Innovations in Applied Engineering and Technology

Experimental Study on the Performance of Frictional Drag Reducer with Low Gravity Solids

2024-03-13T10:05:48+08:00

Reducing energy consumption during drilling operations is beneficial to both the environment and economy. Frictional drag reducers (FDR) are widely used to reduce the energy loss caused by turbulent flow. FDR plays an important role in flow lines as they can reduce the frictional pressure drop effectively, and benefit the selection of circulating fluid and pump. However, several factors can influence the performance of FDR, including fluid additives and incorporated solids, such as drill solids. Thus, the main objective of this paper is to study the influence of low gravity solids (LGS) on the performance of the FDR. This paper is mainly based on experimental study. The experimental work contains two parts: rheology characterization and flow loop tests. Rheology characterization tests were performed to calculate the flow consistency index (K) and flow behavior index (n). Flow loop experiments were conducted for two geometry (0.457 inch and 0.797 inch diameter). Xanthan gum was used as a fractional drag reducer. Bentonite and quartz sand were added as low gravity solids. Three designed water-based mud systems are tested for drag reduction efficiency of Xanthan gum. Flow rate of the mud varied from 3 gpm to 16 gpm. Concentration of Xanthan ranged from 0.1 lbm/bbl to 0.6 lbm/bbl. Low weight solids were added with weight percentage of 0.5%, 1%, 2% and 2.5%. The result shows that xanthan gum is an efficient drag reducer for adequate reasons. Firstly, even at al low concentration, xanthan gum shows high resistance to degradation. Secondly, the maximum drag reduction with xanthan gum is up to 70.54% with a concentration of 0.6 lbm/bbl. However, the existence of different low gravity solids influence the efficiency of xanthan gum in different styles. Experiment results indicate that the higher the weight percentage of bentonite, the lower the drag reduction effectiveness. While with the increasing concentration of quartz sand, the drag reduction does not show an intense change. This study intents to give an instructive guidance on usage of frictional drag reducers in drilling mud system design. Removal of low gravity solids from the mud is difficult, which pose a danger to the drilling fluid. By understanding the effectiveness of FDR, we can reduce energy consumption when irremovable low gravity solids exist. FDR can be used for modifying the mud contents to develop a lower pressure gradient under turbulent flow condition. In the same scenario, adding FDR can suppress turbulent at a constant pressure gradient but with a higher flow rate.

Finite Element Model Calibration with Surrogate Model-Based Bayesian Updating: A Case Study of Motor FEM Model

2024-09-30T10:40:06+08:00

This paper introduces an advanced methodology for the calibration of Finite Element Models (FEM) utilizing a surrogate model-based Bayesian updating framework. The approach is exemplified through a case study on motor design, where precise FEM calibration is essential for predicting and optimizing motor performance. Traditional calibration techniques are often computationally expensive due to the iterative nature of the simulation process. To mitigate this, the proposed method integrates surrogate models to approximate FEM simulations, significantly reducing the computational burden without sacrificing accuracy. Bayesian updating is then employed to iteratively refine the surrogate model by incorporating new data, thereby enhancing prediction accuracy. This dual approach not only accelerates the calibration process but also ensures a high level of precision, making it highly suitable for complex engineering applications requiring both efficiency and reliability. The case study underscores the effectiveness of this methodology, demonstrating its potential to streamline the design process in motor development and other FEM-dependent engineering fields. The findings suggest that the surrogate model-based Bayesian updating approach achieves robust calibration with significantly fewer simulations, thereby optimizing both time and computational resources.

Enhancing Organizational Performance: Harnessing AI and NLP for User Feedback Analysis in Product Development

2024-07-08T17:14:07+08:00

This paper explores the application of AI and NLP techniques for user feedback analysis in the context of heavy machine crane products. By leveraging AI and NLP, organizations can gain insights into customer perceptions, improve product development, enhance satisfaction and loyalty, inform decision-making, and gain a competitive advantage. The paper highlights the impact of user feedback analysis on organizational performance and emphasizes the reasons for using AI and NLP, including scalability, objectivity, improved accuracy, increased insights, and time savings. The methodology involves data collection, cleaning, text and rating analysis, interpretation, and feedback implementation. Results include sentiment analysis, word cloud visualizations, and radar charts comparing product attributes. These findings provide valuable information for understanding customer sentiment, identifying improvement areas, and making data-driven decisions to enhance the customer experience. In conclusion, promising AI and NLP techniques in user feedback analysis offer organizations a powerful tool to understand customers, improve product development, increase satisfaction, and drive business success.

The Research on Intelligent News Advertisement Recommendation Algorithm Based on Prompt Learning in End-to-End Large Language Model Architecture

2024-08-30T14:20:04+08:00

With the explosive growth of information on the internet, users are increasingly facing the problem of information overload, making precise news and ad recommendations an important area of research. While traditional recommendation algorithms can meet user needs to some extent, they still have limitations in dealing with complex and changing user behaviors and dynamic content environments. This paper addresses the shortcomings of existing news and ad recommendation systems by proposing an intelligent recommendation algorithm based on an end-to-end large language model architecture. Firstly, we utilize the BERT model as the foundation, leveraging its powerful text representation capabilities to achieve deep semantic understanding of news and ad content, thereby capturing more detailed content features. Secondly, we apply prompt learning to fine-tune the BERT model, designing specific prompts for the model to better understand the implicit needs and preferences of users. Finally, we integrate these steps into an end-to-end architecture, enabling the model to achieve automated learning and optimization throughout the entire process from input to output, thus improving the precision and efficiency of recommendations. Experimental results demonstrate that the proposed method significantly outperforms traditional methods in the task of news and ad recommendation, not only enhancing the accuracy and relevance of recommendations but also effectively improving the model's interpretability and flexibility. This research explores new possibilities for the application of large language models in recommendation systems.