Automatic task model generation for Interface Agent development

Simulation modeling provides powerful decision support capabilities for production planning in manufacturing systems, yet widespread adoption remains limited by significant barriers in model development and maintenance. Traditional simulation approaches require substantial expertise, time investment, and financial resources, creating accessibility challenges particularly for small and medium enterprises. Current research on automatic simulation generation overlooks the significant potential that generative AI can offer in bridging the gap between natural language expression and executable model creation. This paper presents a novel methodology integrating large language models (LLMs) with automatic simulation model generation (ASMG) to enable direct generation of executable simulation models from natural language conversations. Unlike existing ASMG approaches that require formal specifications or simulation knowledge, our framework reduces programming requirements by allowing users to create functional models through conversational interaction. Our approach leverages natural language processing capabilities to transform user requests into executable simulation models without requiring specialized programming knowledge, enhancing human–machine interaction in production planning environments. The framework implements a four-step process: user intent expression through natural language interfaces, knowledge extraction using structured templates, simulation model construction via object-oriented data-driven components, and simulation execution with comprehensive result analysis for resource utilization, bottleneck identification, and production scheduling optimization. Performance testing demonstrates successful model generation across 18 supported action types with response times ranging from 8 s for simple operations to 5 min for complete manufacturing system creation. By enabling direct conversion of natural language requests into functional simulation models, this LLM-enhanced ASMG approach represents a step toward expanding access to simulation technology for non-expert users while maintaining the analytical power needed for complex manufacturing decision support and production control.

Industrial control systems (ICS) are defined with hardware and software components dedicated to control and monitoring tasks for factory process. Proper functioning of ICS architectures is mainly linked to the performance they offer. System integrators (SI) must know performance of the architecture they propose to the customers by assessing them. Many methodologies have already proven their capabilities to assess ICS architecture performance. One of them is colored Petri Nets (CPN). To assess the performance of ICS architecture using CPN involve defining manually the model. Pre-sales uncertain context involves problematic making this manual model definition challenging. This paper introduces a concept allowing automatic CPN model generation by instantiation and parameterization. However before introducing the concept, the paper shows the problematic involved by the pre-sales context. Then shows why CPN methodology is a relevant solution for assessing the performance of ICS in this context.

The authors discuss the development of a railway simulation system incorporating automatic model specification and automatic model generation techniques. The modeling environment features a GEM-like graphical user interface consisting of a layout editor and an icon editor. The model builder draws only the geometrical layout of a railway network section (e.g., a railway terminal) including the position of the signals, thus constructing a partial railway model. This graphical model consists of arcs representing tracks and nodes that represent junctions. The system assists in completing the specification of the model by automatically inferring the layout of the remaining control installations and the possible train routes through the network. Thus, by the end of this process the modeler has come up with a complete railway network data model stored in a database. The final stage of the project involves the development of a simulation code generator that will transform the stored data model to simulation code. >

This paper presents methods for automatic generation of models of Transducer, a highly flexible communication module for interfacing Multiprocessor System-on-Chip (MPSoC) components. We describe the transducer architecture, comprising the bus interface, high-level communication controllers and buffer management blocks. The well-defined architecture of the transducer enables automatic generation of its Transaction-level and Register-transfer level (RTL) models. Moreover, the simple interface of the transducer provides for a well-defined software interface, making it easy to update the software after changes in MPSoC platform. Our experimental results show that MPSoC design for industrial-size applications, such as MP3 decoder and JPEG encoder, greatly benefits from automatic generation of transducer models. We found productivity gains of 9-23× due to significant savings in modeling effort. On the quality axis, we show that MPSoC communication design using automatically generated transducers has very little overhead in communication delay over a fully connected point-to-point communication architecture. Finally, we show that our automatically generated TLMs greatly reduce the system-level modeling time and provide a fast executable model for early functional validation.

Customization of manipulator configurations using modularity and reconfigurability aspects is receiving much attention. Modules presented so far in literature deals with the conventional and standard configurations. This paper presents the 3D printable, light-weight and unconventional modules: MOIRs' Mark-2, to develop any custom `n'-Degrees-of-Freedom (DoF) serial manipulator even with the non-parallel and non-perpendicular jointed configuration. These unconventional designs of modular configurations seek an easy adaptable solution for both modular assembly and software interfaces for automatic modeling and control. A strategy of assembling the modules, automatic and unified modeling of the modular and reconfigurable manipulators with unconventional parameters is proposed in this paper using the proposed 4 modular units. A reconfigurable software architecture is presented for the automatic generation of kinematic and dynamic models and configuration files, through which, a designer can design, validate using visualization, plan and execute the motion of the developed configuration as required. The framework developed is based upon an open source platform called as Robot Operating System (ROS), which acts as a digital twin for the modular configurations. For the experimental demonstration, a 3D printed modular library is developed and an unconventional configuration is assembled, using the proposed modules followed by automatic modeling and control, for a single cell of the vertical farm setup.

An underlying problem of current interface agent research is the failure to adequately address effective and efficient knowledge representations and associated methodologies suitable for modeling the users' interactions with the system. These user models lack the representational complexity to manage the uncertainty and dynamics involved in predicting user intent and modeling user behavior. A utility theory-based approach is presented for effective user intent prediction by incorporating the ability to explicitly model users' goals, the uncertainty in the users' intent in pursuing these goals, and the dynamics of users' behavior. We present an interface agent architecture, CIaA, that incorporates our approach and discuss the integration of CIaA with three disparate domains — a probabilistic expert system shell, a natural language input database query system, and a virtual space plane —that are being used as test beds for our interface agent research.

In this article, a recurrent neural network (RNN) method is employed for dynamic time-domain modeling of both linear and nonlinear microwave circuits. An automated RNN modeling technique is proposed to efficiently determine the training waveform distribution and internal RNN structure during the offline training process. This technique extends a recent automatic model generation (AMG) algorithm from frequency-domain model generation to dynamic time-domain model generation. Two types of applications of the algorithm are presented, transient electromagnetic (EM) behavior modeling of microwave structures, and time-domain envelope modeling of power amplifiers (PA). For transient EM modeling, we consider EM structures with varying material and geometrical parameters. AMG automatically varies the EM structural parameters during training and drives time-domain EM simulators to generate necessary amount of data for RNN to learn. AMG aims to model the transient behavior with minimum RNN order while satisfying accuracy requirements. In modeling PA behavior, an envelope formulation is used to specifically learn the AM/AM and AM/PM distortions due to third-generation (3G) digital modulation input. The RNN PA model is able to model these time domain distortions after training and can accurately model the amplifier behavior in both time (AM/AM, AM/PM) and frequency (spectral re-growth). © 2008 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2008.

The main purpose of the research was to discover an easy fast and reliable way to generate simulation models and to create a model library. To solve this problem, the automatic element routine generation system (AERO) has been developed as an efficient way for automatic model development using domain specific automatic programming techniques. Behavioural and structural models are generated from Boolean equations, truth tables, HDL descriptions, schematic diagrams or incomplete specifications. By utilising this approach, simulation automation can be achieved by providing the same environment for model generation and simulation. Results show that the system could greatly reduce the cost of simulation model generation for CAD systems and consequently reduce the design cycle considerably.

3D building models are important in several fields, such as urban planning and roof report for insurance industries. However, enormous time and labor has to be consumed to create these 3D models, using a 3D modeling software such as 3ds Max or SketchUp. In order to automate laborious steps, a GIS and CG integrated system is proposed for automatically generating 3D building models, based on building polygons (building footprints) on digital maps. Digital maps show most building polygons' edges meet at right angles (orthogonal polygon). In the digital map, however, not all building polygons are orthogonal. In either orthogonal or non-orthogonal polygons, the new system is proposed for automatically generating 3D building models with general shaped roofs by straight skeleton computation. In this paper, the algorithm for shrinking a polygon and forming a straight skeleton are clarified and, the new methodology is proposed for constructing roof models by assuming ‘the third event’ and, at the end of the shrinking process, the shrinking polygon is converged to ‘a line of convergence’. In our research, extended straight skeleton computation is used for automatic generation of roof models. Based on the monotone polygons which straight skeleton computation forms, roof boards are automatically generated, and a top view of these roof boards can be a roof report for natural disaster damage.

The authors examine domain modeling approaches from the viewpoint of their operational goals. Domain models are representations of an application domain that can be used for a variety of operational goals in support of specific software engineering tasks or processes. Some of the operational goals of domain modeling for software engineering are illustrated. A workshop on domain modeling was organized around operational goals and their resultant domain models and modeling methodologies. The workshop verified the importance of generalized meta-models and their use in instantiating domain knowledge into application domain models. Representation, domain classification and analysis, model development, instantiation evolution and validation, and knowledge structuring and inference are discussed. >

In this paper we propose an approach for automatically building real-time emulations of large scale cyber-physical energy systems. An end-to-end methodology is presented, starting from the system description, continuing with automatic model and interface generation, and finally completing with deployment and real-time execution. The intended target use of the proposed solution is the validation of massively distributed smart-grid software applications. The goal is to provide an automated testing framework that can be integrated in modern software development tool-chains. In this manner, complex software ecosystems that act on critical infrastructure can be exhaustively evaluated and validated before being deployed in the field. <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A prototypical implementation is also presented. This relies on a commercially available real-time simulator whose digital interfacing capabilities were extended in order to meet our automation requirements. As a showcase we consider the problem of generator dispatch using a distributed optimal power flow algorithm. For this example application we consider two test scenarios: one consisting of a smaller network where 13 software agents are deployed, and a larger one involving 123 software agents. Using the proposed framework, scaling the test setup is automated, considerably reducing the required time and errors that typically appear during this process.

Applications of GIFTS III to structural engineering problems

We describe a general approach to automatic model generation in the description of dynamic regulatory networks.

The generation of subject-specific finite element models of the spine is generally a time-consuming process based on computed tomography (CT) images, where scanning exposes subjects to harmful radiation. In this study, a method is presented for the automatic generation of spine finite element models using images from a single magnetic resonance (MR) sequence. The thoracic and lumbar spine of eight adult volunteers was imaged using a 3D multi-echo-gradient-echo sagittal MR sequence. A deep-learning method was used to generate synthetic CT images from the MR images. A pre-trained deep-learning network was used for the automatic segmentation of vertebrae from the synthetic CT images. Another deep-learning network was trained for the automatic segmentation of intervertebral discs from the MR images. The automatic segmentations were validated against manual segmentations for two subjects, one with scoliosis, and another with a spine implant. A template mesh of the spine was registered to the segmentations in three steps using a Bayesian coherent point drift algorithm. First, rigid registration was applied on the complete spine. Second, non-rigid registration was used for the individual discs and vertebrae. Third, the complete spine was non-rigidly registered to the individually registered discs and vertebrae. Comparison of the automatic and manual segmentations led to dice-scores of 0.93–0.96 for all vertebrae and discs. The lowest dice-score was in the disc at the height of the implant where artifacts led to under-segmentation. The mean distance between the morphed meshes and the segmentations was below 1 mm. In conclusion, the presented method can be used to automatically generate accurate subject-specific spine models.

Automatic orientation and 3D modelling from markerless rock art imagery