عنوان مقاله
برآوردهای مفهومی هزینه با استفاده از شبکه عصبی هیبریدی فازی تکاملی برای پروژه های صنعت ساخت و ساز
فهرست مطالب
مقدمه
شبکه عصبی هیبریدی فوزی تکاملی (EFHNN)
برآوردکننده های مفهومی هزینه
نتایج و مقایسه ها
نتیجه گیری
بخشی از مقاله
شبکه عصبی هیبریدی فوزی تکاملی (EFHNN)
EFHNN پیشنهاد شده از چهار شیوه هوش مصنوعی یعنی شبکه عصبی (NN) ، شبکه عصبی مرتبه بالا (HONN)، منطق فوزی (FL) و الگوریتم ژنتیکی (GA) استفاده میکند (شکل 1). NN وHONN موتور استنباطی را تشکیل می دهند، به عبارتی شبکه عصبی هیبریدی پیشنهاد شده (HNN)؛ FL بر لایه های fuzzifier و defuzzifier حاکم می باشد؛ و GA HNN و FL را بهینه می سازد.
کلمات کلیدی:
Conceptual cost estimates using evolutionary fuzzy hybrid neural network for projects in construction industry Min-Yuan Cheng, Hsing-Chih Tsai *, Erick Sudjono Department of Construction Engineering, National Taiwan University of Science and Technology, Taiwan article info Keywords: Construction cost Conceptual estimates Genetic algorithm Fuzzy logic Neural network High order neural network Hybrid neural network abstract Conceptual cost estimates are important to project feasibility studies and impact upon final project success. Such estimates provide significant information that can be used in project evaluations, engineering designs, cost budgeting and cost management. This study proposes an artificial intelligence approach, the evolutionary fuzzy hybrid neural network (EFHNN), to improve conceptual cost estimate precision. This approach first integrates neural networks (NN) and high order neural networks (HONN) into a hybrid neural network (HNN), which operates with alternating linear and non-linear neuron layer connectors. Fuzzy logic (FL) is then used in the HNN to handle uncertainties, an approach that evolves the HNN into a fuzzy hybrid neural network (FHNN). As a genetic algorithm is employed on the FL and HNN to optimize the FHNN, the final version used for this study may be most aptly termed an ‘EFHNN’. For this study, estimates of overall and category costs for actual projects were calculated and compared. Results showed that the proposed EFHNN may be deployed effectively as an accurate cost estimator during the early stages of construction projects. Moreover, the performance of linear and non-linear neuron layer connectors in EFHNN surpasses models that deploy a singular linear NN. Crown Copyright 2009 Published by Elsevier Ltd. All rights reserved. 1. Introduction Cost estimates are fundamental to all project-related engineering and greatly influence planning, design, bidding, cost management/budgeting and construction management. Such estimates allow owners and planners to evaluate project feasibility and control costs effectively in detailed project design work. Due to the limited availability of information during the early stages of a project, construction managers typically leverage their knowledge, experience and standard estimators to estimate project costs. As such, intuition plays a significant role in decision making. Researchers have worked to develop cost estimators that maximize the practical value of limited information in order to improve the accuracy and reliability of cost estimation work and thus enhance the suitability of resultant designs and project execution work. Statistical methods have traditionally been used to develop cost estimating models (Singh, 1990). While regression analysis represents a common alternative (Bowen & Edwards, 1985; Khosrowshahi & Kaka, 1996), an inherent disadvantage is the requirement of a defined mathematical form for cost functions. In general, all traditional methods are hampered in estimating accurate project costs by the large number of significant variables and interactions between these variables. Traditional methods, as a result, face significant limitations in application. Artificial intelligence approaches are applicable to cost estimation problems related to expert systems, case-based reasoning (CBR), neural networks (NNs), fuzzy logic (FL), genetic algorithms (GAs) and derivatives of such. Many research studies have been done in this area. For instance, an integrated knowledge-based system for alternative design decisions, materials selection and cost estimating used mainly in pre-design analysis was proposed by Mohamed and Celik (1998). Serpell (2004) proposed a model of this problem based on existing knowledge and demonstrated how the model could be used to develop a knowledge-based assessment system. Arditi and Suh (1991) developed an expert system that proposed decision criteria used in the classification of available cost estimating packages. An, Kim, and Kang (2007) developed a case-based reasoning model that incorporated experience using an analytic hierarchy process. Yau and Yang (1998) applied CBR to estimate construction project implementation duration and costs during the preliminary design stage. NNs represent the most frequently applied approach in this type of application. Wilmot and Mei (2005) developed an NN model to estimate highway construction cost escalation over time. Adeli and Wu (1998) also employed NNs to estimate highway construction cost and identified noise in the data. Williams (1994) used NNs to predict change in the ENR construction cost index and concluded that
