Step Size Research Articles

Exploring run-and-tumble movement in confined settings through simulation.

Motion in bounded domains is a fundamental concept in various fields, including billiard dynamics and random walks on finite lattices, and has important applications in physics, ecology, and biology. An important universal property related to the average return time to the boundary, the Mean Path Length Theorem (MPLT), has been proposed theoretically and experimentally confirmed in various contexts. We investigated a wide range of mechanisms that lead to deviations from this universal behavior, such as boundary effects, reorientation, and memory processes. This study investigates the dynamics of run-and-tumble particles within a confined two-dimensional circular domain. Through a combination of theoretical approaches and numerical simulations, we validate the MPLT under uniform and isotropic particle inflow conditions. This research demonstrates that although the MPLT is generally applicable for different step length distributions, deviations occur for non-uniform angular distributions, non-elastic boundary conditions, or memory processes. These results underline the crucial influence of boundary interactions and angular dynamics on the behavior of particles in confined spaces. Our results provide new insights into the geometry and dynamics of motion in confined spaces and contribute to a better understanding of a broad spectrum of phenomena ranging from the motion of bacteria to neutron transport. This type of analysis is crucial in situations where inhomogeneity occurs, such as multiple real-world scenarios within a limited domain.

Aero-optical effects of a hypersonic vehicle based on the refractive index step ray tracing method

The aero-optical effect caused by the high-speed flight of aircraft can affect the accuracy of astronomical navigation, so studying the laser transmission characteristics in high-speed flow fields is essential. This study adopts a 3D spherical blunt cone model as the physical aircraft model, incorporates the latest reanalysis data from the National Centers for Environmental Prediction as atmospheric parameters, and uses Fluent software to establish a hypersonic aircraft external flow field model. The ray tracing error is calculated using a method based on the refractive index step size. Results indicate that, under the conditions of flying altitude of 5 km and incident angle of 45°, the proposed ray tracing method has better accuracy than the traditional method. Compared with the Runge–Kutta method and the method based on geometric step size, the proposed ray tracing method reduces the error by 46.4% and 12.5%, respectively, at the flight Mach number of 5.

Deep Learning Algorithms for Addressing Overfitting and Biological Realism in Tree Taper and Volume Predictions

This study addresses the challenges of overfitting and maintaining biological realism in Deep Learning Algorithms (DLAs), for predicting individual tree taper using stem diameters outside bark (DOB) and total tree volume (TTV). To this end, DLAs were trained using two different approaches: a “hyperparameter-optimized DLA,” which customizes specific hyperparameters such as learning rate and momentum rate, and a “regularization-optimized DLA,” which incorporates optimization techniques like early stopping with Root Mean Square Error (RMSE), L1 and L2 regularization, and dropout. Although obtaining the deterioration in predictive capabilities statistics from the taring dataset to the validation dataset by standard DLA with adaptive learning processes without customizing the hyperparameters and regularization parameters, the hyperparameter-optimized DLA with a momentum of 0.8, and a 7 # hidden layer for the TTV and regularization-optimized DLA with a dropout ratio of 0.000001, a 3 # hidden layer for the DOB demonstrated comparable predictive capabilities statistics across both training and validation datasets with generating biologically plausible predictions. Our results support that these hyperparameter-optimized and regularization-optimized DLAs, by improving the "black-box" nature of artificial intelligence, offer significant potential for enhanced interpretability and performance by improving the problem of overfitting and the violations biological realism in forest biometrics applications.

Optimized deep maxout for crowd anomaly detection: A hybrid optimization-based model

ABSTRACT Monitoring Surveillance video is really time-consuming, and the complexity of typical crowd behaviour in crowded situations makes this even more challenging. This has sparked a curiosity about computer vision-based anomaly detection. This study introduces a new crowd anomaly detection method with two main steps: Visual Attention Detection and Anomaly Detection. The Visual Attention Detection phase uses an Enhanced Bilateral Texture-Based Methodology to pinpoint crucial areas in crowded scenes, improving anomaly detection precision. Next, the Anomaly Detection phase employs Optimized Deep Maxout Network to robustly identify unusual behaviours. This network’s deep learning capabilities are essential for detecting complex patterns in diverse crowd scenarios. To enhance accuracy, the model is trained using the innovative Battle Royale Coalesced Atom Search Optimization (BRCASO) algorithm, which fine-tunes optimal weights for superior performance, ensuring heightened detection accuracy and reliability. Lastly, using various performance metrics, the suggested work’s effectiveness will be contrasted with that of the other traditional approaches. The proposed crowd anomaly detection is implemented in Python. On observing the result showed that the suggested model attains a detection accuracy of 97.28% at a learning rate of 90%, which is much superior than the detection accuracy of other models, including ASO = 90.56%, BMO = 91.39%, BES = 88.63%, BRO = 86.98%, and FFLY = 89.59%.

Adaptive ray tracing in freeform gradient-index media using an index directional derivative

Freeform gradient index (F-GRIN) media are increasingly used in optical systems. The existing ray tracing methods for F-GRIN have low calculation efficiency and require manual adjustment of step size, making the design process complex. To address this, we propose an adaptive ray tracing (ART) method for F-GRIN. ART obtains an initial step size based on an index directional derivative and the element’s length. During the subsequent transmission process, the step size is adaptively adjusted. The accuracy and speed of ART were verified through multiple comparison tests. ART can reduce manual participation and significantly improve efficiency in the optical design of F-GRIN.

Two-step deep-learning identification of heel keypoints from video-recorded gait.

Accurate and fast extraction of step parameters from video recordings of gait allows for richer information to be obtained from clinical tests such as Timed Up and Go. Current deep-learning methods are promising, but lack in accuracy for many clinical use cases. Extracting step parameters will often depend on extracted landmarks (keypoints) on the feet. We hypothesize that such keypoints can be determined with an accuracy relevant for clinical practice from video recordings by combining an existing general-purpose pose estimation method (OpenPose) with custom convolutional neural networks (convnets) specifically trained to identify keypoints on the heel. The combined method finds keypoints on the posterior and lateral aspects of the heel of the foot in side-view and frontal-view images from which step length and step width can be determined for calibrated cameras. Six different candidate convnets were evaluated, combining three different standard architectures as networks for feature extraction (backbone), and with two different networks for predicting keypoints on the heel (head networks). Using transfer learning, the backbone networks were pre-trained on the ImageNet dataset, and the combined networks (backbone + head) were fine-tuned on data from 184 trials of older, unimpaired adults. The data was recorded at three different locations and consisted of 193 k side-view images and 110 k frontal-view images. We evaluated the six different models using the absolute distance on the floor between predicted keypoints and manually labelled keypoints. For the best-performing convnet, the median error was 0.55 cm and the 75% quartile was below 1.26 cm using data from the side-view camera. The predictions are overall accurate, but show some outliers. The results indicate potential for future clinical use by automating a key step in marker-less gait parameter extraction.

G-YOLO: A Lightweight Infrared Aerial Remote Sensing Target Detection Model for UAVs Based on YOLOv8

A lightweight infrared target detection model, G-YOLO, based on an unmanned aerial vehicle (UAV) is proposed to address the issues of low accuracy in target detection of UAV aerial images in complex ground scenarios and large network models that are difficult to apply to mobile or embedded platforms. Firstly, the YOLOv8 backbone feature extraction network is improved and designed based on the lightweight network, GhostBottleneckV2, and the remaining part of the backbone network adopts the depth-separable convolution, DWConv, to replace part of the standard convolution, which effectively retains the detection effect of the model while greatly reducing the number of model parameters and calculations. Secondly, the neck structure is improved by the ODConv module, which adopts an adaptive convolutional structure to adaptively adjust the convolutional kernel size and step size, which allows for more effective feature extraction and detection based on targets at different scales. At the same time, the neck structure is further optimized using the attention mechanism, SEAttention, to improve the model’s ability to learn global information of input feature maps, which is then applied to each channel of each feature map to enhance the useful information in a specific channel and improve the model’s detection performance. Finally, the introduction of the SlideLoss loss function enables the model to calculate the differences between predicted and actual truth bounding boxes during the training process, and adjust the model parameters based on these differences to improve the accuracy and efficiency of object detection. The experimental results show that compared with YOLOv8n, the G-YOLO reduces the missed and false detection rates of infrared small target detection in complex backgrounds. The number of model parameters is reduced by 74.2%, the number of computational floats is reduced by 54.3%, the FPS is improved by 71, which improves the detection efficiency of the model, and the average accuracy (mAP) reaches 91.4%, which verifies the validity of the model for UAV-based infrared small target detection. Furthermore, the FPS of the model reaches 556, and it will be suitable for wider and more complex detection task such as small targets, long-distance targets, and other complex scenes.

Damage Evaluation of Unconsolidated Sandstone Particle Migration Reservoir Based on Well–Seismic Combination

The primary factor constraining the performance of unconsolidated sandstone reservoirs is blockage from particle migration, which reduces the capacity of liquid production. By utilizing logging, seismic, core–testing, and oil–well production data, the reservoir damage induced by particle migration in the Bohai A oilfield was characterized and predicted through combined well–seismic methods. This research highlights the porosity, permeability, median grain diameter, and pore structure as the primary parameters influencing reservoir characteristics. Based on their permeability differences, reservoirs can be categorized into Type I (permeability ≥ 800 mD), Type II (400 mD < permeability < 800 mD), and Type III (permeability ≤ 400 mD). The results of the core displacement experiments revealed that, compared to their initial states, the permeability change rates for Type I and Type II reservoirs exceeded 50%, whereas the permeability change rate for Type III reservoirs surpassed 200%. Furthermore, by combining this quantitative relationship model with machine learning techniques and well–seismic methods, the distribution of permeability change rates caused by particle migration across the entire region was successfully predicted and validated against production data from three oil wells. In addition, to build a reliable deep learning model, a sensitivity analysis of the hyperparameters was conducted to determine the activation function, optimizer, learning rate, and neurons. This method enhances the prediction efficiency of reservoir permeability changes in offshore oilfields with limited coring data, providing important decision support for reservoir protection and field development.

Altered learning from positive feedback in adolescents with anorexia nervosa.

Anorexia nervosa (AN) is characterized by severe restriction of calorie intake, which persists despite serious medical and psychological sequelae of starvation. Several prior studies have identified impaired feedback learning among individuals with AN, but whether it reflects a disturbance in learning from positive feedback (i.e., reward), negative feedback (i.e., punishment), or both, and the extent to which this impairment is related to severity and duration of illness, has not been clarified. Participants were female adolescents with AN (n = 76) and healthy teen volunteers (HC; n = 38) between the ages of 12-18 years who completed a probabilistic reinforcement learning task. A Bayesian reinforcement learning model was used to calculate separate learning rates for positive and negative feedback. Exploratory analyses examined associations between feedback learning and duration of illness, eating disorder severity, and self/parent reports of reward and punishment sensitivity. Adolescents with AN had a significantly lower rate of learning from positive feedback relative to HC. Patients and HC did not differ in learning from negative feedback or on overall task performance measures. Feedback learning parameters were not significantly associated with duration of illness, eating disorder severity, or questionnaire-based reports of reward and punishment sensitivity. Adolescents with AN showed a circumscribed deficit in learning from reward that was not associated with duration of illness or reported sensitivity to reward or punishment. Subsequent longitudinal research should explore whether differences in learning from positive feedback relate to course of illness in youth with AN.

Integrating neural networks with advanced optimization techniques for accurate kidney disease diagnosis

Kidney diseases pose a significant global health challenge, requiring precise diagnostic tools to improve patient outcomes. This study addresses this need by investigating three main categories of renal diseases: kidney stones, cysts, and tumors. Utilizing a comprehensive dataset of 12,446 CT whole abdomen and urogram images, this study developed an advanced AI-driven diagnostic system specifically tailored for kidney disease classification. The innovative approach of this study combines the strengths of traditional convolutional neural network architecture (AlexNet) with modern advancements in ConvNeXt architectures. By integrating AlexNet’s robust feature extraction capabilities with ConvNeXt’s advanced attention mechanisms, the paper achieved an exceptional classification accuracy of 99.85%. A key advancement in this study’s methodology lies in the strategic amalgamation of features from both networks. This paper concatenated hierarchical spatial information and incorporated self-attention mechanisms to enhance classification performance. Furthermore, the study introduced a custom optimization technique inspired by the Adam optimizer, which dynamically adjusts the step size based on gradient norms. This tailored optimizer facilitated faster convergence and more effective weight updates, imporving model performance. The model of this study demonstrated outstanding performance across various metrics, with an average precision of 99.89%, recall of 99.95%, and specificity of 99.83%. These results highlight the efficacy of the hybrid architecture and optimization strategy in accurately diagnosing kidney diseases. Additionally, the methodology of this paper emphasizes interpretability and explainability, which are crucial for the clinical deployment of deep learning models.

A Modified Robust Homotopic Method for the Low-Thrust Fuel-Optimal Orbital Control Problem

This study focuses on improving the application of the quadratic penalty smoothing technique for solving the fuel-optimal problem of low-thrust trajectory. Some practical techniques, including the Particle Swarm Optimization algorithm (PSO), the co-state normalization technique, and the single shooting method, are employed. These approaches can enhance convergence to the globally optimal solution. The application of PSO is improved through the introduction of the diversity termination term. Furthermore, a new parameter, the maximum thrust to initial mass ratio (CTm), is introduced and analyzed. The relationships among Lagrange multipliers for different CTm in the energy-optimal auxiliary problem are also derived. These relationships can be used in scenarios with high CTm to reduce the variable search space, leading to a significant decrease in computation time. Nonetheless, few researchers have proposed a well-defined strategy for the homotopic process. We propose a robust iteration strategy, involving the determination of the maximum step size and the distinction of sub-optimal solutions. This iterative strategy could ensure a robust convergence toward the optimal solutions. An interplanetary rendezvous example is provided to demonstrate the effectiveness of the presented techniques and strategy.

An automatic simulation pipeline for coupled simulations of acoustic damping materials

AbstractFoamed materials are widely used to reduce noise due to their comparably good acoustic damping behavior. However, out of a large variety of these materials a suitable candidate has to be identified for each application. This is a challenging process that is typically guided by experiments and experience. While numerical simulations could support these experiments and reduce the effort to a great extent, no suitable discretization approach has yet been established that can fully capture the complex geometry of the foam. A fully resolved model is desirable in order to yield reliable predictions that can then be used to establish homogenized models. We established a monolithic coupling approach based on the finite cell method (FCM) that realizes a vibroacoustic simulation in this sense. The fluid and the structure domain are discretized by Cartesian grids and the geometry defined based on computed tomography scans is accounted for during the quadrature of the weak form. Our simulation in the time domain makes use of explicit time marching schemes and is therefore limited by a critical time step size. This is known to be arbitrarily low for discretizations with the FCM containing cells with arbitrarily small support. As a remedy against this we use the classical ‐stabilization technique and investigate its potentials and limitations.

On the adaptive solution of phase‐field problems with A‐stable explicit last‐stage diagonally implicit Runge–Kutta (ELDIRK) methods

AbstractRunge–Kutta algorithms with adaptive step size control provide reliable tools for the solution of initial value problems with diagonally implicit Runge‐Kutta (DIRK) methods as the most common approach. In this contribution, the new low‐order explicit last‐stage diagonally implicit Runge–Kutta (ELDIRK) methods are investigated, combining implicit schemes with an additional explicit evaluation as an explicit last stage. This results in Butcher tableaus with two solutions of different convergence orders suitable for embedded methods, where the higher‐order solution is achieved by additional explicit evaluations. Thus, the iterative solution of non‐linear systems is omitted for the additional stage, presenting a major reduction in computational cost for the determination of a local error estimate. The key contribution is the application of the novel Butcher tableaux to phase‐field problems, solved with the finite‐element method, leading to substantial numerical investigations with an efficient approach for DIRK schemes. The most important aspects are the investigations of stability properties which lead to the novel class of A‐stable ELDIRK methods. In accordance, the study of the convergence orders is presented. A local error estimator is presented, such that adaptive step size control for the new low‐order embedded schemes based on an empirical approach for error estimation is achieved. A suitable parallel algorithm is presented with conclusive two‐dimensional phase‐field simulations based on a Kobayashi‐Warren‐Carter model. The higher‐order convergence suggested by the novel schemes is confirmed, and their effective results are demonstrated, resulting in a valuable semi‐explicit addition to the family of Runge–Kutta time integration schemes.

Global convergence of Newton’s method for the regularized p-Stokes equations

AbstractThe motion of glaciers can be simulated with the $$\varvec{p}$$ p -Stokes equations. Up to now, Newton’s method to solve these equations has been analyzed in finite-dimensional settings only. We analyze the problem in infinite dimensions to gain a new viewpoint. We do that by proving global convergence of the infinite-dimensional Newton’s method with Armijo step sizes to the solution of these equations. We only have to add an arbitrarily small diffusion term for this convergence result. We prove that the additional diffusion term only causes minor differences in the solution compared to the original $$\varvec{p}$$ p -Stokes equations under the assumption of some regularity. Finally, we test our algorithms on two experiments: A reformulation of the experiment ISMIP-HOM $$\varvec{B}$$ B without sliding and a block with sliding. For the former, the approximation of exact step sizes for the Picard iteration and exact step sizes and Armijo step sizes for Newton’s method are superior in the experiment compared to the Picard iteration. For the latter experiment, Newton’s method with Armijo step sizes needs many iterations until it converges fast to the solution. Thus, Newton’s method with approximately exact step sizes is better than Armijo step sizes in this experiment.

YOLOv8-Based Drone Detection: Performance Analysis and Optimization

The extensive utilization of drones has led to numerous scenarios that encompass both advantageous and perilous outcomes. By using deep learning techniques, this study aimed to reduce the dangerous effects of drone use through early detection of drones. The purpose of this study is the evaluation of deep learning approaches such as pre-trained YOLOv8 drone detection for security issues. This study focuses on the YOLOv8 model to achieve optimal performance in object detection tasks using a publicly available dataset collected by Mehdi Özel for a UAV competition that is sourced from GitHub. These images are labeled using Roboflow, and the model is trained on Google Colab. YOLOv8, known for its advanced architecture, was selected due to its suitability for real-time detection applications and its ability to process complex visual data. Hyperparameter tuning and data augmentation techniques were applied to maximize the performance of the model. Basic hyperparameters such as learning rate, batch size, and optimization settings were optimized through iterative experiments to provide the best performance. In addition to hyperparameter tuning, various data augmentation strategies were used to increase the robustness and generalization ability of the model. Techniques such as rotation, scaling, flipping, and color adjustments were applied to the dataset to simulate different conditions and variations. Among the augmentation techniques applied to the specific dataset in this study, rotation was found to deliver the highest performance. Blurring and cropping methods were observed to follow closely behind. The combination of optimized hyperparameters and strategic data augmentation allowed YOLOv8 to achieve high detection accuracy and reliable performance on the publicly available dataset. This method demonstrates the effectiveness of YOLOv8 in real-world scenarios, while also highlighting the importance of hyperparameter tuning and data augmentation in increasing model capabilities. To enhance model performance, dataset augmentation techniques including rotation and blurring are implemented. Following these steps, a significant precision value of 0.946, a notable recall value of 0.9605, and a considerable precision–recall curve value of 0.978 are achieved, surpassing many popular models such as Mask CNN, CNN, and YOLOv5.

Molecular Classification with Graph ConvolutionalNetworks: Exploring the MUTAG Dataset for Mutagenicity Prediction

This paper presents the implementation of a Graph Convolutional Network (GCN) for the classification of chemical compounds using the MUTAG dataset, which consists of 188 ni- troaromatic compounds labeled according to their mutagenicity. The GCN model leverages the inherent graph structure of molec-ular data to capture and learn from the relationships between atoms and bonds, represented as nodes and edges, respectively. By utilizing three graph convolutional layers followed by a global mean pooling layer, the model effectively aggregates node features to generate meaningful graph-level representations. The model was trained using the Adam optimizer with a learning rate of 0.01, and cross-entropy loss was employed to supervise the classification task. The results demonstrate the efficacy of GCNs in graph classification tasks, with the model achieving a training accuracy of 79.33% and a test accuracy of 76.32%. This study highlights the potential of GCNs in cheminformatics and other domains where graph-structured data is prevalent, paving the way for further exploration and application of advanced graph neural networks in similar tasks.

Design and development of different adaptive MPPT controllers for renewable energy systems: a comprehensive analysis

As of now, all over the world is focusing on the Electric Vehicle (EV) technology because its features are low environmental pollution, less maitainence cost required, high robustness, and good dynamic response. Also, the EVs work continuously until the input fuel is provided to the fuel stack. Here, a Proton Exchange Membrane Fuel Cell (PEMFC) is used as an input source to the electric vehicle system because of its merits fast startup, and quick response. However, the PEMFC gives nonlinear voltage versus current characteristics. As a result, the extraction of maximum power from the fuel stack is very difficult. The main aim of this work is to study different Maximum Power Point Tracking Techniques (MPPT) for the DC-DC converter-fed PEMFC system. The studied MPPT controllers are Adjusted Step Value of Perturb & Observe (ASV with P&O), Adaptive Step Size with Incremental Conductance (ASS with IC), Radial Basis Functional Network (RBFN), Incremental Step-Fuzzy Logic Controller (IS with FLC), Continuous Step Variation based Particle Swarm Optimization (CSV with PSO), and Adaptive Step Value-Cuckoo Search Algorithm (ASV with CSA). The selected MPPT controllers’ comprehensive study has been in terms of maximum power extraction, tracking speed of the MPP, settling time of the fuel stack output voltage, oscillations across the MPP, and design complexity. From the comprehensive performance results of the hybrid MPPT controllers, the ASV with CSA technique gives superior performance when equated to the other MPPT controllers.

A novel systematically optimized tabular neural network (TabNet) algorithm for predicting the tensile modulus of additively manufactured PLA parts

Assessing the elastic modulus of 3D-printed polylactic acid (PLA) components is essential for understanding their stiffness and load capacity, which are crucial for predicting product performance and durability. In this study, the predictive accuracy of a Tabular Neural Network (TabNet) algorithm for determining the elastic modulus of 3D-printed PLA components via fused deposition modeling (FDM) was investigated. Utilizing a comprehensive dataset of 128 literature-sourced data points, divided into 80 % for training and 20 % for validation, the study proposed a new Taguchi-based method for efficient hyperparameter optimization of the TabNet algorithm. This optimization revealed that a configuration of 8 decision blocks, 16 attention blocks, and 5 decision steps, along with the "Adam" optimizer, a gamma of 1, learning rate of 0.1, and lambda-sparse of 0.01, yielded the highest prediction accuracy for the elastic modulus of PLA parts. The performance of the optimized TabNet model was evaluated using R-squared (R²), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) measures. The findings highlighted an R² of 96.855 %, an MAE of 0.158, an MSE of 0.037, and an RMSE of 0.193 in the validation dataset, demonstrating substantial predictive reliability. To further test the model’s robustness, fourteen unseen data points were analyzed. The observed discrepancies between predicted and actual values were under 10 %, affirming the Taguchi-optimized TabNet algorithm’s effectiveness in forecasting the elastic modulus of FDM 3D-printed PLA components. This investigation provides a significant advancement in additive manufacturing, introducing a precise and reliable method for predicting the mechanical properties of 3D-printed materials.

Gait Characteristics and Deviation Factors of Backward Walking in Patients With Chronic Ankle Instability.

Despite growing applications of backward walking (BW) in assessing and rehabilitating neuromuscular conditions, its effects on gait in chronic ankle instability (CAI) remain unclear. Moreover, linking patient-reported and clinically generated measures is imperative for understanding CAI. Patients with CAI will exhibit worse and compensatory spatio-temporal and kinetic gait parameters during BW, and patient-reported outcomes (PROs) will be correlated significantly with gait parameters. Case-control study. Level 4. A total of 46 volunteers participated (23 per group). Patients filled out scales for pain, functions, and fear-avoidance beliefs before testing. All participants walked 6 times each in both forward and backward conditions, and gait was recorded using the Win-Track system. A 2-way mixed analysis of variance was performed to compare gait parameters. The relationship between PRO and gait outcomes was assessed through the Pearson product correlation coefficient. The CAI group demonstrated prolonged support and swing phases, increased walk-off angle, and plantar pressure area, but decreased step length and plantar pressure versus controls (P < 0.05). The CAI group had a smaller right walk-off angle during BW than FW; the control group showed the opposite (P < 0.05). The left single stance duration was greater in the CAI group, while the right was not (P < 0.05). PRO correlated significantly with gait parameters, particularly spatial parameters (P < 0.05). The CAI group exhibited worse gait parameters during BW. The CAI group exhibited a characteristic compensatory gait pattern. Linking the self-reported scores provides a better representation of gait changes in CAI. These results suggest that BW may be an effective strategy for identifying and evaluating CAI. It may be feasible to apply BW to the rehabilitation of CAI.

Improved whale optimization algorithm towards precise state-of-charge estimation of lithium-ion batteries via optimizing LSTM

Accurate state-of-charge (SOC) estimation is a crucial part of the battery management system (BMS). However, conventional estimation methods are unable to capture the extremely complex dynamic characteristics of lithium-ion batteries. Besides, manually setting the optimal hyperparameters of models has many drawbacks. To address the problems, an (improved whale optimization algorithm) IWOA- (long short-term memory) LSTM model is proposed in this work. Utilizing the whale optimization algorithm (WOA) improved with four enhancement strategies (Gaussian chaotic mapping initialization, Nonlinear weight update, Lévy flight mechanism, and Elite opposition-based learning) to optimize the number of hidden layer nodes, the learning rate, and the number of iterations of LSTM model. It not only overcomes the shortcomings of artificially setting LSTM hyperparameters but also further boosts the learning ability of the IWOA-LSTM model, making the model more suitable for SOC estimation under different scenarios. The evaluation results show that the MAE of the proposed model for SOC estimation results is lower than 0.8 % under different temperatures and dynamic conditions. Compared with SOTA models, all MAE, RMSE, and MAPE of the proposed model substantially decline. Furthermore, the R2 of the estimation results using the LG dataset in Experiment Ⅲ is 98.65 %, suggesting the applicability of the proposed model to Li-ion batteries from various manufacturers. The experimental results demonstrate the proposed IWOA-LSTM model is suitable for accurate SOC estimation.