Energy and AI最新文献

Developing a well-predictive machine learning model that also offers improved interpretability is a key challenge to widen the application of artificial intelligence in various application domains. In this work, we present a Data Information integrated Neural Network (DINN) algorithm that incorporates the correlation information present in the dataset for the model development. The predictive performance of DINN is also compared with a standard artificial neural network (ANN) model. The DINN algorithm is applied on two case studies of energy systems namely energy efficiency cooling (ENC) & energy efficiency heating (ENH) of the buildings, and power generation from a 365 MW capacity industrial gas turbine. For ENC, DINN presents lower mean RMSE for testing datasets (RMSE_test = 1.23 %) in comparison with the ANN model (RMSE_test = 1.41 %). Similarly, DINN models have presented better predictive performance to model the output variables of the two case studies. The input perturbation analysis following the Gaussian distribution for noise generation reveals the order of significance of the variables, as made by DINN, can be better explained by the domain knowledge of the power generation operation of the gas turbine. This research work demonstrates the potential advantage to integrate the information present in the data for the well-predictive model development complemented with improved interpretation performance thereby opening avenues for industry-wide inclusion and other potential applications of machine learning.

This paper describes the utilization of artificial intelligence (AI) techniques to identify an optimal machine learning (ML) model for predicting dodecane fuel consumption in diesel combustion. The study incorporates sensitivity analysis to assess the impact levels of various parameters on fuel consumption, thereby highlighting the most influential factors. In addition, this study addresses the impact of noise and implements data cleaning techniques to ensure the reliability of the obtained results. To validate the accuracy of the predictions, the study performs several metrics and validation process, including comparisons with computational fluid dynamics (CFD) results and experimental data. Comprehensive comparisons are made among neural networks (NN), random forest regression (RFR), and Gaussian process regression (GPR) models, taking into account the complexity associated with fuel consumption predictions. The findings demonstrate that the GPR model outperforms the others in terms of accuracy, as evidenced by metrics such as mean absolute error (MAE), mean squared error (MSE), Pearson coefficient (PC), and R-squared (R²). The GPR model exhibits superior predictive ability, accurately detecting and predicting even individual data points that deviate from the overall trend. The significantly lower absolute error values also consistently indicate its higher accuracy compared with the NN and RFR models. Furthermore, the GPR model shows a remarkable speedup, approximately 1.7 times faster than traditional CFD solvers, and physically captures the momentum and thermal characteristics in a surface field prediction. Finally, the target optimization is assessed using the Euclidean distance as a fitness function, ensuring the reliability of predicted data.

Out-of-step oscillation is a very destructive physical phenomenon in power system, which could directly cause big blackout accompanied by serious sociology-economic impacts. Out-of-step splitting control is an indispensable means, which could protect the system from major shocks of out-of-step oscillation. After years of development, it has achieved certain amount of research results. Have the existing methods been able to meet the requirements of out-of-step splitting? What improvements are needed? Under this background, this review is written. It combs the development of out-of-step splitting control technologies and analyzes the technical routes and characteristics of different methods. It points out the contradiction between rapidity and optimality is the biggest technical problem, existing in both the traditional local measurement based out-of-step splitting protection and the wide-area information based out-of-step splitting protection. It further points out that the advantages of the two types of protections can be combined with the unique physical characteristics of the out-of-step center to form a more advantageous splitting strategy. Besides, facing the fact of large-scale renewable energy access to power grid in recent years, this review also analyzes the challenges brought by it and provides some corresponding suggestions. It is hoped to provide some guidance for the subsequent research work.

Electric Load Forecasting (ELF) is the central instrument for planning and controlling demand response programs, electricity trading, and consumption optimization. Due to the increasing automation of these processes, meaningful and transparent forecasts become more and more important. Still, at the same time, the complexity of the used machine learning models and architectures increases.

Because there is an increasing interest in interpretable and explainable load forecasting methods, this work conducts a literature review to present already applied approaches regarding explainability and interpretability for load forecasts using Machine Learning. Based on extensive literature research covering eight publication portals, recurring modeling approaches, trends, and modeling techniques are identified and clustered by properties to achieve more interpretable and explainable load forecasts.

The results on interpretability show an increase in the use of probabilistic models, methods for time series decomposition and the use of fuzzy logic in addition to classically interpretable models. Dominant explainable approaches are Feature Importance and Attention mechanisms. The discussion shows that a lot of knowledge from the related field of time series forecasting still needs to be adapted to the problems in ELF. Compared to other applications of explainable and interpretable methods such as clustering, there are currently relatively few research results, but with an increasing trend.

The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted from the overall system vibration. Faulty characteristics emanating from one single cylinder are also mixed with those from other cylinders. Besides, the change of working condition brings strong nonlinearities in surface vibration. To solve these problems, an improved deep residual shrinkage network (IDRSN) is developed for detecting diverse engine faults at various degrees using single channel surface vibration signal. Within IDRSN, a wide convolution kernel is utilized in first convolution layer to capture the long-term fault-related impacts and eliminate the short-time random impact. The residual network module is adopted to enhance the focus the relevant components of vibration signals. Mini-batch training strategy is used to improve the model stability. Meanwhile, Gradient-weighted class activation map is adopted to assess the consistency between the learned knowledge and the fault-related information. The IDRSN is implemented to diagnosing a diesel engine under various faults, faulty degrees and operating speeds. Comparisons with existing models are analyzed in terms of hyper-parameters, training samples, noise resistance, and visualization. Results demonstrate the proposed IDRSN's superior performance on fault diagnosis accuracy, stability, anti-noise performance, and anti-interference performance. An average accuracy rate of 98.38 % was achieved by the proposed IDRSN, in comparison to 96.64 % and 93.56 % achieved by the DRSN and the wide-kernel deep convolutional neural network respectively. These results highlight the proposed IDRSN's superiority in diagnosing multiple faults under various working conditions, offering a low-cost, highly effective, and applicable approach for complex fault diagnosis tasks.

At present, most fuel cell engines are single-stack systems, and high-power single-stack systems have bottlenecks in meeting the power requirements of heavy-duty trucks, mainly because the increase in the single active area and the excessive number of cells will lead to poor distribution uniformity of water, gas and heat in the stack, which will cause local attenuation and reduce the performance of the stack. This paper introduces the design concept of internal combustion engine, takes three-stack fuel cell engine as an example, designs multi-stack fuel cell system scheme and serialized high-voltage scheme. Through Intelligent control technology of independent hydrogen injection based on multi-stack coupling, the hydrogen injection inflow of each stack is controlled online according to the real-time anode pressure to achieve accurate fuel injection of a single stack and ensure the consistency between multiple stacks. proves the performance advantage of multi-stack fuel cell engine through theoretical design, intelligent control and test verification, and focuses on analyzing the key technical problems that may exist in multi-stack consistency. The research results provide a reference for the design of multi-stack fuel cell engines, and have important reference value for the powertrain design of long-distance heavy-duty and high-power fuel cell trucks.

The intermittency of renewable energy is a key limiting factor for the successful decarbonization of both energy producing and consuming sectors. Green hydrogen has the potential to act as the central energy vector connecting hard-to-abate sectors to renewable power. However, combining energy storage and conversion for a holistic electrolyzer system remains challenging. Here, we show the innovative Zink-Zwischenschritt Elektrolyseur (ZZE), or Zinc Intermediate step Electrolyzer in English, that temporarily decouples the water splitting reaction and uses zinc to store electrical energy in chemical form. To perform optimal operation of a ZZE system, machine learning models were applied to predict the state of charge of a lab scale ZZE system. Using various models, we were able to determine the effectiveness of the prediction and contrast it to state of charge predictions of other energy storage systems. We show that a bi-directional long short-term memory neural network approach has the lowest error within the testing environment. This work serves to perform further ZZE development as well as state of charge prediction for other novel energy storage technologies.

The purpose of this study is to investigate the approaches applied to analyze solid oxide fuel cell (SOFC) microstructural properties. Both manual and automated image processing approaches applied on SOFC microstructural images which are obtained from several types of tomography such as dual-beam focused ion beam with scanning electron microscopy (FIB-SEM), Electron Backscatter Diffraction (EBSD) and others are discussed. In fact, to achieve a realistic and accurate SOFC microstructural properties, such as average diameter, volume fraction, triple phase boundary (TPB), area interface density and tortuosity factor, the approaches of image processing and quantification are crucial for a reliable image generation for quantification purposes. The microstructural properties are optimized to improve SOFC electrode performance. Therefore, the image processing and quantification approaches are outlined and reviewed. Despite the automated image processing and quantification algorithms significantly outperform manual image processing and quantification approaches in terms of computing speed when evaluating and measuring microstructural properties, the efficiency and productivity are still extremely taken into concern. As a result, image processing and quantification approaches are concluded and presented respectively in this paper.

Lithium-ion batteries with composite anodes of graphite and silicon are increasingly being used. However, their degradation pathways are complicated due to the blended nature of the electrodes, with graphite and silicon degrading at different rates. Here, we develop a deep learning health diagnostic framework to rapidly quantify and separate the different degradation rates of graphite and silicon in composite anodes using partial charging data. The convolutional neural network (CNN), trained with synthetic data, uses experimental partial charging data to diagnose electrode-level health of tested batteries, with errors of less than 3.1% (corresponding to the loss of active material reaching ∼75%). Sensitivity analysis of the capacity-voltage curve under different degradation modes is performed to provide a physically informed voltage window for diagnostics with partial charging data. By using the gradient-weighted class activation mapping approach, we provide explainable insights into how these CNNs work; highlighting regions of the voltage-curve to which they are most sensitive. Robustness is validated by introducing noise to the data, with no significant negative impact on the diagnostic accuracy for noise levels below 10 mV, thus highlighting the potential for deep learning approaches in the diagnostics of lithium-ion battery performance under real-world conditions. The framework presented here can be generalised to other cell formats and chemistries, providing robust and explainable battery diagnostics for both conventional single material electrodes, but also the more challenging composite electrodes.

Power system is vital to modern societies, while it is susceptible to hazard events. Thus, analyzing resilience characteristics of power system is important. The standard model of infrastructure resilience, the resilience triangle, has been the primary way of characterizing and quantifying resilience in infrastructure systems for more than two decades. However, the theoretical model provides a one-size-fits-all framework for all infrastructure systems and specifies general characteristics of resilience curves (e.g., residual performance and duration of recovery). Little empirical work has been done to delineate infrastructure resilience curve archetypes and their fundamental properties based on observational data. Most of the existing studies examine the characteristics of infrastructure resilience curves based on analytical models constructed upon simulated system performance. There is a dire dearth of empirical studies in the field, which hindered our ability to fully understand and predict resilience characteristics in infrastructure systems. To address this gap, this study examined more than two hundred power-grid resilience curves related to power outages in three major extreme weather events in the United States. Through the use of unsupervised machine learning, we examined different curve archetypes, as well as the fundamental properties of each resilience curve archetype. The results show two primary archetypes for power grid resilience curves, triangular curves, and trapezoidal curves. Triangular curves characterize resilience behavior based on three fundamental properties: 1. critical functionality threshold, 2. critical functionality recovery rate, and 3. recovery pivot point. Trapezoidal archetypes explain resilience curves based on 1. duration of sustained function loss and 2. constant recovery rate. The longer the duration of sustained function loss, the slower the constant rate of recovery. The findings of this study provide novel perspectives enabling better understanding and prediction of resilience performance of power system infrastructure in extreme weather events.