This research enhanced the Discrete Logarithm Problem-Based (DLP-based) Algorithm, enabling it to utilize two or more security keys in the encryption process. The enhancement enabled the Algorithm to inject multiple h...
详细信息
Early detection and characterization of anomalous events during drilling operations are critical to avoid costly downtime and prevent hazardous events, such as a stuck pipe or a well control event. A key aspect of rea...
详细信息
ISBN:
(纸本)9781613999929
Early detection and characterization of anomalous events during drilling operations are critical to avoid costly downtime and prevent hazardous events, such as a stuck pipe or a well control event. A key aspect of real-time drilling dataanalysis is the capability to make precise predictions of specific drilling parameters based on past time series information. The ideal models should be able to deal with multivariate time series and perform multi-step predictions. The recurrent neural network with a long short-term memory (LSTM) architecture is capable of the task, however, given that drilling is a long process with high data sampling frequency, LSTMs may face challenges with ultra-long-term memory. The transformer-based deep learning model has demonstrated its superior ability in natural language processing and time series analysis. The self-attention mechanism enables it to capture extremely long-term memory. In this paper, transformer-based deep learning models have been developed and applied to real-time drilling data prediction. It comprises an encoder and decoder module, along with a multi-head attention module. The model takes in multivariate real-time drilling data as input and predicts a univariate parameter in advance for multiple time steps. The proposed model is applied to the Volve field data to predict real-time drilling parameters such as mud pit volume, surface torque, and standpipe pressure. The predicted results are observed and evaluated. The predictions of the proposed models are in good agreement with the ground truth data. Four Transformer-based predictive models demonstrate their applicability to forecast real-time drilling data of different lengths. Transformer models utilizing non-stationary attention exhibit superior prediction accuracy in the context of drilling data prediction. This study provides guidance on how to implement and apply transformer-based deep learning models applied to drilling dataanalysis tasks, with a specific focus o
A Digital Twin (Applied Twin™) is a computational model that represents a physical asset such as a process chamber, evolving over time to reflect its structure, behavior, and context. This model treats the asset-twin ...
详细信息
ISBN:
(数字)9798331531850
ISBN:
(纸本)9798331531867
A Digital Twin (Applied Twin™) is a computational model that represents a physical asset such as a process chamber, evolving over time to reflect its structure, behavior, and context. This model treats the asset-twin system as a set of coupled dynamical systems that evolve over time, interacting through observed data and control inputs. [1] They are an evolution of modeling & simulation. The Digital Twin (DT) can be useful in integration, testing, monitoring, and maintenance. Eventually it can be utilized as an early and ad hoc fast learning tool for systems and processes. In semiconductor manufacturing, DTs have found their way in their early rudimentary form as control or predictive applications such as for production control applications like planning, scheduling, and dispatching and for equipment and processcontrol applications like, Run-to-Run (Applied SmartFactory™ Run-2-Run) (R2R), Virtual Metrology, and predictive maintenance. Through this paper we explore the idea of idea of engineering DT and R2R algorithms with intersecting system manipulated variables or inputs between the two systems.
In recent years, organizations are putting an increasing emphasis on anomaly detection. Anomalies in business processes can be an indicator of system faults, inefficiencies, or even fraudulent activities. In this pape...
详细信息
ISBN:
(纸本)9783031278143;9783031278150
In recent years, organizations are putting an increasing emphasis on anomaly detection. Anomalies in business processes can be an indicator of system faults, inefficiencies, or even fraudulent activities. In this paper we introduce an approach for anomaly detection. Our approach considers different perspectives of a business process such as control flow, data and privacy aspects ***, it is able to detect complex anomalies in business processes like spurious dataprocessing and misusage of authorizations. The approach has been implemented in the open source ProM framework and its applicability was evaluated through a real-life dataset from a financial organization. The experiment implies that in addition to detecting anomalies of each aspect, our approach can detect more complex anomalies which relate to multiple perspectives of a business process.
The Tennessee Eastman process (TEP) is a widely studied industrial benchmark for testing fault detection and diagnosis techniques, given its complexity and the need for reliable fault detection systems in chemical pla...
详细信息
ISBN:
(数字)9798331508227
ISBN:
(纸本)9798331508234
The Tennessee Eastman process (TEP) is a widely studied industrial benchmark for testing fault detection and diagnosis techniques, given its complexity and the need for reliable fault detection systems in chemical plants. This paper proposes a comprehensive application of exploratory dataanalysis (EDA) techniques to the TEP dataset to enhance process fault detection and improve understanding of the dataset's features. The proposed methodology involves plotting time series data to capture temporal dynamics and applying Shewhart control charts to monitor process variability. Additionally, deviation atlases are used to detect anomalies across all features, dendrograms are employed to identify hierarchical clusters, and correlation heatmaps visualize interdependencies between process variables. By applying these EDA techniques, patterns and relationships that were less apparent in the raw dataset became identifiable, contributing to a more thorough fault diagnosis. The findings highlight the value of EDA in uncovering hidden insights, which could aid in the development of more robust fault detection algorithms for real-world industrial applications.
The propagation of converter-interfaced generation (CIG) is drawing attention, due to the issues elicited by their large-scale application, and also their potential to advance more complex operational modes. In such c...
详细信息
Single data source, isolated data islands and low information utilization in intelligent transportation lead to the poor inversion of the cyber space to the physical space including Incomplete data integration, high i...
详细信息
Bayesian classification is a common dataanalysis and modeling method in data mining. In this paper, an improved ensemble method and the optimized Kernel density estimation used to Bayesian classifier. Unlike the trad...
详细信息
The improvement of people's living standards, every family has a private car, and large trucks used in industry are the reason for the continuous increase in the traffic flow, and traffic congestion has become an ...
详细信息
ISBN:
(数字)9798350384598
ISBN:
(纸本)9798350384604
The improvement of people's living standards, every family has a private car, and large trucks used in industry are the reason for the continuous increase in the traffic flow, and traffic congestion has become an increasingly serious problem. When traffic congestion becomes an urgent problem that restricts the development of the city, intelligent traffic control becomes a technology that can improve traffic efficiency and traffic safety. When we look at the traffic system from the perspective of big data, we will find that the data involved in the intelligent transportation system is very large, and the traditional method of dataanalysis and processing is no longer applicable. This research conducts in-depth research on the various data sources involved in the intelligent transportation system, and analyzes the features and scale of these data sources. A distributed computing based scalable big dataanalysis framework is proposed in order to solve the problem of big dataanalysis and processing. The framework employs parallel computing and distributed storage technology to process large-scale data efficiently, and to obtain real-time analysis results. The scalability of the proposed scalable big dataanalysis framework and the data preprocessing methods was verified by experimental evaluation, and the performance was highlighted. The research results show that the big dataanalysis technology can process and analyze big data generated in ITS, and provide important decision support for intelligent transportation control based on the true results of the analysis.
As prefabricated construction advances, the enhanced informatization and the industrialized modular construction method of MIC (Modular integrated construction) shear walls have been widely applied in real projects. M...
详细信息
暂无评论