Search

Metaheuristic methods are optimization techniques generally based on natural or physical phenomena. Although these processes inspire, the underlying mechanisms of these phenomena still need to be fully understood. Translating these mechanisms into algorithmic solutions may lead to unclear strategies, whose performance can exhibit unpredictable behavior. On the other hand, a radial basis function neural network (RBFNN) is a powerful method for approximating highly complex functions through a training process. Its key advantage lies in its interpretable structure, which allows us to understand the underlying relationships among the input–output data. This paper proposes a new metaheuristic algorithm based on the architecture of an RBFNN. Under this approach, an RBFNN is trained to approximate the objective function based on initial input data distributed from the search space. After training, the radial basis functions and weights associated with the neurons that maintain a strong influence or contribution to obtain the highest values of the cost function are determined. The parameters of these radial basis functions define the promissory regions of the input space that are used to produce the individuals of the new population through the Latin hypercube sampling technique. Therefore, during the optimization process, different regions of the search space represented by radial basis functions are explored and exploited as the accuracy of the cost function approximation increases. The experimental results demonstrated the success of our approach, as it outperformed the established metaheuristic algorithms on various benchmark functions. [ABSTRACT FROM AUTHOR]

When calculating the seismic response of structures, conventional methods often neglect uncertainty and suffer from excessive computation. Although robustness metrics have been effective in evaluating structural safety, they are not suitable for isolated continuous girder bridges (ICGB). To address this issue, this paper introduces an uncertain seismic response and robustness assessment method tailored to ICGB: Firstly, the method considers uncertainty in material parameters and ground motion by constructing a data set using Monte Carlo simulation. Secondly, a genetic algorithm for parallel optimisation of radial basis function neural network (GAPO-RBFNN) is trained to predict the seismic responses of the bridges. Thirdly, a robustness metric specifically designed for bridges is derived and applied to bridge. Finally, the proposed robustness metric is validated on lead rubber bearing (LRB) and shape memory alloy-lead rubber bearing (SMA-LRB) bridges. Results indicate that the GAPO-RBFNN model accurately approximates the mapping relationship between structural parameters and seismic response, with an average error of only 0.32% and a 70% reduction in computation time compared with traditional methods. Moreover, the new robustness metric overcomes the limitations of the dismantled member method and is applicable to bridge. The robustness of the SMA-LRB-ICGB, strengthened by SMA, is improved, providing evidence of the effectiveness of the proposed robustness metric. [ABSTRACT FROM AUTHOR]

This article is the first attempt in the open literature to investigate the impact of uncertainty in material properties on the critical buckling speed of rim-driven rotating laminated plates. The formulations are constructed using the isogeometric approach (IGA) and higher-order shear deformation theory (HSDT). Coriolis and centrifugal forces resulting from rotation are taken into consideration. The results of the current formulation are compared to the previous results and validated. The accuracy and flexibility of the RBFN-based surrogate model, designed for uncertainty analysis, is verified by comparing the result with Monte Carlo simulation (MCS). Through a variety of parametric experiments, the critical buckling speed of rotating laminates driven by a rim is stochastically analyzed. Variance-based sensitivity analysis is employed to identify the influence of individual material properties on the critical buckling speed. Further, the impact of sensitive properties on the probability of structural failure is estimated. This research can be used to forecast the probability of failure of a structure at various levels of material uncertainty associated with it. [ABSTRACT FROM AUTHOR]

A composite control strategy is proposed to improve the position-tracking performance and anti-interference capabilities of permanent magnet synchronous motors (PMSMs). This strategy integrates an active disturbance rejection controller (ADRC) and a radial basis function neural network (RBFNN) with feedforward control. Initially, the flexibility and robustness of the ADRC are utilized in the position loop control. Subsequently, the parameters of the extended state observer (ESO) within the ADRC are optimized, benefiting from the fast convergence speed and optimal approximation provided by the RBFNN. To further enhance the dynamic tracking performance, a differential feedforward link is introduced between the desired speed and the output signal. The simulation and experimental results demonstrate that when the expected electrical angle inputs are sinusoidal and pulse signals, the incorporation of the feedforward link and the adjustment of parameters in the ADRC lead to improved position-tracking capabilities and greater adaptability to load disturbances. [ABSTRACT FROM AUTHOR]

This paper aimed to realize the accurate prediction of the daily reference crop water requirement of the water storage pit irrigation apple orchard based on the limited meteorological data. According to the data of daily temperature and humidity data of the water storage pit irrigation orchard at the Institute of Shanxi Academy of Agricultural Sciences, an ET0 prediction model based on radial basis neural network was built. The simulation results and the calculation results of the two commonly used ET0 calculation formulas of Hargreaves and Priestley-Taylor were compared with the standard values calculated by the FAO-PM formula. The results show that the simulation results of the radial basis neural network model are closer to the standard values calculated by the FAO-PM formula. The calculation results of the Hargreaves formula and the Priestley-Taylor formula are larger than that of the standard values, which should be corrected by coefficients in practical applications. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract In this paper, an artificial intelligence approach has been employed to analyze the slump and compressive strength (CS) of high-performance concrete (HPC), focusing on its mechanical properties. The importance of assessing these critical concrete characteristics has been widely acknowledged by experts in the field, leading to the development of innovative methods for estimating parameters that typically require laboratory testing. These intelligent techniques improve the accuracy of mechanical property predictions and reduce the resource-intensive and costly nature of experimental work. The radial basis function neural network (RBFNN) is the foundational model for predicting the mechanical attributes of various HPC mixtures. To fine-tune the RBFNN’s performance in replicating the mechanical properties of HPC samples, two optimization algorithms, namely the Golden Eagle Optimizer (GEO) and Dynamic Arithmetic Optimization Algorithm (DAOA), have been employed. In this manner, both RBGE and RBDA models were trained using a dataset comprising 181 HPC samples that included superplasticizers and fly ash. The results show that DAOA has significantly improved the base model’s predictive capability, achieving a higher correlation with a value R 2 of 0.936 when estimating slump. Furthermore, RBDA exhibited a more favorable root mean square error (RMSE) in predicting compressive strength compared to RBGE, with a notable 16% difference. Ultimately, both integrated models demonstrated their effectiveness in accurately modeling the mechanical properties of HPC.

In the last two decades, hyperspectral images have been studied for use in food quality analysis using neural network-based chemometric techniques such as radial basic neural network (RBNN) in classification tasks or multilayer perceptron (MLP) for prediction ones. However, recently, deep learning techniques are receiving special interest as those based on recurrent neural networks (RNN) or gated recurrent units for their feature extraction capacity. A kind of RNN are networks based on long short-term memory (LSTM), which are promising for improving the capabilities of hyperspectral images in food analysis. In this sense, a comparative study on using LSTM-based networks is done, comparing it to RBNN in the discrimination of fish fillets subjected to freeze-thaw cycles. The samples for the study were fresh mackerel fillets subjected to two successive cycles of freezing and thawing. Hyperspectral images of fillets were acquired, both fresh and in each freeze-thaw cycle, and spectral profiles were acquired in the range of 400–1000 nm. Complete spectral profiles were used to generate classification models; these were subsequently optimized using the relevant wavelengths determined by feature selection neighborhood component analysis. The models were trained using a k-cross-fold validation strategy (k = 5), repeating the process thirty times. The models were evaluated, confusion matrices were determined, and their classification metrics were compared. The training process results showed that the LSTM networks had superior potential to the RBNN networks, achieving an average F-measure greater than 0.89 and an accuracy greater than 0.93. This study shows that deep learning techniques can be used to tell the difference between fish fillets that have been frozen and thawed several times. These techniques could also be used to establish systems to control the transport and conservation processes of this type of food. [ABSTRACT FROM AUTHOR]

This study delves into anthropogenic impacts on vegetation diversity within mountainous protected rangelands, exploring habitat weakening and biodiversity loss. Employing artificial intelligence, specifically multilayer perceptron (MLP), radial basis neural network (RBFNN), and support vector regression (SVR), we predict vegetation diversity responses to ecological conditions, livestock grazing, and tourism. Assessing 305 sample plots with 21 variables, the MLP model demonstrated superior accuracy (R2 = 0.93 in training, R2 = 0.81 in the test dataset) compared to RBFNN and SVR. Sensitivity analyses highlighted anthropogenic factors like distance to tourist destinations, roads, pastures, and animal husbandries as significant influencers of vegetation diversity in mountainous protected rangelands. To enhance practical application, a user-friendly graphical interface was developed, enabling rangeland managers to utilize the MLP model. This tool facilitates estimation of livestock grazing and tourism impacts on vegetation diversity, empowering informed decision-making for the preservation and sustainability of mountainous protected rangeland ecosystems. [ABSTRACT FROM AUTHOR]

In the present study, a 100 kW organic Rankine cycle is suggested to recover heat energy from commercial ships. A radial-type turbine is employed with R1233zd(E) and back-to-back layout. To improve the performance of an organic Rankine power system, the efficiency of the turbine is significant. With the conventional approach, the optimization of a turbine requires a considerable amount of time and involves substantial costs. By combining design of experiments, an artificial neural network, and Latin hypercube sampling, it becomes possible to reduce costs and achieve rapid optimization. A radial basis neural network with machine learning technique, known for its advantages of being fast and easily applicable, has been implemented. Using such an approach, an increase in efficiency greater than 1% was achieved with minimal design changes at the first and second turbines. [ABSTRACT FROM AUTHOR]

Assessing riverine pollutant loads is a more realistic method for analysing point and non-point anthropogenic pollution sources throughout a watershed. This study compares numerous mathematical modelling strategies for estimating riverine loads based on the chosen water quality parameters: Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Suspended Solids (SS), and Ammoniacal Nitrogen (NH3–N). A riverine load model was developed by employing various input variables including river flow and pollutant concentration values collected at several monitoring sites. Among the mathematical modelling methods employed are artificial neural networks with feed-forward backpropagation algorithms and radial basis functions. The classical multiple linear regression (MLR) statistical model was used for the comparison. Four widely used statistical performance assessment metrics were adopted to evaluate the performance of the various developed models: the root mean square error (RMSE), mean absolute error (MAE), mean relative error (MRE), and coefficient of determination (R2). The considerable number of errors (with RMSE, MAE, and MRE) discovered in estimating riverine loads using the multiple linear regression (MLR) statistical model can be attributed to the nonlinear relationship between the independent variables (Q and Cx) and dependent variables (W). The feed-forward neural network model with a backpropagation algorithm and Bayesian regularisation training algorithm outperformed the radial basis neural network. This finding implies that, in addition to suspended sediment loads, riverine loads may be predicted using an artificial neural network using pollutant concentration (Cx) and river discharge (Q) as input variables. Other geographical and temporal fluctuation characteristics that may impact river water quality, on the other hand, may be incorporated as input variables to enhance riverine load prediction. Finally, riverine load analyses were successfully conducted to reduce the riverine load.

A composite control strategy is proposed to improve the position-tracking performance and anti-interference capabilities of permanent magnet synchronous motors (PMSMs). This strategy integrates an active disturbance rejection controller (ADRC) and a radial basis function neural network (RBFNN) with feedforward control. Initially, the flexibility and robustness of the ADRC are utilized in the position loop control. Subsequently, the parameters of the extended state observer (ESO) within the ADRC are optimized, benefiting from the fast convergence speed and optimal approximation provided by the RBFNN. To further enhance the dynamic tracking performance, a differential feedforward link is introduced between the desired speed and the output signal. The simulation and experimental results demonstrate that when the expected electrical angle inputs are sinusoidal and pulse signals, the incorporation of the feedforward link and the adjustment of parameters in the ADRC lead to improved position-tracking capabilities and greater adaptability to load disturbances.

The airflow characteristics of the internal flow path of an aero-engine compressor are complex, and the vortex flow field around the blade is characterized by high pressure, high speed, rotation, and unsteadiness. Therefore, there is an urgent need to calculate and predict the aerodynamic characteristics of the complex flow field around the compressor blade efficiently and accurately. The computational fluid dynamics (CFD) method was used to generate the aerodynamic load distribution on the blade surface under different operating conditions for the study of the complex flow fields around aero-engine blades. The radial based function (RBF) neural network was applied to establish the pressure surface aerodynamic load prediction model, and the neural network modeling method was combined with the flow field calculation. The neural network method can learn and train the CFD-based data set to properly compensate the errors from the CFD, which provides a reference for the effective prediction of the complex flow fields around aero-engine compressor blades. [ABSTRACT FROM AUTHOR]

As the lifeline of offshore oil and gas production, a submarine pipeline requires regular safety evaluations with proper maintenance according to the evaluation results. At present, the safety factors based on regional-level commonly used factors in engineering are too many, and this leads to conservative evaluation results with a low acceptance of defects. In this paper, a risk factor evaluation index system for submarine pipeline defects is constructed through an analytic hierarchy process (AHP), and the original safety factors are corrected to achieve accurate evaluations for submarine pipeline safety. By constructing a radial basis neural network (RBFNN), the fast calculation of safety factors for other pipeline defects can be realized. Through comparison, it was found that the values obtained by the machine training were in good agreement with the real values, which reflects the accuracy of the model and provides a basis for the repair of a defective pipeline. [ABSTRACT FROM AUTHOR]

Road traffic injuries from rear-end collisions are one of the leading causes of death from vehicular collisions. An accurate driver model must be developed for autonomous vehicles to prevent such accidents. Existing models such as the conventional car-following models have been created for obstacle avoidance adopted by the parametric modeling techniques. Mentioned technique falls short due to the modeling relationship between the vehicle and the human's driver reaction. Therefore, this study aims to develop an ensemble radial basis function neural network (RBFNN) to produce the predicted steering angle for the driver model in emergency collision avoidance. The data is collected from the ground truth rear-end collision experiment where professional drivers are involved. The variables used during modeling are relative velocity, relative distance, yaw rate, and steering angle. The performance of the developed models is determined by accessing the value of the root mean square error (RMSE) and coefficient of determination, R 2 from the generalisation test. In addition, the comparison analysis between the proposed model and standalone RBFNN as well as feed-forward artificial neural network (FFANN) are conducted. Based on the results, ensemble RBFNN produced an outstanding performance in predicting the steering angle. [ABSTRACT FROM AUTHOR]

The influence of uncertainty in material properties on free vibration and aeroelastic response of variable angle tow (VAT) laminated plates is presented in this work. Free vibration analysis is conducted by a finite element model based on third-order shear deformation theory. The FE model is further coupled with MSC. Nastran to carry out aeroelastic analysis of VAT laminates in the subsonic regime. MSC. Nastran helps to extract the aerodynamic influence coefficient matrix at discrete values of reduced frequencies using Doublet Lattice Method. The accuracy and adaptability of the highly efficient radial basis neural network (RBFN) based surrogate model developed for uncertainty analysis are checked by comparing the result with that of the Monte Carlo simulation. Stochastic analysis of natural frequencies and flutter characteristics of VAT laminates are conducted through various parametric studies. Variance-based sensitivity analysis is used to calculate the contribution of individual material properties to the free vibration and aeroelastic response of VAT laminates. Further, the influence of the highly sensitive properties on the structural failure probability is estimated. This research can be leveraged to predict the probability of failure of the structure at different levels of material uncertainty present in it. [ABSTRACT FROM AUTHOR]

Stability control of the tank gun has emerged as a pivotal issue for moving tank gun control systems (TGCS). As a complex electromechanical integrated system, TGCS of moving tank inevitably possesses significant parametric uncertainties and uncertain nonlinearities. To effectively enhance the stabilization control performance of TGCS, in this study, we introduce an adaptive robust control (ARC) strategy based on radial basis function neural network (RBFNN) compensation. The adaptive technique is employed to address the parametric uncertainties, while the RBFNN is constructed to approximate the uncertain nonlinearities and realize feedforward compensation. Subsequently, to suppress the residual uncertainties, a nonlinear robust feedback control rate is devised to strengthen the robustness of the developed controller. Lyapunov analysis shows that the proposed controller achieves uniform ultimate bounded stability. Extensive simulation and electromechanical experimental results confirm the effectiveness of the proposed controller, which shows outstanding performance in handling strong parametric uncertainties and uncertain nonlinearities.

Purpose – This paper aimed a fractional-order sliding mode-based lateral lane-change control method that was proposed to improve the path-tracking accuracy of vehicle lateral motion. Design/methodology/approach – In this paper the vehicle presighting and kinematic models were established, and a new sliding mode control isokinetic convergence law was devised based on the fractional order calculus to make the front wheel turning angle approach the desired value quickly. On this basis, a fractional gradient descent algorithm was proposed to adjust the radial basis function (RBF) neuron parameter update rules to improve the compensation speed of the neural network. Findings – The simulation results revealed that, compared to the traditional sliding mode control strategy, the designed controller eliminated the jitter of the sliding mode control, sped up the response of the controller, reduced the overshoot of the system parameters and facilitated accurate and fast tracking of the desired path when the vehicle changed lanes at low speeds. Originality/value – This paper combines the idea of fractional order calculus with gradient descent algorithm, proposed a fractional-order gradient descent method applied to RBF neural network and fast adjustment the position and width of neurons.

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We propose an adaptive radial basis (RBF) neural network controller based on Lyapunov stability theory for uncertain fractional-order time-delay chaotic systems (FOTDCSs) with different time delays. The controller does not depend on the system model and can achieve synchronous control under the condition that nonlinear uncertainties and external disturbances are completely unknown. Stability analysis showed that the error system asymptotically tended to zero in combination with the relevant lemma. Numerical simulation results show the effectiveness of the controller. [ABSTRACT FROM AUTHOR]

The interval perturbation method is an effective and successful tool in the uncertainty analysis; however, it suffers from the deficiency in the required differential information, which limits its application in complex engineering problems. To end this, this paper uses the radial basis neural network to formulate the derivative information, and its fine accuracy is demonstrated by a mathematical example. Moreover, a new interval analysis method combining interval perturbation and radial basis neural network differentiation, abbreviated as RBNNIPM is proposed. Furthermore, RBNNIPM is applied to calculate the boundaries of yield stress in a three-bar truss, and the detailed assessment proves that RBNNIPM has both high efficiency and high precision. Finally, an electromagnetic buffer model is established to certificate the practicability of RBNNIPM in practical engineering. [ABSTRACT FROM AUTHOR]

This work presents an alternative system of interpolation of several signals based on artificial neural networks using MATLAB. Different architectures were tested starting with a neural network with multilayer perceptron topology, seeking to obtain twice as many samples of the original signal, whose training algorithm was performed from a database built by acquiring ECG signals captured in a laboratory by the authors. When testing the performance of the network under more demanding circumstances, such as the generation of more samples and responses to a greater variety of signals, it was evidenced that the performance decreased significantly, so the same architecture was retrained using a new public database of larger size. Looking for alternatives, a model is made using the radial based network topology, then the results obtained in the two topologies are compared using as input signals a composite Sin, SinC, a component of the Lorenz attractor, a high order polynomial and different ECG signals. The results obtained show better results in the radial basis network topology compared to the multilayer perceptron topology, however both topologies generate interpolations quite close to the original signal. [ABSTRACT FROM AUTHOR]

In the present study, a 100 kW organic Rankine cycle is suggested to recover heat energy from commercial ships. A radial-type turbine is employed with R1233zd(E) and back-to-back layout. To improve the performance of an organic Rankine power system, the efficiency of the turbine is significant. With the conventional approach, the optimization of a turbine requires a considerable amount of time and involves substantial costs. By combining design of experiments, an artificial neural network, and Latin hypercube sampling, it becomes possible to reduce costs and achieve rapid optimization. A radial basis neural network with machine learning technique, known for its advantages of being fast and easily applicable, has been implemented. Using such an approach, an increase in efficiency greater than 1% was achieved with minimal design changes at the first and second turbines.

The multimodal behavior is common in industrial process. Since multimodal data distribution can be regarded as a special kind of nonlinearity, kernel method is empirically effective in constructing the multimode process monitoring model. However, kernel methods suffer its high complexity when a large number of data are collected. In order to improve the fault detection performance in multimodal data and reduce the computational complexity, we propose a reduced nonstationary discrete convolution kernel which is inspired by the structural design of radial basis function (RBF) neural network, as an alternative to the RBF kernel and the nonstationary discrete convolution (NSDC) kernel. By deleting the unnecessary accumulated terms in the NSDC kernel, the computational complexity of the proposed NSDC kernel algorithm is effectively reduced and the speed of fault detection is accelerated on the premise of ensuring the fault detection performance. The effectiveness of the proposed algorithm is demonstrated on a numerical example and multimodal TE process under the standard kernel principal component analysis framework. [ABSTRACT FROM AUTHOR]

Nowadays, brain tumor has become deadly disease. Therefore, early diagnosis can prevent the severity of the next stage. The existing methods are inefficient in predicting the optimal cluster center (CC) in radial basis neural network (RBNN), which leads to inaccuracy. To overcome this issue, we proposed an improved whale optimization algorithm (IWOA) of RBNN to maximize the convergence speed and accuracy. Initially, the MRI input images are fed to preprocessing steps. Then, the image segmentation is carried out by fuzzy-c means (FCM) clustering for identifying the tumor region. These tumor and non-tumor images undergo a feature extraction process utilizing principle component analysis (PCA), mean, entropy, and wavelet transform. The obtained feature vector is fed to the RBNN layer. It needs an optimal CC, which can be considered by using the newly proposed IWOA. RBNN classifies the abnormality of the brain into brain tumor, inflammatory disease, stroke, and degenerative. Its performance is tested on three datasets. Based on the report of the evaluation, the proposed FCM-IWOA-RBNN gives high accuracy. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed method is suitable for application in robotic arm systems. Robotic manipulators can reduce the cost of production and improve productivity; however, controlling a manipulator to follow a desired trajectory is a thorny problem. In this study, we introduced various forms of interference to facilitate the modeling of a dual-axis manipulator. The interference associated with the payload is handled by an adaptive radial basis neural network (ARBNN) controller, while other interference is estimated by a time delay estimator (TDE). The control signal is output by a non-singular fast terminal sliding mode controller (NFTSMC) to minimize further interference. Since the proposed controller can deal with the payload, system uncertainties, external disturbances, friction, and backlash, compared with conventional control methods, it has better tracking accuracy and stability. [ABSTRACT FROM AUTHOR]

Excessive concentrations of nitrate (NO3-N) in water lead to the deterioration of water quality, reducing biodiversity and destroying ecosystems. Therefore, the present study investigated NO3-N removal from simulated wastewater by nanoscale zero-valent iron-supported ordered mesoporous Zr-Ce-SBA-15 composites (nZVI/Zr-Ce-SBA-15) assisted by response surface methodology (RSM), an artificial neural network combined with a genetic algorithm (ANN-GA) and a radial basis neural network (RBF). The successful support of nZVI on Zr-Ce-SBA-15 was confirmed using XRD, FTIR, TEM, SEM–EDS, N2 adsorption and XPS, which indicated ordered mesoporous materials. The results showed that ANN-GA was better than the RSM for optimizing the conditions of NO3-N removal and the RBF neural network further confirmed the reliability of the ANN-GA model. The removal rate of NO3-N by the composites reached 95.71% under the optimized experimental conditions (initial pH of 4.89, contact time = of 62.27 min, initial NO3-N concentration of 74.84 mg/L and temperature of 24.77 °C). The process of NO3-N adsorption onto Zr-Ce-SBA-15 composites was followed by the Langmuir model (maximum adsorption capacity of 45.24 mg/g), pseudo-second-order kinetics, and was spontaneous, endothermic and entropy driven. The yield of N2 can be improved after nZVI was supported on Zr-Ce-SBA-15, and the composites exhibited a strong renewability in the short term within three cycles. The resolution of Fe2+ experiments confirmed that nZVI/Zr-Ce-SBA-15 was simultaneously undergoing adsorption and catalysis in the process of NO3-N removal. Our study suggests that the ordered mesoporous nZVI/Zr-Ce-SBA-15 composites are a promising material for simultaneously performing NO3-N removal and improving the selectivity of N2, which provides a theoretical reference for NO3-N remediation from wastewater. [ABSTRACT FROM AUTHOR]

Modelling of high-dimension chaotic, noisy, and non-stationary time series of complex fractal dynamics is a big challenge. In this research work, a novel approach of Leverage Convolution LC ARFIMA– GARCH model is presented for sequential learning of irregular, fractal dynamic patterns of stochastic time series dynamics. Different classical methods including the auto-regressive approach indecently are unable to capture fragile patterns and consequently convert some weak signals into random errors by creating white noise patterns. The Convolution Leverage provides an additional degree of freedom for critical noisy points and asymmetrical distribution dynamics to regulate the frequency of imbalance and skewed observation. The designed transformation in the ARFIMA model preserves the loss of information by shifting the skewed data distribution toward a normal pattern. The pattern of population parameters in the proposed leverage paradigm provides out of box approach to track and extract additional information on population variance patterns in the form of an additional degree of freedom to stabilize imbalance signals. The model can provide reliable performance for long-range dependence, particularly for mean reversion chaotic phase variation at critical non-differentiable points. The performance of the dynamic model is verified on chaotic real data of the Ireland Stock Market (ISEQ). The result statistics confirmed the optimized outcome with the addition of the GARCH heteroscedastic multimodal and radial basis neural network. The novel technique can help to address inherited challenges in the imbalance learning and extreme events of the time series modeling by monitoring the chaotic trajectory of fractal physical phenomena, particularly in, finance healthcare, climate, and intelligent sustainability. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai University of Engineering Science / Shanghai Gongcheng Jishu Daxue Xuebao is the property of Journal of Shanghai University of Engineering Science Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The defrosting performance of automotive air conditioners plays an important role in driving safety. This paper uses CFD to simulate the internal flow field of the automobile numerically. Simulation results show that the flow distribution is unreasonable. The horizontal grilles are added at the outlets to improve the defrosting performance of the automobile. Air-flow jet angle and the length of the air conditioning outlets (L1, L2) are selected as design variables based on the radial basis neural network to find the optimal combination scheme. The area of the defrosting dead corner has been reduced from 20-5% after optimization, and the frost layer of the front windshield has been completely melted in 25 minutes. The experiment test is conducted to verify the improvement of the defrosting performance of automotive air conditioners. The design methodology can be applied to the development of the air conditioner. [ABSTRACT FROM AUTHOR]

We propose an adaptive radial basis (RBF) neural network controller based on Lyapunov stability theory for uncertain fractional-order time-delay chaotic systems (FOTDCSs) with different time delays. The controller does not depend on the system model and can achieve synchronous control under the condition that nonlinear uncertainties and external disturbances are completely unknown. Stability analysis showed that the error system asymptotically tended to zero in combination with the relevant lemma. Numerical simulation results show the effectiveness of the controller.

In crane systems, lifting, carrying and lowering the load from one place have different dynamic effects on the system. One of these dynamic effects is the moving load problem caused by the movement of the load on the crane system. With the increasing technology in recent years, production speeds have increased. For this reason, it has made the requirements for fast-running cranes mandatory for the transportation and loading of products. Therefore, it is important to know the dynamic effects of the moving load in fast working conditions. In this experimental study, the dynamic effects occurring on the crane beams with different loads and different working speeds during the transportation of the load on the crane are analysed. Here, there are multiple cars on the crane, and these cars are designed in different numbers on the crane and can be operated at different speeds. Under these conditions, the dynamic effects that have arisen have been tested. Also, vibration measurements were carried out at different points on the bridges. And then, these parameters obtained were used in two different proposed neural network types to predict the vibrations that occur on the crane system. Simulation results show that two approaches suggested that a radial basis neural network type can be used as an adaptive predictor for such systems in the experimental applications. [ABSTRACT FROM AUTHOR]

Implementation of radial basis neural network is demonstrated by considering a test case of non-Newtonian third-grade fluid flow and heat transfer through two parallel plates. Five commonly used stochastic optimization methods: genetic algorithm, global search algorithm, multiple starting point algorithm, simulated annealing algorithm, and pattern search algorithm, are employed to optimize the RBNN. Flow of a non-Newtonian third-grade fluid through two parallel plates, subjected to uniform heat flux, is considered. At first, governing equations, describing the flow and heat transfer problem, are solved by the least-square method, a semi-analytical tool. The velocity and the temperature profiles are obtained for different values of third-grade fluid parameter 'A', which are then used for training different stochastic optimization method-assisted RBNNs (SOMARBNNs). For proper functioning of RBNN, a suitable value for an important attribute called 'spread' is required. Deciding the value for 'spread' requires experience and knowledge of neural networks. The present approach makes the selection of proper value of 'spread' very easy, and beginners can use the RBNN for problem-solving. With the help of different stochastic optimization methods, the value of spread for the RBNN is determined. Once all SOMARBNNs are trained, the temperature profile and the corresponding third-grade fluid parameter 'A' are obtained as output, corresponding to any new velocity profile fed as input. Further, the data for training are perturbed by different levels of noise, and different SOMARBNNs are successfully employed to get the output. The performance evaluation of different SOMARBNNs is carried out in terms of CPU time and error in result. The results indicate that PSAARBNN is better than other SOMARBNNs, as it is able to generate results with high accuracy for both low noise data and high noise data. Moreover, the CPU time requirement by PSAARBNN is lowest. [ABSTRACT FROM AUTHOR]

The stochastic isogeometric analysis (SIGA) based on random geometric methods plays a crucial role in structural random analysis. However, existing intrusive SIGA methods suffer from limitations of low applicability or efficiency. On the other hand, current material uncertainties are mostly limited to low dimensions and often ignore spatial correlations. Therefore, we propose an efficient and adaptive nested non-intrusive SIGA method based on Radial Basis Function Neural Network (RBFNN). This method combines quasi-Monte Carlo simulation (QMCS) to achieve a general solution for high-dimensional material uncertainty in porous functionally graded materials (PFGM) plates, including statistical quantities and probability density functions (PDFs) of random responses. Firstly, within the IGA framework, we establish a geometrically nonlinear model for PFGM plates using HSDT and Von Kármán strain-displacement relations, effectively mitigating shear locking effects. Secondly, by considering spatial correlations, we employ the Karhunen-Loève expansion to establish a high-order random field for material uncertainty. Subsequently, we propose a nested and non-intrusive response surface analysis method using RBFNN, significantly enhancing the accuracy and efficiency of SIGA in addressing high-dimensional uncertainty problems. Finally, by leveraging the efficiency of SIGA, we overcome the low convergence speed drawback of QMCS, achieving a comprehensive solution for statistical quantities and PDFs of high-dimensional uncertainty problems. The advantages of efficiency and accuracy are validated through random response analysis of high-dimensional uncertain PFGM plates. In randomly structured geometrically nonlinear PFGM plates, porosity significantly influences the response, while the gradient exponent and Young's modulus have a weaker but non-negligible impact on the response. [ABSTRACT FROM AUTHOR]

Robotic manipulators can reduce the cost of production and improve productivity; however, controlling a manipulator to follow a desired trajectory is a thorny problem. In this study, we introduced various forms of interference to facilitate the modeling of a dual-axis manipulator. The interference associated with the payload is handled by an adaptive radial basis neural network (ARBNN) controller, while other interference is estimated by a time delay estimator (TDE). The control signal is output by a non-singular fast terminal sliding mode controller (NFTSMC) to minimize further interference. Since the proposed controller can deal with the payload, system uncertainties, external disturbances, friction, and backlash, compared with conventional control methods, it has better tracking accuracy and stability.

A graph's spectral wavelet signature determines a filtration, and consequently an associated set of extended persistence diagrams. We propose a framework that optimizes the choice of wavelet for a dataset of graphs, such that their associated persistence diagrams capture features of the graphs that are best suited to a given data science problem. Since the spectral wavelet signature of a graph is derived from its Laplacian, our framework encodes geometric properties of graphs in their associated persistence diagrams and can be applied to graphs without a priori node attributes. We apply our framework to graph classification problems and obtain performances competitive with other persistence-based architectures. To provide the underlying theoretical foundations, we extend the differentiability result for ordinary persistent homology to extended persistent homology.

Many-objective optimization refers to the optimization aiming at four or more objectives. More complex than multi-objective optimization, which copes with two or three objectives, many-objective optimization represents a challenging problem due to the complex trade-off relationships among the optimization objectives. In this study, a four-objective optimization system was proposed for reducing the resistance and the non-uniformity of wake flow of a deep-sea aquaculture vessel at design speed in full load and ballast conditions. The numerical optimization system was mainly composed of the uniform design (UD), free-form deformation method (FFD), radial basis neural network (RBFNN) and a series of genetic algorithms (GAs). During the optimization process, nine design variables were selected to reconstruct the hull geometry. UD and FFD were utilized to generate a series of derivative ship forms. According to CFD calculation results of all derivative ship forms, four surrogate models were constructed, using RBFNN optimized by the particle swarm optimization (PSO), to replace direct numerical calculations. To verify the prediction accuracy advantage of improved RBFNN-based surrogate models based on small sample size, the accuracy comparison was made among surrogate models based on RBFNN, kriging and support vector regression (SVR). Moreover, Sobol' method was employed to analyze the influence of design variables on the optimization objectives. GAs were applied to perform from single-objective to four-objective optimization of the resistance and non-uniformity of wake flow. Eventually, the optimal ship form was selected from the Pareto front of four-objective optimization. Numerical results of the optimized shape showed that the resistance and the non-uniformity of wake flow in full load and ballast conditions were reduced, and the results of the verification and validation (V&V) procedure proved the validation of the many-objective optimization system. [ABSTRACT FROM AUTHOR]

Motivated by the requirement to lessen the aerodynamic drag and aeroacoustic sound of the bluff bodies, the present paper is devoted to a numerical analysis of the aerodynamics and aeroacoustics related with the flow past wavy circular cylinders. Based on the efficient flow control method, as has been presented by preceding researchers, the existing work embarks upon an investigation on the wavy cylinder at a various wavelength and amplitude conditions. Computations are performed for a circular cylinder of the length-to-diameter ratio (L / D) of 25 at a Reynolds number (Re) of 97300 using large eddy simulation and Ffowcs Williams- Hawking's acoustic analogy. Firstly, the cylinder without waviness is subjected to a uniform incoming flow is considered for validation against measurements. Secondly, various collection of wave shape parameters, specifically dimensionless wavelength λ/ D (=1 to 2.5), and wave amplitude a / D (=0.05 to 0.2) have been taken into consideration. It is disclosed that the proper selection of shape parameters could significantly reduce the drag and sound emission levels, compared to the normal cylinder. Finally, a multi-objective particle swarm optimization was performed using the radial basis neural network to simultaneously reduce the aerodynamic drag and sound emission, with λ/ D and a / D as design variables. We recognized a critical λ/ D and a / D for the wavy circular cylinder at the considered subcritical Re. [ABSTRACT FROM AUTHOR]

To identify large fluctuations of parameters in the process of gasification, a control chart pattern recognition method based on optimized radial basis function neural network (RBFNN) is proposed in this paper to conduct pattern recognition of the parameters of gasification process. The proposed method is described in four aspects, feature description, feature extraction, classifier and algorithm learning and training. The initial data is described from shape features and statistical features to reduce the dimension of the data. The optimal characteristic set is selected by the association rule mining algorithm to reduce the complexity of the model. The performance of neural network is affected by the learning method. With RBFNN as a classifier, a learning method based on Bees algorithm is therefore put forward and then training recognition is compared between the proposed method and the traditional method. The results show that the proposed method has higher recognition rate and simpler structure than the traditional method, and it is very effective in monitoring and identifying abnormal fluctuations of gasification process parameters. • A control chart pattern recognition method based on BEE-RBFNN was proposed. • The parameter instability pattern of gasification process was conducted using the proposed method. • The proposed method can accurately identify the abnormal pattern of parameter. [ABSTRACT FROM AUTHOR]

Due to the complexity of the tool and cutting geometry in machining, many undesirable effects occur during the cutting. Vibrations affecting the poor surface quality of the workpiece and the tool life are one of the most important undesirable effects. These vibrations causing loss of production should be detected and the most appropriate working conditions in which the machine tools will work more stable should be determined. In this work, an artificial neural network estimator has been designed in order to analyze the oscillating effects on computer numerical control (CNC) lathes. Firstly, experimental studies have been carried out, and then vibration analysis has been performed by using two types of artificial neural networks. The experimental part of this manuscript analyses has been carried out for the different material types, spindle speeds and feed rates which are affecting the vibration. After the experimental part, two different artificial neural network structures have been proposed in order to analyze the vibration data measured from the CNC lathe under the relevant working conditions. As a result of these experimental and simulation-based approaches, it was seen that the proposed RBNN structure has a good performance even in real-time parameters in capturing the vibrations occurring in the CNC lathe. [ABSTRACT FROM AUTHOR]