Improved objective Bayesian estimator for a PLP model hierarchically represented subject to competing risks under minimal repair regime

In this paper, we propose a hierarchical statistical model for a single repairable system subject to several failure modes (competing risks). The paper describes how complex engineered systems may be modelled hierarchically by use of Bayesian methods. It is also assumed that repairs are minimal and each failure mode has a power-law intensity. Our proposed model generalizes another one already presented in the literature and continues the study initiated by us in another published paper. Some properties of the new model are discussed. We conduct statistical inference under an objective Bayesian framework. A simulation study is carried out to investigate the efficiency of the proposed methods. Finally, our methodology is illustrated by two practical situations currently addressed in a project under development arising from a partnership between Petrobras and six research institutes.

Download Full-text

Knowledge Discovery for Early Failure Assessment of Complex Engineered Systems Using Natural Language Processing

10.1115/detc2021-70694 ◽

2021 ◽

Author(s):

Sequoia R. Andrade ◽

Hannah S. Walsh

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Failure Modes ◽

Design Information ◽

Complex Engineered Systems ◽

Usable Information ◽

Failure Assessment ◽

Engineered Systems ◽

Related Design

Abstract Emerging complex engineered systems may have unexpected safety issues due to novel operational environments, increasing autonomy, human-machine interaction, and other factors. To prevent failures in operation or testing that necessitate costly redesign, it is desirable to predict likely failure modes early in the design process. Information about past engineering failures in natural language format presents one possible solution by enabling the retrieval of information that can inform new designs. However, identifying documents containing usable information and extracting the required information can be prohibitively time-consuming when implemented at scale. In this research, an automated natural language processing (NLP) framework is proposed to discover relevant knowledge from documents containing failure-related design information. The framework is applied to NASA’s Lessons Learned Information System (LLIS), which is publicly available. Documents containing usable information are filtered using two different NLP-based models. Next, from the identified usable documents, a failure taxonomy is extracted using a partitioned hierarchical topic modeling approach. Partitions of the document describe different sections of the failure taxonomy — i.e., failure, cause of failure, and recommendations — as indicated by the structure of the original document. The extracted failure taxonomy can be leveraged in early design failure assessment methods. Moreover, the framework can be used to identify documents containing usable failure-related design information from other databases and extract relevant information from these documents.

Download Full-text

Preventive maintenance optimization for repairable products considering two-dimensional warranty and customer satisfaction

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability ◽

10.1177/1748006x18804463 ◽

2018 ◽

Vol 233 (4) ◽

pp. 553-566

Author(s):

Yukun Wang ◽

Yiliu Liu ◽

Aibo Zhang

Keyword(s):

Customer Satisfaction ◽

Preventive Maintenance ◽

Product Performance ◽

Maintenance Optimization ◽

Two Dimensional ◽

Maintenance Strategy ◽

Minimal Repair ◽

Proposed Model ◽

Useful Life ◽

Practical Implications

Customer satisfaction with a purchased product is closely related to the product performance within the warranty region and even the performance during the remainder of its useful life. Every satisfied customer may boost the future sales of the same product with positive evaluations and recommendations to others, and thus will create more profits for the manufacturer. During the useful life of the product, the expected cost to the manufacturer normally depends on the warranty policy, product reliability and specific servicing strategies implemented. In this article, considering the effect of customer satisfaction on the manufacturer’s incurred cost, we investigate a periodic and imperfect preventive maintenance strategy for repairable products sold with a two-dimensional warranty policy. The customer satisfaction is measured with the probability of the customer making a repeat purchase from the same manufacturer. In the proposed model, the number of preventive maintenance actions and corresponding maintenance level are jointly derived with the objective of minimizing the expected total cost per product to the manufacturer. The performance of the proposed preventive maintenance strategy is compared with that of minimal repair corrective maintenance strategy in a numerical example, so as to illustrate its applicability. In addition, some practical implications from a detailed sensitivity analysis are elaborated.

Download Full-text

Learning from failures: Design improvements using a multiple criteria decision-making process

Proceedings of the Institution of Mechanical Engineers Part G Journal of Aerospace Engineering ◽

10.1243/095441003769700762 ◽

2003 ◽

Vol 217 (4) ◽

pp. 207-216 ◽

Cited By ~ 13

Author(s):

G G Davidson ◽

A W Labib

Keyword(s):

Decision Making ◽

Failure Modes ◽

Multiple Criteria Decision Making ◽

Multiple Criteria ◽

Mathematical Representation ◽

Analytic Hierarchy ◽

Proposed Model ◽

Invaluable Tool ◽

History Of

This paper proposes a new concept of decision analysis based on a multiple criteria decision making (MCDM) process. This is achieved through the provision of a systematic and generic methodology for the implementation of design improvements based on experience of past failures. This is illustrated in the form of a case study identifying the changes made to Concorde after the 2000 accident. The proposed model uses the analytic hierarchy process (AHP) mathematical model as a backbone and integrates elements of a modified failure modes and effects analysis (FMEA). The AHP has proven to be an invaluable tool for decision support since it allows a fully documented and transparent decision to be made with full accountability. In addition, it facilitates the task of justifying improvement decisions. The paper is divided as follows: the first section presents an outline of the background to the Concorde accident and its history of related (non-catastrophic) malfunctions. The AHP methodology and its mathematical representation are then presented with the integrated FMEA applied to the Concorde accident. The case study arrives at the same conclusion as engineers working on Concorde after the accident: that the aircraft may fly again if the lining of the fuel tanks are modified.

Download Full-text

Forensic Engineering Use Of Fault Tree Analysis

Journal of the National Academy of Forensic Engineers ◽

10.51501/jotnafe.v23i2.662 ◽

2006 ◽

Vol 23 (2) ◽

Author(s):

Frank H. Johnson ◽

DeWitt William E.

Keyword(s):

Fault Tree ◽

Fault Tree Analysis ◽

Tree Analysis ◽

Complex Engineered Systems ◽

Track Record ◽

Forensic Engineering ◽

Fire And Explosion ◽

Engineered Systems ◽

Analytical Tools

Analytical Tools, Like Fault Tree Analysis, Have A Proven Track Record In The Aviation And Nuclear Industries. A Positive Tree Is Used To Insure That A Complex Engineered System Operates Correctly. A Negative Tree (Or Fault Tree) Is Used To Investigate Failures Of Complex Engineered Systems. Boeings Use Of Fault Tree Analysis To Investigate The Apollo Launch Pad Fire In 1967 Brought National Attention To The Technique. The 2002 Edition Of Nfpa 921, Guide For Fire And Explosion Investigations, Contains A New Chapter Entitled Failure Analysis And Analytical Tools. That Chapter Addresses Fault Tree Analysis With Respect To Fire And Explosion Investigation. This Paper Will Review The Fundamentals Of Fault Tree Analysis, List Recent Peer Reviewed Papers About The Forensic Engineering Use Of Fault Tree Analysis, Present A Relevant Forensic Engineering Case Study, And Conclude With The Results Of A Recent University Study On The Subject.

Download Full-text

Unobserved, re-defined, unknown or removed failure modes in competing risks

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability ◽

10.1177/1748006x11401706 ◽

2011 ◽

Vol 225 (4) ◽

pp. 461-474

Author(s):

T Coolen-Maturi ◽

F P A Coolen

Keyword(s):

Competing Risks ◽

Failure Modes ◽

Predictive Approach

Recently the nonparametric predictive approach to inference for competing risks was introduced by Maturi et al. (2010, J. Risk Reliab. 224, 11–26). In this paper further results for such inferences are presented, with focus on four important and closely related aspects. First, the effect of defined failure modes which thus far have not yet caused failures is studied. Second, the effect of re-defining (groups of) failure modes is considered, followed by a discussion of possible unknown, so undefined, failure modes. Finally, the effect of removal of failure modes is illustrated.

Download Full-text

Interval type-2 fuzzy inference-based failure mode and effect analysis model in a group decision-making setting

Kybernetes ◽

10.1108/k-02-2021-0152 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

İlker Gölcük

Keyword(s):

Failure Modes ◽

Fuzzy Inference ◽

Real Life ◽

Effect Analysis ◽

Inference System ◽

Content Type ◽

Proposed Model ◽

Interval Type

PurposeThis paper proposes an integrated IT2F-FMEA model under a group decision-making setting. In risk assessment models, experts' evaluations are often aggregated beforehand, and necessary computations are performed, which in turn, may cause a loss of information and valuable individual opinions. The proposed integrated IT2F-FMEA model aims to calculate risk priority numbers from the experts' evaluations and then fuse experts' judgments using a novel integrated model.Design/methodology/approachThis paper presents a novel failure mode and effect analysis (FMEA) model by integrating the fuzzy inference system, best-worst method (BWM) and weighted aggregated sum-product assessment (WASPAS) methods under interval type-2 fuzzy (IT2F) environment. The proposed FMEA approach utilizes the Mamdani-type IT2F inference system to calculate risk priority numbers. The individual FMEA results are combined by using integrated IT2F-BWM and IT2F-WASPAS methods.FindingsThe proposed model is implemented in a real-life case study in the furniture industry. According to the case study, fifteen failure modes are considered, and the proposed integrated method is used to prioritize the failure modes.Originality/valueMamdani-type singleton IT2F inference model is employed in the FMEA. Additionally, the proposed model allows experts to construct their membership functions and fuzzy rules to capitalize on the experience and knowledge of the experts. The proposed group FMEA model aggregates experts' judgments by using IT2F-BWM and IT2F-WASPAS methods. The proposed model is implemented in a real-life case study in the furniture company.

Download Full-text

Estimating the Gumbel-Barnett copula parameter of dependence

Revista Colombiana de Estadística ◽

10.15446/rce.v41n1.64900 ◽

2018 ◽

Vol 41 (1) ◽

pp. 53-73 ◽

Cited By ~ 3

Author(s):

Jennyfer Portilla Yela ◽

José Rafael Tovar Cuevas

Keyword(s):

Maximum Likelihood ◽

Simulation Study ◽

Bayesian Methods ◽

Prior Distribution ◽

Empirical Evaluation ◽

Bayesian Estimator ◽

Dependence Structure ◽

Type I ◽

Copula Parameter

In this paper, we developed an empirical evaluation of four estimation procedures for the dependence parameter of the Gumbel-Barnett copula obtained from a Gumbel type I distribution. We used the maximum likelihood, moments and Bayesian methods and studied the performance of the estimates, assuming three dependence levels and 20 different sample sizes. For each method and scenario, a simulation study was conducted with 1000 runs and the quality of the estimator was evaluated using four different criteria. A Bayesian estimator assuming a Beta(a,b) as prior distribution, showed the best performance regardless the sample size and the dependence structure.

Download Full-text

A Bayes Continuous Reliability Growth Model with Two Categories of Failures

International Journal of Reliability Quality and Safety Engineering ◽

10.1142/s0218539397000023 ◽

1997 ◽

Vol 04 (01) ◽

pp. 1-15

Author(s):

Daming Lin ◽

W. K. Chiu

Keyword(s):

Competing Risks ◽

Growth Model ◽

Prior Distribution ◽

Hazard Rate ◽

Failure Modes ◽

Weighted Average ◽

Hazard Rates ◽

Development Phase ◽

Reliability Growth ◽

Time Invariant

A Bayesian continuous reliability growth model is presented. It is assumed that the development phase of a product consists of m stages. In each stage, the failure mechanism of the product follows a competing risks model with two specific failure modes: inherent and assignable-cause. The hazard rate for each mode is time-invariant within one stage. Under the assumption that modifications of the product improve its reliability, we assign a reasonable joint prior distribution for the hazard rates. Then Bayesian analysis is carried out using this prior distribution. It turns out that the posterior pdf of the hazard rates of interest is just a weighted average of pdf's which have the same form as the prior pdf. A numerical example is given for illustration.

Download Full-text