Energy and AI最新文献

Anomaly detection in wind turbines typically involves using normal behaviour models to detect faults early. Normal behaviour models are often implemented through the use of neural networks, of which autoencoders are particularly popular in this field. However, training autoencoder models for each turbine is time-consuming and resource intensive. Thus, transfer learning becomes essential for wind turbines with limited data or applications with limited computational resources. This study examines how cross-turbine transfer learning can be applied to autoencoder-based anomaly detection. Here, autoencoders are combined with constant thresholds for the reconstruction error to determine if input data contains an anomaly. The models are initially trained on one year’s worth of data from one or more source wind turbines. They are then fine-tuned using small amounts of data from the target wind turbine. Three methods for fine-tuning are investigated: adjusting the entire autoencoder, only the decoder, or only the threshold of the model. The performance of the transfer learning models is compared to baseline models that were trained on one year’s worth of data from the target wind turbine. The results of the tests conducted in this study indicate that models trained on data of multiple wind turbines do not improve the anomaly detection capability compared to models trained on data of one source wind turbine. In addition, modifying the model’s threshold can lead to comparable or even superior performance compared to the baseline, whereas fine-tuning the decoder or autoencoder further enhances the models’ performance.

This research explores the integration of large language models (LLMs) into scientific data assimilation, focusing on combustion science as a case study. Leveraging foundational models integrated with Retrieval-Augmented Generation (RAG) framework, the study introduces an approach to process diverse combustion research data, spanning experimental studies, simulations, and literature. The multifaceted nature of combustion research emphasizes the critical role of knowledge processing in navigating and extracting valuable information from a vast and diverse pool of sources. The developed approach minimizes computational and economic expenses while optimizing data privacy and accuracy. It incorporates prompt engineering and offline open-source LLMs, offering user autonomy in selecting base models. The study provides a thorough examination of text segmentation strategies, conducts comparative studies between LLMs, and explores various optimized prompts to demonstrate the effectiveness of the framework. By incorporating an external vector database, the framework outperforms a conventional LLM in generating accurate responses and constructing robust arguments. Additionally, the study delves into the investigation of optimized prompt templates for the purpose of efficient extraction of scientific literature. Furthermore, we present a targeted scaling study to quantify the algorithmic performance of the framework as the number of prompt tokens increases. The research addresses concerns related to hallucinations and false research articles by introducing a custom workflow developed with a detection algorithm to filter out inaccuracies. Despite identified areas for improvement, the framework consistently delivers accurate domain-specific responses with minimal human oversight. The prompt-agnostic approach introduced holds promise for future improvements. The study underscores the significance of integrating LLMs and knowledge processing techniques in scientific research, providing a foundation for advancements in data assimilation and utilization.

Technologies for utilizing waste heat for power generation have attracted significant attention in recent years due to their potential to enhance energy efficiency and reduce greenhouse gas emissions. This research focuses on the comparative and optimization analysis of three supercritical carbon dioxide (sCO₂) Rankine cycles (simple, cascade, and split) for gas turbine waste heat recuperation. The study begins with parametric analysis, investigating the significant effects of key variables, including turbine inlet temperature, condenser inlet temperature, and pinch point temperature, on the thermal performance of advanced sCO₂ power cycles. To identify the most efficient cycle configuration, a multi-objective optimization approach is employed. This approach combines a Genetic Algorithm with machine learning regression models (Random Forest, XGBoost, Artificial Neural Network, Ridge Regression, and K-Nearest Neighbors) to predict cycle performance using a dataset extracted from cycle simulations. The decision-making process for determining the optimal cycle configuration is facilitated by the TOPSIS (technique for order of preference by similarity to the ideal solution) method. The study's major findings reveal that the split cycle outperforms the simple and cascade configurations in terms of power generation across various operating conditions. The optimized split cycle not only demonstrates superior power output but also exhibits enhanced net power output, heat recovery, system and exergy efficiency of 7.99 MW, 76.17 %, 26.86 % and 57.96 %, respectively, making it a promising choice for waste heat recovery applications. This research has the potential to contribute to the advancement and widespread adoption of waste heat recovery in energy technologies boosting system efficiency and economic feasibility. It provides a new perspective for future research, contributing to the improvement of energy generation infrastructure.

The design of micro-finned tube heat exchangers is a complex task due to intricate geometry, heat transfer goals, material selection, and manufacturing challenges. Nowadays, mathematical models provide valuable insights, aid in optimization, and allow us to explore various design parameters efficiently. However, existing empirical models often fall short in facilitating an optimal design because of their limited accuracy, sensitivity to assumption, and context dependency. In this scenario, the use of Machine and Deep Learning (ML and DL) methods can enhance accuracy, manage nonlinearity, adjust to varying conditions, decrease dependence on assumptions, automatically extract pertinent features, and provide scalability. Indeed, ML and DL techniques can derive valuable insights from datasets, contributing to a comprehensive understanding. By means of multiple ML and DL methods, this paper addresses the challenge of estimating key parameters in micro-finned tube heat exchangers such as the heat transfer coefficient (HTC) and frictional pressure drop (FPD). The methods have been trained and tested using an experimental dataset consisting of over a thousand data points associated with flow condensation, involving various tube geometries. In this context, the Artificial Neural Network (ANN) demonstrates superior performance in accurately estimating parameters with MAEs in the range below 4.5% for both HTC and FPD. Finally, recognizing the importance of comprehending the internal mechanisms of the black-box ANN model, the paper explores its interpretability aspects.

Forecasting electricity demand is an essential part of the smart grid to ensure a stable and reliable power grid. With the increasing integration of renewable energy resources into the grid, forecasting the demand for electricity is critical at all levels, from the distribution to the household. Most existing forecasting methods, however, can be considered black-box models as a result of deep digitalization enablers, such as deep neural networks, which remain difficult to interpret by humans. Moreover, capture of the inter-dependencies among variables presents a significant challenge for multivariate time series forecasting. In this paper we propose eXplainable Causal Graph Neural Network (X-CGNN) for multivariate electricity demand forecasting that overcomes these limitations. As part of this method, we have intrinsic and global explanations based on causal inferences as well as local explanations based on post-hoc analyses. We have performed extensive validation on two real-world electricity demand datasets from both the household and distribution levels to demonstrate that our proposed method achieves state-of-the-art performance.

This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC power output using real solar power plant measurements spanning a 34-day period, recorded at 15-minute intervals. The intricate nonlinear relationship between solar irradiation, ambient temperature, and module temperature is captured for accurate prediction. Additionally, the paper conducts a comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Mating Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search Algorithm (HSA-DNN), DNN with Adaptive Moment Estimation optimizer (ADAM) and Nonlinear AutoRegressive with eXogenous inputs (NARX). The experimental results distinctly highlight the exceptional performance of EMA-DNN by attaining the lowest Root Mean Squared Error (RMSE) during testing. This contribution not only advances solar power forecasting methodologies but also underscores the potential of merging metaheuristic algorithms with contemporary neural networks for improved accuracy and reliability.

In the context of global efforts to mitigate climate change by pursuing sustainable energy sources, wind energy has emerged as a critical contributor. However, the wind energy industry faces substantial challenges in maintaining and preserving the integrity of wind turbine blades. Timely and accurate detection and classification of blade faults, encompassing issues such as cracks, erosion, and ice buildup, are imperative to uphold wind turbines' ongoing efficiency and safety. This study introduces an inventive approach that amalgamates hyperspectral imaging and 3D Convolutional Neural Networks (CNNs) to augment the precision and efficiency of wind turbine blade fault detection and classification. Hyperspectral imaging is harnessed to capture comprehensive spectral information from blade surfaces, facilitating exact fault identification. The process is streamlined through Incremental Principal Component Analysis (IPCA), reducing data dimensions while maintaining integrity. The 3D CNN model demonstrates remarkable performance, achieving high accuracy in detecting all fault categories in full-band hyperspectral images. The model retains high accuracy even with dimensionality reduction to 20 spectral bands. The reduced processing time of the 20-band image enhances the practicality of real-world applications, thereby reducing downtime and maintenance expenditures. This research represents a significant advancement in wind turbine blade inspection, contributing to the sustainability and dependability of wind energy systems and furthering the cause of a cleaner and more sustainable energy future as part of the broader fight against climate change.

In this paper, we present a novel cloud-based demand side management (DSM) optimization approach for the cost reduction of energy usage in heating, ventilation and air conditioning (HVAC) systems in residential homes at the district level. The proposed approach achieves optimization through scheduling of HVAC energy usage within permissible bounds set by house users. House smart home energy management (SHEM) devices are connected to the utility/aggregator via a dedicated communication network that is used to enable DSM. Each house SHEM can predict its own HVAC energy usage for the next 24 h using minimalistic deep learning (DL) prediction models. These predictions are communicated to the aggregator, which will then do day ahead optimizations using the proposed game theory (GT) algorithm. The GT model captures the interaction between aggregator and customers and identifies a solution to the GT problem that translates into HVAC energy peak shifting and peak reduction achieved by rescheduling HVAC energy usage. The found solution is communicated by the aggregator to houses SHEM devices in the form of offers via DSM signals. If customers’ SHEM devices accept the offer, then energy cost reduction will be achieved. To validate the proposed algorithm, we conduct extensive simulations with a custom simulation tool based on GridLab-D tool, which is integrated with DL prediction models and optimization libraries. Results show that HVAC energy cost can be reduced by up to 36% while indirectly also reducing the peak-to-average (PAR) and the aggregated net load by up to 9.97%.

Coupled electrochemical systems for the direct capture and conversion of CO${}_2$ have garnered significant attention owing to their potential to enhance energy- and cost-efficiency by circumventing the amine regeneration step. However, optimizing the coupled system is more challenging than handling separated systems because of its complexity, caused by the incorporation of solvent and heterogeneous catalysts. Nevertheless, the deployment of machine learning can be immensely beneficial, reducing both time and cost owing to its ability to simulate and describe complex systems with numerous parameters involved. In this review, we summarized the machine learning techniques employed in the development of CO${}_2$ capture solvents such as amine and ionic liquids, as well as electrochemical CO${}_2$ conversion catalysts. To optimize a coupled electrochemical system, these two separately developed systems will need to be combined via machine learning techniques in the future.

The air conditioning systems in electric city buses usually operate in rapidly changing ambient conditions and are more likely to suffer from mechanical faults. Although many fault detection and diagnosis (FDD) methods have been developed for building air conditioning systems, they are difficult to be applied to bus air conditioners since its operation is highly dynamic and fault-free data are usually unavailable. Therefore, this paper proposes an FDD method for electric bus air conditioners to tackle the above issues. First, the method identifies faults in an unsupervised manner by comparing selected features among a group of peer systems. Then, considering the features are influenced by the operating conditions, Gaussian process regression (GPR) models are established to find the relationships between each feature and its influential parameters. The probabilistic nature of the GPR is used to differentiate predictions with large uncertainty, which are then excluded from FDD. In this way, robustness of the method is evidently improved. Finally, fault indexes are defined to detect and diagnose mechanical faults. We applied the method to a group of air conditioners in a city bus fleet. Results showed that it can effectively identify refrigerant undercharge and indoor and outdoor fan problems with low false positive/genitive rates. Also, the method is highly robust and not sensitive to the faulty systems in the bus fleet.