Learning Curve Extrapolation using Machine Learning: Benefits and Limitations of using LCPFN for Learning Curve Extrapolation

This study explores the extrapolation of learning curves, a crucial aspect in evaluating learner performance with varying dataset sample sizes. We use the Learning Curve Prior Fitted Network (LC-PFN), a transformer pre-trained on synthetic data with proficiency in approximate Bayesian inference, to investigate its predictive accuracy using the...

Simulation of the Overall Performance of Glazed Unitised Curtain Walls Under Seismic Action Through Finite Element Modelling and Validation via Full-scale Experimental Testing

Although relevant information regarding the curtain walls structural damage state is available, hardly any data referring to the seismic loading effect on the overall façade performance is found in the literature. The present research attempts to assess the unitised curtain walls seismic performance by identifying the occurring damage mechanisms...

Understanding Risk Extrapolation (REx) and when it finds Invariant Relationships

Generalizing models for new unknown datasets is a common problem in machine learning. Algorithms that perform well for test instances with the same distribution as their training dataset often perform severely on new datasets with a different distribution. This problem is caused by distributional shifts between the training of the model and...

Error-estimate based adaptive mesh refinement: A user-independent approach for LES

Computational fluid dynamics (CFD) has become an indispensable tool in research and engineering. Even though the performance of computers is increasing at unfathomable speeds, the calculation of many fluid problems remains to be challenging. With the emerging widespread use of Large Eddy Simulation (LES), the computational cost of simulations...

Core Analysis and Well Data Interpretation for Facies Extrapolation with a focus on coals and coarse sand in the Carboniferous of the Southern North Sea

In 1990, the 44/21a-6 well was drilled in the Southern North Sea. Core material was taken from the Westphalian A/B part of the core. Some of this core material was recently obtained by the TU Delft via the North Sea Core Initiative. Since the Westphalian A/B in the Pennine Basin is fluvio-deltaic in origin, it is highly variable both vertically...

Investigation of methods for Extrapolation & Interpolation of Radial Compressor & Turbine Performance maps

The project focuses on developing and implementing a 0D or 1D model for radial compressors and turbines, capable of both interpolating and extrapolating the performance maps. The proposed model will be calibrated using the data points available in the maps provided by the manufacturers to produce accurate mass flow for turbines and pressure...

De Extrapolatie Stelling van Yano

In dit verslag behandelen we de Extrapolatie Stelling van Yano: een stelling die voor operators van de vorm T : f(x) -> T(f)(x) in bepaalde omstandigheden een afschatting geeft van de absolute integraal over T(f)(x) in termen van f(x) zelf. We zullen zien dat deze afschatting, en meer afschattingen van soortgelijke vorm, onder de juiste...

Fatigue Assessment of Offshore Wind Turbines Using Measurements of Individual Turbines and Machine Learning Techniques

Fatigue is often a governing design factor for offshore wind turbines. Since the design of offshore wind turbines includes conservatism, the actual accumulated fatigue damage can be lower than what the turbine is designed for. In this case, the operator can make a decision on life time extension of existing wind turbines. Therefore, it is...

A Smart Home – Analysis and Scheduling

In order to cope with various supply sources and loads in an autonomous micro-grid, a system of sensors and control units was developed. The goals were to cope efficiently in the event of an energy supply shortage, and to prevent such events as much as possible. To achieve these goals the aim was to manage energy in the system as efficiently as...

Accelerating Google PageRank by applying Aitken Extrapolation and Quadratic Extrapolation

Google PageRank is an algorithm incorporated by Google to rank websites, using the amount of links a website has as well as the importance of each link. This process can be calculated using the power method. As the amount of websites grows it is essential to speed up this process. Two extrapolation methods, Aitken Extrapolation and Quadratic...

The Reconstruction of Missing Marine Seismic Data

To evaluate the subsurface, seismic surveys are carried out. A requirement for the processing of these data is that it is dense and regularly sampled and it should also include the near-offsets. Because these data cannot be acquired in practice for towed marine surveys, it should be obtained by inter- and extrapolation. The first objective of...

A Policy Analysis for CRS Reprocessing in China