This paper discusses recent developments in the data-based modeling and control of nonlinear chemical process systems using sparse identification of nonlinear dynamics (SINDy). SINDy is a recent nonlinear system ident...
详细信息
This article discusses the aspects of controlling technological parameters for the isothermal forging of cross-ribbed panels, associated with strict adherence to temperature and rate conditions of deformation. However...
详细信息
This article discusses the aspects of controlling technological parameters for the isothermal forging of cross-ribbed panels, associated with strict adherence to temperature and rate conditions of deformation. However, to produce defect-free panels, because of errors and external disturbances, the control of technological parameters based only on the measurement results of temperature field sensors is often insufficient. The metal temperature at the deformation site can only be estimated indirectly. By analogy with the Kalman filter, a method is proposed for monitoring the technological parameters of the process of isothermal forging of ribbed panels based on a set of results obtained from sensors and calculated by the finite element method. The accuracy and speed of calculating a finite element forging model in four widely used specialized software products, DeForm, QForm, Forge NxT, and Simufact Forming, were studied. Comparing the data obtained during the analysis confirmed the high degree of reliability of the modeling results and demonstrated the potential possibility of controlling the technological parameters for the production of defect-free products using the proposed method. The finite element method in a two-dimensional formulation of the problem provided an acceptable velocity for numerical simulation while monitoring the progress of operations in real time. The results obtained are relevant for metallurgical enterprises producing critical parts for the aircraft and space industries. Therefore, there are increased requirements for production processes to comply with the range of permissible changes in technological parameters.
In modern warfare, the ability to make timely and informed decisions is critical for mission success. The traditional OODA (Observe, Orient, Decide, Act) loop provides a framework for combating processanalysis, but i...
详细信息
ISBN:
(纸本)9798400717048
In modern warfare, the ability to make timely and informed decisions is critical for mission success. The traditional OODA (Observe, Orient, Decide, Act) loop provides a framework for combating processanalysis, but in complex and dynamic environments, collaboration among diverse stakeholders becomes essential. This paper proposes a collaborative OODA (Colla-OODA) model for military combating processanalysis. The Colla-OODA model integrates collaboration into each phase of the decision-making process, emphasizing the importance of information sharing, collective analysis, and synchronized action among military units, branches, and allied forces. Sensor fusion plays a central role in enhancing situational awareness by integrating data from various sources such as satellites, drones, ground sensors, and intelligence reports. Through advanced dataprocessing and fusion algorithms, the Colla-OODA model aims to provide decision-makers with a holistic view of the operational environment, enabling more accurate assessments and rapid response to emerging threats and opportunities. The Colla-OODA model is evaluated through comprehensive modeling and simulation analyses, considering factors such as decision-making speed, accuracy, and agility in dynamic scenarios. The findings of this study will contribute to the development of innovative approaches to military decision-making, with potential applications in future battlefield operations and strategic planning efforts.
In Big data-based applications, high-dimensional and incomplete (HDI) data are frequently used to represent the complicated interactions among numerous nodes. A stochastic gradient descent (SGD)-based latent factor an...
详细信息
In Big data-based applications, high-dimensional and incomplete (HDI) data are frequently used to represent the complicated interactions among numerous nodes. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model can process such data efficiently. Unfortunately, a standard SGD algorithm trains a single latent factor relying on the stochastic gradient related to the current learning error only, leading to a slow convergence rate. To break through this bottleneck, this study establishes an SGD-based LFA model as the backbone, and proposes six proportional-integral-derivative (PID)-incorporated LFA models with diversified PID-controllers with the following two-fold ideas: a) refining the instant learning error in stochastic gradient by the principle of six PID-variants, i.e., a standard PID, an integral separated PID, a gearshift integral PID, a dead zone PID, an anti-windup PID, and an incomplete differential PID, to assimilate historical update information into the learning scheme in an efficient way;b) making the hyper-parameters adaptation by utilizing the mechanism of particle swarm optimization for acquiring high practicality. In addition, considering the diversified PID-variants, an effective ensemble is implemented for the six PID-incorporated LFA models. Experimental results on industrial HDI datasets illustrate that in comparison with state-of-the-art models, the proposed models obtain superior computational efficiency while maintaining competitive accuracy in predicting missing data within an HDI matrix. Moreover, their ensemble further improves performance in terms of prediction accuracy.
It is necessary to select appropriate rainfall series as input to the hydrologic model to access more accurate hydrologic predictions and estimate reliable parameters in the modelingprocess. For achieving this aim, i...
详细信息
It is necessary to select appropriate rainfall series as input to the hydrologic model to access more accurate hydrologic predictions and estimate reliable parameters in the modelingprocess. For achieving this aim, in the present study, the rainfall multipliers with a combination of Discrete Wavelet Transform (DWT) and principal component analysis (PCA) are applied to select effective rainfall series for modeling. DREAM((ZS)) algorithm based on the Markov chain Monte Carlo (MCMC) scheme is used to estimate posterior parameters and investigate prediction uncertainties of a five-parameter hydrologic model, HYMOD. The model's results are then compared to those obtained from the other methods that use only the rainfall multipliers or the raw rainfall data. This study reveals the advantages of using a combined application of DWT and PCA methods to estimate hydrological prediction uncertainty and model parameters accurately. Considering the occasional flash flood incident that occurred in the study region (Tamar basin, which is situated in the Gorganroud river basin, Golestan province, Iran), the results of this research can be useful for forecasting floods accurately and planning for flood control management.
Business process Management (BPM) is the factual criteria for business processmodeling. Although it is widely used in various fields, when required When using business processes to express big data business processes...
详细信息
Additive manufacturing (AM) is considered as a transformative manufacturing technology due to its ability to create complex structures and reduce material waste. However, the AM technology also introduces many challen...
详细信息
ISBN:
(纸本)9780791888476
Additive manufacturing (AM) is considered as a transformative manufacturing technology due to its ability to create complex structures and reduce material waste. However, the AM technology also introduces many challenges such as poor surface quality and structural integrity. To address these issues, a novel approach known as a digital twin (DT) has emerged. A digital twin is a digital representation of a physical object or system that enables real-time monitoring and control of their behavior. This study introduces a hybrid physicalvirtual digital twin environment that combines a sensing-driven DT with a process simulation-driven DT. Specifically, we propose a hybrid digital twin environment (HDTE) customized for a fused deposition modeling (FDM) 3D printer. The HDTE is implemented into a 3D development platform. The present DT environment integrates external sensors to collect real-time data on temperature and location of the extruder on a 3D printer. It also includes a virtual AM process simulation using a commercial finite element software to predict temperature distribution and mechanical behavior during 3D printing. Position and temperature assessment experiments confirm the DT's ability to replicate component positions under static and dynamic conditions as well as temperature variation within the 3D printer. Comparative analysis between the simulation and experimental data shows excellent agreement and further validate the DT's capabilities. The present DT holds the potential for a significant advancement in 3D printing technology by offering real-time insights, predictive capabilities, and improved processcontrol.
Froth flotation is a widely used technique for mineral separation, but it poses significant challenges for modeling due to the complex phenomena that happen during the process. To account for the implementation of opt...
详细信息
modeling individualized facial happiness assessment is essential for personalizing recommendations and conversions of facial expressions. We propose an efficient comparison-based method for estimating and optimizing i...
详细信息
ISBN:
(纸本)9798331544461;9784907764838
modeling individualized facial happiness assessment is essential for personalizing recommendations and conversions of facial expressions. We propose an efficient comparison-based method for estimating and optimizing individualized facial happiness assessment in a situation where the number of interactions with the individual is limited. The method combines the black-box function optimization framework, called Bayesian optimization (BO), with list-wise Gaussian process preference learning, which learns a model from list-wise comparison data. In each interaction, the individual ranks a given set of facial images in order of how happy they appear, and the model is updated for each interaction. By using BO, the model allows us to efficiently determine which facial images should be presented to the individual in the next interaction. By using the ranking information represented by list-wise comparison data, the amount of information obtained from a single interaction is increased, which reduces the number of interactions and the time required for training. Experiments on modeling the individualized facial happiness assessment of photo-realistic virtual characters show that the proposed method can construct a more accurate model and find near-optimal facial expressions with fewer interactions than the conventional method.
This study presents an innovative approach to mitigate mobbing as a cyberattack by integrating artificial intelligence (AI) techniques such as Latent Dirichlet Allocation (LDA) and Robustly Optimized BERT Pretraining ...
详细信息
ISBN:
(纸本)9798331534110;9798331534103
This study presents an innovative approach to mitigate mobbing as a cyberattack by integrating artificial intelligence (AI) techniques such as Latent Dirichlet Allocation (LDA) and Robustly Optimized BERT Pretraining Approach (RoBERTa) according with the Cross-Industry Standard process for data Mining methodology (CRISP-DM). Mobbing in digital environments constitutes an emerging form of cyber attack that affects both individuals and organizations. Preventing mobbing requires a comprehensive approach involving legal frameworks, employee awareness, and technological solutions. This work uses AI to identify patterns of mobbing and proposes a structured process based on CRISP-DM to address this phenomenon. It focuses on analyzing mobbing through digital data to develop a content-filtering solution for platforms like email and messaging systems. The study identified eight general phases that describe the overall context of mobbing, as well as four specific phases that outline the detailed process of harassment within it, using fine-tuning techniques for detection. The results show how AI can automate the detection and mitigation of mobbing, minimizing its impact on victims and improving cybersecurity.
暂无评论