This paper describes a method to predict the fire resistance ratings of the wooden floor assemblies using Artificial Neural Networks. Experimental data collected from the previously published reports were used to train, validate, and test the proposed ANN model. A series of model configurations were examined using different popular training algorithms to obtain the optimal structure for the model. It is shown that the proposed ANN model can successfully predict the fire resistance ratings of the wooden floor assemblies from the input variables with an average absolute error of four percent. Besides, the sensitivity analysis was conducted to explore the effects of the separate input parameter on the output. Results from analysis revealed that the fire resistance ratings are sensitive to the change of Applied Load (ALD) and the number of the Ceiling Finish Layer (CFL) input variables. On the other hand, the outputs are less sensitive to a variation of the Joist Type (JTY) parameter.
Keywords:
artificial neural networks; fire resistance; wooden floor assembly; sensitivity analysis.
Nứt là hiện tượng khá phổ biến trong dầm bê tông cốt thép (BTCT). Các tiêu chuẩn hiện hành đều đưa ra công thức tính toán mô men nứt và bề rộng khe nứt thẳng góc nhưng có sự khác biệt đáng kể. Trong bài báo này, tác giả giới thiệu phương pháp tính toán mô men nứt và bề rộng khe nứt thẳng góc theo tiêu chuẩn Nga SP 63.13330.2012. Tiêu chuẩn này là cơ sở để chỉnh sửa tiêu chuẩn hiện hành TCVN 5574:2012 về thiết kế kết cấu bê tông và BTCT. Phương pháp tính toán sự hình thành và mở rộng khe nứt theo tiêu chuẩn SP 63.13330.2012 có thể thực hiện theo mô hình tải trọng giới hạn hoặc mô hình biến dạng phi tuyến. Ngoài ra, bài báo cũng trình bày nghiên cứu thực nghiệm 04 dầm BTCT trong điều kiện Việt Nam để xác định mô men nứt và bề rộng khe nứt thẳng góc của dầm. Từ đó sử dụng kết quả thực nghiệm để đánh giá khả năng áp dụng tính toán lý thuyết theo tiêu chuẩn Nga SP 63.13330.2012 cho thiết kế kết cấu BTCT trong điều kiện Việt Nam.
Nhận ngày 28/01/2018; sửa xong 12/02/2018; chấp nhận đăng 28/02/2018
Recently, the Microsoft Kinect sensor has provided the whole new type of data in computer vision, the depth information. The most important contribution of depth information is to overcome one of the hardest parts in visual information extraction, the segmentation process. Especially in human action recognition field, the depth data help reduce the noise and variance of background and illumination of the real world environment. But beside that, most of state-of-the-art approaches are still using the complex feature representation with quite long feature vectors and they lead to many other tasks to do to reduce the complexity of the whole system model. In this paper, we want to solve this problem using the Elliptical Density Shape (EDS) model that could provide the simplified geometric shape feature of any complex shape object through time sequences but still robust enough when applying in the recognition process.
The ultimate aim of this study is to use experimental work for evaluating the modulus of elasticity (MOE) of Geopolymer concrete (GPC) using marine sand as fine aggregate and seawater for the mix. Four different groups of concrete mixtures, namely CP1a, CP1b, CP2a, CP2b were identified. While the CP1a mix was prepared using GPC with marine sand and seawater, the CP1b was made by adding sodium sulfate (Na2SO4) into the CP1a mix. The same procedure was applied for CP2a and CP2b mixtures; however, instead of using GPC, Portland Cement was used as the binder for the CP2 group (OPC). A total of 12 test samples were cast and tested to determine the development of MOE of GPC and OPC over time. The MOE of concrete was measured at 3, 7, 28, 60, and 120 days. Experimental results were then compared to the MOE obtained using the empirical equation from ACI 318 - 2008. It was found that the experimental MOE of both OPC and GPC specimens was higher than the estimated MOE values from ACI standards. The added sodium sulfate yielded a significant effect on the MOE of OPC but produced a minimal influence on the MOE of GPC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.