Aircraft design requires extensive aerodynamic data to characterize various flight conditions throughout the aircraft's flight envelope. Typically, the aerodynamic data is acquired through wind tunnel testing or n...
详细信息
Aircraft design requires extensive aerodynamic data to characterize various flight conditions throughout the aircraft's flight envelope. Typically, the aerodynamic data is acquired through wind tunnel testing or numerical analysis, which are costly and inevitably entails multiple sources of uncertainty. In the present work, we propose a multi-fidelity Bayesian neural network (MFBNN) framework for multi-source aerodynamic data fusion with heterogeneous uncertainties. We first employ mean-field variational inference (VI) to maximize the evidence lower bound (ELBO), yielding informative priors for BNN hyperparameters. Then, the stochastic Hamiltonian Monte Carlo (HMC) method is adopted to estimate their posteriors. Notably, we introduce mini-batch learning to address a key constraint of traditional HMC methods, particularly in the aerodynamic modeling scenarios involving large sample sizes, where the computation of required gradients for simulation of the Hamiltonian dynamical system is impractical. The proposed MFBNN framework is applied in three cases, including the RAE2822 airfoil, the ONERA M6 wing and the NASA Common Research Model. The results demonstrate that the proposed MFBNN framework can remarkably improve accuracy and outperform the multi-fidelity Gaussian process regression model.
The prospective utilization of electrospun nanofibers across diverse fields has elicited substantial scientific attention. Nevertheless, managing their diameter remains problematic due to the intricate interactions am...
详细信息
The prospective utilization of electrospun nanofibers across diverse fields has elicited substantial scientific attention. Nevertheless, managing their diameter remains problematic due to the intricate interactions among electrospinning variables. This research explores the application of Long Short-Term Memory (LSTM) networks and multiple regression models to forecast the diameters of Titanium Dioxide (TiO2) and Polyvinyl pyrrolidone (PVP) nanofibers, facilitating improved process regulation and enhancement. TiO2 + PVP nanofibers were fabricated under diverse conditions, including changes in applied voltage, solution concentration, and distance between tip to collector. The acquired data underwent analysis using LSTM and regression models to assess their predictive capabilities. The outcomes revealed that both approaches effectively estimated nanofiber diameters;however, the regression model surpassed LSTM with a lower error rate of 0.077% compared to 0.305%. This indicates that while LSTM captures nonlinear relationships, conventional regression models yield more precise predictions in this scenario. These findings underscore the potential of machine learning in advancing electrospinning technology by minimizing trial-and-error experiments and boosting nanofiber production efficiency. The incorporation of artificial intelligence-driven modeling into the electrospinning process sets the stage for more accurate control over fiber morphology, resulting in enhanced material properties and expanded applications in biomedical, environmental, and energy sectors.
controlling groundwater levels is essential for the safe construction of complex or high-rise buildings. In M & eacute;xico, dewatering regulations lack detailed references, and piezometric data are limited, makin...
详细信息
controlling groundwater levels is essential for the safe construction of complex or high-rise buildings. In M & eacute;xico, dewatering regulations lack detailed references, and piezometric data are limited, making precise groundwater control a challenge. This study aimed to develop a numerical groundwater model by translating a conceptual hydrogeological model into a calibrated MODFLOW simulation using the graphical user interface ModelMuse, developed by the United States Geological Survey (USGS). For the project "Torre Tres R & iacute;os", field measurements recorded a water-table level of 33 m above sea level (masl) in July, rising to 35.74 masl in October due to rainy season recharge and the influence of the Tamazula River, then decreasing to 35.20 masl in November. The model, calibrated with a mean absolute error of 0.15 m and a standard deviation of 0.174 m, effectively represented steady and transient states. A spatiotemporal analysis based on the calibrated numerical model enabled the evaluation of different dewatering scenarios. Initially, deep wells with a pumping rate of 120 L per second (lps) were required for dewatering;however, a wellpoint system was proposed, showing improved performance with a reduced impact on groundwater flow and the surrounding environment during the critical August-November period. This study highlights the importance of numerical modeling in refining dewatering system designs, ensuring adaptability to fluctuating groundwater conditions. By providing a methodology for optimizing dewatering strategies, it contributes to more efficient and sustainable construction practices in regions with complex hydrogeological conditions.
Industries involved with process and manufacturing plants require a sound system and process to ensure the outcome of products they produce are of excellent quality, can be ready quickly, and consume minimal operating...
详细信息
The general purpose of this study is to investigate the technological data collected during the operation of a multizone heating furnace by an automated control system (ACS). The certain aim is to develop a mathematic...
详细信息
Accurate and efficient fault root cause diagnosis is an effective means to prevent major accidents in industrial systems. Due to the difficulty of modeling complex systems, Granger causal analysis is widely used. Root...
详细信息
ISBN:
(纸本)9798350321050
Accurate and efficient fault root cause diagnosis is an effective means to prevent major accidents in industrial systems. Due to the difficulty of modeling complex systems, Granger causal analysis is widely used. Root cause diagnosis in the shortest possible time after a fault occurs can improve the accuracy of diagnostic results. Due to the strong nonlinear relationship in the short observation data, this paper introduces Generalized Radial Basis Function(GRBF) neural network of the nonlinear dimensionality reduction method into the Granger causal model to realize the root cause diagnosis of Granger faults based on the nonlinear short observation data. The effectiveness of the proposed method is verified by numerical simulation and fault diagnosis experimental study of Tennessee Eastman,(TE) chemical process. The results show that the proposed method improves the processing ability of Granger causal analysis for nonlinear causality, and can use a small amount of the fault data to complete accurate fault root cause diagnosis.
In engineering informatics, the myriad data types, formats, streaming and storage technologies pose significant challenges in managing data effectively. The problem grows, as new analytics perspectives are emerging fr...
详细信息
ISBN:
(纸本)9783031610066;9783031610073
In engineering informatics, the myriad data types, formats, streaming and storage technologies pose significant challenges in managing data effectively. The problem grows, as new analytics perspectives are emerging from a totally different AI-based tradition. This divide often necessitates the development of custom solutions that link specific data capture methods to particular AI algorithms. Encouraged by the success of object-centric mining models for discrete processes, we look for large clusters of data management practices where novel bridging data models can help navigate the data model divide. We address this question in a two-cycle design science approach. In a first cycle, over 80 actual data model practices from a wide variety of engineering disciplines were analyzed, leading to four candidate fields. In a second cycle, an initial bridging data model for one of these fields was developed and validated wrt some of the found practices. Our findings offer the prospect of significantly streamlining data pipelines, paving the way for enriched AI integration in production engineering, and consequently, a more robust, data-driven manufacturing paradigm.
H-infinity control for nonlinear systems with uncertain, time-varying delays stands as a vital control methodology for managing the complexities inherent in such systems. This approach is frequently employed to addres...
详细信息
ISBN:
(纸本)9798331540845;9789887581598
H-infinity control for nonlinear systems with uncertain, time-varying delays stands as a vital control methodology for managing the complexities inherent in such systems. This approach is frequently employed to address challenges associated with uncertain systems experiencing time delays. In practical applications, the implementation of H-infinity control often leads to enhancements in system stability and robustness. Rooted in the H-infinity norm, this control design method aims to optimize the stability margin of the system. Typically, the steps involved in this process encompass system modeling, performance index selection, controller design, and subsequent performance analysis. Given the inherent complexity of such systems, it is essential to employ appropriate mathematical tools and control strategies to ensure that the controller maintains optimal performance across varying operational conditions. H-infinity control emerges as a potent solution capable of addressing a wide array of complex systems, including nonlinear systems plagued by uncertain time-varying delays. Through prudent controller design, significant improvements in system performance and stability can be achieved, thereby enabling the system to operate seamlessly despite the presence of uncertainty and time delay.
Gaussian process state space models are becoming common tools for the analysis and design of nonlinear systems with uncertain dynamics. When designing control policies for these systems, safety is an important propert...
ISBN:
(纸本)9798350301243
Gaussian process state space models are becoming common tools for the analysis and design of nonlinear systems with uncertain dynamics. When designing control policies for these systems, safety is an important property to consider. In this paper, we provide safety guarantees by computing finite-horizon forward reachable sets for Gaussian process state space models. We use data-driven reachability analysis to provide exact probability measures for state trajectories of arbitrary length, even when no data samples are available. We investigate two numerical examples to demonstrate the power of this approach, such as providing highly non-convex reachable sets and detecting holes in the reachable set.
Abstract: analysis of the features of modern power-supply systems and the increasing requirements of consumers to electric-power-quality indicators (EPQIs) at the point of connection of electrical installations (elect...
详细信息
暂无评论