Improved Support Vector Regression Research Articles

Optimal weight support vector regression ensemble with cluster-based subsampling for electricity price forecasting

Accurate prediction of short-term electricity price is the key to obtain economic benefit and also an important index of power system planning and management. Support vector regression (SVR) based ensemble works have gained remarkable achievements in terms of high accuracy and steady performance, but they are highly dependent on data representativeness and have a high computational complexity O (k * N 3) of data samples and parameter selection. To further improve the data representativeness and reduce its computational complexity, this paper develops a new approach to forecast electricity price via optimal weighted ensemble. In the model, the cluster-based subsampling algorithm is proposed to categorize the inputs being seasonally decomposed into several groups, and representative data are drawn from each group in a certain proportion to ensure that each subset trained with SVR has the same representativeness and features. Moreover, the optimal weighted combination method is presented to assign weights to the sub-SVRs to obtain the optimal support vector regression ensemble model (OWSSVRE). The experimental results show that the improved support vector regression ensemble model with the same features and representativeness of the subset has better performance in electricity price forecasting. As a result, it is suitable to support decision making in the energy and other sectors.

Estimation of Soybean Internal Quality Based on Improved Support Vector Regression Based on the Sparrow Search Algorithm Applying Hyperspectral Reflectance and Chemometric Calibrations

The nutritional components of soybean, such as fat and protein, directly decide soybean quality. The fast and accurate detection of these components is significant to soybean industries and soybean crop breeding. This study developed an improved SSA-SVM (support vector regression based on the sparrow search algorithm) for the rapid and accurate detection of the fat and protein in soybean seeds using hyperspectral reflectance data. In this work, 85 soybean samples were selected. After their fat and protein contents were analyzed using chemical methods, a total of 85 groups of hyperspectral image data were collected using the hyperspectral imaging system. An effective data preprocessing method was applied to reduce the noise for enhancing the prediction models. Some popular models, including partial least-square regression (PLSR), random forest regression (RFR), and support vector regression based on the genetic algorithm (GA-SVR), were also established in this study. The experimental results showed that the improved SSA-SVM model could predict the nutrient contents of the soybean samples with accuracies of 0.9403 and 0.9215 and RMSEs of 0.2234 and 0.325 for the fat and protein, respectively. The convergence speed was improved significantly. Therefore, hyperspectral data combined with the SSA-SVM algorithm presented in this study were effective for evaluating the soybean quality.

A Prediction Framework for State of Health of Lithium-Ion Batteries Based on Improved Support Vector Regression

As one crucial function of battery management system (BMS), the state of health (SOH) prediction of lithium-ion battery is of great significance to system safe operation and battery’s service life. This paper proposes a framework for SOH prediction, which includes the feature points extraction and SOH prediction. Firstly, based on the incremental capacity (IC) curve, the improved incremental capacity (IIC) curve is deduced by taking the derivative of the IC curve, and the grey relational analysis (GRA) is adopted to select the four feature points with the highest grey relational grade (GRG). Then, an improved sparrow search algorithm (ISSA) is proposed to optimize the parameters of the support vector regression (SVR) for more precise SOH prediction. Finally, experiments are carried out and the results show that the proposed feature points extraction method based on the IC/IIC curves and GRA is efficiently to improve the SOH prediction accuracy. Furthermore, compared with three traditional algorithms, the ISSA-SVR can restrict the SOH prediction error within 1.7%, and it also shows the proposed SOH prediction framework has strong robustness and high universality.

Research on Yield Prediction Technology for Aerospace Engine Production Lines Based on Convolutional Neural Networks-Improved Support Vector Regression

Improving the prediction accuracy of aerospace engine production line yields is of significant importance for enhancing production efficiency and optimizing production scheduling in enterprises. To address this, a novel method called Convolutional Neural Networks-Improved Support Vector Regression (CNN-ISVR) has been proposed for predicting the production line yield of aerospace engines. The method first divides the factors influencing production line yield into production cycle and real-time status information of the production line and then analyzes the key feature factors. To solve the problem of poor prediction performance in traditional SVR models due to the subjective selection of kernel function parameters, an improved SVR model is presented. This approach combines the elite strategy genetic algorithm with the hyperparameter optimization method based on grid search and cross-validation to obtain the best penalty factor and kernel function width of the Radial Basis Function (RBF) kernel function. The extracted features of production data are then used for prediction by inputting them into the improved support vector regression model, based on a shallow CNN without dimensionality reduction. Finally, the prediction accuracy of the CNN-ISVR model is evaluated using the three commonly used evaluation metrics: Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and coefficient of determination (R2). The model’s prediction results are then compared to those of other models. The CNN-ISVR hybrid model is shown to outperform other models in terms of prediction accuracy and generalization ability, demonstrating the effectiveness of the proposed model.

Health estimation of lithium-ion batteries with voltage reconstruction and fusion model

Accurate state of health (SOH) estimation is crucial for Lithium-ion battery in electric vehicles (EVs). This work proposes a battery SOH estimation method based on voltage reconstruction and fusion models. Firstly, a voltage curve reconstruction method based on importance sampling is proposed to solve the V–Q curve. Then, feature factors related to SOH are extracted and their correlation with SOH is analyzed. Furthermore, a SOH estimation fusion model is established based on improved Support Vector Regression (SVR) and Convolutional Neural Network (CNN). Finally, the accuracy of the proposed algorithm is verified in 20% and 30% small sample scenarios, respectively. The experimental results show that the numerical evaluation indicators of the proposed method are superior to Gauss Process Regression (GPR), CNN, whale optimization algorithm-SVR (WOA-SVR) and Long Short Term Memory (LSTM) neural network, which indicates that the proposed method has good performance.

State of health estimation for lithium-ion battery based on improved support vector regression

The lithium-ion battery has grown to be one of the most popular types of energy storage because of its many great qualities. However, the state of health (SOH) of the lithium-ion battery decreases as the number of cycles increases, resulting in reduced performance or even failure of the device, so an accurate SOH is essential for the safe operation of the device. To solve the issue of existing estimate methods' low estimation accuracy, a SOH estimation approach based on improved support vector regression is proposed. Firstly, the changes in battery characteristics during charging and discharging are analyzed and the health factors characterizing the SOH degradation are extracted. Pearson and Spearman correlation coefficients are used to quantitatively analyze the correlation between SOH and health factors. In addition, by optimizing the kernel function parameters of the SVR model by IALO, the improved ant lion optimization and support vector regression (IALO-SVR) based SOH estimation technique was developed. The IALO-SVR method was validated with the NASA battery dataset, and the experimental results showed that the method can estimate SOH more accurately compared with Back Propagation Neural Network (BP) and ALO-SVR methods, with an estimation error of no more than 1.8% at most.

Prediction Method for Sugarcane Syrup Brix Based on Improved Support Vector Regression

The brix of syrup is an important parameter in sugar production. To accurately measure syrup brix, a novel measurement method based on support vector regression (SVR) is presented. With the resonant frequency and quality factor as inputs and syrup brix as the output, a mathematical model of the relationship between the resonant frequency, quality factor, and syrup brix is established. Simultaneously, the particle swarm optimization (PSO) algorithm is used to optimize the penalty coefficient and radial basis kernel function of SVR to improve the performance of the model. The calculation model is trained and tested using the collected experimental data. The results show that the mean absolute error, mean absolute percentage error, and root mean square error of the syrup brix calculation model based on the improved SVR model can reach 0.74 °Bx, 2.24%, and 0.90 °Bx, respectively, while the determination coefficient can reach 0.9985. The simulation of the online measurement of syrup brix in the actual production process proves the excellent prediction performance of the syrup brix calculation model based on the improved PSO–SVR model, which can thus be used to predict the syrup brix.

Fatigue life prediction of welded joints based on improved support vector regression model under two‐level loading

AbstractTo meet the lightweight needs of modern machinery equipment, welded structure is widely used in practical engineering. During the service period, the welded structure is often subjected to multilevel variable amplitude loading, and fatigue failure is easy to occur. Due to the complexity and stochasticity of fatigue process, the traditional life prediction models cannot meet the demand of practical engineering. In this work, a novel prediction model based on the whale optimization algorithm (WOA) together with the support vector regression (SVR), namely, a WOA‐SVR model, is established. It combines the advantages of WOA and SVR for global searching optimization and high prediction accuracy dealing with small sample size. By taking into account the sequence of loadings and the interaction effect between loadings, the proposed WOA‐SVR model could overcome the deficiencies and shortcomings in existing models. Experiment results show that WOR‐SVR has better prediction performance than five models.

A fast data-driven optimization method of multi-area combined economic emission dispatch

To provide more feasible schemes for power system optimization management and operation, the interconnection of power grids in different areas is inevitable. Naturally, the multi-area combined economic/emission dispatch (MACEED) problem becomes a more important decision problem. However, as the dimensions of MACEED problems increase, existing studies may not obtain feasible scheduling decisions in a suitable time. On this background, MACEED problems are transferred into computational expensive problems. In order to solve high-dimensional, large-scale MACEED problems, a data-driven surrogate-assisted approach is proposed. First, a feature engineering-based support vector regression surrogate model is proposed to replace the traditional objective functions in high-dimensional MACEED problems. Second, knowledge distillation is applied as a freezing and fine-tuning mechanism for the improved support vector regression surrogate models, which significantly reduces the time required to build surrogate models. Third, an improved non-dominated sorting genetic algorithm-III is proposed to obtain feasible solutions to high-dimensional MACEED problem. The proposed algorithm enhances the convergence and diversity of optimal solutions. The effectiveness of the proposed data-driven approach is demonstrated through simulations of a four-area 40-unit test system under different constraints.

Self-discharge prediction method for lithium-ion batteries based on improved support vector machine

An improved support vector regression (SVR) method is proposed for predicting the self-discharge voltage drop (SDV-drop) in lithium-ion batteries. Multiple features were extracted according to the charge and discharge curves of lithium-ion batteries, and the three features having the strongest correlation with the SDV-drop were identified via grey relational analysis. Then, these three features were assigned different weight parameters to obtain composite features which were input into the improved support vector machine through differential evolution algorithm parameter optimization training. Finally, the improved SVR model was obtained. Model training and testing were performed via a battery charge and discharge experiment and battery static experimental data of a new energy vehicle company, and the results indicated that the proposed method had a higher prediction accuracy than the neural-network model and the Gaussian process regression model.

Prediction and Optimization of Surface Roughness for Laser-Assisted Machining SiC Ceramics Based on Improved Support Vector Regression.

In this paper, the surface roughness of SiC ceramics was investigated in laser-assisted machining (LAM) processes; machine learning was used to predict surface roughness and to optimize the process parameters, and therefore, to ultimately improve the surface quality of a workpiece and obtain excellent serviceability. First, single-factor turning experiments were carried out on SiC ceramics using LAM according to the material removal mechanism to investigate the variation trend of the effects of different laser powers, rotational speeds, feed rates, and cutting depths on surface roughness. Then, laser power, rotational speed, feed rate and cutting depth were selected as the four factors, and the surface roughness was used as the target value for the orthogonal experiments. The results of the single-factor experiments and the orthogonal experiments were combined to construct a prediction model based on the combination of the grey wolf optimization (GWO) algorithm and support vector regression (SVR). The coefficient of determination (R2) of the optimized prediction model reached 0.98676 with an average relative error of less than 2.624%. Finally, the GWO algorithm was used to optimize the global parameters of the prediction model again, and the optimal combination of process parameters was determined and verified by experiments. The actual minimum surface roughness (Ra) value was 0.418 μm, and the relative error was less than 1.91% as compared with the predicted value of the model. Therefore, the prediction model based on GWO-SVR can achieve accurate prediction of the surface roughness of SiC ceramics in LAM and can obtain the optimum surface roughness using parameter optimization.

Remaining useful life prediction of Lithium-ion battery using improved support vector regression and fuzzy information granulation

With the widespread use of lithium-ion batteries in various fields, battery Prognostics and Health Management (PHM) technologies are gaining more and more attention. Repeated use of batteries can lead to degradation of battery performance and thus affect battery life. Accurate prediction of the remaining useful life (RUL) of batteries is crucial and is the most central issue in battery PHM. In this paper, a method based on a combination of fuzzy information granulation (FIG) and support vector regression with artificial bee colony optimization (ABC-SVR) is proposed to estimate the RUL of Lithium-ion batteries. First, the capacity degradation data are divided into several windows using the FIG method. Second, the maximum and minimum values of each window are predicted separately using the ABC-SVR algorithm to obtain the information of the prediction window. Finally, the missing values of the prediction windows are complemented by the linear interpolation method to obtain the complete capacity prediction values, and the remaining useful life of the battery can be calculated according to the failure threshold. The results show that the proposed method obtains the RUL value with high accuracy.

Research on Soft Sensing Method of Straw Ethanol Fermentation Process Based on BSVR

Straw fermented fuel ethanol is a complex process with multivariable, large lag, and strong nonlinearity. It is difficult to directly measure the key parameters such as ethanol concentration and cell concentration online. Aiming at the problem, a soft sensing model of straw fermented ethanol based on improved support vector regression (SVR) is proposed. Based on the analysis of the process of ethanol production from straw fermentation, the Bayesian method is used to optimize the support vector regression (BSVR). And the concepts of generation a priori and generation likelihood are introduced to optimize the data prediction model. The comparative experiment of model training and testing is carried out. The simulation results show that the proposed BSVR method is better than SVR. It can improve the generalization ability of data and the anti-interference of the model, and its prediction accuracy and stability are higher.

Archard model guided feature engineering improved support vector regression for rail wear analysis

This paper applied Archard wear law in feature engineering for the improvement of Support Vector Regression (SVR) performance and realized the rail steel wear behavior prediction. The actual complex rail wear multidimensional degradation information was obtained from field maintenance records over a decade and the hidden data outliers raised the modelling challenges. We applied pre-process technologies including feature importance analysis, physical model guided feature generation and outlier detection to build up the SVR based robust nonlinear regression analysis framework. Individual railway parameters’ effects on the wear process were investigated and revealed through model interpretation-based post analysis. This work provides a practical approach to deploying machine learning algorithms for rail service maintenance data analysis and treatment of data outliers.

SOH prediction for lithium-ion battery based on improved support vector regression

ABSTRACT As a good energy storage element, lithium-ion batteries are used widely in electric vehicles and electric energy storage systems now, but its own State of Health (SOH) is difficult to measure directly. The Support Vector Regression (SVR) method can use the cell characteristics extracted from the experiment to predict the SOH of the cell.However,the method itself is difficult to determine the hyperparameters and has a large impact on the prediction accuracy.For this reason, this paper proposes the joint algorithm of Bat Algorithms (BA) and Support Vector Regression to predict the SOH of lithium-ion batteries, uses the BA algorithm to find the optimal SVR hyperparameters and uses Grey Relationship Analysis (GRA) to verify their high correlation with the battery SOH correlation.The proposed method was validated using a publicly available experimental dataset, and the results showed that the method has higher prediction accuracy compared with the conventional GA-SVR and PSO-SVR.

Quantitative analysis of the 2-mercaptobenzothiazole based on terahertz time-domain spectroscopy and an improved support vector regression

2-Mercaptobenzothiazole is an irreplaceable accelerator for rubber vulcanization. It is important to study the content of 2-mercaptobenzothiazole which has an important influence on the vulcanization process of rubber. In order to improve the detection efficiency of 2-mercaptobenzothiazole, a new quantitative analysis method was proposed based on terahertz time-domain spectroscopy and an improved support vector regression. Experimental samples are mixtures of 2-mercaptobenzothiazole and polyethylene with different mass fractions. Their time-domain spectroscopy was obtained by terahertz time-domain spectroscopy system. It is found that 2-mercaptobenzothiazole has obvious absorption characteristics at 0.88 THz. Use Least squares support vector regression optimized by bat algorithm, Correlation coefficient and root mean-square error of the prediction set were 0.9987 and 0.5564%. Experimental results demonstrate that the predictive result of least squares support vector regression optimized by bat algorithm model is better than that of partial least squares and support vector regression model. It provides a potential approach for quantitative analysis of other rubber additives.

A Dynamic Model Updating Method with Thermal Effects Based on Improved Support Vector Regression

The dynamic modeling of structures in a thermal environment has become a new research topic in structural dynamics. The amount of calculation caused by the complexity of the structure and the size of the FEM, which increase the difficulty in modeling the structural dynamic thermal effects are considered. In this study, model updating in thermal temperature environment is proposed based on the hierarchical method and improved SVR, and an iterative procedure is presented. First, the dynamic problem of structure under a thermal environment is classified into a thermal model and a structural dynamic model, and they are both constructed with the FE method. As a result, the model updating process is conducted for both the thermal model and structural dynamic model. Different from the variables in other model updating methods, the updating variables, which are composed of the mechanical characteristics and thermal parameters, in the proposed method are dominated by the temperature distribution of the structure. A surrogate model based on improved SVR is adopted in the hierarchical model updating approach to make the updating process more efficient. Finally, the improved SVR method is validated on a typical nonlinear function, and the proposed method is validated by updating the model of an elastic thin plate and a wing structure in a thermal environment.

Stochastic model updating considering thermal effect using perturbation and improved support vector regression

The dynamic modeling of structures in a thermal environment has become a new research topic in structural dynamics. Uncertainties caused by noise or material variability increase the difficulty in structural dynamic modeling when considering thermal effects. In this study, a finite element (FE) model updating approach is proposed that includes thermal effects and uncertainties by using a hierarchical strategy. First, the dynamic problem of a structure in a thermal environment is classified into a thermal model and a structural dynamic model, and they are both constructed by using the FE method. As a result, the model updating process is conducted for both the thermal model and structural dynamic model. Different from other works about model updating methods, the updating variables, which are composed of the mechanical characteristics and thermal parameters of the system, are dominated by the temperature distribution of the structure under study. A perturbation method and a surrogate model are adopted in the stochastic model updating approach to make the updating process highly efficient. Finally, the proposed method is validated by updating the model of a fuselage skin and a bolt connection beam in a thermal environment.

Prediction of Welding Deformation and Residual Stress of a Thin Plate by Improved Support Vector Regression.

Thin plates are widely utilized in aircraft, shipbuilding, and automotive industries to meet the requirements of lightweight components. Especially in modern shipbuilding, the thin plate structures not only meet the economic requirements of shipbuilding but also meet the strength and rigidity requirements of the ship. However, a thin plate is less stable and prone to destabilizing deformation in the welding process, which seriously affects the accuracy and performance of the thin plate welding structure. Therefore, it is beneficial to predict welding deformation and residual stress before welding. In this paper, a thin plate welding deformation and residual stress prediction model based on particle swarm optimization (PSO) and grid search(GS) improved support vector regression (PSO-GS-SVR) is established. The welding speed, welding current, welding voltage, and plate thickness are taken as input parameters of the improved support vector regression model, while longitudinal and transverse deformation and residual stress are taken as corresponding outputs. To improve the prediction accuracy of the support vector regression model, particle swarm optimization and grid search are used to optimize the parameters. The results show that the improved support regression model can accurately evaluate the deformation and residual stress of butt welding and has important engineering guiding significance.

Research on Temperature Prediction Model in Greenhouse Based on Improved SVR

The greenhouse is a multivariate, nonlinear, time-varying and time-lag system. The establishment of an accurate greenhouse temperature prediction model can effectively ensure the effectiveness of intelligent temperature control. In order to solve the problem of difficulty in modeling the temperature mechanism of greenhouses, this paper proposes a method based on improved Support Vector Regression to establish greenhouse temperature prediction, The PSO algorithm is used to optimize the hyper-parameters of the SVR. Using real greenhouse data to verify the effectiveness of the proposed model. Experimental results show that compared with the traditional BP neural network prediction model, the temperature prediction model in greenhouse based on improved SVR has significantly improved prediction accuracy and better prediction capabilities. Therefore, the greenhouse temperature prediction model based on improved SVR proposed in this paper can well characterize the actual greenhouse system.