The finite element method (FEM) is widely used to simulate a variety of physics phenomena. Approaches that integrate FEM with neural networks (NNs) are typically leveraged as an alternative to conducting expensive FEM simulations in order to reduce the computational cost without significantly sacrificing accuracy. However, these methods can produce biased predictions that deviate from those obtained with FEM, since these hybrid FEM-NN approaches rely on approximations trained using physically relevant quantities. In this work, an uncertainty estimation framework is introduced that leverages ensembles of Bayesian neural networks to produce diverse sets of predictions using a hybrid FEM-NN approach that approximates internal forces on a deforming solid body. The uncertainty estimator developed herein reliably infers upper bounds of bias/variance in the predictions for a wide range of interpolation and extrapolation cases using a three-element FEM-NN model of a bar undergoing plastic deformation. This proposed framework offers a powerful tool for assessing the reliability of physics-based surrogate models by establishing uncertainty estimates for predictions spanning a wide range of possible load cases.

While finite element (FE) modeling is widely used for ultimate strength assessments of structural systems, incorporating complex distortions and imperfections into FE models remains a challenge. Conventional methods typically rely on assumptions about the periodicity of distortions through spectral or modal methods. However, these approaches are not viable under the many realistic scenarios where these assumptions are invalid. Research efforts have consistently demonstrated the ability of point cloud data, generated through laser scanning or photogrammetry-based methods, to accurately capture structural deformations at the millimeter scale. This enables the updating of numerical models to capture the exact structural configuration and initial imperfections without the need for unrealistic assumptions. This research article investigates the use of point cloud data for updating the initial distortions in a FE model of a stiffened ship deck panel, for the purposes of ultimate strength estimation. The presented approach has the additional benefit of being able to explicitly account for measurement uncertainty in the analysis. Calculations using the updated FE models are compared against ground truth test data as well as FE models updated using standard spectral methods. The results demonstrate strength estimation that is comparable to existing approaches, with the additional advantages of uncertainty quantification and applicability to a wider range of application scenarios.

As a Bayesian approach to fitting motorway traffic flow models remains rare in the literature, we empirically explore the sampling challenges this approach offers which have to do with the strong correlations and multimodality of the posterior distribution. In particular, we provide a unified statistical model to estimate using motorway data both boundary conditions and fundamental diagram parameters in a motorway traffic flow model due to Lighthill, Whitham, and Richards known as LWR. This allows us to provide a traffic flow density estimation method that is shown to be superior to two methods found in the traffic flow literature. To sample from this challenging posterior distribution, we use a state-of-the-art gradient-free function space sampler augmented with parallel tempering.

The seismic response of a wide variety of structures, from small but irreplaceable museum exhibits to large bridge systems, is characterized by rocking. In addition, rocking motion is increasingly being used as a seismic protective strategy to limit the amount of seismic actions (moments) developed at the base of structures. However, rocking is a highly nonlinear phenomenon governed by non-smooth dynamic phases that make its prediction difficult. This study presents an alternative approach to rocking estimation based on a physics-informed convolutional neural network (PICNN). By training a group of PICNNs using limited datasets obtained from numerical simulations and encoding the known physics into the PICNNs, important predictive benefits are obtained relieving difficulties associated with over-fitting and minimizing the requirement for a large training database. Two models are created depending on the validation of the deep PICNN: the first model assumes that state variables including rotations and angular velocities are available, while the second model is useful when only acceleration measurements are known. The analysis is initiated by implementing K-means clustering. This is followed by a detailed statistical assessment and a comparative analysis of the response-histories of a rocking block. It is observed that the deep PICNN is capable of effectively estimating the seismic rocking response history when the rigid block does not overturn.

Monte Carlo algorithms simulates some prescribed number of samples, taking some random real time to complete the computations necessary. This work considers the converse: to impose a real-time budget on the computation, which results in the number of samples simulated being random. To complicate matters, the real time taken for each simulation may depend on the sample produced, so that the samples themselves are not independent of their number, and a length bias with respect to compute time is apparent. This is especially problematic when a Markov chain Monte Carlo (MCMC) algorithm is used and the final state of the Markov chain—rather than an average over all states—is required, which is the case in parallel tempering implementations of MCMC. The length bias does not diminish with the compute budget in this case. It also occurs in sequential Monte Carlo (SMC) algorithms, which is the focus of this paper. We propose an anytime framework to address the concern, using a continuous-time Markov jump process to study the progress of the computation in real time. We first show that for any MCMC algorithm, the length bias of the final state’s distribution due to the imposed real-time computing budget can be eliminated by using a multiple chain construction. The utility of this construction is then demonstrated on a large-scale SMC$ {}^2 $ implementation, using four billion particles distributed across a cluster of 128 graphics processing units on the Amazon EC2 service. The anytime framework imposes a real-time budget on the MCMC move steps within the SMC$ {}^2 $ algorithm, ensuring that all processors are simultaneously ready for the resampling step, demonstrably reducing idleness to due waiting times and providing substantial control over the total compute budget.

In many complex practical optimization cases, the dominant characteristics of the problem are often not known prior. Therefore, there is a need to develop general solvers as it is not always possible to tailor a specialized approach to each application. The previously developed multilevel selection genetic algorithm (MLSGA) already shows good performance on a range of problems due to its diversity-first approach, which is rare among evolutionary algorithms. To increase the generality of its performance, this paper proposes utilization of multiple distinct evolutionary strategies simultaneously, similarly to algorithm selection, but with coevolutionary mechanisms between the subpopulations. This distinctive approach to coevolution provides less regular communication between subpopulations with competition between collectives rather than individuals. This encourages the collectives to act more independently creating a unique subregional search, leading to the development of coevolutionary MLSGA (cMLSGA). To test this methodology, nine genetic algorithms are selected to generate several variants of cMLSGA, which incorporates these approaches at the individual level. The mechanisms are tested on 100 different functions and benchmarked against the 9 state-of-the-art competitors to evaluate the generality of each approach. The results show that the diversity divergence in the principles of working of the selected coevolutionary approaches is more important than their individual performances. The proposed methodology has the most uniform performance on the divergent problem types, from across the tested state of the art, leading to an algorithm more likely to solve complex problems with limited knowledge about the search space, but is outperformed by more specialized solvers on simpler benchmarking studies.

Sensor placement optimization (SPO) is usually applied during the structural health monitoring sensor system design process to collect effective data. However, the failure of a sensor may significantly affect the expected performance of the entire system. Therefore, it is necessary to study the optimal sensor placement considering the possibility of sensor failure. In this article, the research focusses on an SPO giving a fail-safe sensor distribution, whose sub-distributions still have good performance. The performance of the fail-safe sensor distribution with multiple sensors placed in the same position will also be studied. The adopted data sets include the mode shapes and corresponding labels of structural states from a series of tests on a glider wing. A genetic algorithm is used to search for sensor deployments, and the partial results are validated by an exhaustive search. Two types of optimization objectives are investigated, one for modal identification and the other for damage identification. The results show that the proposed fail-safe sensor optimization method is beneficial for balancing the system performance before and after sensor failure.

Compressible anisothermal flows, which are commonly found in industrial settings such as combustion chambers and heat exchangers, are characterized by significant variations in density, viscosity, and heat conductivity with temperature. These variations lead to a strong interaction between the temperature and velocity fields that impacts the near-wall profiles of both quantities. Wall-modeled large-eddy simulations (LESs) rely on a wall model to provide a boundary condition, for example, the shear stress and the heat flux that accurately represents this interaction despite the use of coarse cells near the wall, and thereby achieve a good balance between computational cost and accuracy. In this article, the use of graph neural networks for wall modeling in LES is assessed for compressible anisothermal flow. Graph neural networks are a type of machine learning model that can learn from data and operate directly on complex unstructured meshes. Previous work has shown the effectiveness of graph neural network wall modeling for isothermal incompressible flows. This article develops the graph neural network architecture and training to extend their applicability to compressible anisothermal flows. The model is trained and tested a priori using a database of both incompressible isothermal and compressible anisothermal flows. The model is finally tested a posteriori for the wall-modeled LES of a channel flow and a turbine blade, both of which were not seen during training.

Understanding the subsurface is crucial in building a sustainable future, particularly for urban centers. Importantly, the thermal effects that anthropogenic infrastructure, such as buildings, tunnels, and ground heat exchangers, can have on this shared resource need to be well understood to avoid issues, such as overheating the ground, and to identify opportunities, such as extracting and utilizing excess heat. However, obtaining data for the subsurface can be costly, typically requiring the drilling of boreholes. Bayesian statistical methodologies can be used towards overcoming this, by inferring information about the ground by combining field data and numerical modeling, while quantifying associated uncertainties. This work utilizes data obtained in the city of Cardiff, UK, to evaluate the applicability of a Bayesian calibration (using GP surrogates) approach to measured data and associated challenges (previously not tested) and to obtain insights on the subsurface of the area. The importance of the data set size is analyzed, showing that more data are required in realistic (field data), compared to controlled conditions (numerically-generated data), highlighting the importance of identifying data points that contain the most information. Heterogeneity of the ground (i.e., input parameters), which can be particularly prominent in large-scale subsurface domains, is also investigated, showing that the calibration methodology can still yield reasonably accurate results under heterogeneous conditions. Finally, the impact of considering uncertainty in subsurface properties is demonstrated in an existing shallow geothermal system in the area, showing a higher than utilized ground capacity, and the potential for a larger scale system given sufficient demand.

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.

For research in the fields of engineering asset management (EAM) and system health, relevant data resides in the information systems of the asset owners, typically industrial corporations or government bodies. For academics to access EAM data sets for research purposes can be a difficult and time-consuming task. To facilitate a more consistent approach toward releasing asset-related data, we have developed a data risk assessment tool (DRAT). This tool evaluates and suggests controls to manage, risks associated with the release of EAM datasets to academic entities for research purposes. Factors considered in developing the tool include issues such as where accountability for approval sits in organizations, what affects an individual manager’s willingness to approve release, and how trust between universities and industry can be established and damaged. This paper describes the design of the DRAT tool and demonstrates its use on case studies provided by EAM owners for past research projects. The DRAT tool is currently being used to manage the data release process in a government-industry-university research partnership.

The uptake of electric vehicles (EVs) and renewable energy technologies is changing the magnitude, variability, and direction of power flows in electricity networks. To ensure a successful transition to a net zero energy system, it will be necessary for a wide range of stakeholders to understand the impacts of these changing flows on networks. However, there is a gap between those with the data and capabilities to understand electricity networks, such as network operators, and those working on adjacent parts of the energy transition jigsaw, such as electricity suppliers and EV charging infrastructure operators. This paper describes the electric vehicle network analysis tool (EVENT), developed to help make network analysis accessible to a wider range of stakeholders in the energy ecosystem who might not have the bandwidth to curate and integrate disparate datasets and carry out electricity network simulations. EVENT analyses the potential impacts of low-carbon technologies on congestion in electricity networks, helping to inform the design of products and services. To demonstrate EVENT’s potential, we use an extensive smart meter dataset provided by an energy supplier to assess the impacts of electricity smart tariffs on networks. Results suggest both network operators and energy suppliers will have to work much more closely together to ensure that the flexibility of customers to support the energy system can be maximized, while respecting safety and security constraints within networks. EVENT’s modular and open-source approach enables integration of new methods and data, future-proofing the tool for long-term impact.

Reproducibility of a deep-learning fully convolutional neural network is evaluated by training several times the same network on identical conditions (database, hyperparameters, and hardware) with nondeterministic graphics processing unit operations. The network is trained to model three typical time–space-evolving physical systems in two dimensions: heat, Burgers’, and wave equations. The behavior of the networks is evaluated on both recursive and nonrecursive tasks. Significant changes in models’ properties (weights and feature fields) are observed. When tested on various benchmarks, these models systematically return estimations with a high level of deviation, especially for the recurrent analysis which strongly amplifies variability due to the nondeterminism. Trainings performed with double floating-point precision provide slightly better estimations and a significant reduction of the variability of both the network parameters and its testing error range.

Pharmaceutical distribution routing problem is a key problem for pharmaceutical enterprises, since efficient schedules can enhance resource utilization and reduce operating costs. Meanwhile, it is a complicated combinatorial optimization problem. Existing research mainly focused on delivery route lengths or distribution costs minimization, while seldom considered customer priority and carbon emissions simultaneously. However, considering the customer priority and carbon emissions simultaneously will not only help to enhance customer satisfaction, but also help to reduce the carbon emissions. In this article, we consider the customer priority and carbon emission minimization simultaneously in the pharmaceutical distribution routing problem, the corresponding problem is named pharmaceutical distribution routing problem considering customer priority and carbon emissions. A corresponding mathematical model is formulated, the objectives of which are minimizing fixed cost, refrigeration cost, fuel consumption cost, carbon emission cost, and penalty cost for violating time windows. Moreover, a hybrid genetic algorithm (HGA) is proposed to solve the problem. The framework of the proposed HGA is genetic algorithm (GA), where an effective local search based on variable neighborhood search (VNS) is specially designed and incorporated to improve the intensification abilities. In the proposed HGA, crossover with adaptive probability and mutation with adaptive probability are utilized to enhance the algorithm performance. Finally, the proposed HGA is compared with four optimization algorithms, and experimental results have demonstrated the effectiveness of the HGA.

The exploitation of hydrocarbon reservoirs may potentially lead to contamination of soils, shallow water resources, and greenhouse gas emissions. Fluids such as methane or CO2 may in some cases migrate toward the groundwater zone and atmosphere through and along imperfectly sealed hydrocarbon wells. Field tests in hydrocarbon-producing regions are routinely conducted for detecting serious leakage to prevent environmental pollution. The challenge is that testing is costly, time-consuming, and sometimes labor-intensive. In this study, machine learning approaches were applied to predict serious leakage with uncertainty quantification for wells that have not been field tested in Alberta, Canada. An improved imputation technique was developed by Cholesky factorization of the covariance matrix between features, where missing data are imputed via conditioning of available values. The uncertainty in imputed values was quantified and incorporated into the final prediction to improve decision-making. Next, a wide range of predictive algorithms and various performance metrics were considered to achieve the most reliable classifier. However, a highly skewed distribution of field tests toward the negative class (nonserious leakage) forces predictive models to unrealistically underestimate the minority class (serious leakage). To address this issue, a combination of oversampling, undersampling, and ensemble learning was applied. By investigating all the models on never-before-seen data, an optimum classifier with minimal false negative prediction was determined. The developed methodology can be applied to identify the wells with the highest likelihood for serious fluid leakage within producing fields. This information is of key importance for optimizing field test operations to achieve economic and environmental benefits.

The ability to wirelessly stream data from sensors on heavy mobile equipment provides opportunities to proactively assess asset condition. However, data analysis methods are challenging to apply due to the size and structure of the data, which contain inconsistent and asynchronous entries, and large periods of missing data. Current methods usually require expertise from site engineers to inform variable selection. In this work, we develop a data preparation method to clean and arrange this streaming data for analysis, including a data-driven variable selection. Data are drawn from a mining industry case study, with sensor data from a primary production excavator over a period of 9 months. Variables include 58 numerical sensors and 40 binary indicators captured in 45-million rows of data describing the conditions and status of different subsystems of the machine. A total of 57% of time stamps contain missing values for at least one sensor. The response variable is drawn from fault codes selected by the operator and stored in the fleet management system. Application to the hydraulic system, for 21 failure events identified by the operator, shows that the data-driven selection contains variables consistent with subject matter expert expectations, as well as some sensors on other systems on the excavator that are less easy to explain from an engineering perspective. Our contribution is to demonstrate a compressed data representation using open-high-low-close and variable selection to visualize data and support identification of potential indicators of failure events from multivariate streamed data.

State-of-the-art machine-learning-based models are a popular choice for modeling and forecasting energy behavior in buildings because given enough data, they are good at finding spatiotemporal patterns and structures even in scenarios where the complexity prohibits analytical descriptions. However, their architecture typically does not hold physical correspondence to mechanistic structures linked with governing physical phenomena. As a result, their ability to successfully generalize for unobserved timesteps depends on the representativeness of the dynamics underlying the observed system in the data, which is difficult to guarantee in real-world engineering problems such as control and energy management in digital twins. In response, we present a framework that combines lumped-parameter models in the form of linear time-invariant (LTI) state-space models (SSMs) with unsupervised reduced-order modeling in a subspace-based domain adaptation (SDA) approach, which is a type of transfer-learning (TL) technique. Traditionally, SDA is adopted for exploiting labeled data from one domain to predict in a different but related target domain for which labeled data is limited. We introduced a novel SDA approach where instead of labeled data, we leverage the geometric structure of the LTI SSM governed by well-known heat transfer ordinary differential equations to forecast for unobserved timesteps beyond available measurement data by geometrically aligning the physics-derived and data-derived embedded subspaces closer together. In this initial exploration, we evaluate the physics-based SDA framework on a demonstrative heat conduction scenario by varying the thermophysical properties of the source and target systems to demonstrate the transferability of mechanistic models from physics to observed measurement data.