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 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.
Traffic congestion has become a nightmare to modern life in metropolitan cities. On average, a driver spending X hours a year stuck in traffic is one of most common sentences we often read regarding traffic congestion...
详细信息
ISBN:
(数字)9783907144077
ISBN:
(纸本)9783907144077
Traffic congestion has become a nightmare to modern life in metropolitan cities. On average, a driver spending X hours a year stuck in traffic is one of most common sentences we often read regarding traffic congestion. Our aim in this article is to provide a method to control this seemingly ever-growing problem of traffic congestion. We model traffic dynamics using a continuous-time mass-flow conservation law, and apply optimal control techniques to control traffic congestion. First, we apply the mass-flow conservation law to specify traffic feasibility and present continuous-time dynamics for modeling traffic as a network problem by defining a network of interconnected roads (NOIR). The traffic congestion control is formulated as a boundary control problem and we use the concept of statetransition matrix to help with the optimization of boundary flow by solving a constrained optimal control problem using quadratic programming in MATLAB. Finally, we show that the proposed algorithm is successful by simulating on a network of interconnected roads based on the street map of Phoenix city.
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
In the operation process of the power plant, in addition to the operating state information of the power plant process systems and components is monitored by Industrial control Systems (ICSs), a large number of the op...
详细信息
ISBN:
(纸本)9781665473880
In the operation process of the power plant, in addition to the operating state information of the power plant process systems and components is monitored by Industrial control Systems (ICSs), a large number of the operating state information of ICSs and its components themselves can be obtained. These information helps operators to understand the operation safety state of ICSs themselves, and whether ICSs operate reliably, which plays an important role in maintaining the normal operation of the power plant, controlling abnormal events and mitigating the development of accidents. This paper proposes an integrated methodological framework for real-time risk awareness and prediction of ICS based on the particle filtering model whose features are updating monitoring data and predicting the state transition process, and focus on the measurement of risk states, identification of critical risk states and key components, modeling of the state transition process, prediction of risk levels and estimation of remaining arrival time of high-risk residual. The assumption that the transition probability matrix of system states does not change over time in traditional Markov predictions is discarded in this proposed method. Compared with the traditional ICS safety analysis method, this method can provide global and systemic risk insights for ICS risk situation, with a better real-time performance, and it is a kind of more scientific and objective measurement for ICS risk situation.
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.
In this research paper, we present the design and implementation of an AI assisted interactive framework for datamodeling and high resolution image synthesis that leverages both state of the art latent diffusion mode...
详细信息
ISBN:
(数字)9798331527495
ISBN:
(纸本)9798331527501
In this research paper, we present the design and implementation of an AI assisted interactive framework for datamodeling and high resolution image synthesis that leverages both state of the art latent diffusion models and visualisation of the real-time algorithm. The system proposed enables user to be able to better understand complex datamodelingprocesses and creates high resolution images in the latent space using diffusion. The framework is both interactive, allowing modifications in parameters and real time visualization of change, making it a useful tool both for educational and for advanced AI research. In this paper, we also discuss the underpinning AI-assisted datamodeling algorithms, and why they enable efficient data manipulation as well as high quality image synthesis then provide simulation results and practical applications to illustrate the capabilities of the framework of visualizing the latent diffusion process and generating high resolution images.
The engineering application under industrial big-dataanalysis is of great significance for improving the optimization effect of enterprise production processcontrolprocesses. By analyzing the operating principle of...
详细信息
ISBN:
(数字)9789887581598
ISBN:
(纸本)9798331540845
The engineering application under industrial big-dataanalysis is of great significance for improving the optimization effect of enterprise production processcontrolprocesses. By analyzing the operating principle of the semi-automatic mill and studying its control optimization strategy, based on the operational data of the SAG mill, industrial big-dataanalysis is adopted to self-learning its control optimization rules. Firstly, SPSS is used to preprocess the high-dimensional processdata generated during the operation of the semi-automatic mill. Four parameters, namely power, axial pressure, grinding sound, and grinding concentration, are preliminarily selected. Then, PCA is used to screen and reduce the dimensionality of multidimensional data, and K-Means clustering algorithm is used to classify and identify the reduced dataset. After simulation research, the results show that PCA can reduce the redundancy of SAG mill operation data, and the control optimization rules formed by self-learning can serve as operational guidance for improving the efficiency and energy-saving of SAG mill operation. The effectiveness can be further verified in practical engineering applications in the later stage.
The objective of this paper is to demonstrate the success of an alternative numerical modeling approach to build a static model by incorporating Forward Stratigraphic Modelling (FSM) as geological input. This new meth...
详细信息
ISBN:
(纸本)9781613998359
The objective of this paper is to demonstrate the success of an alternative numerical modeling approach to build a static model by incorporating Forward Stratigraphic Modelling (FSM) as geological input. This new methodology was performed on a field in the Malay Basin where early production wells indicated the high uncertainty in oil-originally-in-place, facies distribution and reservoir connectivity. For this reason, a new approach was developed for a static model in the area that provides new insights of subsurface reservoirs, de-risking future field assets and mitigates the subsurface uncertainty. process-based simulations as presented with FSM present realistic scenarios of lithology distribution and vertical barriers that enable advanced subsurface characterization. FSM process built a quantitative method that simulate sediment distribution from regional to reservoir architecture for A field D and E sands. The main parameters for simulation run include regional understanding of sediment sources, in-situ organic sediment production, global sea-level curve enhanced by Milankovitch cycles and main long-term processes that control the subsidence of the area. FSM prediction combined with regional seismic, cores and well log data have provided a robust scenario of reservoir characteristics for static model. The results of the study detailed high-resolution sequence stratigraphy, significant changes in the depositional system and sand accumulation through time. The results of FSM were quality-checked with the A field well dataset for consistency. After performance of sensitivity analysis, the best-matched model was chosen for subsequent static model building process. In generating static depo- and rock type models, the FSM result were compared with the Geostatistical Stochastic Inversion (GSI) for property distribution away from the well control. The result of FSM guided model building showed A field D reservoirs as relatively having better sand quality with good late
In terms of the generative process, the Gamma-Gamma-Poisson process (G2PP) is equivalent to the nonparametric topic model of Hierarchical Dirichlet process (HDP). Considering the high computational cost of estimating ...
详细信息
暂无评论