Plant Operator Performance Evaluation System

University — industry cooperative study on plant operations

The prospect of a fully-automated technology has been the subject of considerable discussion in the literature of the sociology of work. Many writers have viewed automation as reversing the trends towards extreme fragmentation of tasks and authoritarian management characteristic of mass production technology. Workers will no longer perform simple tasks; they will become responsible for the operation of entire plants. The earlier work of Blauner (1964), who saw automation bringing a new age of ‘responsible workers’ in which operators of plants would enjoy ‘consultation’ with management has influenced this view. Duncan Gallie, for example, believes that automation has ‘blunted the clear-cut distinction between manual and non-manual labour’ and he emphasises ‘the significance of the operator’s work performance for the quantity, quality and cost of the product’ (1978, p. 214). The notion that automation is only effective if workers are given responsibility is the underlying premise of a study by Larry Hirschhorn. ‘In cybernetic settings workers must control the controls. To do so they cannot merely become competent at a fixed and predictable set of tasks … Instead, they must be able to survey and understand the entire production process’ (1986, p. 2). The complexity and flexibility of automated production, as well as the need to attend to the efficiency, reliability and safety of production, requires workers who are knowledgeable, exercise judgement and maintain a consultative relationship with management.

The control and monitoring of power generation plants is being complicated day by day, with the increase size and capacity of equipments involved in power generation process. This calls for the presence of experienced and well trained operators for decision making and management of various plant related activities. Scarcity of well trained and experienced plant operators is one of the major problems faced by modern power industry. Application of artificial intelligence techniques, especially expert systems whose main characteristics is to simulate expert plant operator’s actions is one of the actively researched areas in the field of plant automation. This paper presents an overview of various expert system applications in power generation plants. It points out technological advancement of expert system technology and its integration with various types of modern techniques such as fuzzy, neural network, machine vision and data acquisition systems. Expert system can significantly reduce the work load on plant operators and experts, and act as an expert for plant fault diagnosis and maintenance. Various other applications include data processing, alarm reduction, schedule optimisation, operator training and evaluation. The review point out that integration of modern techniques such as neural network, fuzzy, machine vision, data base, simulators etc. with conventional rule based methodologies have added greater dimensions to problem solving capabilities of an expert system. DOI: http://dx.doi.org/10.11591/ijece.v4i1.5025

Industrial robots of different kinematic structures and functionality are widely used nowadays in different areas of industry and most of them function autonomously with a pre-programmed set of actions or typical trajectories. Some special purpose mobile and stationary robots are human-controlled and in most cases require qualified operator skills. This article describes general approaches and practical aspects of the operator training and qualification system for arm-based special purpose manipulators. The set of training system functions include: general manipulator control (basic motion) and grasping actions, manipulator operations in restricted working areas, operator actions using virtual reality helms and multi-monitor visualization, etc. The hardware and software architecture of training system should allow for an effective training process and teamwork of trainee and instructor to reach good results. The paper proposes a ROS-based software part of the training system with a description of inter-process communication messages, data formats, integration with a database and the following analysis of trainee action.

Real-time Simulation (RTS) has long been used in the nuclear power industry for operator training and engineering purposes. And, online simulation (OLS) is based on RTS and with connection to the plant information system to acquire the measurement data in real time for calibrating the simulation models and following plant operation, for the purpose of analyzing plant events and providing indicative signs of malfunctioning. OLS has been applied in certain industries to improve safety and efficiency. However, it is new to the nuclear power industry. A research project was initiated to implement OLS to assist operators in certain critical nuclear power plant (NPP) operations to avoid faulty conditions. OLS models were developed to simulate the reactor core physics and reactor/steam generator thermal hydraulics in real time, with boundary conditions acquired from plant information system, synchronized in real time. The OLS models then were running in parallel with recorded plant events to validate the models, and the results are presented.

Using LGM analysis to identify hidden contributors to risk in the operation of a nuclear power plant

This research is based on a systematic review of machine learning (ML) approaches for the cognitive load (CL) assessment of applications for unmanned aerial system (UAS) operator training. The review synthesises evidence on how ML techniques have been applied to assess CL using diverse data sources, including physiological signals (e.g., EEG, HRV), behavioural measures (e.g., eye-tracking), and performance indicators. It highlights the effectiveness of models such as Support Vector Machines (SVMs), Random Forests (RFs), and advanced deep learning (DL) architectures such as Long Short-Term Memory (LSTM), as well as how the use of different methods affects the performance of ML models, with studies reporting accuracies of up to 98%. The findings also indicate that, compared with traditional UAS training approaches, ML approaches can enhance training by providing adaptive assessment, with methodological factors such as model selection, data preprocessing, and validation being central to ML assessment performance. These findings highlight the value of accurate CL assessment as a foundation for adaptive training systems, supporting enhanced UAS operator performance and operational safety. By consolidating the methodological insights and identifying research gaps, this review provides valuable background information for advancing ML-based CL assessment and its integration into adaptive UAS operator training systems to enhance UAS operator training.

Two factors that are critical aspects of complex system performance are system design and operator training. The contribution of each of these factors becomes paramount as increases in system complexity demand more sophisticated operator timesharing skills to monitor and control system operations safely and efficiently. In order to increase human operator skill levels, improvements in system design must be achieved to make aspects of monitoring and controlling tasks more commensurate with human abilities. Secondly, more effective and efficient training programs must be developed to allow human operators to acquire and maintain appropriate skill levels. Before these improvements can be accomplished, however, a greater understanding of the capabilities and limitations of the human information processing system must be obtained. In a typical modern system (e.g., aircraft cockpit, centralized control room of a power plant or battle management system) the human may perform many tasks concurrently, including visual search, memory search, retention and recall, comprehension, reasoning, judgement and decision making, and executing fine motor movements. Although some combinations of these kinds of tasks may be compatible and non-interfering, other task combinations may interfere and compete for the human's limited information processing capacity, creating overload conditions. The consequence of the human operator's low threshold for overload leads to increased probability of error, with subsequent deteriorations in system performance. There are two theoretical approaches to human attention and information processing that have implications for system design and operator training issues in the context of timesharing and high workload situations. Multiple resource theory and automatic/controlled processing theory have each stimulated much empirical work that provided useful data on human timesharing abilities. Such data have provided the basis for predicting task combinations and training requirements that allow high levels of performance under timesharing and high workload situations. The purpose of this symposium is to describe recent empirical developments that may further our understanding of human information processing capabilities and limitations, particularly under timesharing and high workload conditions. The set of papers includes theoretical and applied treatments of multiple resource and automaticity theories. The issues discussed include the advantages and disadvantages of spreading information input over different sensory modalities (e.g., visual and auditory), development of training methods to acquire sophisticated high level cognitive skills quickly and efficiently, measurement of information processing capacity required by specific task combinations, and a delineation of the characteristics and limitations of working memory.

Three-dimensional color TV

Parametric investigation of a renewable alternative for utilities adopting the co-firing lignite/biomass concept

Despite the high degree of automation in industrial control systems, human operators in industrial plants play a critical role in ensuring uptime, production quality, and safety. Plant operators do so by not only monitoring the process but also intervening when the process runs into unusual or exception situations. In this paper, we present to ensure smooth plant operation by automatically identifying and investigating potential upcoming issues as well as providing recommendations to plant operators on how to address them with confidence. This is achieved by applying Artificial Intelligence (AI) techniques including deep learning, process mining, and graph search, on historical industrial process data such as alarm and event data, audit trails, engineering documents, and safety procedures. Our solution has been validated on data from the Draugen oil field operated by the Norwegian oil and gas company, OKEA.

Human characteristics of plant operation and man-machine interface

Reducing Refrigeration Costs in the Dairy Plant

In recent decades, the aging of nuclear power plants, the upgrading of safety systems and the concern for life extension of licensed plants close to completing 40 years of operation have been considered by regulatory agencies. The extension of operating licenses for power reactors over 40 years has been a viable option for operators of nuclear power plants to ensure the adequacy of future capacity of power generation, in terms of economic benefits, compared with the construction of new power reactors. Routine reviews of nuclear power plant operation (including modifications to hardware and procedures, significant events, operating experience, plant management and personnel competence) and special reviews following major events of safety significance are the primary means of safety verifications. Rereviews include an assessment of plant design and operation against current safety standards and practices, and they aim at ensuring a high level of safety throughout the plant's operating lifetime. They are complementary to the routine and special safety reviews and do not replace them (IAEA, 2009). In 1991, the US Nuclear Regulatory Commission (NRC) issued rules and associated documentation describing how the licensee must demonstrate that the unit can continue operating for 20 years following the expiration of the 40-year license. These rules were established in 10CFR51 (NRC, 2007a), environmental protection requirements, and 10CFR54 (NRC, 2010a), technical requirements. In 1994, the International Atomic Energy Agency (IAEA) issued recommendations, guidance and associated documentation describing how the licensee must demonstrate that the unit can continue operating through a systematic safety reassessment, named periodic safety review (PSR) (IAEA, 1994(IAEA, , 2003)). The safety guide has the purpose of providing recommendations and guidance on the conduct of a PSR each 10 years for an existing nuclear power plant, and it is directed at plant operating organizations and regulators. In addition, some member states have initiated this reassessment to evaluate the cumulative effects of plant aging and plant modifications, operating experience, technical developments and siting aspects.

The situated approach to situation awareness (SA) claims that system operators often offload information instead of constructing detailed, stable and internal representations of dynamic situations. Offloading, which can be more or less deliberate, is the attenuation of internal processes in favor of augmenting external ones. Operators do this to minimise costly internal processing and storage. This paper uses empirical evidence and phenomenological analysis to argue that situated SA presupposes a motor intentional core. This core refers to embodied skills whose function is to present states of the system as being a certain way. They include, for example, the skillful eye scan patterns of experts and various epistemic actions that involve manipulating objects in the physical world to make information available to other cognitive processes. Through these motor intentional skills, offloaded information can be accessed on an as-needed basis. We discuss metrics for assessing the motor intentional core, as well as implications for interface design and the training of system operators, arguing that many motor intentional skills can be taught directly.