摘要:

Abstract:The analysis of semirigid steel structure connections based on exact theoretical modeling, which is demanding and time consuming if all the nonlinear parameters of the problem are taken into account, can be avoided provided that enough experimental measurements exist and an appropriate predictor can be constructed from them. A supervised learning backpropagation neural network approach is proposed in this paper for the construction of this model free predictor. A number of experimental momentrotation curves for single‐angle and single‐plate beam‐to‐column connections are used in this paper to train the neural network. The trained network provides us with an estimator for the mechanical behavior of the steel structure connection

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00271.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:This paper presents an abridgment of a neural network constructive methodology and applications with real data. The neural network can be considered as the learning core and inference engine of an expert system that produces either different network designs or simulations as output, its input being data sequences. Basically, it consists of additive structural learning, limiting it by a cross‐validation technique.Considerations about uncertainty treatment in neural networks are also presented, including uncertainty in data, in neuron activation, in outputs, and combination of several uncertainty sources.Applications include three different sets of data, all of them related to the energy field. First, river streamflow estimation is discussed. Then CO2concentration prediction from gas injection rate is studied. Finally, the program learns to imitate a feedwater control system in a nuclear reactor. All tests show good results, as can be seen when compared with other standard method

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00272.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:Simple modeling schemes for efficient and reliable analysis of reinforced concrete structures in the inelastic range are presented. The objective of the modeling techniques is to represent overall behavior in terms of macromodels. A reinforced concrete structure is discretized into a series of macroelements: beam columns, shear walls, and general‐purpose inelastic springs. Each element macro‐model is developed from distributed flexibility concepts in which the effects of spread plasticity are implicitly included. Nonlinear material behavior is specified by means of hysteretic force‐deformation models that incorporate stiffness degradation, strength deterioration, and pinching or bondslip effects. The models are incorporated into a microcomputer program that is capable of analyzing two‐dimensional or entire three‐dimensional wall‐frame systems that can be discretized into a series of interconnected parallel frames. Solution modules for nonlinear static, monotonic, quasistatic cyclic, and transient seismic loads are developed. The efficiency and reliability of the modeling are demonstrated in terms of its effectiveness in reproducing experimentally observ

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00273.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:Owners of construction projects often make decisions regarding prequalification of contractors for a specific project. This paper describes a hypertext approach to enhance the contractor prequalification process. Relevant recent research is discussed, and potential benefits of using multiattribute decision making and hypertext information systems versus expert systems are explored. The developed prototype system uses the same criteria as QUALIFIER‐1 and allows the user to make a rational decision about assigning importance weights to various prequalification factors. The flexibility of the system in altering various weights for factors according to the project being considered is discussed. A database system and a procedural language linked to the hypertext system are added to automatically store relevant information about contractors for future reference and to calculate user's input, respectivel

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00274.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:A class of environmental information systems, called environmental decision support systems, is defined. The requirements for such systems are elaborated, and a software architecture that supports these requirements is developed. This architecture is then illustrated through the example of the Sandia Environmental Decision Support System (SEDSS). The SEDSS is a family of workstation applications based on the architecture developed by AT&T Bell Laboratories and prototyped in collaboration with the Environmental Restoration Organization of Sandia National Laboratories. Sharing a common user interface philosophy and software architecture, the members of the SEDSS family are designed to facilitate human decision making with respect to the hydrologic aspects of hazardous waste management. In order to achieve these objectives, the SEDSS family integrates geographic information systems, hydrologic models, Monte Carlo simulation, and a highly interactive graphical user interface, into a coherent software system based on the X Window System.This architecture is currently being applied to such similar environmental management problems as well‐head protection area analysis, in addition to nongroundwater problems such as coastal fisheries management. Applied research in environmental decision support systems continues in the areas of uncertainty management, treatment of qualitative parameters, and the human factors of environmental decision makin

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00275.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:Project acceleration often results in claims. A LISP program for performing time impact analysis for project acceleration is presented. The program helps the user identify the number of days by which the project can be accelerated and what the user's share will be of the acceleration costs involved. The program analyzes the as‐planned, as‐built, and utility data files submitted by the user and identifies all delayed, accelerated, added, and canceled (DAAC) activities. It then generates as‐planned, as‐built, projected, adjusted, owner‐accountable, and contractor‐accountable schedules. The program performs a compression analysis on the remaining portion of the project. After a consultation session with the user, it apportions acceleration costs between the owner and the contractor in an equitable way. This program is expected to help se

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00276.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY

摘要:

Abstract:The feasibility of using neural network models for evaluating CPT calibration chamber test data is investigated. The backpropagation neural network algorithm was used to analyze the data. After learning from a set of randomly selected patterns, the neural network model was able to produce reasonably accurate predictions for patterns not included in the training set. The neural network performance was found to be simpler and more effective than regression analysis for modeling the CPT test data. Correlations between the cone measurements and the engineering properties of sand can be developed using the generalization capabilities of the neural network.

ISSN:1093-9687    

DOI:10.1111/j.1467-8667.1995.tb00277.x

出版商:Blackwell Publishing Ltd    

年代:1995

数据来源: WILEY