Genetic Algorithm Optimized BP Neural Network Research Articles

Relative density prediction of additively manufactured Inconel 718: a study on genetic algorithm optimized neural network models

PurposeThe quality and properties of Inconel 718 (IN718) from selective laser melting (SLM), a major additive manufacturing (AM) process, have been studied extensively. Among all aspects of quality, relative density (RD) is most widely investigated, and it significantly affects the mechanical properties of SLM-ed materials. This study aims to develop robust RD prediction models based on the data accumulated in literature using machining learning approaches.Design/methodology/approachBy mining the literature of SLM-ed IN718, a comprehensive data set is created, which consists of the four major process parameters of laser power, scan speed, hatch spacing, layer thickness and RD data. A back propagation neural network (BPNN) model, along with its two optimized models: genetic algorithm (GA) optimized BPNN (GA-BPNN) and adaptive GA optimized BPNN (AGA-BPNN) models are created for predicting the RD of SLM-ed IN718, and their prediction performances are compared.FindingsOverall, satisfactory prediction accuracies are obtained – the R2 values of the built BPNN, GA-BPNN and AGA-BPNN models are 73.5%, 75.3% and 79.9%, respectively. This also shows that by incorporating the optimization technique, the prediction accuracy of BPNN is improved and AGA-BPNN has the highest accuracy. Moreover, SLM experiments are conducted to test the model predictability. It is found that the predictions generally agree well with the experiment data, and the order of the model prediction accuracies is consistent with that based on the literature data.Originality/valueThis research highlights that by mining literature data, prediction models of RD of SLM-ed IN718 can be obtained with satisfactory performance, which consider more process parameters and cover wider parameter ranges than any individual studies, in a cost-effective manner.

Process optimization of high-speed dry milling UD-CF/PEEK laminates using GA-BP neural network

High-performance carbon fiber-reinforced polyetheretherketone (CF/PEEK) is widely used in aerospace and premium-end medical fields due to its high strength-weight ratio, shock resistance, and reusability. However, its dry machining requirement is a significant limit to improving machining efficiency and machining quality using a traditional process. Addressing this issue, the high-speed dry (HSD) machining technique is imported in this paper. Multi-level mixed orthogonal experiments of dry milling unidirectional (UD) CF/PEEK laminates with the fiber orientation of 0° and 90° are designed. Aiming at quantitative characterizing surface quality, three-dimensional (3D) surface roughness Sq and 3D fractal dimension Ds are used to present surface roughness and surface defects, respectively. A characterization system for surface defects generated in milling CRF/PEEK is proposed. A prediction model of surface quality considering fiber orientation, cutting speed, feed per tooth, and cutting width is then established using the genetic algorithm optimized BP (GA-BP) neural network. The prediction results show that the model is of acceptable generalization capability with a prediction accuracy of over 90.39%. Based on the analysis of surface qualities and cutting temperatures, the HSD machining technique is verified to be feasible in milling UD-CF/PEEK, and the recommended cutting speed in the HSD milling boundary is 1500–1600 m/min. The 3D fractal dimension is verified feasible to evaluate the size of complex surface defects of the machined UD-CF/PEEK. It has a non-rigid negative correlation with Sq in general. Besides, cutting speed and fiber orientation are the key factors affecting the machined surface microstructural characteristics. The present study gives technical references for improving surface quality in HSD milling CF/PEEK.

Mechanical behavior prediction of CF/PEEK-titanium hybrid laminates considering temperature effect by artificial neural network

This paper focuses on the mechanical behaviors of carbon fiber-reinforced PEEK-titanium hybrid laminates (TiGr) under different temperatures. The tensile strength, flexural strength and inter-laminar shear strength (ILSS) of TiGr laminates with different stacking structures were investigated at room temperature, 80, 150 and 220 °C, respectively. The results show that the tensile strength, flexural strength and ILSS gradually decrease as the temperature increases, and reduced by 12.3%, 45.4% and 29.1% for Type I, 12.9%, 48.8% and 30.1% for Type II, 16.1%, 45.1% and 39.4% for Type III at 220 °C. Moreover, a three-layers back-propagation (BP) neural network was developed to predict the corresponding mechanical behaviors of TiGr laminates, then the genetic algorithm (GA) was introduced to optimize the established BP neural network and the accuracies of the two prediction models were compared. It is found that both the trained BP and GA-BP neural networks could predict the mechanical performances of TiGr laminates well while the GA optimized BP neural network has better prediction results, with average absolute errors of 1.78%, 1.92% and 2.41% for tensile, flexural and inter-laminar shear strengths, respectively. Furthermore, the predictability of the trained models was validated with data from published literature, providing a new concept for the application of BP neural networks to fiber metal laminates.

A prediction model of milling force for aviation 7050 aluminum alloy based on improved RBF neural network

Semi-finishing is an important step to reduce the cutting vibration and deformation caused by the thin-walled stiffening rib parts of aeronautical inertial control products during the finishing process. In the semi-finishing process, the variation of cutting force is a key factor of machining deformation. A large number of samples considering the effect of cutting parameters, such as spindle speed, feed per tooth, and milling width were simulated by the finite element simulation software AdvantEdge to obtain the milling forces based on 7050 aluminum alloy (Al7050) for aviation. Moreover, the standardized Euclidean distance was introduced to the radial basis neural network model (RBF-NN) to develop an improved RBF neural network model (IRBF-NN), and a high-precision model to predict the effect of cutting parameters on the thin-walled semi-finishing milling forces was established based on the proposed IRBF-NN. Results show that the maximum relative errors of milling force obtained by the genetic algorithm–optimized BP neural network model (GA-BP-NN), RBF-NN, and IRBF-NN are 13.9%, 12.5%, and 4.1%, respectively. Accordingly, the proposed IRBF-NN has high accuracy and effectiveness to predict milling force for the semi-finishing of aerospace Al7050 thin-walled stiffening rib parts.

Investigation of Strength and Fatigue Life of Rubber Asphalt Mixture.

Strength and fatigue life are essential parameters of pavement structure design. To accurately determine the pavement structure resistance of rubber asphalt mixture, the strength tests at various temperatures, loading rate, and fatigue tests at different stress levels were conducted in this research. Based on the proposed experiments, the change law of rubber asphalt mixture strength with different temperatures and loading rates was revealed. The phenomenological fatigue equation of rubber asphalt mixture was established. The genetic algorithm optimized backpropagation neural network (GA-BPNN) is highly reliable for optimizing production processes in civil engineering, and it has a remarkable application effect. A GA-BPNN strength and fatigue life prediction model was created in this study. The reliability of the prediction model was verified through experiments. The results showed that the rubber asphalt mixture strength decreases and increases with the increase of temperature and loading rate, respectively. The goodness of fit of the rubber asphalt mixture strength and fatigue life prediction model based on the GA-BPNN could reach 0.989 and 0.998, respectively. The indicators of the fatigue life prediction model are superior to the conventional phenomenological fatigue equation model. The GA-BPNN provides an effective method for predicting the rubber asphalt mixture strength and fatigue life, which significantly improves the accuracy of the resistance design of the rubber asphalt pavement structure.

Fault early warning of pitch system of wind turbine based on GA-BP neural network model

A fault early warning method based on genetic algorithm to optimize the BP neural network for the wind turbine pitch system is proposed. According to the parameters monitored by SCADA system, using correlation analysis to screen out the parameters of the pitch system with strong power correlation. The BP neural network optimized by genetic algorithm is used to establish the model of the pitch system under normal working conditions. The verification results show that the input parameters of the pitch system model determined by the correlation coefficient are more reasonable, and the accuracy of the pitch system model established by the genetic algorithm-optimized BP neural network is higher than that of the unoptimized model. Based on the above model, a sliding window model is established, and the early warning threshold is determined through the statistics of the residuals of the sliding window to realize the fault early warning of the pitch system of the wind turbine. The example shows that the method can give early warning in the event of failure, and verifies the effectiveness of the method.

Genetic Algorithm – Back Propagation (GA-BP) Neural Network for Chlorophyll-a Concentration Inversion Using Landsat 8 OLI Data

Chlorophyll-a (Chl-a) accurate inversion in inland water is important for water environmental protection. In this study, we tested the Genetic Algorithm optimized Back Propagation (GA-BP) neural network model to precisely simulated the Chl-a in an inland lake using Landsat 8 OLI images. The result show that the R2 of GA-BP neural network model has increased 28.17% compared to traditional BP neural network model. Then this GA-BP model was applied to another two scenes of Landsat 8 OLI image with the R2 of 0.961, 0.954 respectively for March 26 2018, October 26 2018. And the spatial distribution have shown a reasonable result of Chl-a variation in Lake Donghu. This study can provide a new method for Chla concentration inversion in urban lakes and support water environment protection on a large scale.

Estimation of low calorific value of blended coals based on support vector regression and sensitivity analysis in coal-fired power plants

Low calorific value (LCV) of blended coals is a vital property for the economy and efficiency of the coal-fired power plants. The experimental determination of the fuel calorific value is costly, while proximate analysis is easier and cheaper. Many linear correlations have been developed to describe the relationships between the calorific value and a few constituents of proximate and/or ultimate analysis, although some may be nonlinear. In this paper a specially designed support vector regression based approach (Sensitivity analysis weighted and genetic algorithm optimized support vector regression, SAW-GA-SVR) was applied to estimate the LCV based on proximate analysis of coal fed to a power plant. In this, nonlinear sensitivity coefficients were used as weighting factors and genetic algorithm was used for optimization. The prediction capability of the proposed model was compared with support vector regression (SVR), genetic algorithm optimized support vector regression (GA-SVR), genetic algorithm optimized back propagation neural network (GA-BPNN), and linear correlations from the published literature. According to the results obtained, the SAW-GA-SVR model has shown better capability of modeling and predicting the LCV of coals over the other methods.

Chlorophyll-A Prediction of Lakes with Different Water Quality Patterns in China Based on Hybrid Neural Networks

One of the most important water quality problems affecting lakes and reservoirs is eutrophication, which is caused by multiple physical and chemical factors. As a representative index of eutrophication, the concentration of chlorophyll-a has always been a key indicator monitored by environmental managers. The most influential factors on chlorophyll-a may be dependent on the different water quality patterns in lakes. In this study, data collected from 27 lakes in different provinces of China during 2009–2011 were analyzed. The self-organizing map (SOM) was first applied on the datasets and the lakes were classified into four clusters according to 24 water quality parameters. Comparison amongst the clusters revealed that Cluster I was the least polluted and at the lowest trophic level, while Cluster IV was the most polluted and at the highest trophic level. The genetic algorithm optimized back-propagation neural network (GA-BPNN) was applied to each lake cluster to select the most influential input variables for chlorophyll-a. The results of the four clusters showed that the performance of GA-BPNN was satisfied with nearly half of the input variables selected from the predictor pool. The selected factors varied for the lakes in different clusters, which indicates that the control for eutrophication should be separate for lakes in different provinces of one country.

Identification of vehicle suspension shock absorber squeak and rattle noise based on wavelet packet transforms and a genetic algorithm-support vector machine

The squeak and rattle (S&R) noise of a vehicle’s suspension shock absorber substantially influences the psychological and physiological perception of passengers. In this paper, a state-of-the-art method, specifically, a genetic algorithm-optimized support vector machine (GA-SVM), which can select the most effective feature subsets and optimize the model’s free parameters, is proposed to identify this specific noise. A vehicular road test and a shock absorber rig test are conducted to investigate the relationship between these features, and then an approach for quantifying the shock absorber S&R noise is given. Pre-processed signals are decomposed through a wavelet packet transform (WPT), and two criteria, namely, the wavelet packet energy (WPE) and wavelet packet sample entropy (WPSE), are introduced as the feature extraction methods. Then, the two extracted feature sets are compared based on this genetic algorithm. Another advanced method, known as the genetic algorithm-optimized back propagation neural network (GA-BPNN), is introduced for comparison to illustrate the superiority of the newly developed GA-SVM model. The result shows that the WPSE can extract more useful features than the WPE and that the GA-SVM is more effective and efficient than the GA-BPNN. The proposed approach could be retrained and extended to address other fault identification problems.

Fault Diagnosis of Coal Mine Equipment Based on Improved GA Optimized BP Neural Network

In the face of more and more faults in coal mine equipment, this paper presents the method of combining genetic algorithm (GA) and BP neural network to predict the failure. According to genetic algorithm has a very slow convergence speed, easy to fall into local optimum, this paper uses chaos and reverse individual learning initialization, followed by the use of differential algorithm to operate on the optimal individual. Finally, the improved fitness function is applied to the selection operation, and the accuracy of operation is improved by mutation probability and crossover probability. The improved algorithm is applied to the BP neural network to improve the training effect. The simulation results show that the proposed algorithm improves the accuracy and stability compared to the traditional BP neural network.

Welded joints integrity analysis and optimization for fiber laser welding of dissimilar materials

Dissimilar materials welded joints provide many advantages in power, automotive, chemical, and spacecraft industries. The weld bead integrity which is determined by process parameters plays a significant role in the welding quality during the fiber laser welding (FLW) of dissimilar materials. In this paper, an optimization method by taking the integrity of the weld bead and weld area into consideration is proposed for FLW of dissimilar materials, the low carbon steel and stainless steel. The relationships between the weld bead integrity and process parameters are developed by the genetic algorithm optimized back propagation neural network (GA-BPNN). The particle swarm optimization (PSO) algorithm is taken for optimizing the predicted outputs from GA-BPNN for the objective. Through the optimization process, the desired weld bead with good integrity and minimum weld area are obtained and the corresponding microstructure and microhardness are excellent. The mechanical properties of the optimized joints are greatly improved compared with that of the un-optimized welded joints. Moreover, the effects of significant factors are analyzed based on the statistical approach and the laser power (LP) is identified as the most significant factor on the weld bead integrity and weld area. The results indicate that the proposed method is effective for improving the reliability and stability of welded joints in the practical production.

A New Approach of Geological Disasters Forecasting using Meteorological Factors based on Genetic Algorithm Optimized BP Neural Network

The monitoring and forecasting of the mining slope deformation are of great significance to prevent potential geological disasters in mining regions and the geological factors have been widely used for the purpose of mining slope deformation monitoring. However, literature review shows that very little work has been done in prediction of mining slope deformation using meteorological factors. To address this issue, a new method is proposed using the meteorological factors to forecast the mining slope deformation. Herein, the meteorological factors include the temperature, atmospheric pressure, cumulative rainfall, relative humidity and refractive index of the mining slope. A genetic algorithm optimized BP neural network (GA-BPNN) was employed to fuse the meteorological factors to establish the prediction model for the mining slope deformation. The experiments have been implemented to evaluate the new approach and a comparison between the GA-BPNN, BPNN and radical basis function neural network (RBF) prediction models has been carried out. The analysis results show that the proposed method can provide precise prediction of the mining slope deformation and its performance is superior to its rivals. DOI: http://dx.doi.org/10.5755/j01.eee.20.4.4238

Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification

Multi Artificial Neural Network (ANN) models are used to forecast ozone concentration on single-site for a better forecast accuracy in huge dataset condition. Support Vector Machine (SVM) is used to accurately classify the data into its corresponding categories. Back Propagation neural network (BPNN) was optimized using Genetic Algorithm (GA) to achieve higher forecast stability. SVM classification and GA optimized BPNN (GABPNN) were combined to forecast ozone concentrations in Beijing. The ozone measurements of XiDan sampling site in Beijing were used to test the effectiveness of this method. The modeling dataset used were the records of temperature (T), humidity (H), wind velocity (WV) and UV radiation (UV) from Mar 2009 to Jul 2009. The models were tested using the records of Aug 2009. High accuracy was achieved using this forecast method. Correlation coefficient (R) of the final models on the test stage ranged from 0.86 to 0.90, with an average of 0.87. The predictions of the final models represented a great forecasting capability that could be applied to the real-life ozone forecast in Beijing.