A Fuzzy Inference System for Predicting Human Error and its Application in Process Management (original) (raw)
Related papers
A Fuzzy System for the Assessment of Human Reliability
European Society for Fuzzy Logic and Technology, 2009
This work presents a methodology for the characterization of human reliability based on fuzzy sets concepts, which has been implemented in an innovative decision support system, providing managers with an intelligent computational tool for reducing the possibility of human errors in industrial activities. Considering that such activities can be described as operational, maintenance or inspection processes, which are composed of a set of procedures, the methodology is carried out in two levels: the process level and the procedure level. The proposed system provides a human reliability index, which allows the identification of problems that may constitute causes of human errors, as well as the indication of possible strategies for the control of potentially adverse impacts of interactions that add uncertainty and complexity to processes.
A Critical Review on Reducing Human Error
Advances in Social Science, Education and Humanities Research (ASSEHR), , 2017
In nowadays competition, a private hospital services could be categorized as monopolistic competition. Many of new private hospital established were increasing in the current competition. In order to win, survive in competition, one had to offer a better performance, better competitive advantage from the others. As we spoke of services, one of critical point to build the advantage was through human assets management while reducing human error. A less likely error in services industries would generate a better performance and perceive value from the customer. The source of patients' compliance commonly occurred due to human error, especially the paramedic team. Therefore, we maximized hospital's human assets management to reduce error while preventing it happen in the future. This study aimed to evaluate the human assets management process to reduce human error on private medical field. A number of 138 paramedics of private hospital in Medan were involved in this study. Data were collected by using an organized questionnaire. Data were analyzed using multiple linear regression with SPSS. As result, we found that naturally, human factor tended to create an error while working. These level of error could be reduced overtime through an effective recruitment process and developing employees' skill related to their job. The most important factor to be considered was training and development as it would greatly reduce the human error. This study explained 40.4% variance of human error through selection, and training and development process.
Dynamic Human Error Assessment in Emergency Using Fuzzy Bayesian CREAM
Journal of Research in Health Sciences
Background: Human error is one of the major causes of accidents in the petrochemical industry. Under critical situation, human error is affected by complex factors. Managing such a situation is important to prevent losses and injury. This study aimed to develop a dynamic model of human error assessment in emergencies in the petrochemical industry. Study design: A cross-sectional study. Methods: Fuzzy Bayesian network was used to improve the capabilities of the method for determining the control mode. Fuzzy-AHP-TOPSIS method was also used to prioritize emergency scenarios and human error assessment was applied for the most important emergency condition. Results: Fire in a chemical storage unit was recognized as the most important emergency condition. Common Performance Conditions (CPCs) were determined based on the opinions of a panel of 30 experts and specialists and 7 CPCs were selected for emergencies; then, based on the results of AHP method the relative weights were determined. ...
A fuzzy set-based approach for modeling dependence among human errors
Fuzzy Sets and Systems, 2009
The assessment of dependence among human errors is an important aspect of human reliability analysis. When dependence between two tasks exists, the probability of the operators' failure on one task is higher if they have failed on the preceding task, compared to when they have succeeded. In current practice, the task of assessing dependence among successive operator actions relies to a great extent to expert judgment, often with lack of traceability and repeatability. To overcome these limitations, this work presents a systematic framework for the elicitation of expert knowledge on the factors influencing the dependence between two successive tasks. The framework is based on a fuzzy expert system in which a set of transparent fuzzy logic rules is used to represent the relationship between the input factors and the conditional human error probability. The proposed modeling approach is applied to two tasks required in response to an accident scenario at a nuclear power plant. Given the methodological scope of the work, the fuzzy expert system is tested directly on a working model of dependence, whereas no actual exercise of expert judgment elicitation is carried out.
A fuzzy AHP-based approach for assessing the faulty behaviour risk at workplace
International Journal of Business and Systems Research, 2016
Occupational accidents could negatively affect the productivity and competitiveness of industrial firms. Technical and human-based factors (e.g., preparation of employees, risk perception) have to be evaluated for effectively assessing human error impacts in the overall occupational safety level. The paper proposes a method to assess, in an effective way, faulty behaviour risk (FBR) at workplace; the proposed approach aims also to support the continuous improvement process required by current standards (e.g., OHSAS 18001). The tool applies a fuzzy AHP-based approach to characterise FBR under the influence of technical and organisational criteria. Fuzzy logic has been adopted to add more realistic judgments-compared to 'traditional' AHP-based models-aiming to increase FBR assessment. A test case is proposed to validate the approach. Obtained results will allow safety managers and researchers to identify quantitatively impacts on the overall risk level at workplace due to human behaviour.
A systems approach to human error identification
Safety science, 1996
Human error has been the subject of much debate over the past two decades. Alongside this debate, a number of methods have been developed to predict human error. In this paper a systems approach to the topic is proposed. A methodology based upon the approach has been developed and is reported. The methodology is illustrated by way of a case study. Future directions are indicated. Copyright 0 19%
Chemical engineering transactions, 2014
Human and organizational factors (HOF) contribute to large number of accidents in process industries, therefore it is of prime importance to include HOF into risk assessment. In this paper, a newly developed methodology "Method for Error Deduction and Incident Analysis (MEDIA)" is presented. MEDIA is a taxonomy based HOF assessment methodology which can be used to quantify the HOF risk based on an accidental database (EMARS). Primarily, MEDIA analyzes different organizational characteristics and their effect on human action's outcome. This methodology also accounts for available risk reduction factors and critically of human action failure
Proceedings of the 2019 1st International Conference on Engineering and Management in Industrial System (ICOEMIS 2019), 2019
The accident record from the construction and fabrication company in 2015 until 2018 shows that the highest accident rate is in grinding operation with a percentage of 26%. The main accidents was caused by human error with a percentage 66.67%. This study aims to determine HEPs (Human Error Probabilities) to find out the highest cause of an error, to minimize human error potential, and to determine recommendations. This research determine the HEP values by using HEART (Human Error Assessment and Reduction Technique) method. Fuzzy linguistic approach was integrated on APOA (Assessed Proportion of Affect) determination in order to reduce the expert judgment subjectivity and inconsistency. The calculation result and analysis reveal that the highest Human Error Probabilities (HEP) value is 0.71324 which is shown by the task check the condition of safety guard or protector. Reducing the risk factor and focusing on the main cause of accident are determined by using Impact Assessment to get the risk rating of error and possible error. Some recommendations are given and prioritized based on high rating of error using Error Reduction Analysis.
A fuzzy model for assessing risk of occupational safety in the processing industry
International journal of occupational safety and ergonomics : JOSE, 2012
Managing occupational safety in any kind of industry, especially in processing, is very important and complex. This paper develops a new method for occupational risk assessment in the presence of uncertainties. Uncertain values of hazardous factors and consequence frequencies are described with linguistic expressions defined by a safety management team. They are modeled with fuzzy sets. Consequence severities depend on current hazardous factors, and their values are calculated with the proposed procedure. The proposed model is tested with real-life data from fruit processing firms in Central Serbia.
A methodology for collection and analysis of human error data based on a cognitive model: IDA
Nuclear Engineering and Design, 1997
This paper presents a model-based human error taxonomy and data collection. The underlying model, IDA (described in two companion papers), is a cognitive model of behavior developed for analysis of the actions of nuclear power plant operating crew during abnormal situations. The taxonomy is established with reference to three external reference points (i.e. plant status, procedures, and crew) and four reference points internal to the model (i.e. information collected, diagnosis, decision, action). The taxonomy helps the analyst: (1) recognize errors as such; (2) categorize the error in terms of generic characteristics such as 'error in selection of problem solving strategies' and (3) identify the root causes of the error. The data collection methodology is summarized in post event operator interview and analysis summary forms. The root cause analysis methodology is illustrated using a subset of an actual event. Statistics, which extract generic characteristics of error prone behaviors and error prone situations are presented. Finally, applications of the human error data collection are reviewed. A primary benefit of this methodology is to define better symptom-based and other auxiliary procedures with associated training to minimize or preclude certain human errors. It also helps in design of control rooms, and in assessment of human error probabilities in the probabilistic risk assessment framework. © 1997 Elsevier Science S.A.