Assessment of tunnelling-induced building damage is a complex Soil-Structure Interaction (SSI) probelm, influenced by numerous geometric and material parameters of both the soil and structures, and ...is characterised by strong non-linear behaviour. Currently, there is a trend towards developing data-driven models using Machine Learning (ML) to capture this complex behaviour. Given the scarcity of real data, which typically comes from specific case studies, many researchers have turned to creating extensive synthetic datasets via sophisticated and validated numerical models like Finite Element Method (FEM). However, the development of these datasets and the training of advanced ML algorithms present significant challenges. poses significant challenges. Reliance solely on parameter domains and ranges derived from case studies can lead to imbalanced data distributions and subsequently poor performance of models in less populated regions. In this paper, we introduce a strategy for designing optimal high-confidence datasets through an iterative procedure. This process begins with a systematic literature review to determine the importance of parameters, their ranges, and dependencies as they pertain to building damage induced by SSI. Starting with several hundred FEM simulations, we generate an initial dataset and assess its quality and impact through Sensitivity Analysis (SA) studies, statistical modelling, and re-sampling in statistically significant regions. This evaluation allows us to refine the model’s input space, seeking scenarios that mitigate output distribution imbalances. The procedure is repeated until the datasets achieve a satisfactory balance for training metamodels, minimising bias effectively. Our findings highlight the success of this approach in identifying an optimal and feasible input space that significantly reduces imbalanced distributions of output features. This approach not only proves effective in our study but also offers a versatile methodology that could be adapted to other disciplines aiming to generate high-quality synthetic datasets.
•Systematic analysis of parameters affecting tunnelling-induced building damage.•Novel iterative sampling approach for the generation of feasible and optimal datasets.•A fully automated procedure for the creation of high-fidelity FEM models.•Improvements in ML training and predictions for highly non-linear problems.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
: The aim of this paper is to present the influence of Industry 4.0 on the development of the new simulation modelling paradigm, embodied by the Digital Twin concept, and examine the adoption of the ...new paradigm via a multiple case study involving real-life R&D cases involving academia and industry.
: We introduce the Industry 4.0 paradigm, presents its background, current state of development and its influence on the development of the simulation modelling paradigm. Further, we present the multiple case study methodology and examine several research and development projects involving automated industrial process modelling, presented in recent scientific publications and conclude with lessons learned.
We present the research problems and main results from five individual cases of adoption of the new simulation modelling paradigm. Main lesson learned is that while the new simulation modelling paradigm is being adopted by big companies and SMEs, there are significant differences depending on company size in problems that they face, and the methodologies and technologies they use to overcome the issues.
While the examined cases indicate the acceptance of the new simulation modelling paradigm in the industrial and scientific communities, its adoption in academic environment requires close cooperation with industry partners and diversification of knowledge of researchers in order to build integrated, multi-level models of cyber-physical systems. As shown by the presented cases, lack of tools is not a problem, as the current generation of general purpose simulation modelling tools offers adequate integration options.
Full text
Available for:
CEKLJ, NUK, ODKLJ, UL, UM, UPUK
Accurate as-built information is required to operate, maintain, and adapt existing buildings. Scan-to-BIM has become a feasible approach for collecting and modelling 3D as-built information and has ...three phases: (1) scanning, (2) registration, and (3) modelling. This paper focuses on the modelling phase, which can currently be conducted either manually or semi-automatically. As-built conditions of a building are surveyed, and the geometry is modeled in a series of modelling scenarios. For each trial, geometric dimensions of the BIMs are compared to ground truth dimensions. This paper assesses the impact of levels of automation and modeller training on the accuracy and precision of generated BIMs. Quantitative models are developed for modelling scenarios using empirical datasets. Lastly, the impacts of degrees of accuracy are discussed. This study provides insight into the dimensional certainty of BIMs generated by Scan-to-BIM and helps decision-makers assess the risk of decisions made based on this information.
•Accuracy and precision of scan-to-BIM is investigated for manual vs. automated techniques•Quantitative models are used to estimate the level of dimensional certainty for generated BIMs•Modeller training (i.e., standardizing the modelling approach) can improve accuracy by up to 260%•Primary building objects (e.g., walls) can yield larger errors in scan-to-BIM than for secondary objects (e.g., pipes)•The industry needs a unified system for certifying the level of accuracy in scan-to-BIM
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Port-Hamiltonian system theory is a well-known framework for the control of complex physical systems. The majority of port-Hamiltonian control design methods base on an explicit input-state-output ...port-Hamiltonian model for the system under consideration. However in the literature, little effort has been made towards a systematic, automatable derivation of such explicit models. In this paper, we present a constructive, formally rigorous method for an explicit port-Hamiltonian formulation of multi-bond graphs. Two conditions, one necessary and one sufficient, for the existence of an explicit port-Hamiltonian formulation of a multi-bond graph are given. We summarise our approach in an algorithm for the automated generation of an explicit port-Hamiltonian model from a given multi-bond graph. An academic example illustrates the results of this paper.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•Proposing a new identifiable hysteretic model with explicit physical parameters determined by hysteresis loop.•Extracting dynamic features for training SVM model to identify unknown ...parameters.•Combining SHM and SVM to automatically create a nonlinear model for response prediction.•Validating the method against a full scale 3-story real-world building structure with realistic nonlinear seismic response.•Extending SHM from a retrospective monitoring tool to a prospective tool in earthquake response and recovery.
Structural health monitoring (SHM) is backwards analysis of past to current state of damage, but cannot create a structure-specific nonlinear model for forward analysis of future response and damage. This paper aims to develop an automated modelling approach to translate proven hysteresis loop analysis (HLA) SHM results into nonlinear foundation models for response forecasting in subsequent events, particularly for steel structures with post-yielding behaviors. Support vector machine (SVM) is employed to identify the proposed nonlinear baseline model. Stiffness features are extracted from HLA to train the SVM model incorporating the constraints of SHM identification.
A proof-of-concept case study validates the ability of the proposed method to accurately identify 12 model parameters with average error of 2.8% for a nonlinear numerical structure in the presence of 10% RMS measurement noise. Experimental validation from a full-scale 3-storey real building shows the predicted nonlinear responses match the measured response well with cross correlation coefficients Rcoeff = 0.94, 0.92 and 0.89 for the first, second and third floor, respectively. In addition, the predicted stiffness changes also match the SHM results very well with errors less than 2.1%. Finally, and most importantly, the identified model is able to predict the response of 2 further events with average of correlation coefficient Rcoeff = 0.91 and average error of 1.9% for stiffness changes across all cases. The overall results validate the ability of the created predictive model to accurately capture the essential dynamics and structural degradation, as well as predicting future possible response and risk.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Molybdenum oxides and sulfides on various low-cost high-surface-area supports are excellent catalysts for several industrially relevant reactions. The surface layer structure of these materials is, ...however, difficult to characterize due to small and disordered MoO
x
domains. Here, it is shown how X-ray total scattering can be applied to gain insights into the structure through differential pair distribution function (d-PDF) analysis, where the scattering signal from the support material is subtracted to obtain structural information on the supported structure. MoO
x
catalysts supported on alumina nanoparticles and on zeolites are investigated, and it is shown that the structure of the hydrated molybdenum oxide layer is closely related to that of disordered and polydisperse polyoxometalates. By analysing the PDFs with a large number of automatically generated cluster structures, which are constructed in an iterative manner from known polyoxometalate clusters, information is derived on the structural motifs in supported MoO
x
.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Display omitted
•A knowledge library for automated urban runoff modelling was developed.•Three alternative infiltration methods were encoded in the knowledge library.•Process Based Modelling Tool was ...used to find the optimal rainfall-runoff model.•Nine models were automatically generated with very good performance.•Models that used a combination of infiltration methods performed best.
Modelling tools are widely used to analyse the urban drainage systems and to simulate the effects of future urban development and stormwater control measures. Usually, these tools use only one mathematical model (predetermined by the modeller) at a time to describe a single hydrological process within the urban catchment. When there are alternative mathematical models for describing the same hydrological process, their suitability needs to be investigated separately, which makes the modelling task even more complex, time consuming and open for human errors. Furthermore, models have to be calibrated to achieve a better fit between measured and simulated runoff. Calibration can be performed either manually, by using a trial-and-error approach, or by employing search techniques and parameter optimization tools. To overcome the drawbacks associated with manual selection and calibration of models, automated modelling based on equation discovery was used in this study to a) find the most suitable mathematical model among multiple alternatives for describing every (environmental) process modelled and b) to calibrate the model parameters against measured data. First, knowledge on urban runoff modelling was formalized into a new library of modelling components, compliant with the equation discovery tool ProBMoT (Process Based Modelling Tool). Next, a conceptual model of the experimental urban sub-catchment within the city of Ljubljana, Slovenia, was defined. ProBMoT was used to find the structure and parameters’ values of alternative rainfall-runoff models, according to the defined conceptual model that provide optimal fit against pipe flow measurements. Three alternative methods were used to describe infiltration: the SCS CN method, the Variable UK runoff equation, and the UK Water Industry Research equation. The proposed automated model discovery approach for finding the optimal rainfall-runoff model proved to be very efficient. Nine rainfall-runoff models were created with very good performance. The best performance was achieved by the models that used a combination of two different infiltration methods, i.e. the SCS CN infiltration method for the pervious area and one of the other two infiltration methods for the impervious area.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
•In ITER, activated water will generate significant radiation levels during DT pulses.•Currently, this field cannot be reliably modelled due to the cooling system complexity.•Automated geometry ...modelling and activation calculation methods were developed.•The first realistic neutronics model of the activated water source is presented.
During the plasma pulses, the neutron-induced activation of the cooling water will produce an important contribution to the radiation levels in the ITER Tokamak Complex. The resulting radiation field has a complex spatial distribution due to the combination of decay and production of radioisotopes in the intricate cooling lines that feed the numerous systems inside and outside the bio-shield. An accurate estimation of the cooling water radiation field is necessary to ensure that the radiological zoning is respected. As of today, this issue has been studied using simple, manually defined geometries with limited representation of the tens of thousands of components that constitutes the cooling circuits. This work describes the first production of a realistic and up-to-date integral neutronics modelling of all the cooling systems containing activated water beyond the bio-shield. The work was enabled by the development of computerized geometry modelling techniques to automatically simplify and dimension the system components. An independent review of the method ensured the validity of the simplified model. Moreover, automated scripts produced the activated water radiation source associated with the geometry model. The latter was obtained by linking thousands of cylinders, representing the coolant volumes, in chains of MCNP cells that reproduced the paths of the water lines inside the Tokamak Complex and, eventually, by calculating the radioisotopes activity in each cell. This methodology greatly speeds up the modelling time, reduces the risk of human error and enables the representation of the Tokamak Cooling Water System radiation source with an unprecedented degree of realism.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Molybdenum oxides and sulfides on various low‐cost high‐surface‐area supports are excellent catalysts for several industrially relevant reactions. The surface layer structure of these materials is, ...however, difficult to characterize due to small and disordered MoOx domains. Here, it is shown how X‐ray total scattering can be applied to gain insights into the structure through differential pair distribution function (d‐PDF) analysis, where the scattering signal from the support material is subtracted to obtain structural information on the supported structure. MoOx catalysts supported on alumina nanoparticles and on zeolites are investigated, and it is shown that the structure of the hydrated molybdenum oxide layer is closely related to that of disordered and polydisperse polyoxometalates. By analysing the PDFs with a large number of automatically generated cluster structures, which are constructed in an iterative manner from known polyoxometalate clusters, information is derived on the structural motifs in supported MoOx.
Using pair distribution function analysis, the structure of amorphous supported molybdenum oxides is characterized using a new automated data modelling approach.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
•Global manufacturing companies experience process and data heterogeneity problems.•These problems hinder companies from improving their production processes.•The new Automated modelling with ...abstraction for EA (AMA4EA) method creates EA models.•AMA4EA models compare heterogeneous process and data from different production sites.•AMA4EA is key for understanding and improving heterogeneous production processes.
The heterogeneity of production processes is a serious problem faced by international manufacturing companies. The transformation towards Industry 4.0 and the adoption of Internet-of-Things (IoT) have produced huge amounts of heterogeneous data. The production processes and data from sites across the world cannot be shared and compared at the enterprise level. Therefore, companies cannot improve their production processes and the current state-of-the-art of enterprise architecture (EA) cannot address this heterogeneity problem. To mitigate and address this heterogeneity problem, we extend the automated modelling with abstraction for EA (AMA4EA). We demonstrate the extension using the processes and data of an international manufacturing company in Denmark. The results show that the extended AMA4EA addresses the process heterogeneity problem by automatically creating EA models that relate and compare production processes from different sites. In addition, the extended AMA4EA extracts value from heterogeneous data and visualizes them in EA models. The extended AMA4EA exhibits a novel method in EA to incorporate process and data heterogeneity. This is a significant advance to EA research because it supports EA in modelling the different realities of companies. In addition, the extended AMA4EA demonstrates how production managers can jointly analyse production processes from different sites. As a result, managers can identify potential opportunities for improvement across production sites. Through EA models, they can access data and documentation stored on different enterprise systems. These contributions pave the foundation for understanding and improving the performance of heterogeneous production processes for international manufacturing companies.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP