Search

Recurring bottlenecks significantly contribute to urban freeway congestion, making their analysis essential. This study examines six bottlenecks on Beijing’s Ring Road using multi-day data, identifying them via Dynamic Time Warping and Fuzzy C-Means Clustering (DTW+FCM). Key parameters—free-flow speed, critical speed, critical density, and jam density—are calibrated using fundamental diagram models. The Weibull distribution analyzes flow and speed patterns during congestion phases. The DTW+FCM method effectively identified bottlenecks and congestion levels. Severe congestion lasting over 10 hours on the West Second and Third Ring Roads averaged speeds of 15 km/h. The S3 model best fits data for the West Ring Roads, while the Van Aerde model suits the North Ring Roads. Different methods yield varying traffic capacity estimates, highlighting the need for nuanced approaches in urban expressway planning to maintain traffic quality and comfort. These findings offer valuable guidance for research and practical traffic management solutions. [ABSTRACT FROM AUTHOR]

Capacity estimation of lithium-ion batteries is significant to achieving the effective establishment of the prognostics and health management (PHM) system of lithium-ion batteries. A capacity estimation model based on the variable activation function-long short-term memory (VAF-LSTM) algorithm is proposed to achieve the high-precision lithium-ion battery capacity estimation. By re-selecting each activation function, the proposed algorithm avoids the low estimation accuracy caused by the fixed activation function of the long short-term memory (LSTM) algorithm, and meanwhile, it can effectively speed up the convergence. The algorithm inputs consider two correlation coefficients so that the health factor with the highest correlation coefficient is chosen as the network input. The experimental data used for the experimental validation is the NASA public battery data under different temperature operating conditions. The validation results show that the estimation accuracy of the VAF-LSTM algorithm under different training sets is greatly improved compared with the traditional LSTM algorithm and the back propagation (BP) algorithm, and the average estimation accuracy can reach more than 97.5%. The improvement of estimation accuracy is also clearly demonstrated under the MAE, MSE, and RMSE. Therefore, the capacity estimation model will provide an important reference role in high-precision battery management systems. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries play an irreplaceable role in various areas of production and life as an efficient energy storage element. The state of health (SOH) of lithium-ion batteries is critical to the safe operation of the energy storage system. In this study, measurable data from the battery management system, such as voltage, current and temperature profiles that change due to aging, were used. Based on these data, the relationship between capacity and charging profiles is learned by neural networks. The experimental results achieved in this study are based on the NASA lithium-ion battery data set. It has been observed that compared to the LSTM, GRU and BiLSTM methods, which are deep learning methods, the proposed GRU method with attention mechanism is more successful in estimating the health of the battery in terms of average absolute percentage error by up to 35%, 27% and 20%, respectively. The simulation studies were carried out using the deep learning toolbox in the MATLAB environment. In recent years, attention mechanisms have emerged as a powerful tool to improve the performance of time series forecasting models. In this study, LSTM, BiLSTM and GRU, which are used to solve time series problems, were tested on the same NASA data sets, and GRU was preferred because it is faster and simpler than these three methods. The mechanism proposed in this study is the SoH prediction mechanism created by combining GRU and Attention Mechanism. [ABSTRACT FROM AUTHOR]

Accurate estimation of Li-ion battery capacity is critical for a battery management system (BMS). This paper proposes an innovative method which combines a convolutional neural network and incremental capacity analysis (ICA). In the present approach, the voltage and temperature, which significantly affect the ICA curve during the discharging process, are adopted as the inputs for CNN. Rather than extracting feature parameters of an IC curve, as is carried out in the available research, the present method uses the whole ICA curve as the input to avoid complicated feature extraction and correlation analysis. The results show that the maximum error of capacity estimation is less than 4.7%, the rectified mean squared error is less than 1.3% for each battery, and the overall RMSE is below 1.12%. [ABSTRACT FROM AUTHOR]

Crossing pedestrians may significantly affect the capacity of the left-turn (LT) lane at signalized intersections while sharing the same signal phase in the left-hand traffic system, the quantitative estimation method is still not intensively discussed when considering the vehicle yielding maneuver. Despite the Road Traffic Act in Japan mandating vehicles to yield to pedestrians, instances of vehicles crossing in front of pedestrians are frequent. This study aims to refine the evaluation of LT lane capacity by introducing a novel vehicle yielding maneuver model, considering factors such as pedestrian numbers, crosswalk length, and signal timing. The model, developed using data from various Japanese crosswalks, is subjected to Monte Carlo simulation for validation. Comparative analysis with existing methods in Japanese and U.S. manuals, along with observed data, highlights the effectiveness of our model. This innovative approach has the potential to mitigate vehicle–pedestrian conflicts and reduce air pollution. By incorporating techniques such as signal optimization and two-stage crossing, our model contributes to sustainability while maintaining efficient traffic flow. [ABSTRACT FROM AUTHOR]

Introduction: Deep learning has demonstrated exceptional prowess in estimating battery capacity. However, its effectiveness is often compromised by performance degradation under a consequence of varying operational conditions and diverse charging/discharging protocols. Methods: To tackle this issue, we introduce the Knowledge Query Domain Mixing-up Network (KQDMN), a domain adaptation-based solution adept at leveraging both domain-specific and invariant knowledge. This innovation enriches the informational content of domain features by segregating the functions of feature extraction and domain alignment, enhancing the efficacy of KQDMN in utilizing diverse knowledge types. Moreover, to identify timedeteriorating features in battery time series data, we employ convolutional operations. These operations are pivotal in extracting multi-scale features from the battery's characteristic curves. Inspired by the Transformer model, we have developed a set of knowledge queries that integrate these multi-scale features seamlessly, thereby enabling extensive global feature extraction. To ensure the retention of domain-specific information, we have instituted two independent feature extraction pathways. Pursuing domain-invariant knowledge, this study introduces cross-attention as a mechanism to connect two domain spaces, effectively diminishing the disparity between source and target distributions. Results and Discussion: This approach is crucial for accurately estimating capacity in batteries with diverse performance characteristics. The practicality and robustness of the proposed method are validated using the MIT battery aging dataset, yielding highly satisfactory outcomes. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2) for our capacity estimation process are 0.19%, 0.23%, and 0.997, respectively, highlighting the precision and reliability of our approach. [ABSTRACT FROM AUTHOR]

It is of great significance to improve the safety, efficiency, and economy of lithium-ion batteries by improving the capacity estimation accuracy of lithium-ion batteries. In this paper, feature extraction and correlation analysis are carried out on the data of lithium-ion battery charging process, and the voltage curve of constant current charging stage is extracted. The difference characteristics between each cycle are used to describe the battery capacity, and these statistical characteristics are proved to be highly correlated with the battery capacity. Furthermore, an online estimation model of battery capacity based on convolution self-attention is established, and the above characteristics of constant current charging process and the battery capacity of the latest cycle are fused as input vectors of the model to realize online estimation of battery capacity. Finally, an open data set is used to verify the model experiment. The results show that the prediction error of MAE is 0.17% and that of RMSE is 0.22%. [ABSTRACT FROM AUTHOR]

The lithium thionyl chloride (Li/SOCl2) battery is widely used as an important long‐life backup power source. Accurate battery life prediction is essential to ensure the reliability of equipment and systems. In this paper, a novel method was proposed for the life prediction of Li/SOCl2 batteries based on the pulse load test and accelerated degradation test (ADT). The proposed pulse load test method can estimate the primary battery capacity accurately and nondestructively, which solves the challenge of quantifying degradation due to unknown initial values. Furthermore, we noticed a new phenomenon that capacity loss was affected by electrolyte fluidity, and unexpected capacity loss was observed for batteries at different discharge angles. By analyzing the mechanism of this phenomenon, we avoided serious capacity measurement errors in the 24‐week ADT. A life prediction model with a satisfactory ability to approximate the measured data was established depending on the exponential influence of time and temperature on capacity degradation. [ABSTRACT FROM AUTHOR]

Accurate estimation of Li-ion battery capacity is critical for a battery management system (BMS). This paper proposes an innovative method which combines a convolutional neural network and incremental capacity analysis (ICA). In the present approach, the voltage and temperature, which significantly affect the ICA curve during the discharging process, are adopted as the inputs for CNN. Rather than extracting feature parameters of an IC curve, as is carried out in the available research, the present method uses the whole ICA curve as the input to avoid complicated feature extraction and correlation analysis. The results show that the maximum error of capacity estimation is less than 4.7%, the rectified mean squared error is less than 1.3% for each battery, and the overall RMSE is below 1.12%.

It remains challenging to effectively estimate the remaining capacity of the secondary lithium‐ion batteries that have been widely adopted for consumer electronics, energy storage, and electric vehicles. Herein, by integrating regular real‐time current short pulse tests with data‐driven Gaussian process regression algorithm, an efficient battery estimation has been successfully developed and validated for batteries with capacity ranging from 100% of the state of health (SOH) to below 50%, reaching an average accuracy as high as 95%. Interestingly, the proposed pulse test strategy for battery capacity measurement could reduce test time by more than 80% compared with regular long charge/discharge tests. The short‐term features of the current pulse test were selected for an optimal training process. Data at different voltage stages and state of charge (SOC) are collected and explored to find the most suitable estimation model. In particular, we explore the validity of five different machine‐learning methods for estimating capacity driven by pulse features, whereas Gaussian process regression with Matern kernel performs the best, providing guidance for future exploration. The new strategy of combining short pulse tests with machine‐learning algorithms could further open window for efficiently forecasting lithium‐ion battery remaining capacity. [ABSTRACT FROM AUTHOR]

There is increased talk about using second-life batteries in applications. In first-life applications, the batteries start from new, and a range of life cycle estimation techniques are applied. However, it is not clear how second-life batteries should be monitored compared to first life batteries. This paper investigated different algorithms from first-life applications for estimating and forecasting battery cell state of health in conjunction with capacity calculations using second life cells under long term durability testing. The paper looks at how close these models predict capacity fade based on a set of second-life batteries that have been undertaking sweat testing over six different applications. The paper concludes that there are two methods that could be suitable candidates for predicting lifespan. One of these needed to be modified from the original. [ABSTRACT FROM AUTHOR]

The label-less characteristics of real vehicle data make engineering modeling and capacity identification of lithium-ion batteries face great challenges. Different from ideal laboratory data, the raw data collected from vehicle driving cycles have a great adverse impact on effective modeling and capacity identification of lithium-ion batteries due to the randomness and unpredictability of vehicle driving conditions, sampling frequency, sampling resolution, data loss, and other factors. Therefore, data cleaning and optimization is processed and the capacity of a battery pack is identified subsequently in combination with the improved two-point method. The current available capacity is obtained by a Fuzzy Kalman filter optimization capacity estimation curve, making use of the charging and discharging data segments. This algorithm is integrated into a new energy big data cloud platform. The results show that the identification algorithm of capacity is applied successfully from academic to engineering fields by charge and discharge mutual verification, and that life expectancy meets the engineering requirements. [ABSTRACT FROM AUTHOR]

Extensive research has been conducted on energy storage systems (ESSs) for efficient power use to mitigate the problems of environmental pollution and resource depletion. Various batteries such as lead-acid batteries, lithium batteries, and vanadium redox flow batteries (VRFBs), which have longer life spans and better fire safety, have been actively researched. However, VRFBs undergo capacity reduction due to electrolyte crossover. Additionally, research on the capacity and state of charge (SOC) estimation for efficient energy management, safety, and life span management of VRFBs has been performed; however, the results of short-term experimental conditions with little change in capacity are presented without considering the rebalancing process of the electrolyte. Therefore, herein we propose a method for estimating the capacity of a VRFB using the cumulative charge and electrolyte volume amount under long-term cycle conditions, including rebalancing. The main point of the estimation method is to design a capacity estimation equation in the form of a power function with the measured cumulative charge of the battery as a variable and to update the initial capacity value applied to the estimation equation with the amount of electrolyte measured at the time of rebalancing. Additionally, the performance verification results of the SOC estimation algorithm using the capacity estimation model were presented using the long-term charge/discharge cycle test data of a 10 W-class single cell. [ABSTRACT FROM AUTHOR]

The accuracy of capacity estimation is of great importance to the safe, efficient, and reliable operation of battery systems. In recent years, data-driven methods have emerged as promising alternatives to capacity estimation due to higher estimation accuracy. Despite significant progress, data-driven methods are mainly developed by experimental data under well-controlled charge–discharge processes, which are seldom available for practical battery health monitoring under realistic conditions due to uncertainties in environmental and operational conditions. In this paper, a novel method to estimate the capacity of large-format LiFePO4 batteries based on real data from electric vehicles is proposed. A comprehensive dataset consisting of 85 vehicles that has been running for around one year under diverse nominal conditions derived from a cloud platform is generated. A classification and aggregation capacity prediction method is developed, combining a battery aging experiment with big data analysis on cloud data. Based on degradation mechanisms, IC curve features are extracted, and a linear regression model is established to realize high-precision estimation for slow-charging data with constant-current charging. The selected features are highly correlated with capacity (Pearson correlation coefficient < 0.85 for all vehicles), and the MSE of the capacity estimation results is less than 1 Ah. On the basis of protocol analysis and mechanism studies, a feature set including internal resistance, temperature, and statistical characteristics of the voltage curve is constructed, and a neural network (NN) model is established for multi-stage variable-current fast-charging data. Finally, the above two models are integrated to achieve capacity prediction under complex and changeable realistic working conditions, and the relative error of the capacity estimation method is less than 0.8%. An aging experiment using the battery, which is the same as those equipped in the vehicles in the dataset, is carried out to verify the methods. To the best of the authors' knowledge, our study is the first to verify a capacity estimation model derived from field data using an aging experiment of the same type of battery. [ABSTRACT FROM AUTHOR]

In this work, a battery consisting of eight commercial NMC/graphite cells connected in series was cycled to 60% of its initial capacity. During the test, special care was taken to ensure that the results were not influenced by either the module assembly or the module design. For this purpose, the cells were virtually connected in a laboratory environment with the help of the test device as if they were operated together in a battery. Extrinsic influences that affect cell aging were thus reduced to a minimum. Differential Voltage Analysis (DVA), Electrochemical Impedance Spectrum (EIS), and relaxation measurements were performed to analyze the aging behavior of each cell. The results show that despite a theoretically perfect module design, Cell-to-Cell Variations (CtCV) occurred during aging. The shifting Depth of Discharge (DoD) values among the cells further amplify CtCV. Lithium plating was also observed in the faster aging cells after cyclic aging, suggesting that this aging effect contributes significantly to the development of CtCV. After the aging test, the battery was equipped with an active balancing system that maximizes capacity utilization. More important, the balancing charges which are calculated iteratively within the used balancing algorithm show a strong correlation to the pure capacity losses and thus provide a new way to determine the capacity values of each cell individually without disassembling the battery. [ABSTRACT FROM AUTHOR]

Accurate capacity estimation of onboard lithium-ion batteries is crucial to the performance and safety of electric vehicles. In recent years, data-driven methods based on partial charging curve have been widely studied due to their low requirement of battery knowledge and easy implementation. However, existing data-driven methods are usually based on a fixed voltage segment or state of charge, which would be failed if the charging process does not cover the predetermined segment due to the user's free charging behavior. This paper proposes a capacity estimation method using multiple small voltage sections and back propagation neural networks. It is intended to reduce the requirement of the length of voltage segment for estimating the complete battery capacity in an incomplete charging cycle. Firstly, the voltage segment most possibly covered is selected and divided into a number of small sections. Then, sectional capacity and skewness of the voltage curve are extracted from these small voltage sections, and severed as health factors. Secondly, the Box–Cox transformation is adopted to enhance the correlation between health factors and the capacity. Thirdly, multiple back propagation neural networks are constructed to achieve capacity estimation based on each voltage section, and their weighted average is taken as the final result. Finally, two public datasets are employed to verify the accuracy and generalization of the proposed method. Results show that the root mean square error of the fusion estimation is lower than 4.5%. [ABSTRACT FROM AUTHOR]

Researchers are focused toward the development of electric vehicles and hybrid electric vehicles for the preservation of the ecosystem. Energy storage, conversely, became essential with these changes in vehicular technology. This opens new research fronts and introduces complex problems that are to be investigated regarding the primary storage element. Battery modeling offers improved efficiency, safety, and reliability. Lithium-ion batteries are a popular source of energy in many applications, especially for electric vehicles because of their high performance and high energy density. However, there exist some inherent issues like complex electrochemical reactions that make accurate monitoring a challenging task. This article performs a comparative study of the existing battery state of health (SOH) monitoring and capacity estimation techniques using the NASA dataset for lithium-ion batteries. Charging cycle datasets for voltage, current, and temperature are used for feature identification and extraction. After the modeling of extracted features, the SOH and the capacity of four batteries are estimated using three data-driven techniques. Including convolutional neural network, feed-forward neural network, and long short-term memory (LSTM), and their results are compared. The comparative analysis highlights an outstanding performance and high accuracy of the LSTM-based machine learning technique because of the inherited long-term memory of the LSTM. The study, therefore, recommends the use of LSTM to researchers for battery health monitoring and capacity estimation with the highest possible accuracy. [ABSTRACT FROM AUTHOR]

Global solar photovoltaic capacity has consistently doubled every 18 months over the last two decades, going from 0.3 GW in 2000 to 643 GW in 2019, and is forecast to reach 4240 GW by 2040. However, these numbers are uncertain, and virtually all reporting on deployments lacks a unified source of either information or validation. In this paper, we propose, optimize, and validate a deep learning framework to detect and map solar farms using a state-of-the-art semantic segmentation convolutional neural network applied to satellite imagery. As a final step in the pipeline, we propose a model to estimate the energy generation capacity of the detected solar energy facilities. Objectively, the deep learning model achieved highly competitive performance indicators, including a mean accuracy of 96.87%, and a Jaccard Index (intersection over union of classified pixels) score of 95.5%. Subjectively, it was found to detect spaces between panels producing a segmentation output at a sub-farm level that was better than human labeling. Finally, the detected areas and predicted generation capacities were validated against publicly available data to within an average error of 4.5% Deep learning applied specifically for the detection and mapping of solar farms is an active area of research, and this deep learning capacity evaluation pipeline is one of the first of its kind. We also share an original dataset of overhead solar farm satellite imagery comprising 23,000 images (256 × 256 pixels each), and the corresponding labels upon which the machine learning model was trained. [ABSTRACT FROM AUTHOR]

As the intermittency and uncertainty of photovoltaic (PV) power generation poses considerable challenges to the power system operation, accurate PV generation estimates are critical for the distribution operation, maintenance, and demand response program implementation because of the increasing usage of distributed PVs. Currently, most residential PVs are installed behind the meter, with only the net load available to the utilities. Therefore, a method for disaggregating the residential PV generation from the net load data is needed to enhance the grid-edge observability. In this study, an unsupervised PV capacity estimation method based on net metering data is proposed, for estimating the PV capacity in the customer's premise based on the distribution characteristics of nocturnal and diurnal net load extremes. Then, the PV generation disaggregation method is presented. Based on the analysis of the correlation between the nocturnal and diurnal actual loads and the correlation between the PV capacity and their actual PV generation, the PV generation of customers is estimated by applying linear fitting of multiple typical solar exemplars and then disaggregating them into hourly-resolution power profiles. Finally, the anomalies of disaggregated PV power are calibrated and corrected using the estimated capacity. Experiment results on a real-world hourly dataset involving 260 customers show that the proposed PV capacity estimation method achieves good accuracy because of the advantages of robustness and low complexity. Compared with the state-of-the-art PV disaggregation algorithm, the proposed method exhibits a reduction of over 15% for the mean absolute percentage error and over 20% for the root mean square error. [ABSTRACT FROM AUTHOR]

The battery is an important part of pure electric vehicles and hybrid electric vehicles, and its state and parameter estimation has always been a big problem. To determine the available energy stored in a battery, it is necessary to know the current state-of-charge (SOC) and the capacity of the battery. For the determination of the battery SOC and capacity, it is generally estimated according to the Electromotive Force (EMF) of the battery, which is the open-circuit-voltage (OCV) of the battery in a stable state. An off-line battery SOC and capacity estimation method for lithium-ion batteries is proposed in this paper. The BP neural network with a high accuracy is trained in the case of sufficient data with the new neural network intelligent algorithm, and the OCV can be accurately predicted in a short time. The model training requires a large amount of data, so different experiments were designed and carried out. Based on the experimental data, the feasibility of this method is verified. The results show that the neural network model can accurately predict the OCV, and the error of capacity estimation is controlled within 3%. The mentioned method was also carried out in a real vehicle by using its cloud data, and the capacity estimation can be easily realized while limiting inaccuracy to less than 5%. [ABSTRACT FROM AUTHOR]

The accurate lithium-ion battery capacity estimation is vital for ensuring the safe and reliable operation of battery-powered systems. Existing data-driven methods heavily rely on fixed charging stages for feature extractions, posing significant limitations in real-world applications. This paper proposes an adaptable capacity estimation approach utilising short-duration random charging voltages during the constant-current charging stage and leveraging convolutional neural networks (CNNs). Based on the user-friendly " V s t a r t − t e n d " strategy, two health features including charging voltage and its increment are firstly extracted from random charging segments. Secondly, a feature evolution pattern analysis over the battery's lifespan is proposed to divide the charging voltage range for robust model development. An optimal combination of both the sampling interval and data length is determined for the feature extraction. Then, a two-dimensional CNN model is developed to effectively learn ageing-related knowledge from various random charging segments in a specific charging voltage range. The effectiveness of the proposed approach is ultimately verified using two distinct types of batteries across three operational temperatures. The results demonstrate that the proposed approach show much potential as a promising capacity estimation technique utilising a 600 s random charging segment sampled at a 20 s interval. • Adaptable battery capacity estimation is achieved using random short-duration charging voltages. • Feature evolution analysis is proposed to guide feature extraction and model development. • 2D-CNN model is developed for diverse random inputs and accurate capacity estimation. • The model's effectiveness is validated on two types of batteries at three working conditions. [ABSTRACT FROM AUTHOR]

Accurate state of charge and capacity estimation is crucial for battery packs in electric vehicles. However, the cell inconsistencies, computational complexity, temperature variations, and complex drive cycles all pose great challenges for the state of charge and capacity estimation of battery packs in field operation. This work aims to develop a framework for state of charge and capacity estimation of battery packs in real electric vehicles with few representative cells and physics-informed machine learning. By analyzing the battery data using a quantity-capacity diagram, the representative cells within the pack can be identified based on the relaxation terminal voltage online. Leveraging the physics information of batteries, the state of charge of the representative cells are monitored in a closed-loop manner. Then, state of charge and available capacity of battery pack are achieved based on the state of only two representative cells. We validate our method by evaluating its performance on the datasets of battery pack in real electric vehicles across different temperatures and drive cycles. The improvements of 83.60 % and 85.13 % in average root mean square errors can be achieved at real drive cycles under 30 °C and 15 °C. The results demonstrate that accurate and robust state estimation of battery packs can be achieved in field operations by utilizing the battery data of only two cells in laboratory conditions. [Display omitted] • Co-estimation of state of charge and capacity of battery pack in real EVs. • Only using state information of two cells based on a quantity-capacity analysis. • Physics parameters are incorporated into data-driven model in a closed-loop. • Experimental validation is conducted on a battery pack from commercial EVs. [ABSTRACT FROM AUTHOR]

• An unsupervised feature extraction method of Li-ion batteries' EIS is proposed. • The latent variables are extracted automatically without prior knowledge. • The extracted latent variables are related to battery aging. • The capacity of batteries for uneven usage during degradation is estimated. • The proposed method generates reliable EIS data. In this paper, we propose an unsupervised feature extraction technique using a variational autoencoder and generative adversarial network (VAEGAN) that automatically extracts meaningful latent variables from the electrochemical impedance spectra (EIS) of lithium-ion (Li-ion) batteries. These variables accurately reflect the degree of Li-ion battery degradation and are closely related to its capacity. By analyzing the latent variables, it was found that the network can learn the effect of Li-ion battery capacity degradation on the EIS. The extracted latent variables are then used as input features for Gaussian Process Regression (GPR) to estimate the capacity of Li-ion batteries under uneven usage and with unknown historical data. The results show that the capacity prediction method proposed in this paper can significantly reduce prediction errors compared to the current state-of-the-art methods. The method not only provides a more reliable capacity estimation but is also robust to highly noisy EIS data, making it more suitable for practical application scenarios. [Display omitted] [ABSTRACT FROM AUTHOR]

Hydrocarbon exploration is a high-risk venture; therefore, pre-determining reservoirs' capacities is pertinent, reducing associated uncertainties regarding hydrocarbon presence and production. This study delineates hydrocarbon-bearing sands, determines the reservoir area extent, computes the associated petrophysical parameters and presents the reserve volume estimation based on wireline logs with integrated 3-D seismic surveys. It evaluates and indicates three (3) hydrocarbon-bearing reservoirs sands (NZ(R1), NZ(R2) and NZ(R3)) of varying thicknesses (h) across three (3) wells reservoirs NZ(R1), NZ(R2) and NZ(R3). The reservoir properties, including porosity (Ф), free fluid index (FFI), permeability (K), fluid saturations and reservoir thickness (h), represent potentially viable hydrocarbon reservoir units across the field. It presents the estimation of the recovery factor based on the FFI values. Across the reservoirs, Ф is 0.28 in NZ(R1), 0.27 in NZ(R2) and 0.26 in NZ(R3). FFI is 0.26 in NZ(R1), 0.25 in NZ(R2) and 0.26 in NZ(R3). K is 10388 mD in NZ(R1), 8304mD in NZ(R2), and 6580 mD in NZ(R3). Water saturation (Sw) is up to 0.4, 0.36 and 0.20 with the associated hydrocarbon saturation (Sh) of 0.60, 0.64 and 0.80 corresponding to NZ(R1), NZ(R2) and NZ(R3). Considering the delineated reservoir areas based on the prevailing fault assisted structural style, the total volume of recoverable oil is 11.3×106, while the gas capacity is 1.8 ×109 cuft. These findings will aid the field's oil and gas reservoir developmental activities and serve as reference points to related studies involving similar objectives.

Accurate capacity estimation is important for safe operation of battery. Existing advanced researches heavily rely on feature engineering to model capacity degradation, where features are difficult to design and extract. In this paper, a novel purely data-driven capacity estimation method is proposed by applying ensemble learning to extremely sparse significant points on voltage and/or temperature curve. The significant points are just raw points evenly distributed throughout the charging/discharging process, or points corresponding to specific SoC, which is easy to extract without complicated feature engineering process on raw data. A novel ensemble learning framework incorporating light gradient boosting decision tree (LightGBM) and neural network is employed to find the regression relationship between significant points and battery capacity. Public battery dataset collected by Oxford university is used to verify the effectiveness of the proposed method. Results show that for Oxford dataset, the maximum and mean capacity estimation error could be controlled within 1.25% and 0.5% respectively, which is superior to most of existing capacity estimation methods. Moreover, robustness, generalization ability and model application are well discussed.

As the use of energy storage systems (ESSs) and electric vehicles (EVs) increases, the importance of lithium-ion (Li-ion) batteries is also growing. The accurate capacity estimation of a battery is useful for detecting the degradation and end-of-life of the battery for scheduled maintenance and replacement, thereby improving the reliability of battery-powered systems. However, many of the capacity estimation methods developed thus far are offline methods and are not suitable for online monitoring. In this study, a novel capacity estimation method for Li-ion batteries is proposed, based on the enhanced coulomb counting (ECC) method. Typically, the battery capacity calculated by ECC has a large error owing to the error in the state of charge estimation. Therefore, additional means are required to obtain an accurate value for the battery capacity. The Kalman filter is an optimal estimator of the hidden state with Gaussian noise and is applied to the capacity values calculated by the ECC method. The performance of the proposed method in estimating capacity is verified through experiments with a Li-ion battery operated using a standard vehicle driving schedule. The results show that the online capacity estimation using the proposed method is performed successfully within 10 h with a 1.7% error.

The precise capacity estimation of batteries can extend their lifespan and is necessary to ensure reliability and safety of operation. Many methods have been developed with this objective in the last decades. However, there is still research for more accurate and less complex methods in order to estimate the state of charge of operating batteries. This article presents exponential decay equations that model the behavior of the battery capacity drop with the discharge current. Experimental data for different application batteries showed that these equations have a superior accuracy compared to the empirical Peukert equation. Their parameters are dimensionally coherent and make the characterization and categorization of batteries possible, besides, they give insights about the behavior of the electrodes under different discharge rates. Due to the low complexity and easy adaptability to the currently employed methods, these equations can be easily employed in battery management systems without the need for great computational power. DOI: http://dx.doi.org/10.17807/orbital.v13i5.1555

Summary: The battery pack of electric vehicles (EV) is generally composed of multiple cells in series. Due to the inconsistency between the cells in the production process and use stage, the capacity and state‐of‐charge (SOC) of the cells will be different. We propose an online estimation method based on the charging curve similarity principle in this paper. The proposed method uses a series of charging time differences (CTD) during the charge. By analyzing the CTD curve, the capacity and SOC difference can be achieved. The first‐order resistance circuit model is used for the series charging curve simulation. Further experimental verification is conducted using two groups of four cells in series. In simulations and experiments, the error of the proposed capacity estimation method and the initial SOC error are less than 1%. Finally, the robustness of the proposed method is verified using EV cloud data. The results demonstrate that the proposed method has good robustness at the level of EV cloud data. [ABSTRACT FROM AUTHOR]

To accurately estimate the state of charge (SOC) of the aged batteries, the capacity estimation must not be ignored. Based on the battery charging data, this paper proposes a co-estimation model to estimate the SOC and capacity for lithium-ion batteries. First, a new health indicator of capacity is extracted based on the charging data of lithium batteries; second, the capacity is estimated by least squares support vector machine (LSSVM). The results are recorded based on a memory gate and used as the input of SOC estimation. Third, a moving window method is adopted to address the long-term dependency loss problem of the recurrent neural network (RNN), and a co-estimation model is obtained. Finally, the proposed model is compared with other models. The results show that the proposed model performs better. The maximum RMSE of the proposed model is 0.85%, and the computational cost of the proposed model is below 5 s.

Lithium-ion batteries (LIBs) have emerged as the preferred energy storage systems for various types of electric transports, including electric vehicles, electric boats, electric trains, and electric airplanes. The energy management of LIBs in electric transports for all-climate and long-life operation requires the accurate estimation of state of charge (SOC) and capacity in real-time. This study proposes a multi-stage model fusion algorithm to co-estimate SOC and capacity. Firstly, based on the assumption of a normal distribution, the mean and variance of the residual error from the model at different ageing levels are used to calculate the weight for the establishment of a fusion model with stable parameters. Secondly, a differential error gain with forward-looking ability is introduced into a proportional–integral observer (PIO) to accelerate convergence speed. Thirdly, a fusion algorithm is developed by combining a multi-stage model and proportional–integral–differential observer (PIDO) to co-estimate SOC and capacity under a complex application environment. Fourthly, the convergence and anti-noise performance of the fusion algorithm are discussed. Finally, the hardware-in-the-loop platform is set up to verify the performance of the fusion algorithm. The validation results of different aged LIBs over a wide range of temperature show that the presented fusion algorithm can realize a high-accuracy estimation of SOC and capacity with the relative errors within 2% and 3.3%, respectively.

Alternating current (AC) impedance is an important and promising feature for lithium‐ion battery state estimation and prediction. Herein, a new battery capacity estimation method using AC impedance with Gaussian process regression (GPR) is proposed. A bunch of high‐energy 18 650‐type batteries with a nominal capacity of 3.5 Ah are cycled at 25, 35, and 45 °C until the capacity drops below 2.6 Ah. Two single‐frequency points are found which are highly correlated with the battery residual capacity regardless of the cycling temperatures. Machine learning methods are used to probe the battery capacity with the real and imaginary impedance of two single‐frequency points. The best model achieves a test root‐mean‐squared error of 0.5% (17.36 mAh) with GPR. This work provides a new perspective to predicting the complex dynamical behavior of batteries by combining electrochemical impedance with data‐driven methods. [ABSTRACT FROM AUTHOR]

Accurate battery capacity estimation is crucial for ensuring battery management systems' safe and reliable operation. Although deep learning algorithms have been widely applied in the field of image recognition, their application in battery diagnosis is relatively limited. Besides, obtaining complete cycling data during charging/discharging processes can be challenging in practical applications. This paper proposes a battery capacity estimation method based on partial charge curves and pruned residual neural networks. To leverage the aging information inherent in partial charge curves, the partial segment battery data is transformed into images using wavelet denoising and soft dynamic time warping algorithms. Subsequently, we present a stratified random sampling method to address the issue of imbalanced sample distributions in battery dataset partitioning, and employ residual neural networks to mitigate performance degradation caused by stacking multiple network layers. To validate the effectiveness of the proposed method, experiments are conducted on three types of battery data. During the experimental phase, the root mean square error and mean absolute error of estimated battery capacity are both below 0.79% and 0.54%. Furthermore, a hybrid-pruning algorithm is proposed to enable the deployment of the model on the battery management system, which reduces the model size and computational complexity without compromising accuracy. Compared to other pruning algorithms, the proposed hybrid-pruning algorithm outperforms diagnostic accuracy and computational efficiency after fine-tuning, reducing the model size by 77.40% and creating a more compact structure. [ABSTRACT FROM AUTHOR]

Capacity is a key factor in assessing battery health. Traditional capacity estimation methods assume by default the battery is in a normal state. When there is a latent short-circuit fault, the measured current deviates from the actual current flowing into or out of the battery unit, leading to errors in capacity estimation. To address this challenge, we have constructed an end-cloud collaborative framework to accurately estimate the module's capacity considering the latent short-circuit faults. The core scheme is to estimate the module's charging capacity and discharging capacity simultaneously, obtain the module's operating mode based on the historical relationship between the two, conduct quantitative diagnosis for the short-circuit fault, and feedback the accurate capacity value. This framework addresses the coupled issue of erroneous capacity estimation in the presence of latent short-circuit faults, and the inability to diagnose module external short-circuit faults due to the lack of a comparison. This has profound significance for achieving more reliable battery safety management. • Different from traditional algorithms, the core algorithm in this paper can accurately estimate module capacity considering the latent SC faults; • Utilizing capacity estimation results, this paper has achieved the diagnosis of module ESC faults, overcoming the challenge posed by the lack of a comparison; • We have proposed an end-cloud collaborative framework that effectively combines the advantages of both the vehicle end and the cloud, achieving accurate module capacity estimation and quantitative diagnosis of SC faults. [ABSTRACT FROM AUTHOR]

Several European road operators and authorities joined the C-Roads Platform with the aim of harmonising the deployment activities of cooperative intelligent transport systems (C-ITS). C-ITS research is preliminary to future automated-driving vehicles. The current conventional highways were designed on traditional criteria and models specifically developed for traffic flows of manually guided vehicles. Thus, this article describes some new criteria for designing and monitoring road infrastructures on the basis of performance features of autonomous (or self-driving) vehicles.

Reliable capacity estimation is crucial for safe operation of lithium-ion batteries (LIBs). This work combines the temporal convolutional network (TCN) and Gaussian process regression (GPR) to establish a novel probabilistic capacity estimation method. The proposed TCN-GPR method can not only provide accurate capacity estimation but also quantify the uncertainty of the estimation. Besides, the TCN-GPR method can automatically extract degradation features from partial charging segments, overcoming the limitations of manual experience. In addition, the TCN-GPR method can be applied to different types of LIBs through transfer learning using only a small amount of training data. For validation, the Oxford battery dataset is used to demonstrate the accuracy and robustness of the TCN-GPR method, where a mean absolute percentage error (MAPE) of less than 0.3% can be achieved with only a 15-min partial charging segment. Furthermore, our own experimental dataset is used to demonstrate the generalization ability of the TCN-GPR method through transfer learning, where a MAPE of less than 0.7% can be achieved by using only one battery cell as the training sample. • A novel TCN-GPR method is proposed for probabilistic capacity estimation of LIBs. • The degradation features can be automatically extracted without manual experience. • The uncertainty of capacity estimation can be effectively quantified. • Reliable capacity estimation can be achieved using only short charging segment. • Transfer learning can be used for capacity estimation of different types of LIBs. [ABSTRACT FROM AUTHOR]

Since the inconsistency in battery pack and failure of charging equipment, the slight overcharging for LiFePO 4 batteries is occurred and even caused thermal runaway phenomenon. In this study, an integrated framework of aging mechanism and machine learning approach is utilized for capacity estimation of LiFePO 4 batteries under slight overcharging cycling. Specifically, the non-destructive and post-mortem analyses are introduced to identify aging mechanism of LiFePO 4 batteries. Meanwhile, the correlation between the internal chemical mechanism and incremental capacity curves is comprehensively conducted, and incremental capacity features are selected and verified as health indicators under slight overcharge cycling. The results show that the lithium dendrite and graphite-coated material separation accelerate the failure of LiFePO 4 batteries under slight overcharge cycling. Moreover, the least square support vector machine is established for accurate capacity estimation of LiFePO 4 batteries. When compared to the existing methods, the proposed approach can obtain higher accuracy in capacity estimation with a maximum relative error below 2%. • An integrated framework of mechanism and machine learning approach is proposed for capacity estimation. • Aging mechanism is achieved based on non-destructive and post-mortem analyses under slight overcharging cycling. • The correlation between chemical mechanism and incremental capacity curves is conducted under slight overcharging cycling. • Least square support vector machine is built for degradation model of LiFePO 4 batteries. [ABSTRACT FROM AUTHOR]

Geological carbon storage and sequestration (GCS), a key method within carbon capture and sequestration (CCS), is globally recognized as an effective strategy to reduce atmospheric carbon dioxide (CO 2) levels and combat the greenhouse effect. However, discrepancies between projected and actual storage capacities, especially in large-scale CO 2 storage, have raised concerns among stakeholders regarding potential overestimations. This paper reviews the definitions and methods used to estimate storage capacity, highlighting variations and providing a practical guide for predictions while suggesting directions for future research. We discuss numerous analytical and numerical models that account for dynamic constraints such as safety considerations, trapping mechanisms, and reservoir performance, primarily focusing on local scales. These models enhance the accuracy of capacity estimations over conventional static models by quantifying CO 2 storage capacity both spatially and temporally. Additionally, this review underscores the need for sophisticated evaluations of large-scale storage. We introduce two pivotal tools designed for basin-scale capacity estimation and discuss the challenges associated with expanding dynamic capacity assessments to larger scales. In conclusion, the paper explores the burgeoning use of machine learning-based models, advocating for future research efforts to leverage machine learning in developing integrated tools that offer more comprehensive and precise capacity estimations for GCS. • Reviews CO2 storage capacity definitions, noting the discrepancies. • Dynamic capacity: safety, trapping, reservoir performance limits beyond static. • Reviews models, uncertainties and influencing factors for capacity estimation. • Focusing on large-scale storage, introduces two efficient estimation tools. • Addresses needs, challenges and techniques of scaling up dynamic capacity. [ABSTRACT FROM AUTHOR]

The label-less characteristics of real vehicle data make engineering modeling and capacity identification of lithium-ion batteries face great challenges. Different from ideal laboratory data, the raw data collected from vehicle driving cycles have a great adverse impact on effective modeling and capacity identification of lithium-ion batteries due to the randomness and unpredictability of vehicle driving conditions, sampling frequency, sampling resolution, data loss, and other factors. Therefore, data cleaning and optimization is processed and the capacity of a battery pack is identified subsequently in combination with the improved two-point method. The current available capacity is obtained by a Fuzzy Kalman filter optimization capacity estimation curve, making use of the charging and discharging data segments. This algorithm is integrated into a new energy big data cloud platform. The results show that the identification algorithm of capacity is applied successfully from academic to engineering fields by charge and discharge mutual verification, and that life expectancy meets the engineering requirements.

There is increased talk about using second-life batteries in applications. In first-life applications, the batteries start from new, and a range of life cycle estimation techniques are applied. However, it is not clear how second-life batteries should be monitored compared to first life batteries. This paper investigated different algorithms from first-life applications for estimating and forecasting battery cell state of health in conjunction with capacity calculations using second life cells under long term durability testing. The paper looks at how close these models predict capacity fade based on a set of second-life batteries that have been undertaking sweat testing over six different applications. The paper concludes that there are two methods that could be suitable candidates for predicting lifespan. One of these needed to be modified from the original.

Extensive research has been conducted on energy storage systems (ESSs) for efficient power use to mitigate the problems of environmental pollution and resource depletion. Various batteries such as lead-acid batteries, lithium batteries, and vanadium redox flow batteries (VRFBs), which have longer life spans and better fire safety, have been actively researched. However, VRFBs undergo capacity reduction due to electrolyte crossover. Additionally, research on the capacity and state of charge (SOC) estimation for efficient energy management, safety, and life span management of VRFBs has been performed; however, the results of short-term experimental conditions with little change in capacity are presented without considering the rebalancing process of the electrolyte. Therefore, herein we propose a method for estimating the capacity of a VRFB using the cumulative charge and electrolyte volume amount under long-term cycle conditions, including rebalancing. The main point of the estimation method is to design a capacity estimation equation in the form of a power function with the measured cumulative charge of the battery as a variable and to update the initial capacity value applied to the estimation equation with the amount of electrolyte measured at the time of rebalancing. Additionally, the performance verification results of the SOC estimation algorithm using the capacity estimation model were presented using the long-term charge/discharge cycle test data of a 10 W-class single cell.

In this work, a battery consisting of eight commercial NMC/graphite cells connected in series was cycled to 60% of its initial capacity. During the test, special care was taken to ensure that the results were not influenced by either the module assembly or the module design. For this purpose, the cells were virtually connected in a laboratory environment with the help of the test device as if they were operated together in a battery. Extrinsic influences that affect cell aging were thus reduced to a minimum. Differential Voltage Analysis (DVA), Electrochemical Impedance Spectrum (EIS), and relaxation measurements were performed to analyze the aging behavior of each cell. The results show that despite a theoretically perfect module design, Cell-to-Cell Variations (CtCV) occurred during aging. The shifting Depth of Discharge (DoD) values among the cells further amplify CtCV. Lithium plating was also observed in the faster aging cells after cyclic aging, suggesting that this aging effect contributes significantly to the development of CtCV. After the aging test, the battery was equipped with an active balancing system that maximizes capacity utilization. More important, the balancing charges which are calculated iteratively within the used balancing algorithm show a strong correlation to the pure capacity losses and thus provide a new way to determine the capacity values of each cell individually without disassembling the battery.

The accuracy of capacity estimation is of great importance to the safe, efficient, and reliable operation of battery systems. In recent years, data-driven methods have emerged as promising alternatives to capacity estimation due to higher estimation accuracy. Despite significant progress, data-driven methods are mainly developed by experimental data under well-controlled charge–discharge processes, which are seldom available for practical battery health monitoring under realistic conditions due to uncertainties in environmental and operational conditions. In this paper, a novel method to estimate the capacity of large-format LiFePO4 batteries based on real data from electric vehicles is proposed. A comprehensive dataset consisting of 85 vehicles that has been running for around one year under diverse nominal conditions derived from a cloud platform is generated. A classification and aggregation capacity prediction method is developed, combining a battery aging experiment with big data analysis on cloud data. Based on degradation mechanisms, IC curve features are extracted, and a linear regression model is established to realize high-precision estimation for slow-charging data with constant-current charging. The selected features are highly correlated with capacity (Pearson correlation coefficient < 0.85 for all vehicles), and the MSE of the capacity estimation results is less than 1 Ah. On the basis of protocol analysis and mechanism studies, a feature set including internal resistance, temperature, and statistical characteristics of the voltage curve is constructed, and a neural network (NN) model is established for multi-stage variable-current fast-charging data. Finally, the above two models are integrated to achieve capacity prediction under complex and changeable realistic working conditions, and the relative error of the capacity estimation method is less than 0.8%. An aging experiment using the battery, which is the same as those equipped in the vehicles in the dataset, is carried out to verify the methods. To the best of the authors’ knowledge, our study is the first to verify a capacity estimation model derived from field data using an aging experiment of the same type of battery.