摘要:

Today's state-of-the-art expert systems are plagued by four major problems: brittleness, lack of metaknowledge, knowledge acquisition, and validation. Knowledge acquisition by itself is a very time consuming and tedious process. The uncertainty of information and erroneous data have also caused knowledge engineers anxious moments. In order to address these problems, several machine learning techniques supported by well-formulated theories and algorithms, have been developed. In this article some of these techniques are reviewed along with examples of their application to civil engineering problems. The techniques presented either fall under the category “learning from examples” (commonly referred to as inductive learning) including the ID3 algorithm, the rough sets theory, and the PROTOS algorithm, or “learning from observations” (also known as conceptual clustering) including the COBWEB algorithm, or a combination of both.

ISSN:0263-0257    

DOI:10.1080/02630259608970203

出版商:Taylor & Francis Group    

年代:1996

数据来源: Taylor

摘要:

In moment-based reliability analysis, the probability of failure is calculated from a probability distribution fitted to the first few calculated moments of a limit state function. The calculation of the moments and the distributions fitting in the analysis are described. We suggest using the point estimate method to calculate the moments of the limit state function. A probability distribution from the Gram-Charlier series type A distributions or the Johnson family of distributions is selected to fit the calculated moments. The method, in general, does not require knowledge of the probability distributions of the basic random variables involved in the limit state function but their statistical moments. The method is simple to implement and can be used directly with an available deterministic computer program because it does not require iteration or derivatives of the limit state function.

ISSN:0263-0257    

DOI:10.1080/02630259608970204

出版商:Taylor & Francis Group    

年代:1996

数据来源: Taylor

摘要:

Even though consumers are situated along links of water supply networks and thus water is withdrawn at different points along links, the usual network analysis procedures assume node-concentrated demands. An analysis methodology that considers consumption along links and thus link-distributed demands is developed. Necessary equations are formulated and their solution through the commonly used methods is described. An illlustrative example that compares the analysis results considering link-distributed demands with that considering node-concentrated demands is provided. As illustrated, the available nodal heads are generally lower for link-distributed demands than those for node-concentrated demands. Thus, a network that may be satisfactory considering node-concentrated demands may become unsatisfactory when link-distributed demands are considered.

ISSN:0263-0257    

DOI:10.1080/02630259608970205

出版商:Taylor & Francis Group    

年代:1996

数据来源: Taylor

摘要:

Existing resource allocation models schedule activities by balancing resource requirement with resource availability using the resource available profile as a constraint to guide the scheduling process. The given resource available profile, however, may not be the best configuration for the project. Consequently, the resource available profile may have to be modified to produce improved resource utilization. With each modification the activities have to be rescheduled to meet resource availability constraints. A model is presented herein which is able to generate activity schedules that is optimal with respect to the resource available profile that is configured interactively with the schedule for minimum resource idling. The entire project is subdivided into separate resource contracts. The model then employs genetic algorithm (GA) to determine the start times of the activities and simultaneously self-adjust the resource hiring levels and end-dates for each contract in order to minimize the objective function. Results show that the model can provide schedules and corresponding resource available profiles that yield considerable savings in idle resources even in multi-resource problems.

ISSN:0263-0257    

DOI:10.1080/02630259608970206

出版商:Taylor & Francis Group    

年代:1996

数据来源: Taylor

ISSN:0263-0257    

DOI:10.1080/02630259608970207

出版商:Taylor & Francis Group    

年代:1996

数据来源: Taylor