Search

The paper shows the feasibility of building closed-form and fast-to-evaluate surrogate models via supervised kernel-based machine learning regressions behaving as digital twins for computationally expensive multibody simulations. The aforementioned surrogate models are adopted to predict the railway vehicle dynamics safety indexes defined in the international standards, depending on the wheel-rail forces, directly from the results of longitudinal train dynamics simulations. The digital twin models are trained with the outputs of Simpack multibody simulations of a reference freight wagon, to which the in-train forces calculated by an in-house MATLAB longitudinal train dynamics simulator are applied. Two machine learning techniques are considered: the support vector machine and the least-squares support vector machine regressions. Both techniques ensure a good accuracy even with a limited number of training samples. The derivation of the surrogate models can strongly enhance the modelling capabilities of common longitudinal train dynamics simulators, that cannot evaluate the wheel-rail contact forces. At the same time, the method shown in the paper allows to strongly reduce the total computational times, as the evaluation of the closed-form surrogate models allows to effectively estimate the safety indexes with no need for computationally demanding multibody simulations. [ABSTRACT FROM AUTHOR]

Robotic systems have become a standard tool in modern manufacturing due to their unique characteristics, such as repeatability, precision, and speed, among others. One of the main challenges of robotic manipulators is the low degree of reliability. Low reliability increases the probability of disruption in manufacturing processes, minimizing in this way the productivity and by extension the profit of the company. To address the abovementioned challenges, this research work proposes a robotic cell reliability optimization method based on digital twin and predictive maintenance. Concretely, the simulation of the robot is provided, and emphasis is given to the reliability optimization of the robotic cell's critical component. A supervised machine learning model is trained, aiming to detect and classify the faulty behavior of the critical component. Furthermore, a framework is proposed for the remaining useful life prediction with the aim to improve the reliability of the robotic cell. Thus, following the results of the current research work, appropriate maintenance tasks can be applied, preventing the robotic cell from serious failures and ensuring high reliability. [ABSTRACT FROM AUTHOR]

The goal of this work is to achieve the defect-free production of parts made using Additive Manufacturing (AM) processes. As a step towards this goal, the objective is to detect flaws in AM parts during the process by combining predictions from a physical model (simulation) with in-situ sensor signatures in a machine learning framework. We hypothesize that flaws in AM parts are detected with significantly higher statistical fidelity (F-score) when both in-situ sensor data and theoretical predictions are pooled together in a machine learning model, compared to an approach that is based exclusively on machine learning of sensor data (black-box model) or physics-based predictions (white-box model). We test the hypothesized efficacy of such a gray-box model or digital twin approach in the context of the laser powder bed fusion (LPBF) and directed energy deposition (DED) AM processes. For example, in the DED process, we first predicted the instantaneous spatiotemporal distribution of temperature in a thin-wall titanium alloy part using a computational heat transfer model based on graph theory. Subsequently, we combined the preceding physics-derived thermal trends with in-situ temperature measurements obtained from a pyrometer in a readily implemented supervised machine learning framework (support vector machine). We demonstrate that the integration of temperature predictions from an ab initio heat transfer model and in-situ sensor data is capable of detecting flaws in the DED-produced thin-wall part with F-score approaching 90%. By contrast, the F-score decreases to nearly 80% when either temperature measurements from the in-situ sensor or temperature distribution predictions from the theoretical model are used alone by themselves. This work thus demonstrates an early foray into the digital twin paradigm for real-time process monitoring in AM via seamless integration of physics-based modeling (simulation), in-situ sensing, and data analytics (machine learning). [ABSTRACT FROM AUTHOR]

High dimensional quantum entanglement based on orbital angular momentum (OAM) can provide infinite freedom theoretically, providing a significant improvement on the capacity of the quantum communication. However, the vortex beam that carries OAM signal can be easily distorted by atmospheric turbulence and can degrade the performance of the system. Consequently, for the operation, administration and maintenance of quantum system, an accurate digital twin model of the turbulent channel is necessary. Digital twin model is a mathematical model which can reflect the influence of atmospheric channel on quantum system by theoretical analysis. Nevertheless, it is challenging to achieve for the complex mechanism of atmospheric turbulence. To address this problem, deep learning (DL) techniques have been studied recently. Whereas, for the training of DL, a massive number of labeled samples are needed, i.e., the actual free-space channel, which are hard to be obtained in practical systems. The pool generalization also hinders the use of these DL-based algorithms in practice. To overcome the above challenges, we propose a self-supervised DL algorithm, which does not need any labeled samples in advance, meaning the training of the algorithm can be restarted any time once the environment changes. Compared with previous studies, the proposed algorithm can better suite as the digital twin of the turbulent channel. To verify the performance of the proposed algorithm, we perform extensive verification, whose results demonstrate the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Distributed fiber optic sensors have exhibited superior capabilities in monitoring cracks in engineering structures through measuring detailed strain distributions. However, manually interpreting the measurements from long distributed sensors deployed in large-scale structures is time-consuming, labor-intensive, and subject to human errors. This paper proposes to automate the identification, localization, quantification, and visualization of cracks through intelligent interpretation of strain distributions measured from distributed fiber optic sensors based on machine learning. Based on these intelligent capabilities, a live digital twin model based on building information modeling is developed to visualize cracks. The digital twin model is updatable with real-time measurements from strain distributions from distributed fiber optic sensors. The proposed approach is evaluated via laboratory testing of a concrete beam. The results show that the proposed approach achieves high accuracy in interpretation of sensor data for crack monitoring. This research advances the capabilities of structural health monitoring using distributed fiber optic sensors. [Display omitted] • Automatic interpretation of strain distributions from distributed fiber optic sensors is enabled. • Machine learning approaches are presented to identify, locate, quantify, and visualize cracks. • A digital twin model is developed to visualize cracks and updated by real-time measurement. • Unsupervised and supervised learning approaches achieve high accuracy and high efficiency. [ABSTRACT FROM AUTHOR]

Metabolic engineering encompasses several widely-used strategies, which currently hold a high seat in the field of biotechnology when its potential is manifesting through a plethora of research and commercial products with a strong societal impact. The genomic revolution that occurred almost three decades ago has initiated the generation of large omics-datasets which has helped in gaining a better understanding of cellular behavior. The itinerary of metabolic engineering that has occurred based on these large datasets has allowed researchers to gain detailed insights and a reasonable understanding of the intricacies of biosystems. However, the existing trail-and-error approaches for metabolic engineering are laborious and time-intensive when it comes to the production of target compounds with high yields through genetic manipulations in host organisms. Machine learning (ML) coupled with the available metabolic engineering test instances and omics data brings a comprehensive and multidisciplinary approach that enables scientists to evaluate various parameters for effective strain design. This vast amount of biological data should be standardized through knowledge engineering to train different ML models for providing accurate predictions in gene circuits designing, modification of proteins, optimization of bioprocess parameters for scaling up, and screening of hyper-producing robust cell factories. This review briefs on the premise of ML, followed by mentioning various ML methods and algorithms alongside the numerous omics datasets available to train ML models for predicting metabolic outcomes with high-accuracy. The combinative interplay between the ML algorithms and biological datasets through knowledge engineering have guided the recent advancements in applications such as CRISPR/Cas systems, gene circuits, protein engineering, metabolic pathway reconstruction, and bioprocess engineering. Finally, this review addresses the probable challenges of applying ML in metabolic engineering which will guide the researchers toward novel techniques to overcome the limitations. [Display omitted] • Synergism of metabolic engineering and machine learning captures cell metabolism. • Machine learning towards exploring CRISPR/Cas systems have been reviewed. • Application of machine learning for robust gene circuit design has been provided. • Machine learning contributes greatly in targeted pathway and protein engineering. • Bioprocess Digital Twin helps in an improved predictability of physical processes. [ABSTRACT FROM AUTHOR]