Blank holder force (BHF) is an important measure to control the sheet metal forming. BHF is identified quickly using artificial neural network (ANN) on the basis of its analytical description. And critical rupture and...Blank holder force (BHF) is an important measure to control the sheet metal forming. BHF is identified quickly using artificial neural network (ANN) on the basis of its analytical description. And critical rupture and wrinkle BHF curves are given. A close-loop control system is established to finish the forming process.展开更多
At present,iron and steel enterprises mainly use“after spot test ward”to control final product quality.However,it is impossible to realize on-line quality predetermining for all products by this traditional approach...At present,iron and steel enterprises mainly use“after spot test ward”to control final product quality.However,it is impossible to realize on-line quality predetermining for all products by this traditional approach,hence claims and returns often occur,resulting in major eco-nomic losses of enterprises.In order to realize the on-line quality predetermining for steel products during manufacturing process,the predic-tion models of mechanical properties based on deep learning have been proposed in this work.First,the mechanical properties of deep drawing steels were predicted by using LSTM(long short team memory),GRU(gated recurrent unit)network,and GPR(Gaussian process regression)model,and prediction accuracy and learning efficiency for different models were also discussed.Then,on-line re-learning methods for transfer learning models and model parameters were proposed.The experimental results show that not only the prediction accuracy of optimized trans-fer learning models has been improved,but also predetermining time was shortened to meet real time requirements of on-line property prede-termining.The industrial production data of interstitial-free(IF)steel was used to demonstrate that R2 value of GRU model in training stage reaches more than 0.99,and R2 value in testing stage is more than 0.96.展开更多
The back-propagation neural （BPN） network was proposed to model the relationship between the parameters of the dieless draw- ing process and the microstrecmres of the QSi3-1 silicon bronze alloy. Combined with image...The back-propagation neural （BPN） network was proposed to model the relationship between the parameters of the dieless draw- ing process and the microstrecmres of the QSi3-1 silicon bronze alloy. Combined with image processing techniques, grain sizes and grain-boundary morphologies were respectively determined by the quantitative metallographic method and the flactal theory. The outcomes obtained show that the deformed microstructures exhibit typical fractal features, and the boundaries can be characterized quantitatively by ffactal dimensions. With the temperature of 600-800℃ and the drawing speed of 0.67-1.00 mm-s-1, either a lower temperature or a higher speed will cause a smaller grain size together with an elevated fractal dimension. The developed model can be capable for forecasting the microstructure evolution with a minimum error. The average relative errors between the predicted results and the experimental values of grain size and fractal dimension are 3.9% and 0.9%, respectively.展开更多
Intellectualization of sheet metal in deep drawing is a new combined technology, which is concerned with control science and computer science and sheet metal forming theory. The intelligent control system for sheet me...Intellectualization of sheet metal in deep drawing is a new combined technology, which is concerned with control science and computer science and sheet metal forming theory. The intelligent control system for sheet metal deep drawing consists of four fundamental factors: real time measurement, identification, prediction and control. Real time identification of material properties and friction coefficient is the most important factor in the whole system. An artificial neural network model for identification of the material properties and friction coefficient was established according to deep drawing characteristics and more automation. The identification of the material properties and friction coefficient was realized.展开更多
在工业自动化领域,数字化流程图在提高生产效率和降低成本等方面发挥着显著作用。工艺流程图是对具体生产过程进行抽象和概括,以图形化方式表示各种生产流程、设备和生产线路之间的关系和组合。在工艺流程图分析和再绘制应用中,人工识...在工业自动化领域,数字化流程图在提高生产效率和降低成本等方面发挥着显著作用。工艺流程图是对具体生产过程进行抽象和概括,以图形化方式表示各种生产流程、设备和生产线路之间的关系和组合。在工艺流程图分析和再绘制应用中,人工识别流程图具有机械性与重复性等特点,费时费力,效率低下。为此提出了一种基于深度学习的工艺流程图智能识别方法,利用目标检测网络、OCR(Optical Character Recognition,光学字符识别)网络和图像处理算法提取工艺流程图信息,包括工业设备、标识、文本和管线等元素,实现解放人力和提高工作效率的目的。展开更多
文摘Blank holder force (BHF) is an important measure to control the sheet metal forming. BHF is identified quickly using artificial neural network (ANN) on the basis of its analytical description. And critical rupture and wrinkle BHF curves are given. A close-loop control system is established to finish the forming process.
基金financially supported by the National Natural Science Foundation of China (No. 52175284)the State Key Lab of Advanced Metals and Materials in University of Science and Technology Beijing (No. 2021ZD08)
文摘At present,iron and steel enterprises mainly use“after spot test ward”to control final product quality.However,it is impossible to realize on-line quality predetermining for all products by this traditional approach,hence claims and returns often occur,resulting in major eco-nomic losses of enterprises.In order to realize the on-line quality predetermining for steel products during manufacturing process,the predic-tion models of mechanical properties based on deep learning have been proposed in this work.First,the mechanical properties of deep drawing steels were predicted by using LSTM(long short team memory),GRU(gated recurrent unit)network,and GPR(Gaussian process regression)model,and prediction accuracy and learning efficiency for different models were also discussed.Then,on-line re-learning methods for transfer learning models and model parameters were proposed.The experimental results show that not only the prediction accuracy of optimized trans-fer learning models has been improved,but also predetermining time was shortened to meet real time requirements of on-line property prede-termining.The industrial production data of interstitial-free(IF)steel was used to demonstrate that R2 value of GRU model in training stage reaches more than 0.99,and R2 value in testing stage is more than 0.96.
基金supported by the National Basic Research Priorities Program of China (No.2006CB605200)the National Natu-ral Science Foundation of China (Nos.50674008 and 50634010)+1 种基金the Program for New Century Excellent Talents in Chinese Universities (No.NCET-06-0083)the Foundation of State Key Laboratory for Advanced Metals and Materials (No.2008Z-15)
文摘The back-propagation neural （BPN） network was proposed to model the relationship between the parameters of the dieless draw- ing process and the microstrecmres of the QSi3-1 silicon bronze alloy. Combined with image processing techniques, grain sizes and grain-boundary morphologies were respectively determined by the quantitative metallographic method and the flactal theory. The outcomes obtained show that the deformed microstructures exhibit typical fractal features, and the boundaries can be characterized quantitatively by ffactal dimensions. With the temperature of 600-800℃ and the drawing speed of 0.67-1.00 mm-s-1, either a lower temperature or a higher speed will cause a smaller grain size together with an elevated fractal dimension. The developed model can be capable for forecasting the microstructure evolution with a minimum error. The average relative errors between the predicted results and the experimental values of grain size and fractal dimension are 3.9% and 0.9%, respectively.
文摘Intellectualization of sheet metal in deep drawing is a new combined technology, which is concerned with control science and computer science and sheet metal forming theory. The intelligent control system for sheet metal deep drawing consists of four fundamental factors: real time measurement, identification, prediction and control. Real time identification of material properties and friction coefficient is the most important factor in the whole system. An artificial neural network model for identification of the material properties and friction coefficient was established according to deep drawing characteristics and more automation. The identification of the material properties and friction coefficient was realized.
文摘在工业自动化领域,数字化流程图在提高生产效率和降低成本等方面发挥着显著作用。工艺流程图是对具体生产过程进行抽象和概括,以图形化方式表示各种生产流程、设备和生产线路之间的关系和组合。在工艺流程图分析和再绘制应用中,人工识别流程图具有机械性与重复性等特点,费时费力,效率低下。为此提出了一种基于深度学习的工艺流程图智能识别方法,利用目标检测网络、OCR(Optical Character Recognition,光学字符识别)网络和图像处理算法提取工艺流程图信息,包括工业设备、标识、文本和管线等元素,实现解放人力和提高工作效率的目的。
