Parameter Optimization Method Research Articles

Parameter Optimization Method for Metal Surface pBRDF Model Based on Improved Strawberry Algorithm

To study the polarization reflection characteristics of metal surfaces, a parameter optimization method for the polarization bidirectional reflection distribution function (pBRDF) model of metal surfaces based on the improved strawberry algorithm has been proposed. Firstly, the light scattering characteristics of metal surfaces were analyzed and a multi-parameter pBRDF model was constructed. Then, the working mechanism of the strawberry optimization algorithm was investigated and improved by introducing the chaotic mapping and Levy flight strategy to overcome the shortcomings, such as low convergence rate and easily falling into local optimum. Finally, the method proposed in this paper was validated by simulating open-source data from references and the obtained ones with a self-built experimental platform. The results show that the proposed method outperforms those by nonlinear least squares, particle swarm optimization and the original strawberry algorithm in fitting the detected degree of polarization (DOP) data, indicating the modeling accuracy was significantly improved and better suited to characterize the polarized reflection properties of metal surfaces.

On the Parameter Calibration Method for Dual-Spectral Triocular Camera

The dual-spectrum triocular camera system composed of a binocular visible light camera and mid-infrared camera is used for high-precision thermal fault detection and thermal field reconstruction of industrial equipment. The realization of its function depends on the high-precision camera parameter calibration. The difficulty lies in how to realize the infrared camera calibration quickly and improve the parameter accuracy of multi-lens camera. In this paper, according to the characteristics of the dual-spectral triocular camera system, the theoretical model is constructed, and the circular asymmetric calibration plate under infrared supplementary light is selected as the calibration object through experiments. A method for combining infrared image adaptive histogram enhancement and binarization processing based on the Sauvola algorithm is proposed to effectively calibrate the infrared camera. A global parameter optimization method based on traditional passive vision binocular stereo calibration is proposed. The optimization of experimental parameters finds the reprojection error value is 0.16, which meets the demand of high-precision calibration and solves the problem of difficult-to-calibrate weak image texture of infrared camera and the calibration accuracy of the camera under different imaging capabilities.

Broad learning system based on maximum multi-kernel correntropy criterion

The broad learning system (BLS) is an effective machine learning model that exhibits excellent feature extraction ability and fast training speed. However, the traditional BLS is derived from the minimum mean square error (MMSE) criterion, which is highly sensitive to non-Gaussian noise. In order to enhance the robustness of BLS, this paper reconstructs the objective function of BLS based on the maximum multi-kernel correntropy criterion (MMKCC), and obtains a new robust variant of BLS (MKC-BLS). For the multitude of parameters involved in MMKCC, an effective parameter optimization method is presented. The fixed-point iteration method is employed to further optimize the model, and a reliable convergence proof is provided. In comparison to the existing robust variants of BLS, MKC-BLS exhibits superior performance in the non-Gaussian noise environment, particularly in the multi-modal noise environment. Experiments on multiple public datasets and real application validate the efficacy of the proposed method.

Application of the Taguchi method and RSM for process parameter optimization in AWSJ machining of CFRP composite-based orthopedic implants

Abstract Abrasive water suspension jet (AWSJ) machining on carbon fiber-reinforced polymer (CFRP) composite-based orthopedic implants yielded insightful results based on experimental data and subsequent statistical validations. Underwater AWSJ cutting consistently outperformed free air cutting, with numerical findings demonstrating its superiority. For instance, at #100 abrasive size and 5 mm standoff distance (SOD), the material removal rate (MRR) peaked at 2.44 g/min with a kerf width of 0.89 mm and a surface roughness (SR) of 9.25 µm. Notably, the increase in abrasive size correlated with higher MRR values, such as achieving 2.15 g/min at #120 grit and 3 mm SOD. Furthermore, optimization techniques like the Taguchi method and response surface methodology (RSM) were applied to refine machining parameters. These methodologies enhanced MRR, exemplified by achieving 2.10 g/min with #120 abrasive size and 5 mm SOD in underwater cutting conditions. The research explored the impact of key process parameters, namely, the speed, feed, and SOD on the MRR, kerf width, and SR in both free air cutting and underwater cutting conditions, which is one of the novel research endeavors in the domain of abrasive jet machining of composites.

Coil Parameter Optimization Method for Wireless Power Transfer System Based on Crowding Distance Division and Adaptive Genetic Operators

In a Magnetically Coupled Resonant Wireless Power Transfer (MCR-WPT) system, the magnetic coupling coil is one of the key factors that determines the system’s output power, transmission efficiency, anti-offset capability, and so on. This article proposes a coil parameter optimization method for a wireless power transfer system based on crowding distance division and adaptive genetic operators. Through optimizing the design of decision variables, such as the numbers of transmitting and receiving coil turns, the spacings between transmitting and receiving coil turns, the inner radii of the transmitting and receiving coils, and the vertical distance of the coil, the best transmission performance can be achieved. This study improves the NSGA-II algorithm through proposing a genetic operator algorithm for average crowding and high crowding populations based on adaptive operators, as well as a genetic operator algorithm for low crowding populations based on information entropy. These improved algorithms avoid problems inherent to traditional genetic operators such as fixed genetic proportions, do not easily cause the algorithm to fall into a local optimal solution, and show better convergence in the ZDT1–ZDT3 test functions. The optimization design method in this article is not only independent of commercial software such as ANSYS Maxwell 2021 R1, but can also significantly improve the calculation speed compared with traditional simulation software.

Development of a new environmentally friendly and efficient centrifugal variable diameter metering device.

The design of the maize metering device involves centrifugal variable diameter pneumatic and cleaning mechanisms, aiming to enhance the performance and power efficiency of pneumatic maize metering devices. Leveraging the impact of changes in centrifugal diameter and the guidance and positioning of airflow, we optimize the hole insert, seeding plate, seed limit board, and integrated front shell. This optimization facilitates the adjustment of both the quantity and posture of seed filling. As a result, seeds can form a uniform flow within the annular cavity, reducing the wind pressure necessary for regular operation and decreasing power consumption. A quadratic regression orthogonal rotation combination experiment is conducted using a self-made experiment bench, considering ground speed, wind pressure, and seeding rate as the experiment factors. Furthermore, a comparative experiment involving a novel centrifugal variable-diameter type metering device. The results indicate optimal seeding performance when the ground speed is 13.2 km/h, the wind pressure is 1.2 kPa, and the feeding rate is 25 seeds/s. Under these conditions, the quality of feed index reaches 95.20%, the multi-index is 3.87%, and the miss index is 0.93%. Findings reveal that the developed seed metering device achieved a quality of feed index exceeding 93.00% across varying speeds of 12~18 km/h, aligning with the production requirements. Moreover, the actual power consumption of Type B and C is about 85.00% and 98.00% lower than Type A, standing at only 32.90 W at 18 km/h. The COP of Type C is about 86 times and 12 times that of Type A and B, respectively, meeting the demands for efficient production of maize seed metering devices. In comparison to traditional design and structural parameter optimization methods for maize seed metering device, this study is helpful to the sustainable development of maize industry and reduce environmental pollution.

Application of melt pool profiles for parameter calibration of Goldak’s heat source model

Goldak’s ellipsoidal heat source model is widely accepted in laser powder bed fusion (LPBF) process simulations. The model is dependent on three inherent flux distribution parameters and absorptivity which need to be calibrated before application. However, the uniqueness of the calibrated heat source parameters has not been established, which is crucial to accurately represent the energy density distribution in numerical studies. This paper proposed a novel parametric optimization method that can uniquely calibrate these four heat source parameters with high accuracy. Both the simulated cross-sectional (CS) profile and the mid-front (MF) profile of the melt pool were used during calibration. The differences between the experimental and simulated profiles formed the objective function of the parametric optimization problem, which was calculated by using the least power norm method on the deviations between melt pool boundary curves. A genetic algorithm (GA) with elitism selection approach was employed to optimize the heat source parameters by minimizing this single objective function value. To theoretically verify the applicability of the method, two theoretical case studies involving two distinct sets of heat source parameters were carried out. A unique solution of Goldak’s heat source parameters with less than 2 % error can be achieved within 50 generations of the optimization process. A single-track experiment was conducted to demonstrate the application of the proposed method in a real scenario. The CS and MF melt pool profiles were extracted and the calibration procedure was applied. The profiles from simulation with the calibrated heat source parameters exhibited a good agreement with experimental results. The calibrated parameters were used to simulate multi-track printing on a single layer for validation of the proposed method. The CS melt pool profiles obtained from the multi-track simulation and multi-track experiment agreed well, which validated the accuracy of the proposed calibration method and its utility in obtaining the key Goldak heat source parameters for LPBF simulation.

Learning Distributed Parameters of Land Surface Hydrologic Models Using a Generative Adversarial Network

AbstractLand surface hydrologic models adeptly capture crucial terrestrial processes with a high level of spatial detail. Typically, these models incorporate numerous uncertain, spatially varying parameters, the specification of which can profoundly impact the simulation capabilities. There is a longstanding tradition wherein parameter calibration has served as the conventional procedure to enhance model performance. However, calibrating distributed land surface hydrologic models presents a great challenge, often resulting in uneven spatial performance due to the compression of information inherent in model outputs and observations into a single‐value objective function. To address this problem, we propose a novel Generative Adversarial Network‐based Parameter Optimization (GAN‐PO) method. By leveraging a deep neural network to discern model spatial biases, we train a generative network to produce spatially coherent parameter fields, minimizing distinctions between simulations and observations. By leveraging neural network‐based surrogate models to make the physical model differentiable, we employ GAN‐PO to calibrate the Variable Infiltration Capacity (VIC) model against evapotranspiration (ET) over China's Huaihe basin. The results show that GAN‐PO can diminish errors in simulated ET derived from default parameters across nearly all grid cells within the study region, surpassing the conventional calibration approach based on the parameter regionalization technique. Ablation analysis indicates that relying solely on the traditional loss could lead to deteriorated model performance, underscoring the crucial role of the discriminator. Notably, due to the discriminator's explicit identification of model spatial biases, GAN‐PO excels in maintaining spatial consistency, outperforming the state‐of‐the‐art differentiable parameter learning (dPL) method in terms of model spatial performance.

Operation Parameters Optimization Method of Coal Flow Transportation Equipment Based on Convolutional Neural Network

Operation Parameters Optimization Method of Coal Flow Transportation Equipment Based on Convolutional Neural Network

Design parameter optimization method for a prestressed steel structure driven by multi-factor coupling

Design parameter optimization method for a prestressed steel structure driven by multi-factor coupling

The Specific Application and Meaning Expression of Folk Art in Urban Landscape Design Under the Optimized Interactive Genetic Algorithm

In the major cities with many high-rise buildings in contemporary China, land resources are becoming more and more scarce, and the urban ecological environment is in urgent need of recycling, and due to the blind imitation of Western culture and design mode and the neglect of China traditional regional culture, the urban landscape lacks interaction, resonance, and sense of belonging with citizens, and the phenomenon of landscape similarity emerges in various cities, focusing on the landscape space of urban complexes. There are also these problems. Urban residents urgently need a third space that can adjust their physical, mental, and spiritual needs. How to design an urban complex landscape that meets the aesthetic needs and humanistic needs of contemporary cities and has regional characteristics has become the first important task of my research. Folk art is an artistic treasure created by the working people in their production and life. Folk art is the embodiment of cultural regionality and the foundation of national culture. It awakens people’s awareness of the importance of local culture, awakens people’s sense of belonging, and is closer to the local public life. Today, the living soil and social and humanistic environment of folk art are in the process of urbanization in China, and there is a trend of gradual disappearance of lifestyle changes. How to make the contemporary urban complex landscape an organic soil for the survival, expression, application, and development of folk art is an important task in contemporary urban landscape design. Based on optimization, related concepts such as symbols, folk art symbols, urban complexes, urban complex landscape design, etc. have been sorted out. The relevant experimental results show that the construction land accuracy of the logistic regression model based on genetic algorithm has increased from 78.0% to 85.3%. kappa increased from 74.5% to 81.2%. Research shows that the logistic regression parameter optimization method based on genetic algorithm has better simulation effect than the conventional logistic regression method and is more suitable for the situation of unbalanced data distribution and many data features in the simulation of large-scale urban land dynamic changes.

Wave spectral partitioning for the SWIM spectrometer based on the wave age and parameter optimization method

The paper proposes a wave spectral partitioning method for the surface waves investigation and monitoring (SWIM) spectrometer based on the wave age and parameter optimization (WA-PO) method. The wave age criterion is a way to identify waves as wind waves or swells, and parameter optimization methods enable the modeling of wave spectra. The combination of the two can use the spectrum models to fit the SWIM spectra based on clarifying whether the spectrum models belong to wind waves or swells, which achieves spectral partitioning. The WA-PO method consists of four steps: peaks region dividing, spectral peaks searching, objective function constructing, and model parameters optimizing. The results show that compared with the partition products provided by the SWIM, the partition parameters obtained from the WA-PO method are closer to those of the Integrated Ocean Waves for Geophysical and other Applications (IOWAGA) numerical hindcast dataset developed from the WAVEWATCH III (WW3). The WA-PO method can prevent over-partitioning of the wave spectra and detect wind-wave components hidden in the swell partition.

OPTIMIZATION OF CYBER-PHYSICAL SYSTEM PARAMETERS BASED ON INTELLIGENT IOT SENSORS DATA

The optimization of cyber-physical systems (CPS) parameters is researched with focusing on the integration of computation, networking, and physical processes with the Internet of Things (IoT). The use of intelligent IoT sensors is crucial for collecting real-time data, which is necessary for enhancing the efficiency, reliability, and performance of CPS. Various methods of CPS parameters optimization are analyzed and categorized into model-based approaches, data-driven approaches, and hybrid approaches. The model-based approaches rely on mathematical models to describe CPS behavior and use optimization algorithms like linear programming and evolutionary algorithms to predict system responses and optimize parameters. But, the limitations of model-based approaches are related to complex systems with uncertain or dynamic behavior. The data-driven approaches are more suitable for complex cyber-physical systems. These approaches utilize machine learning and data analytics techniques to extract patterns from sensor data, which are then used to adjust system parameters. The hybrid approaches combine elements of both model-based and data-driven methods. The method of cyber-physical system parameters optimization based on intelligent IoT sensors data processing is developed with using of distributed neural network. The optimization problem is formulated with constraints for the system parameters. The neural network mathematical model and learning algorithm are proposed. The performed research shows the importance of developing optimization methods for CPS parameters based on intelligent IoT sensor data, considering the evolving nature of IoT technology. The integrating intelligent sensors into CPS offers new opportunities for optimizing system performance but also presents challenges in data management and security that should be addressed in future.

Research on Design and Optimization of Micro-Hole Aerostatic Bearing in Vacuum Environment

Micro-hole aerostatic bearings are important components in micro-low-gravity simulation of aerospace equipment, and the accuracy of micro-low-gravity simulation tests is affected by them. In order to eliminate the influence of air resistance on the attitude control accuracy of remote sensing satellites and achieve high fidelity of micro-low-gravity simulation tests, in this study, a design and parameter optimization method was proposed for micro-hole aerostatic bearings for a vacuum environment. Firstly, the theoretical analysis was conducted to investigate the impact of various bearing parameters and external conditions on the bearing load capacity and mass flow. Subsequently, a function model describing the variation in bearing load capacity and mass flow with bearing parameters was obtained utilizing a BP neural network. The parameters of aerostatic bearings in a vacuum environment were optimized using the non-dominated sorting genetic algorithm (NSGA-II) with the objectives of maximizing the load capacity and minimizing the mass flow. Subsequently, experimental tests were conducted on the optimized bearings in both atmospheric and vacuum conditions to evaluate their load capacity and mass flow. The results show that in a vacuum environment, the load capacity and mass flow of aerostatic bearings are increased compared to those in standard atmospheric conditions. Furthermore, it has been determined that the optimal solution for the bearing’s load capacity and mass flow occurs when the bearing has an orifice aperture of 0.1 mm, 36 holes, and an orifice distribution diameter of 38.83 mm. The corresponding load capacity and mass flow are 460.644 N and 11.816 L/min, respectively. The experimental and simulated errors are within 10%; thus, the accuracy of the simulation is verified.

Structural optimization of PVDF cellular resonators for energy-harvesting enhancement based on backpropagation neural network and NSGA-II algorithm

Metamaterials with honeycomb structures have garnered significant attention in energy-harvesting applications. In this study, we present three conventional cantilever resonators with honeycomb substrates featuring positive, zero, and negative Poisson’s ratios (PPR, ZPR, and NPR). Polyvinylidene fluoride consisting electrode layers is attached to the substrate surfaces. A process parameter optimization method of honeycomb structure design was proposed, in which finite element simulation for data generation, backpropagation neural network for data prediction, and nondominated sorting genetic algorithm II (NSGA-II) for data optimization. This method aims to determine the optimum geometric parameters of the honeycomb structures, which addresses general cantilever resonators, where the first structural vibration modes are typically of interest and have to match specific target eigenfrequencies for engineering applications. Finite element simulations show that the peak voltage of PPR, ZPR, and NPR resonators at 75 Hz is increased by 12 %, 22 %, and 32 %, respectively, due to optimization. The optimized structures are fabricated and measured to validate the numerical model. The performance of the resonators with cellular materials featuring a full characteristic range of Poisson’s ratios is then compared systematically to explore their energy-harvesting potential. The results revealed that the NPR structure exhibits superior performance for energy-harvesting. Moreover, stress distribution and displacement have also been highlighted in this paper.

Deployable support truss for parabolic cylindrical antennas with shape reconfiguration

The increasing scarcity of orbit resources has directed the focus onto the versatility of space antennas. Through shape reconfiguration, large antennas can achieve enhanced task compliance. In this paper, a two-degree-of-freedom (DOF) deployable support truss with shape reconfiguration is designed for parabolic cylindrical antennas. A design strategy is presented for the support truss, in which the synchronous deployment is realized first through the expansion of basic deployable units. The branch chains are then supplemented to realize the controllable reconfiguration of the entire support truss. Moreover, the mobility and kinematic analyses of the basic modules on the support truss are conducted to parametrically analyze the DOF space and realize the expected reconfiguration. The unit number and structure parameters of the support truss can influence the mimicking preciseness. To fulfill the mimicking error requirement with a more concise mechanism, a parameter optimization method based on the genetic algorithm is proposed to achieve the minimum number of the required deployable units. Simulation of the deployment and reconfiguration of the support truss as well as the verification test conducted on the principle prototype demonstrate the feasibility of the mechanism design. This paper may provide candidates for support trusses of large reconfigurable antennas with enhanced task flexibility and efficiency, and serve as references for the design of deployable mechanisms with the reconfiguration function.

Analyze of pipeline transport characteristics and optimization method of structural parameters in slurry shield circulation system with spiral structure

This study introduces the application of a spiral structure in pipeline transportation to enhance the pipeline capacity of a slurry shield circulation system. A numerical model of solid–fluid coupling in a pipeline with a double spiral structure was established based on computational fluid dynamics and the discrete element method (CFD–DEM) theory, and its validity was confirmed through comparison with experimental data. The characteristics of the spiral pipeline were evaluated by comparing them with those of a conventional smooth straight pipeline. A multi-objective optimization method for determining the structural parameters of a spiral pipeline in a slurry shield circulation system is proposed using the Kriging surrogate model. The optimized design of a spiral pipeline was demonstrated through a specific project, and the impact of the main structural parameters on the slurry transport characteristics of the pipeline was analyzed. The results indicated that the optimized structural parameters led to an 18.65% increase in the average flow rate of the slurry and a 19.13% reduction in the accumulation of stones in the pipeline.

Dynamic Balance Simulation and Optimization of Electric Vehicle Scroll Compressor Rotor System

In order to solve the problem of imbalance of internal forces in the system caused by the gravity force of the eccentric wheel and the orbiting scroll close to the drive bearing and the rotational inertia force during the operation of the electric scroll compressor, a dynamic model of the rotor system of the scroll compressor that takes into account the effect of the gas force was established using the multibody dynamics software ADAMS/View 2020. Dynamic simulation analysis of the rotor system is carried out, focusing on the force of the drive bearing; a parametric optimization method is adopted to optimize the position of the center-of-mass coordinates of the eccentric wheel of the relevant components, and the relevant parameters are derived after optimization. The results show that by adjusting the center-of-mass position of the eccentric wheel it is possible to optimize the unbalance force and unbalance moment of the main shaft drive system; compared with the pre-optimization, the force fluctuation ranges of the drive bearing in the horizontal and vertical directions are reduced, the peak value is reduced by 18%, and the impact force of the drive bearing during the initial period of compressor operation is effectively relieved. Through optimization calculation, the vibration and noise of the system are reduced, the operating stability of the scroll compressor is improved, and analytical methods and theoretical guidance are provided for the design and prediction of the dynamic behavior of the scroll compressors.

Cell-specific models of hiPSC-CMs developed by the gradient-based parameter optimization method fitting two different action potential waveforms

Parameter optimization (PO) methods to determine the ionic current composition of experimental cardiac action potential (AP) waveform have been developed using a computer model of cardiac membrane excitation. However, it was suggested that fitting a single AP record in the PO method was not always successful in providing a unique answer because of a shortage of information. We found that the PO method worked perfectly if the PO method was applied to a pair of a control AP and a model output AP in which a single ionic current out of six current species, such as IKr, ICaL, INa, IKs, IKur or IbNSC was partially blocked in silico. When the target was replaced by a pair of experimental control and IKr-blocked records of APs generated spontaneously in human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs), the simultaneous fitting of the two waveforms by the PO method was hampered to some extent by the irregular slow fluctuations in the Vm recording and/or sporadic alteration in AP configurations in the hiPSC-CMs. This technical problem was largely removed by selecting stable segments of the records for the PO method. Moreover, the PO method was made fail-proof by running iteratively in identifying the optimized parameter set to reconstruct both the control and the IKr-blocked AP waveforms. In the lead potential analysis, the quantitative ionic mechanisms deduced from the optimized parameter set were totally consistent with the qualitative view of ionic mechanisms of AP so far described in physiological literature.

Comparison of parameter optimization methods for a runoff forecast model based on a support vector machine

Long-term flow prediction is crucial in water resource management, with support vector regression (SVR) commonly used for runoff prediction. This paper aims to clarify SVR parameter optimization through a case study, focusing on the penalty coefficient (C), the kernel function parameter (γ), and the insensitive loss coefficient (ε), using different heuristic methods including particle swarm optimization (PSO), a complex method (CM), and simulated annealing (SA). A runoff prediction model based on SVR was established to forecast the monthly inflow runoff of Zipingpu Reservoir. The study evaluates the applicability of each optimization method for the SVM-based monthly streamflow forecast model. Results indicate CM has the best operational efficiency with an average running time of less than 2 s, significantly lower than PSO and SA. SA shows the best stability with an average standard deviation of fitness values of 0.00032, significantly lower than PSO's 0.0015 and CM's 0.021. The SA-SVM model reduces RMSE and MARE by 8.35% and 15% respectively, compared to the standard SVM model, while NS and R improve by 11.67% and 6.57%, achieving the highest prediction accuracy. Thus, the SA algorithm is the most applicable, followed by the PSO algorithm.