Stochastic Predictions Research Articles

Intelligent fatigue damage tracking and prognostics of composite structures utilizing raw images via interpretable deep learning

In recent years, prognostics gained attention in various industries by optimizing maintenance, boosting operational efficiency, and preventing costly downtime. Central to prognostics is the Remaining Useful Life (RUL), representing the critical time before system failure. Deep learning advancements facilitate RUL forecasting by extracting features from diverse data formats such as time series, images, or sequences thereof, in one, two, or three dimensions, respectively. Yet, predicting RUL from image sequences often relies heavily on resource-intensive techniques like digital image correlation, complicating data acquisition. To address challenges with high-dimensional data and unreliable models, this study introduces ISTRUST, an innovative Transformer-based architecture. ISTRUST (Interpretable Spatiotemporal TRansformer for Understanding STructures) tackles the dual challenges posed by high-dimensional data and the black-box nature of existing models. Leveraging Transformers’ attention mechanism, ISTRUST breaks down the spatiotemporal domain, effectively realizing interpretable RUL predictions under uncertainty using only sparse raw image sequences as input. Evaluated on fatigue-loaded composite samples showcasing crack propagation, ISTRUST interprets the relation between cracks and RUL via the attention mechanism. The results substantiate its capacity to interpret and clarify instances in which predictions may exhibit variability in accuracy. Through the attention mechanism, a strong correlation between the model’s spatiotemporal focus and the RUL predictions is established, making it, to the best of our knowledge, the first model to provide interpretable stochastic RUL predictions directly from sequential images of this nature.

Fatigue Crack and Residual Life Prediction Based on an Adaptive Dynamic Bayesian Network

Monitoring the health status of aerospace structures during their service lives is a critical endeavor, aimed at precisely evaluating their operational condition through observation data and physical modeling. This study proposes a probabilistic assessment approach utilizing Dynamic Bayesian Networks (DBNs), enhanced by an improved adaptive particle filtering technique. This approach combines physical modeling with various predictive sources, encompassing cognitive uncertainties inherent in stochastic predictions and crack propagation forecasts. By employing crack observation data, it facilitates predictions of crack growth and the residual life of metal structure. To demonstrate the efficacy of this method, the research leverages data from three-point bending and single-edge tension fatigue tests. It gathers data on crack length during the fatigue crack progression, integrating these findings with digital twin theory to forecast the residual fatigue life of the specimens. The outcomes show that the adaptive DBN model can precisely predict fatigue crack propagation in test specimens, offering a potential tool for the online health assessment and life evaluation for aerospace structures.

Characterization of SOL profiles and turbulence in ICRF-heated plasmas in EAST

Scrape-off layer (SOL) profiles and turbulence in ion cyclotron range of frequency (ICRF)-heated plasmas are investigated by the reciprocating probe diagnostic system (FRPs) and gas puff imaging (GPI) diagnostic in EAST. A radio-frequency (RF) sheath potential reaching up to 100 V is identified proximate to the ICRF antennas. Notably, the amplitude of this RF sheath potential escalates in response to rising ICRF power and inversely with plasma density. When a RF sheath is present in the far SOL, a pronounced density ‘shoulder’ forms in front of the ICRF antennas, while the ‘shoulder’ fade away as the antenna and associated RF sheath shift outwards. A strong E r shear is revealed by measurements from both FRPs and GPI. Analysis of the poloidal wave number-frequency spectrum reveals suppression of high-frequency turbulence in the far SOL due to the RF sheath. This effect is manifested in the reduced autocorrelation time τ c and reduced average blob size δ blob of the SOL plasma. Intriguingly, the poloidal propagation direction of the low-frequency turbulence reverses from the electron to the ion diamagnetic drift direction at the RF sheath location. A surge of tungsten impurity is potentially attributed to the heightened interaction between the SOL plasmas and the wall material. Shifting the ICRF antennas outward, to alleviate heat spots, results in the relocation of the RF sheath to the shaded region of the main limiter. This shift amplifies the radial velocity of blobs in the far SOL and concurrently diminishes the SOL density when compared to conditions without ICRF injection. The properties of ion saturation current fluctuations are consistent with the stochastic model predictions.

Implementing policies and predictive stochastic models to attend to borderline personality disorder crises: rationalising ssri antidepressants prescription in suicide prevention

Introduction We are facing increased suicide attempts and deliberate self-harm from persons with borderline personality disorder (BPD) who are also on antidepressants, multiple antidepressant prescriptions and antidepressant augmentations. Our previous observations suggest that antidepressants might increase suicide attempts in those on this medication and who have BPD. The absent response to antidepressants is due mainly to the comorbid dysthymia, cyclothymia, rumination, autism and ADHD in BPD.ObjectivesTo generate forecasting models and preventive policies to deal with BPD crises and improve the effectiveness of the UK National Healthcare Service (NHS) in suicide prevention.MethodsThe underlying analysis framework is stochastic forecasting. We used current knowledge and data to complete systematic future predictions extracted from recent trends. A logical-mathematical model generated the required expressions. The software for logic prediction and annotation was Wolfram Alpha (Wolframalpha.com). The four parameters for stochastic predictions are, BPD (A), antidepressant No. 1 (B), antidepressant No. 2 (C), and suicide attempts (D). Boolean function metrics can help analyse the impact and truth of forecast modelling with truth density.ResultsThe logic expression for suicide prediction due to liberal antidepressant prescribing is Ψ = A intersects B, intersects C, intersects D; that is,. Ψ = A ∩ B ∩ C ∩ D, which yields a Boolean truth density of 6.25%. The truth table always has a positive outcome as long as any of the factors exist except when none is present.ConclusionsThe predictive Boolean function and truth table suggest that suicide presentation is predictable if there is a prescribing of one or more antidepressants in BPD and if there is an antidepressant augmentation or dose maximisation. We speculate that SSRI antidepressants block self-regulatory mechanisms of fear of death while triggering impulses to self-harm and suicide from overstimulation of SSRI receptors. Without fear mechanisms, death by suicide is felt as not terrifying.Disclosure of InterestNone Declared

Projecting environmental impacts with varying population, affluence and technology using IPAT – Climate change and land use scenarios

We theoretically explore the interrelations between population (P), affluence (A) and technology (T) for various environmental impacts (I ) using IPAT-type modelling. To illustrate the differences across environmental dimensions, climate and land use impacts are modelled. We use middle-of-the-road projections for population and per capita income and different forecasting methods for technology, including extrapolations of historical trends, models based on stochastic IPAT (STIRPAT) and predictions in the literature. The different approaches are compared within the IPAT framework. We also explore the consequences of alternative trajectories for P, A and T, and we discuss the implications of these trajectories for reaching global goals based on our modelling. The findings are analysed in light of three theories in environmental sociology, each of which places a different emphasis on the different components of IPAT. We argue that the large amount of technological mitigation assumed in many forecasts makes affluence and population relatively irrelevant for climate change. However, we also consider it likely that both factors will be determinants of land use impact in the 21st century.

Stochastic effects on solution landscapes for nematic liquid crystals

ABSTRACT We study the effects of additive and multiplicative noise on the solution landscape of nematic liquid crystals confined to a square domain within the Landau-de Gennes framework, as well as the impact of additive noise on the symmetric radial hedgehog solution for nematic droplets. The introduction of random noise can be used to capture material uncertainties and imperfections, which are always present in physical systems. We implement random noise in our framework by introducing a Q -Wiener stochastic process to the governing differential equations. On the square, the solution landscape for the deterministic problem is well understood, enabling us to compare and contrast the deterministic predictions and the stochastic predictions, while we demonstrate that the symmetry of the radial hedgehog solution can be violated by noise. This approach of introducing noise to deterministic equations can be used to test the robustness and validity of predictions from deterministic liquid crystal models, which essentially capture idealised situations.

Probabilistic-Mechanistic Evaluation of a Hybrid Drying System Using l1 Norm Regularisation: Simultaneous Ohmic Heating and Convection Drying

Ohmic-assisted drying (OAD) is a novel drying system that combines ohmic heating and convection drying simultaneously. The present study is aimed at evaluating the mechanism of OAD system behaviours against the combined impact of operational and model uncertainties. Moreover, the dynamic (time-dependent), as well as static (end-of-drying) spatial homogeneity of the model predictions, was quantitatively described for the first time in the literature using Buzas and Gibson’s evenness value (an α-diversity index). The Monte Carlo simulation approach was used to propagate the uncertainty of randomly selected input variables using the Halton sequence sampling method. Mechanistic models include input uncertainties that lead to deviations in model estimations. Both time-dependent and independent global sensitivity of moisture, sample temperature, sample’s internal pressure, their spatial homogeneity, and drying time were assessed using Lasso regression (a variable selection method that penalises the coefficients using l1 norm). The stochastic results of the mechanistic investigation showed that the effects of the input variables are almost identical both as static and time-dependent variables. Lasso regression results indicated that operational and model uncertainties cause varying changes in the magnitude and direction of the stochastic model predictions throughout the process. By contrast, the homogeneity properties of the dry product are not caused by these variations and heterogeneous distribution of the electric field. Additionally, electrical conductivity, oven temperature, applied voltage, and initial moisture were found to be the variables which have the most significant effect on all the variables which were examined in terms of operational and model uncertainties. Practical Applications. The present study investigates the stochastic behaviour of the OAD system through the mechanistic model and using a probabilistic modelling approach. To the best of our knowledge, in addition to being the first study to probabilistically evaluate the OAD system, we are introducing Buzas and Gibson’s evenness value for the first time in the food science/technology literature. This measure serves as a numerical indicator of the spatial distribution homogeneity of the physical properties of the sample. The study’s findings and proposed methodologies will have further applications not only for researchers but also for manufacturers, particularly for those involved in the design and analysis of new drying and food systems in general. Moreover, the presented methods and novel homogeneity measures are generic tools; they can be easily adapted to other process improvement practices involving input/output uncertainty/variability.

Enhanced quantum state preparation via stochastic predictions of neural networks

Enhanced quantum state preparation via stochastic predictions of neural networks

Data-driven predictive control for demand side management: Theoretical and experimental results

Demand side management is perceived as a tool to support a secure and reliable energy system operation amid growing integration of renewable energy resources. However, the lack of scalable modeling and control procedures hinders the practical implementation. To address this challenge, this paper proposes a novel signal matrix model predictive control algorithm. Compared to existing data-driven methods, this approach explicitly provides stochastic predictions considering both disturbance and measurement errors with few tuning parameters, ensuring reliability by high-probability constraint satisfaction. The performance is extensively compared with three state-of-the-art algorithms in a space heating case study using a high-fidelity simulator. The results are further validated with physical experiments using the same system that the simulator is based on. To assess transferability, the algorithm is further implemented on diverse controlled systems, including a domestic hot water heating system and a stationary electric battery. The simulation results show that, compared to existing data-driven methods, the proposed approach improves constraint satisfaction and energy savings by up to 90 % and 8 %, respectively. The experimental results further confirm that the algorithm is applicable to multiple tasks of demand side management, with reasonable control performance observed in all case studies.

Kernel mixed and Kernel stochastic restricted ridge predictions in the partially linear mixed measurement error models: an application to COVID-19

ABSTRACT In this article, we define mixed predictor and stochastic restricted ridge predictor of partially linear mixed measurement error models by taking advantage of Kernel approximation. Under matrix mean square error criterion, we make the comparison of the superiorities the linear combinations of the new defined predictors. Then we investigate the asymptotic normality characteristics and the situation of the unknown covariance matrix of measurement errors. Finally, the study is ended with a Monte Carlo simulation study and COVID-19 data application.

Trust-based Performance Optimization for Human-Swarm Collaboration

This work develops a trust inference model to address scenarios where agents in a swarm collaborate to achieve the coverage control task. To gather empirical data from human subjects for the probabilistic model development, we build various simulation tools and user interfaces. Using our visual training tool, we train a single-agent model and then extend that to create our multi-agent model. These models utilize a dynamic Bayesian network and produce stochastic predictions. We then apply these models to our Voronoi-based area coverage problem in real time, where agents adjust their behavior to maximize the team performance and hence human trust. As a result of this research, multi-agent teams will be able to increase their individual trust levels thereby enhancing team performance and efficiency.

Addressing the different sources of excitation variability in seismic response distribution estimation using kriging metamodeling

AbstractThis paper investigates the impact of the different sources of excitation variability within the stochastic kriging framework recently developed by the authors for the estimation of the distribution of engineering demand parameters (EDPs) in applications that the seismic hazard is described through stochastic ground motion models. For a given seismic event, described by seismicity characteristics such as the moment magnitude and the distance to source, one can distinguish two type of uncertainties in the excitation description: (g.i) the stochastic sequence utilized within the excitation model; (g.ii) the predictive models relating the ground motion parameters, such as significant duration, arias intensity, or frequency properties of seismic waves, to the seismicity characteristics. The original formulation of the authors treats (g.i) as aleatoric uncertainty and (g.ii) as parametric uncertainty, including the latter in the model parameters for the risk characterization, representing the metamodel input. Implementation establishes the EDP distribution approximation by utilizing a database of EDP estimates for a set of different input parameters, considering replications of these estimates for different stochastic sequences for some small part of this database. The database with replications is first leveraged to approximate the heteroscedastic behavior with respect to the aleatoric uncertainty, and the entire database is subsequently used, coupled with the previous heteroscedasticity approximation, to establish the stochastic kriging predictions for the EDP distribution. For excitation models with a large number of ground motion parameters, the original formulation leads to a significant increase of the input dimensionality for the metamodel development, requiring a larger database for facilitating accurate EDP approximations. Here, an alternative formulation is investigated, considering some (or perhaps even all) of the ground motion parameters to be part of the aleatoric uncertainty of the excitation description. It is shown that careful selection is needed for the exact ground motion parameters that can be treated as part of this aleatoric uncertainty, to accommodate an accurate overall EDP approximation. Similarities are discussed for applications that consider the description of the seismic hazard through the selection of ground motions based on intensity measures. An extensive validation of this new approach is presented considering two different stochastic ground motion models.

Effects of the microstructural uncertainties on the poroelastic and the diffusive properties of mortar

The assessment of the durability of civil engineering structures subjected to several chemical attacks requires the development of chemo-poromechanical models. The mechanical and chemical degradations depend on several factors such as the initial composition of the porous medium. A multi-scale model is used to incorporate the multi-level microstructural properties of the mortar material. The present paper aims to study the effect of morphological and local material properties uncertainties on the poroelastic and diffusive properties of mortar estimated with the help of analytical homogenization. At first, the proposed model is validated for different cement paste and mortar by comparison to experimental results and micromechanical models. Secondly, based on a literature study, sensitivity and uncertainty analysis have been developed to assess the stochastic predictions of the multi-scale model. The main result highlights the predominant impact of the cement matrix phases (C-S-H) and interfacial transition area at the mortar scale. Furthermore, the sensitive analysis underlines that the material properties induce more variability than the volume fraction.

A real-time data assimilative forecasting system for animal tracking.

Monitoring technologies now provide real‐time animal location information, which opens up the possibility of developing forecasting systems to fuse these data with movement models to predict future trajectories. State‐space modeling approaches are well established for retrospective location estimation and behavioral inference through state and parameter estimation. Here we use a state‐space model within a comprehensive data assimilative framework for probabilistic animal movement forecasting. Real‐time location information is combined with stochastic movement model predictions to provide forecasts of future animal locations and trajectories, as well as estimates of key behavioral parameters. Implementation uses ensemble‐based sequential Monte Carlo methods (a particle filter). We first apply the framework to an idealized case using a nondimensional animal movement model based on a continuous‐time random walk process. A set of numerical forecasting experiments demonstrates the workflow and key features, such as the online estimation of behavioral parameters using state augmentation, the use of potential functions for habitat preference, and the role of observation error and sampling frequency on forecast skill. For a realistic demonstration, we adapt the framework to short‐term forecasting of the endangered southern resident killer whale (SRKW) in the Salish Sea using visual sighting information wherein the potential function reflects historical habitat utilization of SRKW. We successfully estimate whale locations up to 2.5 h in advance with a moderate prediction error (<5 km), providing reasonable lead‐in time to mitigate vessel–whale interactions. It is argued that this forecasting framework can be used to synthesize diverse data types and improve animal movement models and behavioral understanding and has the potential to lead to important advances in movement ecology.

New England Shelf Break Acoustic (NESBA) experiment: Stochastic acoustic prediction

Sonar performance prediction has been a topic of interest for decades. Predictions are based on acoustic propagation modeling that is typically deterministic, i.e., lacking quantified confidence or uncertainty bounds. While this may be adequate in some locations, in oceanographically complex regions it can result in misleading predictions and conclusions that sonar performance predictions are unreliable. A better approach includes explicit calculations of the underlying source, receiver, and environmental uncertainties to provide a prediction confidence level. In oceanographically complex areas, the resulting uncertainties are likely to be high; however, knowledge of this allows uncertainties to be managed. The NESBA Signals and Noise experiment was conducted in April–May 2021. The goal of the experiment was to assess the potential for sonar prediction effectiveness gains given improved environmental awareness. This talk addresses the NESBA sub-goal of demonstrating that high-resolution ocean modeling with ensemble forecasts (in this case, Regional NCOM) could be leveraged for stochastic acoustic predictions, resulting in increased accuracy in performance predictions with quantified uncertainty bounds. NESBA results will be presented leveraging the high-resolution ocean model forecasts with ensembles run concurrently with NESBA and the numerous temperature/salinity profiles taken during the experiment. [Work supported by the Office of Naval Research.]

Capturing Regional Differences in Flood Vulnerability Improves Flood Loss Estimation

Flood vulnerability is quantified by loss models which are developed using either empirical or synthetic approaches. In reality, processes influencing flood risk are stochastic and loss predictions bear significant uncertainty, especially due to differences in vulnerability across exposed objects and regions. However, many state-of-the-art flood loss models are deterministic, i.e., they do not account for data and model uncertainty. The Bayesian Data-Driven Synthetic (BDDS) model was one of the first approaches that used empirical data to reduce the prediction errors at object-level and enhance the reliability of synthetic flood loss models. However, the BDDS model does not account for regional differences in vulnerability which may result in over-/under-estimation of losses in some regions. In order to overcome this limitation, this study introduces a hierarchical parameterization of the BDDS model which enhances synthetic flood loss model predictions by quantifying regional differences in vulnerability. The hierarchical parameterization makes optimal use of the process information contained in the overall data set for the various regional applications, so that it is particularly suitable for cases in which only a small amount of empirical data is available. The implementation and performance of the hierarchical parametrization is demonstrated with the Multi-Colored Manual (MCM) loss functions and empirical damage dataset from the UK consisting of residential buildings from the regions Appleby, Carlisle, Kendal and Cockermouth that suffered losses during the 2015 flood event. The developed model improves prediction accuracy of flood loss compared to MCM by reducing the absolute error and bias by at least 23 and 90%, respectively. The model reliability in terms of hit rate (i.e., the probability that the observed value lies in the 90% high density interval of predictions) is 88% for residential buildings from the same regions used for calibration and 73% for residential buildings from new regions. The approach is of high practical relevance for all regions where only limited amounts of empirical flood loss data is available.

Differentiable Predictions for Large Scale Structure with SHAMNet

In simulation-based models of the galaxy-halo connection, theoretical predictions for galaxy clustering and lensing are typically made based on Monte Carlo realizations of a mock universe. In this paper, we use Subhalo Abundance Matching (SHAM) as a toy model to introduce an alternative to stochastic predictions based on mock population, demonstrating how to make simulation-based predictions for clustering and lensing that are both exact and differentiable with respect to the parameters of the model. Conventional implementations of SHAM are based on iterative algorithms such as Richardson-Lucy deconvolution; here we use the JAX library for automatic differentiation to train SHAMNet, a neural network that accurately approximates the stellar-to-halo mass relation (SMHM) defined by abundance matching. In our approach to making differentiable predictions for large scale structure, we map parameterized PDFs onto each simulated halo, and calculate gradients of summary statistics of the galaxy distribution by using autodiff to propagate the gradients of the SMHM through the statistical estimators used to measure one- and two-point functions. Our techniques are quite general, and we conclude with an overview of how they can be applied in tandem with more complex, higher-dimensional models, creating the capability to make differentiable predictions for the multi-wavelength universe of galaxies.

An alternative simulation framework to evaluate the sustainability of annual harvest on large forest estates

Sustainability is central to forest management. To determine the sustainable annual harvest, practitioners rely on a simulation framework that combines inventory data, growth models, and optimization software. Because this standard simulation framework is based on model predictions aggregated into yield tables, it may not properly capture natural dynamics. In this paper, we designed an alternative simulation framework that does not require aggregated model predictions. However, the growth model must implement a harvest submodel and produce stochastic predictions. To showcase this alternative simulation framework, we used a forest management unit in southwestern Quebec, Canada, and compared our simulation results with those of the standard simulation framework. Our alternative simulation framework showed that the standing volume of most coniferous species would decrease, whereas that of maple species would increase over the 21st century. The annual harvest of one species as determined through the standard simulation framework was found to be unsustainable in the alternative simulation framework. Being much lighter in terms of computation, this alternative simulation framework can be used as a complement to the standard simulation framework, notably for checking if the optimization-based annual harvest is sustainable.

Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication

Abstract This work presents a data-driven methodology for multi-objective optimization under uncertainty of process parameters in the fused filament fabrication (FFF) process. The proposed approach optimizes the process parameters with the objectives of minimizing the geometric inaccuracy and maximizing the filament bond quality of the manufactured part. First, experiments are conducted to collect data pertaining to the part quality. Then, Bayesian neural network (BNN) models are constructed to predict the geometric inaccuracy and bond quality as functions of the process parameters. The BNN model captures the model uncertainty caused by the lack of knowledge about model parameters (neuron weights) and the input variability due to the intrinsic randomness in the input parameters. Using the stochastic predictions from these models, different robustness-based design optimization formulations are investigated, wherein process parameters such as nozzle temperature, nozzle speed, and layer thickness are optimized under uncertainty for different multi-objective scenarios. Epistemic uncertainty in the prediction model and the aleatory uncertainty in the input is considered in the optimization. Finally, Pareto surfaces are constructed to estimate the tradeoffs between the objectives. Both the BNN models and the effectiveness of the proposed optimization methodology are validated using the actual manufacturing of the parts.

Diameter, height and volume increment single tree models for improved Sitka spruce in Great Britain

Abstract The British forestry sector lacks reliable dynamic growth models for stands of improved Sitka spruce, the most important commercial forest type in Great Britain. The aim of this study is to fill this gap by trialling a new modelling framework and to lay the foundations of a future dynamic growth simulator for that forest type. First, we present single tree diameter and height increment models that are climate sensitive and include explicit competition effects. The predictions from the increment models are pooled to project diameter and height at a given age. These projections are then used as inputs to an integrated taper model from which stochastic tree volume predictions are obtained. Retrospective data from over 1400 trees collected in two extensive genetic trials in Scotland and Wales were used for the purposes of this study. Diameter increment and height increment predictions were highly accurate and diameter and height projections proved consistent. The predicted volume at the time of harvesting also exhibited a high degree of accuracy, which shows the robustness of our approach. Further data will be needed in the future to recalibrate the present models and extend their range of validity to the whole of Great Britain.