Search

Planning of construction technical specifications (CTS) for deep foundations is critical for ensuring works performed safely. k-nearest neighbors (kNN) is regarded as a practical algorithm for case retrieval in a case-based reasoning (CBR) cycle to search for past similar plans for new plan making. The parameter k and neighbors' weights affect the performance of the CBR cycle deeply but kNN neglects the weights' effect on case retrieval. The massive and multisource data of CTS of deep foundations presents a challenge for retaining case data in a database and for decision making due to an inefficient data process of the traditional tool. This paper presents a new framework to integrate weighted k-nearest neighbors (kkNN) to improve the performance of a CBR system for technical planning of deep foundations. It contains two parts: (1) a process to deal with a large amount of data derived from CTS; and (2) kkNN to obtain similar cases considering k and the weights of neighbors'. The feasibility of the proposed approach is validated through a case study and the evaluation result shows that the approach enhances the performance of the CBR cycle in creating construction technical specifications in deep foundation projects. [ABSTRACT FROM AUTHOR]

On the basis of observed data and numerical calculations of dam structural responses, the back-analysis approach is usually used to determine the material parameters of a dam and its foundation. The reasonableness of the obtained result is related to the chosen structural responses and their observations and calculations. To advance the accuracy and efficiency of a back-analysis, some methods need to be adopted to implement the optimal selection for the preceding resource. The criterion of optimal selection is presented. The parameter sensitivity is taken as a key index of optimal selection. The uniform design method is combined with an artificial neural network and support vector machine to build the mapping relationship between multiple material parameters and dam structural responses at different positions. According to the preceding mapping relationship, models are proposed to calculate the sensitivity of a structural response on the material parameter. The parameter sensitivity-based method choosing the optimal resource is developed. One actual concrete gravity dam is taken as an example. The proposed method is used to implement the optimal selection of a back-analysis resource of an elastic modulus on a dam body and a deformation modulus on a dam foundation. The accuracy and efficiency of the optimal resource-based back-analysis is verified. [ABSTRACT FROM AUTHOR]

This paper introduces a new system that utilizes the advantages of boundary element analysis in structural engineering applications. A standardized building information model (BIM) for automated structural analysis and design of reinforced concrete plates based on the boundary element method (BEM) is proposed. Based on the model view definition approach, BIM standards are presented for the preprocessing and postprocessing of BEM analysis. Furthermore, standards are proposed for automated structural design of structural slab and beam elements based on the BEM analysis results. For each of the BIM components, standards are provided for the object structure, data flow, and graphical user interface (GUI). The extensibility of the software and applicability for a wide range of research and practical applications are considered in all the proposed standards. The system created can act as the basis for structural analysis and design of building floor and foundation problems. Object-oriented programming is used to implement the standards in a prototype. The prototype was verified by application to the solution of practical structural engineering problems. The performance of the proposed system is evaluated in terms of the modeling and the processing time required to analyze typical structural engineering applications using the prototype. [ABSTRACT FROM AUTHOR]