Wind turbine towers are subjected to highly varying internal loads, characterized by large uncertainty. The uncertainty stems from many factors, including what the actual wind fields experienced over time will be, modeling uncertainties given the various operational states of the turbine with and without controller interaction, the influence of aerodynamic damping, and so forth. To monitor the true experienced loading and assess the fatigue, strain sensors can be installed at fatigue-critical locations on the turbine structure. A more cost-effective and practical solution is to predict the strain response of the structure based only on a number of acceleration measurements. In this contribution, an approach is followed where the dynamic strains in an existing onshore wind turbine tower are predicted using a Gaussian process latent force model. By employing this model, both the applied dynamic loading and strain response are estimated based on the acceleration data. The predicted dynamic strains are validated using strain gauges installed near the bottom of the tower. Fatigue is subsequently assessed by comparing the damage equivalent loads calculated with the predicted as opposed to the measured strains. The results confirm the usefulness of the method for continuous tracking of fatigue life consumption in onshore wind turbine towers.

Traffic congestion across the world has reached chronic levels. Despite many technological disruptions, one of the most fundamental and widely used functions within traffic modeling, the volume–delay function has seen little in the way of change since it was developed in the 1960s. Traditionally macroscopic methods have been employed to relate traffic volume to vehicular journey time. The general nature of these functions enables their ease of use and gives widespread applicability. However, they lack the ability to consider individual road characteristics (i.e., geometry, presence of traffic furniture, road quality, and surrounding environment). This research investigates the feasibility to reconstruct the model using two different data sources, namely the traffic speed from Google Maps’ Directions Application Programming Interface (API) and traffic volume data from automated traffic counters (ATC). Google’s traffic speed data are crowd-sourced from the smartphone Global Positioning System (GPS) of road users, able to reflect real-time, context-specific traffic condition of a road. On the other hand, the ATCs enable the harvesting of the vehicle volume data over equally fine temporal resolutions (hourly or less). By combining them for different road types in London, new context-specific volume–delay functions can be generated. This method shows promise in selected locations with the generation of robust functions. In other locations, it highlights the need to better understand other influencing factors, such as the presence of on-road parking or weather events.

The decreasing cost and improved sensor and monitoring system technology (e.g., fiber optics and strain gauges) have led to more measurements in close proximity to each other. When using such spatially dense measurement data in Bayesian system identification strategies, the correlation in the model prediction error can become significant. The widely adopted assumption of uncorrelated Gaussian error may lead to inaccurate parameter estimation and overconfident predictions, which may lead to suboptimal decisions. This article addresses the challenges of performing Bayesian system identification for structures when large datasets are used, considering both spatial and temporal dependencies in the model uncertainty. We present an approach to efficiently evaluate the log-likelihood function, and we utilize nested sampling to compute the evidence for Bayesian model selection. The approach is first demonstrated on a synthetic case and then applied to a (measured) real-world steel bridge. The results show that the assumption of dependence in the model prediction uncertainties is decisively supported by the data. The proposed developments enable the use of large datasets and accounting for the dependency when performing Bayesian system identification, even when a relatively large number of uncertain parameters is inferred.

In chemical process engineering, surrogate models of complex systems are often necessary for tasks of domain exploration, sensitivity analysis of the design parameters, and optimization. A suite of computational fluid dynamics (CFD) simulations geared toward chemical process equipment modeling has been developed and validated with experimental results from the literature. Various regression-based active learning strategies are explored with these CFD simulators in-the-loop under the constraints of a limited function evaluation budget. Specifically, five different sampling strategies and five regression techniques are compared, considering a set of four test cases of industrial significance and varying complexity. Gaussian process regression was observed to have a consistently good performance for these applications. The present quantitative study outlines the pros and cons of the different available techniques and highlights the best practices for their adoption. The test cases and tools are available with an open-source license to ensure reproducibility and engage the wider research community in contributing to both the CFD models and developing and benchmarking new improved algorithms tailored to this field.

Despite the growing availability of sensing and data in general, we remain unable to fully characterize many in-service engineering systems and structures from a purely data-driven approach. The vast data and resources available to capture human activity are unmatched in our engineered world, and, even in cases where data could be referred to as “big,” they will rarely hold information across operational windows or life spans. This paper pursues the combination of machine learning technology and physics-based reasoning to enhance our ability to make predictive models with limited data. By explicitly linking the physics-based view of stochastic processes with a data-based regression approach, a derivation path for a spectrum of possible Gaussian process models is introduced and used to highlight how and where different levels of expert knowledge of a system is likely best exploited. Each of the models highlighted in the spectrum have been explored in different ways across communities; novel examples in a structural assessment context here demonstrate how these approaches can significantly reduce reliance on expensive data collection. The increased interpretability of the models shown is another important consideration and benefit in this context.

Model-based systems engineering (MBSE) aims at creating a model of a system under development, covering the complete system with a level of detail that allows to define and understand its behavior and enables to define any interface and work package based on the model. Once the model is established, further benefits can be reaped, such as the analysis of complex technical correlations within the system. Various insights can be gained by displaying the model as a formal graph and querying it. To enable such queries, a graph schema is necessary, which allows to transfer the model into a graph database. In the course of this paper, we discuss the design of a graph schema and MBSE modeling approach, enabling deep going system analysis and anomaly resolution in complex embedded systems with a focus on testing and anomaly resolution. The schema and modeling approach are designed to answer questions such as What happens if there is an electrical short in a component? Which other components are now offline and which data cannot be gathered anymore? If a component becomes unresponsive, which alternative routes can be established to obtain data processed by it. We build on the use case of qualification and operations of a small spacecraft. Structural elements of the MBSE model are transferred to a graph database where analyses are conducted on the system. The schema is implemented by means of an adapter for MagicDraw to Neo4J. A selection of complex analyses is shown in the example of the MOVE-II space mission.

We develop a model that successfully learns social and organizational human network structure using ambient sensing data from distributed plug load energy sensors in commercial buildings. A key goal for the design and operation of commercial buildings is to support the success of organizations within them. In modern workspaces, a particularly important goal is collaboration, which relies on physical interactions among individuals. Learning the true socio-organizational relational ties among workers can therefore help managers of buildings and organizations make decisions that improve collaboration. In this paper, we introduce the Interaction Model, a method for inferring human network structure that leverages data from distributed plug load energy sensors. In a case study, we benchmark our method against network data obtained through a survey and compare its performance to other data-driven tools. We find that unlike previous methods, our method infers a network that is correlated with the survey network to a statistically significant degree (graph correlation of 0.46, significant at the 0.01 confidence level). We additionally find that our method requires only 10 weeks of sensing data, enabling dynamic network measurement. Learning human network structure through data-driven means can enable the design and operation of spaces that encourage, rather than inhibit, the success of organizations.

Neural networks-based learning of the distribution of non-dispatchable renewable electricity generation from sources, such as photovoltaics (PV) and wind as well as load demands, has recently gained attention. Normalizing flow density models are particularly well suited for this task due to the training through direct log-likelihood maximization. However, research from the field of image generation has shown that standard normalizing flows can only learn smeared-out versions of manifold distributions. Previous works on normalizing flow-based scenario generation do not address this issue, and the smeared-out distributions result in the sampling of noisy time series. In this paper, we exploit the isometry of the principal component analysis (PCA), which sets up the normalizing flow in a lower-dimensional space while maintaining the direct and computationally efficient likelihood maximization. We train the resulting principal component flow (PCF) on data of PV and wind power generation as well as load demand in Germany in the years 2013–2015. The results of this investigation show that the PCF preserves critical features of the original distributions, such as the probability density and frequency behavior of the time series. The application of the PCF is, however, not limited to renewable power generation but rather extends to any dataset, time series, or otherwise, which can be efficiently reduced using PCA.

Aging ships and offshore structures face harsh environmental and operational conditions in remote areas, leading to age-related damages such as corrosion wastage, fatigue cracking, and mechanical denting. These deteriorations, if left unattended, can escalate into catastrophic failures, causing casualties, property damage, and marine pollution. Hence, ensuring the safety and integrity of aging ships and offshore structures is paramount and achievable through innovative healthcare schemes. One such paradigm, digital healthcare engineering (DHE), initially introduced by the final coauthor, aims at providing lifetime healthcare for engineered structures, infrastructure, and individuals (e.g., seafarers) by harnessing advancements in digitalization and communication technologies. The DHE framework comprises five interconnected modules: on-site health parameter monitoring, data transmission to analytics centers, data analytics, simulation and visualization via digital twins, artificial intelligence-driven diagnosis and remedial planning using machine and deep learning, and predictive health condition analysis for future maintenance. This article surveys recent technological advancements pertinent to each DHE module, with a focus on its application to aging ships and offshore structures. The primary objectives include identifying cost-effective and accurate techniques to establish a DHE system for lifetime healthcare of aging ships and offshore structures—a project currently in progress by the authors.

Data-Centric Engineering is an emerging branch of science that certainly will take on a leading role in data-driven research. We live in the Big Data era with huge amounts of available data and unseen computing power, and therefore a crafty combination of Statistics (or, in more modern terms, Data Science), Computer Science and Engineering is required to filter out the most important information, master the ever more difficult challenges of a changing world and open new paths. In this paper, we will highlight some of these aspects from a combined perspective of a statistician, an engineer and a software developer. In particular, we will focus on sound data handling and analysis, computational science in Structural Engineering, data care, security and monitoring, and conclude with an outlook on future developments.

Data mining and knowledge discovery (DMKD) focuses on extracting useful information from data. In the chemical process industry, tasks such as process monitoring, fault detection, process control, optimization, etc., can be achieved using DMKD. However, the selection of the appropriate method for each step in the DMKD process, namely data cleaning, sampling, scaling, dimensionality reduction (DR), clustering, clustering analysis and data visualization to obtain meaningful insights is far from trivial. In this contribution, a computational environment (FastMan) is introduced and used to illustrate how method selection affects DMKD in chemical process data. Two case studies, using data from a simulated natural gas liquid plant and real data from an industrial pyrolysis unit, were conducted to demonstrate the applicability of these methodologies in real-life scenarios. Sampling and normalization methods were found to have a great impact on the quality of the DMKD results. Also, a neighbor graphs method for DR, t-distributed stochastic neighbor embedding, outperformed principal component analysis, a matrix factorization method frequently used in the chemical process industry for identifying both local and global changes.

As the Reynolds number increases, the large-eddy simulation (LES) of complex flows becomes increasingly intractable because near-wall turbulent structures become increasingly small. Wall modeling reduces the computational requirements of LES by enabling the use of coarser cells at the walls. This paper presents a machine-learning methodology to develop data-driven wall-shear-stress models that can directly operate, a posteriori, on the unstructured grid of the simulation. The model architecture is based on graph neural networks. The model is trained on a database which includes fully developed boundary layers, adverse pressure gradients, separated boundary layers, and laminar–turbulent transition. The relevance of the trained model is verified a posteriori for the simulation of a channel flow, a backward-facing step and a linear blade cascade.

This article presents a system architecture and a set of interfaces that can build scalable information systems capable of large city modeling based on dynamic geospatial knowledge graphs to avoid pitfalls of Web 2.0 applications while blending artificial and human intelligence during the knowledge enhancement processes. We designed and developed a GeoSpatial Processor, an SQL2SPARQL Transformer, and a geospatial tiles ordering tasks and integrated them into a City Export Agent to visualize and interact with city models on an augmented 3D web client. We designed a Thematic Surface Discovery Agent to automatically upgrade the model’s level of detail to interact with thematic parts of city objects by other agents. We developed a City Information Agent to help retrieve contextual information, provide data concerning city regulations, and work with a City Energy Analyst Agent that automatically estimates the energy demands for city model members. We designed a Distance Agent to track the interactions with the model members on the web, calculate distances between objects of interest, and add new knowledge to the Cities Knowledge Graph. The logical foundations and CityGML-based conceptual schema used to describe cities in terms of the OntoCityGML ontology, together with the system of intelligent autonomous agents based on the J-Park Simulator Agent Framework, make such systems capable of assessing and maintaining ground truths with certainty. This new era of GeoWeb 2.5 systems lowers the risk of deliberate misinformation within geography web systems used for modeling critical infrastructures.

We propose, calibrate, and validate a crowdsourced approach for estimating power spectral density (PSD) of road roughness based on an inverse analysis of vertical acceleration measured by a smartphone mounted in an unknown position in a vehicle. Built upon random vibration analysis of a half-car mechanistic model of roughness-induced pavement–vehicle interaction, the inverse analysis employs an L2 norm regularization to estimate ride quality metrics, such as the widely used International Roughness Index, from the acceleration PSD. Evoking the fluctuation–dissipation theorem of statistical physics, the inverse framework estimates the half-car dynamic vehicle properties and related excess fuel consumption. The method is validated against (a) laser-measured road roughness data for both inner city and highway road conditions and (b) road roughness data for the state of California. We also show that the phone position in the vehicle only marginally affects road roughness predictions, an important condition for crowdsourced capabilities of the proposed approach.

X-ray tomography has applications in various industrial fields such as sawmill industry, oil and gas industry, as well as chemical, biomedical, and geotechnical engineering. In this article, we study Bayesian methods for the X-ray tomography reconstruction. In Bayesian methods, the inverse problem of tomographic reconstruction is solved with the help of a statistical prior distribution which encodes the possible internal structures by assigning probabilities for smoothness and edge distribution of the object. We compare Gaussian random field priors, that favor smoothness, to non-Gaussian total variation (TV), Besov, and Cauchy priors which promote sharp edges and high- and low-contrast areas in the object. We also present computational schemes for solving the resulting high-dimensional Bayesian inverse problem with 100,000–1,000,000 unknowns. We study the applicability of a no-U-turn variant of Hamiltonian Monte Carlo (HMC) methods and of a more classical adaptive Metropolis-within-Gibbs (MwG) algorithm to enable full uncertainty quantification of the reconstructions. We use maximum a posteriori (MAP) estimates with limited-memory BFGS (Broyden–Fletcher–Goldfarb–Shanno) optimization algorithm. As the first industrial application, we consider sawmill industry X-ray log tomography. The logs have knots, rotten parts, and even possibly metallic pieces, making them good examples for non-Gaussian priors. Secondly, we study drill-core rock sample tomography, an example from oil and gas industry. In that case, we compare the priors without uncertainty quantification. We show that Cauchy priors produce smaller number of artefacts than other choices, especially with sparse high-noise measurements, and choosing HMC enables systematic uncertainty quantification, provided that the posterior is not pathologically multimodal or heavy-tailed.

Predicting the occurrence of thermoacoustic instabilities is of major interest in a variety of engineering applications such as aircraft propulsion, power generation, and industrial heating. Predictive methodologies based on a physical approach have been developed in the past decades, but have a moderate-to-high computational cost when exploring a large number of designs. In this study, the stability prediction capabilities and computational cost of four well-established classification algorithms—the K-Nearest Neighbors, Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP) algorithms—are investigated. These algorithms are trained using an in-house physics-based low-order network model tool called OSCILOS. All four algorithms are able to predict which configurations are thermoacoustically unstable with a very high accuracy and a very low runtime. Furthermore, the frequency intervals containing unstable modes for a given configuration are also accurately predicted using multilabel classification. The RF algorithm correctly predicts the overall stability and finds all frequency intervals containing unstable modes for 99.6 and 98.3% of all configurations, respectively, which makes it the most accurate algorithm when a large number of training examples is available. For smaller training sets, the MLP algorithm becomes the most accurate algorithm. The DT algorithm is found to be slightly less accurate, but can be trained extremely quickly and runs about a million times faster than a traditional physics-based low-order network model tool. These findings could be used to devise a new generation of combustor optimization tools that would run much faster than existing codes while retaining a similar accuracy.

Reliable short-term load forecasting is vital for the planning and operation of electric power systems. Short-term load forecasting is a critical component used in purchasing and generating electric power, dispatching, and load switching, which is essential for balancing supply and demand and mitigating the risk of power shortages. This is becoming even more critical given the transition to carbon-neutral technologies in the energy sector. Specifically, since renewable sources are inherently uncertain, a distributed energy system with renewable generation units is more heavily dependent on accurate load forecasts for demand-response management than traditional energy sectors. Despite extensive literature on forecasting electricity demand, most studies focus on predicting the total demand solely based on the previous-step observations of aggregate demand. With advances in smart-metering technology and the availability of high-resolution consumption data, harnessing fine-resolution smart-meter data in load forecasting has attracted increasing attention. Studies using smart-meter data mainly involve a “bottom-up” approach that develops separate forecast models at sub-aggregate levels and aggregates the forecasts to estimate the total demand. While this approach is conducive to incorporating fine-resolution data for load forecasting, it has several shortcomings that can result in sub-optimal forecasts. However, these shortcomings are hardly acknowledged in the load forecasting literature. This work demonstrates how limitations imposed by such a bottom-up load forecasting approach can lead to misleading results, which could hamper efficient load management within a carbon-neutral grid.

New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health, and societal well-being. Could artificial intelligence (AI) accelerate science to meet these global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here that it could be more holistic and encompassing. We introduce the concept of virtual laboratories as a new perspective on scientific knowledge generation and a means to incentivize new AI research and development. Despite the often perceived domain-specific research practices and inherent tacit knowledge, we argue that many elements of the research process recur across scientific domains and that even common software platforms for serving different domains may be possible. We outline how virtual laboratories will make it easier for AI researchers to contribute to a broad range of scientific domains, and highlight the mutual benefits virtual laboratories offer to both AI and domain scientists.

The integration of Artificial Neural Networks (ANNs) and Feature Extraction (FE) in the context of the Sample- Partitioning Adaptive Reduced Chemistry approach was investigated in this work, to increase the on-the-fly classification accuracy for very large thermochemical states. The proposed methodology was firstly compared with an on-the-fly classifier based on the Principal Component Analysis reconstruction error, as well as with a standard ANN (s-ANN) classifier, operating on the full thermochemical space, for the adaptive simulation of a steady laminar flame fed with a nitrogen-diluted stream of n-heptane in air. The numerical simulations were carried out with a kinetic mechanism accounting for 172 species and 6,067 reactions, which includes the chemistry of Polycyclic Aromatic Hydrocarbons (PAHs) up to C $ {}_{20} $ . Among all the aforementioned classifiers, the one exploiting the combination of an FE step with ANN proved to be more efficient for the classification of high-dimensional spaces, leading to a higher speed-up factor and a higher accuracy of the adaptive simulation in the description of the PAH and soot-precursor chemistry. Finally, the investigation of the classifier’s performances was also extended to flames with different boundary conditions with respect to the training one, obtained imposing a higher Reynolds number or time-dependent sinusoidal perturbations. Satisfying results were observed on all the test flames.

Aeroengine performance is determined by temperature and pressure profiles along various axial stations within an engine. Given limited sensor measurements, we require a statistically principled approach for inferring these profiles. In this paper we detail a Bayesian methodology for interpolating the spatial temperature or pressure profile at axial stations within an aeroengine. The profile at any given axial station is represented as a spatial Gaussian random field on an annulus, with circumferential variations modelled using a Fourier basis and radial variations modelled with a squared exponential kernel. This Gaussian random field is extended to ingest data from multiple axial measurement planes, with the aim of transferring information across the planes. To facilitate this type of transfer learning, a novel planar covariance kernel is proposed. In the scenario where frequencies comprising the temperature field are unknown, we utilise a sparsity-promoting prior on the frequencies to encourage sparse representations. This easily extends to cases with multiple engine planes whilst accommodating frequency variations between the planes. The main quantity of interest, the spatial area average is readily obtained in closed form. We term this the Bayesian area average and demonstrate how this metric offers far more representative averages than a sector area average---a widely used area averaging approach. Furthermore, the Bayesian area average naturally decomposes the posterior uncertainty into terms characterising insufficient sampling and sensor measurement error respectively. This too provides a significant improvement over prior standard deviation based uncertainty breakdowns.