The early stages of structural design increasingly make use of computational tools that support rapid exploration, performance-informed decision-making, and closer interaction between design and engineering. This systematic mapping study examines how Algorithm-Aided Design (AAD) and the Finite Element Method (FEM) are applied and combined in conceptual design workflows. Based on a structured search across three academic databases and a coding scheme applied to 87 publications, the literature is mapped according to algorithmic strategies, FEM applications, element types, disciplinary domains, and levels of integration. The results show that algorithmic and predictive approaches are reported with increasing frequency after 2020, alongside growing use of surrogate models and optimisation routines. Linear-elastic analyses and shell- or beam-based models are frequently reported, particularly in civil engineering contexts, while nonlinear, dynamic, and solid-element analyses appear more prominently in mechanical domains. More tightly coupled AAD–FEM workflows become increasingly visible after 2021, reflecting a growing interest in real-time or near-real-time simulation feedback during early design exploration. At the same time, the literature highlights persistent challenges related to computational cost, fragmented toolchains, limited interoperability, and the relatively limited use of multiscale or advanced material models in conceptual design. Taken together, the findings suggest that continued progress toward more integrated AAD–FEM workflows is closely tied to advances in computational efficiency, improved data exchange and interoperability, and the development of more accessible design–analysis environments across disciplinary boundaries.

This study systematically maps how artificial intelligence (AI) has been applied within finite-element (FE)-based structural engineering. A corpus of 5995 unique English-language publications was compiled and classified by discipline, with 3345 relevant papers further categorized by application group. A representative subset of 372 studies underwent detailed full-text classification across seven analytical dimensions covering AI methods, element formulations, materials, and structural objects. The analysis reveals rapid growth after 2015, including a pronounced expansion of surrogate modeling and data-driven prediction methods. The disciplinary composition of the literature has also evolved, with structural engineering studies becoming more prominent in recent years relative to earlier decades. Optimization & Design remains the largest application area across the full dataset, while Structural Performance Prediction and FEM Acceleration/Surrogate Modeling show the fastest growth, reflecting increasing emphasis on predictive, solver-efficient, and hybrid physics–data approaches. These findings indicate a maturing field in which AI is increasingly embedded across all stages of FE-based analysis and design. This study provides a structured overview of methodological patterns, identifies emerging hybrid strategies, and highlights opportunities for future research and industrial integration.

This paper presents a data set from an extensive experimental benchmark study of a steel bridge subject to imposed damage. The data set includes organized dynamic response and load measurement data of the bridge under different structural state conditions, where the structural state conditions range from an undamaged (reference) state to known damage states. Furthermore, the data set includes acceleration and strain data from the response monitoring and acceleration data from the load monitoring, where a modal vibration shaker is used as an excitation source. A validation of the data is provided. The data set is published in an open-access data repository that can be accessed and downloaded freely. As such, the data set provides an important benchmark to the scientific community within bridge damage detection, structural health monitoring (SHM), and population-based SHM.

More than half of the 900 steel railway bridges in Norway have exceeded their design service life. The design of these bridges did not account for modern axle loads and train speeds, nor fatigue limit states. Replacing every bridge that has exceeded its design service life, however, would not be feasible, and many of these bridges are still structurally sound. To calculate the remaining service life of bridges, finite-element models have been established. The accuracy of a remaining service life calculation is dependent on the accuracy of the model. In this case, a model of Lundamo railway bridge, a steel open-deck truss bridge, was developed, and its accuracy tested. To this end, strain gauges were affixed to the structural components of the bridge. Strain measurements from train passages over the bridge were collected via these gauges, and the results were compared to the model-predicted values to determine the error in the model.

This contribution presents the open-access sharing of comprehensive data sets derived from bridge monitoring projects in Norway. Through these open-access repository initiatives, we aim to encourage collaborative efforts among researchers and provide a verification basis for techniques in experimental or operational modal analysis, structural health monitoring, damage detection, model updating, virtual sensing, machine learning approaches, and other data-driven approaches in structural dynamics. The data sets featured in this open access initiative include long-span bridges in operation on the road network, focusing on dynamic responses to environmental loading (wind/waves) and monitoring of ageing steel railway bridges, where fatigue damage is a concern. The repositories contain time series for acceleration and strain responses, temperatures, wind velocities, and wave elevations. A central aspect of our exposition is the welldocumented detailing of the data, tests, sensor locations and specifications, units, reference systems, and other metadata information.

An accurate method is needed to estimate the lateral loads acting externally on road vehicles such that transient aerodynamic loads and driver response can be studied in-situ. The aim this work is to develop a Kalman filter that can be practically applied to estimate external lateral loads using measurements from sensors that are commonly installed by manufacturers on modern road vehicles. An appraisal of the accuracy of the estimates-and the estimate uncertainties-is presented using real-world experiments performed with a test vehicle in presence of crosswinds. A network of surface pressure taps was installed on the vehicle body to provide a reference estimation of the aerodynamic loads. The effect of making different assumptions about the process, measurement and cross-covariance matrices-as well as Gaussian random walk and a latent force model of the unknown loads-on the accuracy precision of the estimates is discussed and recommendations are given for best practice. Given calibrated single-track model, the method can be applied to any road vehicle legally operating on public roads and has potential to be used as a low-cost method to collect large datasets describing road and crosswind disturbances on public road networks.

In architectural and structural design, computational methods have transformed the conceptual phase, allowing the exploration of diverse and efficient solutions. This paper introduces a new framework that integrates shape grammar, genetic algorithms, and clustering techniques to optimize structural designs in the early stages of architectural workflows. Unlike traditional optimization methods that aim for a single optimal solution, this approach generates multiple rational design options, balancing structural performance, aesthetics, and project constraints. Shape grammar effectively manages complex topologies with intuitive inputs, enabling designers to create varied structural forms while understanding the underlying rules and processes. Algorithmically, shape grammar offers significant design variety while maintaining designer control and insight into each configuration's production. This research focuses on developing a tool for designing 2D trusses and frame systems, with the aim of creating a functional prototype and verifying its performance through a case study. The method uses shape grammar for initial topologies, clustering algorithms to group similar designs, and genetic algorithms to refine and optimize each cluster. This ensures efficient and diverse designs, providing a strong foundation for future developments. The framework's effectiveness is demonstrated in a case study of a simplified large-scale convention hall, where these computational techniques generate innovative structural layouts. The results show the framework's ability to produce diverse designs meeting architectural and structural needs, offering advantages over traditional parametric design. This research contributes to architectural and structural design by providing a powerful tool for early design stages, where multiple options are crucial. The framework enhances the creative potential and aligns with the requirements of structural engineering, such as safety and performance. By promoting efficiency, diversity, and adaptability, this approach can transform the way architects and engineers tackle complex design challenges, leading to more innovative building practices.

The reuse of reclaimed materials in structural engineering holds significant potential for fostering sustainability and reducing construction waste. This paper explores a focused framework that emphasizes two critical processes: visual scanning of materials and algorithmic matching. The proposed approach demonstrates how advanced technologies like 3D scanning and generative design software can streamline workflows for integrating reclaimed elements into modern architectural designs.

In this research, a robust and efficient damage detection methodology for identifying defects in railway catenary systems is presented. An encoder-decoder architecture supplemented by residual analysis is employed for this purpose. A novel signal segmentation strategy based on the structural features of catenaries is introduced, coupled with a quasi-Welch method designed to mitigate edge effects. The potential impact of GPS inaccuracies on detection precision is examined. Additionally, a comprehensive analysis of various normalization techniques and their significant effects on defect identification outcomes is conducted. Two primary types of defects are considered: hard points in the contact wire and periodic short-wavelength irregularities (PSWI) of the contact wire, with variations in train speeds and defect magnitudes. A defect detection criterion has been developed, facilitating rapid and automatic identification of catenary defects. This integrated approach enables effective detection of defects and accurate determination of their location and can overcome the limitations of previous approaches, such as the requirement for high sampling frequency. This work not only advances the methodology for catenary inspection but also contributes to enhancing the safety and reliability of railway operations. The innovation of this work lies in the integration of the reconstruction capabilities of the encoder-decoder architecture with a residual-based defect detection method. This synergy allows the respective features of each to complement the other effectively.

Structural optimization has gained popularity in modern structural design, helping to reduce material consumption while maintaining the structural performance of buildings. This process also significantly influences the architectural appearance, affecting various aspects such as cross-section sizing, structural forms, and the layout of structural members. Beyond minimizing materials or costs, structural optimization can serve as a powerful tool for making architecture more visually appealing. However, with the wide variety of structural optimization methods proposed, gaining a comprehensive overview has become challenging. To address this, a systematic mapping study has been conducted, focusing on methods introduced over the past decade. The relevant journal articles are categorized based on several factors, including types of optimization, materials used, structural typologies, areas of application, and optimization objectives. The results of this study provide both a broad overview of recent developments in structural optimization and valuable insights into research-rich and under-explored areas. Moreover, the paper discusses which types of structural optimization are more relevant when applied as part of the architectural design process. It is suggested that future research should focus on identifying gaps and challenges in effectively applying structural optimization to architectural design, thus enhancing both efficiency and aesthetic potential.

Environmental conditions such as wind and ground traffic introduce motion in camera measurement systems and affect measurement accuracy. Conventional camera motion correction methods track static reference points with one or multiple cameras, reducing applicability. This study proposes a novel 6-degree-of-freedom (DOF) camera motion correction method using only an inertial measurement unit (IMU) sensor. A Kalman filter is adopted as a data fusion method to estimate the camera orientation and translation using IMU data. Six pinhole camera models are built to evaluate and correct 6-DOF camera motions. The motion correction efficiency and robustness are tested for different object distances and focal lengths of optical lenses. The motion correction ratio is statistically analysed and reaches approximately 80%. The object distance has little effect on the motion correction ratio. The rotation-induced pixel movement is independent of the object distance. More than 90% of the pixel movement noise is caused by camera rotation. The translation-induced pixel movement is inversely correlated with the object distance.

Rivets are critical mechanical fasteners in steel bridges, and rivet defects may cause catastrophic failure. This study proposes a convolutional neural network (CNN)‐based inspection system for fast rivet identification and diagnosis. Rivet states are classified as normal, rusted, loose, and missing. A CNN‐based training workflow was introduced to develop a reliable rivet diagnosis system. A multiscale moving window searching technique was proposed to solve the challenge of small rivet identification. A continuous dataset enrichment strategy was applied, which improves training efficiency and minimizes training time. The model performance was assessed based on a historical bridge in Gjerstad. The proposed multiscale moving window searching technique significantly enhances the rivet identification rate to 96.3%. The classification accuracy and model robustness were evaluated, and conditions leading to unidentified rivets were discussed and summarized.

This paper describes practical application of a novel and oven-controlled crystal oscillator (OCXO) high-precision synchronised wireless data acquisition system for a modal testing of the tallest all-timber building in the world - the 18-storey, 88.8m tall Mjostarnet (the Mjosa Tower) in Brumunddal, Norway. The modal testing was challenging as it was conducted in an occupied building in normal operation and was based on measuring both dynamic excitation and response yielding a set of frequency response functions (FRFs) across four different floors of the building. To the best knowledge of the authors, this was the first time that an FRF-based modal test was attempted on such a large building structure in operation. Moreover, although the structure was in operation, the testing was completed in only 48h, including commissioning and de-commissioning of all of the instrumentation, yielding a full set of point- and transfer accelerance FRFs. The paper presents the equipment used, key logistical challenges and quality assurance steps made to assure measurement of good quality FRF data in such short period of time demonstrating feasibility of the whole exercise. A total of seven modes of vibration, including higher order modes of vibration were estimated by curve-fitting the measured FRF data. This includes the 3rd bending and 2nd torsion modes difficult to measure via the standard ambient vibration testing of tall buildings. These modes could be used to investigate a number of uncertain modelling features in tall timber buildings, such as the stiffness of timber joints.

Environmental conditions such as wind and ground traffic will introduce motions in camera systems, which contribute as noise and thus affect measurement accuracy. The conventional camera motion correction methods need to track static reference objects by one or multiple cameras, reducing applicability and increasing costs. This study proposes a novel 6-degree-of-freedom (DOF) camera motion correction method based on an inertial measurement unit (IMU) sensor. The Kalman filter is adopted as a data fusion method to estimate the camera orientation and translation. Six pinhole camera models are built to evaluate and correct 6-DOF camera motions. The system hardware configuration is detailly introduced. The motion correction efficiency and robustness have been tested under different object distances and focal lengths. The motion correction ratio has been statistically analysed and achieved approximately 80

A data set from an extensive experimental benchmark study of the Hell Bridge Test Arena (HBTA), a full-scale steel bridge subject to imposed damage, has been established. The data set includes organized dynamic response and load measurement data of the bridge under different structural state conditions, where the structural state conditions range from an undamaged (reference) state to known damage states. Furthermore, the data set includes acceleration and strain data from the response monitoring and acceleration data from the load monitoring, where a modal vibration shaker is used as an excitation source. The data is collected in one h5-file (hierarchical data format version 5) with a sampling rate of 100 Hz. Signal processing and resampling of the data has been performed according to the description provided in the references below. The data set is now published in this open-access data repository and can be accessed and downloaded freely. As such, the data set provides an important benchmark to the scientific community within bridge damage detection and SHM.

Imprecise Structural Reliability Analysis (ISRA) is a novel and promising field in structural reliability. This work develops and introduces a framework for ISRA applied to steel railway bridges. The classical methods for estimating the remaining fatigue life of structures often rely on unsupported assumptions in cases of lack of data, leading to inaccurate results. The framework of ISRA represents uncertainties in a demonstrative and fair manner using p-boxes. Unlike classical Structural Reliability Analysis (SRA), which yields specific failure probabilities, ISRA provides intervals of failure probabilities. The developed ISRA approach was demonstrated for the Taller & aring;s railway bridge. The method was found to be useful for obtaining insight into the level of uncertainties of estimated failure probability. The paper concludes with a discussion of the consequences of using SRA or ISRA for railway bridge assessment.

Some of the strongest wind-induced lateral perturbations of the vehicle-driver system on bridges are observed when passing the towers. Occupants may feel uncomfortable or unsafe as a result. The aims of this work are to characterise the wind velocity profile observed in the wakes of bridge towers and understand the mechanisms through which the vehicle-driver system responds. A test vehicle was repeatedly driven across 5 cable-supported bridges with towers, of which 4 have been studied. Observed changes in wind speed were between 7 and 20 m/s with reference wind speeds of 14 to 25 m/s. The spatial periods of the wind profiles varied between 1.0 and 3.5 vehicle lengths giving disturbances at frequencies of 0.7 to 3.2 Hz at 60 to 80 km/h. The results show that the driver overcompensates for the changes in aerodynamic loading at the towers and the handling response of the vehicle is dominated by steering input – rather than aerodynamic input – once the driver initiates steering compensation. It is also shown, in agreement with an existing conceptual model, that the amplitude of the driver’s steering response is linearly related to the change in the vehicle’s yaw rate immediately preceding the compensation attempt.