Engineering Reports

An electrochemical/thermodynamic analytical model for hard-pack lithium-ion batteries is proposed. The highly nonlinear dynamic model is discretized into a series of static problems, which are solved using the Levenberg-Marquardt algorithm. The efficient and compact MATLAB code is provided as an instructional tool for engineering education.

The Flow chart represents a model for the selection of optimized diagnostic approach for cardio vascular diseases. This novel model follows the concept of computational process incorporated with novel aggregation operators that are more flexible in nature.

The graphical abstract illustrates an in-depth discussion of ICN features, architectures, and naming schemes. It presents the categories of caching, followed by an examination of existing caching strategies, and explores the role of caching in diverse applications, including IoT, IoV, mobility, edge computing, and fog computing. It also conducts a comparative analysis with existing surveys, while Section 7 presents recent research advances on key ICN performance indicators.

Machine learning–based solar power generation monitoring.

This study proposes SB-YOLO-V8, an enhanced YOLO-based CNN model optimized with SMOTE and Binary ALO, for efficient real-time human detection in agricultural settings. SB-YOLO-V8 obtains better performance in precision, speed, and efficiency. This significantly outperforms previous YOLO versions, making it well-suited for challenging visual scenarios in farming environments.

A comparative analysis of traditional and ensemble machine learning models with advanced feature selection to detect polycystic ovary syndrome.

By introducing CA attention, GSConv and NWD Loss, the improved YOLOv5s achieves PCB defect detection accuracies of 0.970 and 0.991 on the PCB_DATASET and DeepPCB data sets, respectively. The detection accuracy is improved by 1.1% and 2.2%, respectively, compared to YOLOv5s.

Due to the FCM module in the IGRU-FCM model performing optimization operations on the offspring in the population, the population fitness reached a convergence state around the 400 generation, while the Copula model only began to converge in the 2000 generation. From this, the fitness of the optimal individual in the IGRU-FCM model was 0.82, which had better compatibility for different credit data analyses. In (b), the ROC value of the IGRU-FCM model was 0.99, which was 12.50% higher than the Logistic algorithm and simpler to calculate. From this, the IGRU-FCM model can accurately classify various data in credit, making it more accurate in assessing risks. In addition to performance evaluation metrics such as accuracy, computation time is also a critical index for measuring algorithm effectiveness.

This paper proposes a deep aggregation seq2seq network with time feature fusion for air pollutant concentration prediction, which integrates temporal feature encoding with historical air pollutant concentration data through a cross attention network, and then excavates hidden features through deep aggregation seq2seq network.

In this paper, the carbon emission flow factor is used to accurately guide the demand response of electric vehicles on load side, and then the system is optimized and adjusted. The results show that EV participation in system interaction can reduce the overall carbon emission level.

A novel computational model is developed to analyze the evolution of tumor tissue, incorporating drug resistance and the convective mass flux of tumor cell movement for a more realistic representation of tumor dynamics. Key findings: Higher initial nutrient concentrations promote tumor growth, highlighting the importance of monitoring and managing nutrient levels in patients. The relationship between drug concentration and cell death is nonlinear, suggesting that there might be an optimal drug concentration range to maximize efficacy. These insights offer valuable guidance for optimizing drug delivery and designing effective tumor control strategies. Conclusion: This study contributes to a deeper understanding of tumor growth and the development of more effective cancer treatments to improve patient outcomes. The proposed model serves as a valuable tool for researchers and clinicians to explore different treatment regimens and predict patient responses to therapy.

This study optimizes basalt/glass fiber composites with hybrid MWCNT/SiO₂ nanofillers. Key factors—filler weight, pressure, and sonication—are analyzed via RSM. A tensile strength of 267 MPa is achieved with 1% filler, 15 MPa, and 30 min sonication. SEM analysis confirms enhanced bonding, validating accurate predictive models.

A random pore model based on product island growth theory and its application to redox reactions of iron ore oxygen carriers in chemical looping.

This research introduces two conjugate gradient methods, BIV1 and BIV2, designed to enhance the efficiency and performance of unconstrained optimization problems with only first derivative vectors. The study explores the derivation of new conjugate gradient parameters and investigates their practical performance. The proposed BIV1 and BIV2 methods are tested on a variety of test problems sourced from the CUTE library and other unconstrained problem collections. Key performance metrics, including the number of iterations, function evaluations, and CPU time, demonstrate that both BIV1 and BIV2 methods offer superior efficiency and effectiveness compared to the HS method. Furthermore, the effectiveness of these methods is illustrated in the context of training artificial neural networks and achieve competitive performance in terms of convergence rate and accuracy, especially in the context of solving complex optimization tasks.

To solve the problems of visual information misjudgment caused by closed orchard branches and leaves, as well as the delayed obstacle avoidance of robots caused by complex working terrain, a wheeled plant protection robot operation trajectory optimization method, which is based on the improved dynamic window algorithm integrating ant colony algorithm (ACO-DWA) algorithm is proposed. Combined with the kinematic model and job specification constraints of the plant protection robot, a series of candidate trajectory sets are generated using the model based prediction algorithm (SBMPO). Using the improved ACO-DWA algorithm, the robot's travel cost is integrated into the objective function of the search node, and the path planning is carried out online based on the environmental map.

The study aimed to establish the adoption status, drivers, and barriers for Lean Manufacturing for various sizes of manufacturing industries. The study has revealed that adoption status increases with the increase in the size of the industry. Furthermore, drivers and barriers vary based on the size of the manufacturing industry.As the level of the industry changes, from micro to large, drivers and barriers also change.

This paper investigates the fixed-time synchronization of fuzzy memristive neural networks via developing a new fixed-time stability theorem that provides more accurate settling time estimation. By designing a new saturation function based control scheme, some new sufficient conditions are obtained to ensure the fixed-time synchronization of considered systems.

Design of a three-channel power divider using integrated waveguide technology in the substrate. Phase curve of scattering parameters and comparison of simulation and measurement result for three modes: (A) without metal post, (B) three-channel with two posts metallic.

Aiming at the practical situation of new energy power system which contains a large amount of measurement data and variable operation status, a false data injection attack localization detection method based on associative feature-multi-label cascade augmented forest is proposed with higher accuracy, detection rate, and sensitivity.