Search

To ensure well integrity, wellbore must be strongly cased using durable cement slurries with essential additives during downhole completion. The rubber materials that come from industrial waste are becoming extremely encouraged in the use as an additive in preparing cement slurries due to their growing environmental footprint. However, the proper design of cement slurry strongly depends on its rheological, mechanical, petrophysical, and creep properties, which can be altered by changing additives. This study aimed to examine the cement properties under alteration in different chemical admixtures to create efficient binding properties, and to estimate the optimum cement–rubber slurry composition for eco-sustainable completion. Three cement samples with different mesh sizes of the crumb rubber particles were prepared. This study examined the variation in rheological behaviors, elastic and failure characteristics, permeability, and creep behavior of the cement–rubber composites for petroleum well construction. The experimental study showed that the addition of 15% or more crumb rubber to the cement resulted in very thick slurries. Moreover, it was shown that the addition of crumb rubber with various particle sizes to the cement reduced the strength by more than 50%, especially for a higher amount of rubber added. It was also revealed that the addition of a superplasticizer resulted in an 11% increase in compressive strength. The results showed that cement–crumb-rubber composites with 12% by weight of cement (BWOC) represented the optimum composite, and considerably improved the properties of the cement slurry. Water-permeability tests indicated the addition of 12% BWOC with 200-mesh crumb rubber decreased the permeability by nearly 64% compared to the base cement. Creep tests at five different stress levels illustrated that the neat cement was brittle and did not experience strain recovery at all stress levels. Cement slurries with the largest rubber-particle size were elastic and demonstrated the highest amount of strain recovery. Finally, a relationship was established between the permeability, average strain, and mesh size of the rubber particles, which offered the strain recovery, satisfied the zonal isolation, and consequently reduced the microannulus problem to ensure the cement's integrity. [ABSTRACT FROM AUTHOR]

Examines the approach for measuring and estimating running force for laboratories and field conditions. Description of experimental and simulation procedures of rod and pipe sizes; Significance of the radius of curvature, hole clearance and contact scenario on the running force; Evidence of elastic and plastic deformation of pipes.

This paper introduces an innovative approach to Wind Turbine Blade (WTB) inspection through the synergistic use of thermal and RGB imaging, coupled with advanced deep learning techniques. We curated a unique dataset of 1000 thermal images of healthy and faulty blades using a FLIR C5 Compact Thermal Camera, which is equipped with Multi-Spectral Dynamic Imaging technology for enhanced imaging. This paper focuses on evaluating 35 deep learning classifiers, with a standout ensemble model combining Vision Transformer (ViT) and DenseNet161, achieving a remarkable 100% accuracy on the dataset. This model demonstrates the exceptional potential of deep learning in thermal diagnostic applications, particularly in predictive maintenance within the renewable energy sector. Our findings underscore the synergistic combination of ViT's global feature analysis and DenseNet161's dense connectivity, highlighting the importance of controlled environments and sophisticated preprocessing for accurate thermal image capture. This research contributes significantly to the field by providing a comprehensive dataset and demonstrating the efficacy of several deep learning models in ensuring the operational efficiency and reliability of wind turbines. [ABSTRACT FROM AUTHOR]

The ability to train a network without memorizing the input/output data, thereby allowing a good predictive performance when applied to unseen data, is paramount in ANN applications. In this paper, we propose a frequency-domain approach to evaluate the network initialization in terms of quality of training, i.e., generalization capabilities. As an alternative to the conventional time-domain methods, the proposed approach eliminates the approximate nature of network validation using an excess of unseen data. The benefits of the proposed approach are demonstrated using two numerical examples, where two trained networks performed similarly on the training and the validation data sets, yet they revealed a significant difference in prediction accuracy when tested using a different data set. This observation is of utmost importance in modeling applications requiring a high degree of accuracy. The efficiency of the proposed approach is further demonstrated on a real-world problem, where unlike other initialization methods, a more conclusive assessment of generalization is achieved. On the practical front, subtle methodological and implementational facets are addressed to ensure reproducibility and pinpoint the limitations of the proposed approach. [ABSTRACT FROM AUTHOR]