The shape of strip is calculated by iterative method which combines strip plastic deformation model with rolls elastic deformation model through their calculation results, which can be called results coupling method. ...The shape of strip is calculated by iterative method which combines strip plastic deformation model with rolls elastic deformation model through their calculation results, which can be called results coupling method. Be- cause the shape and rolling force distribution are very sensitive to strip thickness transverse distribution% variation, the iterative course is rather unstable and sometimes convergence cannot be achieved. In addition, the calculating speed of results coupling method is low, which restricts its usable range. To solve the problem, a new model cou- pling method is developed, which takes the force distribution between rolls, rolling force distribution and strip＇s exit transverse displacement distribution as basic unknowns, and integrates strip plastic deformation model and rolls elas- tic deformation model as a unified linear equations through their internal relation, so the iterative calculation between the strip plastic deformation model and rolls elastic deformation model can be avoided. To prove the effectiveness of the model coupling method, two examples are calculated by results coupling method and model coupling method re- spectively. The results of front tension stress, back tension stress, strip^s exit gauge, the force between rolls and rolling force distribution calculated by model coupling method coincide very well with results coupling method. How- ever the calculation course of model coupling method is more steady than results coupling method, and its calculating speed is about ten times as much as the maximal speed of results coupling method, which validates its practicability and reliability.展开更多
It is difficult to obtain the desired strip shape using Sendzimir rolling mills because small diameter work rolls can be easily deformed by the roiling force. To control the strip shape effectively, it is important to...It is difficult to obtain the desired strip shape using Sendzimir rolling mills because small diameter work rolls can be easily deformed by the roiling force. To control the strip shape effectively, it is important to understand the relationship between the behavior of the shape actuator and the variation of the strip shape. A numerical model based on the contact element method was proposed for the prediction of strip shape. In this numerical model, the re- lationships between the actuating forces, the roll deflections, the thickness profiles of the entry and exit sides, and the strip shape were considered. The proposed numerical model for strip shape prediction was evaluated by computer simulation and experiment with respect to various AS-U roll and first intermediate roll positions.展开更多
In the strip rolling process, shape control system possesses the characteristics of nonlinearity, strong coupling, time delay and time variation. Based on self adapting Elman dynamic recursion network prediction model...In the strip rolling process, shape control system possesses the characteristics of nonlinearity, strong coupling, time delay and time variation. Based on self adapting Elman dynamic recursion network prediction model, the fuzzy control method was used to control the shape on four-high cold mill. The simulation results showed that the system can be applied to real time on line control of the shape.展开更多
Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed un...Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed under different icing conditions.Due to the complexity of the icing process,the rapid assessment of ice shape remains an important challenge.In this paper,an efficient prediction model of aircraft icing is established based on the deep belief network(DBN)and the stacked auto-encoder(SAE),which are all deep neural networks.The detailed network structures are designed and then the networks are trained according to the samples obtained by the icing numerical computation.After that the model is applied on the ice shape evaluation of NACA0012 airfoil.The results show that the model can accurately capture the nonlinear behavior of aircraft icing and thus make an excellent ice shape prediction.The model provides an important tool for aircraft icing analysis.展开更多
Instance segmentation has drawn mounting attention due to its significant utility.However,high computational costs have been widely acknowledged in this domain,as the instance mask is generally achieved by pixel-level...Instance segmentation has drawn mounting attention due to its significant utility.However,high computational costs have been widely acknowledged in this domain,as the instance mask is generally achieved by pixel-level labeling.In this paper,we present a conceptually efficient contour regression network based on the you only look once(YOLO)architecture named YOLO-CORE for instance segmentation.The mask of the instance is efficiently acquired by explicit and direct contour regression using our designed multiorder constraint consisting of a polar distance loss and a sector loss.Our proposed YOLO-CORE yields impressive segmentation performance in terms of both accuracy and speed.It achieves 57.9%AP@0.5 with 47 FPS(frames per second)on the semantic boundaries dataset(SBD)and 51.1%AP@0.5 with 46 FPS on the COCO dataset.The superior performance achieved by our method with explicit contour regression suggests a new technique line in the YOLO-based image understanding field.Moreover,our instance segmentation design can be flexibly integrated into existing deep detectors with negligible computation cost(65.86 BFLOPs(billion float operations per second)to 66.15 BFLOPs with the YOLOv3 detector).展开更多
基金Sponsored by National Science and Technology Support Plan of China (2009AA04Z143)Science and Technology Support Plan of Hebei Province of China (10212101D)Important Natural Science Foundation of Hebei Province of China (E2006001038)
文摘The shape of strip is calculated by iterative method which combines strip plastic deformation model with rolls elastic deformation model through their calculation results, which can be called results coupling method. Be- cause the shape and rolling force distribution are very sensitive to strip thickness transverse distribution% variation, the iterative course is rather unstable and sometimes convergence cannot be achieved. In addition, the calculating speed of results coupling method is low, which restricts its usable range. To solve the problem, a new model cou- pling method is developed, which takes the force distribution between rolls, rolling force distribution and strip＇s exit transverse displacement distribution as basic unknowns, and integrates strip plastic deformation model and rolls elas- tic deformation model as a unified linear equations through their internal relation, so the iterative calculation between the strip plastic deformation model and rolls elastic deformation model can be avoided. To prove the effectiveness of the model coupling method, two examples are calculated by results coupling method and model coupling method re- spectively. The results of front tension stress, back tension stress, strip^s exit gauge, the force between rolls and rolling force distribution calculated by model coupling method coincide very well with results coupling method. How- ever the calculation course of model coupling method is more steady than results coupling method, and its calculating speed is about ten times as much as the maximal speed of results coupling method, which validates its practicability and reliability.
基金Item Sponsored by Korea Science and Engineering Foundation(KOSEF)Grant Funded by Korea Government(MEST)(2010-0022521)
文摘It is difficult to obtain the desired strip shape using Sendzimir rolling mills because small diameter work rolls can be easily deformed by the roiling force. To control the strip shape effectively, it is important to understand the relationship between the behavior of the shape actuator and the variation of the strip shape. A numerical model based on the contact element method was proposed for the prediction of strip shape. In this numerical model, the re- lationships between the actuating forces, the roll deflections, the thickness profiles of the entry and exit sides, and the strip shape were considered. The proposed numerical model for strip shape prediction was evaluated by computer simulation and experiment with respect to various AS-U roll and first intermediate roll positions.
基金ItemSponsored by Provincial Natural Science Foundation of Hebei Province of China (E2004000206)
文摘In the strip rolling process, shape control system possesses the characteristics of nonlinearity, strong coupling, time delay and time variation. Based on self adapting Elman dynamic recursion network prediction model, the fuzzy control method was used to control the shape on four-high cold mill. The simulation results showed that the system can be applied to real time on line control of the shape.
基金supported in part by the National Natural Science Foundation of China(No.51606213)the National Major Science and Technology Projects(No.J2019-III-0010-0054)。
文摘Icing is an important factor threatening aircraft flight safety.According to the requirements of airworthiness regulations,aircraft icing safety assessment is needed to be carried out based on the ice shapes formed under different icing conditions.Due to the complexity of the icing process,the rapid assessment of ice shape remains an important challenge.In this paper,an efficient prediction model of aircraft icing is established based on the deep belief network(DBN)and the stacked auto-encoder(SAE),which are all deep neural networks.The detailed network structures are designed and then the networks are trained according to the samples obtained by the icing numerical computation.After that the model is applied on the ice shape evaluation of NACA0012 airfoil.The results show that the model can accurately capture the nonlinear behavior of aircraft icing and thus make an excellent ice shape prediction.The model provides an important tool for aircraft icing analysis.
基金supported by the National Key R&D Program of China(Nos.2018AAA0100104 and 2018AAA0100100)Natural Science Foundation of Jiangsu Province,China(No.BK20211164).
文摘Instance segmentation has drawn mounting attention due to its significant utility.However,high computational costs have been widely acknowledged in this domain,as the instance mask is generally achieved by pixel-level labeling.In this paper,we present a conceptually efficient contour regression network based on the you only look once(YOLO)architecture named YOLO-CORE for instance segmentation.The mask of the instance is efficiently acquired by explicit and direct contour regression using our designed multiorder constraint consisting of a polar distance loss and a sector loss.Our proposed YOLO-CORE yields impressive segmentation performance in terms of both accuracy and speed.It achieves 57.9%AP@0.5 with 47 FPS(frames per second)on the semantic boundaries dataset(SBD)and 51.1%AP@0.5 with 46 FPS on the COCO dataset.The superior performance achieved by our method with explicit contour regression suggests a new technique line in the YOLO-based image understanding field.Moreover,our instance segmentation design can be flexibly integrated into existing deep detectors with negligible computation cost(65.86 BFLOPs(billion float operations per second)to 66.15 BFLOPs with the YOLOv3 detector).
