Large language model-based agent systems are emerging as transformative technologies in chemical process simulation, enhancing efficiency, accuracy, and decision-making. By automating data analysis across structured a...Large language model-based agent systems are emerging as transformative technologies in chemical process simulation, enhancing efficiency, accuracy, and decision-making. By automating data analysis across structured and unstructured sources—including process parameters, experimental results, simulation data, and textual specifications—these systems address longstanding challenges such as manual parameter tuning, subjective expert reliance, and the gap between theoretical models and industrial application. This paper reviews the key barriers to broader adoption of large language model-based agent systems, including unstable software interfaces, limited dynamic modeling accuracy, and difficulties in multimodal data integration, which hinder scalable deployment. We then survey recent progress in domain-specific foundation models, model interpretability techniques, and industrial-grade validation platforms. Building on these insights, we propose a technical framework centered on three pillars: multimodal task perception, autonomous planning, and knowledge-driven iterative optimization. This framework supports adaptive reasoning and robust execution in complex simulation environments. Finally, we outline a next-generation intelligent paradigm where natural language-driven agent workflows unify high-level strategic intent with automated task execution. The paper concludes by identifying future research directions to enhance robustness, adaptability, and safety, paving the way for practical integration of large language model based agent systems into industrial-scale chemical process simulation.展开更多
We propose a dynamic automated infrastructure model for the cloud data centre which is aimed as an efficient service stipulation for the enormous number of users.The data center and cloud computing technologies have b...We propose a dynamic automated infrastructure model for the cloud data centre which is aimed as an efficient service stipulation for the enormous number of users.The data center and cloud computing technologies have been at the moment rendering attention to major research and development efforts by companies,governments,and academic and other research institutions.In that,the difficult task is to facilitate the infrastructure to construct the information available to application-driven services and make business-smart decisions.On the other hand,the challenges that remain are the provision of dynamic infrastructure for applications and information anywhere.Further,developing technologies to handle private cloud computing infrastructure and operations in a completely automated and secure way has been critical.As a result,the focus of this article is on service and infrastructure life cycle management.We also show how cloud users interact with the cloud,how they request services from the cloud,how they select cloud strategies to deliver the desired service,and how they analyze their cloud consumption.展开更多
In the modern analogue design, Transistor Level Fault Simulation (TLFS) plays the im-portant part since every fault in the whole circuit has to be simulated at that level. Unfortunately, it is a very CPU intensive tas...In the modern analogue design, Transistor Level Fault Simulation (TLFS) plays the im-portant part since every fault in the whole circuit has to be simulated at that level. Unfortunately, it is a very CPU intensive task even though it maintains the high accuracy. Therefore, High Level Fault Modeling (HLFM) and High Level Fault Simulation (HLFS) are required in order to alleviate the efforts of simulation. In this paper, different HLFM approaches are reviewed at the device level during last two decades. We clarify their domains of application and evaluate their strengths and current limitations. We also analyze causes of faults and introduce various test approaches.展开更多
This paper proposes a wireframe model-based method for automated internal design. The method is used to extract geometric structure of an internal wireframe model and find out all loop structures of furniture models. ...This paper proposes a wireframe model-based method for automated internal design. The method is used to extract geometric structure of an internal wireframe model and find out all loop structures of furniture models. The wireframe models are classified as the multiple independent sub-models according to the geometric structure by statistical analysis. The corresponding models are selected from a 3D model database to build an internal scene based on characteristic points of furniture wireframe models. In the experiments 3D database via manually selected 268 3D furniture models from Google 3D warehouse is built up. The experiments show that the method can construct 3D scenes in 1.1×103 ms. This method costs less time compared with traditional hierarchical method and depth-sensing camera method in the same experimental conditions. The method can be also used for 3D visualization either with complex backgrounds.展开更多
Soft biological tissues are challenging materials for both testing and modeling.Despite the development of many constitutive models,the processing of choosing the most suitable model remains heuristic,relying signific...Soft biological tissues are challenging materials for both testing and modeling.Despite the development of many constitutive models,the processing of choosing the most suitable model remains heuristic,relying significantly on personal experience and preference.Another issue is that the amount of collected experimental data is always finite.In this study,we trained a constitutive artificial neural network based on experimental data of cattle skeletal muscle tissue for the self-directed auto-discovery of constitutive models.The discovered models inherently satisfy thermodynamic consistency,material objectivity,polyconvexity,and necessary physical restrictions.Two constitutive models have been discovered by the trained neural network.Considering the constraints of finite experimental data,the generality and reliability of the auto-discovered con-stitutive models remain to be analyzed.Through experimental data of pig skeletal muscle tissue,we assess the goodness-of-fit and parameter identifiability of the automatically discovered constitutive models.At first glance,both auto-discovered models have excellent prediction accuracy.Further exploration from the perspective of information geometry suggests that one of the auto-discovered models is superior to the other in terms of parameter identifiability.The findings of the current work are expected to extend our understanding of auto-discovered constitutive models and offer a new perspective to advance machine learning-driven mechanics.展开更多
Challenges arise in automate design with building information modeling(BIM)in underground space.Industry foundation classes(IFC)standard lacks detailed entity objects for describing excavation retaining structures and...Challenges arise in automate design with building information modeling(BIM)in underground space.Industry foundation classes(IFC)standard lacks detailed entity objects for describing excavation retaining structures and geological information,and automated design based on BIM models is not yet for practical application.This study presents a novel automated framework.It integrates the extended IFC standard with mechanical analysis and BIM modeling,significantly advancing structural optimization and rebar detailing.Direct 3D model generation streamlines complex excavation projects,aligning with the trend towards automated,precision-driven design.Key contributions include:(1)the extension of the IFC standard to support excavation retaining structures with objects like IfcBracedPit and IfcPitWall,improving interoperability between geotechnical models and BIM systems;(2)the integration of heuristic algorithms for automated optimization of deformation control parameters,reducing manual intervention;and(3)the promotion of design methodology that bypasses two-dimensional modeling and directly generates three-dimensional models,enhancing efficiency and allowing engineers to focus on high-level decision-making.However,the framework is primarily suited for standard cross-section projects like subway stations and tunnels.Future work will focus on refining the framework for more complex geotechnical projects,addressing software independence and improving design robustness and independence.展开更多
In order to reduce the traffic pressure of urban arterial road with the rational utilization of the branch road,the vehicle meeting behavior on the branch road without divided lane was described,and the cellular autom...In order to reduce the traffic pressure of urban arterial road with the rational utilization of the branch road,the vehicle meeting behavior on the branch road without divided lane was described,and the cellular automation (CA) model was put forward by introducing meeting behavior to reflect the relation between safe meeting speed and road width.The numerical simulation results depict several relation curves between road section capacity,speed and road width under different directional distributions of traffic flow,as well as the curves between the major and minor direction saturation flow,speed and road width.These relation characteristics indicate that except the one-way road section capacity and speed remaining unchanged,other road section capacities and speeds under different directional distributions increase with the increase of road width.On narrow road,the two-way traffic capacity and speed are less than those of one-way traffic;on wide road,the two-way traffic capacity doubles that of one-way traffic,but their speeds are almost the same.As the directional distribution moves to an even distribution of 50/50,the major direction saturation flows and speeds as well as the minor direction speeds tend to decease,while the minor direction saturation flow tends to increase.展开更多
In this paper, we use the cellular automation model to imitate earthquake process and draw some conclusionsof general applicability. First, it is confirmed that earthquake process has some ordering characters, and it ...In this paper, we use the cellular automation model to imitate earthquake process and draw some conclusionsof general applicability. First, it is confirmed that earthquake process has some ordering characters, and it isshown that both the existence and their mutual arrangement of faults could obviously influence the overallcharacters of earthquake process. Then the characters of each stage of model evolution are explained withself-organized critical state theory. Finally, earthquake sequences produced by the models are analysed interms pf algorithmic complexity and the result shows that AC-values of algorithmic complexity could be usedto study earthquake process and evolution.展开更多
Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.H...Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.However,the collected data often lack context;this can make the automated models less precise in terms of domain knowledge than those created by an expert human modeler.The lack of domain knowledge in modeling automation can be addressed with ontologies.In this paper,we introduce an ontology framework to improve automatic threat modeling.The framework is developed with conceptual modeling and validated using three different datasets:a small scale utility lab,water utility control network,and university IT environment.The framework produced successful results such as standardizing input sources,removing duplicate name entries,and grouping application software more logically.展开更多
Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.H...Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.However,the collected data often lack context;this can make the automated models less precise in terms of domain knowledge than those created by an expert human modeler.The lack of domain knowledge in modeling automation can be addressed with ontologies.In this paper,we introduce an ontology framework to improve automatic threat modeling.The framework is developed with conceptual modeling and validated using three different datasets:a small scale utility lab,water utility control network,and university IT environment.The framework produced successful results such as standardizing input sources,removing duplicate name entries,and grouping application software more logically.展开更多
To address the challenges of ill-defined optimization objectives,difficult constraint coordination,and lack of quantitative basis for interconnection splicing and switch placement in current distribution network topol...To address the challenges of ill-defined optimization objectives,difficult constraint coordination,and lack of quantitative basis for interconnection splicing and switch placement in current distribution network topology optimization,this paper proposes a data-driven intelligent optimization method for panoramic construction of distribution network topology based on the Common Information Model(CIM).This method integrates multi-source heterogeneous data relationships-including equipment,terminals,and connection nodes-through joint analysis of multi-line CIM and hierarchical topology extraction.It automatically identifies feeder trunk paths and branch structures,incorporates inter-connection switch splicing and intelligent path optimization strategies,and performs topology opti-mization and switch placement based on the principle of minimizing outage impact.This constructs a complete,robust main-branch topology graph model.The algorithm employs depth-first search(DFS)for supply path modeling,complemented by semantic analysis of equipment attributes and hierarchical node classification to refine topology simplification.Batch testing on a dataset of 6880 medium-voltage feeders in a Central China city achieved a 98.30%successful modeling rate for complete interconnection information,with an average processing time of approximately 4.57 s per feeder.Further validation using representative overhead,cable,and hybrid lines demonstrated high consistency between the automatically generated topology and the original system diagram in node identification,path con-struction,and information annotation,confirming the algorithm's structural adaptability and engi-neering practicality.These findings provide dynamically interactive topology model support for multiple distribution network scenarios-including planning,operation,and maintenance-offering significant application and promotion value.展开更多
Effective model reduction methods are required to deal with new challenges in active distribution network simulations that are on a large scale and have complicated structures.In the development of advanced electromag...Effective model reduction methods are required to deal with new challenges in active distribution network simulations that are on a large scale and have complicated structures.In the development of advanced electromagnetic transient simulation programs,automated model reduction plays an important role.This paper proposes an automated realization algorithm for the Krylov subspace based model reduction methods of an active distribution network with which the reduced model can be automatically established according to a given threshold of reduction error.The combined state-space nodal analysis framework is employed to apply the automated model reduction algorithm in popular EMTP-type simulation programs.Simulations are performed using PSCAD and a self-developed program to show the feasibility and validity of the proposed methods.展开更多
文摘Large language model-based agent systems are emerging as transformative technologies in chemical process simulation, enhancing efficiency, accuracy, and decision-making. By automating data analysis across structured and unstructured sources—including process parameters, experimental results, simulation data, and textual specifications—these systems address longstanding challenges such as manual parameter tuning, subjective expert reliance, and the gap between theoretical models and industrial application. This paper reviews the key barriers to broader adoption of large language model-based agent systems, including unstable software interfaces, limited dynamic modeling accuracy, and difficulties in multimodal data integration, which hinder scalable deployment. We then survey recent progress in domain-specific foundation models, model interpretability techniques, and industrial-grade validation platforms. Building on these insights, we propose a technical framework centered on three pillars: multimodal task perception, autonomous planning, and knowledge-driven iterative optimization. This framework supports adaptive reasoning and robust execution in complex simulation environments. Finally, we outline a next-generation intelligent paradigm where natural language-driven agent workflows unify high-level strategic intent with automated task execution. The paper concludes by identifying future research directions to enhance robustness, adaptability, and safety, paving the way for practical integration of large language model based agent systems into industrial-scale chemical process simulation.
基金This research work was fully supported by King Khalid University,Abha,Kingdom of Saudi Arabia,for funding this work through a Large Research Project under grant number RGP/161/42.
文摘We propose a dynamic automated infrastructure model for the cloud data centre which is aimed as an efficient service stipulation for the enormous number of users.The data center and cloud computing technologies have been at the moment rendering attention to major research and development efforts by companies,governments,and academic and other research institutions.In that,the difficult task is to facilitate the infrastructure to construct the information available to application-driven services and make business-smart decisions.On the other hand,the challenges that remain are the provision of dynamic infrastructure for applications and information anywhere.Further,developing technologies to handle private cloud computing infrastructure and operations in a completely automated and secure way has been critical.As a result,the focus of this article is on service and infrastructure life cycle management.We also show how cloud users interact with the cloud,how they request services from the cloud,how they select cloud strategies to deliver the desired service,and how they analyze their cloud consumption.
基金Supported by the Fundamental Research Grand Scheme(Ref: frgs 2/2010/TK/UTP/0318, Ministry of High Education (MOHE)MalaysiaShort Tem Internal Research Fund (STIRF No. 20/10.11)) provided by Research Enterprise Office, Universiti Teknologi Petronas, Malaysia in 2010-2012
文摘In the modern analogue design, Transistor Level Fault Simulation (TLFS) plays the im-portant part since every fault in the whole circuit has to be simulated at that level. Unfortunately, it is a very CPU intensive task even though it maintains the high accuracy. Therefore, High Level Fault Modeling (HLFM) and High Level Fault Simulation (HLFS) are required in order to alleviate the efforts of simulation. In this paper, different HLFM approaches are reviewed at the device level during last two decades. We clarify their domains of application and evaluate their strengths and current limitations. We also analyze causes of faults and introduce various test approaches.
基金Suppported by the National Natural Science Foundation of China(61303214)
文摘This paper proposes a wireframe model-based method for automated internal design. The method is used to extract geometric structure of an internal wireframe model and find out all loop structures of furniture models. The wireframe models are classified as the multiple independent sub-models according to the geometric structure by statistical analysis. The corresponding models are selected from a 3D model database to build an internal scene based on characteristic points of furniture wireframe models. In the experiments 3D database via manually selected 268 3D furniture models from Google 3D warehouse is built up. The experiments show that the method can construct 3D scenes in 1.1×103 ms. This method costs less time compared with traditional hierarchical method and depth-sensing camera method in the same experimental conditions. The method can be also used for 3D visualization either with complex backgrounds.
基金supported by the National Natural Science Foundation of China(NNSFC)(Grant Nos.12272132 and 11922206).
文摘Soft biological tissues are challenging materials for both testing and modeling.Despite the development of many constitutive models,the processing of choosing the most suitable model remains heuristic,relying significantly on personal experience and preference.Another issue is that the amount of collected experimental data is always finite.In this study,we trained a constitutive artificial neural network based on experimental data of cattle skeletal muscle tissue for the self-directed auto-discovery of constitutive models.The discovered models inherently satisfy thermodynamic consistency,material objectivity,polyconvexity,and necessary physical restrictions.Two constitutive models have been discovered by the trained neural network.Considering the constraints of finite experimental data,the generality and reliability of the auto-discovered con-stitutive models remain to be analyzed.Through experimental data of pig skeletal muscle tissue,we assess the goodness-of-fit and parameter identifiability of the automatically discovered constitutive models.At first glance,both auto-discovered models have excellent prediction accuracy.Further exploration from the perspective of information geometry suggests that one of the auto-discovered models is superior to the other in terms of parameter identifiability.The findings of the current work are expected to extend our understanding of auto-discovered constitutive models and offer a new perspective to advance machine learning-driven mechanics.
基金supported by the National Key R&D Program of China(Grant No.2023YFC3009400)National Natural Science Foundation of China(Grant Nos.52238009,52208344,and 52278350)+1 种基金Natural Science Foundation of Jiangxi Province(Grant No.20223BBG71018)the Innovation Fund of Jiangxi Province for Postgraduate(Grant No.YC2024-B196).
文摘Challenges arise in automate design with building information modeling(BIM)in underground space.Industry foundation classes(IFC)standard lacks detailed entity objects for describing excavation retaining structures and geological information,and automated design based on BIM models is not yet for practical application.This study presents a novel automated framework.It integrates the extended IFC standard with mechanical analysis and BIM modeling,significantly advancing structural optimization and rebar detailing.Direct 3D model generation streamlines complex excavation projects,aligning with the trend towards automated,precision-driven design.Key contributions include:(1)the extension of the IFC standard to support excavation retaining structures with objects like IfcBracedPit and IfcPitWall,improving interoperability between geotechnical models and BIM systems;(2)the integration of heuristic algorithms for automated optimization of deformation control parameters,reducing manual intervention;and(3)the promotion of design methodology that bypasses two-dimensional modeling and directly generates three-dimensional models,enhancing efficiency and allowing engineers to focus on high-level decision-making.However,the framework is primarily suited for standard cross-section projects like subway stations and tunnels.Future work will focus on refining the framework for more complex geotechnical projects,addressing software independence and improving design robustness and independence.
基金Project(71171200) supported by the National Natural Science Foundation of China
文摘In order to reduce the traffic pressure of urban arterial road with the rational utilization of the branch road,the vehicle meeting behavior on the branch road without divided lane was described,and the cellular automation (CA) model was put forward by introducing meeting behavior to reflect the relation between safe meeting speed and road width.The numerical simulation results depict several relation curves between road section capacity,speed and road width under different directional distributions of traffic flow,as well as the curves between the major and minor direction saturation flow,speed and road width.These relation characteristics indicate that except the one-way road section capacity and speed remaining unchanged,other road section capacities and speeds under different directional distributions increase with the increase of road width.On narrow road,the two-way traffic capacity and speed are less than those of one-way traffic;on wide road,the two-way traffic capacity doubles that of one-way traffic,but their speeds are almost the same.As the directional distribution moves to an even distribution of 50/50,the major direction saturation flows and speeds as well as the minor direction speeds tend to decease,while the minor direction saturation flow tends to increase.
文摘In this paper, we use the cellular automation model to imitate earthquake process and draw some conclusionsof general applicability. First, it is confirmed that earthquake process has some ordering characters, and it isshown that both the existence and their mutual arrangement of faults could obviously influence the overallcharacters of earthquake process. Then the characters of each stage of model evolution are explained withself-organized critical state theory. Finally, earthquake sequences produced by the models are analysed interms pf algorithmic complexity and the result shows that AC-values of algorithmic complexity could be usedto study earthquake process and evolution.
基金This work has received funding from the European Unions H2020 research and innovation programme under the Grant Agreement No.832907Swedish Governmental Agency for Innovation Systems(Vinnova),the Swedish Energy Agency,SweGRIDS,and STandUP for Energy.
文摘Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.However,the collected data often lack context;this can make the automated models less precise in terms of domain knowledge than those created by an expert human modeler.The lack of domain knowledge in modeling automation can be addressed with ontologies.In this paper,we introduce an ontology framework to improve automatic threat modeling.The framework is developed with conceptual modeling and validated using three different datasets:a small scale utility lab,water utility control network,and university IT environment.The framework produced successful results such as standardizing input sources,removing duplicate name entries,and grouping application software more logically.
基金received funding from the European Unions H2020 research and innovation programme under the Grant Agreement No.832907Swedish Governmental Agency for Innovation Systems(Vinnova)the Swedish Energy Agency,SweGRIDS,and STandUP for Energy.
文摘Threat modeling is of increasing importance to IT security,and it is a complex and resource demanding task.The aim of automating threat modeling is to simplify model creation by using data that are already available.However,the collected data often lack context;this can make the automated models less precise in terms of domain knowledge than those created by an expert human modeler.The lack of domain knowledge in modeling automation can be addressed with ontologies.In this paper,we introduce an ontology framework to improve automatic threat modeling.The framework is developed with conceptual modeling and validated using three different datasets:a small scale utility lab,water utility control network,and university IT environment.The framework produced successful results such as standardizing input sources,removing duplicate name entries,and grouping application software more logically.
基金supported by the State Grid Corporation of China science and technology project funding(5400-202322560A-3-2-ZN).
文摘To address the challenges of ill-defined optimization objectives,difficult constraint coordination,and lack of quantitative basis for interconnection splicing and switch placement in current distribution network topology optimization,this paper proposes a data-driven intelligent optimization method for panoramic construction of distribution network topology based on the Common Information Model(CIM).This method integrates multi-source heterogeneous data relationships-including equipment,terminals,and connection nodes-through joint analysis of multi-line CIM and hierarchical topology extraction.It automatically identifies feeder trunk paths and branch structures,incorporates inter-connection switch splicing and intelligent path optimization strategies,and performs topology opti-mization and switch placement based on the principle of minimizing outage impact.This constructs a complete,robust main-branch topology graph model.The algorithm employs depth-first search(DFS)for supply path modeling,complemented by semantic analysis of equipment attributes and hierarchical node classification to refine topology simplification.Batch testing on a dataset of 6880 medium-voltage feeders in a Central China city achieved a 98.30%successful modeling rate for complete interconnection information,with an average processing time of approximately 4.57 s per feeder.Further validation using representative overhead,cable,and hybrid lines demonstrated high consistency between the automatically generated topology and the original system diagram in node identification,path con-struction,and information annotation,confirming the algorithm's structural adaptability and engi-neering practicality.These findings provide dynamically interactive topology model support for multiple distribution network scenarios-including planning,operation,and maintenance-offering significant application and promotion value.
基金supported in part by the National Key Technology Research and Development Program of China(2013BAAOlB03)in part by the National Natural Science Foundation of China(51261130473).
文摘Effective model reduction methods are required to deal with new challenges in active distribution network simulations that are on a large scale and have complicated structures.In the development of advanced electromagnetic transient simulation programs,automated model reduction plays an important role.This paper proposes an automated realization algorithm for the Krylov subspace based model reduction methods of an active distribution network with which the reduced model can be automatically established according to a given threshold of reduction error.The combined state-space nodal analysis framework is employed to apply the automated model reduction algorithm in popular EMTP-type simulation programs.Simulations are performed using PSCAD and a self-developed program to show the feasibility and validity of the proposed methods.
