The finite element analysis of the cold flat rolling process is well established. However, the requirement of large computational time makes it unsuitable for online applications. Recently, there have been some applic...
详细信息
The finite element analysis of the cold flat rolling process is well established. However, the requirement of large computational time makes it unsuitable for online applications. Recently, there have been some applications of modeling the rolling process by means of neural networks. In most of the previous works, trained networks predict only roll force and roll torque. The input data for training the neural network have been obtained either through experiments or from finite element method (FEM) code. In this work, the neural networks have been used for predicting the velocity field and location of neutral point. The training data are obtained from a rigid-plastic finite element code. The trained network provides a suitable guess for the velocity field and location of the neutral point, that is further refined by the finite element code. The post-processor of the FEM code computes roll force, roll torque, strain distribution, etc. This procedure provides highly accurate solution with reduced computational time and is suitable for on line control or optimization. (c) 2006 Elsevier Ltd. All rights reserved.
Very often important process variables cannot be measured online due to low sampling rate of sensors or because their values have to be obtained by laboratory analysis. In order to enable continuous process monitoring...
详细信息
ISBN:
(纸本)9780769549132
Very often important process variables cannot be measured online due to low sampling rate of sensors or because their values have to be obtained by laboratory analysis. In order to enable continuous process monitoring and efficient processcontrol in such cases, soft sensors are usually used to estimate these difficult-to-measure process variables. Most industrial processes exhibit some kind of time-varying behavior. To ensure that soft sensor retains its precision, adaptation mechanism has to be implemented. In this paper adaptive soft sensor based on Gaussian process Regression (GPR) is presented. To make GPR model training more efficient, algorithm for variable selection based on Mutual Information is proposed. Prediction capabilities of the proposed method are examined on real industrial data obtained at an oil distillation column.
Through disassembling the workflow of mobile electronic commerce distribution pattern into two processes, the advertising process model and selling process model based on Petri nets are proposed. Through analyzing the...
详细信息
ISBN:
(纸本)9781424417339
Through disassembling the workflow of mobile electronic commerce distribution pattern into two processes, the advertising process model and selling process model based on Petri nets are proposed. Through analyzing the transfer of funds denoted from the two process models and making several reasonable assumptions, we use mathematics approach to indicate the optimal business strategy for mobile commerce service provider in this business pattern. Under this strategy, the service provider will maximize its profits.
Instructional tools for process dynamics and control should be visually appealing, easy-to use and accepted by students and practitioners. Loop-Pro is software designed to meet these goals so students will: - learn ho...
详细信息
Instructional tools for process dynamics and control should be visually appealing, easy-to use and accepted by students and practitioners. Loop-Pro is software designed to meet these goals so students will: - learn how to collect and analyze processdata to determine the essential dynamic behavior of a process, - learn what "good" or "best" control performance means for a particular process, - understand the computational methods behind the different control algorithms and learn when and how to use each one to achieve best performance, - learn how the different adjustable or tuning parameters required for control algorithm implementation impact control performance and how to determine values for these parameters, - become aware of the limitations and pitfalls of each control algorithm and learn how to turn this knowledge to their advantage. Loop-Pro is comprised of three modules: Case Studies, Custom process and Design Tools. The Case Studies module provides real-world experience in modern methods and practices of processcontrol through a collection of realistic processes to practice upon. The Custom process module is a block oriented environment that lets students construct a process and controller architecture to their own specifications for a wide range of custom control analyses. The Design Tools module is used to fit linear dynamic models to processdata and to compute PID controller tuning values. The models from Design Tools can also be used to construct advanced control strategies that use process models internal to the controller architecture such as feed forward and model predictive control. This paper explores the use of the control Station training simulator for processcontrol education. In particular, the discussion focuses on how this simulator bridges the gap between textbook theory and laboratory learning. Methods and benefits of using control Station in the undergraduate curriculum are presented. control Station is currently used by more than 150
Mobile marketing campaigns are now largely deployed through the intermediaries of demand side platforms (DSPs) who provide a performance intensive real-time bidding (RTB) version of predictive analytics as a service. ...
详细信息
ISBN:
(纸本)9781479973675
Mobile marketing campaigns are now largely deployed through the intermediaries of demand side platforms (DSPs) who provide a performance intensive real-time bidding (RTB) version of predictive analytics as a service. Performance thresholds are roughly 100ms for DSPs to decide whether and how much to bid for a potential client to receive a particular advertisement via their mobile device This decision requires simultaneous access to multiple very large databases with typically millions of rows and the ability to execute multiple predictive models (e.g., logistic regression) to gauge the customer's propensity to engage. In this environment, analytic modeling must be automated via model feedback loops which adjust the models dynamically as real time data streams in. We call this mode of analytics adaptive modeling. We detail the process of adaptive modeling from the perspective of a DSP and describe the corresponding model management environment necessary to plan, execute, and evaluate RTB campaigns.
In this contribution, a method for the identification of a game-theoretic driver decision model is presented. The aim of the identification process is to find performance index parameters for which the solution of the...
详细信息
ISBN:
(数字)9781665473385
ISBN:
(纸本)9781665473385
In this contribution, a method for the identification of a game-theoretic driver decision model is presented. The aim of the identification process is to find performance index parameters for which the solution of the optimization problem representing the driver decision making process is identical to a given set of recorded trajectories. In order to solve the identification problem a bi-level approach is used. Hereby, the lower level problem is the optimization problem modeling the decision making of the driver. The upper-level optimization problem on the other hand models the parameter optimization problem searching for the performance index parameters. A limitation of the model to be identified is, that the optimization problem modeling the decision making process cannot be solved analytically. Therefore, the identification problem can not be solved using model-based parameter-optimization techniques. To circumvent this problem an evolutionary algorithm is applied. While in the first step the algorithm is developed for the identification of a single driver, it is extended to the multi-player case in the second step. Finally, the developed approach is validated using artificially created data.
With the advancement of sensing and information technology, sensor networks and imaging devices have been increasingly used in manufacturing and healthcare to improve information visibility and enhance operational qua...
详细信息
With the advancement of sensing and information technology, sensor networks and imaging devices have been increasingly used in manufacturing and healthcare to improve information visibility and enhance operational quality and integrity. Furthermore, the Internet of Things (IoT) technology has been integrated for the continuous monitoring of machine and patient conditions. As such, large amounts of data are generated with high dimensionality and complex structures. This provides an unprecedented opportunity to realize smart automated systems such as smart manufacturing and connected health care. However, it also raises new challenges in dataanalysis and decision making. Realizing the full potential of the data-rich environment calls for the development of new methodologies for data-driven information processing, modeling, and *** dissertation develops new methods and tools that enable 1) better handling of large amounts of multi-channel signals and imaging data generated from advanced sensing systems in manufacturing and healthcare settings, 2) effective extraction of information pertinent to system dynamics from the complex data, and 3) efficient use of acquired knowledge for performance optimization and system improvement. The accomplishments include:1)Fusion and analysis of multi-channel signals. In Chapter 2, a spatiotemporal warping approach was developed to characterize the dissimilarity among 3-lead functional recordings. A network was then optimally constructed based on the dissimilarity and network features were extracted for the identification of different types of diseases. 2)Statistical processcontrol based on time-varying images. In Chapter 3, a stream of time-varying images were represented as a dynamic network. Then, community structure of the network was characterized and community statistics were extracted from time to time. Finally, a new control charting approach was developed for in-situ monitoring of manufacturing processes. 3)Mon
In a composite network, a piece of information traveling through links in a social network may have to travel over multiple links in an associated communication network. In this paper, we propose a model of composite ...
详细信息
ISBN:
(纸本)9781450308984
In a composite network, a piece of information traveling through links in a social network may have to travel over multiple links in an associated communication network. In this paper, we propose a model of composite networks that consists of two networks and an embedding between them, and several composite metrics that characterize information flow under a particular type of embedding. We present analytic results for the scaling behavior of "constrained composite stretch" of a path, "constrained composite diameter" of a graph, and "constrained composite broadcast time" of a tree, under random uniform embeddings onto various communication network structures. We validate our analytical results on composite stretch using two data sets consisting of a friendship social network geographically spread across Western Europe and a historical deployment of a military chain of command. We also present a randomized model of field deployment consistent with real-world data, and use simulations over this model to explore the distribution of constrained composite broadcast time. Finally, we show that our analytical bounds for composite broadcast time agree well with the simulation results.
The objective of this paper is to show a new way of depicting information systems' models of design methods. New terms of the method are created by sequential transformations from the existing terms. The model of ...
详细信息
ISBN:
(纸本)9728865430
The objective of this paper is to show a new way of depicting information systems' models of design methods. New terms of the method are created by sequential transformations from the existing terms. The model of elements' transformation is an instance of this model. It depicts the process of constructing given information system.
This paper investigates state feedback control for a class of discrete-time multiple input and multiple output nonlinear systems from the perspective of model-free adaptive control and state observation. The design of...
详细信息
This paper investigates state feedback control for a class of discrete-time multiple input and multiple output nonlinear systems from the perspective of model-free adaptive control and state observation. The design of a dynamic state feedback control can be efficiently carried out using dynamic linearization and state observation. The stability of the proposed method is guaranteed by theoretical analysis. Numerical simulation tests and experimentation on a continuous stirred tank reactor are carried out to validate the effectiveness of the proposed approach. Note to Practitioners-The growth in the scale of factories and the complexity of associated production processes increases the complexity and time involved in associated mathematical modelling. data driven approaches to control remove the need to model processes. To the best of the authors' knowledge, existing approaches to model-free adaptive control (MFAC) of general systems are all based on an input-output control paradigm. These methods thus cannot guarantee the stability of the system state. The purpose of this study is to develop a novel Model-Free Adaptive control (MFAC) approach to achieve control of the system state. In this paper, the assumptions required to achieve model-free adaptive control by state feedback are presented mathematically. A controller design and the associated stability proof are then presented. Numerical simulation and experimentation is conducted to validate the effectiveness of the proposed approach. In future research, state feedback datacontrol in the presence of random disturbances will be investigated.
暂无评论