first estimates alpha-fractiles of time to failure from the observed data for multiple alpha values, and then fits the estimates associated with each alpha value to a three-parameter power-law model. The fitted power-law models are used to estimate the fractiles of a certain future TBF, which form an empirical distribution of the future TBF. The empirical distribution can be further fitted to a distribution model. Due to multiple fractiles are estimated, it is expected that the proposed approach is robust. The approach is illustrated by the well-known bus-motor failure data.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133116486","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}
Grodzenskiy Sergey, Grodzenskiy Yakov, Chesalin Alexander
The efficiency of the optimal statistical sequential criteria: Wald test, Aivazyan test, Lorden test, Grodzenskiy test in the reliability trials is researched. The reseach is carried out for both continuous distributions (Weibull distribution), and for discrete ones (binomial distribution). The comparison of the effectiveness of the examined tests is carried out using the method of statistical modeling (Monte-Carlo).
{"title":"About the Effectiveness of the Statistical Sequential Analysis in the Reliability Trials","authors":"Grodzenskiy Sergey, Grodzenskiy Yakov, Chesalin Alexander","doi":"10.1109/SMRLO.2016.83","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.83","url":null,"abstract":"The efficiency of the optimal statistical sequential criteria: Wald test, Aivazyan test, Lorden test, Grodzenskiy test in the reliability trials is researched. The reseach is carried out for both continuous distributions (Weibull distribution), and for discrete ones (binomial distribution). The comparison of the effectiveness of the examined tests is carried out using the method of statistical modeling (Monte-Carlo).","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"496 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131774470","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}
In industrial applications, practitioners usually face a considerable complexity when optimizing operating strategies under uncertainty. Typical real-world problems arising in practice are notoriously challenging from a computational viewpoint, requiring solutions to Markov Decision problems in high dimensions. In this work, we address a novel approach to obtain an approximate solution to a certain class of problems, whose state process follows a controlled linear dynamics. Our techniques is illustrated by an implementation within the statistical language R, which we discuss by solving a typical problem arising in practice.
{"title":"Solving Control Problems with Linear State Dynamics - A Practical User Guide","authors":"Juri Hinz, Jeremy Yee","doi":"10.1109/SMRLO.2016.103","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.103","url":null,"abstract":"In industrial applications, practitioners usually face a considerable complexity when optimizing operating strategies under uncertainty. Typical real-world problems arising in practice are notoriously challenging from a computational viewpoint, requiring solutions to Markov Decision problems in high dimensions. In this work, we address a novel approach to obtain an approximate solution to a certain class of problems, whose state process follows a controlled linear dynamics. Our techniques is illustrated by an implementation within the statistical language R, which we discuss by solving a typical problem arising in practice.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133766815","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}
V. Oboskalov, S. Timashev, A. Bushinskaya, S. Gusev
This paper considers calculation of structural reliability indices (SRI) for electrical power system (EPS), when "cutoff" failures are taken into account. Calculations are based on "exclusion-renewal" technique. In this paper, the design scheme slightly differs from the electrical scheme. Stochastic network reduction (SNR) technique is considered as the main tool for network reduction. SNR also accounts for directional elements, which have different SRI in forward and backward direction of power flow. The paper shows that difference in resulting SRI of diverse software solutions (SS) arise from different approaches to SNR of series-connected elements. The article compares "p" and "gamma" network reduction techniques (NRT). Taking into account specific nature of EPS, the paper proposes the "gamma" NRT for practical calculations of the EPS structural reliability. The paper also considers implementation of the rhomb NRT at the stage of renewal of the rank 2 nodes. This method is based on parallel calculus of the SRI, which permits substantial speed-up of the design procedure.
{"title":"Stochastic Network Reduction Technique for Calculations of Electrical Power System Structural Reliability","authors":"V. Oboskalov, S. Timashev, A. Bushinskaya, S. Gusev","doi":"10.1109/SMRLO.2016.33","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.33","url":null,"abstract":"This paper considers calculation of structural reliability indices (SRI) for electrical power system (EPS), when \"cutoff\" failures are taken into account. Calculations are based on \"exclusion-renewal\" technique. In this paper, the design scheme slightly differs from the electrical scheme. Stochastic network reduction (SNR) technique is considered as the main tool for network reduction. SNR also accounts for directional elements, which have different SRI in forward and backward direction of power flow. The paper shows that difference in resulting SRI of diverse software solutions (SS) arise from different approaches to SNR of series-connected elements. The article compares \"p\" and \"gamma\" network reduction techniques (NRT). Taking into account specific nature of EPS, the paper proposes the \"gamma\" NRT for practical calculations of the EPS structural reliability. The paper also considers implementation of the rhomb NRT at the stage of renewal of the rank 2 nodes. This method is based on parallel calculus of the SRI, which permits substantial speed-up of the design procedure.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117060189","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}
The problem of efficient clustering of candidate protein structures into a limited number of groups is addressed. Such clustering can be expensive and is rarely used in practice due to its computational complexity. We present a parallel algorithm for the efficient clustering of proteins into groups. The input consists of thousands of candidate proteins structures that have been stochastically generated Monte-Carlo style. The first step is to make a Root Mean Square Deviation (RMSD) comparison matrix. The second step is to utilize parallel processors to calculate a hierarchal cluster of these proteins based on the RMSD matrix and using the Lance-Williams update algorithm. The final output is a Dendrogram of clusters. We have implemented our algorithm and have found it to be scalable.
{"title":"Parallel Clustering of Protein Structures Generated via Stochastic Monte Carlo","authors":"S. Dexter, Gavriel Yarmish, Philip Listowsky","doi":"10.1109/SMRLO.2016.71","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.71","url":null,"abstract":"The problem of efficient clustering of candidate protein structures into a limited number of groups is addressed. Such clustering can be expensive and is rarely used in practice due to its computational complexity. We present a parallel algorithm for the efficient clustering of proteins into groups. The input consists of thousands of candidate proteins structures that have been stochastically generated Monte-Carlo style. The first step is to make a Root Mean Square Deviation (RMSD) comparison matrix. The second step is to utilize parallel processors to calculate a hierarchal cluster of these proteins based on the RMSD matrix and using the Lance-Williams update algorithm. The final output is a Dendrogram of clusters. We have implemented our algorithm and have found it to be scalable.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127661909","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}
In this research we performed comparative analysis of possible solutions for the extended Bin Packing problem, belonging to the group of NP-Complete optimization problems for organization and storage of digital information. The objective was finding a dispersion of N elements from n different classes among the number of resource units while meeting resource capacity. In addition, dispersion elements of this class between different resource units must be minimal. The problem has been defined literally and in mathematical terms and the approach for solution was shown by Greedy Branch and Bound. The advantages and shortcomings of different solution methods are discussed.
{"title":"An Algorithms for Solving Extended Bin Packing Problem for Efficient Storage of Digital Information","authors":"Svetlana Daichman, B. Efros","doi":"10.1109/SMRLO.2016.107","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.107","url":null,"abstract":"In this research we performed comparative analysis of possible solutions for the extended Bin Packing problem, belonging to the group of NP-Complete optimization problems for organization and storage of digital information. The objective was finding a dispersion of N elements from n different classes among the number of resource units while meeting resource capacity. In addition, dispersion elements of this class between different resource units must be minimal. The problem has been defined literally and in mathematical terms and the approach for solution was shown by Greedy Branch and Bound. The advantages and shortcomings of different solution methods are discussed.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127506226","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}
This paper deals with Data Envelopment Analysis (DEA), where we have several organizational units or Decision Making Units -- DMUs. Each DMU has multiple inputs and multiple outputs. DEA calculates the relative efficiencies of DMUs via linear programming. Various versions of DEA were developed. Although DEA is a deterministic model, during the last two decades statistical methods are used in three main dimensions: 1. In preparing the input and output data and DMUs, 2. As a stochastic alternative to derive DMUs efficiencies, 3. As a second stage after the efficiencies are derived to test the relationship between the efficiency and various environmental parameters. Our paper explores the use of the various statistical methods in the DEA context covering these three main dimensions. The major statistical methods we present are: comparisons including parametric and non-parametric tests, correlation and regression, analyses of variance, multivariate analyses, and bootstrapping. Examples from the literature, using various statistical methods in the DEA context, will be presented along the above three dimensions.
{"title":"Statistical Analysis in the DEA Context","authors":"Z. Sinuany-Stern, Lea Friedman","doi":"10.1109/SMRLO.2016.82","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.82","url":null,"abstract":"This paper deals with Data Envelopment Analysis (DEA), where we have several organizational units or Decision Making Units -- DMUs. Each DMU has multiple inputs and multiple outputs. DEA calculates the relative efficiencies of DMUs via linear programming. Various versions of DEA were developed. Although DEA is a deterministic model, during the last two decades statistical methods are used in three main dimensions: 1. In preparing the input and output data and DMUs, 2. As a stochastic alternative to derive DMUs efficiencies, 3. As a second stage after the efficiencies are derived to test the relationship between the efficiency and various environmental parameters. Our paper explores the use of the various statistical methods in the DEA context covering these three main dimensions. The major statistical methods we present are: comparisons including parametric and non-parametric tests, correlation and regression, analyses of variance, multivariate analyses, and bootstrapping. Examples from the literature, using various statistical methods in the DEA context, will be presented along the above three dimensions.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123479053","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}
Sagi Finish, Marina Felshin, I. Frenkel, L. Khvatskin
We present availability and unloading capacity assessment of multi-state material handling system, operate in a stochastic environment and investigate an impact of stochastic demands for material handling. In order to determine the system availability and unloading capacity we constructed Markov models, representing the various unloading capacity levels of each element and sub-system in the Material Handling System. The entire system can be represented as Markov model with 96 different states expressing the different performance levels of the entire process. The stochastic demands for material handling is described as three level Markov model, typical for such environment. The entire Markov model is described as system with 288 differential equations, solution of which is complicated problem. To overcome this obstacle we propose an application of the Lz-transform method for availability and unloading capacity assessment of multi-state Material Handling System (MSMHS). We demonstrated that the suggested method can be implemented in engineering decision making and construction of various MSS systems related to requirements, unloading capacity and production processes.
{"title":"Availability and Unloading Capacity Assessment of Multi-state Material Handling System, Operate in a Stochastic Environment and Material Handling Stochastic Demand","authors":"Sagi Finish, Marina Felshin, I. Frenkel, L. Khvatskin","doi":"10.1109/SMRLO.2016.64","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.64","url":null,"abstract":"We present availability and unloading capacity assessment of multi-state material handling system, operate in a stochastic environment and investigate an impact of stochastic demands for material handling. In order to determine the system availability and unloading capacity we constructed Markov models, representing the various unloading capacity levels of each element and sub-system in the Material Handling System. The entire system can be represented as Markov model with 96 different states expressing the different performance levels of the entire process. The stochastic demands for material handling is described as three level Markov model, typical for such environment. The entire Markov model is described as system with 288 differential equations, solution of which is complicated problem. To overcome this obstacle we propose an application of the Lz-transform method for availability and unloading capacity assessment of multi-state Material Handling System (MSMHS). We demonstrated that the suggested method can be implemented in engineering decision making and construction of various MSS systems related to requirements, unloading capacity and production processes.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"12 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124133612","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}
Yuan Yan, Yi Ding, Chuangxin Guo, R. Wang, Lin Cheng, Yuanzhan Sun
The peaking generating units such as gas and hydro turbines have been widely for providing operating reserve during real time operation of power systems. These generating units usually require a short lead time to start, synchronize and carry load. If the unit starts up successfully, it will transit to the in-service state for generation. However, if the unit fails to start-up or meets a random failure during operation, it goes into the failure state, which may have serious impact on system reliability. In this paper, a multi-state model has been developed for peaking generating units considering their start-up failures and degradation. The conceptual modeling and corresponding reliability solutions for peaking generating units have been comprehensively analyzed.
{"title":"Operating Reliability Analysis of Peaking Generating Units Considering Start-Up Failures and Degradation","authors":"Yuan Yan, Yi Ding, Chuangxin Guo, R. Wang, Lin Cheng, Yuanzhan Sun","doi":"10.1109/SMRLO.2016.37","DOIUrl":"https://doi.org/10.1109/SMRLO.2016.37","url":null,"abstract":"The peaking generating units such as gas and hydro turbines have been widely for providing operating reserve during real time operation of power systems. These generating units usually require a short lead time to start, synchronize and carry load. If the unit starts up successfully, it will transit to the in-service state for generation. However, if the unit fails to start-up or meets a random failure during operation, it goes into the failure state, which may have serious impact on system reliability. In this paper, a multi-state model has been developed for peaking generating units considering their start-up failures and degradation. The conceptual modeling and corresponding reliability solutions for peaking generating units have been comprehensively analyzed.","PeriodicalId":254910,"journal":{"name":"2016 Second International Symposium on Stochastic Models in Reliability Engineering, Life Science and Operations Management (SMRLO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116833940","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：