Human Error Factors Research Articles

Integrated Machine Learning and Region Growing Algorithms for Enhanced Concrete Crack Detection: A Novel Approach

In the field of construction engineering, the cracking of concrete structures is a common engineering problem, which has a great impact on the overall stability and service life of the engineered structure. During structural repair, crack detection is the most critical step. Automatic detection significantly reduces the engineering cost and human factor error compared with manual detection. However, due to the changeable environment of the project site and different image specifications, using a single algorithm makes it difficult to balance high efficiency and high accuracy. In this study, we designed a combined recognition method including the region growth algorithm and machine learning regression that can achieve a tradeoff between accuracy and efficiency. Firstly, the regression method learns the image features of the dataset and the specific region growth threshold, and the regression function is trained by using the open-source dataset to determine the region growth threshold using the characteristics of the images included in the tests. The region growth algorithm is used to expand the threshold from the seed points of the image to obtain the crack recognition results. The results show that this method improves the accuracy of SSIM by 7% compared with the traditional region growth algorithm, and does not significantly increase the computational cost, with an increase of 0.78 s per photo process. Compared with the deep learning method, the recognition accuracy of SSIM is decreased by 5.96%, but it takes less resources and has high efficiency.

Patient safety during transfers from critical care: developing and assessing a checklist.

Critically ill patients often need to be transferred from the intensive care unit (ICU) to the imaging department. This can compromise their safety, not only because of the inherent risk of deterioration but also because of the potential for incidents due to the inadequate preparation of medicines, equipment and monitoring. Using a patient transfer checklist can reduce the risk of human factor errors. This article reports on a quality improvement project conducted at the ICU of an acute hospital trust in the Midlands to develop and evaluate a patient transfer checklist. The checklist was developed based on guidance from the Intensive Care Society and evaluated using retrospective incident reports, an audit of staff compliance and a user survey. Using a transfer checklist in the ICU is likely to reduce patient safety incidents during transfers, but a shift in workplace culture may be needed to enhance incident reporting.

Safety evaluation of human-caused errors in civil aviation based on analytic hierarchy process and fuzzy comprehensive evaluation method

PurposeAt present, the statistics of human error events in domestic civil aviation are limited, and the analysis indicators are difficult to quantify. The purpose of this study is to reduce the incidence of human error events and improve the safety of civil aviation.Design/methodology/approachIn this paper, a safety prevention evaluation method combining analytic hierarchy process (AHP) and fuzzy comprehensive evaluation (FCE) is proposed. The risk factors of civil aviation safety are identified through questionnaire survey and calculated by MATLAB software.FindingsThe results of the study are as follows: a safety risk evaluation index system including 4 first-level indicators and 16 second-level indicators is constructed; the AHP is used to calculate the weight of the influencing factors of human error and sort them; and the FCE method is used to quantitatively evaluate the safety prevention of civil aviation human error and put forward the countermeasures.Research limitations/implicationsThis study also has some limitations. While it provides an overall quantitative identification of civil aviation safety risk factors, the research methods chosen, such as the questionnaire survey method and the AHP, involve individual subjectivity. Consequently, the research results may have errors. In the preliminary preparation of the follow-up study, we should analyze a large number of civil aviation accident investigation reports, more accurately clarify the human error factors and completely adopt the quantitative analysis method in the research method.Practical implicationsThis study identifies the risk factors of civil aviation safety and conducts a reasonable analysis of human error factors. In the daily training of civil aviation, the training can be focused on previous man-made accidents; in view of the “important” influencing factors, the aviation management system is formulated to effectively improve the reliability of aviation staff; according to the evaluation criteria of human error in civil aviation, measures to prevent and control accidents can be better formulated.Social implicationsIn view of these four kinds of influencing factors, the corresponding countermeasures and preventive measures are taken according to the discussion, so as to provide the basis for the prevention of aviation human error analysis, management and decision-making, prevent the risk from brewing into safety accidents and improve the safety of aviation management.Originality/valueBased on the questionnaire survey, this study creatively applies the safety prevention evaluation method combining AHP and FCE to the study of civil aviation human error, integrates the advantages of qualitative and quantitative methods, flexibly designs qualitative problems, objectively quantifies research results and reduces subjective variables. Then, by discussing civil aviation safety management measures to avoid risk factors, reduce the incidence of human error events and improve the safety of civil aviation.

Uncertainty-Aware and Explainable Human Error Detection in the Operation of Nuclear Power Plants

The timely and accurate identification of incidents, such as human factor error, is important to restore nuclear power plants (NPPs) to a stable state. However, the identification of abnormal operating conditions is difficult because of the existence of multiple scenarios. In addition, to implement mitigation actions rapidly after an incident occurs, operators must accurately identify an incident by monitoring the trends of many variables. The mental burden posed by this can increase human error and cause failure in identifying incidents. Failure to identify incidents directly results in erroneous mitigation measures, which are detrimental to NPPs. In this study, we leverage uncertainty-aware models to identify such errors and thereby increase the chances of mitigating them. We use the data collected from a physical test bed. The goal is to identify both certain and accurate models. For this, the two main aspects of focus in this study are explainable artificial intelligence (XAI) and uncertainty quantification (UQ). While XAI elucidates the decision pathway, UQ evaluates decision reliability. Their integration paints a comprehensive picture, signifying that understanding decisions and their confidence should be interlinked. Thus, in this study we leverage UQ measures (e.g. entropy and mutual information) along with Shapley additive explanations to gain insights into the features contributing to both accuracy and uncertainty in error identification. Our results show that uncertainty-aware models combined with XAI tools can explain the artificial intelligence–prescribed decisions, with the potential of better explaining errors for the operators.

Dynamic reliability analysis of angular contact ball bearing based on maximum entropy quadratic fourth moment method*

ABSTRACT Bearing failure occurs when the dynamic contact stress exceeds the yield strength of the bearing material during operation. To minimise the risk of bearing failure, a new reliability theory method is proposed based on the stress-strength model of bearings, incorporating random input variables to analyse the reliability of angular contact ball bearings (ACBBs) and quantify their dynamic performance. The maximum entropy quadratic fourth moment method is used to calculate the probability distribution of maximum orthogonal shear stress-strength of bearing, and the maximum entropy principle is used to obtain the approximation of the minimum human error factors. Additionally, reliability-based sensitivity indices are derived to investigate the parametric significance of random input variables. Using B218 bearing as an example, the engineering application of this method in dynamic reliability and reliability-based sensitivity analysis is illustrated. Monte Carlo simulation is performed to verify the accuracy and effectiveness of the method to provide benchmark results. The results show that the Poisson’s ratio have a greater influence on the dynamic reliability of ACBBs than other parameters. Improving parameters such as ball diameter, raceway groove curvature radius and contact angle can also improve the reliability of bearings to some extent.

Identifying and preventing human error in the sugar production process: A multi-stage approach using HTA, HEC and PHEA techniques

This article discusses the importance of identifying and preventing human error in industrial environments, specifically in the sugar production process. The article emphasizes the importance of choosing the right technique for risk assessment studies resulting from human errors. A cross-sectional study was conducted using a multi-stage approach – Hierarchical Task Analysis (HTA), Human Error Calculator (HEC), and Predictive Human Error Analysis (PHEA) – to identify potential human errors in the sugar production process. The HTA, HEC, and PHEA techniques were employed to evaluate each stage of the process for potential human errors. The results of the HTA technique identified 35 tasks and 83 sub-tasks in 14 units of the sugar production process. According to HEC technique 4 tasks with 80 % probability of human error and 2 tasks with 50 % probability of human error had the highest calculated error probabilities. The factors of individual skill, task repetition and importance were the most important factors of human error in the present study. The analysis of PHEA worksheets showed that the number of human errors identified in the tasks with highest probability were 8 errors, of which 50 % were action errors, 25 % checking errors, 13 % selection errors, and 12 % retrieval errors. To mitigate the consequences of human error, it was recommended training courses, raising operator awareness of error consequences, and installing instructions in the sugar production process. Based on the findings, the article concludes that the HEC and PHEA techniques are applicable and effective in identifying and analyzing human errors in process and food industries.

Mesh Characteristic Analysis of Spiral Bevel Gear Pairs Considering Assembly Errors and Tooth Tip Chipping Faults

Due to machining errors, location inaccuracies, human error, and various other factors, it is challenging to avoid assembly errors during the production of spiral bevel gears (SBGs). When SBG assembly errors occur, it can cause the appearance of edge contact and may even lead to severe tooth tip chipping. In this study, we propose an improved method based on loaded tooth contact analysis (LTCA) to examine mesh characteristics, including time-varying mesh stiffness (TVMS), unloaded transmission error, and contact stress. Furthermore, we explore the effects of assembly errors and tooth tip chipping. Moreover, it is observed that assembly errors can alter the contact area of SBGs and potentially reduce the peak-to-peak value of TVMS. Additionally, the occurrence of tooth tip chipping decreases TVMS within the chipping region, lowers transmission error, and increases maximum contact stress. Notably, when assembly errors are present, the reduction in TVMS due to tooth tip chipping exceeds that of a properly assembled SBG pair.

AUTOMATION OF THE PROCESS AND OPTIMIZATION OF TECHNICAL DIAGNOSTICS RESULTS PROCESSING

High safety requirements are imposed on the operation of production facilities. One of the requirements is periodic diagnostics of equipment and structures. Technical diagnostics is the recognition of the state of a technical system, which includes a wide rangeof problems associated with obtaining and evaluating diagnostic information. Surveys provide extensive information about the diagnostic object, which allows us to conclude about the operability of the object, to make a decision about repairs or modernization.The article discusses the process of diagnostics, its shortcomings and methods of their elimination. A program for automating the process and processing the results of technical diagnostics is proposed. The implementation of the development is aimed at increasing the reliability of the data obtained, reducing labor costs, and improving the state of safety at production facilities. It is also assumed that when using the development, the number of industrial accidents that occurred due to human factor errors during technical diagnostics will be reduced.The program consists of four elements, which will allow them to be gradually implemented in production: a sensor-server commu-nication system, a database, an electronic technological scheme of the object, a computing module. The communication system will simplify the transmission of data from the control sites. The database will facilitate work with documentation for control objects. The information available on the electronic technological scheme will increase the speed of interaction of employees of various services during diagnostics. The calculation module will eliminate the human factor during calculations and accelerate the formation of control acts and the conclusion of the industrial safety expertise.The joint use of all elements of the program will facilitate and accelerate the work on technical diagnostics and simplify the work with documentation for research objects.

Designing of Goods Separation Conveyor using GM65 QR Code Scanner Sensor

The sorting or separation process is crucial in the delivery of goods or packages, especially when viewed from the many regions in Indonesia. From the management system of separating goods which is generally still done manually, causing some goods to experience destination errors and delivery delays or commonly called Criss-Cross (CC). Delivery delays are also influenced by human error factors, so special tools are needed to separate goods based on the destination city of the goods, one of which uses a conveyor with a GM65 QR Code Scanner sensor. This sensor works based on commands from Arduino which has been programmed in such a way that it can control all inputs and outputs used in the system. In this system, the goods to be separated are made in the form of 3D mode boxes, where each box is affixed with a different QR code, namely A, B, and C. Each QR code represents the destination city of the goods to be separated, namely city A and city B, but for QR code C indicates data other than city A and city B which will be separated as foreign goods so that in this case it does not match any separation. After testing, the tool can work properly and obtain the results of separating goods in the form of a type of QR code that is read with the destination city of each item that has been separated.

MODEL REGRESI LINIER PENGARUH STANDAR TEKNIS JALAN TERHADAP KECELAKAAN LALU LINTAS PADA JALAN PROVINSI (STUDI KASUS : RUAS JALAN PEMALANG – PURBALINGGA)

In the 2016-2021, there were 12 accidents with 22 deaths and 107 injuries on the Pemalang – Purbalingga road section. One of the factors causing accidents is the lack of attention to infrastructure that meets safety aspects. Even though the number of accidents caused by infrastructure is relatively small when compared to the human error (human) and vehicle (facility) factors, serious attention must still be paid. Traffic accidents caused by a lack of road infrastructure are generally caused by an inaccurate road geometric design, poor road surface conditions, lack of visibility and so on. Therefore the research aims to find accident-prone locations, the causes of accidents from the standard values of road technical requirements and accident regression models. The results of this study. Segments that are categorized as accident-prone locations are STA 32+000, 34+000, 36+000, 47+000 and 48+000. Substandard grades will be the cause of traffic accidents based on road technical requirements. The regression model that can be used to predict the number of accidents on provincial roads according to the variables examined in this study is: Y = -2.618 + 0.049 Grade – 0.019 X Slope – 0.008 H Curv – 0.417 V Curv + 0.264 road width + 0.081 condition IRI roads + 0.014 PCI Road Conditions

Human reliability of the intelligent construction site tower crane driver interface based on DEMATEL-ISM-BN.

With the arrival of Industry 4.0, intelligent construction sites have seen significant development in China. However, accidents involving digitized tower cranes equipped with smart systems continue to occur frequently. Among the main causes of these accidents is human unsafe behavior. To assess the human factors reliability of intelligent construction site tower cranes, it is necessary to shift the safety focus to the human-machine interface and identify patterns of human error behaviors among tower crane drivers through text mining techniques (TF-IDF-TruncatedSVD-ComplementNB). Based on the SHEL model, the behavioral factors influencing human factors reliability in the human-machine interface are categorized and a Performance Shaping Factors (PSF) system is constructed. Building on the foundation of constructing an indicator system for human factors error influence in the driver interface of intelligent construction site tower cranes, the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method is combined with the Interpretive Structural Modeling (ISM) to analyze the importance of various factors in causing human errors and to analyze the logical structure among these factors. Simultaneously, a Bayesian network is constructed using a multi-level hierarchical structural model, thus establishing a new evaluation method for the human-machine interface. The effectiveness of the proposed method is validated through Bayesian network causal inference based on real case studies. The results demonstrate that the evaluation process of this method aligns with the operational scenarios of tower crane drivers in intelligent construction sites. It not only allows for quantifying the likelihood of human errors but also enables the development of targeted measures for controlling unsafe behaviors among tower crane drivers in intelligent construction sites.

Information System Web-Based HSSE Performance In PT.XYZ

Information Technology systems are developing very quickly and are a challenge for all types of industries. Data management of a company is very important in this digital 4.0 era. This system aims to help computerized data and information management is expected to reduce the risk of human error factors. The method begins with analyzing needs using the discussion method, translating data into UML (Unified Modeling Language) diagrams and implementing systems using web-based applications by taking data at PT XYZ, Department of Health, Safety, Security, Environment in processing HSSE Performance data which still uses semi-conventional applications and redundancies, so that it will produce an Information System that can make it easier for Company Management to Monitor the Achievement of HSSE Department Performance Targets which are presented visually in the form of a Dashboard. The design of the information system uses a prototype method that can be added or reduced according to the development process that can be adjusted to the needs of the company. This web-based application designs an HSSE Performance Information System to support operational data management in the company. The information system to be designed is the HSSE Performance information system in the HSSE Department, providing information results that can be used by leaders and management in making decisions.

Sustainability in High Reliability Organizations Employing Digitized Automation Inspection Processes

Digitization technologies offer several advantages over manual methods of accomplishing job-related tasks. Accurately measuring, documenting, and reporting surface damages, due to volume calculation variations are vital in increased efficiency, productivity, and thus mainly, human performance. Several sensation and perception issues were identified, mainly with concerns about accuracy of visual measurements that take place during quality control inspections. This research project portrays High Reliability Organizations utilizing digitized systems and automation concepts, with emphasis in Sensation, Perception, and Human Performance. Problem areas in measuring and assessing damaged Thermal Protection System (TPS) tile surfaces are identified and documented. Analysis of performance issues, causes, and effects, of human error factors are analyzed.

PERBAIKAN KUALITAS PRODUK MENGGUNAKAN METODE QUALITY CONTROL CIRCLE (QCC) DI PT. PUDAK ORIENTAL INDONESIA

PT. Pudak Oriental Indonesia is one of the companies that emphasize the importance of product quality. The common issue faced in the quality inspection process is the presence of numerous defective products that fail quality testing. The objective of this research is to identify the types of defects that frequently occur, identify their root causes, and reduce the defect rate using the Quality Control Circle (QCC) method, employing PDCA (Plan, Do, Check, Act), and Control Charts. QCC is a method aimed at reducing defects and improving product quality. The research findings indicate that the most frequent type of defect is white body defects, with a total of 309 pieces. The root cause analysis reveals that the most influential factors are human error and material factors. The results of the quality improvement implementation initially started at 18% and have reduced to 11%. Specifically for the white body defect type, after the defect mitigation efforts, the defect rate has been reduced from the initial 309 pieces to 54 pieces.

An Analysis of Causes Related to Human Factors in Maritime Accidents

Safety is the most critical job of any Mariner. Recently, the maritime industry has embedded automated systems onboard ships to reduce workload and improve safety. This study explores several recent marine incidents generated by human errors resulting from improper use of technology and the loss of situational awareness. Accidents within three categories of vessels illustrate findings, small passenger vessels, a container ship, and military vessels, using the official accident reports and agency findings. The results indicate that three categories of errors were identified: competence-based, regulatory-based, and perception-based. By sharing this information, Governments, Educators, Mariners, Admiralty Lawyers, and vessel owners can work together to improve maritime safety. This research article proposes academic Maritime Education and Training (MET) strategies and administrative systems to recognise the deficiencies between human factor errors and digital innovation to prevent such accidents from reoccurrence.

CAMERA-BASED DETECTORS AS AN ALTERNATIVE TO DETECTING TRAINS IN A LEVEL CROSSING IMPLEMENTATION

Based on data from Indonesia Directorate General of Railways in 2017, it is mentioned that the problems at the level crossing of railroad tracks are mostly caused by human error factors themselves. The current train headway and the crossing system that is still operated manually can increase the potential for accidents. Therefore, the development of alternative camera-based detectors to support the railroad crossing automation system is needed at this time. The development of this camera-based train detector uses the basic program You Only Look Once (YOLO), where YOLOv3 has proven to be accurate enough to detect moving objects. The development results show promising results for several types of alternative trains.

Non-engineering house damage after the February 25th, 2022 West Pasaman Earthquake

The earthquake that occurred on February 25, 2022 with a magnitude of M6.2 in West Pasaman Regency, West Sumatera has resulted in many losses such as casualties and damages to infrastructure, especially residential buildings. To determine the level of damage to community houses due to the earthquake, a rapid visual assessment survey was conducted with the National Agency for Disaster Countermeasure (BNPB) and 100 Civil Engineering students. The Method used in this survey is based on the Public Work Minister Regulation, which categorizes the damaged houses into 3 categories, namely light, moderate and heavy damage. Based on the results of the assessment, the damage generally occurred on the walls and structural elements of the houses. The damages is caused by human error factors such as lack of planning, poor construction implementation, site selection and selection of quality building materials that were not in accordance with earthquake safe house building standards. One of the efforts to overcome the problem of the damage is to strengthen the house using a ferrocement layer. The level of buildings damage based on the distance from the earthquake center and the implementation of retrofitting on the damaged houses are also discussed in this paper.

A hybrid HFACS model using DEMATEL-ORESTE method with linguistic Z-number for risk analysis of human error factors in the healthcare system

The human error factor is one of the leading causes of medical errors. Among risk analysis techniques for human error factors, HFACS (Human Factor Analysis and Classification System) method has been regarded as one of the most valuable approaches due to its advantage in potential failure classification. However, the conventional HFACS method is insufficient to handle the risk analysis problem for human error factors considering the interactive relationship among these factors. Moreover, the current fuzzy HFACS frameworks cannot address quantitative risk analysis issues, including imprecision and reliability of information. Thus, this paper constructs an integrated linguistic Z-number-based HFACS framework for analyzing the risk of human error factors. This framework can capture the uncertainty and reliability of the risk evaluation information and the interactive relationships among factors. First, the linguistic Z-number-DEMATEL (Decision Making Trial and Evaluation Laboratory) method is used to generate the comprehensive risk matrix of human error factors identified by the HFACS method. Then, an extended linguistic Z-number-ORESTE method based on the score function is presented to prioritize the risk of human error factors, which can show the preference, indifference, and incomparability relationship among human error factors. Finally, a case study of a healthcare system is conducted to illustrate the reliability of the proposed method. The result of this case indicates that inadequate resources are the most severe risk. Sensitivity analysis and comparative analysis indicate the necessity of considering the effect of the semantics of language terms and the interrelationships between human error factors on risk analysis results. These results show that the proposed hybrid framework is a reliable means to analyze the risk of human error factors within the HFACS method.

Accident Prevention and Traffic Safety for Sekolah Alam Robbani Bekasi - (KidSafe)

In 2020, the number of traffic accidents from student age was 42,604 people. Meanwhile, there were 26,355 traffic accidents from student age until September this year. Based on gender, the majority of traffic accidents occurred in men. Traffic accidents contribute greatly as one of the causes of death in Indonesia. Traffic accidents have a high fatality rate. Data shows that in one year, 25, 2666 people died due to traffic accidents. Among the victims of traffic accidents are school children. About 95% of the causes of accidents are human error factors. The purpose of this community service is to provide an understanding of good traffic in early childhood. Understanding facilities for pedestrians and cycling lanes. The method provided is by providing material, pictures of traffic signs, and play displays related to traffic signs. Evaluation and results of activities by dividing students into several small groups and this is effective, students are able to explain traffic signs, and good traffic procedures, especially for users of pedestrian facilities and safe cyclist routes.

A consensus model-based risk matrix for human error factors risk analysis in medical devices by considering risk acceptability

Medical devices related event caused by potential human error factors has been one of the leading life-threatening factors. These factors may emerge in multi-hierarchy because of the multi-dimensional organizational structure in the healthcare system. The Human Factor Analysis and Classification System (HFACS), a systematic human error analysis tool, can be integrated with the risk matrix to identify human error factors and prioritize risk in medical devices. Meanwhile, integrating the consensus model into the risk matrix can yield highly recognized risk analysis results. Nevertheless, most consensus models did not consider the heterogenous risk acceptability of experts. Therefore, this paper first proposed a consensus model-based risk matrix to address the HFACS-based human error factor risk analysis problem considering the experts’ risk acceptability. In the proposed method, a novel feedback mechanism considering risk acceptability is constructed to guide experts to modify their risk evaluation information and reach a consensus, where experts' risk acceptability model is established to reflect their willingness to adjust risk evaluation information. Especially, a novel consensus measurement is constructed based on the risk rating results yielded by the risk matrix. Finally, a case of risk analysis of human error factors of ventilators is studied to validate the proposed method.