Artificial intelligence techniques are important tools for modelling and optimizing the solid-state fermentation (SSF) factors. The performance of fermentation processes is affected by numerous factors, including temp...
详细信息
Artificial intelligence techniques are important tools for modelling and optimizing the solid-state fermentation (SSF) factors. The performance of fermentation processes is affected by numerous factors, including temperature, moisture content, agitation, inoculum level, carbon and nitrogen sources, etc. In this paper, the identification of non-linear relationship between fermentation factors and targeted objectives is performed, first, using the learning capabilities of a neural network (NN). Then, this approach is coupled with various artificial intelligence techniques to optimize the fermentation process, such as Genetic algorithm (GA) and Particle swarmoptimization (PSO). The effectiveness of different approaches is compared with the classical statistical techniques, such as Response Surface Methodology (RSM), that are increasingly being used. This paper presents the first attempt to adapt these approaches on the solid state fermentation process. The obtained results prove the effectiveness of the proposed approach. Particularly, we show that this approach leads to a significant improvement on the fermentation process performance. Biotechnol. & Biotechnol. Eq. 2012, 26(6), 3443-3450
swarm intelligence (SI) approaches are a group of populace-dependent, nature influenced meta-heuristic approaches that are impressed via collective intelligence of homogeneous insects, birds, etc. These algorithms sim...
详细信息
ISBN:
(纸本)9789811059032;9789811059025
swarm intelligence (SI) approaches are a group of populace-dependent, nature influenced meta-heuristic approaches that are impressed via collective intelligence of homogeneous insects, birds, etc. These algorithms simulate the behaviour of the group of homogeneous biological entities to get a global ideal solution in optimization problems, where classical optimizationalgorithms may fail. Examples consist of a flock of birds, colonies of bees, colonies of ants, school of fish, etc. This paper presents a comparative study of different swarm intelligence approaches: particlesswarmoptimization (PSO) algorithm, intelligent water drop (IWD) approach, artificial bee colony (ABC) algorithm and ant colony optimization (ACO) algorithm for the optimization of single-layer neural networks.
In the last three decades, an integrated approach to optimize logistics system is considered as one of the most important aspects of optimizing supply chain management. This approach involves the ties between location...
详细信息
In the last three decades, an integrated approach to optimize logistics system is considered as one of the most important aspects of optimizing supply chain management. This approach involves the ties between locations of facility, allocation of suppliers/customers, structure of transportation routes and inventory control. The aim of this paper is to investigate the ordering planning of a supply chain with multi supplier, multi distribution center, multi customer and one perishable raw material. This paper provides a mathematical model taking in consideration the limitation of raw material corruptibility (perishable material) which belongs to the category of NP-hard problems. To solve the proposed model, the Ant Colony optimizationalgorithm (ACO) and Particle swarmoptimizationalgorithm (PSO) are employed. In order to improve performances of ACO and PSO parameters, a Taguchi experimental design method was applied to set their proper values. Besides, to evaluate the performance of the proposed model, an example of the dairy industry is analyzed by using MATLAB R 2015a. To validate the proposed meta-heuristic algorithms, the results of them were compared with together. The results of the comparison show that ACO is greater than PSO in speed convergence rate and the number of solutions iterations.
An improved strategy particle swarmoptimizationalgorithm is proposed to solve the dynamic load economic dispatch problems in power systems. Many constraints such as ramp rate limits and prohibited zones are tak...
详细信息
An improved strategy particle swarmoptimizationalgorithm is proposed to solve the dynamic load economic dispatch problems in power systems. Many constraints such as ramp rate limits and prohibited zones are taken into account, and the loss is also calculated. On the basis of strategy particle swarmoptimizationalgorithm, a new improved strategy is provided to handle the constraints and make sure the particles to satisfy the constraints. The strategy can guarantee the particles to search in or around the feasible solutions area combined with penalty functions. The accuracy and speed of the algorithm are improved for the particles will rarely search in the infeasible solutions area, and the results also show that the new algorithm has fast speed, high accuracy and good convergence.
暂无评论