Prediction of slope stability using artificial neural network (case study: Noabad, Mazandaran, Iran)

2009 ◽  
Vol 2 (4) ◽  
pp. 311-319 ◽  
Author(s):  
A. J. Choobbasti ◽  
F. Farrokhzad ◽  
A. Barari
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Slope Stability ◽  
Artificial Neural

Freeway Slope Stability Evaluation Based on Multi-Level Fuzzy Neural Network

2012 ◽  
Vol 430-432 ◽  
pp. 1700-1703
Author(s):  
Yan Kai Wu ◽  
Xian Song Sang ◽  
Bin Niu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Slope Stability ◽  
Basic Principle ◽  
Fuzzy Neural Network ◽  
Stability Assessment ◽  
High Slope ◽  
Fuzzy Neural ◽  
Multi Level ◽  
Artificial Neural

On the basis of introduced basic principle of fuzzy-artificial neural network, this article constructed a slope stability assessment index system with multi-level fuzzy neural network, and made detailed evaluation criterion according to the assessment characteristics of slope stability. Through introducing the basic principle of multi-level comprehensive assessment from fuzzy mathematics and artificial neural network theory, it overcomes the defect of difficult to be quantified in evaluation process of slope stability. Therefore, it can be better to deal with some uncertain problems occurred in the slope stability assessment process, and as much as possible to express all factors influencing slope stability really and objectively. We selected 20 single factor evaluation indexes to assess slope stability based on surveying the high slope stability in Mian county-Ningqiang county freeway section. It took "normal distribution model function" as a membership function to develop a program with the model of fuzzy neural network. Furthermore, we took 30 typical slope examples as training sample to conduct effectiveness test and feedback test for the program. After the precision requirement was met, we used the program to evaluate 21 high slope examples and compared the results with the ones solved by traditional mechanical methods. The coincidence degree by using two kinds of methods to assess the same slope stability is 76.2%.

Knowledge-Based Design of Artificial Neural Network Topology for Additive Manufacturing Process Modeling: A New Approach and Case Study for Fused Deposition Modeling

2018 ◽  
Vol 141 (2) ◽  
Author(s):  
Hari P. N. Nagarajan ◽  
Hossein Mokhtarian ◽  
Hesam Jafarian ◽  
Saoussen Dimassi ◽  
Shahriar Bakrani-Balani ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Additive Manufacturing ◽  
Fused Deposition Modeling ◽  
Expert Knowledge ◽  
Fused Deposition ◽  
Knowledge Based ◽  
Deposition Modeling ◽  
Artificial Neural

Additive manufacturing (AM) continues to rise in popularity due to its various advantages over traditional manufacturing processes. AM interests industry, but achieving repeatable production quality remains problematic for many AM technologies. Thus, modeling different process variables in AM using machine learning can be highly beneficial in creating useful knowledge of the process. Such developed artificial neural network (ANN) models would aid designers and manufacturers to make informed decisions about their products and processes. However, it is challenging to define an appropriate ANN topology that captures the AM system behavior. Toward that goal, an approach combining dimensional analysis conceptual modeling (DACM) and classical ANNs is proposed to create a new type of knowledge-based ANN (KB-ANN). This approach integrates existing literature and expert knowledge of the AM process to define a topology for the KB-ANN model. The proposed KB-ANN is a hybrid learning network that encompasses topological zones derived from knowledge of the process and other zones where missing knowledge is modeled using classical ANNs. The usefulness of the method is demonstrated using a case study to model wall thickness, part height, and total part mass in a fused deposition modeling (FDM) process. The KB-ANN-based model for FDM has the same performance with better generalization capabilities using fewer weights trained, when compared to a classical ANN.

Sign in / Sign up

Export Citation Format

Share Document