In this article, to estimate the battery state of health (SOH) under realistic electric vehicle (EV) conditions, a robust and efficient data-driven algorithm is developed and validated through comprehensive battery li...
详细信息
In this article, to estimate the battery state of health (SOH) under realistic electric vehicle (EV) conditions, a robust and efficient data-driven algorithm is developed and validated through comprehensive battery life testing. More than 50 state-of-the-art EV battery cells have been tested under a variety of cycling conditions with different charging protocols, dynamic driving cycles, voltage ranges, pulse rates, and temperatures. Some of the cells have also been tested under a combination of cycling and storage conditions, constant current and multistep charging, and a periodic temperature variation that mimics real life conditions. Only partial data (voltage, current, and temperature) within a narrow state-of-charge range under a dynamic driving condition are required to extract the health indicators. A neural network is trained to find the mapping between the health features and the battery SOH. The life test data are divided into three groups. The first dataset ( approximate 55% of data) is used for training and initial validation and testing, whereas the second and third datasets ( approximate 45% of data) are entirely used for the final validation and testing to minimize the network overfitting. The results show that the SOH estimation root-mean-squared error for all datasets is less than 0.9%, signifying the fidelity and reliability of the proposed method.
A data-driven algorithm is proposed for flow reconstruction from sparse velocity and/or scalar measurements. The algorithm is applied to the flow around a two-dimensional, wall-mounted, square prism. To reduce the pro...
详细信息
A data-driven algorithm is proposed for flow reconstruction from sparse velocity and/or scalar measurements. The algorithm is applied to the flow around a two-dimensional, wall-mounted, square prism. To reduce the problem dimensionality, snapshots of flow and scalar fields are processed to derive POD modes and their time coefficients. Then a system identification algorithm is employed to build a reduced order, linear, dynamical system for the flow and scalar dynamics. Optimal estimation theory is subsequently applied to derive a Kalman estimator to predict the time coefficients of the POD modes from sparse measurements. Analysis of the flow and scalar spectra demonstrate that the flow field leaves its footprint on the scalar, thus extracting velocity from scalar concentration measurements is meaningful. The results show that remarkably good reconstruction of the flow statistics (Reynolds stresses) and instantaneous flow patterns can be obtained using a very small number of sensors (even a single scalar sensor yields very satisfactory results for the case considered). The Kalman estimator derived at one condition is able to reconstruct with acceptable accuracy the flow fields at two nearby off-design conditions. Further work is needed to assess the performance of the algorithm in more complex, three-dimensional, flows.
Wearable inertial measurement units (IMUs) are used increasingly to estimate biomechanical exposures in lifting-lowering tasks. The objective of the study was to develop and evaluate predictive models for estimating r...
详细信息
Wearable inertial measurement units (IMUs) are used increasingly to estimate biomechanical exposures in lifting-lowering tasks. The objective of the study was to develop and evaluate predictive models for estimating relative hand loads and two other critical biomechanical exposures to gain a comprehensive understanding of work-related musculoskeletal disorders in lifting. We collected 12,480 lifting-lowering phases from 26 subjects (15 men and 11 women) performing manual lifting-lowering tasks with hand loads (0-22.7 kg) at varied workstation heights and handling modes. We implemented a Hierarchical model, that sequentially classified risk factors, including workstation height, handling mode, and relative hand load. Our algorithm detected lifting-lowering phases (>97.8%) with mean onset errors of 0.12 and 0.2 seconds for lifting and lowering phases. It estimated workstation height (>98.5%), handling mode (>87.1%), and relative hand load (mean absolute errors of 5.6-5.8%) across conditions, highlighting the benefits of data-driven models in deriving lifting-lowering occurrences, timing, and critical risk factors from continuous IMU-based kinematics. Practitioner summary: The study developed and validated algorithms for detecting and predicting exposure to various risk factors during diverse lifting-lowering tasks. These factors encompass the occurrence, timing, workstation height, handling mode, and relative hand position. This approach facilitates the extraction of contextual information related to lifting tasks conducted in real-world settings through a continuous stream of inertial sensor measurements. Consequently, it can enable automated risk assessment for lifting activities in the field.
Accurate short-term forecasting of photovoltaic power generation is crucial for power dispatching, capacity analysis, and unit commitment. Existing data-driven prediction algorithms have a certain impact on calculatio...
详细信息
Accurate short-term forecasting of photovoltaic power generation is crucial for power dispatching, capacity analysis, and unit commitment. Existing data-driven prediction algorithms have a certain impact on calculation speed and prediction accuracy, but they fail to consider the internal mechanism of photovoltaic power generation and have the risk of generalization. First, the fuzzy C-means clustering (FCM) algorithm method was used for preprocessing of the PV sample set. The sample points with variability were categorized into different sample sets with less variability. Second, the photovoltaic mechanism model is added to the first layer learner of the Stacking framework to form a one-layer learner of the Long Short-Term Memory (LSTM) neural network, Light Gradient Boosting model (LGBM), and mechanism-driven model. The mechanistic model limits PV generation to a reasonable range as a prediction constraint for the data-driven model. The proposed model can seize the useful inherent information from the mechanism model and utilize the ability of data analysis to extract the inexplicit linear relationship. Finally, the PV power and weather observation data collected from photovoltaic power stations located in a certain place in Germany are used to verify the effectiveness of the proposed method.
We present a new approach to calculating time eigenvalues of the neutron transport operator (also known as $$\alpha $$alpha eigenvalues) by extending the dynamic mode decomposition (DMD) to allow for nonuniform time s...
详细信息
We present a new approach to calculating time eigenvalues of the neutron transport operator (also known as $$\alpha $$alpha eigenvalues) by extending the dynamic mode decomposition (DMD) to allow for nonuniform time steps. The new method, called variable dynamic mode decomposition (VDMD), is shown to be accurate when computing eigenvalues for systems that were infeasible with DMD due to a large separation in timescales (such as those that occur in delayed supercritical systems). The $$\alpha $$alpha eigenvalues of an infinite medium neutron transport problem with delayed neutrons, and consequently having multiple, very different relevant timescales, are computed. Furthermore, VDMD is shown to be of similar accuracy to the original DMD approach when computing eigenvalues in other systems where the previously studied DMD approach can be used.
This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artifici...
详细信息
This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artificial intelligence (AI) algorithm development are the three key factors driving the adoption of digitized solutions in the power grid. The impact of these three factors on critical functions of power system operation and planning practices is reviewed and illustrated with industrial practice case studies. Open challenges and research opportunities for data, computing, and AI algorithms are articulated within the context of the power industry's tremendous decarbonization efforts.
Historical data are typically limited. We study the following fundamental data-driven pricing problem. How can/should a decision maker price its product based on data at a single historical price? How valuable is such...
详细信息
Historical data are typically limited. We study the following fundamental data-driven pricing problem. How can/should a decision maker price its product based on data at a single historical price? How valuable is such data? We consider a decision maker who optimizes over (potentially randomized) pricing policies to maximize the worst-case ratio of the garnered revenue compared to an oracle with full knowledge of the distribution of values, when the latter is only assumed to belong to a broad nonparametric set. In particular, our framework applies to the widely used regular and monotone nondecreasing hazard rate (mhr) classes of distributions. For settings where the seller knows the exact probability of sale associated with one historical price or only a confidence interval for it, we fully characterize optimal performance and near-optimal pricing algorithms that adjust to the information at hand. The framework we develop is general and allows to characterize optimal performance for deterministic or more general randomized mechanisms and leads to fundamental novel insights on the value of data for pricing. As examples, against mhr distributions, we show that it is possible to guarantee 85% of oracle performance if one knows that half of the customers have bought at the historical price, and if only 1% of the customers bought, it still possible to guarantee 51% of oracle performance.
Advances in edge computing are powering the development and deployment of Internet of Things (IoT) systems to provide advanced services and resource efficiency. However, large-scale IoT-based load-altering attacks (LA...
详细信息
Advances in edge computing are powering the development and deployment of Internet of Things (IoT) systems to provide advanced services and resource efficiency. However, large-scale IoT-based load-altering attacks (LAAs) can seriously impact power grid operations, such as destabilising the grid's control loops. Timely detection and identification of any compromised nodes are essential to minimise the adverse effects of these attacks on power grid operations. In this work, two data-driven algorithms are proposed to detect and identify compromised nodes and the attack parameters of the LAAs. The first method, based on the Sparse Identification of Nonlinear Dynamics approach, adopts a sparse regression framework to identify attack parameters that best describe the observed dynamics. The second method, based on physics-informed neural networks, employs neural networks to infer the attack parameters from the measurements. Both algorithms are presented utilising edge computing for deployment over decentralised architectures. Extensive simulations are performed on IEEE 6-, 14-, and 39-bus systems to verify the effectiveness of the proposed methods. Numerical results confirm that the proposed algorithms outperform existing approaches, such as those based on unscented Kalman filter, support vector machines, and neural networks (NN), and effectively detect and identify locations of attack in a timely manner.
Soft sensors are mathematical models employed to estimate hard-to-measure variables from available easy-to-measure variables. These sensors are typically developed using either model-drivenalgorithms or data-driven c...
详细信息
Soft sensors are mathematical models employed to estimate hard-to-measure variables from available easy-to-measure variables. These sensors are typically developed using either model-drivenalgorithms or data-driven counterparts. data-driven algorithms are preferable since developing soft sensors via model-drivenalgorithms is in most cases unprofitable, technically difficult, or impossible. Soft sensors are desirable to be adaptive so that they can cope with the state and characteristics changes in industrial processes. Among the existing adaptive methods, just-in-time (JIT) models are gaining popularity due to their advantages of dealing with nonlinear, and time-varying processes with abrupt changes processes. In this paper, the existing JIT-based algorithms adopted to formulate adaptive soft sensors are critically reported and discussed. Furthermore, the limitations of these JIT-based algorithms are also highlighted. These JIT-based models are generally categorized into Gaussian and non-Gaussian distributed algorithms. A short discussion on algorithms considering nonlinear and missing data is also presented. Lastly, recommendations and future directions on JIT-based algorithms are outlined. It is envisaged that this manuscript will serve as a more comprehensive and up-to-date review and provide general guidelines for developing JIT models as soft sensors.& COPY;2023 Elsevier Ltd. All rights reserved.
The accurate prediction of mutual inductance in inductive planar coils is a critical challenge in advancing wireless power transfer (WPT) systems, particularly as traditional analytical methods struggle to balance pre...
详细信息
The accurate prediction of mutual inductance in inductive planar coils is a critical challenge in advancing wireless power transfer (WPT) systems, particularly as traditional analytical methods struggle to balance precision and computational speed in complex, real-world scenarios. This study addresses these limitations by exploring data-driven algorithms for predicting mutual inductance. Additionally, the study offers a robust solution to handle the nonlinearities and dynamic requirements of three-dimensional coil configurations. Seven regression algorithms-linear, polynomial, kernel ridge, decision tree, random forest, support vector and neural network-are evaluated to identify the most effective approach. Key results reveal the superior performance of kernel ridge, support vector and neural network regression models, achieving R2 scores of 0.995, 0.987 and 0.992, respectively. Kernel ridge regression demonstrated the lowest error metrics, with an MAE of 49.624 nH and an RMSE of 86.174 nH, whereas support vector and neural network regression followed closely with slightly higher errors. Conversely, traditional models such as linear regression and decision tree showed significantly higher MAEs and RMSEs, highlighting their inadequacy for handling the complexities of WPT datasets. This research establishes a scalable and accurate framework for mutual inductance prediction, paving the way for improved efficiency in WPT systems.
暂无评论