Function Neural Network Model Research Articles

Radial Basis Function Neural Network and Response Surface Methodology-Based Optimization of Glue Breakage in Waste Drilling Fluids

This paper aims to solve the problems of difficult breakage and low water yield of wastewater-based drilling fluids. The effects of breakage agent dosage, reaction temperature, stirring speed, and pumping time on the water yield of wastewater-based drilling fluids were analyzed through one-way experiments, and these parameters were optimized by Response Surface Methodology (RSM). A Radial Basis Function Neural Network (RBF) model was also introduced to compare its performance with that of RSM in predicting optimal process conditions. To further improve the accuracy of the model, a combination of Genetic Algorithm (GA) and RBF was used for optimization. The results show that both RSM and RBF models can predict the water yield of wastewater-based drilling fluids with high accuracy, in which the coefficient of determination of the RSM model is 0.9939, which is better than that of the RBF model (0.9778). The optimal operating conditions are determined through numerical optimization: the amount of glue breaker added is 3.97 kg/m3, the reaction temperature is 51 °C, the stirring speed is 419 rpm, and the maximum water yield is 62.37%, which is the best-predicted water yield. The GA-RBF coupled model performed better in terms of root mean square error (RMSE), coefficient of determination (R2 = 0.998), and mean absolute error (MAE), and the t-test verified that there was no significant difference between the predicted and actual values. The maximum value of the water yield of the waste mud could reach 61.97% when the gum breaker was added at 3.83 kg/m3, the reaction temperature was 53 °C, and the stirring speed was 424 rpm, which provided an accurate and reliable theoretical basis and technical support for the harmless treatment of deep and complex drilling fluids.

Heterogeneous virus classification using a functional deep learning model based on transmission electron microscopy images

Viruses are submicroscopic agents that can infect other lifeforms and use their hosts’ cells to replicate themselves. Despite having simplistic genetic structures among all living beings, viruses are highly adaptable, resilient, and capable of causing severe complications in their hosts’ bodies. Due to their multiple transmission pathways, high contagion rate, and lethality, viruses pose the biggest biological threat both animal and plant species face. It is often challenging to promptly detect a virus in a host and accurately determine its type using manual examination techniques. However, computer-based automatic diagnosis methods, especially the ones using Transmission Electron Microscopy (TEM) images, have proven effective in instant virus identification. Using TEM images collected from a recent dataset, this article proposes a deep learning-based classification model to identify the virus type within those images. The methodology of this study includes two coherent image processing techniques to reduce the noise present in raw microscopy images and a functional Convolutional Neural Network (CNN) model for classification. Experimental results show that it can differentiate among 14 types of viruses with a maximum of 97.44% classification accuracy and F1-score, which asserts the effectiveness and reliability of the proposed method. Implementing this scheme will impart a fast and dependable virus identification scheme subsidiary to the thorough diagnostic procedures.

Grain storage temperature prediction based on chaos and enhanced RBF neural network

Grain storage has very strict temperature requirements. Aiming at the problems of nonlinear characteristics and poor prediction accuracy of temperature parameters in grain storage, a combination of chaos theory and enhanced radial basis neural network is proposed as a temperature prediction model for grain storage (C-ERBF). The model first determines the embedding dimension and time delay of the grain storage temperature sequence using chaos theory. It then calculates the Lyapunov exponent to confirm its chaotic properties and reconstructs the sequence in the phase space to extract the hidden dynamic information and structure behind the sequence. Furthermore, the q-Normalized Least Mean Square Fourth (qXE-NLMF) algorithm is designed to enhance the radial basis function (RBF) neural network model for weight updating, to improve its prediction accuracy, and to accelerate the training speed of the model. As verified by the simulation experiments of Mackey–Glass chaotic time series prediction, the enhanced RBF (ERBF) network has faster convergence speed and lower steady-state error compared to the traditional RBF network. Finally, the optimized dataset from chaos theory is input into the model to achieve accurate predictions of grain storage temperature series. The experimental results show that the proposed C-ERBF model has higher prediction accuracy compared to other time series prediction methods. It can realize the grain pile temperature in advance, and take control measures in advance. This proactive approach significantly reduces the consumption of stored grain and prevents issues before they arise.

Adaptive neural network backstepping control for the magnetorheological semi-active air suspension system with uncertain mass and time-varying input delay

Aiming at rejecting external disturbance induced by the random road profile, this paper proposes an adaptive robust control strategy to address the control problem of semi-active air suspension system installed with magnetorheological dampers (MRD) for enhancing ride comfort and handling performance. To effectively depict the inherent nonlinear dynamics of the adjustable air spring, a radial basis function neural network (RBFNN) model is trained by the experimental data offline, and an adaptive learning algorithm is introduced to maintain the modeling accuracy. Moreover, to handle the prevalent sensitive parameter variation (such as sprung mass), a nonlinear estimator is designed to estimate the uncertain sprung mass. Furthermore, a delay compensator is integrated into the control law to mitigate the impact of the time-varying input delay caused by the actuator of MRD to restrain the chattering phenomena. Additionally, the stability of the closed-loop system is rigorously proven by employing a Lyapunov–Krasovskii functional, guaranteeing the boundedness of both tracking error and estimation error. Simulation results are displayed and analyzed, illustrating the feasibility and efficiency of the proposed control strategy in depressing the sprung mass acceleration and tire deflection, showing its significance in both control performance enhancement and chattering elimination.

Strategic optimization of dual-fuel diesel/gas engines by numerical approach for environmental and economic benefits

The study introduces a framework for optimizing eco-friendly dual-fuel engines, combining CFD and ANN, to reduce carbon emissions and improve sustainable transportation.We achieved optimal performance with a 52–65 % NG substitution ratio. SOI timing had a big effect on NOx emissions; later injection decreased NOx formation because it made the mixture more homogeneous. We developed a radial basis function neural network model to predict engine performance and emissions with 99 % accuracy. The study examines the effect of fuel droplet spraying on cylinder walls on engine performance and emissions, utilizing response surface methodology to create engine maps. Numerical experiments revealed that a lowered natural gas replacement ratio of less than 50 % resulted in decreased flame propagation and the attainment of a burn mixture mode. The decrease in flame propagation speed during CA10 led to a fivefold increase in CO emissions. As the NG substitution ratio exceeded 50 %, the air/fuel ratio neared equilibrium, resulting in a reduction in NOx emissions and in-cylinder combustion temperature. Nevertheless, the highest RoHR level decreased by 25 %. The downward trend proceeded until the natural gas substitution ratio reached to 90 %. The TOPSIS method was utilized to identify optimal operating conditions for DFDI engines, offering valuable insights for efficiency and emissions reduction.

Stability analysis of flying wing layout aircraft based on radial basis function neural network model

PurposeTo ensure the stability of the flying wing layout unmanned aerial vehicle (UAV) during flight, this paper uses the radial basis function neural network model to analyse the stability of the aforementioned aircraft.Design/methodology/approachThis paper uses a linear sliding mode control algorithm to analyse the stability of the UAV's attitude in a level flight state. In addition, a wind-resistant control algorithm based on the estimation of wind disturbance with a radial basis function neural network is proposed. Through the modelling of the flying wing layout UAV, the stability characteristics of a sample UAV are analysed based on the simulation data. The stability characteristics of the sample UAV are analysed based on the simulation data.FindingsThe simulation results indicate that the UAV with a flying wing layout has a short fuselage, no tail with a horizontal stabilising surface and the aerodynamic focus of the fuselage and the centre of gravity is nearby, which is indicative of longitudinal static instability. In addition, the absence of a drogue tail and the reliance on ailerons and a swept-back angle for stability result in a lack of stability in the transverse direction, whereas the presence of stability in the transverse direction is observed.Originality/valueThe analysis of the stability characteristics of the sample aircraft provides the foundation for the subsequent establishment of the control model for the flying wing layout UAV.

GNSS-IR Soil Moisture Retrieval Using Multi-Satellite Data Fusion Based on Random Forest

The accuracy and reliability of soil moisture retrieval based on Global Positioning System (GPS) single-star Signal-to-Noise Ratio (SNR) data is low due to the influence of spatial and temporal differences of different satellites. Therefore, this paper proposes a Random Forest (RF)-based multi-satellite data fusion Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) soil moisture retrieval method, which utilizes the RF Model’s Mean Decrease Impurity (MDI) algorithm to adaptively assign arc weights to fuse all available satellite data to obtain accurate retrieval results. Subsequently, the effectiveness of the proposed method was validated using GPS data from the Plate Boundary Observatory (PBO) network sites P041 and P037, as well as data collected in Lamasquere, France. A Support Vector Machine model (SVM), Radial Basis Function (RBF) neural network model, and Convolutional Neural Network model (CNN) are introduced for the comparison of accuracy. The results indicated that the proposed method had the best retrieval performance, with Root Mean Square Error (RMSE) values of 0.032, 0.028, and 0.003 cm3/cm3, Mean Absolute Error (MAE) values of 0.025, 0.022, and 0.002 cm3/cm3, and correlation coefficients (R) of 0.94, 0.95, and 0.98, respectively, at the three sites. Therefore, the proposed soil moisture retrieval model demonstrates strong robustness and generalization capabilities, providing a reference for achieving high-precision, real-time monitoring of soil moisture.

Radial basis function neural network and overlay sampling uniform design toward polylactic acid molecular weight prediction

Polylactic acid (PLA) is a potential polymer material as a substitute for traditional plastics, and the accurate molecular weight distribution range of PLA is strictly required in practical applications. Therefore, exploring the relationship between synthetic conditions and PLA molecular weight is crucially important. In this work, direct polycondensation combined with overlay sampling uniform design (OSUD) was applied to synthesize the low molecular weight PLA. Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature, reaction time, and catalyst dosage were developed for PLA molecular weight prediction. The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method. Meanwhile, the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight. Among them, both artificial neural network models had significantly better predictive performance than the regression model. Notably, the radial basis function neural network model had the best predictive accuracy with only 11.9% of mean relative error on the validation dataset, which improved by 67.7% compared with the traditional multiple regression model. This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD, which provided guidance for the future implementation of molecular weight-controlled polymer’ synthesis.

Early diagnosis of Cladosporium fulvum in greenhouse tomato plants based on visible/near-infrared (VIS/NIR) and near-infrared (NIR) data fusion

Plant diseases can inflict varying degrees of damage on agricultural production. Therefore, identifying a rapid, non-destructive early diagnostic method is crucial for safeguarding plants. Cladosporium fulvum (C. fulvum) is one of the major diseases in tomato growth. This work presents a method of data fusion using two hyperspectral imaging systems of visible/near-infrared (VIS/NIR) and near-infrared (NIR) spectroscopy for the early diagnosis of C. fulvum in greenhouse tomatoes. First, hyperspectral images of samples at health and different times of infection were collected. The average spectral data of the image regions of interest were extracted and preprocessed for subsequent spectral datasets. Then different classification models were established for VIS/NIR and NIR data, optimized through various variable selection and data fusion methods. The principal component analysis-radial basis function neural network (PCA-RBF) model established using low-level data fusion achieved optimal results, achieving accuracies of 100% and 99.3% for calibration and prediction, respectively. Moreover, both the macro-averaged F1 (Macro-F1) values reached 1, and the geometric mean (G-mean) values reached 1 and 1, respectively. The results indicated that it was feasible to establish a PCA-RBF model by using the hyperspectral technique with low-level data fusion for the early detection of C. fulvum in greenhouse tomatoes.

Radial Basis Function Neural Network with ensemble clustering for modeling mathematics achievement in Indonesia based on cognitive and non-cognitive factors

Mathematics achievement could be influenced by cognitive and non-cognitive factors. The potential variable of cognitive factor is metacognition, whereas non-cognitive factors include Economic, Social, and Cultural Status (ESCS), resilience, life satisfaction, happiness, pride, fear, sadness, and gender. Those variables involve numerical and categorical data. For this reason, this study aims to apply the Radial Basis Function Neural Network (RBFNN) model with ensemble clustering to model the relation between cognitive and non-cognitive aspects and mathematics achievement. The RBFNN is a soft computing approach based on the neural network model and has been shown as an effective model and free of assumption. The ensemble clustering is a process in RBFNN modeling to capture the independent variables involving the numerical and categorical data. It employs K-means clustering for the numerical data and K-modes for categorical data and combines the results of those two methods. The data used in this study are published by PISA (Program for International Student Assessment) 2018. The results show that the RBFNN with ensemble clustering deliver good performance in modeling the students’ mathematics achievement based on the cognitive and non-cognitive factors in terms of prediction accuracy. Other than RBFNN model, the use of cognitive and non-cognitive factors involving in this study also contributes to the high accuracy prediction. This further emphasizes that these factors are good predictors of mathematic achievement. Additionally, we suggest the silhouette cluster validation in the clustering process, since it leads to the number of hidden neurons of the best RBFNN model.

Enhancing slope stability prediction using a multidisciplinary approach and radial basis function neural network: A case study on the Jelapang rock slope in Perak

Accurately predicting the stability of complex high rock slopes is crucial to prevent infrastructure damage and potential casualties. Existing studies have primarily relied on linear or log-linear regression models based on laboratory data, limiting their practical application. In this study focused on the Jelapang rock slope in Perak, a multidisciplinary approach combining geological, geotechnical, and remote sensing analyses was employed to consider various rock mass properties and slope geometrical parameters. The Rock Mass Rating (RMR), Slope Mass Rating (SMR), and factor of safety (FOS) were computed for 48 regions of the rock slope. Subsequently, a Radial Basis Function Neural Network (RBFNN) model was utilised to predict the FOS, RMR, and SMR. Three RBFs were developed: RBF-1 for estimating the factor of safety, RBF-2 for rock mass rating, and RBF-3 for slope mass rating. For comparison purposes, the performance of the RBFNN models was compared with Multilayer Perceptron (MLP) models. The results demonstrated that the optimised RBFNN model provided a state-of-the-art technique for accurately predicting and controlling slope stability. Notably, the RBFNN models exhibited remarkable precision, as indicated by root-mean-squared error (RMSE) values of 2.02172e-30 for the training process of RBF-1, 7.58671e-28 for RBF-2, and 2.71129e-27 for RBF-3. Comparison results revealed that the RBF models outperformed the MLPs. Additionally, sensitivity analysis results indicated that Uniaxial Compressive Strength (UCS) had the highest effect on the FOS.

The Evaluation and Prediction of Flame Retardancy of Asphalt Mixture Based on PCA-RBF Neural Network Model.

Warm mix flame retardant asphalt mixture can reduce the energy dissipation and harmful gas emissions during asphalt pavement construction, as well as mitigate the adverse effects of road fires. For this, this paper studies the design and performance of a mixture modified with a combination of warm mix agent and flame retardant, and the pavement performance and flame retardancy of the modified mixture are evaluated. Additionally, a flame retardancy prediction model based on the radial basis function (RBF) neural network model is established. On this basis, the principal components analysis (PCA) model is used to analyze the most significant evaluation indicators affecting flame retardancy, and finally, a three-dimensional finite element model is developed to analyze the effects of loading on the pavement structure. The results show that compared to virgin asphalt mixture, the modified mixture shows a reduction in mixing and compaction temperatures by approximately 12 °C. The high-temperature performance of the mixture is improved, while the low-temperature performance and moisture stability slightly decrease, but its flame retardancy is significantly enhanced. The RBF neural network model revealed that the established flame retardancy prediction model has a high accuracy, allowing for precise evaluation of the flame retardancy. Finally, the PCA model identified that the combustion time has a significant effect on the flame retardancy of the asphalt mixture, and the finite element model revealed that the displacements of the warm mix fire retardant asphalt mixture were lower than virgin asphalt mixture in all directions under the loading.

Computational intelligence modelling of methylene blue adsorption by metal-organic frameworks

ABSTRACT Computational intelligence models for wastewater treatment utilise mathematical algorithms to simulate and optimise the processes involved in the removal of pollutants from wastewater, aiding in the design and operation of the wastewater treatment plant. The aim of this work was to compare the efficiency of computational models in modelling the dynamic adsorption of dyes. Metal-organic frameworks (MOFs) are considered as adsorbents because of their excellent properties. Further, the dataset used for this study was sourced from literature pertaining to the adsorption of methylene blue (MB), which is one of the commonly found dyes in wastewater. Adsorption parameters considered for the study are initial concentration, bed height, flow rate, pH and time, for the continuous adsorption process. The efficacy of the selected computational models was compared by employing various statistical metrics. Moreover, the results show the efficiency of artificial neural network and radial basis function neural network models is superior to other models based on R2 and mean square error, which were in the range of 0.95–0.999 and 10–3–10–5, respectively. In summary, the computational intelligence models serve as the best tools for the prediction of the adsorption performance of MOFs for MB.

Susceptibility Mapping of Thaw Slumps Based on Neural Network Methods along the Qinghai–Tibet Engineering Corridor

Climate warming has induced the thawing of permafrost, which increases the probability of thaw slump occurrences in permafrost regions of the Qinghai–Tibet Engineering Corridor (QTEC). As a key and important corridor, thaw slump distribution is widespread, but research into effectively using neural networks to predict thaw slumping remains insufficient. This study automated the identification of thaw slumps within the QTEC and investigated their environmental factors and susceptibility assessment. We applied a deep learning-based semantic segmentation method, combining U-Net with ResNet101, to high spatial and temporal resolution images captured by the Gaofen-1 images. This methodology enabled the automatic delineation of 455 thaw slumps within the corridor area, covering 40,800 km², with corresponding precision, recall, and F1 scores of 0.864, 0.847, and 0.856, respectively. Subsequently, employing a radial basis function neural network model on this inventory of thaw slumps, we investigated environmental factors that could precipitate the occurrence of thaw slumps and generated sensitivity maps of thaw slumps along the QTEC. The model demonstrated high accuracy, and the area under the curve (AUC) value of the receiver operating characteristic (ROC) curve reached 0.95. The findings of the study indicate that these thaw slumps are predominantly located on slopes with gradients of 1–18°, distributed across mid-elevation regions ranging from 4500 to 5500 m above sea level. Temperature and precipitation were identified as the predominant factors that influenced the distribution of thaw slumps. Approximately 30.75% of the QTEC area was found to fall within high to extremely high susceptibility zones. Moreover, validation processes confirmed that 82.75% of the thaw slump distribution was located within areas of high or higher sensitivity within the QTEC.

Construction and Validation of Surface Soil Moisture Inversion Model Based on Remote Sensing and Neural Network

Surface soil moisture (SSM) reflects the dry and wet states of soil. Microwave remote sensing technology can accurately obtain regional SSM in real time and effectively improve the level of agricultural drought monitoring, and it is of great significance for agricultural precision irrigation and smart agriculture construction. Based on Sentinel-1, Sentinel-2, and Landsat-8 images, the effect of vegetation was removed by the water cloud model (WCM), and SSM was retrieved and validated by a radial basis function (RBF) neural network model in bare soil and vegetated areas, respectively. The normalized difference vegetation index (NDVI) calculated by Landsat-8 (NDVI_Landsat-8) had a better effect on removing the influence the of vegetation layer than that of NDVI_Sentinel-2. The RBF network model, established in a bare area (R = 0.796; RMSE = 0.029 cm3/cm3), and the RBF neural network model, established in vegetated areas (R = 0.855; RMSE = 0.024 cm3/cm3), have better simulation effects on SSM than a linear SSM inversion model with single polarization. The introduction of surface parameters to the RBF neural network model can improve the accuracy of the model and realize the high-accuracy inversion of SSM in the study area.

Online identification and feed-forward compensation of nonlinear friction in servo system based on RBF neural network model

In this paper, an online identification and compensation method of nonlinear friction based on radial basis function (RBF) neural network model is proposed for the influence of nonlinear friction on machining accuracy in the low speed process of servo feed system of CNC machine tools. First, a three-layer single-input-output RBF neural network model is established for describing the nonlinear friction of servo feeding system. Second, the neural network online learning algorithm is improved based on adaptive gain, which improves the stability and accuracy of the algorithm. Finally, experiments were carried out on a three-axis milling machine to compensate the friction in the servo feed system in real time based on the online identification results. The results show that the method can effectively improve the online identification accuracy and convergence rate, and effectively improved the low-speed performance of the servo feed system.

RBFNN-based UWB 4×4 MIMO Antenna Design with Compact Size, High Isolation, and Improved Diversity Performance for Millimeter-Wave 5G Applications

Abstract The millimeter-wave spectrum has emerged as a compelling solution to address the pressing need for high-datarate
capabilities in the development of 5G technology systems. Spanning between 20 GHz and 40 GHz, this spectrum
encompasses several prominent frequency bands crucial for advancing 5G applications. In light of this, our study
presents a thorough investigation into the design and performance of a compact cross-shaped slot broadband antenna,
complemented by a 4×4 Multiple-InputMultiple-Output (MIMO) configuration tailored for 5G operations at
28 GHz. The primary objective of this study is to develop an antenna system capable of achieving an extended bandwidth
ranging from 20 GHz to 40 GHz, effectively covering the crucial frequency bands essential for 5G millimeterwave(
mmWave) operations. To accomplish this, the optimization of antenna performance is meticulously carried out
using the Radial Basis FunctionNeuralNetworks (RBFNN) model. The RBFNNmodel serves as a robust tool for establishing
the intricate relationship between antenna dimensions, resonant frequency, and bandwidth. Subsequently,
the developed RBFNN model is employed to predict optimal antenna dimensions, ensuring resonance at 28 GHz and
meeting specified bandwidth targets. The single antenna is designed with a rectangular patch and a cross-shaped
slot and is constructed on the low loss Rogers RT Duroid 5880 substrate. This design reaches an outstanding bandwidth
of 19.5 GHz, and exhibits excellent radiation characteristics, with a high radiation efficiency of up to 99% and a
corresponding gain of 5.75 dB. The antenna’s design and performance are rigorously designed using HFSS software,
which is then compared to the results acquired using CST software. In addition, the proposed MIMO configuration
offers excellent performance in terms of key features such as small size (16 × 16.2 mm2), very wide bandwidth of 20
GHz, good gain of 6.75 high isolation exceeding 35 dB, and significant improvements in diversity performance measures
such as Envelope Correlation Coefficient (ECC), Diversity Gain (DG), Channel Capacity Loss (CCL), Total Active
Reflection Coefficient (TARC), and Mean Effective Gain (MEG). The potential of the proposed MIMO configuration
for high-speed applications is particularly remarkable. Practical verification of the MIMO configuration is carefully
carried out by fabrication andmeasurement. Experimental results strongly confirmthe effectiveness of the proposed
antenna design, establishing it as a competitive challenger for 5G technology.

Learning active subspaces and discovering important features with Gaussian radial basis functions neural networks

Providing a model that achieves a strong predictive performance and is simultaneously interpretable by humans is one of the most difficult challenges in machine learning research due to the conflicting nature of these two objectives. To address this challenge, we propose a modification of the radial basis function neural network model by equipping its Gaussian kernel with a learnable precision matrix. We show that precious information is contained in the spectrum of the precision matrix that can be extracted once the training of the model is completed. In particular, the eigenvectors explain the directions of maximum sensitivity of the model revealing the active subspace and suggesting potential applications for supervised dimensionality reduction. At the same time, the eigenvectors highlight the relationship in terms of absolute variation between the input and the latent variables, thereby allowing us to extract a ranking of the input variables based on their importance to the prediction task enhancing the model interpretability. We conducted numerical experiments for regression, classification, and feature selection tasks, comparing our model against popular machine learning models, the state-of-the-art deep learning-based embedding feature selection techniques, and a transformer model for tabular data. Our results demonstrate that the proposed model does not only yield an attractive prediction performance compared to the competitors but also provides meaningful and interpretable results that potentially could assist the decision-making process in real-world applications. A PyTorch implementation of the model is available on GitHub at the following link.11https://github.com/dannyzx/Gaussian-RBFNN.

Thermal resistance optimization of ultra-thin vapor chamber based on data-driven model and metaheuristic algorithm

The ultra-thin vapor chamber(UTVC) is extensively utilized across various fields due to its excellent heat dissipation performance and good temperature uniformity. The data-driven modeling approach is well suited to predict the thermal resistance of the UTVC due to its great flexibility and accuracy. In this paper, a novel approach is proposed to optimize the UTVC thermal resistance, which combines the radial basis function neural network(RBFNN) model with an improved adaptive differential fish swarm evolution algorithm(ADFEA). The mean square error of the RBFNN model was 0.00016 on the training set and 0.00027 on the test sets, which indicates that the model is able to accurately predict the thermal resistance of the UTVC. The data are obtained from experiments on a mesh wick UTVC with dimensions of 124 × 14 × 1 mm. A novel optimization algorithm, ADFEA, has been designed to enhance optimization capability and convergence accuracy. This algorithm combines differential algorithm and artificial fish swarm algorithm, incorporating a parameter adaptation mechanism. The optimal operating parameters of the UTVC are obtained by ADFEA optimization and the accuracy of the optimized results is verified by experiment. The proposed optimization method provides new insights for the design and optimization of UTVC.

Research on thermal efficiency and weld forming coefficient prediction of ultra-high strength steel welded joint under different energy inputs

As an ultra-high strength steel, Al–Si coated 22MnB5 hot stamping steel is widely used in the manufacturing of body-in-white structural parts. Compared with traditional welding technology, laser welding is widely used in the field of automobile body-in-white manufacturing due to its high energy density, small heat affected zone, and high weld quality. For ultra-high strength steel laser welded joints, the weld forming coefficient is an important index to reflect the welding quality. In order to investigate the influence of weld forming coefficient on the Al content and the thermal efficiency, laser welding experiments of ultra-high strength steel under different laser energy inputs are carried out. The melting of the base metal and coating under different laser energy inputs is also considered. Particle swarm optimization (PSO) algorithm is introduced into radial basis function (RBF) neural network model to optimize the central parameters as the RBF neural network model alone is not sufficient in predicting the outcomes. The results shows that if the laser power density is constant (7 × 105 W/cm2), when laser energy inputs are 400 J/cm to 1200 J/cm, the Al content in welded joints is 1.458%–1.886%, the melting efficiency of welded joints is 0.23–0.26, the energy conversion efficiency of welded joints is 0.45–0.46. When the laser energy inputs are lower than 522 J/cm, the Al content of the laser welded joint increases gradually. When the laser energy inputs are higher than 522 J/cm, the Al content of the laser welded joint decreases. The root mean square error(RMSE) of PSO-optimized RBF neural network testing sets prediction results is 0.1551, R-square (R2) is 0.771 and mean absolute percentage error (MAPE) is 2.758%. The prediction accuracy of the PSO-optimized RBF neural network model for the upper surface weld width, waist weld width, and lower surface weld width is 93.9%, 91.1%, and 92.2%.