Model-based System Research Articles

A Trustworthy and Explainable Framework for Benchmarking Hybrid Deep Learning Models Based on Chest X-Ray Analysis in CAD Systems

Evaluating the trustworthiness of deep learning-based computer-aided diagnosis (CAD) systems is challenging. There is a need to optimize trust and performance in model selection. A wide range of models based on evaluation metrics can make it challenging to choose the best one, especially for complex multi-criteria decision-making problems. In the case of COVID-19 diagnosis, using both physicians’ evaluation and AI techniques to establish trust is essential. In this study, 1551 chest X-rays were analyzed using deep transfer learning (DTL) with six models and four SVM kernels. This resulted in 24 hybrid DTL–SVM models. Seven metrics were evaluated using fuzzy multiple-criteria decision-making (MCDM), which uses a dynamic decision matrix to select the best model. This matrix incorporates fuzzy-weighted zero-inconsistency (FWZIC) for weight coefficients and Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) for benchmarking. The Grad-CAM technique compared the best model with 16 images, ensuring explainability. Top-performing models were identified, including SqueezeNet-SVM linear, VGG19-SVM linear, and VGG19-SVM. Sensitivity analysis was used to quantify the impact of changing weighted criteria values. A physician expert validated fuzzy MCDM through Grad-CAM analysis, a new aspect of this study. The framework presented in this study was benchmarked against seven other studies and achieved a perfect score in four crucial areas. Trustworthiness is essential for CAD systems, and this study effectively addresses trust and performance challenges in AI model-based CAD systems. The study systematically evaluated the requirements for trustworthiness, including accountability, fairness, robustness, accuracy, and reproducibility, and the results supported this.

A semantic model-based systems engineering approach for assessing the operational performance of metal forming process

Metal Forming is a basic and essential industrial process to provide materials for constructing complex products. To design an efficient metal forming process, the functional requirements and operational performance are two important aspects to be considered. In this paper, a semantic Model-based Systems Engineering (sMBSE) approach is proposed to support the design of the entire metal forming process. A multi-architecture modeling language KARMA is used to develop meta-models and architecture models of the metal forming process from the perspectives of mission, operation, function, logic flow and physical structure. Enabled by customized software, the KARMA models are transformed to ontology models, which are then converted to Petri Net (PN) models. Simulations are conducted based on the PN models to evaluate the operational performance of the created processes. A case study based on a real metal forming scenario is conducted to evaluate the proposed approach using quantitative and qualitative analysis. The result proves that the proposed approach enables to formalize the entire architecture modeling for metal forming process; and to provide an efficient approach for evaluating the operational performance of the designed solution for initial verification.

Low Temperature Combustion Modeling and Predictive Control of Marine Engines

The increase of popularity of reactivity-controlled compression ignition (RCCI) is attributed to its capability of achieving ultra-low nitrogen oxides (NOx) and soot emissions with high brake thermal efficiency (BTE). The complex and nonlinear nature of the RCCI combustion makes it challenging for model-based control design. In this work, a model-based control system is developed to control the combustion phasing and the indicated mean effective pressure (IMEP) of RCCI combustion through the adjustments of total fuel energy and blend ratio (BR) in fuel injection. A physics-based nonlinear control-oriented model (COM) is developed to predict the main combustion performance indicators of an RCCI marine engine. The model is validated against a detailed thermo-kinetic multizone model. A novel linear parameter-varying (LPV) model coupled with a model predictive controller (MPC) is utilized to control the aforementioned parameters of the developed COM. The developed system is able to control combustion phasing and IMEP with a tracking error that is within a 5% error margin for nominal and transient engine operating conditions. The developed control system promotes the adoption of RCCI combustion in commercial marine engines.

Accelerating the Homologation of Software Updates with Model-based Systems Engineering

Accelerating the Homologation of Software Updates with Model-based Systems Engineering

ExKidneyBERT: a language model for kidney transplant pathology reports and the crucial role of extended vocabularies.

Pathology reports contain key information about the patient's diagnosis as well as important gross and microscopic findings. These information-rich clinical reports offer an invaluable resource for clinical studies, but data extraction and analysis from such unstructured texts is often manual and tedious. While neural information retrieval systems (typically implemented as deep learning methods for natural language processing) are automatic and flexible, they typically require a large domain-specific text corpus for training, making them infeasible for many medical subdomains. Thus, an automated data extraction method for pathology reports that does not require a large training corpus would be of significant value and utility. To develop a language model-based neural information retrieval system that can be trained on small datasets and validate it by training it on renal transplant-pathology reports to extract relevant information for two predefined questions: (1) "What kind of rejection does the patient show?"; (2) "What is the grade of interstitial fibrosis and tubular atrophy (IFTA)?" Kidney BERT was developed by pre-training Clinical BERT on 3.4K renal transplant pathology reports and 1.5M words. Then, exKidneyBERT was developed by extending Clinical BERT's tokenizer with six technical keywords and repeating the pre-training procedure. This extended the model's vocabulary. All three models were fine-tuned with information retrieval heads. The model with extended vocabulary, exKidneyBERT, outperformed Clinical BERT and Kidney BERT in both questions. For rejection, exKidneyBERT achieved an 83.3% overlap ratio for antibody-mediated rejection (ABMR) and 79.2% for T-cell mediated rejection (TCMR). For IFTA, exKidneyBERT had a 95.8% exact match rate. ExKidneyBERT is a high-performing model for extracting information from renal pathology reports. Additional pre-training of BERT language models on specialized small domains does not necessarily improve performance. Extending the BERT tokenizer's vocabulary library is essential for specialized domains to improve performance, especially when pre-training on small corpora.

Model-based Decision Support System Using a System Dynamics Approach to Increase Corn Productivity

Background: As the population increases, the need for corn products also increases. Corn is needed for various purposes, such as food consumption, industry, and animal feed. Therefore, increasing corn production is crucial to support food availability and the food industry. Objective: The objective of this project is to create a model to increase corn farming productivity using scenarios from drip irrigation systems and farmer field school programs. Methods: A system dynamics approach is utilized to model the complexity and nonlinear behaviour of the corn farming system. In addition, several scenarios are formulated to achieve the objective of increasing corn productivity. Results: Simulation results showed that adopting a drip irrigation system and operating a farmer field school program would increase corn productivity. Conclusion: The corn farming system model was successfully developed in this research. The scenario of implementing a drip irrigation system and the farmer field school program allowed farmers to increase corn productivity. Through the scenario of implementing a drip irrigation system, farmers can save water use, thereby reducing the impact of drought. Meanwhile, the scenario of the farmer field school program enables farmers to manage agriculture effectively. This study suggests that further research could consider the byproducts of corn production to increase the profits of corn farmers. Keywords: Corn Farming, Decision Support System, Modeling, Simulation, System Dynamics

Examining the intersection of ontology, model-based system engineering, and user interface development: the future of design?

Examining the intersection of ontology, model-based system engineering, and user interface development: the future of design?

Стратегирование координации организаций строительного комплекса стран БРИКС в условиях экономики данных

In 2024, Russia chairs the BRICS, having defined its global strategy as “strengthening multilateralism for equitable global development and security”. According to the methodology developed by Prof. V.L. Kvint, the global strategy depends on the relevant international, national, and corporate strategies of companies from the BRICS countries. Data economy uses algorithms for data processing and analysis, including AI solutions. Prof. V.L. Kvint defines the strategy as a combination of wisdom, a correct attack vector, and an adequate assessment of resources. Prof. A.A. Romanov and Prof. V.V. Kondratiev used Model-Based Systems Engineering 2.0 to adapt Prof. L.A. Bakhvalov’s methodology of system modeling to the modern conditions. All these principles can yield a new approach to multi-criteria modeling of related cross-country and cross-industry corporate strategies, especially if facilitated by the digital twin method and the interoperability policy. The major construction industry is high on the BRICS agenda in terms of large infrastructure and industrial facilities. Therefore, Model-Based Systems Engineering 2.0 provides good prospects for development strategy modeling.

From Data to Draught: Modelling and Predicting Mixed-Culture Beer Fermentation Dynamics Using Autoregressive Recurrent Neural Networks

The ascendency of the craft beer movement within the brewing industry may be attributed to its commitment to unique flavours and innovative styles. Mixed-culture fermentation, celebrated for its novel organoleptic profiles, presents a modelling challenge due to its complex microbial dynamics. This study addresses the inherent complexity of modelling mixed-culture beer fermentation while acknowledging the condition monitoring limitations of craft breweries, namely sporadic offline sampling rates and limited available measurement parameters. A data-driven solution is proposed, utilising an Autoregressive Recurrent Neural Network (AR-RNN) to facilitate the production of novel, replicable, mixed-culture fermented beers. This research identifies time from pitch, specific gravity, pH, and fluid temperature as pivotal model parameters that are cost-effective for craft breweries to monitor offline. Notably, the autoregressive RNN fermentation model is generated using high-frequency multivariate data, a departure from intermittent offline measurements. Employing the trained autoregressive RNN framework, we demonstrate its robust forecasting prowess using limited offline input data, emphasising its ability to capture intricate fermentation dynamics. This data-driven approach offers significant advantages, showcasing the model’s accuracy across various fermentation configurations. Moreover, tailoring the design to the craft beer market’s unique demands significantly enhances the model’s practicable predictive capabilities. It empowers nuanced decision-making in real-world mixed-culture beer production. Furthermore, this model lays the groundwork for future studies, highlighting transformative possibilities for cost-effective model-based control systems in the craft beer sector.

Seamless Function-Oriented Mechanical System Architectures and Models

One major challenge of today’s product development is to master the constantly increasing product complexity driven by the interactions between different disciplines, like mechanical, electrical and software engineering. An approach to master this complexity is function-oriented model-based systems engineering (MBSE). In order to guide the developer through the process of transferring requirements into a final product design, MBSE methods are essential. However, especially in mechanics, function-oriented product development is challenging, as functionality is largely determined by the physical effects that occur in the contacts of physical components. Currently, function-oriented MBSE methods enable either the modeling of contacts or of structures as part of physical components. To create seamless function-oriented mechanical system architectures, a holistic method for modeling contacts, structures and their dependencies is needed. Therefore, this paper presents an extension of the motego method to model structures, by which the seamless parametric modeling of function-oriented mechanical system architectures from requirements to the physical product is enabled.

Mission-Oriented Electrified Aircraft Propulsion System Design and Verification Using Model-Based Systems Engineering

Abstract The concept of electrified aircraft propulsion (EAP) has garnered substantial attention and investigation due to its potential for mitigating fuel consumption, emissions, and noise. Present studies mainly concentrate on point design rather than systematic design space exploration. This paper considers the attainment of prescribed mission objectives as a paramount evaluation criterion and proposed a mission-oriented design and verification method based on model-based systems engineering (MBSE). Instead of using a general modeling language, this method develops a domain-specific metamodel library for EAP based on six meta-metamodels. A Mission-Operational-Functional-Logical-Physical (MOFLP) modeling methodology is provided to standardize EAP design process. Furthermore, the modeling process is integrated with the verification process by executable verification script. A case study about skydiving mission is conducted to verify the effectiveness of this method. The case results corroborate the utility of this method in the generation of an initial EAP solution. Such initial solution can serve as a fundamental benchmark for iterative design.

Application of Harmony SE in civil aircraft design

With the refinement of civil aircraft technology and the enhancement of product complexity, civil aircraft design has changed from traditional text-based system engineering to model-based system engineering, the expression of the system has also transformed from text-centered to model-centered. To further improve the model quality and correctness of aircraft system modeling, this paper explores the applicability of model-driven and verification-oriented system engineering methods in the field of civil aircraft design, and establishes the system engineering practice framework of civil aircraft design, which can ensure the rapid design and efficient delivery of civil aircraft. Firstly, starting from the Harmony SE modeling method, the workflow and modeling ideas of system are introduced; then the noticeable problems in the practice of civil aircraft system engineering are analyzed, and the system engineering practice of civil aircraft design is established with the support of the applicability of the Harmony SE method; finally, the fuel tank pressurization component is taken as the research object of the practice system in component-level. The results show that the system engineering practice framework of civil aircraft design and method proposed in this paper can correctly and reasonably allocate design requirements and establish a complete system model, which is helpful to improve the efficiency and accuracy of civil aircraft design at this stage.

Overview of Identified Challenges in the Development Process of Superconducting Accelerator Magnets

Development challenges in the domain of superconducting magnets are concentrated on technical problems in the current literature. Organizational, domain-specific challenges are often seen as secondary but must be considered with new holistic development approaches like Model-Based Systems Engineering (MBSE) becoming more popular. This work quantifies the domain challenges and gives the foundation to derive success criteria for design support in the future. A systematic literature review has been conducted to identify the overall domain challenges, and extensive interviews in the CERN technology department have been carried out to identify the development challenges on a practical level. Problems in knowledge management have been identified as a major challenge in the development process and the general literature. The paper concludes by picking up the most important challenges from the interviews and literature and puts them into the context of the authors’ knowledge of electrical magnet design.

Realization of digital twin for dynamic control towardsample variation of ion exchange chromatography in antibody separation.

Digital twin (DT) is a virtual and digital representation of physical objects or processes. In this paper, this concept is applied to dynamic control of the collection window in the ion exchange chromatography (IEC) towardsample variations. A possible structure of a feedforward model-based control DT system was proposed. Initially, a precise IEC mechanistic model was established through experiments, model fitting, and validation. The average root mean square error (RMSE) of fitting and validation was 8.1% and 7.4%, respectively. Then a model-based gradient optimization was performed, resulting in a 70.0% yield with a remarkable 11.2% increase. Subsequently, the DT was established by systematically integrating the model, chromatography system, online high-performance liquid chromatography, and a server computer. The DT was validated under varying load conditions. The results demonstrated that the DT could offer an accurate control with acidic variants proportion and yield difference of less than 2% compared to the offline analysis. The embedding mechanistic model also showed a positive predictive performance with an average RMSE of 11.7% during theDT test under >10% sample variation. Practical scenario tests indicated that tightening the control target could further enhance the DT robustness, achieving over 98% success rate with an average yield of 72.7%. The results demonstrated that the constructed DT could accurately mimic real-world situations and perform an automated and flexible pooling in IEC. Additionally, a detailed methodology for applying DT was summarized.

The Effects of Parameter Settings on Triggering Time and Climb Rate during Lean-Premixed Combustion Thermoacoustic Oscillations

This study theoretically explored the effects of parameter settings on thermoacoustic oscillations with a low-order model. Three factors were explored—combustor length, inlet gas temperature and thermal power. The research findings indicate that optimizing the parameter settings can yield better thermoacoustic oscillation suppression results. The sound pressure amplitude decreased from 3.2 × 105 Pa to 2.1 × 105 Pa as the combustor length increased from 1.2 m to 6.0 m. The triggering time increased from 0.32 s to 0.91 s when the combustion chamber length increased. The climb rate declined from 23.38 × 105 Pa/s to 3.75 × 105 Pa/s when the combustor length was elongated. The sound pressure amplitude decreased from 3.44 × 105 Pa to 2.4 × 105 Pa as the gas temperature rose from 0 to 100 °C. The triggering time and climb rate variation tendency were similar when the gas temperature increased—both declined as the gas temperature rose. The sound pressure amplitude experienced a slight fluctuation when the thermal power rose. However, the triggering time decreased from 0.26 s to 0.043 s when the thermal power improved. The climb rate increased from 18.72 × 105 Pa/s to 27.65 × 105 Pa/s when the thermal power rose. The oscillation frequency presented was completely different in three cases that had different wavelengths and oscillation intensities. The triggering time and climb rate fluctuated extensively in varying conditions, and the above two factors were interrelated and contradictory to each other when thermoacoustic oscillation was excited. This study explored parameters’ effects on triggering time and climb rate, thereby providing references for constructing a model-based control system for thermoacoustic oscillation feedback control.

A personalized prediction model for urinary tract infections in type 2 diabetes mellitus using machine learning.

Patients with type 2 diabetes mellitus (T2DM) are at higher risk for urinary tract infections (UTIs), which greatly impacts their quality of life. Developing a risk prediction model to identify high-risk patients for UTIs in those with T2DM and assisting clinical decision-making can help reduce the incidence of UTIs in T2DM patients. To construct the predictive model, potential relevant variables were first selected from the reference literature, and then data was extracted from the Hospital Information System (HIS) of the Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital for analysis. The data set was split into a training set and a test set in an 8:2 ratio. To handle the data and establish risk warning models, four imputation methods, four balancing methods, three feature screening methods, and eighteen machine learning algorithms were employed. A 10-fold cross-validation technique was applied to internally validate the training set, while the bootstrap method was used for external validation in the test set. The area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to evaluate the performance of the models. The contributions of features were interpreted using the SHapley Additive ExPlanation (SHAP) approach. And a web-based prediction platform for UTIs in T2DM was constructed by Flask framework. Finally, 106 variables were identified for analysis from a total of 119 literature sources, and 1340 patients were included in the study. After comprehensive data preprocessing, a total of 48 datasets were generated, and 864 risk warning models were constructed based on various balancing methods, feature selection techniques, and a range of machine learning algorithms. The receiver operating characteristic (ROC) curves were used to assess the performances of these models, and the best model achieved an impressive AUC of 0.9789 upon external validation. Notably, the most critical factors contributing to UTIs in T2DM patients were found to be UTIs-related inflammatory markers, medication use, mainly SGLT2 inhibitors, severity of comorbidities, blood routine indicators, as well as other factors such as length of hospital stay and estimated glomerular filtration rate (eGFR). Furthermore, the SHAP method was utilized to interpret the contribution of each feature to the model. And based on the optimal predictive model a user-friendly prediction platform for UTIs in T2DM was built to assist clinicians in making clinical decisions. The machine learning model-based prediction system developed in this study exhibited favorable predictive ability and promising clinical utility. The web-based prediction platform, combined with the professional judgment of clinicians, can assist to make better clinical decisions.

Co-Design and Energy Management for Future Vessels

The maritime industry is undergoing a significant shift towards more sustainable and efficient forms of transportation. As a result, designing Power, Propulsion and Energy (PPE) Systems for future vessels presents new challenges that require a systematic approach that reduces the risk in development and implementation. This paper focuses on three aspects of such a systematic approach: Model-Based System Engineering (MBSE), Co-design, and Verification and Validation. The MBSE approach can be used to mitigate the risks associated with the transition by maintaining a clear traceability of user needs, functional requirements and physical realizations. A rigorous needs analysis and functional design reduces the optimisation design space that results in a significant reduction in the complexity of a design optimisation problem. Further, co-design is discussed as a methodology for a combined optimisation of the hardware and software design where the Modular Energy Management approach supports automated controller generation for the optimisation, a key challenge when optimising PPE systems. An important aspect of the MBSE approach is the use of models for the verification and validation of the developed designs. However, the successful use of models is contingent on their applicability. This paper proposes a way to categorise model confidence for verification and validation studies.

Digital Twin Technologies for Autonomous Environmental Control and Life Support Systems

Environmental control and life support systems will require enhanced self-awareness and self-sufficiency as human spaceflights are designed to reach further destinations. These requirements have led to the development of autonomous technologies and systems to enable more Earth independence, while at the same time relying more heavily on the knowledge contained in their computational models (as opposed to the knowledge of ground control experts). For environmental control and life support systems, these consist of disparate models often tailored to specific subsystems and use cases, such as temperature control and CO2 removal. Therefore, there is a need for technologies supporting the integration of existing models. We propose to extend existing digital twin frameworks to integrate models and serve as a tool for answering onboard queries during operation. Toward this vision, we identify research directions for three types of technologies: i) streamlining the process of merging information models without redundancies by leveraging model-based systems engineering languages; ii) the calibration of simulation models that requires a better understanding of how to encode domain knowledge into a probabilistic representation of subsystem states and model parameters; and iii) automating the query understanding process and constructing a mapping between information and simulation models.

Analysis of research into the mathematical foundations of model-based systems engineering

The article provides an analysis of research into the mathematical foundations of model-based systems engineering (MBSE, Model-Based Systems Engineering). Both the classical mathematical theory of Wymore’s system design and modern research are considered, in particular, the formalization of the semantics of the SysML language using automata theory, the use of category theory as a formal mathematical basis for model-based system design, the study of the possibilities of combining the theoretical basis of Wymore’s systems and the universal Discrete Event System Specification (DEVS) modeling formalism.

An Adaptive Hammerstein Model for FES-Induced Torque Prediction Based on Variable Forgetting Factor Recursive Least Squares Algorithm.

Modeling the muscle response to functional electrical stimulation (FES) is an important step during model-based FES control system design. The Hammerstein structure is widely used in simulating this nonlinear biomechanical response. However, a fixed relationship cannot cope well with the time-varying property of muscles and muscle fatigue. In this paper, we proposed an adaptive Hammerstein model to predict ankle joint torque induced by electrical stimulation, which used variable forgetting factor recursive least squares (VFFRLS) method to update the model parameters. To validate the proposed model, ten healthy individuals were recruited for short-duration FES experiments, ten for long-duration FES experiments, and three stroke patients for both. The isometric ankle dorsiflexion torque induced by FES was measured, and then the test performance of the fixed-parameter Hammerstein model, the adaptive Hammerstein model based on fixed forgetting factor recursive least squares (FFFRLS) and the adaptive Hammerstein model based on VFFRLS was compared. The goodness of fit, root mean square error, peak error and success rate were applied to evaluate the accuracy and stability of the model. The results indicate a significant improvement in both the accuracy and stability of the proposed adaptive model compared to the fixed-parameter model and the adaptive model based on FFFRLS. The proposed adaptive model enhances the ability of the model to cope with muscle changes.