Musa Hakan Arslan

A new application area of ANN and ANFIS: determination of earthquake load reduction factor of prefabricated industrial buildings

The earthquake load reduction factor, R, is one of the most important parameters in the design stage of a building. Significant damages and failures were experienced on prefabricated reinforced concrete structures during the last earthquakes in Turkey and the experts agreed that they resulted mainly from the incorrectly selected earthquake load reduction factor, R. In this study, an attempt was made to estimate the R coefficient for prefabricated industrial structures having a single storey, one and two bays, which are commonly constructed for manufacturing and warehouse operation with variable dimensions. According to the selected variable dimensions, 280 sample (140 samples for one bay (S-1) and 140 samples for two bays (S-2)) frames’ load–displacement relations were computed using pushover analysis and the earthquake load reduction factor, R, was calculated for each frame. Then, formulated three-layered artificial neural network methods (ANNs) and adaptive neuro-fuzzy inference system (ANFIS) were trained by using 214 of the 280 sample frames. Then, the methods were tested with the other 66 sample frames. Accuracy rates were found to be about 94% and 96% for ANN and ANFIS, respectively. The use of ANN and ANFIS provided an alternative way for estimating the R and it also showed that ANFIS estimated R more successfully than ANN.

AN ANN APPROACHES ON ESTIMATING EARTHQUAKE PERFORMANCES OF EXISTING RC BUILDINGS

This study aims at developing an artificial intelligence-based (ANN based) analytical method to analyze earthquake performances of the reinforced concrete (RC) buildings. In the scope of the present study, 66 real RC buildings with four to ten storeys were subject to performance analysis according to 19 parameters considered effective on the performance of RC buildings. In addition, the level of performance of these buildings in case of an earthquake was determined on the basis of the 4-grade performance levels specified in Turkish Earthquake Code-2007 (TEC-2007). Thus, an output performance data group was created for the analyzed buildings, in accordance with the input data. Thanks to the ANN- based fast evaluation algorithm mentioned above and developed within the scope of the proposed project study, it will be possible to make an economic and rapid evaluation of four to ten-storey RC buildings in Turkey with great accuracy (about 80%). Detection of post-earthquake performances of RC buildings in the scope of the present study will facilitate reaching important results in terms of buildings, which will be beneficial for Civil Engineers of Turkey and similar countries.

Results and lessons learned from the buildings which failed under their own weight in Turkey

The Zumrut Apartment Building in Turkey collapsed completely and suddenly on February 2, 2004, killing 92 people. A few months later, on October 29, 2004, cracks occurred on two reinforced concrete columns in the basement of the Altinbasak Apartment Building, about 500 m away from the Zumrut Building. In both cases the collapses occurred spontaneously, and were not related to an earthquake or other external causes. At the end of the investigations performed in situ and on the project documents, the main reasons for the collapse and damage were determined to be the mistakes made in the design load selection, the inappropriate dimensions of the load-carrying members, poor material quality, and poor soil conditions. The main aim of this study was to investigate the causes of the collapse and damage to these two buildings by considering the significant mistakes made during the design and construction stages. In addition, the research and observations performed on the buildings and the results from tests made on specimens taken from them, will be presented in this paper. A discussion of the values obtained from computer models of the buildings using the finite element method is also presented, and their relationship to the damages observed in the buildings, especially on the vertical load-bearing members.

Evaluation of a Gravity Load Designed Reinforced Concrete Structure Failed under its Own Weight due to Creep in Concrete

Turkish building stock is commonly composed of reinforced concrete moment resisting frames. Recent earthquakes in Turkey resulted thousands of failed or heavily damaged residential houses and office buildings. In addition of the earthquake failures, reinforced concrete structures may also failed only under their own weight. There are several examples such as Hicret Apartment in Diyarbakir (1983), Zumrut Apartment in Konya, in central Anatolia, Huzur Apartment in Istanbul (2007). On February 2nd, 2004 a 9-story reinforced concrete building in Konya (Zumrut Apartment) collapsed leaving 92 people dead. The first author of the paper was governmentally charged about the investigation of the failure causes. Carrot samples were taken from the concrete columns and steel samples were obtained from the disaster area. The dimensions of the structural members were determined. The structure was modeled in three dimensional space and vertical collapse analyses were conducted. The one of the main cause of failure was determined as the creep of the concrete occurred in excessively loaded columns. The main reasons of the damages and failures were determined to be the insufficiency in material quality, mistakes made in load selection and the inappropriate load-carrying dimensions. The construction mistakes and not obeying the design drawings are the other flaws. In this paper detailed information about the structure, creep analyses and vertical collapse analyze results were depicted in understandable format.