Contribution to development of risk analysis methods by application of artificial intelligence techniques

During the life cycle of technical systems, precise and detail failure risk analysis gives suitable input elements for taking appropriate actions, which allows reducing of unwanted uncertainty and occurrences. Traditional method for risk analysis, which is applied for many years, especially in analysis of functionality of technical systems, is Failure Mode and Effects Analysis (FMEA) method. However, in many cases, this method shows weaknesses related to the inconsistency, which is a result of insecure subjectivity during the determination of values for parameters that gives Risk Priority Number (RPN), as well as other weaknesses. This paper shows contribution to the development of failure risk analysis based on FMEA method. Contribution of the development of risk analysis methods is given through modification of traditional FMEA method by integration of artificial intelligence techniques, in this case, by integration of fuzzy logic and by including a few principles based on special classification of recognized failures. Thus, it is minimized effect of methodological inconsistency and some of other identified weaknesses of traditional FMEA method. FMEA method is improved, which provides more precise failure risk evaluation and thus better prediction and minimizing of unwanted occurrences (failures of elements, subsystems, components, etc., of technical systems). It was proved by comparative analysis of applied traditional FMEA method as well as modified FMEA method, hereinafter called “intelligent” FMEA method (IFMEA) on system of tires for city busses.     

Modified failure mode and effects analysis using approximate reasoning

The marine industry is recognising the powerful techniques that can be used to perform risk analysis of marine systems. One technique that has been applied in both national and international marine regulations and operations is failure mode and effects analysis (FMEA). This risk analysis tool assumes a failure mode, which occurs in a system/component through some failure mechanism; the effect of this failure is then evaluated. A risk ranking is produced in order to prioritise the attention for each of the failure modes identified. The traditional method utilises the risk priority number (RPN) ranking system. This method determines the RPN by finding the multiplication of factor scores. The three factors considered are probability of failure, severity and detectability. Traditional FMEA has been criticised to have several drawbacks. These drawbacks are addressed in this paper. A new proposed approach, which utilises the fuzzy rules base and grey relation theory is presented.     

An interval probability-based FMEA model for risk assessment: A real-world case

Failure mode and effect analysis (FMEA) is an effective quality tool to eliminate the risks and enhance the stability and safety in the fields of manufacturing and service industry. Nevertheless, the conventional FMEA has been criticized for its drawbacks in the evaluation process of risk factors or the determination of risk priority number (RPN), which may lead to inaccurate evaluation results. Therefore, in this paper, we develop a novel FMEA method based on rough set and interval probability theories. The rough set theory is adopted to manipulate the subjectivity and uncertainty of experts' assessment and convert the evaluation values of risk factors into interval numbers. Meanwhile, the interval exponential RPN (ERPN) is used to replace the traditional RPN due to its superior properties, eg, solving the problems of duplicate numbers and discontinuity of RPN values. Furthermore, an interval probability comparison method is proposed to rank the risk priority of each failure mode for avoiding the information loss in the calculation process of RPN. Finally, a real case study is presented, and the comparison analysis among different FMEA methods is conducted to demonstrate the reliability and effectiveness of the proposed FMEA method.     

Using Fuzzy Cost‐Based FMEA,GRA and Profitability Theory for Minimizing Failures at a Healthcare Diagnosis Service

This paper proposes an integrated approach to identify, evaluate and improve the potential failures in a service setting. This integrated approach combines Fuzzy cost‐based service‐specific FMEA (FCS‐FMEA), Grey Relational Analysis (GRA) and profitability theory for better prioritization of the service failures by considering cost as an important issue and using the profitability theory in a way that the corrective actions costs are taken into account. Considering profitability with FCS‐FMEA and GRA reduces the losses caused by failure occurrence. Besides, a maximization linear mathematical problem is used to select the best mix of failures to be repaired. We apply our approach to an academic example concerning the potential failures diagnosis of the Internal Medicine service of a hospital located in Seoul, Korea. We applied our approach and solved the associated maximization problem by a commercial solver, producing an optimal solution which indicates the most convenient mix of failures to be repaired by considering available budget. Copyright © 2013 John Wiley & Sons, Ltd.     

A Novel Approach for FMEA: Combination of Interval 2‐Tuple Linguistic Variables and Gray Relational Analysis

Failure mode and effect analysis (FMEA) is a powerful tool for defining, identifying, and eliminating potential failures from the system, design, process, or service before they reach the customer. Since its appearance, FMEA has been extensively used in a wide range of industries. However, the conventional risk priority number (RPN) method has been criticized for having a number of drawbacks. In addition, FMEA is a group decision behavior and generally performed by a cross‐functional team. Multiple experts tend to express their judgments on the failure modes by using multigranularity linguistic term sets, and there usually exists uncertain and incomplete assessment information. In this paper, we present a novel FMEA approach combining interval 2‐tuple linguistic variables with gray relational analysis to capture FMEA team members’ diversity opinions and improve the effectiveness of the traditional FMEA. An empirical example of a C‐arm X‐ray machine is given to illustrate the potential applications and benefits of the proposed approach. Copyright © 2014 John Wiley & Sons, Ltd.     

Enhancing FMEA assessment by integrating grey relational analysis and the decision making trial and evaluation laboratory approach

Failure modes and effects analysis (FMEA) is used widely to improve product quality and system reliability, employing a risk priority number (RPN) to assess the influence of failures. The RPN is a product of three indicators—severity (S), occurrence (O), and detection (D)—on a numerical scale from 1 to 10. However, the traditional RPN method has been criticized for its four chief shortcomings: its (1) high duplication rate; (2) assumption of equal importance of S, O, and D; (3) not following the ordered weighted rule; and (4) failure to consider the direct and indirect relationships between failure modes (FMs) and causes of failure (CFs). To resolve these drawbacks, we propose a novel approach, integrating grey relational analysis (GRA) and the decision-making trial and evaluation laboratory (DEMATEL) method, to rank the risk of failure, wherein the GRA is used to modify RPN values to lower duplications and the ordered weighted rule is followed; then, the DEMATEL method is applied to examine the direct and indirect relationships between FMs and CFs, giving higher priority when a single CF causes FMs to occur multiple times. Finally, an actual case of the TFT-LCD cell process is presented to verify the effectiveness of our method compared with other methods in providing decision-makers more reasonable reference information.     

Risk Failure Deployment: A novel integrated tool to prioritize corrective actions in failure mode and effects analysis

In this paper, a novel integrated tool for failure mode and effects analysis (FMEA), opportunely named Risk Failure Deployment (RFD), which is able to evaluate the most critical failure modes and provide analyst with a practical and step-by-step guidance by selecting the most effective corrective actions for removal/mitigation process of root causes, is presented. Thanks to the modification of the framework of the Manufacturing cost deployment (MCD) and to its well-structured use of matrices, the novel RFD is able both to handle the dependencies and interactions between different and numerous failures and to evaluate the most critical ones on the basis of the risk priority number (RPN). Thereafter, the logical relationship between root causes and failure modes is assessed. Successively, the prioritization of corrective actions that are the most suitable for root causes is executed using not only the RPN but also other criteria, such as the economic aspect and the ease of implementation, that are unavoidable to execute a rational and effective selection of improvement activities. The effectiveness and usefulness in practice of the original tool for the prioritization of corrective actions to mitigate the risks due to failure modes collected during FMEA are presented in a case study.     

A linguistic risk prioritization approach for failure mode and effects analysis: A case study of medical product development

Failure mode and effects analysis (FMEA) is a widely used risk management technique for identifying the potential failures from a system, design, or process and determining the most serious ones for risk reduction. Nonetheless, the traditional FMEA method has been criticized for having many deficiencies. Further, in the real world, FMEA team members are usually bounded rationality, and thus, their psychological behaviors should be considered. In response, this study presents a novel risk priority model for FMEA by using interval two‐tuple linguistic variables and an integrated multicriteria decision‐making (MCDM) method. The interval two‐tuple linguistic variables are used to capture FMEA team members' diverse assessments on the risk of failure modes and the weights of risk factors. An integrated MCDM method based on regret theory and TODIM (an acronym in Portuguese for interactive MCDM) is developed to prioritize failure modes taking experts' psychological behaviors into account. Finally, an illustrative example regarding medical product development is included to verify the feasibility and effectiveness of the proposed FMEA. By comparing with other existing methods, the proposed linguistic FMEA approach is shown to be more advantageous in ranking failure modes under the uncertain and complex environment.     

Utility Priority Number Evaluation for FMEA

Traditionally, decisions on how to improve an operation are based on risk priority number (RPN) in the failure mode and effects analysis (FMEA). Many scholars questioned the RPN method and proposed some new methods to improve the decision process, but these methods are only measuring from the risks viewpoint while ignoring the importance of corrective actions. The corrective actions may be interdependent; hence, if the implementation of corrective actions is in proper order, selection may maximize the improvement effect, bring favorable results in the shortest times, and provide the lowest cost. This study aims to evaluate the structure of hierarchy and interdependence of corrective action by interpretive structural model (ISM), then to calculate the weight of a corrective action through the analytic network process (ANP), then to combine the utility of corrective actions and make a decision on improvement priority order of FMEA by utility priority number (UPN). Finally, it verifies the feasibility and effectiveness of this method by application to a case study. An erratum to this article can be found at     

Applying UGF Concept to Enhance the Assessment Capability of FMEA

The purpose of this paper is to propose a modified version of Failure Mode and Effects Analysis (FMEA) to alleviate its drawbacks. FMEA is an important tool in risk evaluation and finding the priority of potential failure modes for corrective actions. In the proposed method, the Universal Generating Function (UGF) approach has been used to improve the assessment capability of the conventional Risk Priority Number (RPN) in ranking. The new method is named as URPN. It generates the most number of unique values in comparison with the previous methods and considers relative importance for the parameters while it is easy to compute. More unique numbers help to avoid from having the same priority level for different failure modes which represent various risk levels. A case study has been employed to demonstrate that the URPN not only can improve the shortcomings but also is able to provide accurate values for risk assessment. Copyright © 2015 John Wiley & Sons, Ltd.     

基于改进的TOPSIS法与RSR法的质量改善项目综合评估

针对失效模式与影响分析中的风险优先数（RPN）方法在质量改善项目排序问题上的局限性,提出一种新的排序方法。首先,借助模糊集理论和熵权法,确定决策指标的模糊指标值和主、客观权重;随后采用改进的理想解逼近法（TOPSIS）与秩和比法（RSR）获得优先级排序和分档;同时,提出并定义了相对应的关键术语：改善主题、难易程度、发生度和改善潜力,最后,结合企业实例验证了新排序方法的有效性和稳定性。     

Failure mode and effect analysis: an application in reducing risk in blood transfusion

BACKGROUND: In February 2001 Good Samaritan Hospital in Dayton, Ohio, conducted a Failure Mode and Effect Analysis (FMEA) on the blood transfusion process to reduce the risk of problems inherent in the procedure. DEVELOPING THE FMEA: The major steps of the analysis were to identify problems (failure modes), define their causes, and surmise the effects if failures occurred. Numerical scores were assigned for the likelihood of failure occurrence, the severity of the effects, and the possibility that the failure would escape detection. These scores were multiplied and reported as a risk priority number (RPN) for each failure mode. Solutions (process redesign actions) and monitoring plans (design validation) were developed to address the failure modes with the highest RPNs. PRESENTING THE FMEA: In March 2001 the FMEA document was presented to the Safety Board, which approved design changes such as use of a blood barrier system that restricts access to the blood until a patient-specific code is dialed. RESULTS: Measures were developed to analyze results, and rapid-cycle Plan-Do-Study-Act methodology was used to test and document redesign changes; most became the standard operating procedure. The new process accomplished its purpose of preventing serious, avoidable errors. No outcome errors occurred from March 2001 through June 2001 or in the 8 months following housewide implementation on June 18, 2001. DISCUSSION: FMEA was a valuable tool in error-trapping the blood transfusion process. Yet the FMEA process was time-consuming, tedious, and difficult and should be reserved for an organization's highest-priority processes.     

Artificial neural network technology for the classification and cartography of scientific and technical information

This paper describes the implementation of multivariate data analysis: NEURODOC applies the axial k-means method for automatic, non-hierarchical cluster analysis and a Principal Component Analysis (PCA) for representing the clusters on a map. We next introduce Artificial Neural Networks (ANNs) to extend NEURODOC into a neural platform for the cluster analysis and cartography of bibliographic data. The ANNs tested are: the Adaptive Resonance Theory (ART 1), a Multilayer Perceptron (MLP), and an associative network with unsupervised learning (KOHONEN). This platform is intended for quantitative analysis of information.     

Fuzzy smart failure modes and effects analysis to improve safety performance of system: Case study of an aircraft landing system

Failure modes and effects analysis (FMEA) is a safety and reliability technique that is widely used to evaluate, design, and process a system against diverse possible ways through which the potential failure has a tendency to occur. In conventional FMEA, the risk evaluation is determined by risk priority number (RPN) obtained by multiplying of three risk factors—severity, occurrence, and detection. However, because of many shortages in conventional FMEA, the RPN scores have been widely criticized along issues bothering on ambiguity and vagueness, scoring, appraising, evaluating, and selecting corrective actions. In this paper, we propose a new integrated fuzzy smart FMEA framework where the combination of fuzzy set theory, analytical hierarchy process (AHP), and data envelopment analysis (DEA) is used, respectively, to handle uncertainty and to increase the reliability of the risk assessment. These are achieved by employing a heterogeneous group of experts and determining the efficiency of FMEA mode with adequate priority and corrective actions using RPN, time, and cost as indicators. A numerical example (aircraft landing system) is provided to exemplify the feasibility and effectiveness of the proposed model. The outputs of the proposed model compared with the conventional risk assessment technique results show its effectiveness, reliability, and propensity for real applications.     

Adaptive resonance theory-based neural algorithms for manufacturing process quality control

The demand for quality products in industry is continuously increasing. To produce products with consistent quality, manufacturing systems need to be closely monitored for any unnatural deviation in the state of the process. Neural networks are potential tools that can be used to improve the analysis of manufacturing processes. Indeed, neural networks have been applied successfully for detecting groups of predictable unnatural patterns in the quality measurements of manufacturing processes. The feasibility of using Adaptive Resonance Theory (ART) to implement an automatic on-line quality control method is investigated. The aim is to analyse the performance of the ART neural network as a means for recognizing any structural change in the state of the process when predictable unnatural patterns are not available for training. To reach such a goal, a simplified ART neural algorithm is discussed then studied by means of extensive Monte Carlo simulation. Comparisons between the performances of the proposed neural approach and those of well-known SPC charts are also presented. Results prove that the proposed neural network is a useful alternative to the existing control schemes.     

一种改进型自适应加权模糊均值滤波算法

针对原有的自适应加权模糊均值AWFM滤波器对局部噪声幅度估计不足的缺点。提出了一种新的改进型自适应加权模糊均值MAWFM滤波算法。该算法采用了一种新的模糊检测方法，可以同时检测各个像素点的正负向噪声幅度，从而能够建立一种新的自适应的模糊信号空间，以适应噪声在各个图像局部的变化。实验结果表明，MAWFM滤波器比以前的AWFM滤波器及传统的中值滤波器均有较优越的性能。     

集成鱼骨分析与进化法则的产品失效预测及问题求解

 基于传统FMEA在失效问题分析与解决方面的不足,提出了一种集成鱼骨图、FMEA和进化法则的创新设计方法．利用鱼骨图层次化分析辅助FMEA全面挖掘可能发生的失效模式,按照FMEA的规范表达分析失效模式并确定风险优先指数RPN,然后运用进化法则针对失效问题进行有效的解决,提高了解决问题的效率．最后通过铁路减振的示例验证了该集成方法的可行性．     

Unsupervised classification of Space Acceleration Measurement System (SAMS) data using ART2-A

The Space Acceleration Measurement System (SAMS) has been developed by NASA to monitor the microgravity acceleration environment aboard the space shuttle. The amount of data collected by a SAMS unit during a shuttle mission is in the several gigabytes range. Adaptive Resonance Theory 2-A (ART2-A), an unsupervised neural network, has been used to cluster these data and to develop cause and effect relationships among disturbances and the acceleration environment. Using input patterns formed on the basis of power spectral densities (psd), data collected from two missions, STS-050 and STS-057, have been clustered.     

New Failure Mode and Effects Analysis: An Evidential Downscaling Method

Failure mode and effects analysis (FMEA) is an engineering and management technique, which is widely used to define, identify, and eliminate known or potential failures, problems, errors, and risk from the design, process, service, and so on. In a typical FMEA, the risk evaluation is determined by using the risk priority number (RPN), which is obtained by multiplying the scores of the occurrence, severity, and detection. However, because of the uncertainty in FMEA, the traditional RPN has been criticized because of several shortcomings. In this paper, an evidential downscaling method for risk evaluation in FMEA is proposed. In FMEA model, we utilize evidential reasoning approach to express the assessment from different experts. Multi‐expert assessments are transformed to a crisp value with weighted average method. Then, Euclidean distance from multi‐scale is applied to construct the basic belief assignments in Dempster–Shafer evidence theory application. According to the proposed method, the number of ratings is decreased from 10 to 3, and the frame of discernment is decreased from 2¹⁰ to 2³, which greatly decreases the computational complexity. Dempster's combination rule is utilized to aggregate the assessment of risk factors. We illustrate a numerical example and use the proposed method to deal with the risk priority evaluation in FMEA. The results and comparison show that the proposed method is more flexible and reasonable for real applications. Copyright © 2014 John Wiley & Sons, Ltd.     

A quantitative method for Failure Mode and Effects Analysis

Failure Mode and Effects Analysis (FMEA) is commonly used for designing maintenance routines by analysing potential failures, predicting their effect and facilitating preventive action. It is used to make decisions on operational and capital expenditure. The literature has reported that despite its popularity, the FMEA method lacks transparency, repeatability and the ability to continuously improve maintenance routines. In this paper an enhancement to the FMEA method is proposed, which enables the probability of asset failure to be expressed as a function of explanatory variables, such as age, operating conditions or process measurements. The probability of failure and an estimate of the total costs can be used to determine maintenance routines. The procedure facilitates continuous improvement as the dataset builds up. The proposed method is illustrated through two datasets on failures. The first was based on an operating company exploiting a major gas field in the Netherlands. The second was retrieved from the public record and covers degradation occurrences of nuclear power plants in the United States.