Interoperability Optimization using a modified PSO algorithm

An isotropic mechanical structure cannot withstand shocks, accidents, and mechanical loading. In this perspective, composite structures have been introduced to improve the performance of mechanical structures. We are interested in the study of laminates with the aim to find an optimal structure resistant to vibrations and buckling. To remedy the problem of vibrations and buckling, we use artificial intelligence methods to optimize the design of composite structures. As it is a typical method of artificial intelligence adapted to this studied problem, we use genetic algorithms based on a new genetic operator. In the present article, an optimization procedure based on the new genetic operator called genetic immigration operator is developed to determine the maximum buckling load and fundamental frequency of the laminated plate with plies oriented at -45•/45• ,0•, and 90•. The aim of this paper is the use of two different methods for their effectiveness. These optimization works consist of first maximizing the buckling load factor with UGA (Uniform Genetic Algorithm) and a new evolutionary search strategies called Immigration Genetic: SIG (Standard Immigration Genetic Algorithm) and AIG (Improved Genetic Immigration Algorithm) and second of solving a multi-objective problem with minimizing the cost and weight of the hybrid laminate made of the fibers of two composite materials. The resolution of this problem by the proposed genetic immigration approach is reinforced by the optimization of the CPU computation time which is due to the exploitation of the parallel architecture based on the multi-processor parallel computation.

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence Approach for Multi-Objective Design Optimization of Composite Structures: Parallel Genetic Immigration

Majdoubi¹

2020

“…A new mathematical model, which named Whale Optimization Algorithm (WOA), is introduced from the inspiration of humpback whales [35]. Similar to Particle Swarm Optimization (PSO) algorithm [40], WOA is a novel nature-inspired meta-heuristic optimization algorithm which mimics the social behaviour and hunting behaviour of humpback whales. WOA is chosen in this study due to its population-based meta-heuristic properties which is different than that of swarm intelligence-based algorithm.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Development of Whale Optimization Neural Network for Daily Water Level Forecasting

Louis¹

2019

Development of water level forecasting model is essential in flood prediction and water resources planning and management. Through accurate water level forecasting models, high efficiency in the usage of water resources as well as minimization of flood damage with proper management of future development can be achieved. Therefore, the objective of this paper was set to develop a novel artificial neural network (ANN) for predicting the water level of Batu Kitang river via the implementation of a metaheuristic algorithm, Whale Optimization Algorithm (WOA). WOA was used to train and optimized the ANN. To compare the reliability of Whale Optimization Neural Network (WONN) in predicting the water level at Batu Kitang river, WONN is compared against a conventional neural network, Levenberg-Marquardt Neural Network (LMNN). The predicted water level showed that WONN outperformed LMNN in various evaluation criterion. However, inaccurate predictions occurred on both WONN and LMNN, which shows that further improvements are required to boost the prediction performance.

“…Also there are several methods developed to solve the TP. A lot of factors affect deciding the objective functions like traffic quality which should be optimized like described in [1].The collected data about the problem is very important which help to get the real optimal solution of the problem like mentioned in [2].Recently TP could contain more than one objective function like transportation cost, delivery time … etc. which is called multi objective transportation problem (MOTP).…”

Section: Introductionmentioning

confidence: 99%

Solving Multi-Objective Transportation Problem Using Opportunity Cost Method

2020

In this paper, a simple method is proposed to get the best compromise solution of linear multi-objective transportation problem (MOTP). After getting the greater cost matrix, it is used the idea of opportunity cost method to get the solution. Using this method, we get an efficient solution, which is liked by decision maker. Also this method is simple and has less time. For the application of proposed method, numerical example is tested from the literature and is solved with proposed method which proved its efficiency.