A method for the calculation of the sensitivity factors of the rollingprocess has been obtained by differentiating the roll force model based on support vector machine.It can eliminate the algebraic loop of the analyt...A method for the calculation of the sensitivity factors of the rollingprocess has been obtained by differentiating the roll force model based on support vector machine.It can eliminate the algebraic loop of the analytical model of the rolling process. The simulationsin the first stand of five stand cold tandem rolling mill indicate that the calculation forsensitivities by this proposed method can obtain a good accuracy, and an appropriate adjustment onthe control variables determined directly by the sensitivity has an excellent compensation accuracy.Moreover, the roll gap has larger effect on the exit thickness than both front tension and backtension, and it is more efficient to select the roll gap as the control variable of the thicknesscontrol system in the first stand.展开更多
Due to its highly favorable physical and chemical properties,titanium and titanium alloy are widely used in a variety of industries.Because of the low output of a single batch,plate cold rolling without tension is the...Due to its highly favorable physical and chemical properties,titanium and titanium alloy are widely used in a variety of industries.Because of the low output of a single batch,plate cold rolling without tension is the most common rolling production method for titanium alloy.This method is lack of on-line thickness closed-loop control,with carefully thickness setting models for precision.A set of high-precision thickness setting models are proposed to suit the production method.Because of frequent variations in rolling specification,a model structural for the combination of analytical models and statistical models is adopted to replace the traditional self-learning method.The deformation resistance and friction factor,the primary factors which affect model precision,are considered as the objectives of statistical modeling.Firstly,the coefficient fitting of deformation resistance analytical model based on over-determined equations set is adopted.Additionally,a support vector machine（SVM）is applied to the modeling of the deformation resistance and friction factor.The setting models are applied to a 1450 plate-coiling mill for titanium alloy plate rolling,and then thickness precision is found consistently to be within 3%,exceeding the precision of traditional setting models with a self-learning method based on a large number of stable rolling data.Excellent application performance is obtained.The proposed research provides a set of high-precision thickness setting models which are well adapted to the characteristics of titanium alloy plate cold rolling without tension.展开更多
The on-line diameter measurement of larger axis workpieces is hard to achieve high precision detection, because of the bad environment of locale, the problem to amend the measuring error by non-uniform temperature fie...The on-line diameter measurement of larger axis workpieces is hard to achieve high precision detection, because of the bad environment of locale, the problem to amend the measuring error by non-uniform temperature field, and the difficulty to collimate and locate by usual method. By improving the measurement accuracy of larger axis accessories, it is useful to raise axis and hole＇s industry produce level. Because of the influence of complex environment in locale and some influential factors which are hard excluded from the large diameter measurement with multi-rolling-wheels method, the measurement results may not support or even contradict each other. To the situation, this paper puts forward a mutual support deviation distinguish data fusion method, including mutual support deviation detection and weight data fusion. The mutual support deviation detection part can effectively remove or weaken the unexpected impact on the measurement results and the weight data fusion part can get more accurate estimate result to the detected data. So the method can further improve the reliability of measurement results and increase the accuracy of the measurement system. By using the weight data fusion based on the mutual support （DFMS） to the simulation and experiment data, both simulation results and experiment results show that the method can effectively distinguish the data influenced by unexpected impact and improve the stability and reliability of measurement results. The new provided mutual support deviation distinguish method can be used to single sensor measurement and multi-sensor measurement, and can be used as a reference in the data distinguish of other area. The DFMS is helpful to realize the diameter measurement expanded uncertainty in 5 ×10^-6D or even higher when the measured axis workpiece＇s diameter is 1-5 m （ 1 m ≤ D ≤5 m ）.展开更多
The investigation of the influences of important parameters including steel chemical composition and hot rolling parameters on the mechanical properties of steel is a key for the systems that are used to predict mecha...The investigation of the influences of important parameters including steel chemical composition and hot rolling parameters on the mechanical properties of steel is a key for the systems that are used to predict mechanical properties. To improve the prediction accuracy, support vector machine was used to predict the mechanical properties of hot-rolled plain carbon steel Q235B. Support vector machine is a novel machine learning method, which is a powerful tool used to solve the problem characterized by small sample, nonlinearity, and high dimension with a good generalization performance. On the basis of the data collected from the supervisor of hotrolling process, the support vector regression algorithm was used to build prediction models, and the off-line simulation indicates that predicted and measured results are in good agreement.展开更多
基金This project is supported by Provincial Natural Science Foundation of Hebei, China(No.503293).
文摘A method for the calculation of the sensitivity factors of the rollingprocess has been obtained by differentiating the roll force model based on support vector machine.It can eliminate the algebraic loop of the analytical model of the rolling process. The simulationsin the first stand of five stand cold tandem rolling mill indicate that the calculation forsensitivities by this proposed method can obtain a good accuracy, and an appropriate adjustment onthe control variables determined directly by the sensitivity has an excellent compensation accuracy.Moreover, the roll gap has larger effect on the exit thickness than both front tension and backtension, and it is more efficient to select the roll gap as the control variable of the thicknesscontrol system in the first stand.
基金Supported by National Natural Science Foundation of China(Grant No.51304017)National Key Technology R&D Program of the 12th Five-year Plan of China(Grant Nos.2012BAF04B02,2011BAE23B04)Fundamental Research Funds for Central Universities,China(Grant No.FRF-SD-12-013B)
文摘Due to its highly favorable physical and chemical properties,titanium and titanium alloy are widely used in a variety of industries.Because of the low output of a single batch,plate cold rolling without tension is the most common rolling production method for titanium alloy.This method is lack of on-line thickness closed-loop control,with carefully thickness setting models for precision.A set of high-precision thickness setting models are proposed to suit the production method.Because of frequent variations in rolling specification,a model structural for the combination of analytical models and statistical models is adopted to replace the traditional self-learning method.The deformation resistance and friction factor,the primary factors which affect model precision,are considered as the objectives of statistical modeling.Firstly,the coefficient fitting of deformation resistance analytical model based on over-determined equations set is adopted.Additionally,a support vector machine（SVM）is applied to the modeling of the deformation resistance and friction factor.The setting models are applied to a 1450 plate-coiling mill for titanium alloy plate rolling,and then thickness precision is found consistently to be within 3%,exceeding the precision of traditional setting models with a self-learning method based on a large number of stable rolling data.Excellent application performance is obtained.The proposed research provides a set of high-precision thickness setting models which are well adapted to the characteristics of titanium alloy plate cold rolling without tension.
基金supported by Focus of the Funding Item of Metrology of Military Industry in National Defense of China in "Tenth-five-year" Project (Grant No. 60104208)
文摘The on-line diameter measurement of larger axis workpieces is hard to achieve high precision detection, because of the bad environment of locale, the problem to amend the measuring error by non-uniform temperature field, and the difficulty to collimate and locate by usual method. By improving the measurement accuracy of larger axis accessories, it is useful to raise axis and hole＇s industry produce level. Because of the influence of complex environment in locale and some influential factors which are hard excluded from the large diameter measurement with multi-rolling-wheels method, the measurement results may not support or even contradict each other. To the situation, this paper puts forward a mutual support deviation distinguish data fusion method, including mutual support deviation detection and weight data fusion. The mutual support deviation detection part can effectively remove or weaken the unexpected impact on the measurement results and the weight data fusion part can get more accurate estimate result to the detected data. So the method can further improve the reliability of measurement results and increase the accuracy of the measurement system. By using the weight data fusion based on the mutual support （DFMS） to the simulation and experiment data, both simulation results and experiment results show that the method can effectively distinguish the data influenced by unexpected impact and improve the stability and reliability of measurement results. The new provided mutual support deviation distinguish method can be used to single sensor measurement and multi-sensor measurement, and can be used as a reference in the data distinguish of other area. The DFMS is helpful to realize the diameter measurement expanded uncertainty in 5 ×10^-6D or even higher when the measured axis workpiece＇s diameter is 1-5 m （ 1 m ≤ D ≤5 m ）.
文摘The investigation of the influences of important parameters including steel chemical composition and hot rolling parameters on the mechanical properties of steel is a key for the systems that are used to predict mechanical properties. To improve the prediction accuracy, support vector machine was used to predict the mechanical properties of hot-rolled plain carbon steel Q235B. Support vector machine is a novel machine learning method, which is a powerful tool used to solve the problem characterized by small sample, nonlinearity, and high dimension with a good generalization performance. On the basis of the data collected from the supervisor of hotrolling process, the support vector regression algorithm was used to build prediction models, and the off-line simulation indicates that predicted and measured results are in good agreement.
