To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new lig...To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.展开更多
<i><span style="font-family:;" "="">Parkia biglobosa</span></i><span style="font-family:;" "=""> is a much-loved and over-exploited Afric...<i><span style="font-family:;" "="">Parkia biglobosa</span></i><span style="font-family:;" "=""> is a much-loved and over-exploited African savannah species for its socio-economic importance. Knowing and taking into account its architectural unit, which is the basis for diagnosing phenology, productivity and tree health, could provide a new perspective on its sustainable management. The aim of this study is to establish the architectural development in <i>Parkia biglobosa</i> by retrospective analysis. To achieve this objective, 390 individuals of all sizes ranging from seedlings to senescent trees were observed and analysed under various soil and climatic conditions in Côte d’Ivoire. The results showed that <i>Parkia biglobosa</i> is a light plant but shading tolerant. It is a mixed vegetative axis plant, the stem is orthotropic* in its proximal part and plagiotropic* (collapsing) in its distal part in young stage. The tree then transitions to an adult and old stage into a tree with a plagiotropic* axis in the proximal and distal parts, the trunk is built up by superimposing collapsed relay axes that gradually straighten, branching is sympodial*, growth is defined and sexuality is terminal and lateral. The ontogeny takes place in three phases: initiation of development and establishment of the crown (young), then flowering and establishment of the architectural unity (adult) and finally the death of secondary axes in the crown, duplication of the architecture by a series of partial and total reiterations (old). The level of organisation is 5: the phytomere, the module or growth unit, the axis, the architectural unit and the reiterated complex. Retrospective analysis of the modules showed that the dimensions of the growth units are indicators of morphological variation and species adaptation to a changing climate (<i>P</i> < 0.05). However, the equations generated by the morphological and habitat dimension linkage models are not significant (<i>R</i><sup>2</sup> and <i>r</i> </span><span style="font-family:;" "="">< 0.7) to be used as a guide for field data collection. This study represents an initiation into the architectural study of this species and the information provided will serve as a basis for further research into the architecture in relation to the sustainable use of this species.</span>展开更多
The Moving Particle Semi-implicit (MPS) method performs well in simulating violent free surface flow and hence becomes popular in the area of fluid flow simulation. However, the implementations of searching neighbouri...The Moving Particle Semi-implicit (MPS) method performs well in simulating violent free surface flow and hence becomes popular in the area of fluid flow simulation. However, the implementations of searching neighbouring particles and solving the large sparse matrix equations (Poisson-type equation) are very time-consuming. In order to utilize the tremendous power of parallel computation of Graphics Processing Units (GPU), this study has developed a GPU-based MPS model employing the Compute Unified Device Architecture (CUDA) on NVIDIA GTX 280. The efficient neighbourhood particle searching is done through an indirect method and the Poisson-type pressure equation is solved by the Bi-Conjugate Gradient (BiCG) method. Four different optimization levels for the present general parallel GPU-based MPS model are demonstrated. In addition, the elaborate optimization of GPU code is also discussed. A benchmark problem of dam-breaking flow is simulated using both codes of the present GPU-based MPS and the original CPU-based MPS. The comparisons between them show that the GPU-based MPS model outperforms 26 times the traditional CPU model.展开更多
基金support provided by the National Natural Science Foundation of China(22122802,22278044,and 21878028)the Chongqing Science Fund for Distinguished Young Scholars(CSTB2022NSCQ-JQX0021)the Fundamental Research Funds for the Central Universities(2022CDJXY-003).
文摘To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.
文摘<i><span style="font-family:;" "="">Parkia biglobosa</span></i><span style="font-family:;" "=""> is a much-loved and over-exploited African savannah species for its socio-economic importance. Knowing and taking into account its architectural unit, which is the basis for diagnosing phenology, productivity and tree health, could provide a new perspective on its sustainable management. The aim of this study is to establish the architectural development in <i>Parkia biglobosa</i> by retrospective analysis. To achieve this objective, 390 individuals of all sizes ranging from seedlings to senescent trees were observed and analysed under various soil and climatic conditions in Côte d’Ivoire. The results showed that <i>Parkia biglobosa</i> is a light plant but shading tolerant. It is a mixed vegetative axis plant, the stem is orthotropic* in its proximal part and plagiotropic* (collapsing) in its distal part in young stage. The tree then transitions to an adult and old stage into a tree with a plagiotropic* axis in the proximal and distal parts, the trunk is built up by superimposing collapsed relay axes that gradually straighten, branching is sympodial*, growth is defined and sexuality is terminal and lateral. The ontogeny takes place in three phases: initiation of development and establishment of the crown (young), then flowering and establishment of the architectural unity (adult) and finally the death of secondary axes in the crown, duplication of the architecture by a series of partial and total reiterations (old). The level of organisation is 5: the phytomere, the module or growth unit, the axis, the architectural unit and the reiterated complex. Retrospective analysis of the modules showed that the dimensions of the growth units are indicators of morphological variation and species adaptation to a changing climate (<i>P</i> < 0.05). However, the equations generated by the morphological and habitat dimension linkage models are not significant (<i>R</i><sup>2</sup> and <i>r</i> </span><span style="font-family:;" "="">< 0.7) to be used as a guide for field data collection. This study represents an initiation into the architectural study of this species and the information provided will serve as a basis for further research into the architecture in relation to the sustainable use of this species.</span>
基金supported by the National Natural Science Foundation of China with Grant No. 10772040, 50921001 and 50909016The financial support from the Important National Science & Technology Specific Projects of China with Grant No. 2008ZX05026-02 is also appreciated
文摘The Moving Particle Semi-implicit (MPS) method performs well in simulating violent free surface flow and hence becomes popular in the area of fluid flow simulation. However, the implementations of searching neighbouring particles and solving the large sparse matrix equations (Poisson-type equation) are very time-consuming. In order to utilize the tremendous power of parallel computation of Graphics Processing Units (GPU), this study has developed a GPU-based MPS model employing the Compute Unified Device Architecture (CUDA) on NVIDIA GTX 280. The efficient neighbourhood particle searching is done through an indirect method and the Poisson-type pressure equation is solved by the Bi-Conjugate Gradient (BiCG) method. Four different optimization levels for the present general parallel GPU-based MPS model are demonstrated. In addition, the elaborate optimization of GPU code is also discussed. A benchmark problem of dam-breaking flow is simulated using both codes of the present GPU-based MPS and the original CPU-based MPS. The comparisons between them show that the GPU-based MPS model outperforms 26 times the traditional CPU model.
