检索结果-内蒙古大学图书馆

REPRESENTATION OF process TRENDS .2. THE PROBLEM OF SCALE AND QUALITATIVE SCALING

COMPUTERS & CHEMICAL engineering 1990年第4-5期14卷 511-539页

作者： CHEUNG, JTY STEPHANOPOULOS, G Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

The formal representation of process trends introduced in Part I of this series is completed in this paper through the formal definition and representation of time scales, which allow: (a) the systematic and unambiguous description of trends at any time scale of interest; and (b) the discovery of descriptions at dominant time scales. The representation is based on the concept of “scaling episodes,” which are constructed from the “triangular episodes” introduced in Part I, to describe the distinct events characterizing the time scales of process trends. The “qualitative spectrum of scales” can then be synthesized to reveal the distribution of the underlying physicochemical events occurring at various time scales. Specific procedures are proposed to carry out local or global scaling as well as the transformation of information between different time scales, leading to the construction of the “qualitative structure of scale,” which provides simultaneous descriptions of a trend at all scales. In contrast to the Fourier notion of scale, the time-domain approach proposed in this paper allows interpretations of time scales on the basis of the occurring physicochemical phenomena.

关键词： process Control

来源：评论

学校读者我要写书评

暂无评论

SYNTHESIS OF OPERATING PROCEDURES FOR COMPLETE CHEMICAL-PLANTS .3. PLANNING IN THE PRESENCE OF QUALITATIVE, MIXING CONSTRAINTS

引用

COMPUTERS & CHEMICAL engineering 1990年第3期14卷 301-317页

作者： LAKSHMANAN, R STEPHANOPOULOS, G Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

A nonlinear planning methodology for handling qualitative mixing constraints is presented. It is intended to account for operational specifications prohibiting the mixing of two or more chemical species which form undesirable or potentially dangerous mixtures. The approach is based on the concept of the planning island and several algorithms derived from graph theory. The methodology is provably correct and all stated constraints are satisfied, thus ensuring that only feasible operating procedures are automatically synthesized. The methodology has been successfully applied to two industrial case studies: (a) the catalyst regeneration of powerforming reactors in a petroleum refinery; and (b) the planning of recovery procedures from faults in an ethylenediaminetetraacetic acid (EDTA) plant. The synthesis of operating plans for complete chemical plants is an interesting problem and one that has many practical applications. The thrust of a computer-based planning methodology should be toward increased automation, improvement in the efficiency of planning (planning should be achieved in polynomial time, wherever possible) and guarantees that the planning methodology produces correct (feasible) plans. It is also desirable that the plans generated are optimal, or at least cost efficient in their implementation. In developing this methodology, we have addressed the first three of these considerations within a modelling framework that is easy-to-use, menu-driven and which utilizes models with which process engineers are generally familiar. There has been an implicit tradeoff between safety (correctness) and optimality. Future work should address the issue of the completeness of the methodology (i.e. if a feasible plan exists, it will be found) which can not be currently guaranteed without the exhaustive (and practically infeasible) generate-and-test approach.

关键词： Mixing

来源：评论

学校读者我要写书评

暂无评论

DIAGNOSIS USING BACKPROPAGATION NEURAL NETWORKS - ANALYSIS AND CRITICISM

引用

COMPUTERS & CHEMICAL engineering 1990年第12期14卷 1323-1338页

作者： KRAMER, MA LEONARD, JA Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

Artificial neural networks based on a feedforward architecture and trained by the backpropagation technique have recently been applied to static fault diagnosis problems. The networks are used to classify measurement vectors into a set of predefined categories that represent the various functional and malfunctional states of the process. While the networks can usually produce decision surfaces that correctly classify the training examples, regions of the input space not occupied by training data are classified arbitrarily. As a result, the networks may not accurately extrapolate from the training data. Although extrapolation is not required under ideal circumstances, in practice the network may be required to extrapolate when undersized training sets are used, when parent distributions of fault classes undergo shifts subsequent to training, and when the input data is corrupted by missing or biased sensors. These situations cause relatively high error rates for the neural classifier. A related probem is that the networks cannot detect when they lack the data for a reliable classification, a serious deficiency in many practical applications. Classifiers based on distance metrics assign regions of the input space according to their proximity to the training data, and thus extrapolation is not arbitrary but based on the most relevant data. Distance-based classifiers perform better under nonideal conditions and are to be preferred to neural network classifiers in diagnostic applications.

关键词： Neural Networks

来源：评论

学校读者我要写书评

暂无评论

MODEL LA - A MODELING LANGUAGE FOR process engineering .2. MULTIFACETED MODELING OF processING systems

引用

COMPUTERS & CHEMICAL engineering 1990年第8期14卷 847-869页

作者： STEPHANOPOULOS, G HENNING, G LEONE, H Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

Multifaceted (multiview, multicontext, multilevel) modeling of processing systems is a central requirement for further automation of process engineering tasks. This paper describes how the formal framework of ***., established in Part I, is being used to construct multifaceted models of processing systems. More specifically, it shows how ***. (a) can access multiple views of a model; (b) generate contextual models; and (c) establish consistency among multiple, concurrent models developed at different levels of abstraction. The procedures carrying out these operations are described and a series of illustrations is used to clarify the various concepts.

关键词： Chemical Operations

来源：评论

学校读者我要写书评

暂无评论

MODEL LA - A MODELING LANGUAGE FOR process engineering .1. THE FORMAL FRAMEWORK

引用

COMPUTERS & CHEMICAL engineering 1990年第8期14卷 813-846页

A modeling language (***.) has been constructed for the interactive or automatic definition of models for processing systems. It is based on six modeling elements and 11 semantic relationships obeying basic axioms of transitivity, monotonicity, commutativity and merging. Its syntax can be described by an extended BNF (Backus—Naur Form). The structure of process models is depicted by specific digraphs, which are symbolically constructed by algorithmic procedures driven by the context of the modeling activity. ***. can generate models of processing systems: (a) at various levels of abstraction; (b) capturing qualitative, semiquantitative and quantitative knowledge; (c) with complete documentation of the modeling context (assumptions, simplifications, process engineering task). Its object-oriented modularity makes it extensible and easily maintainable. Although a large part of ***. is domain-independent, its vocabulary and syntax is specific to process engineering activities such as: process development, design, control and operations. A language for modeling processing systems, called ***., has been presented. Realizing the limitations of the previous procedural attempts, it is based on an object-oriented, declarative approach. The language has been designed to be capable of: (i) expressing all points of interest assumed to be needed in modeling processing systems; (ii) representing processing systems at any level of detail; (iii) generating automatically the set of basic mathematical relationships that are describing the model components; and (iv) offering explicit documentation of all the assumptions that give rise to a particular model. It can be viewed as a very high-level special-purpose language, that moves the user several levels away from the inherent programming language (e.g. LISP, as in this case, Pascal or C). ***. complies with all the requirements that were proposed for its design. Its basic strengths are its modularity and its i

关键词： Chemical Operations

来源：评论

学校读者我要写书评

暂无评论

IMPROVEMENT OF THE BACKPROPAGATION ALGORITHM FOR TRAINING NEURAL NETWORKS

引用

COMPUTERS & CHEMICAL engineering 1990年第3期14卷 337-341页

作者： LEONARD, J KRAMER, MA Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 U.S.A.

The application of artificial neural networks (ANNs) to chemical engineering problems, notably malfunction diagnosis, has recently been discussed (Hoskins and Himmelblau, Comput. chem. Engng 12 , 881–890, 1988). ANNs “learn”, from examples, a certain set of input-output mappings by optimizing weights on the branches that link the nodes of the ANN. Once the structure of the input-output space is learned, novel input patterns can be classified. The backpropagation (BP) algorithm using the generalized delta rule (GDR) for gradient calculation (Werbos, Ph.D. Thesis, Harvard University, 1974), has been popularized as a method of training ANNs. This method has the advantage of being readily adaptable to highly parallel hardware architectures. However, most current studies of ANNs are conducted primarily on serial rather than parallel processing machines. On serial machines, backpropagation is very inefficient and converges poorly. Some simple improvements, however, can render the algorithm much more robust and efficient.

关键词： Neural Networks

来源：评论

学校读者我要写书评

暂无评论

INTEGRATED APPROACH USING NEURAL NETWORKS FOR FAULT-DETECTION AND DIAGNOSIS

INTEGRATED APPROACH USING NEURAL NETWORKS FOR FAULT-DETECTIO...

引用

INTERNATIONAL JOINT CONF ON NEURAL NETWORKS ( IJCNM-90 )

作者： YAMAMOTO, Y VENKATASUBRAMANIAN, V CIM Project Corporate Planning Department Furukawa Electric Company Limited Chiyoda Tokyo Japan Laboratory for Intelligent Process Systems School of Chemical Engineering Purdue University West Lafayette IN USA

An integrated approach using neural networks for detecting and diagnosing process failures is presented. The system, which consists of three major components, quantitative networks, qualitative networks, and inverse qualitative networks, effectively reduces the inherent ambiguity of forward-mapping neural networks by incorporating the inverse mapping neural networks, which corresponds to the mapping from the fault space to the symptom space, and identifies the most plausible case in a process. The system is tested on four kinds of possible fault groups, including novel single faults, two two-fault groups, and sensor faults. It is shown that, due to the successful integration of quantitative information and qualitative information associated with process data, the system can successfully and substantially improve the diagnostic performance without additional information

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying process Behavior with Neural Networks: Strategies for Improved Training and Generalization

Classifying Process Behavior with Neural Networks: Strategie...

引用

American Control Conference (ACC)

作者： James A. Leonard Mark A. Kramer Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA 02139 Laboratory for Intelligent Systems in Process Engineering Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA USA

Artificial neural networks trained by backpropagation have recently been applied to fault diagnosis problems. Backpropagation produces-decision surface that effectively separate training examples of different cases. However, separation of the training examples does not necessarily result in the most plausible or robust classifier. The decision surfaces may deviate from optimality and take on non-intuitive shapes because the decision surfaces are based on hyperplanes. This also results in backpropagation networks having no mechanism to detect when a case to be classified falls in a region with no training data. To remedy these difficulties a network is proposed which uses Radial Basis Functions instead of sigmoid threshold units. This network is compared to the standard backpropagation network on an prototypical example problem.

关键词： Neural networks Error analysis Backpropagation Artificial neural networks Testing Chemical sensors Fault diagnosis Robustness Shape Training data

来源：评论

学校读者我要写书评

暂无评论

A NEURAL NETWORK METHODOLOGY FOR process FAULT-DIAGNOSIS

引用

AICHE JOURNAL 1989年第12期35卷 1993-2002页

作者： VENKATASUBRAMANIAN, V CHAN, K Laboratory for Intelligent Process Systems School of Chemical Engineering Purdue University West Lafayette IN 47907

The ability of knowledge-based expert systems to facilitate the automation of difficult problems in process engineering that require symbolic reasoning and an efficient manipulation of diverse knowledge has generated considerable interest recently. Rapid deployment of these systems, however, has been difficult because of the tedious nature of knowledge acquisition, the inability of the system to learn or dynamically improve its performance, and the unpredictability of the system outside its domain of *** paper proposes a neural-network-based methodology for providing a potential solution to the preceding problems in the area of process fault diagnosis. The potential of this approach is demonstrated with the aid of an oil refinery case study of the fluidized catalytic cracking process. The neural-network-based system successfully diagnoses the faults it is trained upon. It is able to generalize its knowledge to successfully diagnose novel fault combinations it is not explicitly trained upon. Furthermore, the network can also handle incomplete and uncertain data. In addition, this approach is compared with the knowledge-based approach.

关键词： Chemical Operations

来源：评论

学校读者我要写书评

暂无评论

DEVELOPMENT OF A DIAGNOSTIC EXPERT SYSTEM FOR A WHIPPED TOPPINGS process

引用

JOURNAL OF LOSS PREVENTION IN THE process INDUSTRIES 1989年第3期2卷 145-154页

作者： RICH, SH VENKATASUBRAMANIAN, V NASRALLAH, M MATTEO, C Engineering Department Mobil Research and Development Corporation Princeton NJ 08540 USA Laboratory for Intelligent Process Systems Department of Chemical Engineering Purdue University West Lafayette IN 47907 USA General FoodsCorporation Technical Center 250 North Street White Plains NY 10625 USA

A diagnostic expert system for the whipped toppings process was developed in an effort to: improve product quality/consistency; improve process efficiency by reducing downtime; improve product yield by minimizing production of marginal product; and standardize diagnostic performance by further educating the plant operators. The expert system is PC-based and has been implemented using VP-Expert, a rule-based development tool, and VP-Info, a database management system. The main principles of operation are as follows. First, the expert system runs off-line and is triggered when the plant operator recognizes, during normal inspection, that a problem exists in the process or with the product. Then, the diagnostic expert system, acting as a consultant to the plant operator, seeks to locate the physical or process malfunctions that are the root causes of the observed process abnormalities. During the course of diagnostic consultations, the expert system serves to focus the attention of the plant operators and aids in coordinating the diagnostic activity of the plant operators and plant maintenance personnel. The expert system proposes corrective actions upon discovery of a malfunction in the plant. The system architecture is of a modular construction so that it may act as a template for future diagnostic expert systems. This paper also includes a discussion of lessons learned from experience in building the expert system.

关键词： fault administration process flexibility expert systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：