In the traditional rolling force model of tandem cold rolling mills,the calculation of the deformation resistance of the strip head does not consider the actual size and mechanical properties of the incoming material,...In the traditional rolling force model of tandem cold rolling mills,the calculation of the deformation resistance of the strip head does not consider the actual size and mechanical properties of the incoming material,which results in a mismatch between the deformation resistance setting and the actual state of the incoming material and thus affects the accuracy of the rolling force during the low-speed rolling process of the strip head.The inverse calculation of deformation resistance was derived to obtain the actual deformation resistance of the strip head in the tandem cold rolling process,and the actual process parameters of the strip in the hot and cold rolling processes were integrated to create the cross-process dataset as the basis to establish the support vector regression(SVR)model.The grey wolf optimization(GWO)algorithm was used to optimize the hyperparameters in the SVR model,and a deformation resistance prediction model based on GWO–SVR was established.Compared with the traditional model,the GWO–SVR model shows different degrees of improvement in each stand,with significant improvement in stands S3–S5.The prediction results of the GWO–SVR model were applied to calculate the head rolling setting of a 1420 mm tandem rolling mill.The head rolling force had a similar degree of improvement in accuracy to the deformation resistance,and the phenomenon of low head rolling force setting from stands S3 to S5 was obviously improved.Meanwhile,the thickness quality and shape quality of the strip head were improved accordingly,and the application results were consistent with expectations.展开更多
In order to predict backfill strength rapidly with high accuracy and provide a new technical support for digitization and intelligentization of mine,a support vector regression(SVR)model improved by grey wolf optimiza...In order to predict backfill strength rapidly with high accuracy and provide a new technical support for digitization and intelligentization of mine,a support vector regression(SVR)model improved by grey wolf optimization(GWO),GWO-SVR model,is established.First,GWO is used to optimize penalty term and kernel function parameter in SVR model with high accuracy based on the experimental data of uniaxial compressive strength of filling body.Subsequently,a prediction model which uses the best two parameters of best c and best g is established with the slurry density,cement dosage,ratio of artificial aggregate to tailings,and curing time taken as input factors,and uniaxial compressive strength of backfill as the output factor.The root mean square error of this GWO-SVR model in predicting backfill strength is 0.143 and the coefficient of determination is 0.983,which means that the predictive effect of this model is accurate and reliable.Compared with the original SVR model without the optimization of GWO and particle swam optimization(PSO)-SVR model,the performance of GWO-SVR model is greatly promoted.The establishment of GWO-SVR model provides a new tool for predicting backfill strength scientifically.展开更多
With the continuous increase of solar penetration rate, it has brought challenges to the smooth operation of the power grid. Therefore, to make photovoltaic power generation not affect the smooth operation of the grid...With the continuous increase of solar penetration rate, it has brought challenges to the smooth operation of the power grid. Therefore, to make photovoltaic power generation not affect the smooth operation of the grid, accurate photovoltaic power prediction is required. And short-term forecasting is essential for the deployment of daily power generation plans. In this paper, A short-term photovoltaic power generation forecast method based on K-means++, grey relational analysis (GRA) and support vector regression (SVR) (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data was clustered through the multi-index K-means++ algorithm. And the similar days and the nearest neighbor similar day of the prediction day were selected by the GRA algorithm. Then, similar days and nearest neighbor similar days were used to train SVR to obtain an accurate photovoltaic power prediction model. Under ideal weather, the average values of MAE, RMSE, and R<sup>2</sup> were 0.8101 kW, 0.9608 kW, and 99.66%, respectively. The average computation time was 1.7487 s, which was significantly better than the SVR model. Thus, the demonstrated numerical results verify the effectiveness of the proposed model for short-term PV power prediction.展开更多
In order to ensure that the large-scale application of photovoltaic power generation does not affect the stability of the grid, accurate photovoltaic (PV) power generation forecast is essential. A short-term PV power ...In order to ensure that the large-scale application of photovoltaic power generation does not affect the stability of the grid, accurate photovoltaic (PV) power generation forecast is essential. A short-term PV power generation forecast method using the combination of K-means++, grey relational analysis (GRA) and support vector regression (SVR) based on feature selection (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data were clustered through the multi-index K-means++ algorithm and divided into ideal and non-ideal weather. The GRA algorithm was used to match the similar day and the nearest neighbor similar day of the prediction day. And selected appropriate input features for different weather types to train the SVR model. Under ideal weather, the average values of MAE, RMSE and R2 were 0.8101, 0.9608 kW and 99.66%, respectively. And this method reduced the average training time by 77.27% compared with the standard SVR model. Under non-ideal weather conditions, the average values of MAE, RMSE and R2 were 1.8337, 2.1379 kW and 98.47%, respectively. And this method reduced the average training time of the standard SVR model by 98.07%. The experimental results show that the prediction accuracy of the proposed model is significantly improved compared to the other five models, which verify the effectiveness of the method.展开更多
Grain yield security is a basic national policy of China,and changes in grain yield are influenced by a variety of factors,which often have a complex,non-linear relationship with each other.Therefore,this paper propos...Grain yield security is a basic national policy of China,and changes in grain yield are influenced by a variety of factors,which often have a complex,non-linear relationship with each other.Therefore,this paper proposes a Grey Relational Analysis-Adaptive Boosting-Support Vector Regression(GRA-AdaBoost-SVR)model,which can ensure the prediction accuracy of the model under small sample,improve the generalization ability,and enhance the prediction accuracy.SVR allows mapping to high-dimensional spaces using kernel functions,good for solving nonlinear problems.Grain yield datasets generally have small sample sizes and many features,making SVR a promising application for grain yield datasets.However,the SVR algorithm’s own problems with the selection of parameters and kernel functions make the model less generalizable.Therefore,the Adaptive Boosting(AdaBoost)algorithm can be used.Using the SVR algorithm as a training method for base learners in the AdaBoost algorithm.Effectively address the generalization capability problem in SVR algorithms.In addition,to address the problem of sensitivity to anomalous samples in the AdaBoost algorithm,the GRA method is used to extract influence factors with higher correlation and reduce the number of anomalous samples.Finally,applying the GRA-AdaBoost-SVR model to grain yield forecasting in China.Experiments were conducted to verify the correctness of the model and to compare the effectiveness of several traditional models applied to the grain yield data.The results show that the GRA-AdaBoost-SVR algorithm improves the prediction accuracy,the model is smoother,and confirms that the model possesses better prediction performance and better generalization ability.展开更多
基金This work was supported by the National Key Research and Development Plan of China(Grant No.2020YFB1713600)the National Natural Science Foundation of China(Grant No.51975043)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M69035)Fundamental Research Funds for the Central Universities(Grant Nos.FRF-TP-19-002A3 and FRF-TP-20-105A1).
文摘In the traditional rolling force model of tandem cold rolling mills,the calculation of the deformation resistance of the strip head does not consider the actual size and mechanical properties of the incoming material,which results in a mismatch between the deformation resistance setting and the actual state of the incoming material and thus affects the accuracy of the rolling force during the low-speed rolling process of the strip head.The inverse calculation of deformation resistance was derived to obtain the actual deformation resistance of the strip head in the tandem cold rolling process,and the actual process parameters of the strip in the hot and cold rolling processes were integrated to create the cross-process dataset as the basis to establish the support vector regression(SVR)model.The grey wolf optimization(GWO)algorithm was used to optimize the hyperparameters in the SVR model,and a deformation resistance prediction model based on GWO–SVR was established.Compared with the traditional model,the GWO–SVR model shows different degrees of improvement in each stand,with significant improvement in stands S3–S5.The prediction results of the GWO–SVR model were applied to calculate the head rolling setting of a 1420 mm tandem rolling mill.The head rolling force had a similar degree of improvement in accuracy to the deformation resistance,and the phenomenon of low head rolling force setting from stands S3 to S5 was obviously improved.Meanwhile,the thickness quality and shape quality of the strip head were improved accordingly,and the application results were consistent with expectations.
基金the National Natural Science Foundation of China(No.51304011)。
文摘In order to predict backfill strength rapidly with high accuracy and provide a new technical support for digitization and intelligentization of mine,a support vector regression(SVR)model improved by grey wolf optimization(GWO),GWO-SVR model,is established.First,GWO is used to optimize penalty term and kernel function parameter in SVR model with high accuracy based on the experimental data of uniaxial compressive strength of filling body.Subsequently,a prediction model which uses the best two parameters of best c and best g is established with the slurry density,cement dosage,ratio of artificial aggregate to tailings,and curing time taken as input factors,and uniaxial compressive strength of backfill as the output factor.The root mean square error of this GWO-SVR model in predicting backfill strength is 0.143 and the coefficient of determination is 0.983,which means that the predictive effect of this model is accurate and reliable.Compared with the original SVR model without the optimization of GWO and particle swam optimization(PSO)-SVR model,the performance of GWO-SVR model is greatly promoted.The establishment of GWO-SVR model provides a new tool for predicting backfill strength scientifically.
文摘With the continuous increase of solar penetration rate, it has brought challenges to the smooth operation of the power grid. Therefore, to make photovoltaic power generation not affect the smooth operation of the grid, accurate photovoltaic power prediction is required. And short-term forecasting is essential for the deployment of daily power generation plans. In this paper, A short-term photovoltaic power generation forecast method based on K-means++, grey relational analysis (GRA) and support vector regression (SVR) (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data was clustered through the multi-index K-means++ algorithm. And the similar days and the nearest neighbor similar day of the prediction day were selected by the GRA algorithm. Then, similar days and nearest neighbor similar days were used to train SVR to obtain an accurate photovoltaic power prediction model. Under ideal weather, the average values of MAE, RMSE, and R<sup>2</sup> were 0.8101 kW, 0.9608 kW, and 99.66%, respectively. The average computation time was 1.7487 s, which was significantly better than the SVR model. Thus, the demonstrated numerical results verify the effectiveness of the proposed model for short-term PV power prediction.
文摘In order to ensure that the large-scale application of photovoltaic power generation does not affect the stability of the grid, accurate photovoltaic (PV) power generation forecast is essential. A short-term PV power generation forecast method using the combination of K-means++, grey relational analysis (GRA) and support vector regression (SVR) based on feature selection (Hybrid Kmeans-GRA-SVR, HKGSVR) was proposed. The historical power data were clustered through the multi-index K-means++ algorithm and divided into ideal and non-ideal weather. The GRA algorithm was used to match the similar day and the nearest neighbor similar day of the prediction day. And selected appropriate input features for different weather types to train the SVR model. Under ideal weather, the average values of MAE, RMSE and R2 were 0.8101, 0.9608 kW and 99.66%, respectively. And this method reduced the average training time by 77.27% compared with the standard SVR model. Under non-ideal weather conditions, the average values of MAE, RMSE and R2 were 1.8337, 2.1379 kW and 98.47%, respectively. And this method reduced the average training time of the standard SVR model by 98.07%. The experimental results show that the prediction accuracy of the proposed model is significantly improved compared to the other five models, which verify the effectiveness of the method.
基金This work was support in part by Research on Key Technologies of Intelligent Decision-Making for Food Big Data under Grant 2018A01038in part by the National Science Fund for Youth of Hubei Province of China under Grant 2018CFB408+2 种基金in part by the Natural Science Foundation of Hubei Province of China under Grant 2015CFA061in part by the National Nature Science Foundation of China under Grant 61272278in part by the Major Technical Innovation Projects of Hubei Province under Grant 2018ABA099。
文摘Grain yield security is a basic national policy of China,and changes in grain yield are influenced by a variety of factors,which often have a complex,non-linear relationship with each other.Therefore,this paper proposes a Grey Relational Analysis-Adaptive Boosting-Support Vector Regression(GRA-AdaBoost-SVR)model,which can ensure the prediction accuracy of the model under small sample,improve the generalization ability,and enhance the prediction accuracy.SVR allows mapping to high-dimensional spaces using kernel functions,good for solving nonlinear problems.Grain yield datasets generally have small sample sizes and many features,making SVR a promising application for grain yield datasets.However,the SVR algorithm’s own problems with the selection of parameters and kernel functions make the model less generalizable.Therefore,the Adaptive Boosting(AdaBoost)algorithm can be used.Using the SVR algorithm as a training method for base learners in the AdaBoost algorithm.Effectively address the generalization capability problem in SVR algorithms.In addition,to address the problem of sensitivity to anomalous samples in the AdaBoost algorithm,the GRA method is used to extract influence factors with higher correlation and reduce the number of anomalous samples.Finally,applying the GRA-AdaBoost-SVR model to grain yield forecasting in China.Experiments were conducted to verify the correctness of the model and to compare the effectiveness of several traditional models applied to the grain yield data.The results show that the GRA-AdaBoost-SVR algorithm improves the prediction accuracy,the model is smoother,and confirms that the model possesses better prediction performance and better generalization ability.