Introduction: Traditional forecasts of end-of-life vehicle (ELV) flows treat all cars as a single homogeneous stock, ignoring the emerging split between fuel vehicles and new-energy vehicles (NEVs). This omission becomes critical as NEV sales soar and their batteries enter the recycling stream. To address this gap, this research establishes a high-precision forecasting framework for the ELV volume of NEVs in China, tackling critical data scarcity and the lack of classified prediction between fuel and electric vehicles. By integrating sales-driven lifetime modeling with macroeconomic scenario sensitivity, the study develops and validates a NEV-oriented scrappage framework to improve prediction accuracy and provide a robust foundation for recycling research and national resource supply planning. Methods: Fuel-vehicle stock was benchmarked against NEV stock, historical NEV sales were fitted (exponential trend; R2=0.9876), and a Weibull failure-rate model was integrated with sales to estimate NEV retirements; additionally, quarterly ownership data were expanded using SMOTE, growth stabilization was characterized via a Grey Model, and a Gompertz curve was fitted to link per-capita vehicle ownership with GDP per capita to enable scenario-based dynamic scrappage forecasting. Results: Compared with the traditional Gompertz model, which often overlooks the distinct scrapping characteristics of NEVs, the proposed method reduces the forecasting bias. The integration of Weibull-based survival analysis enables the model to achieve a significant improvement in precision, with a low relative error of 8.999%. Incorporating SMOTE-enhanced ownership data, Grey- Model-identified stabilization periods, and a Gompertz ownership-GDP relationship improved data completeness and enabled dynamic scrappage predictions under different economic growth scenarios, offering stronger scenario adaptability than traditional approaches. Discussion: The findings provide a critical foundation for future recycling research. By enabling precise forecasting, the model significantly impacts the supply chain by stabilizing the supply of raw materials for the NEV industry and boosting metal resource efficiency. This approach directly catalyzes the transition from linear consumption models to a closed-loop circular economy. Ultimately, these contributions align with the broader strategic objectives of carbon neutrality and sustainable development, providing policymakers and industrial stakeholders with the quantitative support required to advance greener practices within the automotive sector. Conclusion: The proposed framework provides a validated and flexible methodology for forecasting NEV retirement volumes in China, supporting recycling research, stabilizing raw-material supply, and improving metal resource efficiency across the NEV supply chain; future work should refine classification by distinguishing between battery electric vehicles and plug-in hybrid electric vehicles to further enhance accuracy and policy relevance. For future research, vehicle categories should be refined by distinguishing between BEVs and PHEVs. Additionally, separate failure parameters should be developed for private and commercial vehicles to account for different usage intensities.
Introduction: This study aims to address the problems of low energy storage density and insufficient structural reliability in magnetic levitation flywheel rotors, which are critical for enhancing power grid stability and power supply quality in physical energy storage systems. Methods: To address the low energy storage density in magnetic-levitation flywheel rotors, a collaborative optimization method based on a PSO-GA two-layer hybrid strategy was proposed. This method uses the outer PSO to adaptively tune the hyperparameters of the inner GA, which performs size-feature optimization. The method takes the thickness and interlayer interference of the threelayer composite material as design variables, and the geometric size constraints, interference assembly requirements, and the Tsai-Hill strength failure criterion as constraints. The optimization model is constructed to maximize the energy storage density. Finally, the effectiveness of the optimization results was verified through finite element analysis and rotor dynamics simulation. Results: After 300 iterations of PSO-GA, the rotor energy storage density increased by 11.28% and the total energy output by 21.15%. At the rated speed of 38,000 rpm, both the maximum stress and the critical speed margin remained within safety limits. Discussion: These improvements validate the effectiveness of the hybrid algorithm for high-speed rotor design. The satisfaction of stress and critical speed constraints under rated conditions confirms reliability, offering a practical reference for future energy storage rotor optimization. Conclusion: This method provides a theoretical basis and engineering application data reference for the optimized design of high-efficiency flywheel energy storage.
Introduction: Wire Arc Additive Manufacturing is increasingly used for producing medium- and large-scale metallic components due to its high deposition rate and efficient material usage. Despite these advantages, achieving consistent bead geometry and defect-free deposition depends strongly on the selection of process parameters. The present study aims to examine and optimize key input parameters that affect the formation of a single-layer weld bead in the WAAM process. Methods: Single-layer weld beads were fabricated using SS316L stainless steel MIG filler wire. The main process variables considered were shielding gas flow rate, open-circuit voltage, and welding speed. The quality of the deposited bead was evaluated in terms of height-to-width ratio and microhardness. Experiments were designed using a Taguchi L9 (3⁴) orthogonal array, and the results were analyzed with Minitab 17 and ANOVA F-test to determine the influence of each parameter and identify suitable operating conditions. Results: The experimental results indicate that variations in SGFR, OCV, and WS have a noticeable effect on bead geometry and hardness. Certain parameter combinations resulted in improved bead shape with a more uniform height-to-width ratio, along with better hardness values. The analysis also highlighted the relative significance of each parameter in controlling the deposition characteristics. Discussion: The study shows that proper adjustment of process parameters is essential for maintaining bead stability and achieving desirable mechanical properties. The interaction between heat input and material deposition plays a key role in defining bead shape and hardness. The outcomes provide useful guidance for selecting process conditions in WAAM applications to improve build quality and consistency. Conclusion: The investigation demonstrates that optimizing the shielding gas flow rate, opencircuit voltage, and welding speed improves weld-bead characteristics in WAAM. The Taguchi method proved effective in identifying suitable parameter settings, supporting better control of the deposition process and enhancing overall performance.
Introduction: Lubrication failure restricts the service life of artificial joints, and surface texturing improves tribological performance by modulating surface micro-topography. This study aims to achieve precise fabrication of micro/nano-scale surface textures on artificial joint surfaces and to promote the enrichment of lubricating biomacromolecules within these regular textures to enhance lubrication performance. Methods: Nano-Fe3O4 particles were synthesized via co-precipitation coupled with hydrothermal treatment. These particles were dispersed into a photosensitive resin and subsequently cured under simultaneous magnetic field induction and UV irradiation. A 0.3 wt% chitosan aqueous solution was adopted as a lubricant for tribological tests. Results: The synthesized nano-Fe3O4 particles exhibited a uniform average diameter of 30 ± 5 nm. Under a magnetic field of 0.71 T and UV irradiation at 400 W/m2, the magnetically responsive photosensitive resin slurry containing 30 wt% nano-Fe3O4 formed ordered, chain-like micro-nano arrays aligned along the magnetic field direction. In contrast, slurries with 10 wt% and 20 wt% nano- Fe3O4 yielded only random particle dispersion. Tribological tests demonstrated that lubricant accumulation within the regular surface textures effectively reduced the average friction coefficient. Discussion: This methodology enables the precise fabrication of ordered micro- and nanostructured surface textures, thereby enhancing interfacial lubrication and offering a viable strategy to extend the service life of artificial joints. Conclusion: Magnetically assisted photopolymerization utilizing nano-Fe3O4 particles represents an effective approach for fabricating functional surface textures. The resulting micro-nano textures effectively reduce the friction coefficient and enrich lubricating biomacromolecules, thereby improving the tribological performance and service durability of artificial joints.
Introduction: By using the latest patents and technology progress in maritime hydrodynamics, this research aims to improve the maneuvering ability of an Unmanned Surface Vehicle (USV) through the method of carrying out systematic optimization on rudder configuration parameters. Methods: Numerical simulation works were carried out via Unsteady Reynolds-Averaged Navier– Stokes (URANS) equations coupled with shear transport k-ω turbulence model, which was implemented through Computational Fluid Dynamics (CFD) software STAR-CCM+ 2310. Results: The main parameters: horizontal position, vertical position, aspect ratio, and area were optimized, which led to a decrease in the turning radius by 21.2% with an insignificant effect on propulsive performance. Discussion: Such results prove that the specified parameter optimization of the rudders may enhance the level of steering greatly without resorting to deteriorating propulsion efficiency. Conclusion: The rudder design optimization proposed methodology is a transferable and robust proposal applicable to the USV and could be extrapolated and applied to other marine systems.
introduction: Mechanical gears face contact issues; magnetic gears offer a solution, but research on axially coupled permanent magnet planetary gears, especially regarding key parameter matching, is insufficient. materials and methods: A 2K-H type mechanism was designed with NdFeB magnets, followed by parametric design and 3D electromagnetic simulations (FEMM, Ansoft Maxwell). results: Magnetic force and torque are proportional to tooth dimensions but inversely proportional to the air gap; optimal transmission performance requires a 4:4:2:1 ratio of tooth height, width, thickness, and working air gap. discussion: To design and analyze a novel axially coupled permanent magnet planetary gear, optimizing its transmission performance by evaluating the impact of key structural parameters. conclusion: The proposed design achieves non-contact, low-noise transmission and offers a validated parametric method and optimal ratio for specialized applications.
Introduction/Objective: This study aims to develop a learning-based framework that enables autonomous path planning and continuous control for multiple interacting vehicles in unstructured environments. In unstructured scenarios that lack lane markings and right-of-way constraints and exhibit irregular geometry, existing learning-based planners struggle to achieve safety, efficiency, and real-time performance simultaneously. They also fail to adequately characterize nonlinear edge interactions. To address this gap, this paper proposes the Graph Learning Planning and Control Framework (TEKM), geared towards engineering implementation and patent-related applications, aiming to achieve a robust trade-off between safety and efficiency. Method: This approach explicitly models the relationships between multiple agents and obstacles using a graph structure: TransformerConv captures global dependencies, while EdgeConv encodes local geometry. Learnable B-splines are introduced during the message passing phase to transfer nonlinearity from nodes to edges, enhancing expressiveness and interpretability. The decoder employs a dual-branch architecture, outputting Q and V from the attention mechanism, respectively, used to construct interaction weights and global aggregation representations. Supervision signals are generated by MPCs satisfying feasible constraints. Training utilizes a segmented, stepped learning rate and reweighting of difficult samples, with non-leaking partitioning and multi-random seed verification based on map and scenario conditions. Results: Under the unified protocol, TEKM exhibits faster convergence and lower steady-state loss compared to learning-based and classical baselines, achieving higher task success rates and lower collision rates in multi-scenario evaluations. Inference latency shows linearly controllable scalability with increasing agent and obstacle numbers. Sensitivity analysis reveals that the prediction step size is most sensitive to stability, and piecewise stepped learning rates significantly reduce dependence on the initial learning rate. Discussion: Moving the learnable splines forward to the interaction edges enhances the expressiveness and interpretability of unit parameters. Combined with safety-focused loss weights and backoff mechanisms such as speed and curvature tightening, robustness is maintained in high-density scenarios. Current work does not explicitly incorporate surface material and slope modeling, falling within the scope of method-level validation. Conclusion: TEKM unifies global attention and edge-level nonlinearity, achieving safety-priority and real-time planning and control in unstructured environments, demonstrating patent-related engineering deployment potential. Future work will introduce surface parameters such as material and slope, and extend to 2.5D and 3D terrain for broader cross-domain validation.
Introduction: To address the severe sample imbalance problem in rolling bearing fault diagnosis, where normal samples are abundant while fault samples are scarce, this study proposes an intelligent diagnostic method based on simulation–experimental data fusion to enhance diagnostic accuracy under small-sample conditions. Materials and Methods: A multi-source bearing dataset is constructed by fusing high-fidelity simulated vibration signals from a dynamic fault model with experimental data. To enhance feature extraction, a Particle Swarm Optimization-based adaptive Variational Mode Decomposition (PSO-VMD) method is developed to automatically optimize key parameters. To reduce distribution discrepancies between simulated and experimental data, a sample entropy-based cross-domain alignment strategy is introduced. The method is validated on the Case Western Reserve University bearing dataset. Results: Experimental results indicate that the proposed method achieves a diagnostic accuracy of 98.58%, representing a 7.53% improvement over using experimental data alone, along with superior numerical stability. Discussion: The method demonstrates superior robustness and numerical stability across different fault categories and small-sample scenarios. Although the quantitative results are obtained from a specific benchmark dataset, the proposed framework is not limited to a particular bearing type. By adjusting simulation parameters such as bearing geometry, rotational speed, and load conditions, the method can be extended to other bearing systems without altering the overall diagnostic framework. Conclusion: The results confirm that simulation–experimental data fusion combined with PSOVMD feature extraction and entropy-based cross-domain alignment provides an effective solution to small-sample and data imbalance challenges in rolling bearing fault diagnosis. The proposed method offers high diagnostic accuracy and strong industrial applicability, and has entered the stage of formal patent protection.
IntroductionHelical gears are essential components in high-speed transmission systems, in which meshing power loss arising from friction, viscous shear, and thermal effects substantially compromises transmission efficiency and operational reliability. This study develops a simplified, physics-based method to predict the meshing power loss of helical gear pairs. MethodsA novel simplified calculation method is proposed by reducing a conventional two-dimensional finite line-contact elastohydrodynamic lubrication (EHL) model into a onedimensional formulation through axial slicing. The model integrates EHL theory, numerical iterative computation, and physical mechanisms related to oil-film shear, viscous dissipation, and toothsurface friction. Gear kinematics, thermal-coupled film properties, instantaneous engaged-tooth number, load distribution, and the pinion helix angle are simultaneously incorporated. ResultsThe method was applied to the first-stage helical gear set of a high-speed electric vehicle reducer. The results capture the transient meshing power loss associated with both single-tooth pair meshing and multi-tooth pair interactions. The predicted power loss trends align with the physical evolution of contact load and sliding ratios along the mesh. DiscussionCompared with traditional high-dimensional EHL models, the proposed approach significantly reduces computational effort while maintaining sufficient accuracy for engineering applications. Its ability to describe the dynamic characteristics of meshing loss provides valuable insight into the efficiency behavior of the high-speed helical gears cycle. Conclusion: The proposed simplified model offers a practical and efficient tool for predicting meshing power loss in helical gear transmissions, supporting the design and optimization of highefficiency gear systems used in electric vehicle drivetrains and other high-speed applications, as well as potential patents.
Introduction: Optimization of DLP (digital light processing) printing parameters to improve the long-term durability of fabricated orthodontic retainers is essential for enhancing oral health, reducing waste, and promoting sustainable manufacturing practices, thereby contributing to the UN Sustainable Development Goals. However, depending on the printing parameters used, the mechanical properties of printed retainers can vary significantly. Methods: Twelve specimens fabricated using the combination of optimal parameters for enhanced mechanical performance were used as the basis for the multi-objective optimization approach of the current study. Several mechanical tests, including compressive strength and surface roughness, were performed to assess the mechanical properties of printed retainer materials. Different combinations of printing parameters were analyzed statistically to determine the significance of the observed disparities. Results: The optimized parameters (e.g., layer height: X microns, orientation angle: Y degrees, curing time: Z minutes) resulted in an [X%] increase in compressive strength and a [Y%] reduction in surface roughness compared to baseline/unoptimized conditions. Experimental validation of the predicted results showed minor error percentages, with optimized results at a layer height of 90.1185, orientation angle of 89.9987, and curing time of 99.9921, yielding a compressive strength of 293.6757 and surface roughness of 0.28838. Discussion: The optimized DLP printing parameters significantly improved the mechanical strength and surface finish of orthodontic retainers, indicating enhanced durability, reduced material defects, and better clinical reliability. Future studies may explore a broader range of material types and parameter variations. Conclusion: The results of the present study can be used by orthodontic professionals and manufacturers to enhance the mechanical properties of printed retainers, optimize the printing process, and improve the long-term performance of patented orthodontic retainers. conclusion: The findings provide a basis for orthodontic professionals and manufacturers to optimize the DLP printing process, leading to improved mechanical properties and long-term performance of orthodontic retainers, contributing to enhanced oral health and sustainable manufacturing.
Introduction: In the process of manufacturing and installation of a high-speed motorized spindle, due to the uneven mass distribution of the rotor system, the dynamic balance often fails. In order to study the influence of unbalanced mass on the temperature of motorized spindle during operation, the spindle was changed into an unbalanced state by adjusting the counterweight block on the dynamic balance ring. The temperature of front bearing and rear bearing was tested, and the relationship between unbalanced mass and temperature was analyzed. Then, based on the experimental data, a CNN-BiGRU-Attention temperature prediction model was proposed and compared with the CNN-BiGRU model. The results show that the prediction errors are significantly reduced, which significantly improves the prediction performance and verifies the accuracy of the model in the temperature monitoring of motorized spindle. The proposed CNN-BiGRU-Attention model and its optimization strategy offer potential for patent application due to their novelty and effectiveness in enhancing the thermal monitoring and early warning capabilities of high-speed motorized spindles. Uneven mass distribution in high-speed motorized spindles causes dynamic imbalance, leading to abnormal vibration and a rise in temperature that compromises machining accuracy. This study aims to design a temperature prediction model for motorized spindles under unbalanced states, capable of accurately forecasting temperature trends and providing early warnings to prevent thermal faults. Methods: A CNN-BiGRU-Attention model integrates spatial feature extraction, bidirectional temporal learning, and attention-based feature weighting. It was trained on temperature data from front and rear bearings under four unbalanced mass conditions. Results: The proposed model achieves a superior prediction performance compared to the CNNBiGRU baseline. It effectively captures temperature fluctuations and steady-state behavior under various unbalanced states, demonstrating strong adaptability and prediction accuracy. Discussion: The proposed model effectively captures complex thermal dynamics through its multicomponent architecture, demonstrating strong potential for predictive maintenance in highprecision manufacturing. conclusion: It shows that the established CNN-BiGRU-Attention temperature prediction model can be used to predict the temperature trend of high-speed motorized spindle. Conclusion: The CNN-BiGRU-Attention model provides a reliable and efficient solution for temperature prediction in unbalanced motorized spindles. This method offers a valuable reference and a practical tool for the intelligent monitoring and thermal safety management of high-speed precision equipment, contributing significantly to the advancement of predictive maintenance in smart manufacturing.
Introduction: The paddle-wheel propeller has the ability to resist winding and adapt to a shallow water environment. It is widely used in inland and wetland ships. As the core factor of generating thrust, blade geometry has a critical impact on hydrodynamic performance. However, recent patents and studies have shown that the systematic comparison of blade geometry is still limited. In this study, the thrust performance of representative blade types was evaluated quantitatively to determine the optimal design. Methods: Four parametric blade models (including a traditional flat blade) were simulated by transient CFD. The Realizable k–ε turbulence model was combined with the VOF multiphase approach to resolve the air–water interaction. The interaction between rotating speed (60-350 rpm) and blade geometry is studied under strict cylindrical space constraints. Results: With the increase of rotating speed, the thrust of all blades increased, but at the same time, the stability decreased, and there was an obvious peak value. At the same speed, the wave blade produced the highest thrust and efficiency, with peak thrust 10.7% higher and efficiency 5.9% greater than the flat blade. The backward-curved and straight blades showed moderate performance, whereas the radial blade generated the lowest thrust. The high-speed rotating Curved blade enhances the splash effect. Water lift is related to efficiency, but it is not the only factor. Discussion: The computational fluid dynamics analysis of the system confirms that the corrugated blade has better thrust performance. The thrust and efficiency of wavy blades are higher than those of straight, backward curved, and radially curved blades. Conclusion: The results reveal the key interaction between speed and blade geometry, and provide practical guidance for the selection and optimization of paddle wheels. The method used is simple and effective, and has strong engineering relevance.
Introduction: Buckling is recognized as a paramount form of instability failure in chemical process equipment, making its prevention a central subject of ongoing investigation. This patent provides a detailed analysis of the revised buckling collapse prevention methodology in the 2025 edition of the ASME Section VIII, Division 2 Code. Methods: A detailed comparative analysis was conducted between the new code and earlier versions. The application of the new assessment procedure was illustrated through engineering examples using general finite element software, with demonstrations provided for key operational steps. Results: The main revisions identified include: the consolidation of analysis methods from three to two; a shift in the evaluation index from critical load to critical membrane stress; more stringent requirements for defining initial geometric imperfections; a reduction of the buckling load factor in the elastic-plastic method to 1.67; and the introduction of a new method for evaluating protection against creep buckling. Discussion: The core of this revision is to facilitate a shift in pressure vessel design and analysis from relatively conservative empirical methods toward a more precise, physics-based digital analysis paradigm. By integrating load combinations, clarifying geometric imperfection, and promoting an elastic-plastic analysis method with broader applicability, the new specification effectively mitigates the subjectivity and conservatism inherent in the design process. Conclusion: The 2025 revisions to the ASME VIII-2 Code enhance the precision, practicality, and economic efficiency of buckling design for pressure equipment. The updated methods provide a more rigorous and comprehensive framework for preventing buckling collapse, representing a significant advancement in the field.
Introduction: To solve the problems of poor air quality and high energy consumption in subway stations caused by factors such as confined spaces and large crowds, the decision on which ventilation mode to activate during different seasons is currently made entirely manually based on experience. This approach has led to increased energy consumption without significant improvements in environmental indicators. Methods: This paper focuses on the airflow field in the public areas of island-platform subway stations and adopts a research method combining theoretical analysis, experimental research, and numerical simulation. Results: The numerical simulation results reveal that, under the simulated autumn conditions, the relative humidity at the station hall and platform levels is approximately 75% and 79%, respectively, indicating excessively high relative humidity. By comparing the simulation results with actual measurements from subway stations, the overall error is small, demonstrating the accuracy of the simulation. Discussion: To address excessive relative humidity while reducing energy consumption, this paper proposes reducing the chilled water load on the air-conditioning units' chilled water systems to lower the moisture content of the supplied air. Conclusion: The simulation results show that the relative humidity at the station hall and platform levels decreased by 16.4% and 16.7%, respectively. This improved solution not only enhances comfort but also reduces energy consumptio
In the originally published article titled “Optimization Design of the Luffing Mechanism of Truck Crane Based on NSGA-II”, published in “Recent Patents on Mechanical Engineering”, Vol: 18, Issue: 1, 2025 [1], a particular phrase was unclear, which may have affected readability. This has now been revised to improve clarity and ensure that the intended meaning is accurately conveyed. The corrections do not affect the results, interpretations, or conclusions of the article. The original article can be found online at: https://www.eurekaselect.com/article/139900. Details of the error and its correction are provided here. ORIGINAL: The optimization model of the luffing mechanism is established, and the optimization solution is completed by multi-objective genetic calculation. CORRECTED: The optimization model of the luffing mechanism is established, and the optimization solution is completed by multi-objective genetic algorithm.
In recent years, accurately predicting building energy consumption has gained significant momentum to support decarbonization and efficient energy management. However, traditional machine learning methods depend largely on historical data for training and work best with accessible data. Currently, forecasting energy demand for new buildings is challenging due to limited consumption data. To overcome this challenge, this study explores the use of deep transfer learning techniques to predict energy usage in buildings with limited historical data. The research uses a structured experimental method, combining baseline models with advanced deep learning techniques. A benchmark dataset with real-time, appliance-level energy consumption data was utilized to develop the model. An Artificial Neural Network (ANN) was initially developed as a baseline predictor for the energy use of the targeted building. A deep transfer learning framework was then introduced, employing Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models. The pre-trained base model was developed and fine-tuned, enabling knowledge transfer from a data-rich source domain to the targeted domain. Experimental results demonstrate that the deep transfer learning method surpasses standalone LSTM and GRU models, achieving the lowest Root Mean Square Error (RMSE) of 0.859061 and decreasing training time by about 1.18406 seconds. These findings demonstrate the effectiveness of deep transfer learning in overcoming data scarcity. This method offers a patentable and sustainable approach to enhancing energy efficiency strategies in real-world building applications. Deep transfer learning offers an effective way to predict building energy consumption with limited historical data, supporting efficient energy management.
IntroductionPosture control is critical for wheel-legged hybrid robots to improve adaptability and motion stability in unstructured terrains. Recent patents in this field provide important references for this study. MethodsWe establish a kinematic model for posture adjustment considering terrain variations. Leveraging the serial-chain structure of the wheel-leg system, we employ an improved Denavit-Hartenberg (D-H) method to develop single-leg and whole-body kinematic models. Wheel-ground contact force data is processed using first-order low-pass filtering, and a variable-damping admittance control algorithm is designed for leg motion. Additionally, a centroid height control algorithm and a wheel control strategy are proposed to assist in constraining leg states. ResultsComparative simulation experiments demonstrate that the proposed control strategy effectively tracks desired body postures, maintains constant wheel-ground contact forces, and stabilizes centroid height. This significantly improves the robot's adaptability and motion stability in unstructured terrains. DiscussionThe multi-modal cooperative control strategy integrates posture feedback, force tracking, height stabilization, and wheel-driven assistance, overcoming the limitations of traditional decoupled control methods. The simulation results validate its robustness in complex terrains. ConclusionThe developed multi-modal cooperative control strategy enables precise posture control for wheel-legged robots, thereby enhancing their performance in challenging environments through the integration of kinematic modeling, admittance control, and wheel-leg coordination.
IntroductionTo improve the maintenance efficiency and reliability of missile systems under complex combat conditions, this study proposes a novel modeling framework integrating swarm intelligence optimization and ensemble learning to address high-dimensional nonlinear prediction in missile health management. The approach improves prediction accuracy, reduces maintenance costs, and supports lifecycle management, offering significant engineering value and defense applications. MethodsThis study proposes a hybrid prediction model that integrates Particle Swarm Optimization (PSO) with the Random Forest (RF) algorithm. PSO is used to optimize key hyperparameters of the RF model to enhance its generalization ability and prediction accuracy. ResultsThe performance of the proposed PSO-RF model is compared with Radial Basis Function (RBF) neural networks and Back Propagation (BP) neural networks. Experimental results demonstrate that the PSO-RF model outperforms the other models, achieving an average error percentage of 1.63% and a Root Mean Square Error (RMSE) of 0.0128. DiscussionThe technical scheme has become a core part of a patent application and a software copyright registration, demonstrating its originality, software implementation capability, and potential for engineering application. ConclusionThe model effectively identifies potential failure risks, providing accurate and reliable decision support for the preventive maintenance of missile systems.
Automatic parking system plays a key role in the field of intelligent driving. The automatic parking system primarily consists of three modules: environment sensing, path planning, and tracking control. Among these modules, the key component of environment sensing is parking space detection. The article reviews the three main technologies of automatic parking systems, provides a relatively comprehensive overview of their development, and categorizes the technologies as follows: space detection methods are divided into vision-based and non-visual detection methods; path planning technologies are classified into geometry-based, map search-based, random sampling-based, and artificial intelligence-based approaches; and tracking control technologies are categorized into parking path-based and artificial intelligence control methods. Existing research on each technology is compared and analyzed to provide a more comprehensive overview of the current advancements in parking space detection, path planning, and tracking control. Finally, the research prospects for automatic parking technology are proposed, offering a valuable reference for researchers in the field of autonomous driving.
