Search

In gas-fired power plants, emissions may reduce turbine blade rotation, thus decreasing power output. This study proposes a hybrid model integrating the Feed forward Neural Network (FFNN) model and Particle Swarm Optimization (PSO) algorithm to predict gas emissions from natural gas power plants. The FFNN predicts gas turbine nitrogen oxides (NOx) and carbon monoxide (CO) emissions, while the PSO optimizes FFNN weights, improving prediction accuracy. The PSO adopts a unique random number selection strategy, incorporating the K-Nearest Neighbor (KNN) algorithm to reduce prediction errors. Neighbor Component Analysis (NCA) selects parameters most correlated with CO and NOx emissions. The hybrid model is constructed, trained, and testedusing publicly available datasets, evaluating performance with statistical metrics like Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results show significant improvement in FFNN training with the PSO algorithm, boosting CO and NOx prediction accuracy by 99.18% and 82.11%, respectively. The model achieves the lowest MSE, MAE, and RMSE values for CO and NOx emissions. Overall, the hybrid model achieves high prediction accuracy, particularly with optimized PSO parameter selection using seed random generators.

The energy supply sector, encompassing vital components such as generation, transmission, and distribution, holds a pivotal role in satisfying the energy demands of modern society. Its intricate web of technologies and infrastructure ensures the reliable provision of electricity from diverse fuel sources, bolstering economic advancement and enhancing overall living standards worldwide. In the context of ongoing global energy transitions, the energy sector assumes a critical role in addressing the escalating demand for alternative energy sources and adapting resource allocation strategies to align with evolving societal energy requirements. Nonetheless, the energy supply sector confronts formidable challenges, including infrastructure degradation and grid instability. Not only that, but the demand of energy supply is also expected to rise by 50% by 2050. To counter these issues and enable predictive maintenance and grid optimization, digital twin solutions have emerged as a necessity. This is particularly significant as industry integrates renewable and non-renewable energy sources while managing risks in a dynamic energy landscape that undergoes constant transformation. This paper presents a comprehensive analysis of the myriad applications, benefits, and impediments associated with digital twin technology within the energy supply sector. Employing a methodological framework grounded in systematic reviews, detailed case studies, and extensive data analysis, this review article utilizes illustrative diagrams and visual aids to enhance clarity and comprehension. These pedagogical tools elucidate essential concepts for the deployment of digital twin technology in the energy supply industry. The analysis reveals that 4.81% (35 out of 727) of the reviewed papers explored the application of digital twins in various energy sectors. The review paper yields several significant findings, including a meticulous synthesis of existing literature, an in-depth examination of case

In gas-fired power plants, emissions may reduce turbine blade rotation, thus decreasing power output. This study proposes a hybrid model integrating the Feed forward Neural Network (FFNN) model and Particle Swarm Optimization (PSO) algorithm to predict gas emissions from natural gas power plants. The FFNN predicts gas turbine nitrogen oxides (NOx) and carbon monoxide (CO) emissions, while the PSO optimizes FFNN weights, improving prediction accuracy. The PSO adopts a unique random number selection strategy, incorporating the K-Nearest Neighbor (KNN) algorithm to reduce prediction errors. Neighbor Component Analysis (NCA) selects parameters most correlated with CO and NOx emissions. The hybrid model is constructed, trained, and testedusing publicly available datasets, evaluating performance with statistical metrics like Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results show significant improvement in FFNN training with the PSO algorithm, boosting CO and NOx prediction accuracy by 99.18% and 82.11%, respectively. The model achieves the lowest MSE, MAE, and RMSE values for CO and NOx emissions. Overall, the hybrid model achieves high prediction accuracy, particularly with optimized PSO parameter selection using seed random generators.

The energy supply sector, encompassing vital components such as generation, transmission, and distribution, holds a pivotal role in satisfying the energy demands of modern society. Its intricate web of technologies and infrastructure ensures the reliable provision of electricity from diverse fuel sources, bolstering economic advancement and enhancing overall living standards worldwide. In the context of ongoing global energy transitions, the energy sector assumes a critical role in addressing the escalating demand for alternative energy sources and adapting resource allocation strategies to align with evolving societal energy requirements. Nonetheless, the energy supply sector confronts formidable challenges, including infrastructure degradation and grid instability. Not only that, but the demand of energy supply is also expected to rise by 50% by 2050. To counter these issues and enable predictive maintenance and grid optimization, digital twin solutions have emerged as a necessity. This is particularly significant as industry integrates renewable and non-renewable energy sources while managing risks in a dynamic energy landscape that undergoes constant transformation. This paper presents a comprehensive analysis of the myriad applications, benefits, and impediments associated with digital twin technology within the energy supply sector. Employing a methodological framework grounded in systematic reviews, detailed case studies, and extensive data analysis, this review article utilizes illustrative diagrams and visual aids to enhance clarity and comprehension. These pedagogical tools elucidate essential concepts for the deployment of digital twin technology in the energy supply industry. The analysis reveals that 4.81% (35 out of 727) of the reviewed papers explored the application of digital twins in various energy sectors. The review paper yields several significant findings, including a meticulous synthesis of existing literature, an in-depth examination of case

Gas power plants are fast-establishing power plants capable of producing reliable energy in high watts volumes. One of its significant features is its dependency on natural air as raw material to run the gas turbine. Air passes through several stages that involve heating the air to increase its pressure before being used in electric power generation. Leakage in gas power stations is considered a vital indication of irregular processes of those stages. Any fault existing in the meanwhile operations can result in lousy production performance. Considering the human and economic losses of gas leakage, it has become a challenge to prevent the same. One of the essential approaches to managing gas leakage reduction is an accurate prediction. This paper proposes an automatic prevention approach relying on deep learning technology for predicting gas leakage status. Furthermore, a novel dataset was supplied by a natural gas power plant to predict CO and NOx emissions. The dataset is used to train the deep learning models using Long-short Term Memory and Feed-Forward Neural Networks. The optimum accuracy obtained is over 92% for CO and over 58% for NOx while using the LSTM model as a predictor.

Gas power plants are fast-establishing power plants capable of producing reliable energy in high watts volumes. One of its significant features is its dependency on natural air as raw material to run the gas turbine. Air passes through several stages that involve heating the air to increase its pressure before being used in electric power generation. Leakage in gas power stations is considered a vital indication of irregular processes of those stages. Any fault existing in the meanwhile operations can result in lousy production performance. Considering the human and economic losses of gas leakage, it has become a challenge to prevent the same. One of the essential approaches to managing gas leakage reduction is an accurate prediction. This paper proposes an automatic prevention approach relying on deep learning technology for predicting gas leakage status. Furthermore, a novel dataset was supplied by a natural gas power plant to predict CO and NOx emissions. The dataset is used to train the deep learning models using Long-short Term Memory and Feed-Forward Neural Networks. The optimum accuracy obtained is over 92% for CO and over 58% for NOx while using the LSTM model as a predictor.

Transformer failures have a significant cost impact on the operation of an electrical network. In many utilities, transformers have been operating for many years past their expected usable life. As power demand has surged, transformers in some areas are being loaded beyond their rated capacity to meet the demand. One of the vital components in a transformer is the on-load tap changer (OLTC), which regulates the voltage in the distribution network. This study aims to review several condition-monitoring techniques (online and offline) that can monitor the health of the OLTC and assure the safety of the transformer’s OLTC from irreparable damage by detecting the defect at an earlier stage, which is preceded by the specification of typical faults. This paper also discussed the common faults of the OLTC and the root causes of these faults. The OLTC is prone to mechanical faults due to its frequently changing mechanism in the tap operation. The OLTC are also prone to oil as well as thermal faults. As a result, it is critical to monitor OLTC conditions while they are in use. Proper management of condition monitoring (CM) for the OLTC is useful and necessary to increase availability and achieve optimised operating. Condition monitoring (CM) and diagnostics methods (DM) have been developing since the 1950s. CM and DM have been implemented to diagnose and detect an incipient fault, especially for the OLTC. Many techniques, online and offline, are being used to monitor the condition of the OLTC to prevent failure and minimize outages. These DM and CM will prolong the operational cycle and avoid a major disaster for the OLTC, which is an unfavorable scenario.

The PV systems' sources are environmentally friendly, but at the same time, they are constantly changing with time. When evaluating solar energy resources, it is necessary to consider the variability and effects of different environmental operation parameters like solar irradiances, ambient temperature, and module temperature. The study introduces a method to simulate an existing photovoltaic system using a mathematical model that permits intelligent strategies to optimise the efficiency and adjust the most effective operational parameters for the solar energy systems. A mathematical analysis for the data framework, including correlation and regression coefficients, was calculated to identify and chart the relationships between the system's most influential parameters and the generated power from the PV system. An improved mathematical model was built with the most influential parameters. The improved model was simple, accurate, and based on the loss ratio by eliminating the unknown parameters. The system's efficiency was analysed using an existing data framework-recorded hourly from 1 st January 2017 to December 2018 for a grid-connected photovoltaic system installed in the south of Oman. The results showed that the most influential parameters on the efficiency were the module's solar irradiance and surface temperature. The operating parameters such as ambient temperature, wind speed, and air humidity had a negligible effect on the generated power compared to the cell temperatures and solar radiation. The dissipation factor was used in the new output current and voltage equations to stimulate the output power of the PV model. The improved model was validated in a MATLAB Simulink and showed a more promising output with a lower RMSE of 5 %.

Transformer failures have a significant cost impact on the operation of an electrical network. In many utilities, transformers have been operating for many years past their expected usable life. As power demand has surged, transformers in some areas are being loaded beyond their rated capacity to meet the demand. One of the vital components in a transformer is the on-load tap changer (OLTC), which regulates the voltage in the distribution network. This study aims to review several condition-monitoring techniques (online and offline) that can monitor the health of the OLTC and assure the safety of the transformer’s OLTC from irreparable damage by detecting the defect at an earlier stage, which is preceded by the specification of typical faults. This paper also discussed the common faults of the OLTC and the root causes of these faults. The OLTC is prone to mechanical faults due to its frequently changing mechanism in the tap operation. The OLTC are also prone to oil as well as thermal faults. As a result, it is critical to monitor OLTC conditions while they are in use. Proper management of condition monitoring (CM) for the OLTC is useful and necessary to increase availability and achieve optimised operating. Condition monitoring (CM) and diagnostics methods (DM) have been developing since the 1950s. CM and DM have been implemented to diagnose and detect an incipient fault, especially for the OLTC. Many techniques, online and offline, are being used to monitor the condition of the OLTC to prevent failure and minimize outages. These DM and CM will prolong the operational cycle and avoid a major disaster for the OLTC, which is an unfavorable scenario.

The PV systems' sources are environmentally friendly, but at the same time, they are constantly changing with time. When evaluating solar energy resources, it is necessary to consider the variability and effects of different environmental operation parameters like solar irradiances, ambient temperature, and module temperature. The study introduces a method to simulate an existing photovoltaic system using a mathematical model that permits intelligent strategies to optimise the efficiency and adjust the most effective operational parameters for the solar energy systems. A mathematical analysis for the data framework, including correlation and regression coefficients, was calculated to identify and chart the relationships between the system's most influential parameters and the generated power from the PV system. An improved mathematical model was built with the most influential parameters. The improved model was simple, accurate, and based on the loss ratio by eliminating the unknown parameters. The system's efficiency was analysed using an existing data framework-recorded hourly from 1 st January 2017 to December 2018 for a grid-connected photovoltaic system installed in the south of Oman. The results showed that the most influential parameters on the efficiency were the module's solar irradiance and surface temperature. The operating parameters such as ambient temperature, wind speed, and air humidity had a negligible effect on the generated power compared to the cell temperatures and solar radiation. The dissipation factor was used in the new output current and voltage equations to stimulate the output power of the PV model. The improved model was validated in a MATLAB Simulink and showed a more promising output with a lower RMSE of 5 %.

Growing worldwide demand for energy leads to increasing the levels of challenge in power plants management. These challenges include but are not limited to complex equipment maintenance, power estimation under uncertainty, and energy optimisation. Therefore, efficient power plant management is required to increase the power plant’s operational efficiency. Conventional optimisation tools in power plants are not reliable as it is challenging to monitor, model and analyse individual and combined components within power systems in a plant. However, intelligent computational tools such as artificial neural networks (ANN), nature-inspired computations and meta-heuristics are becoming more reliable, offering a better understanding of the behaviour of the power systems, which eventually leads to better energy efficiency. This paper aims to provide an overview of the development and application of intelligent computational tools such as ANN in managing power plants. Also, to present several applications of intelligent computational tools in power plants operations management. The literature review technique is used to demonstrate intelligent computational tools in various power plants applications. The reviewed literature shows that ANN has the greatest potential to be the most reliable power plant management tool.

Growing worldwide demand for energy leads to increasing the levels of challenge in power plants management. These challenges include but are not limited to complex equipment maintenance, power estimation under uncertainty, and energy optimisation. Therefore, efficient power plant management is required to increase the power plant’s operational efficiency. Conventional optimisation tools in power plants are not reliable as it is challenging to monitor, model and analyse individual and combined components within power systems in a plant. However, intelligent computational tools such as artificial neural networks (ANN), nature-inspired computations and meta-heuristics are becoming more reliable, offering a better understanding of the behaviour of the power systems, which eventually leads to better energy efficiency. This paper aims to provide an overview of the development and application of intelligent computational tools such as ANN in managing power plants. Also, to present several applications of intelligent computational tools in power plants operations management. The literature review technique is used to demonstrate intelligent computational tools in various power plants applications. The reviewed literature shows that ANN has the greatest potential to be the most reliable power plant management tool.