The introduction of artificial intelligence (AI)-driven tools has revolutionized offset well analysis, particularly in estimating well time for conceptualization and planning phases. Previously labor-intensive manual ...
详细信息
ISBN:
(纸本)9781959025436
The introduction of artificial intelligence (AI)-driven tools has revolutionized offset well analysis, particularly in estimating well time for conceptualization and planning phases. Previously labor-intensive manual processes for analyzing legacy data have been transformed into digital predictions of activities, operational sequences, key performance indicators (KPIs), and risk estimations through a web application. This system comprises AI engines that model specific aspects of well construction, working with a user interface that enables control over data and domain parameters. Engineers can develop well designs and, using existing designs as references, the application computes KPIs, forecasts operational sequences, assesses risks, and estimates well durations. By employing probability distributions for each input and iterating the process multiple times, the application generates histograms for each output upon simulation completion. Before AI tools, engineers faced the daunting task of manually analyzing extensive drilling reports, a process that could take weeks. The new web application streamlines this into a swift, efficient process, drastically reducing time and enhancing accuracy. Tested successfully in projects across Mexico and Ecuador, the application has shown significant improvements in efficiency and competitiveness. These AI-driven tools not only save time but also reduce costs and carbon emissions, exemplifying their transformative impact on the oil and gas industry. Copyright 2025, International Petroleum Technology conference.
The medical device manufacturing industry is driven by stringent regulatory compliances and faces challenges in implementing quality management systems. One such challenge is the preparation of the paper-based documen...
详细信息
Thermal runaway caused by the internal short circuit (ISC) poses a significant safety risk for sodium-ion batteries (SIBs) in electric vehicles and energy storage applications. Early detection of ISC faults is conside...
详细信息
This paper is a comparison of aircraft analysis techniques of the H-King Bixler 1.1, a small fixed-wing UAS. Geometric characteristics including wing, fuselage, control surfaces, and moments of inertia were measured, ...
详细信息
Medical image registration is a fundamental and core technology in the field of medical image processing and analysis. In recent years, deep learning-based registration methods have made significant progress and gradu...
详细信息
Medical image registration is a fundamental and core technology in the field of medical image processing and analysis. In recent years, deep learning-based registration methods have made significant progress and gradually replaced traditional registration methods. However, many existing methods still face challenges when dealing with large deformations caused by significant structural differences or topological changes. To address this issue, we propose a competitive hybrid registration network. Specifically, our network combines the advantages of Vision Transformer (ViT) and Convolutional Neural Network (CNN) in feature extraction, allowing it to enhance long-range dependencies between images while preserving the integrity of local features. Furthermore, we have developed a novel coarse-to-fine registration strategy in which the deformation fields (DFs) are refined dynamically to obtain more accurate and robust estimation. We extensively evaluated our method on multiple registration tasks, and the experiments demonstrate that our approach outperforms other deep learning methods in terms of accuracy, robustness, and generalization.
This study focuses on the development and evaluation of soft sensor models for predicting NH3-N values in a wastewater treatment process. The study compares the performance of linear regression (LR), neural networks (...
详细信息
This study focuses on the development and evaluation of soft sensor models for predicting NH3-N values in a wastewater treatment process. The study compares the performance of linear regression (LR), neural networks (NN) and random forest regression (RFR) models. The proposed methodology involves optimizing the sequencing batch reactor process using artificial intelligence and an automatic control system. Real-time NH3-N values are obtained by inputting data from electronic conductivity and temperature sensors into the prediction models. Once the predicted NH3-N value falls below the effluent standard, the cycle ends, improving energy efficiency and sustainability by cutting down the agitator and aerator. The research results demonstrate that the RNN-based NH3-N soft sensor built in this study exhibits the best performance, which is promising for wastewater treatment process optimization and evaluation. The results show that sensor model NNR[0.5Y]H exhibits exceptional performance, utilizing recurrent neural network with 5-step input delays. Sensor NNR[0.5Y]H exhibits an R-2 of 0.921, an RMSE of 6.110, and an MAE of 4.558. Based on the findings, recurrent neural network (RNN) variants emerge as the most effective modeling technique due to their ability to capture temporal dependencies and handle variable-length sequences. This study provides satisfied performance results for the NNR[0.5Y]H soft sensor model in NH3-N monitoring and process optimization in wastewater treatment, highlighting the effectiveness of recurrent neural networks and their contribution to improving interpretability, accuracy, and adaptability of soft sensor models.
The high cost and difficulty of data collection result in discrete intermittency and limited available data for most datasets, posing challenges to modeling and prediction needs. Thus, it is crucial to explore methodo...
详细信息
The National Ecological Observatory Network (NEON) provides over 180 distinct data products from 81 sites (47 terrestrial and 34 freshwater aquatic sites) within the United States and Puerto Rico. These data products ...
详细信息
The National Ecological Observatory Network (NEON) provides over 180 distinct data products from 81 sites (47 terrestrial and 34 freshwater aquatic sites) within the United States and Puerto Rico. These data products include both field and remote sensing data collected using standardized protocols and sampling schema, with centralized quality assurance and quality control (QA/QC) provided by NEON staff. Such breadth of data creates opportunities for the research community to extend basic and applied research while also extending the impact and reach of NEON data through the creation of derived data products-higher level data products derived by the user community from NEON data. Derived data products are curated, documented, reproducibly-generated datasets created by applying various processing steps to one or more lower level data products-including interpolation, extrapolation, integration, statistical analysis, modeling, or transformations. Derived data products directly benefit the research community and increase the impact of NEON data by broadening the size and diversity of the user base, decreasing the time and effort needed for working with NEON data, providing primary research foci through the development via the derivation process, and helping users address multidisciplinary questions. Creating derived data products also promotes personal career advancement to those involved through publications, citations, and future grant proposals. However, the creation of derived data products is a nontrivial task. Here we provide an overview of the process of creating derived data products while outlining the advantages, challenges, and major considerations.
The proceedings contain 39 papers. The special focus in this conference is on Informatics in Economy. The topics include: Performance Evaluation of data Vault and Dimensional modeling: Insights from TPC-DS dataset Ana...
ISBN:
(纸本)9789819601608
The proceedings contain 39 papers. The special focus in this conference is on Informatics in Economy. The topics include: Performance Evaluation of data Vault and Dimensional modeling: Insights from TPC-DS dataset analysis;revolutionizing Healthcare: Harnessing Natural Language processing and Big data for Predictive Disease Diagnosis;enhancing the Involvement Level of Volunteer Students in the Academic Community: Efficient Usage of Digital Resources;intelligent Models in Power Delivery Management for Economic Damage Computation;smart City Parking Applications in Romania: An analysis and Conclusions;measurement and Verification Solution for Energy Performance Contracting in the Building Sector;analyzing the Antecedents of Deceived Buying and Disinformation Risk;driving Factors of Social Commerce Intention: The Role of Social Commerce Constructs, Social Influence, and Trust;strategic Collaboration in International University Networks–Case Study;Comparative analysis of Natural Language Query Responses on BPMN Model Serializations: RDF Graphs Versus BPMN XML;a Hybrid Retrieval-Augmented Generation Approach for Heterogeneous Knowledge Bases;digitalization in Higher Education—Designing and Implementing an Application to Facilitate the University Final Thesis Collaboration process;an Overlook of IoT Finance and Pre-existing Security Challenges in Financial Transactions via IoT Devices on Blockchain Networks;models for Network Traffic Behavioral analysis in IoT Systems;augmented Reality in Education—Prototype for the Undergraduate System in Romania;empowering Sustainability: Upcycling Smartphones as the Future of IoT and Edge Computing in Emerging Economies;quantum Computing and Cybersecurity: Threat or Opportunity?;new Real-Time Encryption Mechanism for Financial Transactions;enhanced Blockchain-Based e-Voting System Using Zero-Knowledge Proofs;The Environmental Kuznets Curve for Deforestation in Romania: An ARDL-Based Evaluation.
Magneto-mechanical coupling in the growth of soft materials presents challenges due to the complex interactions between magnetic fields, mechanical forces, and growth-induced deformations. While growth modeling has be...
详细信息
Magneto-mechanical coupling in the growth of soft materials presents challenges due to the complex interactions between magnetic fields, mechanical forces, and growth-induced deformations. While growth modeling has been extensively studied, integrating magnetic stimuli into growth processes remains underexplored. In this work, we develop a 3D governing system for capturing the coupled magneto-mechanical growth behaviors of soft materials. Based on the governing system, we propose a finite element framework, where the robustness and accuracy of the proposed framework are demonstrated through numerical simulations, including the uniaxial loading of a circular tube, a mesh convergence study, and surface pattern evolution. We also conduct experiments on surface pattern modulation in magneto- active soft materials. Specifically, we fabricate film-substrate samples and apply growth-induced instabilities combined with external magnetic fields to generate tunable surface patterns. To demonstrate the capabilities of our method, we apply our numerical framework to mimic the biological morphogenesis, such as the inversion process of the algal genus Volvox. Our study shows that integrating magneto-mechanical coupling with growth effects allows for flexible control over surface patterns, significantly enhancing the adaptability and responsiveness of soft materials. This work paves the way for innovative designs of adaptive and programmable soft materials, with potential applications in soft robotics, biomimetic structures, and tissue engineering.
暂无评论