Genetic Algorithm-based Neural Network Research Articles

Evolutionary Computing for the Radiative-Convective Heat Transfer of a Wetted Wavy Fin Using a Genetic Algorithm-Based Neural Network.

Evolutionary algorithms are a large class of optimization techniques inspired by the ideas of natural selection, and can be employed to address challenging problems. These algorithms iteratively evolve populations using crossover, which combines genetic information from two parent solutions, and mutation, which adds random changes. This iterative process tends to produce effective solutions. Inspired by this, the current study presents the results of thermal variation on the surface of a wetted wavy fin using a genetic algorithm in the context of parameter estimation for artificial neural network models. The physical features of convective and radiative heat transfer during wet surface conditions are also considered to develop the model. The highly nonlinear governing ordinary differential equation of the proposed fin problem is transmuted into a dimensionless equation. The graphical outcomes of the aspects of the thermal profile are demonstrated for specific non-dimensional variables. The primary observation of the current study is a decrease in temperature profile with a rise in wet parameters and convective-conductive parameters. The implemented genetic algorithm offers a powerful optimization technique that can effectively tune the parameters of the artificial neural network, leading to an enhanced predictive accuracy and convergence with the numerically obtained solution.

Improved Giza pyramids construction algorithm for Modify the deep neural network-based method for energy demand forecasting

Accurate prediction of energy demand is crucial for improving services, reducing costs, and optimizing operations in energy systems. Deep neural networks (DNNs) have emerged as a popular method for energy demand forecasting. However, the performance of DNNs can be affected by data quality and hyperparameter selection. To address these concerns, this study proposes a novel energy demand forecasting technique that combines DNNs with an enhanced Giza pyramid construction methodology. The aim of this study is to provide a more reliable and effective approach for forecasting energy demand. The DNNs are employed to capture the complex relationships between input and output variables, while the Giza pyramids algorithm is utilized to optimal selection of hyperparameters of the network. Real-world energy demand data is used to evaluate the proposed approach, comparing it with state-of-the-art baseline models. The research methodology involves assessing the suggested approach using real-world energy demand information and conducting a comparative analysis with cutting-edge baseline models, including modified BP neural network (MBPNN), Neural Network based Genetic Algorithm (NNGA), and reinforcement learning and deep neural network (RLDNN). The IGPCA/CNN method outperforms other methods in energy prediction accuracy across short-term, medium-term, and long-term time scales. It achieves an MSE score of 0.564, lower than MBPNN, NNGA, and RLDNN. In medium-term prediction, it achieves an MSE score of 0.587, better than MBPNN, NNGA, and RLDNN. In long-term prediction, it achieves an MSE score of 0.629, lower than MBPNN and RLDNN. Further analysis and validation experiments are needed to ensure robustness and generalizability. Comparing the method with other state-of-the-art approaches can provide a comprehensive understanding of its superiority. The performance of the models is evaluated based on reliability and effectiveness in energy demand forecasting. The major conclusion of this study is that the proposed approach outperforms the initial models in accurately forecasting energy demand. The combination of DNNs and the improved Giza pyramid construction methodology results in enhanced performance, demonstrating superior reliability and effectiveness compared to other models. The study highlights the significance of accurate energy demand prediction for optimizing energy systems and reducing costs.

Genetic neuro-computing model for insights on membrane performance in oily wastewater treatment: An integrated experimental approach

In this study, response surface methodology (RSM) and artificial neural network-based genetic algorithm (ANN-GA) were utilized to predict two crucial output parameters of membrane performance, namely separation efficiency and oil flux, derived from experimental investigations. The central composite design (CCD) screening approach of RSM was employed to evaluate the influence of important process input parameters, such as oil concentration (ranging from 50 to 10,000 ppm), feed flow rate (ranging from 150 to 300 mL/min), and pH of the feed (ranging from 4 to 10), as well as their synergistic effects on the output variables. The constructed RSM model and ANN-GA were effectively employed to estimate the optimum conditions for maximizing the output variables. Statistical analysis using the determination coefficient (R2) and standard error of prediction (SEP), along with analysis of variance (ANOVA) and the t-test, demonstrated the accurate description of the membrane performance process by both models. For the oil flux, the RSM model showed an estimated R2 of 0.9916 and SEP of 3.54%, while the ANN model exhibited an R2 of 0.9933 and SEP of 3.31%. In terms of separation efficiency, the RSM model yielded R2 = 0.9929 and SEP = 1.31%, whereas the ANN model achieved R2 = 0.9961 and SEP = 0.99%. Remarkably, the ANN-GA approach revealed the best optimum conditions for both responses. Furthermore, the sensitivity analysis of the developed ANN model indicated the order of significance of the variables as follows: oil concentration > feed pH > feed flow rate. These findings substantiate the efficacy of the proposed approach, making it viable for implementation in diverse industries to facilitate sustainable monitoring and management practices.

A Framework for Optimizing Antenna Through Genetic Algorithm-Based Neural Network

Abstract In this research paper, the application of Artificial Neural Networks (ANN) for designing antennas is introduced. The primary objective of this optimization technique is to focus on the antenna’s parameters to achieve a desirable S11 value, which is a key metric of an antenna’s performance. To demonstrate the effectiveness of this approach, the optimization method to design three different antennas using the Numerical Analyzer (MATLAB) tool is employed. Through this study, it is tried to provide new insights into the optimization of antenna design using ANN and demonstrate its potential applications in the field of antenna engineering. The results of this research could potentially lead to the development of more efficient and effective antenna systems with improved performance in various applications.

Neural-network based wind pressure prediction for low-rise buildings with genetic algorithm and Bayesian optimization

Low-rise wood buildings, which occupy over 95% of all residential structures in the U.S., suffer from wind hazards, such as hurricanes, winter storms, and tornadoes. Realistic wind pressures are critical to obtaining the actual responses of buildings for structural design and damage prediction. Wind tunnel experiments provide realistic wind pressure distributions on buildings for structural analysis. However, it is time-consuming and costly to experiment with every building under different wind scenarios. An effective alternative way is to use the neural network (NN) to predict the wind pressures for buildings with different geometries and under various wind directions based on the available databases. However, this method could have a high computational cost due to the challenges of determining an optimal NN structure with suitable hyperparameters. In the present study, the influences of the hyperparameters (namely the input variable and transfer function), the number of data pairs, and the NN structures on the performances of NNs are evaluated when predicting wind pressure coefficients based on building dimensions and roof slopes. To overcome the tedious trial-and-error procedure for optimal NN selection, two new approaches, genetic algorithm-based neural network (GANN) and Bayesian optimization-based neural network (BONN), are proposed. The BONN is demonstrated to be the most efficient, saving 88–94% computational time compared with the traditional trial-and-error neural network (TENN), while the GANN costs about twice the time of BONN. The much higher efficiencies of the proposed two approaches in wind pressure predictions help broaden the application of NN.

An Intelligent Multimode Clustering Mechanism Using Driving Pattern Recognition in Cognitive Internet of Vehicles.

Connected autonomous vehicles can leverage communication and artificial intelligence technologies to effectively overcome the perceived limitations of individuals and enhance driving safety and stability. However, due to the high dynamics of the vehicular network and frequent interruptions and handovers, it is still challenging to provide stable communication connections between vehicles, which is likely to cause disasters. To address this issue, in this paper, we propose an intelligent clustering mechanism based on driving patterns in heterogeneous Cognitive Internet of Vehicles (CIoVs). In the proposed approach, we analyze the driving mode containing multiple feature parameters to accurately capture the driving characteristics. To ensure the accuracy of pattern recognition, a genetic algorithm-based neural network pattern recognition algorithm is proposed to support the reliable clustering of connected autonomous vehicles. The cognitive engines recognize the driving modes to group vehicles with a similar driving mode into a relatively stable cluster. In addition, we formulate the stability and survival time of clusters and analyze the communication performance of the clustering mechanism. Simulation results show that the proposed mechanism improves the reliable communication throughput and average cluster lifetime by approximately 14.4% and 11.5% respectively compared to the state-of-the-art approaches.

Evaluation of Intelligence Models to Estimate the Least Limiting Water Range Using Conveniently Measurable Soil Properties

Direct measurement of the least limiting water range (LLWR) is costly and time-consuming. In this study, genetic algorithm-based neural network (ANN-GA), artificial neural network (ANN) and stepwise multivariate regression (SMR) were used to estimate the LLWR of soil using easily measurable soil properties in the Khanmirza Plain. Then, depending on the location of each area, a total of 250 points were randomly identified as approximate sampling sites. Results showed that the accuracy of the SMR model with the percentage of clay, organic carbon and fine sand had a coefficient of determination of 0.42. The ANN-GA and ANN models with the highest coefficient of determination (R2 = 0.98) and mean square error (MAE = 0.0538) were suitable for estimating the least limiting water range. Therefore, the efficiency of models showed that the ANN and ANN-GA predicted the LLWR more accurate compared to the SMR and their results were close to the measured ones.

Comparison of Stepwise Multilinear Regressions, Artificial Neural Network, and Genetic Algorithm-Based Neural Network for Prediction the Plant Available Water of Unsaturated Soils in a Semi-arid Region of Iran (Case Study: Chaharmahal Bakhtiari Province)

ABSTRACT Plant available water (PAW) is one of the physical parameters of soils and the basic data of irrigation plans. Although various theoretical or empirical approaches have been proposed to describe this phenomenon, it is still possible to investigate and evaluate the relevance and applicability of new sciences such as artificial neural network method in predicting this phenomenon. In existing methods for determination of PAW, time-consuming tests are required. Nowadays, the capabilities of artificial neural network (ANN) methods in modeling have led to the use of ANN in parallel with the application of conventional approaches in various engineering sciences. In this study, artificial neural networks have been used as a new method to predict the PAW of soils. The study area is Khanimirza plain in Chaharmahal va Bakhtiari province. Soil sampling was performed randomly from 0 to 20 cm depth. The measured property in this study was the amount of plant available water (PAW). Readily available parameters including sand, silt and clay percentage, organic carbon, bulk density (BD), pH, Electrical conductivity (EC), calcium carbonate equivalent (CCE), and calcium carbonate are considered as model inputs. Modeling was performed using Stepwise multilinear regressions (SMLR), artificial neural network (ANN) and genetic algorithm-based neural network (ANN-GA). The results of PAW modeling showed that ANN-GA model with 0.90 coefficient is better than the other two methods. In general, ANN and ANN-GA showed better performance than SMLR. In fact, ANN and ANN-GA do not use a special type of equations and the network can achieve satisfactory results by establishing a proper relationship between input and output data.

Inverse analysis and multi-objective optimization of coupling mechanism based laser forming process

Laser forming of non-developable surfaces necessitates simultaneous bending and shrinkage of the sheet blank. This can be obtained by coupling mechanism based laser forming. However, soft computing based modeling of this process as well as different laser parameter sets under coupling mechanism giving different optimum combinations of simultaneous bending and shrinkage is rarely reported. In this work, experiments have been carried out following a design of experiments with considered suitable ranges of the input factors, i.e., laser power, travel speed and laser beam diameter activating coupling mechanism. Response surface models for the outputs namely bending and thickening (resulted due to shrinkage) were developed in terms of the considered inputs and parametric effects were analyzed. Finite element modeling was also carried out to analyze the deformation behavior. Multi-objective optimization of laser parameters for different combinations of maximum/minimum of bending and thickening of the sheet material undergoing coupling mechanism has been shown. Forward and inverse models of the process have been built with the help of a backpropagation neural network (BPNN) and genetic algorithm-based neural network (GANN) based on experimental data. Because of the ability of genetic algorithm (GA) to obtain global search, GANN models provide better estimation of the input parameters for inverse modeling or process synthesis compared to that by the BPNN model. Finally, several dome-shaped surfaces were built with constant line energy but different Fourier numbers and hence, different proportions of bending and shrinkage. This was to demonstrate the importance of simultaneous bending and thickening of the sheet (achievable only by coupling mechanism) to generate such non-developable surface with minimal distortion.

Wavelet Neural Network for Modeling Chlorophyll a Concentration Affected by Artificial Upwelling

Through bringing nutrient-rich subsurface water to the surface, the artificial upwelling technology is applied to increase the primary marine productivity which could be assessed by Chlorophyll a concentration. Chlorophyll a concentration may vary with different water physical properties. Therefore, it is necessary to study the relationship between Chlorophyll a concentration and other water physical parameters. To ensure the accuracy of predicting the concentration of Chlorophyll a, we develop several models based on wavelet neural network (WNN). In this study, we build up a three-layer basic wavelet neural network followed by three improved wavelet neural networks, which are namely genetic algorithm-based wavelet neural network (GA-WNN), particle swarm optimization-based wavelet neural network (PSO-WNN), and genetic algorithm & particle swarm optimization-based wavelet neural network (GAPSO-WNN). The experimental data were collected from Qiandao Lake, China. The performances of the proposed models are compared based on four evaluation parameters, i.e., R-square, root mean square error (RMSE), mean of error (ME), and distance (D). The modeling results show that the wavelet neural network can achieve a certain extent of accuracy in modeling the relationships between Chlorophyll a concentration and the five input parameters (salinity, depth, temperature, pH, and dissolved oxygen).

Prediction of critical properties of biodiesel fuels from FAMEs compositions using intelligent genetic algorithm-based back propagation neural network

ABSTRACT Biodiesels are considered as promising fuels to substitute diesel fuel which can fill the gap of energy shortage while maintaining the diesel engine’s efficiency. Variations in the properties of different biodiesel fuels are caused by the varied fatty acid methyl esters (FAMEs) compositions derived from their parent oils. Therefore, correlating key properties such as cetane number (CN), kinematic viscosity (KV), iodine value (IV) and cold filter plugging point (CFPP) with FAMEs compositions of each biodiesel fuel is significant to developing whatever new types of fuels applied on diesel engines. In this study, an intelligent genetic algorithm (GA)-based back propagation neural network (BPNN) model was proposed to predict the properties of biodiesel fuels according to FAMEs compositions. The hybrid BPNN-GA model has five inputs (methyl palmitate, methyl stearate, methyl oleate, methyl linoleate and methyl linolenate) corresponding to the FAMEs compositions and outputs with estimated fuel properties, with the GA assisting on training to find out local minimum deviation and updated weighting configurations. It was found that the intelligent learning-training method proposed hybrid BPNN-GA model enabled to map the non-linear relationships between the FAMEs compositions and key properties of biodiesel fuels with fairly good agreement. The predicted value of fuel properties agrees with measured ones with R-square up to 96%, along with lower value (less than 10%) over Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) than those of other empirical correlations. In addition, a sensitivity analysis was conducted to in-depth investigate the FAMEs compositions on key properties. It was concluded that saturated FAMEs have positive impacts on CN, KV and the CFPP, while IV is typically dependent on unsaturated FAMEs. Therefore, it is attainable to formulate new types of alternative fuels based on the required properties on diesel engine applications.

Multi-objective optimization in face milling process with cryogenic cooling using grey fuzzy analysis and BPNN-GA methods

Purpose The purpose of this study is to investigate the prediction and optimization of multiple performance characteristics in the face milling process of tool steel ASSAB XW-42. Design/methodology/approach The face milling parameters (cutting speed, feed rate and axial depth of cut) and flow rate (FR) of cryogenic cooling were optimized with consideration of multiple performance characteristics, i.e. surface roughness (SR), cutting force (Fc) and metal removal rate (MRR). FR of cryogenic cooling has two levels, whereas the three face milling parameters each have three levels. Using Taguchi method, an L18 mixed-orthogonal array was selected as the design of experiments. The rough estimation of the optimum face milling parameters was determined by using grey fuzzy analysis. The global optimum face milling parameters were searched by applying the backpropagation neural network-based genetic algorithm (BPNN-GA) method. Findings The optimum SR, cutting force (Fc) and MRR could be obtained by setting FR, cutting speed, feed rate and axial depth of cut at 0.5 l/min, 280 m/min, 90 mm/min and 0.2 mm, respectively. The experimental confirmation results showed that BPNN-based GA optimization method could accurately predict and significantly improve all of the multiple performance characteristics. Originality/value To the best of the authors’ knowledge, there were no publications available regarding multi-response optimization using the combination of grey fuzzy analysis and BPNN-based GA methods during cryogenically face milling process.

Ionospheric foF2 disturbance forecast using neural network improved by a genetic algorithm

A single station short-term ionospheric disturbance forecasting model has been developed with a genetic algorithm-based neural network (GA-NN). The genetic algorithm is used to optimize the initial weights of the neural network to avoid the local minimum during NN training. Using this model, the single station predictions of the ionospheric F2 layer critical plasma frequency, foF2, with the time-scale 1–24 h in advance in the China region have been investigated. Input parameters of the forecasting GA-NN model include the Beijing time (GMT+8), season information, solar zenith angle, day number, solar activity, geomagnetic activity, neutral winds, geographic coordinates and previous values of foF2. The training dataset in this model are obtained from the ionosonde stations in China. The data coverage is from 1990 to 2004 (more than one solar cycle) except 1995 and 2000. The data of ionospheric disturbances in 1995 (solar minimum) and 2000 (solar maximum) are used as the validation dataset. The prediction results at the different stations show that 1 h ahead prediction is more accurate than predictions of 3, 6, 12 and 24 h ahead. Comparisons between the observed and predicted values of foF2 in the low and middle latitudes during the year of solar minimum (1995) and solar maximum (2000) indicate that, the prediction accuracy at middle latitudes are generally better than that at low latitudes. The prediction root-mean-square error (RMSE) in the low solar activity is smaller than that in the high solar activity. The ionospheric disturbances prediction results manifest that the model works well even when the observed values of foF2 are far away from the monthly median value and the ionospheric storm lasts for 18 h.

Prediction of ionospheric vertical total electron content from GPS data using ordinary kriging-based surrogate model

The total electron content (TEC) is the number of electrons present in a ray path between satellite and receiver. TEC affects the propagation of radio signal from satellite to receiver, which causes a ranging error. In the case of single frequency user receiver, the prediction of TEC helps to correct the range errors. TEC is measured using TEC unit (TECU), where $1~\text{TECU} = 1 \times 10^{16}~\text{electrons}/\text{m}^{2}$ . The vertical total electron content (VTEC) of the L1 band is estimated by using data collected from GPS receiver which is installed at the ACSCE station Bangalore. In this work, an ordinary kriging (OK)-based surrogate model algorithm and Matlab code is developed and used to predict the hourly basis ionospheric VTEC. Six parameters such as time, sun spot number (SSN), the solar flux index at 10.7 cm (F10.7), Kp and Ap and observed TEC are used to build the surrogate model. These parameters are related to the ionospheric diurnal variations, solar cycle and geomagnetic activities. In order to cover all regions of the world during different solar activity periods six input parameters are collected from low-, mid- and high-latitude regions during low, medium and high solar activity periods. The root mean square error (RMSE) of the OK-based surrogate model ranges from 0.6–3.6 TECU, and the correlation coefficient varies between 0.79–0.99 and range error varies from 0.04654–0.3017244 m at three regions. The TEC prediction results from the OK-based surrogate model are compared with results obtained from (i) a genetic algorithm-based neural network (GA-NN), (ii) a back-propagation neural network (BP-NN) and (iii) the IRI-2012 model at the CHAN station. For a typical dataset the RMSE of the OK-based surrogate model is 4.523 TECU and the correlation coefficient is 0.9733. The RMSE values for the GA-NN, BP-NN and IRI-2012 models are 5.3529, 6.2913 and 6.7179 TECU and The correlation coefficients are 0.8343, 0.7869 and 0.7797, respectively. The OK model is also compared with a time series method for the CHAN station; it is observed that, for 3 days (7-1-2008 to 9-1-2008) prediction, the OK model gives a 75% result for $\Delta \textit{TEC} <1~\text{TECU}$ condition, the time series method gives 39% for the same condition. The results indicate that the OK-based surrogate model is suitable for applications in ionospheric TEC predictions.

Genetic Algorithm-Based Neural Network for Estimation of Scour Depth Around Bridge Abutment

Genetic Algorithm-Based Neural Network for Estimation of Scour Depth Around Bridge Abutment

Neural network based optimization approach for energy demand prediction in smart grid

Energy usage and demand forecasting is an essential and complex task in real time implementation. Proper coordination is required between the consumer and power companies for monitoring, scheduling and operating the electrical devices without any damages. In this paper, we propose a novel neural network based optimization approach for energy demand prediction. Initially, the Conventional Neural Network (CNN) approach is employed to find the required energy demand prediction at the consumer end. Secondly, Neural Network based Genetic Algorithm (NNGA) and Neural Network based Particle Swarm Optimization (NNPSO) approaches are implemented where the weights of the neural network are automatically adjusted. Closer observation from the result reveals that the proposed NNGA approach performs better for short term load forecasting and proposed NNPSO is more suitable for the long term energy prediction. For the experimental results, real time data are taken from pecan street (Pecan Street Inc.). From the simulations, it can be concluded that the proposed optimization approach algorithm yield better results than the CNN approach in predicting the future energy demand. Further, the result reveals that it is possible to manage the demand and supply, planning of power grid and prediction of future energy requirement in the smart grid.

A Comparison Among ARIMA, BP-NN, and MOGA-NN for Software Clone Evolution Prediction

Software evolution continues throughout the life cycle of the software. During the evolution of software system, it has been observed that the developers have a tendency to copy the modules completely or partially and modify them. This practice gives rise to identical or very similar code fragments called software clones. This paper examines the evolution of clone components by using advanced time series analysis. In the first phase, software clone components are extracted from the source repository of the software application by using the abstract syntax tree approach. Then, the evolution of software clone components is analyzed. In this paper, three models, Autoregressive Integrated Moving Average, back propagation neural network, and multi-objective genetic algorithm-based neural network, have been compared for the prediction of the evolution of software clone components. Evaluation is performed on the large open-source software application, ArgoUML. The ability to predict the clones helps the software developer to reduce the effort during software maintenance activities.

Modeling Chlorophyll &lt;formula formulatype="inline"&gt; &lt;tex Notation="TeX"&gt;$a$&lt;/tex&gt; &lt;/formula&gt; Concentration Affected by Artificial Upwelling in Qiandao Lake

Artificial upwelling of ocean water has been increasingly used to enhance primary marine productivity. This approach brings nutrient-rich deep water to the surface and alters the physical characteristics of water and thus the distribution of the nutrient over an effective period. Various water physical characteristics may affect chlorophyll $a$ concentration, a key indicator for assessing primary marine productivity. Therefore, it is important to study the correlation between chlorophyll $a$ concentration and various water physical characteristics in the artificial upwelling, which has never been examined in literature. In this paper, several water quality parameters, which have potential correlation with chlorophyll $a$ concentration, are selected and multiple linear regression (MLR) and multivariate quadratic regression (MQR) are employed to test the correlation. Then, two novel neural network approaches, i.e., genetic-algorithm-based neural network (GA-NN) and particle-swarm-optimization-based neural network (PSO-NN) are proposed to model the correlation, which are further compared with regular backpropagation neural network (BP-NN), MLR, and MQR. The experimental data are collected from Qiandao Lake, China. The modeling results show that chlorophyll $a$ concentration has a strong correlation with salinity, temperature, dissolved oxygen (DO), and pH in the process of artificial upwelling, and GA-NN and PSO-NN can provide reliable prediction of the correlation.

Artificial neural network-based genetic algorithm to predict natural gas consumption

The present study developed a hybrid model to predict the natural gas consumption in the city of Yasouj in Iran. In proposed model, an artificial neural network-based genetic algorithm (ANN-GA) integrates weather records (degree-day, relative humidity, wind speed, rainfall) and real gas consumption to predict daily gas consumption. The GAis used to optimize the neural network topology and its parameters. The results indicate that the ANN-GA model show good agreement with real data with an absolute deviation of 2.19 % and a high correlation coefficient (\(R\) = 0.998). The proposed ANN-GA model can consistently and accurately be used to predict daily natural gas consumption and is a powerful tool that can assist authorities in developing equitable and economic policies for natural gas distribution.

A hybrid algorithm to optimize cutting parameter for machining GFRP composite using alumina cutting tools

In this paper, two different evolutionary algorithm-based neural network models were developed to optimise the unit production cost. The hybrid neural network models are, namely, genetic algorithm-based neural network (GA-NN) model and particle swarm optimization- based neural network (PSO-NN) model. These hybrid neural network models were used to find the optimal cutting conditions of Ti(C,N) mixed alumina-based ceramic cutting tool (CC650) and SiC whisker-reinforced alumina- based ceramic cutting tool (CC670) on machining glass fibre-reinforced plastic (GFRP) composite. The objective considered was the minimization of unit production cost subjected to various machine constraints. An orthogonal design and analysis of variance was employed to determine the effective cutting parameters on the tool life. Neural network helps obtain a fairly accurate prediction, even when enough and adequate information is not available. The GA-NN and PSO-NN models were compared for their performance. Optimal cutting conditions obtained with the PSO-NN model are the best possible compromise com- pared with the GA-NN model during machining GFRP composite using alumina cutting tool. This model also proved that neural networks are capable of reducing uncertainties related to the optimization and estimation of unit production cost.