Radial Basis Function Method Research Articles

An Efficient Local Radial Basis Function Method for Image Segmentation Based on the Chan–Vese Model

An Efficient Local Radial Basis Function Method for Image Segmentation Based on the Chan–Vese Model

Modeling the effect of processing parameters on temperature history in Directed Energy Deposition: an analytical and finite element approach

PurposeThe purpose of this paper is to assess the feasibility of analytical models, specifically the radial basis function method, Akbari–Ganji method and Gaussian method, in conjunction with the finite element method. The aim is to examine the impact of processing parameters on temperature history.Design/methodology/approachThrough analytical investigation and finite element simulation, this research examines the influence of processing parameters on temperature history. Simufact software with a thermomechanical approach was used for finite element simulation, while radial basis function, Akbari–Ganji and Gaussian methods were used for analytical modeling to solve the heat transfer differential equation.FindingsThe accuracy of both finite element and analytical methods was validated with about 90%. The findings revealed direct relationships between thermal conductivity (from 100 to 200), laser power (from 400 to 800 W), heat source depth (from 0.35 to 0.75) and power absorption coefficient (from 0.4 to 0.8). Increasing the values of these parameters led to higher temperature history. On the other hand, density (from 7,600 to 8,200), emission coefficient (from 0.5 to 0.7) and convective heat transfer (from 35 to 90) exhibited an inverse relationship with temperature history.Originality/valueThe application of analytical modeling, particularly the utilization of the Akbari–Ganji, radial basis functions and Gaussian methods, showcases an innovative approach to studying directed energy deposition. This analytical investigation offers an alternative to relying solely on experimental procedures, potentially saving time and resources in the optimization of DED processes.

Пространственный подход к выявлению методологических ошибок в процессе расчета кадастровой стоимости

The authors describe a method for identifying methodological errors made in the process of determining the cadastral value using a spatial approach in order to increase the accuracy and objectivity of the results. An analysis and comparison of interpolation and clustering methods is also given, due to them the method of radial basis functions was selected to identify territories with significant discrepancies between cadastral and market values. Their subsequent study enables implementing an effective mechanism for controlling the calculation of cost. A program to carry out spatial approach to identifying methodological errors in the mentioned field is presented; geoinformation layers localizing unaccounted parameters affecting to some degree the value of a property in Petrodvortsovy district, an administrative-territorial unit of St. Petersburg, RF

Radial Basis Function Method for Linearization of Thermocouple Data: An Efficient and Accurate Approach

Radial Basis Function Method for Linearization of Thermocouple Data: An Efficient and Accurate Approach

A design method of volute profile of multi-blade centrifugal fan based on DRBF model

The forward-curved multi-blade centrifugal fan is widely used in the ventilation and household appliance industries with limited space due to its small size factor, high pressure coefficient, and large outlet flow coefficient. Conventional centrifugal fan structural designs rely on empirical data, resulting in drawbacks during usage such as low airflow velocity, high noise levels, and high energy consumption. In order to optimize fan structure, enhance aerodynamic performance, and seek new, effective approaches for energy efficiency and emissions reduction, this paper focuses on a combined design method that integrates scroll line design with aerodynamic performance and noise control. The goal is to propose a noise prediction and analysis method for multi-blade centrifugal fans, addressing the design contradiction between optimal fan functionality and minimal noise within limited design dimensions. The dynamic radial basis function method is introduced to investigate the geometric parameters of the scroll line, utilizing coherence analysis to identify the reasons for insufficient aerodynamic performance and noise reduction measures. Through the research, it is found that unreasonable design leads to a large turbulent vortex region within the blade passage and internal flow field, particularly involving circulation and backflow, which significantly reduces the fan's aerodynamic performance and operational efficiency. The design incorporates a composite scroll with a logarithmic spiral and circular arc integrated into one, and algorithm-based optimization of the scroll tongue, facilitating the transition of turbulence at the scroll outlet and the gap between the scroll tongue and impeller. Numerical results show an increase in airflow of 3.04 m3/min and a noise reduction of 3.79%. This indicates that the composite scroll design with a logarithmic spiral plays a dominant role in accelerating the aerodynamic performance of the scroll and reducing noise radiation.

Application of Adaptive Radial Basis Function Method in Concrete with Cooling Water Pipe

Application of Adaptive Radial Basis Function Method in Concrete with Cooling Water Pipe

Assessing air pollution changes during the COVID-19 and its impact on the urban environment using remote sensing and neural networks

The COVID-19 pandemic, spanning nearly two years, instigated a worldwide lockdown, resulting in a notable decline in pollution levels across numerous urban centers. This investigation leveraged satellite data to scrutinize alterations in air quality pre and post the onset of the COVID-19 pandemic, focusing on the Isfahan region in central Iran and Fars province in the south. We assessed vegetation conditions employing remote sensing indices, including the Enhanced Vegetation Index (EVI), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Built-Up Index (NDBI). Additionally, we evaluated thermal pollution in urban environments using indices such as Land Surface Temperature (LST), Surface Urban Heat Island (SUHI), and Urban Thermal Features Vegetation Index (UTFVI). Linear regression analysis revealed significant correlations between LST and pollutants, with SO2 (R2 = 0.983), NO2 (R2 = 0.824), CO2 (0.808), and CO (R2 = 0.710) exhibiting strong associations. Pollution maps for CO2, CH4, CO, NO2, O3, and SO2 were generated for the pre-COVID-19 (2019) and COVID-19 (2020) periods, highlighting reduced pollution levels during the pandemic due to decreased industrial activities and vehicle traffic. We employed Markov and Cellular Automata (CA)-Markov methods to predict future LST trends, using probability matrices as input data. The CA-Markov chain results forecasted an increase in LST in 2040. Additionally, we compared Radial Basis Function (RBF) and Multilayer Perceptron (MLP) neural network methods. Our investigation found that MLP outperforms RBF, with optimal neuron counts in the hidden layers varying by index. MLP demonstrated higher accuracy, with R2 values of 0.98 for SUHI, 0.93 for UTFVI, 0.98 for CO, and 0.99 for O3, and lower RMSE. In conclusion, our study, focused on Isfahan and Fars province in Iran, reveals that the reduction in urban air pollution during the COVID-19 pandemic primarily resulted from diminished industrial activities and reduced vehicular traffic. MLP neural networks displayed superior performance in predicting index values, highlighting the role of reduced human activities on urban environmental quality.

A novel prediction for conjugated heat and mass transfer in falling film and membrane during LiBr absorption

The present investigation is intended to develop an understanding of how the vapor pressure and inlet temperature of the solution affect the absorption rate, which is helpful for the design of absorption heat pump systems. Many conjugated heat and mass transfer processes in falling film and membrane during lithium bromide (LiBr) absorption have not been well addressed. This paper proposes combining the meshless Radial Basis Function (RBF) and Discontinuous Galerkin (DG) methods to solve the conjugated heat and mass transfer in falling film and membrane-based absorption problems. The derivatives in the transverse direction are discretized using the RBF method. Owing to the parabolic nature of the governing equations, the DG methods can be used to discretize the derivatives in the streamwise direction. The efficacy of the proposed method is shown by comparing its results with analytical solutions and experimental data available in the literature. Furthermore, the proposed method is used to evaluate the analytical solutions of the heat and mass transfer problem in a membrane-based absorber. The previous published works simplified the problem to obtain the analytical solutions by providing the mean temperature and concentration values as the boundary conditions at the membrane-solution interface. The comparison of the RBF-DG method and the analytical solutions reveals that there are minor changes in temperature and local concentration values along the streamwise direction, but the profiles and trends are relatively similar across the film. A comparison of mass absorption rate calculations shows that RBF-DG and analytical solutions are compatible. The advantage of the numerical method is that various types of boundary conditions can be handled easily without any simplifications. Moreover, the numerical results of the proposed method are compared with experimental data, and they present good agreement. As a results, the absorption rate of falling film and membrane becomes capable of being accurately predicted.

A flight control system for quadrotor plant protection UAV based on RBF-PID algorithm

As a powerful tool for modern agricultural protection, unmanned aerial vehicle (UAV) has the advantages of good adaptability and high efficiency in spraying and other operations compared with traditional manual operations The attitude and control of plant protection UAV are greatly affected by external factors during operation. However, the traditional proportional-integral-derivative (PID) controller commonly used at present cannot adapt to the complex environment because of the fixed parametersTherefore, a more sensitive method is needed to achieve adaptive balance of the aircraft attitude. In this paper, we establish the dynamic mathematical model of quadrotor UAV, and the influence of air resistance and rotational torque is considered in the process. Adopting the combined control method of Radial Basis Function (RBF) neural network and PID, the dynamic tuning of system control parameters is achieved through the self-learning of neural network and the feature of nonlinear mapping. The control system not only has the advantages of simple PID control structure and clear physical meaning, but also has the ability of neural network self-learning and adaptation. Matlab/Simulink was used as the experimental platform to respectively simulate the RBF-PID control system and the traditional PID control system. The simulation results show that the control system based on RBF-PID algorithm has a shorter response time and stronger robustness, which enhances the systems self-adaptability

An improved local radial basis function method for solving small-strain elasto-plasticity

Strong-form meshless methods received much attention in recent years and are being extensively researched and applied to a wide range of problems in science and engineering. However, the solution of elasto-plastic problems has proven to be elusive because of often non-smooth constitutive relations between stress and strain. The novelty in tackling them is the introduction of virtual finite difference stencils to formulate a hybrid radial basis function generated finite difference (RBF-FD) method, which is used to solve small-strain von Mises elasto-plasticity for the first time by this original approach. The paper further contrasts the new method to two alternative legacy RBF-FD approaches, which fail when applied to this class of problems. The three approaches differ in the discretization of the divergence operator found in the balance equation that acts on the non-smooth stress field. Additionally, an innovative stabilization technique is employed to stabilize boundary conditions and is shown to be essential for any of the approaches to converge successfully. Approaches are assessed on elastic and elasto-plastic benchmarks where admissible ranges of newly introduced free parameters are studied regarding stability, accuracy, and convergence rate.

Experimental Study of Deformation Risk and Interpolation Analysis of Temperature for Water Walls under Flexible Low-Load Conditions

With the development of renewable energy in power generation, a large number of thermal power plants operate under flexible working conditions. To study water wall deformation risk under flexible low-load conditions, a lab-scale opposed firing boiler was built to measure and analyze the temperature and thermal stress of the water wall under low-load flexible operating conditions with several nontypical burner arrangements. The results showed that flame radiation and flue gas convection heat transfer induced a high-temperature zone. Thermal stress was mainly caused by thermal expansion of the metal and expansion or extrusion deformation of other areas. Also, local thermal stress fluctuations and excessive values appeared under variable conditions. In addition, the burners’ symmetrical arrangement in the center effectively reduced thermal stress fluctuations and overall thermal stress under flexible working conditions. Finally, based on the limited temperature measurement points in this experiment, the optimal power parameter α for the inverse distance weighted (IDW) method and the shape parameter ε for the radial basis function (RBF) method were found to make a reasonable interpolation prediction of the temperature distribution of the water wall. This study highlights the recommended burner arrangements under flexible low-load conditions and the optimal parameters of the IDW and the RBF methods for estimating temperature in guiding safe operation of the water wall.

Evolutionary Airfoil Shape Optimization Coupling Parameterization Methods with Lagrangian Vortex Method

In the present paper, the evolutionary algorithm for single-objective optimization is developed using a genetic algorithm and employing polynomial-based (PARSEC) and radial basis function (RBF) functions for NACA 2412 airfoil parameterization. The determination of the objective functions, being aerodynamic coefficients, are performed using the Lagrangian vortex particle method. The results of the lift coefficient at the wide range of angle of attack using the vortex particle method shows a good agreement with experimental data listed in the literature. For the optimization results, the lift coefficient obtained from the PARSEC method is optimized to be larger for the whole range of angle of attack; while it still keeps the stall region at the upper surface of the airfoil to be the same as that of the original airfoil. In addition, the RBF method illustrates the lift coefficients larger at the range of angle of attack from -50 to 140 but stall occurs earlier than the original airfoil.

Rheological behavior of polyvinylidene fluoride/dimethylacetamide solutions: Experimental investigation and machine learning modeling

This study aimed to investigate the rheological properties of polyvinylidene fluoride/dimethylacetamide solutions. The influences of shear rate, temperature, and additives fractions on solution viscosity were experimentally studied. The results indicated that the viscosity is noticeably reduced by increasing the temperature at low shear rates, while the temperature dependence of viscosity was diminished at high levels of shear rate. On the other hand, adding water to the solution tended the viscosity to increase, especially at lower shear rates and temperatures. Furthermore, an exponential enhancement was observed in the viscosity by growing the inorganic/organic additive ratio. The measured data were employed to design predictive methods for solution viscosity by defining six factors including temperature, shear rate, and the fractions of solvent and additives as input variables. The modeling phase was carried out by implementing three computer-aided approaches, among which the radial basis functions (RBF) method overcame the others from the standpoint of accuracy and reliability with total average absolute relative errors and R2 values of 1.29% and 99.86%, respectively, for 1064 measured data. Also, a visual description through the contour diagram affirmed that the RBF model performs excellently in the suit of describing the rheological behavior of the polymeric solution under various operating conditions. Eventually, the factors with the greatest influences on solution viscosity were designated through a sensitivity analysis based on the recently proposed model.

Assessment of radial basis function method with thin plate spline kernel for evaluable precipitable water vapor interpolation from GPS observations over state of California, USA

Assessment of radial basis function method with thin plate spline kernel for evaluable precipitable water vapor interpolation from GPS observations over state of California, USA

A semiparametric spatio‐temporal model of crop yield trend and its implication to insurance rating

AbstractWe demonstrate the benefit of spatial smoothing for crop trend estimation with a deterministic spatio‐temporal trend model. The proposed model is semiparametric, where the parametric temporal trend is modeled with a two‐knot spline function for forecasting robustness, and the nonparametric spatially‐varying coefficients are modeled by the radial basis function method for flexibility. To select the smoothing parameter of our trend model, we propose a forward validation criterion tailored to meet the forecasting nature of rating crop insurance. This criterion is based on a rolling regression approach that adds one year of data at a time for validation. We also propose a new criterion for model comparison using relative mean squared error in forecasting insurance payouts. Our empirical results show that the proposed trend model is more efficient and capable of identifying profitable insurance policies than two competing models in most state‐crop combinations.

Applied machine learning-based models for predicting the geomechanical parameters using logging data

Geomechanical (GM) parameters play a significant role in geomechanical studies. The calculation of GM parameters by analyzing finite rock samples is very limited. The GM parameters show a nonlinear trend; thus, applying empirical relationships is unreliable to predict their quantities. Machine learning (ML) methods are generally used to improve the estimation of such parameters. Recent researches show that ML methods can be useful for estimating GM parameters, but it still requires analyzing different datasets, especially complex geological datasets, to emphasize the correctness of these methods. Therefore, the aim of this study is to provide a robust recombinant model of the ML methods, including genetic algorithm (GA)–multilayer perceptron (MLP) and genetic algorithm (GA)–radial basis function (RBF), to estimate GM parameters from a complex dataset. To build ML models, 48,370 data points from six wells in the complicated Norwegian Volve oil field are used to train GA–MLP and GA–RBF methods. Moreover, 20,730 independent data points from another three wells are used to verify the GM parameters. GA–MLP predicts GM parameters with the root-mean-squared error (RMSE) of 0.0032–00079 and coefficient determination (R2) of 0.996–0.999. It shows similar prediction accuracy when used to an unseen dataset. Comparing the results indicates that the GA–MLP model has better accuracy than the GA–RBF model. The results illustrate that both GA–MLP and GA–RBF methods perform better at estimating GM parameters compared to empirical relationships. Concerns about the integrity of the methods are indicated by assessing them on another three wells.

Laminar Rayleigh–Benard convection in a closed square field with meshless radial basis function method

Abstract Research on natural convection is exciting in some experimental and numerical cases, especially in rectangular cavities with relatively low heat dissipation and thermal control systems with low cost, reliability, and ease of use. The present study will use the meshless radial basis function method to solve the velocity formulation of the Navier–Stokes equations by varying some nominal Rayleigh numbers of 104, 105, and 106. The numerical accuracy is compared with the previous research. The advantages of the meshless method are that it does not require a structured mesh and does not require inter-nodal connectivity. The results show that the temperature pattern is identical to the previous research. The calculations have been done for three different Rayleigh numbers of 104, 105, and 106 for 151 × 151 nodes. The variations of the Ra number will affect the isothermal, velocity contours, and Nusselt number.

Numerical Analysis of Seepage in Steady and Transient Flow State by the Radial Basis Function Method

Numerical Analysis of Seepage in Steady and Transient Flow State by the Radial Basis Function Method

Investigating the effect of surface urban heat island on the trend of temperature changes

Urbanization has led to the emergence of surface urban heat islands (SUHI) and air pollution, necessitating comprehensive investigations into the urbanization process. This study explores the impact of urbanization on temperature trends in northern Iran using remote sensing and neural networks. MODIS images from 2001, 2010, and 2019 were employed to determine climatic features and vegetation levels. SUHI indices and the Urban Thermal Field Variance Index (UTFVI) were utilized to assess ecological comfort and urban heat islands. Markov chain methods were used for forecasting future thermal pollution. The relationship between temperature, air pollutants, spectral indices, and thermal indices was investigated through regression analysis. Furthermore, multilayer perceptron (MLP), radial basis function (RBF), and long short-term memory (LSTM) neural networks were employed for predicting indicator values. The findings reveal an increase in thermal pollution indicated by elevated Land Surface Temperature (LST), SUHI, and UTFVI values, along with a decrease in Normalized Difference Vegetation Index (NDVI) values between 2001 and 2019. The Urbanization Index (UI) values demonstrate a 5% increase in urban areas during the same period. The UTFVI values suggest a decline in ecological comfort due to urbanization and reduced vegetation, with the majority of the region experiencing the poorest thermal comfort in 2019. The SUHI index peaked at 11.72 in 2019, with the highest values observed in spring and the lowest in winter. Correlation analysis highlights a significant relationship between LST and various factors, including SUHI, UTFVI, CH4, SO2, and CO2, underscoring the influence of temperature increase on pollution escalation in the study area. Air pollution assessment indicates the highest concentration of CO gas in the northern and southern parts of the region. Tehran exhibits the highest CO gas levels at 0.051 ppm, while Golestan records the lowest at 0.012 ppm. SO2 levels reach their peak in northern regions (0.0088 ppm) and are lowest in southern regions (0 ppm). The Markov and CA-Markov chain methods predict that by 2050, approximately 50% of the region will experience high temperatures. Neural network results demonstrate that the LSTM method outperforms MLP and RBF methods, with R2 values of 0.99 and 0.98, respectively, indicating higher accuracy in LST prediction during testing and validation stages. Overall, this study highlights the potential of neural networks in predicting thermal pollution and facilitating effective land management strategies in urban areas.

FUEL INCREASE SENTIMENT ANALYSIS USING SUPPORT VECTOR MACHINE WITH PARTICLE SWARM OPTIMIZATION AND GENETIC ALGORITHM AS FEATURE SELECTION

BBM, or fuel oil, is one of the essential needs of the Indonesian people. The government's policy regarding the increase in fuel prices raises many opinions from the public. Twitter is one of the social media that Indonesian people often use to express opinions on a topic. In this study, sentiment analysis was carried out on public opinion regarding the fuel price increase policy from Twitter social media. This research is expected to help determine public opinion regarding the fuel price increase policy with positive, neutral and negative sentiments. The sentiment analysis method used is the Support Vector Machine (SVM) classification algorithm. The results of the accuracy of SVM were compared with accuracy by adding a feature selection process. The Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) algorithms are used for the feature selection method. After several experiments using the three methods, the SVM method with the Radial Basis Function (RBF) kernel produced the best accuracy of 71.2%. The combination of the SVM method with the RBF and PSO kernels obtained an accuracy of 68.84%, and the combination of the RBF and GA kernel SVM methods obtained an accuracy of 69.52%.