Room Operators Research Articles

Fault Detection in Transmission Line

Abstract: This project focuses on the design and implementation of an advanced fault detection system for overhead transmission lines, utilizing key components such as the ESP 8266 microcontroller, current sensors, a GPS module, and IoT integration. The system is capable of detecting and classifying four major fault types: single line to ground (L-G), line to line (LL), double line to ground (L-L-G), and three-phase faults (L-L-LG). By placing current sensors at the transmission line's sending end, the system identifies faults and accurately determines their location through GPS coordinates .Simulations using protect us software were conducted to verify the system’s performance prior to building a hardware prototype. Upon fault detection, the system provides alerts via an LCD display and a buzzer, while real-time fault data is transmitted to an Android app and web server through the arduino IoT cloud. Testing confirmed the system’s precision in fault identification and location tracking, ensuring timely notifications for control room and remote device operators. This successful implementation highlights the system's potential for improving safety and efficiency in power transmission networks. the project lays the groundwork for further exploration into advanced fault detection and real-time monitoring solutions in electrical engineering.

Team-centered IDAC: Modeling and simulation of operating crew in complex systems - Part 2: Simulation aspects and application

Complex systems operations, such as Nuclear Power Plants (NPPs), generally require professional operating teams. Factors associated with teamwork, such as inappropriate communication and coordination, are important contributing factors to accidents and unsafe behavior. The impact of crew interactions on team effectiveness and, consequently, on the entire system, has yet to be fully and quantitatively explored in high-risk environments such as NPPs. Since a team is an interactive social system, team-specific issues must be studied and evaluated from a “team perspective”—based on team dynamics and processes. This paper is a part of a two-papers series that presents a simulation-based Team Model for NPP control room operations. Part 1 describes the theoretical fundaments of the model and details its elements. The current paper, Part 2, describes the simulation aspects and a full application of the method to an NPP four-steam generator feedwater system pipe break. It presents how to set up the simulation elements, such as hardware and humans within a team, using MATLAB Simulink. The method is demonstrated through a case study of an NPP four-steam generator feed water system pipe break. The results are discussed and assessed against theoretical and experimental findings.

Rooms versus F&B: How changes in operations contribute to hotel productivity

This study investigates how different operational responses impact hotel productivity change, specifically investigating the importance of F&B operations in comparison to room operations and applying the case of the Taiwanese hotel industry, conducting 93 international tourist hotels from April 2012 to March 2021. Using regression discontinuity design analysis, first, the study finds a significant causal impact of COVID-19 travel restrictions on hotel operations. Second, using the control function methods, findings show that F&B operation is a more efficient strategy compared to rooms to recover hotel productivity from crises. This research provides insights into how hotels can reallocate their operational resources in response to crises and offers an alternative measure of productivity for the hotel industry.

Team-centered IDAC: Modeling and simulation of operating crew in complex systems – Part 1: Team model and fundamentals

Operation of highly complex systems such as Nuclear Power Plants (NPPs) generally require highly trained professional operating teams. Factors associated with teamwork, such as ineffective communication and coordination, can be important contributing factors to accidents and unsafe behavior. The impact of crew interactions on team effectiveness and, consequently, on the entire system, has not been fully and quantitatively explored in high-risk environments such as NPPs. Since a team is an interactive social system, team-specific issues must be studied and evaluated from a “team perspective”—based on team dynamics and processes. This paper is part of a two-papers series that presents a simulation-based Team Model for NPP control room operations. The current paper, Part 1, describes the theoretical fundaments of the model and details its elements. The accompanying paper describes the simulation aspects, and a full application of the method to a pipe break accident in a four- four-loop steam generator feedwater system. The proposed model is based on the IDAC (Information, Decision, and Action in Crew context) cognitive model framework. The resulting model, Team-centered IDAC (Tc-IDAC), examines the team activities “Collaborative information collection,” “Shared decision making,” and “Distributed action execution” through specific modules for Team Error Management. These modules include error detection, error indication and error correction, and team performance shaping factors.

Design challenges and response plans for intelligent decision support systems for Korean nuclear power plants under normal and abnormal conditions

In nuclear power plants (NPPs), an intelligent decision support system (IDSS) aids the decision-making process of main control room operators. It achieves this by monitoring and diagnosing conditions, predicting progress, and providing preventive advice during both normal and abnormal operations. Despite ongoing research in Korea, few IDSS for NPPs have been effectively applied and verified. Furthermore, established designs and validation guidelines for IDSSs for Korean NPPs remain lacking. To address this gap, this study systematically identifies problems and corresponding countermeasures for applying artificial intelligence-based design and validation technologies, while complying with licensing regulatory standards. The aim is to develop a practical and effective IDSS. This study identifies design challenges in the practical application of fundamental IDSS technology, outlining necessary design and validation technologies. Additionally, it suggests technology-specific response plans for the identified design challenges.

Factors Affecting Control Room Operator Situation Awareness and ITS Fuzzy Logic Model

Factors Affecting Control Room Operator Situation Awareness and ITS Fuzzy Logic Model

The Correlation Between Lighting Intensity, Eye Fatigue, Occupational Stress, and Sleep Quality in the Control Room Operators of Abadan Refinery

Background: The control room is a critical work environment where optimal performance is essential to minimize errors. Lighting is one of the key environmental factors influencing the performance of control room operators. Inadequate sleep quality and job stress also significantly impact job performance. Poor sleep quality, eye fatigue, inappropriate lighting, and occupational stress can lead to errors and decreased accuracy in work. Objectives: The present study aims to determine the correlation between lighting intensity, eye fatigue, occupational stress, and sleep quality among control room operators at the Abadan Refinery. The study was conducted in 2022. Methods: This cross-sectional descriptive-analytical study was conducted on 190 control room operators at the Abadan Refinery in 2022. A lux meter device was used to evaluate the intensity of lighting. Standard Pittsburgh sleep quality, eye fatigue, and Occupational Stress questionnaires were also administered. The results were analyzed using SPSS software. Results: The average light intensity of the work surface was 347.95 ± 147.34 lux. The mean and standard deviation of job stress score and sleep quality were 155.42 ± 9.18 and 9.38 ± 1.62, respectively. The average eye fatigue score was 5.09 ± 0.821 in people without glasses and 4.47 ± 0.828 in people with glasses. A significant correlation was found between brightness intensity and visual fatigue (ρ = 0.201, P = 0.029). The correlation between eye fatigue and sleep quality score was also significant (ρ = 0.225, P = 0.002). However, no significant correlation was observed between lighting intensity and sleep quality (ρ = - 0.005, P = 0.946). The correlation between the overall score of occupational stress and sleep quality was statistically significant (r = - 0.148, P = 0.042). Conclusions: The results showed a significant correlation between lighting intensity and the factors of sleep quality and eye fatigue. Additionally, there was a significant correlation between eye fatigue and sleep quality, as well as between occupational stress and sleep quality. Therefore, it is suggested that planning to minimize job stress, and improve lighting and sleep quality for gas refinery control room personnel should be designed and implemented by the authorities.

Exploring the Influence of Human System Interfaces: Introducing Support Tools and an Experimental Study

Situational awareness and decision support tools such as procedures and alarm systems are vital for effective interaction among control room operators, especially in safety-critical situations. In safety-critical environments such as process plants, there remains a gap in evaluating specific tools during actual operations, or ”work-as-done.” Additionally, the underlying factors that might impact operators’ cognitive states and performance concerning safety have not been thoroughly explored. The need for such an evaluation is further bolstered by current interaction configurations where operators are more passive than active, thus reducing their cognitive performance. Therefore, this experimental study addresses the highlighted evaluation gap by introducing and comparing three human system interfaces/decision support tools in four human-in-the-loop configurations. The supports include two alarm design formats (prioritized vs. non-prioritized) and three procedure representation formats (paper, screen-based digitized, and an AI-based support system built with an integrated Bayesian network and reinforcement learning model). Ninety-two people (n = 92) participated voluntarily in the test. They were divided equally into four groups. Each group tested three safety-related events in a simulated formaldehyde production facility. Individuals belonging to the group with prioritized alarms and utilized paper procedures rated procedural support slightly higher on average than others in different groups. Unlike the other groups, their assessment of alarm prioritization support remained consistent across all scenarios. Further analysis of the impact of the setup on cognitive states and actual performance will be performed.

Hybrid Optimal Power System Recovery and Load Pick-Up With DGAllocation In Electrical Power System

The increasing demand for electricity, the expansion of complex power networks, and the operation of power systems near their capacity have heightened the risk of power outages. Consequently, control room operators must develop comprehensive restoration plans to minimize recovery time. Key steps in power system restoration include starting non-black-start units with black-start units and initiating load pick-up. This process requires identifying the shortest route between nodes to expedite repairs. This research presents an expert plan employing the Modified Cuckoo Search algorithm (MCSA) to determine optimal pathways. Additionally, it explores the optimal allocation of distributed generators (DG) to enhance the system's voltage profile and reduce power losses using particle swarm optimization (PSO). The results demonstrate that DG significantly reduces losses during recovery. The study prioritizes the restoration of DGs with strong black start capability, considering network and DG constraints. The effectiveness of the proposed restoration approach is validated through MATLAB simulations on theIEEE 39-bus system.

An investigation of the effect of workload on ship engine room operators using fNIRS

This is an investigation into the Performance Shaping Factors (PSFs) associated with ship engine room operators. This study looks at the effect of workload. There is a large portion of human error associated with marine incidents. Human error may be considered as a result of additional supplementary tasks on top of an accustomed workload. The aim of this study is to evaluate the effect of workload on human performance. To achieve this, a TRANSAS simulator series 5000 was used to replicate a real scenario with the addition of workload as a PSF. Each participant engaged in a fault detection and correction task. 20 participants were used for the workload study; all 20 were trained for 3 h to use the engine room software interface. The participants then completed a 30-min ballasting task. During this interaction, 50% of the participants underwent a simulated scenario where the workload was increased. The other 50% were given a standard task. Functional near-infrared spectroscopy (fNIRS) was used to measure the participant's activation levels, more specifically from the dorsolateral prefrontal cortex (DLPFC) region of the cerebrum. The results showed an increase in activation of the DLPFC during each phase of the task, this trend was magnified by the addition of increased workload. The results are discussed with respect to human performance during varying workload. From the results of this study, a human classification performance model was developed. This model can be used by the maritime industry to better evaluate and understand human error causation.

Impact of Updating Surgical Instrumentation Preference Cards on Operating Room Operations

Hospital systems across the United States have implemented quality improvement initiatives designed to mitigate unnecessary waste and decrease healthcare costs that are frequently passed on to patients. One key source of waste is excess sterile instrumentation in surgical operating rooms. This quality improvement project identified waste by auditing and updating surgical instrumentation preference cards (SIPCs) for the three most common procedures at a multi-center academic health system. Unnecessary items were recorded and savings calculated using 2022 supplier price data. Forty-nine procedures were audited, resulting in changes to 111 unique SIPCs. Although this process produced significant savings for the health system, it was limited to fewer than 10% of the total cases performed. Total savings were observed at $337,007 with savings of $56,254 for open instrumentation. A manual audit of all SIPCs across the institution and regular updates has the potential to decrease instrumentation waste and annual expenditures by approximately $4 million.

Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room.

Artificial intelligence (AI) and large language models (LLMs) can play a critical role in emergency room operations by augmenting decision-making about patient admission. However, there are no studies for LLMs using real-world data and scenarios, in comparison to and being informed by traditional supervised machine learning (ML) models. We evaluated the performance of GPT-4 for predicting patient admissions from emergency department (ED) visits. We compared performance to traditional ML models both naively and when informed by few-shot examples and/or numerical probabilities. We conducted a retrospective study using electronic health records across 7 NYC hospitals. We trained Bio-Clinical-BERT and XGBoost (XGB) models on unstructured and structured data, respectively, and created an ensemble model reflecting ML performance. We then assessed GPT-4 capabilities in many scenarios: through Zero-shot, Few-shot with and without retrieval-augmented generation (RAG), and with and without ML numerical probabilities. The Ensemble ML model achieved an area under the receiver operating characteristic curve (AUC) of 0.88, an area under the precision-recall curve (AUPRC) of 0.72 and an accuracy of 82.9%. The naïve GPT-4's performance (0.79 AUC, 0.48 AUPRC, and 77.5% accuracy) showed substantial improvement when given limited, relevant data to learn from (ie, RAG) and underlying ML probabilities (0.87 AUC, 0.71 AUPRC, and 83.1% accuracy). Interestingly, RAG alone boosted performance to near peak levels (0.82 AUC, 0.56 AUPRC, and 81.3% accuracy). The naïve LLM had limited performance but showed significant improvement in predicting ED admissions when supplemented with real-world examples to learn from, particularly through RAG, and/or numerical probabilities from traditional ML models. Its peak performance, although slightly lower than the pure ML model, is noteworthy given its potential for providing reasoning behind predictions. Further refinement of LLMs with real-world data is necessary for successful integration as decision-support tools in care settings.

Identification of propagation path and root cause of faults based on generative adversarial networks in industrial systems

Fault diagnosis and detection (FDD) improves product quality, process safety, and profitability in modern industrial plants. Faults can propagate between different parts of plants due to connections between devices and control loops. As a result, control room operators may receive multiple alarms that distract their attention from addressing the main causes of abnormal situations. Therefore, investigating causal relationships between process variables is essential in determining the root cause of faults. This study proposes a new systematic approach for causality analysis to identify the propagation path and root cause of faults in industrial plants. The research's innovations are categorized into two main parts. Initially, the study utilizes machine learning algorithms to identify causal relationships using probabilistic concepts. Additionally, it introduces a novel architecture by merging the generative adversarial network (GAN) with the variational auto-encoder (VAE). The process variables are mapped to a latent space, where an adversarial generative network will investigate the causal relationship between variables. Finally, the Tennessee Eastman Process simulation and gas turbine industrial data are used to evaluate the proposed algorithm.

Perancangan Monitoring Coal Handling System PLTU Kaltim Teluk Berbasis Internet of Things

Abstract— Balikpapan Bay PLTU is a large capacity power plant located in the city of Balikpapan, which is located in East Kalimantan. This PLTU with a capacity of 2X110 MW meets the electricity needs of the Barito Mahakam network, which consists of the East Kalimantan, North Kalimantan, Central Kalimantan and South Kalimantan regions. The main fuel for electricity generation is low grade coal (LRC) or low calorie coal. High Speed Diesel (HSD) oil is used as initial fuel. DCS (Distributed Control System) is used for wood management at PLTU Kaltim Teluk. DCS helps operations by monitoring and controlling the main and supporting components, however, management, supervisors and other staff have difficulty knowing the operating conditions of the generating unit remotely because the monitoring system can only be accessed by the control room operator at the CCR. The aim of this research is to design an Internet of Things-based coal handling system control system for PLTU Kaltim Teluk. This real time based digital monitoring system can collect and display data from every sensor in the field. The research method is a literature study method and a field method to apply the design results and collect monitoring data at the two Balikpapan Bay PLTUs. The results show that testing, which includes integration testing with MySQL, functional testing, and URL and Endpoint testing, was carried out successfully. As expected, all the main features and functions of the PLTU monitoring system are running well. This system has averagepercentage error 0.1%. So this study has an accuracy rate of 99.9%. This system has the ability to make it easier for managers to monitor the system.

Predicting the duration of motorway incidents using machine learning

AbstractMotorway incidents are frequent & varied in nature. Incident management on motorways is critical for both driver safety & road network operation. The expected duration of an incident is a key parameter in the decision-making process for control room operators, however, the actual duration for which an incident will impact the network is never known with true certainty. This paper presents a study which compares the ability of different machine learning algorithms to estimate the duration of motorway incidents on Ireland’s M50 motorway, using an extensive historical incident database. Results show that the support vector machine has the best performance in most cases, but a different method may need to be used to improve accuracy in some situations. Results highlight the main challenges in accurately forecasting incident durations in real time & recommendations are made for improving prediction accuracy through systematic recording of various additional incident details.

Environmental Risk Assessment of a Hydrocracker Unit in Abadan Oil Refinery Using the EFMEA Analysis

Background: The aim of risk assessment is to use a rational method to analyze risks and to identify the possible hazards and outcomes for people, equipment, materials, and the environment. Methods: The criteria and indices for assessing the environmental, health, and safety risks of the hydrocracker unit were determined by a Delphi questionnaire in this study. Then, an Environmental Failure Mode and Effects Analysis was applied to evaluate, score, and rank the risks based on their probability of occurrence, severity, probability of detection, extent of pollution, and potential of recycling. Results: According to the results of the Delphi process, 19 out of the 22 items were identified as the main criteria in the environmental, health, and safety risk evaluation of the hydrocracker unit at the Abadan Oil Refinery. However, the results indicated that 67% of the risks associated with the life cycle operation were low while 33% of them were high in terms of intensity. In contrast, 75% of the risks associated with control room operators were low and 25% were high in terms of intensity. On the other hand, 64, 7, and 29% of the risks associated with the activities of site employees were low, moderate, and high in terms of intensity, respectively, while the corresponding figures were 14, 29, and 57% in the case of risks associated with repairs. Conclusion: Based on the results of techniques of environmental failure modes and effects analysis (EFMEA) and Delphi, appropriate methods can be used to identify and reduce risks in similar industries.

Enhancing Control Room Operator Decision Making

In the dynamic and complex environment of industrial control rooms, operators are often inundated with numerous tasks and alerts, leading to a state known as task overload. This condition can result in decision fatigue and increased reliance on cognitive biases, which may compromise the decision-making process. To mitigate these risks, the implementation of decision support systems (DSSs) is essential. These systems are designed to aid operators in making swift, well-informed decisions, especially when their judgment may be faltering. Our research presents an artificial intelligence (AI)-based framework utilizing dynamic influence diagrams and reinforcement learning to develop a powerful decision support system. The foundation of this AI framework is the creation of a robust, interpretable, and effective DSS that aids control room operators during critical process disturbances. By incorporating expert knowledge, the dynamic influence diagram provides a comprehensive model that captures the uncertainties inherent in complex industrial processes. It excels in anomaly detection and recommending optimal actions. Furthermore, this model is improved through a strategic collaboration with reinforcement learning, which refines the recommendations to be more context-specific and accurate. The primary goal of this AI framework is to equip operators with a live, reliable DSS that significantly enhances their response during process upsets. This paper describes the development of the AI framework and its implementation in a simulated control room environment. Our results show that the DSS can improve operator performance and reduce cognitive workload. However, it also uncovers a trade-off with situation awareness, which may decrease as operators become overly dependent on the system’s guidance. Our study highlights the necessity of balancing the advantages of decision support with the need to maintain operator engagement and understanding during process operations.

The potential impact of emotionally loaded stimuli on over/under-estimating neutral situations among power plant control-room operators.

Human emotions vary on a contextual basis. The significance of emotions becomes even more salient in Control Room Operators (CROs) in power plants. This study investigated the effects of emotionally loaded pictures on over/underestimating neutral situations. Twenty CROs voluntarily enrolled in the present study. Twenty-one blocks were considered, including ten emotionally loaded and 11 neutral blocks. The stimuli were alternatively submitted to subjects in random order. Each block comprised 13 images from the International Affective Picture System (IAPS), which were shown for 5 seconds. Subjects were required to complete the Self-Assessment Manikin (SAM) after exposure to the first and the last neutral blocks, which were identical. Our analyses showed significant differences between IAPS arousal and SAM1 and SAM2 arousal ratings (p SAM1&IAPS = 0.00, p SAM2&IAPS = 0.02). There was no significant relationship between the first and the second arousals, and emotionally loaded images corresponded to no significant difference in terms of valence. The findings suggested that the participants overestimated neutral situations compared with IAPS only in arousal level. Furthermore, CROs can still retain their ability to assess neutral situations in the case of viewing emotional stimuli, especially in valence level, at least half an hour after the first rating. A study design with pure negative/positive and high arousal levels may still provide even more significant results.

Multi-class classification of control room operators’ cognitive workload using the fusion of eye-tracking and electroencephalography

Chemical process industries are hazard intensive. Most industrial accidents occur today due to human error. For safe and efficient operation, it is therefore critical to ensure optimal operator performance. With the advent of Industry 4.0 and concomitant digitalization, the role of operators has become cognitively challenging. Therefore, it is imperative to assess the cognitive performance of operators. One of the major constructs to understand cognitive performance is the cognitive workload. An increase in cognitive workload often leads to degradation in performance. Traditional assessment techniques fail to capture cognitive aspects of performance. Recently, researchers in various domains such as aviation, driving, marine, and nuclear power have started to utilize physiological measures to gauge the cognitive workload of their operators. In our previous works, we have used electroencephalography (EEG) and eye-tracking separately to assess the cognitive workload of operators in the process industries. In contrast, in this paper, we explore the benefits of their fusion in classifying process industry control room operators’ workload into low, medium, and high classes while they tackle abnormal situations. The methodology employs the fusion of metrics derived from pupil, gaze, and EEG data to train a decision tree-based model for workload classification. Our results reveal that fusion leads to an increase in classification accuracy of upto 22 %. The work has the potential to identify the expertise level of operators and hence, can be critical in ensuring their optimal performance.

Effect of coronavirus disease 2019 lockdown on admission of surgical emergencies at Ain Shams University Hospital

Background: Globally speaking, the COVID-19 pandemic has had a significant impact on healthcare services. Several publications about the restructuring of surgical activity during the COVID-19 pandemic have been written, but few of them have specifically addressed the effects of this restructuring on the emergency and trauma surgery. The goal of this study was to evaluate the impact of the COVID-19 pandemic and Egypt’s national lockdown on admissions for acute surgical conditions at Ain Shams University Hospitals and compare those numbers to any existing international literature. Methods: The data were collected from the records of the surgical emergency department at Ain Shams University Hospital (El-Demerdash) for the period of national lockdown in the months of March, April, May and June 2020 and compared this with the data of the year 2019. Findings and Results: Total patients’ visits in the period from first of March till the end of June 2020 was 10294 patients visits with average daily visits 84, while it was 15672 with average daily visits 128 in the same period of 2019. There was a slight increase in the percent of admission from total visits from 30% in the period of March to June 2019 to 32% in the lockdown period in 2020, which means slight decrease of the unnecessary patients visits. The percent of emergency room (ER) operations of total admissions increased in the lockdown period which refer to the decrease in the number of conservatively managed patients of admitted patients. Conclusion: The COVID-19 pandemic had its impact on the surgical emergency departments all over the world. It reduced the number of avoidable non-emergency ER visits, but in same time, it hasn’t stopped patients with high-risk surgical emergencies from getting urgent care. Also, during the pandemic surgeons delt with more severe conditions and complications as a result of the pandemic.