Design of steel frames by an enhanced moth-flame optimization algorithm

2017 ◽  
Vol 24 (1) ◽  
pp. 129-140 ◽  
Author(s):  
Saeed Gholizadeh ◽  
Hamed Davoudi ◽  
Fayegh Fattahi
Keyword(s):  
Optimization Algorithm ◽  
Steel Frames ◽  
Moth Flame Optimization Algorithm

scholarly journals Chaos-enhanced moth-flame optimization algorithm for global optimization

2019 ◽  
Vol 30 (6) ◽  
pp. 1144-1159 ◽  
Author(s):  
Hongwei LI ◽  
Jianyong LIU ◽  
Liang CHEN ◽  
Jingbo BAI ◽  
Yangyang SUN ◽  
...  
Keyword(s):  
Global Optimization ◽  
Optimization Algorithm ◽  
Moth Flame Optimization Algorithm

scholarly journals Optimization of Surface Roughness in Deep Hole Drilling using Moth-Flame Optimization

2019 ◽  
Vol 18 (3-2) ◽  
pp. 62-68
Author(s):  
Anis Farhan Kamaruzaman ◽  
Azlan Mohd Zain ◽  
Razana Alwee ◽  
Noordin Md Yusof ◽  
Farhad Najarian
Keyword(s):  
Surface Roughness ◽  
Optimization Algorithm ◽  
Feed Rate ◽  
Spindle Speed ◽  
Hole Drilling ◽  
P Value ◽  
Machining Parameters ◽  
Deep Hole ◽  
Deep Hole Drilling ◽  
Moth Flame Optimization Algorithm

This study emphasizes on optimizing the value of machining parameters that will affect the value of surface roughness for the deep hole drilling process using moth-flame optimization algorithm. All experiments run on the basis of the design of experiment (DoE) which is two level factorial with four center point. Machining parameters involved are spindle speed, feed rate, depth of hole and minimum quantity lubricants (MQL) to obtain the minimum value for surface roughness. Results experiments are needed to go through the next process which is modeling to get objective function which will be inserted into the moth-flame optimization algorithm. The optimization results show that the moth-flame algorithm produced a minimum surface roughness value of 2.41µ compared to the experimental data. The value of machining parameters that lead to minimum value of surface roughness are 900 rpm of spindle speed, 50 mm/min of feed rate, 65 mm of depth of hole and 40 l/hr of MQL. The ANOVA has analysed that spindle speed, feed rate and MQL are significant parameters for surface roughness value with P-value <0.0001, 0.0219 and 0.0008 while depth of hole has P-value of 0.3522 which indicates that the parameter is not significant for surface roughness value. The analysis also shown that the machining parameter that has largest contribution to the surface roughness value is spindle speed with 65.54% while the smallest contribution is from depth of hole with 0.8%. As the conclusion, the application of artificial intelligence is very helpful in the industry for gaining good quality of products.

School based optimization algorithm for design of steel frames

2018 ◽  
Vol 171 ◽  
pp. 326-335 ◽  
Author(s):  
Mohammad Farshchin ◽  
Mohsen Maniat ◽  
Charles V. Camp ◽  
Shahram Pezeshk
Keyword(s):  
Optimization Algorithm ◽  
Steel Frames ◽  
School Based

Moth Flame Optimization Algorithm Range-Based for Node Localization Challenge in Decentralized Wireless Sensor Network

2019 ◽  
Vol 10 (1) ◽  
pp. 82-109 ◽  
Author(s):  
Mihoubi Miloud ◽  
Rahmoun Abdellatif ◽  
Pascal Lorenz
Keyword(s):  
Swarm Intelligence ◽  
Optimization Algorithm ◽  
Dimensional Space ◽  
Fitness Function ◽  
Low Cost ◽  
Bat Algorithm ◽  
Wireless Sensor ◽  
Flower Pollination Algorithm ◽  
Node Localization ◽  
Moth Flame Optimization Algorithm

Recently developments in wireless sensor networks (WSNs) have raised numerous challenges, node localization is one of these issues. The main goal in of node localization is to find accurate position of sensors with low cost. Moreover, very few works in the literature addressed this issue. Recent approaches for localization issues rely on swarm intelligence techniques for optimization in a multi-dimensional space. In this article, we propose an algorithm for node localization, namely Moth Flame Optimization Algorithm (MFOA). Nodes are located using Euclidean distance, thus set as a fitness function in the optimization algorithm. Deploying this algorithm on a large WSN with hundreds of sensors shows pretty good performance in terms of node localization. Computer simulations show that MFOA converge rapidly to an optimal node position. Moreover, compared to other swarm intelligence techniques such as Bat algorithm (BAT), particle swarm optimization (PSO), Differential Evolution (DE) and Flower Pollination Algorithm (FPA), MFOA is shown to perform much better in node localization task.

Sign in / Sign up

Export Citation Format

Share Document