Experimental Study on Creep Properties Prediction of Reed Bales Based on SVR and MLP

Background: Reed has high lignin content, wide distribution and low cost. It is an ideal raw material for replacing wood in the paper industry. Reeds are rich in resources, but the density of reeds is low, leading to high transportation and storage costs. This paper aims to study the compression process of reeds and the creep behaviour of compressed reeds, and provide theoretical guidance for the reed compressor management, bundling equipment and the stability of compressed reed bales.Results: We studied the strain-time relationship and strain of the reed bales compressed under constant force and the creep behaviour of the reed bales under different holding forces. Additionally, the creep behaviour of reed bales under various retention forces was investigated. The test curves are fitted by Machine Learning Prediction Algorithms and Support Vector Machine Regression. And use machine learning prediction algorithm model to establish a quaternary model of reed creep. The results show that the creep behaviour of a reed bale was positively correlated with the initial maximum compressive stress. The established Burgers four-element model was capable of simulating the creep process of reed bales. The test curves coincided well with the model-simulated curves. Reed bales were found to exhibit viscoelasticity. During the creep process, the elastic dynamic force and the viscous resistance were mutually constrained. The strain of reeds was composed of elastic, viscoelastic and plastic εs. And elaborated the three stages of the creep process in detail.Conclusions: We studied the relationship between the strain and time of the reed and the strain and creep behaviour of the reed bag under different holding forces under constant force. It is proved that the multi-layer perceptron network is better than the support vector machine regression in predicting the characteristics of reed materials. The three stages of elasticity, viscoelasticity and plasticity in the process of reed creep are analysed in detail. This article opens up a new way for using machine learning methods to predict the mechanical properties of materials. The proposed prediction model provides new ideas for the characterization of material characteristics.

Prediction of Nickel Concentrations in Urban and Peri-Urban Soils: Application of a Hybridized Empirical Bayesian Kriging and Support Vector Machine Regression Approach

Soil pollution is a big issue caused by anthropogenic activities. The spatial distribution of potentially toxic elements (PTEs) varies in most urban and peri-urban areas. As a result, spatially predicting the PTEs content in such soil is difficult. A total number of 115 samples were obtained from Frydek Mistek in the Czech Republic. Calcium(Ca), magnesium(Mg), potassium(K), and nickel (Ni) concentrations were determined using Inductively Coupled Plasma Optical Emission Spectroscopy. The correlation matrix between the response variable and the predictors revealed a satisfactory correlation between the elements. The prediction results indicated that support vector machine regression (SVMR) performed well although its estimated root mean square error (RMSE) (235.974) and mean absolute error (MAE) (166.946) were higher when compared with the other methods applied. Conversely, the hybridized model of empirical bayesian kriging -multiple linear regression (EBK-MLR) performed poorly as indicated by the measured coefficient of determination value below 0.1. The empirical bayesian kriging-support vector machine regression (EBK-SVMR) model was the best model, with low RMSE (95.479) and MAE (77.368) values and a high coefficient of determination (R2 = 0.637). EBK-SVMR modeling technique was visualized using self-organizing map. The clustered neurons of the hybridized model CakMg -EBK-SVMR component plane showed a diverse color pattern predicting the concentration of Ni in the urban and peri urban soil. The results proved that combining EBK and SVMR is an effective technique for predicting Ni concentrations in urban and peri-urban soil.

Erratum to: Prognostics of Induction Motor Shaft Based on Feature Importance and Least Square Support Vector Machine Regression

This is an erratum to International Journal of Automotive and Mechanical Engineering 2021; 18(1): 8464–8477. Please refer to the related article: https://doi.org/10.15282/ijame.18.1.2021.06.0641

Energy Consumption Estimation of the Electric Bus Based on Grey Wolf Optimization Algorithm and Support Vector Machine Regression

Electric buses have many significant advantages, such as zero emissions and low noise and energy consumption, making them play an important role in saving the operation cost of bus companies and reducing urban traffic pollution emissions. Therefore, in recent years, many cities in the world dedicate to promoting the electrification of public transport vehicles. Whereas due to the limitation of on-board battery capacity, the driving range of electric buses is relatively short. The accurate estimation of energy consumption on the electric bus routes is the premise of conducting bus scheduling and optimizing the layout of charging facilities. This study collected the actual operation data of three electric bus routes in Meihekou City, China, and established the support vector machine regression (SVR) model by taking the state of charge (SOC), trip travel time, mean environment temperature and air-conditioning operation time as the independent variables; while the energy consumptions of the route operations served as the dependent variables. Furthermore, the grey wolf optimization (GWO) algorithm was adopted to select the optimal parameters of the proposed model. Finally, a support vector machine regression model based on the grey wolf optimization algorithm (GWO-SVR) is proposed. Three real bus lines were taken as examples to validate the model. The results show that the mean average percentage error is 14.47% and the mean average error is 0.7776. In addition, the estimation accuracy and training time of the proposed model are superior to the genetic algorithm-back propagation neural network model and grid-search support vector machine regression model.

Financial stock market forecasting based on intelligent support vector machine regression model

The financial stock market is highly complex, nonlinear and uncertain, which makes it difficult to predict price fluctuation. With the advent of the era of artificial intelligence, a variety of intelligent optimization algorithms are constantly applied to the prediction of the stock market. The purpose of this study is to use a support vector machine regression model optimized by an intelligent fuzzy algorithm to predict the situation of the securities market. In this study, the stock price information of sh600060hisense electric equipment from June 2019 to December 2019 was used as the experimental data. As the input parameters of regression models, the starting price, the maximum price, the lowest price, the stock price, the transaction quantity, and the transaction quantity are taken up, and the fuzzy logic is used to make the sample data fuzzy, and the kernel function and optimization parameter are chosen. Then, the obtained data are trained in MATLAB, and the obtained data are effectively classified, and the stock price prediction of the financial market is obtained. The results show that the optimal parameters of the support vector machine regression model of stock data are C = 100, y = 0.01, ɛ= 0.01, and the accuracy of FSVM is about 0.75, which is higher than that of the SVM model (0.71), the square root mean square error (RMSE) is about 0.12, and the average absolute error (MAE) is about 0.015, According to the data, it can be said that the prediction results of the model are effective for the selected seven stocks one-minute data. It is concluded that the fuzzy support vector machine improves the prediction accuracy of the stock market. This study contributes to the prediction of an intelligent algorithm in the stock market.