Computer simulation codes were developed based on a proposed mathematical model for centrifugal mold filling processes and previous computer software for 3D mold filling and solidification of castings (CASM-3D for Win...Computer simulation codes were developed based on a proposed mathematical model for centrifugal mold filling processes and previous computer software for 3D mold filling and solidification of castings (CASM-3D for Windows). Sample simulations were implemented for mold filling processes of precision titanium castings under gravity and different centrifugal casting techniques. The computation results show that the alloy melt has a much stronger mold filling ability for thin section castings under a centrifugal force field than that only under the gravity. A 'return back' mold filling manner is showed to be a reasonable technique for centrifugal casting processes, especially for thin section precision castings.展开更多
A continuum model proposed for dendrite solidification of multicomponent alloys, with any partial solid back diffusion, was used to numerically simulate the macroscopic solidification transport phenomena and macrosegr...A continuum model proposed for dendrite solidification of multicomponent alloys, with any partial solid back diffusion, was used to numerically simulate the macroscopic solidification transport phenomena and macrosegregations in an upwards directionally solidified plain carbon steel ingot. The computational results of each macroscopic field of the physical variables involved in the solidification process at a middle solidification stage were presented.展开更多
Individual fish segmentation is a prerequisite for feature extraction and object identification in any machine vision system.In this paper,a method for segmentation of overlapping fish images in aquaculture was propos...Individual fish segmentation is a prerequisite for feature extraction and object identification in any machine vision system.In this paper,a method for segmentation of overlapping fish images in aquaculture was proposed.First,the shape factor was used to determine whether an overlap exists in the picture.Then,the corner points were extracted using the curvature scale space algorithm,and the skeleton obtained by the improved Zhang-Suen thinning algorithm.Finally,intersecting points were obtained,and the overlapped region was segmented.The results show that the average error rate and average segmentation efficiency of this method was 10%and 90%,respectively.Compared with the traditional watershed method,the separation point is accurate,and the segmentation accuracy is high.Thus,the proposed method achieves better performance in segmentation accuracy and effectiveness.This method can be applied to multi-target segmentation and fish behavior analysis systems,and it can effectively improve recognition precision.展开更多
In aquaculture,the accurate prediction of feed intake for group fish is considered to be crucial to any feeding system.Previous studies mainly used mathematical statistics to establish the mapping relationship between...In aquaculture,the accurate prediction of feed intake for group fish is considered to be crucial to any feeding system.Previous studies mainly used mathematical statistics to establish the mapping relationship between feed intake and influencing factors.The result was easily influenced by subjective experience.To solve the above issues,this paper proposed a feed intake prediction model for group fish using the back-propagation neural network(BPNN)and mind evolutionary algorithm(MEA).Firstly,four factors,including water temperature,dissolved oxygen,the average fish weight and the number of fish were selected as the input of the BPNN model.Secondly,the initial weight and threshold of the BPNN were optimized by the MEA to improve the matching precision.Finally,the prediction model was achieved after training.Experimental results showed that the correlation coefficient between the predicted and measured values reached 0.96.And the root mean squared error,mean square error,mean absolute error,mean absolute percent error of the model was 6.89,47.53,6.17 and 0.04,respectively.In addition,the proposed method also had the better nonlinear fitting ability than BPNN and GA-BP.By using an intelligent optimization algorithm,the mapping relationship between fish intake and environmental factors was automatically established,thus avoiding the subjectivity of traditional methods.Therefore,it can lay a theoretical foundation for the development of intelligent feeding equipment and meet the needs of the smart fishery.展开更多
文摘Computer simulation codes were developed based on a proposed mathematical model for centrifugal mold filling processes and previous computer software for 3D mold filling and solidification of castings (CASM-3D for Windows). Sample simulations were implemented for mold filling processes of precision titanium castings under gravity and different centrifugal casting techniques. The computation results show that the alloy melt has a much stronger mold filling ability for thin section castings under a centrifugal force field than that only under the gravity. A 'return back' mold filling manner is showed to be a reasonable technique for centrifugal casting processes, especially for thin section precision castings.
文摘A continuum model proposed for dendrite solidification of multicomponent alloys, with any partial solid back diffusion, was used to numerically simulate the macroscopic solidification transport phenomena and macrosegregations in an upwards directionally solidified plain carbon steel ingot. The computational results of each macroscopic field of the physical variables involved in the solidification process at a middle solidification stage were presented.
基金The research was supported by the National Key Technology R&D Program of China(2019YFD090086)the Beijing Excellent Talents Development Project(2017000057592G125)the Beijing Natural Science Foundation(4184089).
文摘Individual fish segmentation is a prerequisite for feature extraction and object identification in any machine vision system.In this paper,a method for segmentation of overlapping fish images in aquaculture was proposed.First,the shape factor was used to determine whether an overlap exists in the picture.Then,the corner points were extracted using the curvature scale space algorithm,and the skeleton obtained by the improved Zhang-Suen thinning algorithm.Finally,intersecting points were obtained,and the overlapped region was segmented.The results show that the average error rate and average segmentation efficiency of this method was 10%and 90%,respectively.Compared with the traditional watershed method,the separation point is accurate,and the segmentation accuracy is high.Thus,the proposed method achieves better performance in segmentation accuracy and effectiveness.This method can be applied to multi-target segmentation and fish behavior analysis systems,and it can effectively improve recognition precision.
基金The work was supported by the Beijing Excellent Talents Development Project(2017000057592G125)National Key Research and Development Program of China(2017YFD0701700).
文摘In aquaculture,the accurate prediction of feed intake for group fish is considered to be crucial to any feeding system.Previous studies mainly used mathematical statistics to establish the mapping relationship between feed intake and influencing factors.The result was easily influenced by subjective experience.To solve the above issues,this paper proposed a feed intake prediction model for group fish using the back-propagation neural network(BPNN)and mind evolutionary algorithm(MEA).Firstly,four factors,including water temperature,dissolved oxygen,the average fish weight and the number of fish were selected as the input of the BPNN model.Secondly,the initial weight and threshold of the BPNN were optimized by the MEA to improve the matching precision.Finally,the prediction model was achieved after training.Experimental results showed that the correlation coefficient between the predicted and measured values reached 0.96.And the root mean squared error,mean square error,mean absolute error,mean absolute percent error of the model was 6.89,47.53,6.17 and 0.04,respectively.In addition,the proposed method also had the better nonlinear fitting ability than BPNN and GA-BP.By using an intelligent optimization algorithm,the mapping relationship between fish intake and environmental factors was automatically established,thus avoiding the subjectivity of traditional methods.Therefore,it can lay a theoretical foundation for the development of intelligent feeding equipment and meet the needs of the smart fishery.