Particle Swarm Optimization Neural Network Research Articles

Reliability Prediction of the Distribution Network Based on Wavelet Neural Network with Quantum Particle Swarm Optimization Algorithm

For distribution networks with fuzzy network structure or large scale, traditional reliability assessment is limited by data collection and lack of data samples. Compared with traditional methods, the distribution network reliability prediction method can use fewer data to calculate and obtain reliability results, and its operation is simpler and more practical. In this paper, a distribution network original parameters and reliability prediction method based on wavelet neural network (WNN) and quantum particle swarm optimization algorithm (QPSO) is proposed. Firstly, given the blindness of mother wavelet selection, this paper analyses the error and running time through example analysis and selects the most suitable mother wavelet for distribution network reliability prediction. According to the characteristics of premature convergence of QPSO, the evolutionary speed factor and aggregation factor are introduced to modify the scaling factor to control the convergence of the algorithm. The improved QPSO is used to optimize the initial values and thresholds of the WNN. It can reduce their influence on the prediction results. Finally, the analysis results of different examples show that the method has higher forecast accuracy, better generalization ability, and stability. This method also provides new scientific ideas for the reliability prediction of distribution networks.

Thermal-Stress Coupling Optimization for Coaxial through Silicon Via

In this paper, a thermal-stress coupling optimization strategy for coaxial through silicon via (TSV) is developed based on the finite element method (FEM), artificial neural network (ANN) model and particle swarm optimization (PSO) algorithm. In order to analyze the effect of design parameters on the thermal-stress distribution of coaxial TSV, the FEM simulations of coaxial TSV are conducted by COMSOL Multiphysics. The structure of coaxial TSV is symmetric. The mapping relationships between the design parameters and performance indexes are described by ANN models based on the simulation data of FEM. In addition, the multi-objective optimization function is formulated based on the desired performance indexes, and then the design parameters are optimized by the modified PSO algorithm. Based on the optimized design parameters, the effectiveness of the developed method is validated by FEM simulations. The simulated performance indexes agree well with the desired ones, which implies that the design parameters of coaxial TSV can be optimized to control the thermal-stress distribution. Therefore, the thermal-stress coupling optimization of coaxial TSV can achieve thermal-stress management to improve its reliability.

Adaptive Hyperparameter Fine-Tuning for Boosting the Robustness and Quality of the Particle Swarm Optimization Algorithm for Non-Linear RBF Neural Network Modelling and Its Applications

A method is proposed for recognizing and predicting non-linear systems employing a radial basis function neural network (RBFNN) and robust hybrid particle swarm optimization (HPSO) approach. A PSO is coupled with a spiral-shaped mechanism (HPSO-SSM) to optimize the PSO performance by mitigating its constraints, such as sluggish convergence and the local minimum dilemma. Three advancements are incorporated into the hypothesized HPSO-SSM algorithms to achieve remarkable results. First, the diversity of the search process is promoted to update the inertial weight ω based on the logistic map sequence. Then, two distinct parameters are trained in the original position update algorithm to enhance the work efficiency of the successive generation. Finally, the proposed approach employs a spiral-shaped mechanism as a local search operator inside the optimum solution space. Moreover, the HPSO-SSM method concurrently improves the RBFNN parameters and network size, building a model with a compact configuration and higher precision. Two non-linear benchmark functions and the total phosphorus (TP) modelling issue in a waste water treatment process (WWTP) are utilized to assess the overall efficacy of the creative technique. The results of testing indicate that the projected HPSO-SSM-RBFNN algorithm performed very effectively.

ANALYSIS OF COVID-19 GROWTH TRENDS THROUGH DATA MINING APPROACH AS DECISION SUPPORT

This study aims to analyze the growth trend of covid-19 using prediction algorithms in data mining for covid-19 data throughout Indonesia. This can be used as a decision support to analyze several government policies towards regulatory intervention so far. The method used is the best prediction method in time series data, including Neural Network, SVM, Linear Regression, K-Neirest Neighborn and optimizes it with optimization algorithms. This research is focused on the application of these applications. It is hoped that this research will produce an analysis of the growth trend of Covid cases every day, in addition to its contribution so that it can assist the government in determining the best policy direction and also as an education to the public. in addition, the research will contribute to science in the field of predictive analysis by finding the best RMSE formulation. The results of this study show that Neural Network-Particle Swarm Optimization has the smallest Roort Mean Square Error which is 265,326, and the two Neural Network Genetic Algorithm are 266.801, Neural Network Forward Selection is 275,372 and Neural Network without optimization has the largest RMSE which is 297.204. These results can be used as a reference for the use of similar algorithms in time series data, both Covid-19 data and other data.

Improved Supervised and Unsupervised Metaheuristic-Based Approaches to Detect Intrusion in Various Datasets

Due to the increasing number of cyber-attacks, the necessity to develop efficient intrusion detection systems (IDS) is more imperative than ever. In IDS research, the most effectively used methodology is based on supervised Neural Networks (NN) and unsupervised clustering, but there are few works dedicated to their hybridization with metaheuristic algorithms. As intrusion detection data usually contains several features, it is essential to select the best ones appropriately. Linear Discriminant Analysis (LDA) and t-statistic are considered as efficient conventional techniques to select the best features, but they have been little exploited in IDS design. Thus, the research proposed in this paper can be summarized as follows. a) The proposed approach aims to use hybridized unsupervised and hybridized supervised detection processes of all the attack categories in the CICIDS2017 Dataset. Nevertheless, owing to the large size of the CICIDS2017 Dataset, only 25% of the data was used. b) As a feature selection method, the LDA performance measure is chosen and combined with the t-statistic. c) For intrusion detection, unsupervised Fuzzy C-means (FCM) clustering and supervised Back-propagation NN are adopted. d) In addition and in order to enhance the suggested classifiers, FCM and NN are hybridized with the seven most known metaheuristic algorithms, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), Cultural Algorithm (CA), Harmony Search (HS), Ant-Lion Optimizer (ALO) and Black Hole (BH) Algorithm. Performance metrics extracted from confusion matrices, such as accuracy, precision, sensitivity and F₁-score are exploited. The experimental result for the proposed intrusion detection, based on training and test CICIDS2017 datasets, indicated that PSO, GA and ALO-based NNs can achieve promising results. PSO-NN produces a tested accuracy, global sensitivity and F₁-score of 99.97%, 99.95% and 99.96%, respectively, outperforming performance concluded in several related works. Furthermore, the best-proposed approaches are valued in the most recent intrusion detection datasets: CSE-CICIDS2018 and LUFlow2020. The evaluation fallouts consolidate the previous results and confirm their correctness.

Sb (III) Removal from Aqueous Solutions by the Mesoporous Fe3O4/GO Nanocomposites: Modeling and Optimization Using Artificial Intelligence

The mesoporous graphene oxide-supported ferroferric oxide (Fe 3 O 4 /GO) nanocomposites (the average size of 30.08 nm) were controllably synthesized in the present study. The successful in situ growth of Fe 3 O 4 nanoparticles on GO surface was ascribed to the oxygen-containing groups on GO. The magnetic separation was employed for Sb(III) removal from aqueous solutions and artificial intelligence techniques were adopted to reduce the number and cost of experiments, in order to render these nanocomposites of a practical value. The three methods, including response surface methodology (RSM), artificial neural network-genetic algorithm (ANN-GA) and artificial neural network-particle swarm optimization (ANN-PSO), were used to model and optimize the removal of Sb(III) from aqueous solutions. These three models were evaluated based on correlation coefficient (R 2 ) and mean squared error (MSE). The higher R 2 value and lower MSE of ANN-GA demonstrated the superiority of ANN-GA model over ANN-PSO and RSM models. Analysis of variance, gradient boosted regression trees (GBRT) and Garson method exhibited that contact time was the most influential variable for the Sb(III) removal. Fitting of isotherm data showed that the removal process was controlled by the monolayer adsorption on a homogeneous surface based on the values of R 2 , x 2 , sum of absolute errors (SAE) and average percentage errors (APE). The adsorption process followed the pseudo-second-order model, which was spontaneous and entropy-driven. It was observed that the adsorption process was accompanied with the redox reaction based on the XPS analysis. The regeneration experiments showed that the mesoporous Fe 3 O 4 /GO nanocomposites are an effective and reusable adsorbent within four regeneration cycles.

Automated Evaluation of Surface Roughness using Machine Vision based Intelligent Systems

Machine vision systems play a vital role in entirely automating the evaluation of surface roughness due to the hitches in the conformist system. Machine vision systems significantly abridged the ideal time and human errors for evaluation of the surface roughness in a nondestructive way. In this work, face milling operations are performed on aluminum and a total of 60 diverse cutting experiments are conducted. Surface images of machined components are captured for the development of machine vision systems. Images captured are processed for texture features namely RGB (Red Green Blue), GLCM (Grey Level Co-occurrence Matrix) and an advanced wavelet known as curvelet transforms. Curvelet transforms are developed to study the curved textured lines present in the captured images and this module is capable to unite the discontinuous curved lines present in images. The CNC machined components consists of visible lay patterns in the curved form, so this novel machine vision technique is developed to identify the texture well over the other two extensively researched methods. Artificial Neural Network-Particle Swarm Optimization (ANN-PSO) intelligent models are developed to evaluate the surface roughness from texture features. The model average error attained using RGB, GLCM, Curvelet transform-based machine vision systems are 12.68, 7.8 and 3.57 respectively. In comparison, the results proved that computer vision system based on curvelet transforms outperformed the other two existing systems. This curvelet based machine vision system can be used for the evaluation of surface roughness. Here, image processing might be crucial in identifying certain information. One crucial issue is that, even as performance improves, cameras continue to get smaller and more affordable. The possibility for new applications in Industry 4.0 is made possible by this technological advancement and the promise of ever-expanding networking.

Comparing Restricted Boltzmann Machine – Backpropagation Neural Networks, Artificial Neural Network – Genetic Algorithm and Artificial Neural Network – Particle Swarm Optimization for Predicting DHF Cases in DKI Jakarta

Dengue hemorrhagic fever (DHF) is a common disease in tropical countries such as Indonesia that is often fatal. Early predictions of DHF case numbers help reduce the risk of community transmission and help related authorities develop prevention plans and strategies. Previous research shows that temperature, rainfall, and humidity indirectly affect DHF spread patterns. Therefore, this research uses and compares three machine learning models—restricted Boltzmann machine-backpropagation neural network (RBM-BPNN), artificial neural network-genetic algorithm (ANN-GA), and artificial neural network-particle swarm optimization (ANN-PSO)—to predict DHF case numbers in DKI Jakarta, the capital of Indonesia, which is in the DHF red zone. RBM and PSO are used to calculate optimal initial weight and bias before starting the prediction stage with ANN; meanwhile, GA updates weight and bias during the backward pass in ANN. The data includes temperature, rainfall, and humidity, plus previous DHF case data for five districts in DKI Jakarta from Jan. 6, 2009, to Sept. 25, 2017. We used Arima, Autocorrelation, and Pearson correlation for pre-processing data. The DHF case data fluctuates strongly and requires the moving averages method. The data consists of 70% training data and 30% testing data. The results show that each district requires different model architectures for the best predictions. `The best RMSE prediction of DHF cases with RBM-BPNN in Central Jakarta is 3,78%; the best RMSEs using ANN-GA in North and East Jakarta are 5,65% and 5,99%, respectively. The ANN-PSO model had the largest RMSE value in every district, with an average of 8,43%.

Application of the PSO–neural network in rainfall–runoff modeling

Abstract In this study, rainfall–runoff (R–R) models were developed by assembling Particle Swarm Optimization (PSO) with the Feed Forward Neural Network (FFNN) and the Wavelet Neural Network (WNN). Performances of the model were compared with the wavelet ensembled neural network (WNN) and the conventional FFNN. The data from 1981 to 2005 were used for calibration and from 2006 to 2014 for validation of the models. Different combinations of rainfall and runoff were considered as inputs to the PSO–FFNN model. The fitness value and computational time of all the combinations were computed. Input combination was selected based on the lowest fitness value and lowest computational time. Four R–R models (FFNN, WNN, PSO–FFNN and PSO–WNN) were developed with the best input combination. The performance of the models was evaluated using statistical parameters (Nash–Sutcliffe Efficiency (NSE), D and root mean square error (RMSE)) and parameters vary in the range of (0.86–0.90), (0.95–0.97) and (68.87–84.37), respectively. After comparing the performance parameters and computational time of all four models, it was found that the PSO–FFNN model gave better values of NSE (0.89), D (0.97), RMSE (68.87) and less computational time (125.42 s) than other models. Thus, the PSO–FFNN model was better than the other three models (FFNN, WNN and PSO–WNN).

Voltage stability assessment prediction using a guide strategy-based adaptive particle swarm optimisation-neural network algorithm

<span lang="EN-US">In this work, the indicators of electrical power network stability and voltage stability (VS) are discussed and developed with the aim of using a power transfer stability index (PTSI) indicator as a predictor for voltage stability (VS) in electrical power networks. The power transfer stability index (PTSI) was thus used to detect abnormally weak voltages in buses within such power system networks (weak). The target data are obtained using the Newton Raphson method (NR) and include magnitude, phase angle, and active and reactive power. A new adaptive particle swarm optimization-neural network algorithm based on a guiding strategy (GSAPSO-NN) was also used to achieve the goal of the paper by improving the mixed particle updates and the weightings of the neural network to decrease the search time. All results were then compared with actual values as calculated using the PTSI NR method. The final results show only simple differences or approximately the same values using both the proposed and the classical methods. The MATLAB-PSAT package was employed to obtain most of these results and the testing of the new method was done on the IEEE14 bus system as well as the Iraqi 24-bus power system. The effectiveness validation of the new hybrid method for assessing voltage stability was thus achieved.</span>

Multi-objective optimization of seeding performance of a pneumatic precision seed metering device using integrated ANN-MOPSO approach

Uniform seed spacing within the row is the most desirable prerequisite for better crop yield. The seeding uniformity of a pneumatic seed metering device is significantly affected by its key design and operational parameters, i.e., shape and size of the suction hole, vacuum pressure, and forward speed of operation. Therefore, these parameters need to be optimized to achieve better seeding performance. In this study, A novel intelligent multi-objective optimization methodology based on artificial neural network (ANN) and multi-objective particle swarm optimization (MOPSO), named as integrated ANN-MOPSO approach, was employed to accomplish the set goal. Maximizing the quality feed index (QFI) and minimizing the precision index (PI) were chosen as two objectives. The multilayer perceptron (MLP) and radial basis function (RBF) neural network models were developed for predicting the QFI and PI. The results revealed that the RBFNN (4-15-2) model outperformed the MLPNN (4-7-2) model; hence it was further coupled with the MOPSO algorithm for retrieving the Pareto-optimal set of the design and operational parameters corresponding to the maximum QFI and minimum PI.The most appropriate optimum entry shape and size of the suction hole, vacuum pressure, and operating speed were found to be chamfered holes with 3 mm diameter, 3.5 kPa, and 2.84 km/h, respectively. The validation results showed a variation of -2.11 % and +5.398 % between the observed and predicted values of the QFI and PI, respectively, thus confirming the adequacy of the proposed approach.

Quantitative Assessment and Spatial Analysis of Metals and Metalloids in Soil Using the Geo-Accumulation Index in the Capital Town of Romblon Province, Philippines.

The municipality of Romblon in the Philippines is an island known for its marble industry. The subsurface of the Philippines is known for its limestone. The production of marble into slab, tiles, and novelty items requires heavy equipment to cut rocks and boulders. The finishing of marble requires polishing to smoothen the surface. During the manufacturing process, massive amounts of particulates and slurry are produced, and with a lack of technology and human expertise, the environment can be adversely affected. Hence, this study assessed and monitored the environmental conditions in the municipality of Romblon, particularly the soils and sediments, which were affected due to uncontrolled discharges and particulates deposition. A total of fifty-six soil and twenty-three sediment samples were collected and used to estimate the metal and metalloid (MM) concentrations in the whole area using a neural network-particle swarm optimization inverse distance weighting model (NN-PSO). There were nine MMs; e.g., As, Cr, Ni, Pb, Cu, Ba, Mn, Zn and Fe, with significant concentrations detected in the area in both soils and sediments. The geo-accumulation index was computed to assess the level of contamination in the area, and only the soil exhibited contamination with zinc, while others were still on a safe level. Nemerow's pollution index (NPI) was calculated for the samples collected, and soil was evaluated and seen to have a light pollution level, while sediment was considered as "clean". Furthermore, the single ecological risk (Er) index for both soil and sediment samples was considered to be a low pollution risk because all values of Er were less than 40.

Development of Hybrid Artificial Neural Network–Particle Swarm Optimization Model and Comparison of Genetic and Particle Swarm Algorithms for Optimization of Machining Fixture Layout

Development of Hybrid Artificial Neural Network–Particle Swarm Optimization Model and Comparison of Genetic and Particle Swarm Algorithms for Optimization of Machining Fixture Layout

Prediction of resisting force and tensile load reduction in GFRP composite materials using Artificial Neural Network-Enhanced Jaya Algorithm

This work presents an experimental and a numerical studies on the effect of the phenomenon of porosity on the mechanical properties of Glass Fiber Reinforced Polymer (GFRP). In a first part, material elaboration, as well as its characterization using a three-point bending test to extract the basic mechanical properties of the material, is considered. In a second part, a finite element model is created to simulate the problem of air bubbles broadly. Several cases of different shapes and sizes are simulated. The results show a significant effect on the reduction of load in both tensile and bending cases as the size of the bubbles increases. Furthermore, the second part includes the application of the Artificial Neural Network-Enhanced Jaya Algorithm (ANN-E JAYA) to predict the reduction of the tensile load as a function of different crack lengths obtained from an Extended Finite Element Method (XFEM) model. Next, to verify the accuracy of provided application , a comparison is made with two other applications such as Artificial Neural Network-Jaya Algorithm (ANN-JAYA) and Artificial Neural Network-Particle Swarm Optimization (ANN-PSO). The results of the three algorithms show good convergence, with a slight increase in accuracy for ANN-E JAYA. MATLAB code and data used in this article can be found at https://github.com/Samir-Khatir/GFRP-ANN-E-JAYA.git.

A fault diagnosis method of rolling element bearing based on improved PSO and BP neural network

Aiming at the inherent defects of BP neural network in the field of rolling bearing fault diagnosis, based on the optimization of particle swarm optimization algorithm, this paper uses a variety of optimization strategies to optimize the particle swarm optimization algorithm, and then uses the optimized particle swarm optimization algorithm to optimize the BP neural network. Therefore, a new fault diagnosis method (Dual Strategy Particle Swarm Optimization BP neural network, DSPSOBP) is proposed. DSPSOBP fault diagnosis method is mainly divided into two steps. The first step is EMD decomposition of vibration signal, and the second step is to classify rolling bearing faults by using BP neural network optimized by Double Strategy Particle Swarm Optimization algorithm. Experiments show that DSPSOBP has stronger advantages than BP neural network basic fault diagnosis model.

High-Order Sliding Mode Control for Three-Joint Rigid Manipulators Based on an Improved Particle Swarm Optimization Neural Network

This paper presents a control method for the problem of trajectory jitter and poor tracking performance of the end of a three-joint rigid manipulator. The control is based on a high-order particle swarm optimization algorithm with an improved sliding mode control neural network. Although the sliding mode variable structure control has a certain degree of robustness, because of its own switching characteristics, chattering can occur in the later stage of the trajectory tracking of the manipulator end. Hence, on the basis of the high-order sliding mode control, the homogeneous continuous control law and super-twisting adaptive algorithm were added to further improve the robustness of the system. The radial basis function neural network was used to compensate the errors in the modeling process, and an adaptive law was designed to update the weights of the middle layer of the neural network. Furthermore, an improved particle swarm optimization algorithm was established and applied to optimize the parameters of the neural network, which improved the trajectory tracking of the manipulator end. Finally, MATLAB simulation results indicated the validity and superiority of the proposed control method compared with other sliding mode control algorithms.

Distributed Scheduling Strategy of Virtual Power Plant Using the Particle Swarm Optimization Neural Network under Blockchain Background.

Large-scale and widely dispersed distributed energy resource (DER) can be gathered by a virtual power plant (VPP) in a given area, and its parameters can be combined into a single external operation profile. Each distributed energy source in the VPP has a complete backup of the critical information for the entire network because it is a node of blockchain. The distribution network can be accessed by DER freely and adaptable under the scientific management of the VPP, and it can offer the system high-reliability, high-quality, and high-security power services. An energy blockchain network model based on particle swarm optimization (PSO) to optimise the neural network is proposed in this paper as a solution to the issues with the current VPP models. This will enable distributed dispatching of the VPP and reasonable load distribution among units. According to the simulation results, this algorithm's error is minimal and its accuracy can reach 94.98 percent. This model can more accurately capture demand-side real-time information, which benefits VPP's stable scheduling with a welcoming environment and transparent information. It also enhances the system's data security and storage security. This system can successfully address the issues of subject-to-subject mistrust and high information interaction costs in the VPP.

Hyperspectral Remote Sensing Inversion and Monitoring of Organic Matter in Black Soil Based on Dynamic Fitness Inertia Weight Particle Swarm Optimization Neural Network

Long-term degradation of black soil has led to reductions in soil fertility and ecological service functions, which have seriously threatened national food security and regional ecological security. This study is motivated by the UN’s Sustainable Development Goal (SDG) 2—Zero Hunger, specifically, SDG 2.4 Sustainable Food Production Systems. The aim was to monitor the soil organic matter (SOM) content of black soil and its dynamics via hyperspectral remote sensing inversion. This is of great significance to the effective utilization and sustainable development of black soil resources. Taking the typical black soil area of Northeast China as an example, the hyperspectral data of ground features were compared with SOM contents measured in soil samples to correlate SOM with spectral features. Based on their quantitative relationship, a dynamic fitness inertia weighted particle swarm optimization (DPSO) algorithm is proposed, which balances the global and local search abilities of a particle swarm optimization algorithm. The DPSO algorithm is applied to the parameter adjustment of an artificial neural network (BPNN), which is used instead of a traditional error back propagation algorithm, to build a DPSO-BPNN model. Then a global optimal analytical expression of hyperspectral inversion is obtained to improve the generalization ability and stability of the remote sensing quantitative inversion model. The results show that DPSO-BPNN model is more stable and accurate than existing models, such as multiple stepwise regression, partial least squares, and BP neural network models (adjust complex coefficient of determination = 0.89, root mean square error = 1.58, relative recent deviation = 2.93). The results of DPSO-BPNN inversion are basically consistent with the trend in SOM contents measured during surface geochemical exploration. As such, this study provides a basis for hyperspectral remote sensing inversion and monitoring of the SOM contents in black soil.

An Augmented Reality-Assisted Prognostics and Health Management System Based on Deep Learning for IoT-Enabled Manufacturing.

With increasingly advanced Internet of Things (IoT) technology, the composition of workshop equipment has become more and more complex. Based on this, the rate of system performance degradation and the probability of fault have both increased. Owing to this, not only has the difficulty of constructing the remaining useful life (RUL) model increased but also the improvement in speed of maintenance personnel cannot keep up with the speed of equipment replacement. Therefore, an augmented reality (AR)-assisted prognostics and health management system based on deep learning for IoT-enabled manufacturing is proposed in this paper. Firstly, the feature extraction model based on Convolutional Neural Network-Particle Swarm Optimization (PSO-CNN) is proposed with the purpose of excavating the internal associations in large amounts of production data. Based on this, the high-accuracy RUL prediction is accomplished by Gate Recurrent Unit (GRU)-attention, which can capture the long-term and short-term dependencies of time series and successfully solve the gradient disappearance problem of RNN. Moreover, more attention will be paid to important content with the help of the attention mechanism. Additionally, high-efficiency maintenance guidance and visible instructions can be accomplished by AR. On top of this, the remote expert can offer help when maintenance personnel encounters tough problems. Finally, a real case was implemented in a typical IoT-enabled workshop, which validated the effectiveness of the proposed approach.

Prediction and Analysis of College Sports Test Scores Based on Computational Intelligence

Nowadays, colleges and universities are paying more and more attention to the physical condition of students. Many schools set up physical education courses to exercise students and improve their physical quality. They also conduct physical examinations every semester to test students’ conditions. In order to ensure more accurate sports results, this paper uses optimization of the neural group particle group model method to forecast the physical culture test scores of the investigated students. In addition, to guarantee accuracy the particle swarm optimization neural network model method, we compare the GXD method and the LM method with our method. It has the advantage of high precision, optimal prediction effect, strong versatility, higher recall rate, stronger antinoise performance, and wider application range. The article compares the neural network model method for particle swarm optimization with the GXD way and the LM way to ensure precision the neural network model method for particle swarm optimization.