Search

Due to increasing concerns about global warming regarding CO2 release to the atmosphere, various methods are used to capture CO2, among which chemical absorption via amine mixture solutions is very well developed. A set of 179 data related to CO2 absorption in a mixture, including a physical absorbent (sulfolane) and a chemical absorption (AEEA) in a wide range of temperature, pressure and solvent concentration is used to develop two Artificial Neural Networks (ANN). In Multi-Layer Perceptron (MLP), the Levenberg-Marquardt method is used to train the network. Most important factors such as regression analysis value (R2) of 0.99963, Mean Squared Error (MSE) value of 1.22E-05 and Average Absolute Relative Deviation value (%AARD) of 0.2671 factors reveal that the MLP network has a high capability to predict CO2 loading (αCO2). Also, a Radial Basis Function (RBF) network was developed. RBF network with a spread value of 2.2 and 138 neurons had an outstanding performance and achieved an MSE value of 2.53E-05 along with an R2 value of 0.99993, 11 seconds, and a %AARD value of 0.1460. According to experimental and predicted data, the neural networks are well trained and are able to predict CO2 loading precisely in an economic and optimized way.

Abstract Nowadays, the use of artificial intelligence is common to increase the accuracy of the study and, close to reality, is used in the oil industry to increase the accuracy of studying and understanding the relationship between various parameters. The main purpose of this study is to compare the performance of the two methods of Extreme Learning Machine (ELM) and Radial Basis Function (RBF) in porosity estimation, which is static oil modeling. The data from seven wells in the offshore field (Hendijan Oilfield) of the northwestern Persian Gulf were examined. In this regard, post-stack seismic attributes which have a significant relationship with porosity and porosity log for each well were used to compare the performance of the ELM and RBF networks under the same conditions. Eventually, it reveals that ELM is quite sensitive to the data set and needs more data points to prepare a map (quantitatively), but is better than RBF in terms of classification (qualitative). On the other hand, RBF is one of the most powerful algorithms in mapping, especially in low numbers of data points, which can be challenging for others.

Changes in the waxing and waning of carbon pools in forest ecosystems have a profound impact on the global carbon cycle. The study takes forests in a city as an example, uses sample plot survey data and Sentinel-2 and GF-1 satellite remote sensing data as data sources, and after multiple feature extraction, the RBF neural network optimized by the PSO algorithm is used for modeling the dynamic estimation of carbon storage, assessing the accuracy of the model and inverting the estimation of carbon storage in the sample area. The results show that the PSO-RBF model in this paper has the best fit and prediction accuracy for carbon storage estimation, with the highest R² of 0.644 and the smallest RRMSE and MAE of 0.287 and 15.368 in the combination of the two data sources, and the estimated value of forest carbon storage in 2022 in the sample area is 6809451.80t, which differs from the actual value by 0.04% and the difference of predicted and actual values in each subarea is 0.04%. The predicted and measured values in subregions had a difference of less than 0.34%. The forest carbon storage model that utilizes PSO-RBF has a good estimation effect overall. The technical support provided by this study enables accurate monitoring of carbon storage in forest ecosystems.

The explosive development of artificial intelligence technology greatly promotes the intelligent construction of museums and strengthens their cultural inheritance role. This paper takes artificial intelligence technology as its guide, analyzes the advantages of AI technology in the intelligent museum, and establishes the specific structure of an intelligent museum by combining VR technology. Wisdom Museum can realize the effective repair and presentation of cultural relics data. This paper uses three-dimensional laser scanning technology to obtain cultural relics point cloud data, repair the holes in the point cloud data through RBF, optimize the point cloud data by combining texture mapping, and input the optimized data into the GC-GAN model to realize the three-dimensional digital repair of cultural relics images. Moreover, the smart museum’s intelligent interaction system is built by combining virtual reality technology and related equipment. Taking Dunhuang mural point cloud data as an example, the number of point clouds of the RBF hole repair algorithm differs from the original data by only 5.86%, and the SSIM and PSNR values on the repaired portraits are 0.83 and 26.36 dB, respectively. The SUS total score for the user on the intelligent interactive system is 73.875, and the UEQ factor scores are averaged out at 1-3 points. The creation of a smart museum can be realized using AI technology, providing users with an immersive cultural relics viewing experience and activating the vitality of all kinds of cultural relics in the museum.

The present study focused on developing predictive neural networks and response surface methodology (RSM)-based model. In order to develop the predictive model, experimental data of CO2 capture by KOH-modified activated alumina was obtained through laboratory scale adsorption setup. Three independent input variables, including time (t: 0–1800 sec), initial temperature (Tin: 20–80 °C), and initial pressure (Pin:1.651–10.028 bar) of the reactor, were considered in the training process. Furthermore, CO2 adsorption capacity, and final pressure were considered as the output. The multilayer perceptron (MLP) and radial basis function (RBF) networks have been employed. The best corresponding optimized MLP network, out of all the 460 different structures, was chosen to be a structure trained with Levenberg Marquardt back propagation algorithm with four hidden layers, in which there were 25, 23, 7, and 20 neurons. The best corresponding transfer functions for the first, second, third, and fourth hidden layers plus the output layer were Purelin, Logsig, Tansing, Logsig, and Purelin, respectively. Finally, the performance of the RBF was explored on the experimental data. Out of the 385 built structures, the optimized corresponding RBF network was chosen to be the one with 2.5 as its spread value and 40 as its neuron numbers. Lastly, in the RSM design, the cubic model with square root transformation presented a comparably better performance. The coefficient of determination values for CO2 adsorption capacity in MLP, RBF, and RSM models were calculated as 0.999, 0.998, and 0.949, respectively.

Osteoarthritis is one of the most common cause of disability among elderly. It can affect every joint in human body, however, it is most prevalent in hip, knee, and hand joints. Early diagnosis of cartilage lesions is essential for fast and accurate treatment, which can prolong joint function. Available diagnostic methods include conventional X-ray, ultrasound and magnetic resonance imaging. However, those diagnostic modalities are not suitable for screening purposes. Vibroarthrography is proposed in literature as a screening method for cartilage lesions. However, exact method of signal acquisition as well as classification method is still not well established in literature. In this study, 84 patients were assessed, of whom 40 were in the control group and 44 in the study group. Cartilage status in the study group was evaluated during surgical treatment. Multilayer perceptron - MLP, radial basis function - RBF, support vector method - SVM and naive classifier – NBC were introduced in this study as classification protocols. Highest accuracy (0.893) was found when MLP was introduced, also RBF classification showed high sensitivity (0.822) and specificity (0.821). On the other hand, NBC showed lowest diagnostic accuracy reaching 0.702. In conclusion vibroarthrography presents a promising diagnostic modality for cartilage evaluation in clinical setting with the use of MLP and RBF classification methods.

The temperature system of the Continuous Stirred Tank Reactor (CSTR) has the characteristics of strong nonlinearity and uncertain parameters. The linear PID controller makes it difficult to meet CSTR's control requirements. Nonlinear PID (NPID) can improve the control effect of nonlinear controlled objects, but due to the influence of nonlinear function selection and manual parameter setting, when parameters are uncertain or subject to external interference, the control performance of the system will decrease. To improve the adaptive capability of the NPID controller, the RBF-NPID control algorithm is proposed. The learning ability of RBF neural network is used to adjust NPID parameters online to improve the control performance of the system. In order to verify the effectiveness of the proposed algorithm, a CSTR model was established in MATLAB and algorithm comparison research was carried out. Simulation results show the effectiveness and superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The explosive growth of video data poses a significant challenge in retrieving relevant content swiftly. Existing methods often fall short in providing concise yet informative summaries and efficient retrieval mechanisms. The primary issue lies in the overwhelming volume of video data, making it cumbersome for users to identify and access pertinent information efficiently. Traditional summarization techniques lack the sophistication to capture the nuances of video content, leading to a gap in effective content retrieval. Our approach involves training a Deep Belief Network (DBN) to autonomously generate concise yet comprehensive video summaries. Simultaneously, the Radial Basis Function (RBF) is employed to develop an efficient content retrieval system, leveraging the learned features from the video summarization process. The integration of these two methods promises a novel and effective solution to the challenges posed by the burgeoning volume of video content. Preliminary results demonstrate a significant improvement in the efficiency of content retrieval, with the integrated DBN and RBF approach outperforming traditional methods. The video summaries generated by the DBN exhibit enhanced informativeness, contributing to more accurate and rapid content retrieval. [ABSTRACT FROM AUTHOR]

The cumulative effect of many incidents that are brought about by an increase in temperature establishes an environment in which premature failure (including fatigue failure) becomes a challenging issue. Isothermal rotating bending fatigue (IT‐RBF) testing may simulate industrial components' high temperatures and rotating environments. This state‐of‐the‐art review paper covers the current research on IT‐RBF failure in wrought and additive‐manufactured alloys, focusing on microstructural and lifetime models. The article emphasizes the need of using microstructural information in fatigue life models to better represent complex material structure‐failure behavior associations. Additive‐manufactured alloys contain unique microstructural characteristics and processing‐induced defects making fatigue modeling difficult. The paper concludes with implications for industrial fatigue‐resistant alloy development. It emphasizes the necessity for a multidisciplinary approach that integrates materials science, mechanics, and data science to optimize these materials under cyclic loads. The review concludes by proposing future research and innovation in this subject. Highlights: Elevated‐temperature RBF evaluates endurance and fatigue life for high‐temp. applications.Cyclic loading induces crack formation and accelerated propagation at elevated temps.Surface, stress, and loading conditions are crucial in isothermal RBF crack initiation.Environmental and metallurgical phenomena influence high‐temperature RBF failure.RBF at elevated temperatures aids modifying fatigue models for various applications. [ABSTRACT FROM AUTHOR]

Accurate monitoring of atmospheric water vapor content is essential for the early warning of extreme weather events. As known, GNSS zenith troposphere delay (GNSS_ZTD) is an indispensable data source for retrieving precipitable water vapor (PWV). However, the newest GPT3 empirical model is not accurate enough to perform the ZTD (GPT3_ZTD) and PWV (GPT3_PWV) estimation in some regions, such as Japan. Thus, here, we introduce a radial basis function (RBF) neural network to establish ZTD forecast models based on the GPT3 model and use the predicted ZTD to retrieve PWV and adopt the retrieved PWV in forecasting precipitation. To thoroughly verify the accuracy of forecast results in 2021, we selected three external validation data: GNSS, radiosonde, and meteorological data. The GNSS_ZTD validation results show that the error compensation model of GPT3 based on RBF is superior to the GPT3 model and the model using a single RBF and back propagation (BP) neural network. The average RMSE of all GNSS stations is 50.7 mm, 53.7 mm, and 37.8 mm for GPT3_ZTD, RBF_BP_ZTD, and RBF_GPT3_ZTD, respectively. The GNSS_PWV and RO_PWV validation results show that the retrieved PWV with compensation of RBF_GPT3_ZTD is better than the uncompensated GPT3_ZTD, the average accuracy of RBF_GPT3_PWV of GNSS stations and radiosonde stations is improved by 40.4% and 25.8% against that of GPT3_PWV. For the precipitation forecast model results, the average forecast accuracy of all GNSS stations and radiosonde stations is 63.1% and 61.4%, according to the ERA5 precipitation. The average forecast accuracy is 66.3%, validated by meteorological precipitation records. The proposed model not only improves the GPT3 model but also forecasts the PWV value, which can improve the precipitation forecast in Japan, and is expected to expand to other regions. [ABSTRACT FROM AUTHOR]

Resting b**ch face (RBF) is described as an unintentional angry facial expression that is evaluated negatively and usually attributed to women. A 2 (smiling/RBF) x 2 (female/male provider) online experiment, guided by expectancy violations theory, investigated whether U.S. adults' perceptions of a healthcare provider, medical care quality, and likelihood to make another appointment would be impacted by the provider's facial expression and sex. Results indicated that RBF was an expectancy violation resulting in decreased liking and perceptions of care quality. The female provider with RBF was evaluated more negatively than the smiling female provider and the male provider with RBF on liking, caring, medical care quality, and likelihood to make a future appointment. Additional findings are further discussed in the paper. Patients may hold biases toward providers based on their facial expressions and biological sex. [ABSTRACT FROM AUTHOR]

This study is devoted to analyse of free and forced vibrations and semi-active control vibrations of sandwich microbeam with Functionally Graded Materials (FGM) and viscoelastic/electrorheological (ER) core. The intended model is for top and bottom layers of functionally graded materials with power law and a core model for Viscoelastic materials with complex shear modulus. Hamilton principle is used to determine the governing Equations of motion on the sandwich microbeam based on the modified couple stress theory. Mesh less method of Radial Basis Functions (RBF) is used to calculate natural frequency and the loss factor. All the effects of length scale parameter, shear modulus and changes due to variation of the electric field on the natural frequency and loss factor have been drawn. Combination of RBF method and forward difference led to evaluation of forced vibration and deflection of microbeam for length scale parameters and different electric fields under the dynamic load have been calculated and drawn. The feedback effects are analyzed for vibration amplitudes of sandwich microbeam by using Linear Quadratic Gaussian (LQG) and optimal control method. At the end, the results are compared with papers for different viscoelastic models such as Kelvin model, Bingham plastic model and complex modulus. [ABSTRACT FROM AUTHOR]

Radial basis functions (RBFs) with modified radial distance are proposed for vibration analysis of functionally graded materials (FGM) rectangular plates. The displacement field with five variables higher-order shear deformation theory (HSDT) is considered. The governing differential equations (GDEs) and boundary conditions are obtained using Hamilton's principle. The governing differential equations formulations are solved via strong-form solutions. The rectangular plates are analyzed in the framework of the RBF-based meshfree method. The novelty of the present modified method is to analyze the square and rectangular plates without changing the shape parameters. Here, the seventeen different RBFs are available in various literature to demonstrate the accuracy and efficiency of the present method in terms of the number of nodes and computational time. The results of several numerical examples have shown that the present modified RBF-based mesh-free method can lead to much more accurate solutions. Computational times of different RBFs are also analyzed.

The paper evaluated the possibility of using artificial neural network models for predicting the compressive strength (Fc) of concretes with the addition of recycled concrete aggregate (RCA). The artificial neural network (ANN) approaches were used for three variable processes modeling (cement content in the range of 250 to 400 kg/m3, percentage of recycled concrete aggregate from 25% to 100% and the ratios of water contents 0.45 to 0.6). The results indicate that the compressive strength of recycled concrete at 3, 7 and 28 days is strongly influenced by the cement content, %RCA and the ratios of water contents. It is found that the compressive strength at 3, 7 and 28 days decreases when increasing RCA from 25% to 100%. The obtained MLP and RBF networks are characterized by satisfactory capacity for prediction of the compressive strength of concretes with recycled concrete aggregate (RCA) addition. The results in statistical terms; correlation coefficient (R) reveals that the both ANN approaches are powerful tools for the prediction of the compressive strength.

The comprehensive and accurate assessment of the indoor air quality (IAQ) in large spaces, such as offices or multipurpose facilities, is essential for IAQ management. It is widely recognized that various IAQ factors affect the well-being, health, and productivity of indoor occupants. In indoor environments, it is important to assess the IAQ in places where it is difficult to install sensors due to space constraints. Spatial interpolation is a technique that uses sample values of known points to predict the values of other unknown points. Unlike in outdoor environments, spatial interpolation is difficult in large indoor spaces due to various constraints, such as being separated into rooms by walls or having facilities such as air conditioners or heaters installed. Therefore, it is necessary to identify independent or related regions in indoor spaces and to utilize them for spatial interpolation. In this paper, we propose a spatial interpolation technique that groups points with similar characteristics in indoor spaces and utilizes the characteristics of these groups for spatial interpolation. We integrated the IAQ data collected from multiple locations within an office space and subsequently conducted a comparative experiment to assess the accuracy of our proposed method in comparison to commonly used approaches, such as inverse distance weighting (IDW), kriging, natural neighbor interpolation, and the radial basis function (RBF). Additionally, we performed experiments using the publicly available Intel Lab dataset. The experimental results demonstrate that our proposed scheme outperformed the existing methods. The experimental results show that the proposed method was able to obtain better predictions by reflecting the characteristics of regions with similar characteristics within the indoor space. [ABSTRACT FROM AUTHOR]

The definition of an appropriate number of Radial Basis Functions and their parameters in Radial Basis Function networks is a non-trivial task. The fitting of its parameters has direct implications on model performance and generalization. Techniques such as cross-validation associated with error metrics, which frequently rely on iterative optimization, have been used to address this problem, requiring significant computational effort and uncertain solutions. We propose a method for determining the number and parameters of Radial Basis Functions based on the Dominating Set of the Gabriel graph, which represents the structure of the input data, such that no exterior/prior parameter estimation or heuristic methods are necessary. [ABSTRACT FROM AUTHOR]

Jet fires and their repercussions play a significant role in catastrophic incidents that typically have a cascading impact in process industries. Several hydrocarbon experiments from 19 papers were incorporated into the current endeavour to develop simulations of jet flames using machine learning (ML) models. Dimensionless characteristics have been used as output and input variables, including mass flow rates, fuel density, jet flame length, and heat release fluxes. When training three layers of the multi‐layer feedforward neural network (MLFFNN) method, a Bayesian regularization backpropagation approach was adopted and evaluated with the radial based functions (RBF) algorithm. Through an optimization procedure, the first and second hidden layers of the MLFFNN have been optimized to include 10 and five neurons, respectively. The RBF algorithm with 40 neurons in a single layer has been computed using the same method. The best mean square error (MSE) validation results for RBF and MLFFNN were 0.006 and 0.0002, respectively, for 40 and 100 epochs. The MLFFNN and RBF models' respective regression statistical analysis outputs were 0.9949 and 0.9645. The ML method has been identified as a potentially useful technique for precisely predicting the geometrical and radiative characteristics of jet flames. [ABSTRACT FROM AUTHOR]

The adaptive backstepping control method of permanent magnet motor has the problems of complicated coordinate transformation process and high position tracking error. Based on this, an adaptive backstepping control method of permanent magnet synchronous motor based on RBF is proposed. According to the principle of electrical machinery, the electromagnetic wave and magnetic field data are obtained, and the mathematical model of permanent magnet synchronous motor is constructed. Under the condition of keeping the resultant magnetomotive force after coordinate transformation unchanged, the structure of motor torque neural network is established by RBF method, and the coordinate transformation process is optimized. Through the compensation control strategy, the adaptive backstepping control mode is designed to realize the adaptive backstepping control of permanent magnet synchronous motor. The simulation results show that the position tracking error of the proposed method is 4.549 mm when the running time is 7 s and 43.699 mm when the running time is 14 s, which proves that the adaptive backstepping control effect of the proposed method is better. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) is a major population disease. In diabetes as well as hypertension, kidney disease is one of the most serious complications. Recent research has demonstrated that chronic hypoxia is a key actor in the pathogenesis of CKD. In this review, we focus on how functional magnetic resonance imaging (fMRI) techniques can shed light on pathogenetic mechanisms and monitor new treatments aimed at preventing or ameliorating the disease. Multiparametric MRI techniques can measure changes in renal artery flow, tissue perfusion, and oxygenation repetitively over short time periods, enabling high time resolution. Furthermore, renal fibrosis can be quantified noninvasively by MRI diffusion tensor imaging, and techniques are upcoming to measure renal oxygen consumption. These techniques are all radiation and contrast‐free. We briefly present data, demonstrating that fMRI techniques can play a major role in future research in CKD, and possibly also in daily clinical practice. [ABSTRACT FROM AUTHOR]

This paper addresses tracking control problems for autonomous underwater vehicle (AUV) systems with coupled nonlinear functions. For the first time, the radial basis function (RBF) is applied to the model reference adaptive control system, and the vehicle horizontal plane model is proposed. When the AUV movement is affected by the driving force, ocean resistance, and the force generated by the water current, the expected output of the AUV's system is difficult to meet the expectations, making the AUV trajectory tracking problems challenging. There are two main options for finding suitable controllers for AUVs. The first is making the AUV model achieve better stability using a more complex controller. The second is the simpler controller structure, which can ensure faster system feedback. The RBF and model reference adaptive control (MEAC) system are combined to increase the number of hidden layers, increasing the AUV tracking stability. Because the embedded computing module of an AUV is a bit limited, 31 hidden layers are chosen to simplify the controller structures. A couple of Lyapunov functions are designed for the expected surge and sway velocities, and the vehicle tracking error gradually converges to (0,0). The controller design results are imported into the AUV actuator model by software, and after 0.64 s, the AUV tracking error is less than 1%. At last, the vehicle tracking experiments were carried out, showing that after 0.5 s, the AUV tracking error was less than 1%. [ABSTRACT FROM AUTHOR]

The pulse-jet cleaning process is a critical part of the bag filter workflow. The dust-cleaning effect has a significant impact on the operating stability of bag filters. Aiming at the multi-parameter optimization problem involved in the pulse-jet cleaning process of bag filters, the construction method of hybrid surrogate models based on second-order polynomial response surface models (PRSMs), radial basis functions (RBFs), and Kriging sub-surrogate models is investigated. With four sub-surrogate model hybrid modes, the corresponding hybrid surrogate models, namely PR-HSM, PK-HSM, RK-HSM, and PRK-HSM, are constructed for the multi-parameter optimization involved in the pulse-jet cleaning process of bag filters, and their objective function is the average pressure on the inner side wall of the filter bag at 1 m from the bag bottom. The genetic algorithm is applied to search for the optimal parameter combination of the pulse-jet cleaning process. The results of simulation experiments and optimization calculations show that compared with the sub-surrogate model PRSM, the evaluation indices RMSE, R 2 , and RAAE of the hybrid surrogate model RK-HSM are 9.91%, 4.41%, and 15.60% better, respectively, which greatly enhances the reliability and practicability of the hybrid surrogate model. After using the RK-HSM, the optimized average pressure F on the inner side wall of the filter bag at 1 m from the bag bottom is −1205.1605 Pa, which is 1321.4543 Pa higher than the average pressure value under the initial parameter condition set by experience, and 58.4012 Pa to 515.2836 Pa higher than using the three sub-surrogate models, verifying its usefulness. [ABSTRACT FROM AUTHOR]

The technological breakthrough and the availability of multispectral remote sensing data have given rise to an ambitious challenge for the classification of the multispectral images accurately to support administrative bodies in decision-making. In this paper, the multi-temporal medium resolution Sentinel-2 imagery of the densely populated urban area of Delhi-NCR is classified using SVM into five different land cover classes, namely water bodies, barren land, vegetative region, road network, and residential areas. Further, the effect of different kernel functions of SVM on land cover classification performance is contrasted and the radial basis function (RBF) leads to the best results. The experimental results are compared with the maximum likelihood classification (MLC) method on different evaluation metrics. The SVM with RBF kernel shows promising improvements in the overall accuracy by 10% relative to the polynomial kernel and by 3% compared to MLC. The analysis of multitemporal spectral imagery of the study area reflects the increase in a built-up area (road network, Buildings), water bodies, and decrement in the area of barren land and vegetation. [ABSTRACT FROM AUTHOR]

Fractional differential equations (FDEs) arising in engineering and other sciences describe nature sufficiently in terms of symmetry properties. This paper proposes a numerical technique to approximate ordinary fractional initial value problems by applying fractional radial basis function neural network. The fractional derivative used in the method is considered Riemann-Liouville type. This method is simple to implement and approximates the solution of any arbitrary point inside or outside the domain after training the ANN model. Finally, three examples are presented to show the validity and applicability of the method. [ABSTRACT FROM AUTHOR]

Accurate parameter estimation of photovoltaic (PV) cells is crucial for establishing a reliable cell model. Based on this, a series of studies on PV cells can be conducted more effectively to improve power output; an accurate model is also crucial for the operation and control of PV systems. However, due to the high nonlinearity of the cell and insufficient measured current and voltage data, traditional PV parameter identification methods are difficult to solve this problem. This article proposes a parameter identification method for PV cell models based on the radial basis function (RBF). Firstly, RBF is used to de-noise and predict the data to solve the current problems in the parameter identification field of noise data and insufficient data. Then, eight prominent meta-heuristic algorithms (MhAs) are used to identify the single-diode model (SDM), double-diode model (DDM), and three-diode model (TDM) parameters of PV cells. By comparing the identification accuracy of the three models in two datasets in detail, the final results show that this method can effectively achieve parameter extraction, with advantages such as high extraction accuracy and stability, greatly improving the accuracy and reliability of parameter identification. Especially in the TDM, the I-V data and P-V data obtained from the PV model established through the identified parameters have very high fitting accuracy with the measured I-V and P-V data, reaching 99.58% and 99.65%, respectively. The research can effectively solve the low accuracy problem caused by insufficient data and noise data in the traditional method of identifying PV cells and can greatly improve the accuracy of PV cell modeling. It is of great significance for the operation and control of PV systems. [ABSTRACT FROM AUTHOR]

Active suspension control technologies have become increasingly significant in improving suspension performance for driving stability and comfort. An RBF-based fractional-order SMC fault-tolerant controller is developed in this research to guarantee ride comfort and handling stability when faced with the partial loss of actuator effectiveness due to failure. To obtain better control performance, fractional-order theory and the RBF algorithm are discussed to solve the jitter vibration problem in SMC, and the RBF is exploited to obtain a more appropriate switching gain. First, a half-nonlinear active suspension model and a fault car model are presented. Then, the design process of the RBF-based fractional-order SMC fault-tolerant controller is described. Next, a simulation is presented to demonstrate the effectiveness of the proposed strategy. According to the simulation, the proposed method can improve performance in the case of a healthy suspension, and the fault-tolerant controller can guarantee the capabilities when actuators go wrong.

The performance of a ducted wind turbine was simulated in this study utilizing an artificial neural network under various duct operating conditions. Ducted wind turbines have been identified as one of the cleanest and most effective future renewable energy possibilities. Different methods have been used throughout time to exploit the flow stream power successfully. However, the Ducted Wind Turbine System is one method that is still in its early phases. The operation of the ducted wind turbine is analyzed in this research under different wind conditions. The ANN algorithm is recommended for generating turbine power at various wind speeds. The proposed neural network model is shown to perform better for estimating turbine power curves. The ANN models used the free-stream wind speed, wind speed in the throat section, turbulence intensity, and wind power in the intake part of the duct as input datasets and the output power of wind in the throat section as output datasets. At the same time, a three-layer backpropagation training method from the Multilayer Perceptron algorithm approach, a Levenberg–Marquardt, was selected as the best ANN. It was evaluated by comparing to a Radial-based functions approach with a single hidden layer. The optimum number of neurons in the MLP method’s first and second hidden layers, as well as the RBF method’s single hidden layer, has been determined to be 55 and 70, respectively. At 77 and 70 epochs, the best MSE evaluation efficiency of MLP and RBF networks was estimated to be 0. 000103 and 0. 000353, respectively.

In this work, adsorption and reduction of CO2 by carbon molecular sieves (CMS) was modeled using response surface methodology (RSM) and artificial neuron networks (ANNs). The CO2 adsorption experiments were carried out at temperature in range of 20–80 °C, pressure in range of 2–10 bar, and time in range of 0–1800 sec. 311 experimental data points of CO2 adsorption on the carbon molecular sieves are applied in the development of an ANN model. A Bayesian regularization algorithm was used as the best algorithm among of Scaled conjugate gradient back propagation and Levenberg-Marquardt back propagation for training the Multilayer perceptron (MLP) network. The best architecture is obtained after 100 epochs and it has 7 neurons in the first hidden layer, 8 neurons in the second hidden layer. The mean square error (MSE) value of 0.0006246 was obtained at 100 epochs for the best-developed MLP. Then, performance was compared with radial basis functions (RBF) algorithm. MLP, RBF and RSM models were efficient in the modelling of the CO2 adsorption with correlation coefficients of 0.99784, 0.9497 and 0.8958, respectively. The MLP showing good agreement between the experimental data and predicted data of CO2 adsorption via CMS (R2> 0.99). It is proved that ANN algorithm is a promising model for the prediction of CO2 adsorption by carbon molecular sieves.

In the present study, temperature of 313.15–473.15 K and pressure of 0.5–200 MPa have been developed for the CO2 solubility simulations via deep learning artificial (ANN) neural network approach and response surface methodology (RSM). Levenberg Marquardt backpropagation algorithm has been selected from MLP and compared with RBF. The number of neurons twenty and ten has been selected for the first and second hidden layers, respectively. RSM and ANN models for CO2 solubility produced mean R2 values of 0.9617 and 0.9998, respectively. The best MSE validation performance of MLP and RBF networks were 0.00294229 and 0.000190 at 6 and 150 epochs, respectively.

In this paper, we study the spectral properties of the periodized Radial Basis Function interpolation matrix as well as the related harmonic operators discretized using Radial Basis Functions. For Gaussian RBF, this procedure could be easily extended to an arbitrarily high dimensional space on a tensor-product grid as presented in the later parts of the paper. The experimental result of Boyd's condition number [1] is analytically well predicted in the context of periodized RBF. [ABSTRACT FROM AUTHOR]

Carbon dioxide (CO2) is a major greenhouse gas that causes global warming. In this study, piperazine‐modified activated alumina was used for CO2 capture process. The number of 626 experimental data were obtained at different operating conditions to develop the artificial neural networks (ANNs) and response surface methodology (RSM), employed to identify the behavior and performance of the CO2 capture process. Three independent factors, including time (t: 0–1800 s), temperature (T: 20–80°C), and pressure (P: 2.067–10.088 bar), were used as the input variables and CO2 adsorption capacity was used as the response. Among 243 different structures, the multilayer perceptron (MLP) model was optimized with Bayesian regularization backpropagation algorithm and two hidden layers with 17 and 16 neurons. The radial basis function (RBF) model was used with 367 different structures. The optimized structure of the RBF model was obtained with 100 neurons and the spread of 0.5. For optimal networks of MLP and RBF, the best mean square error (MSE) was observed at 1.72e‐04 and 8.28e‐05, and the best coefficient of determination (R2) was obtained 0.998 and 0.999, respectively. Moreover, the response surface methodology (RSM) was used to model the process. The best MSE and R2 values were obtained 0.00454 and 0.9462, respectively. The results showed that ANNs produced more accurate predictions than RSM. [ABSTRACT FROM AUTHOR]

The decanoic acid-palmitic acid composite phase change material compounds with SiO2 and TiO2 to prepare decanoic acid-palmitic acid/SiO2@TiO2 phase change microcapsules (D-P-SiO2@TiO2 PCM). The D-P-SiO2@TiO2 PCM could show efficient temperature regulation, remove pollutants through photocatalysis, and control air humidity. However, it is difficult to obtain the best experimental scheme directly using the traditional experimental setup due to the complicated photocatalytic-humidity performance. The radial basis function (RBF) model optimized the uniform experimental design parameters, and the D-P-SiO2@TiO2 PCM showed enhanced photocatalytic-humidity performance. The RBF-calculated preparation parameters were as follows: the molar ratio of decanoic acid-palmitic acid to tetraethyl silicate was 0.42, pH was 1.83, the molar ratio of deionized water to tetraethyl silicate was 98.15, while the molar rate of tetrabutyl titanate to tetraethyl silicate was 0.76. The degradation rate of gaseous formaldehyde by the RBF-optimized D-P-SiO2@TiO2 PCM was 69.57% after 6 h, and the moisture content was between 0.0923 and 0.0940 g·g−1 at 43.16–75.29% relative humidity (RH). The comparison between model optimization and the experiment sample prepared using the optimized parameters showed that the theoretical photocatalytic-humidity performance target value was 2.0502, and the tested target value was 2.0757. The error calculated from these two values was only 1.24%, and both were better than the best value of uniform experimental calculation. RBF mathematical model was proved to be an effective, convenient, and economic-saving method to simulate and predict D-P-SiO2@TiO2 PCM experimental design parameters. SEM and TEM analyses of the RBF-optimized D-P-SiO2@TiO2 PCM showed a uniform spherical structure, and the particle size analysis analyses was about 200 nm. The DSC analysis showed the phase transition temperature range was between 16.97 and 28.94 °C, within the comfort range of the human body. The UV–Vis investigations showed the absorption edge of the RBF-optimized D-P-SiO2@TiO2 PCM was 380 nm, in line with the band gap structure of the TiO2 anatase phase. The thermogravimetric investigations showed that this composite was stable at normal temperature and pressure. After a 100 times hot–cold cycle, the quality of the RBF-optimized D-P-SiO2@TiO2 PCM maintained its stability, as the photocatalytic-humidity performance was almost the same. The N2-adsorption analysis showed it had a high specific surface area and irregular pore structures, which could help it regulate air humidity. Considering these results, the D-P-SiO2@TiO2 PCM, a new ecological functional material, would be used in the construction industry to improve the architectural ecological environment. [ABSTRACT FROM AUTHOR]

This paper proposes a numerical scheme for the (2 + 1)‐dimensional nonlinear Zakharov–Kuznetsov–Benjamin–Bona–Mahony equation (ZK‐BBME). The ZK‐BBME represents a long‐wave model with large wavelength that explains the water wave phenomena in nonlinear dispersive system. The solution of the ZK‐BBME is discretized by using hybridization of the finite difference and localized radial basis function based on partition of unity method. The association of this hybridization leads to a meshless method and it does not requires any linearization. In the initial step, the PDE is converted into a nonlinear ODE system by making use of radial kernels. In the next step, the obtained nonlinear ODE system is solved based on an ODE solver of high order. The global collocation technique imposes a large computational cost because a dense algebraic system must be calculated. This proposed strategy is based on decomposing the initial domain into a number of sub‐domains using kernel approximation on each sub‐domain. Three numerical examples are illustrated to clarify the efficiency and accuracy of the proposed strategy. [ABSTRACT FROM AUTHOR]

Evaluating the permeability and irreducible water saturation of tight sandstone reservoirs is challenging. This study uses distribution functions to fit measured NMR T2 distributions of tight sandstone reservoirs and extract parameters for characterizing pore size distribution. These parameters are then used to establish prediction models for permeability and irreducible water saturation of reservoirs. Results of comparing the fit of the T2 distributions by the Gauss and Weibull distribution functions show that the fitting accuracy with the Weibull distribution function is higher. The physical meaning of the statistical parameters of the Weibull distribution function is defined to establish nonlinear prediction models of permeability and irreducible water saturation using the radial basis function (RBF) method. Correlation coefficients between the predicted values by the established models and the measured values of the tight sandstone core samples are 0.944 for permeability and 0.851 for irreducible water saturation, which highlight the effectiveness of the prediction models. [ABSTRACT FROM AUTHOR]

In this paper, we use the rational radial basis functions (RRBFs) method to solve the Korteweg-de Vries (KdV) equation, particularly when the equation has a solution with steep front or sharp gradients. We approximate the spatial derivatives by RRBFs method then we apply an explicit fourth-order Runge-Kutta method to advance the resulting semi-discrete system in time. Numerical examples show that the presented scheme preserves the conservation laws and the results obtained from this method are in good agreement with analytical solutions. [ABSTRACT FROM AUTHOR]

Fruit growth patterns are often exploited in predictions of final fruit size and to inform planting and harvesting decisions. Ten local apricot (Prunus armeniaca) varieties with superior genotypes (two early-ripening, five mid-ripening and three late-ripening varieties) were assessed using 20 nonlinear regression models (NRMs) and a radial basis function (RBF) neural network model. Fruit diameter and weight measurements for each genotype were collected at four-day intervals from fruit set to commercial harvest. Patterns based on diameter and weights were attributed to each genotype. Among the NRM tested, only four were able to flawlessly predict apricot diameter and weight during the growing season. In addition, comparison of nonlinear regression methods with the neural network indicated than the RBF model displayed fewer prediction errors than the NRMs. The RBF model predicted fruit size with a coefficient of determination (R2 value) greater than 0.95. Therefore, predictions of growth patterns in fruit trees can be accomplished with neural network modeling. [ABSTRACT FROM AUTHOR]

To improve the control precision of the nonlinear register system for flexographic printing, a feedforward active disturbance rejection control (ADRC) parameter self-tuning decoupling control strategy based on radial basis function (RBF) is proposed to address the existence of coupling interference and multiple working conditions. Firstly, according to the structure of the flexographic printing equipment system and registration principle, a nonlinear mathematical model of the global registration system is established and linearized using the small deviation method. Secondly, the decoupled controller of the register system is designed by integrating feedforward control, ADRC, and RBF, in which the feedforward control is used to eliminate the registration errors caused by modeled disturbances, the ADRC performs the estimation and compensation of unmodeled disturbances, and the RBF realizes the self-tuning of the ADRC controller parameters. Finally, different operating conditions are simulated to compare and verify the control performance of the proposed controller. Simulation results show that the designed controller has a better performance compared to traditional PID and ADRC control, and its register error peak is reduced by about 32% compared to ADRC, achieving the high accuracy control of a multi-color register system. [ABSTRACT FROM AUTHOR]

Since 1993, Devices based on CNTs have applicationsranging from nanoelectronics to optoelectronics. Thechallenging issue in designing these devices is that thenonequilibrium Green's function (NEGF) method has tobe employed to solve the Schrödinger and Poissonequations, which is complex and time consuming. In thepresent study, a novel smart and optimal algorithm ispresented for fast and accurate modeling of CNT fieldeffecttransistors (CNTFETs) based on an artificial neuralnetwork. A new and efficient way is presented forincrementally constructing radial basis function (RBF)networks with optimized neuron radii to obtain theestimator network. An incremental extreme learningmachine (I-ELM) algorithm is used to train the RBFnetwork. To ensure the optimal radii for incrementalneurons, this algorithm utilizes a modified version of anoptimization algorithm known as the Nelder-Meadsimplex algorithm. Results confirm that the proposedapproach reduces the network size for faster errorconvergence while preserving the estimation accuracy.

The growing complexity of industrial processes and manufactured parts, the growing need for safety in service and the desire to optimize the life of parts, require the implementation of increasingly complex quality assessments. Among the various anomalies to consider, sub-millimeter surface defects must be the subject of particular care. These defects are extremely dangerous as they are often the starting point for larger defects such as fatigue cracks, which can lead to the destruction of the parts.

Abstract Multifidelity surrogates (MFSs) replace computationally intensive models by synergistically combining information from different fidelity data with a significant improvement in modeling efficiency. In this paper, a modified MFS (MMFS) model based on a radial basis function (RBF) is proposed, in which two fidelities of information can be analyzed by adaptively obtaining the scale factor. In the MMFS, an RBF was employed to establish the low-fidelity model. The correlation matrix of the high-fidelity samples and corresponding low-fidelity responses were integrated into an expansion matrix to determine the scaling function parameters. The shape parameters of the basis function were optimized by minimizing the leave-one-out cross-validation error of the high-fidelity sample points. The performance of the MMFS was compared with those of other MFS models (MFS-RBF and cooperative RBF) and single-fidelity RBF using four benchmark test functions, by which the impacts of different high-fidelity sample sizes on the prediction accuracy were also analyzed. The sensitivity of the MMFS model to the randomness of the design of experiments (DoE) was investigated by repeating sampling plans with 20 different DoEs. Stress analysis of the steel plate is presented to highlight the prediction ability of the proposed MMFS model. This research proposes a new multifidelity modeling method that can fully use two fidelity sample sets, rapidly calculate model parameters, and exhibit good prediction accuracy and robustness.

This study provides a numerical scheme for solving nonlinear third-kind Volterra delay integral equations (VDIEs) using mesh-free approaches based on the collocation technique with radial basis functions (RBFs). The proposed approach is stable and requires less computer memory. It combines RBFs and a collocation method technique based on scattered points to represent the solution of third-kind VDIEs by interpolating RBFs using Legendre-Gauss–Lobatto nodes and weights. A description of the approach to the suggested equations is presented. Furthermore, the error analysis of the proposed scheme is investigated. A numerical example that clearly illustrates the validity of the proposed scheme is presented. This problem was also compared with the moving least squares collocation technique and other methods, demonstrating the reliability and efficiency of this approach for solving third-kind VDIEs. [ABSTRACT FROM AUTHOR]

We systematically investigate the prediction of nuclear charge radii using a support vector regression (SVR) model in machine learning(ML), specifically employing a radial basis function (RBF) kernel. Our model is designed to capture the global structure of the radius surface through the utilization of feature spaces encompassing both ( N , Z ) and ( N , Z , A ). We achieved a root mean square deviation of 0.019 fm with respect to 885 measured charge radii ( Z $\unicode{x2A7E}$ 8). By incorporating the atomic mass number as an additional feature, the model successfully reproduces the charge radii of ( $ ^{40-50}$ Ca), ( $ ^{74-96}$ Kr), ( $ ^{120-148}$ Ba), and ( $ ^{183-199}$ Au) isotopes. Furthermore, our ML method demonstrated an extrapolation capability with a deviation of 0.016 fm relative to 10 022 calculated charge radii based on the Weizsacker–Skyrme model. The SVR model’s performance is further tested across different regions of the charge radii table, demonstrating significant agreement with experimental data and underscoring the efficacy of the RBF kernel in nuclear charge radii prediction.