Some companies must transport their personnel within facilities. This is especially the case for oil companies that use helicopters to transport engineers, technicians and assistant personnel from platform to platform...
详细信息
Some companies must transport their personnel within facilities. This is especially the case for oil companies that use helicopters to transport engineers, technicians and assistant personnel from platform to platform. This operation has the potential to become expensive if the transportation routes are not correctly planned and provide a bad quality of service. Here this issue is modelled as a pick-up and delivery problem where a set of transportation requests should be scheduled in routes, minimizing the total transportation cost while the most urgent requests are satisfied by priority. To solve the problem, a method based on a non-dominatedsorting Genetic algorithm (NSGA-II) is proposed. This algorithm is tested on both randomly generated and real instances provided by a petroleum company. The results show that the proposed algorithm improves the best-known solutions.
This paper investigates the task scheduling problem for the Earth observation Interferometric Synthetic Aperture Radar (InSAR) satellite system. The mission time window generation method is introduced, and the constra...
详细信息
This paper investigates the task scheduling problem for the Earth observation Interferometric Synthetic Aperture Radar (InSAR) satellite system. The mission time window generation method is introduced, and the constraint satisfaction model for task scheduling in the InSAR satellite system is constructed. To address the mission allocation issue between the chief satellite and deputy satellites, a mission conflict detection and resolution mechanism is developed. Moreover, based on the single-objective student psychology-based optimization (SPBO) algorithm, a modified non-dominatedsorting SPBO (NSSPBO) algorithm is proposed to tackle the multi-objective task scheduling problem for the InSAR satellite system. Numerical simulations are presented to demonstrate the effectiveness and superiority of the proposed NSSPBO algorithm.
This study investigates the issue of multi-objective mission planning for multi-payload satellite constellations via the nondominatedsorting carnivorous plant algorithm (NSCPA). Observation time windows are generated...
详细信息
This study investigates the issue of multi-objective mission planning for multi-payload satellite constellations via the nondominatedsorting carnivorous plant algorithm (NSCPA). Observation time windows are generated, and a constraint satisfaction model is established based on multiple regional targets, satellite orbits, and characteristics of the synthetic aperture radar (SAR) payload and optical payload. A task conflict detection and resolution method is proposed to handle the task assignment among multiple satellites. Based on the existing single objective-based CPAs, a modified multi-objective NSCPA is first developed for multi-objective planning optimization using the non-dominated sorting algorithm. The effectiveness and superiority of the NSCPA are verified by a series of simulation experiments and comparisons with the traditional non-dominatedsorting genetic algorithms-II (NSGA-II) and particle swarm optimization (PSO).
Ammonia and hydrogen, as carbon-free clean energy, can be converted and applied in various scenarios. They can also be mixed to achieve synergistic efficiency. To promote the carbon-neutral development of heavy-duty v...
详细信息
Ammonia and hydrogen, as carbon-free clean energy, can be converted and applied in various scenarios. They can also be mixed to achieve synergistic efficiency. To promote the carbon-neutral development of heavy-duty vehicles, this paper studies an ammonia-hydrogen powertrain equipped with both a fuel cell and an engine (FCEAP). This powertrain efficiently allocates energy between multiple power sources and exploits the potential of ammonia-hydrogen synergy fuel. The modeling of FCEAP is based on experimental data obtained from engine bench tests, and the control strategy enables real-time control. Additionally, FCEAP undergoes multi-objective co-optimization using the non-dominated sorting algorithm-III (NSGA-III). By optimizing ammonia consumption, acceleration time, and manufacturing cost, Pareto solutions for the configuration and control strategy parameters are obtained. Furthermore, FCEAP is compared to ammonia-hydrogen powertrains equipped with either a fuel cell (FCAP) or an engine (EAP). The trade-off solutions indicate that FCEAP effectively balances energy consumption and manufacturing cost compared with FCAP and EAP. A comprehensive analysis of the energy flow distribution within various ammonia-hydrogen powertrains is conducted, revealing the operational processes and details of each component. The proposed ammonia-hydrogen powertrain represents an important technological pathway for achieving carbon neutrality in the future heavy-duty long-haul trucks industry.
This paper aims at multi-objective optimization of single-product for four-echelon supply chain architecture consisting of suppliers, production plants, distribution centers (DCs) and customer zones (CZs). The key des...
详细信息
This paper aims at multi-objective optimization of single-product for four-echelon supply chain architecture consisting of suppliers, production plants, distribution centers (DCs) and customer zones (CZs). The key design decisions considered are: the number and location of plants in the system, the flow of raw materials from suppliers to plants, the quantity of products to be shipped from plants to DCs, from DCs to CZs so as to minimize the combined facility location and shipment costs subject to a requirement that maximum customer demands be met. To optimize these two objectives simultaneously, four-echelon network model is mathematically represented considering the associated constraints, capacity, production and shipment costs and solved using swarm intelligence based Multi-objective Hybrid Particle Swarm Optimization (MOHPSO) algorithm. This evolutionary based algorithm incorporates non-dominated sorting algorithm into particle swarm optimization so as to allow this heuristic to optimize two objective functions simultaneously. This can be used as decision support system for location of facilities, allocation of demand points and monitoring of material flow for four-echelon supply chain network. (C) 2012 Elsevier Ltd. All rights reserved.
Virtual Machine (VM) migration has become quite prevalent in cloud computing. Numerous VM migration-oriented techniques are required for efficient VM allocation but continue to struggle due to incorrect energy usage i...
详细信息
Virtual Machine (VM) migration has become quite prevalent in cloud computing. Numerous VM migration-oriented techniques are required for efficient VM allocation but continue to struggle due to incorrect energy usage in the cloud model. Bio-inspired R&D-WOA (Re-initialization and Decomposition-Whale Optimization algorithm) is proposed by integrating WOA with NSGA-II algorithm to discover Pareto-optimal solutions. The proposed algorithm optimizes the allocation of the task to VM which diminishes the number of VM migrations, thereby lowering the migration cost and energy consumption. The efficiency of the Bio-inspired R&D-WOA is 67%, 7%, 1%, and 1.98% improved than the performance of existing WOA with regard to load, migration cost, energy utilized, and resource abundance respectively. At a similar level of load, it provided 24.80% efficiency in energy, 31.77% reduction in migration cost with maximal resource availability of 0.9917 compared to the ChicWhale algorithm.(c) 2022 The Authors. Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).
In order to have a competitive edge, manufacturing companies have to develop superior quality products at minimum cost. Tolerance design is the most critical part of concurrent engineering in which optimal values of t...
详细信息
In order to have a competitive edge, manufacturing companies have to develop superior quality products at minimum cost. Tolerance design is the most critical part of concurrent engineering in which optimal values of tolerances have to be determined for all components of an assembly, with due consideration towards the cost as well as quality. In this paper, tolerance design optimization of two products namely piston - cylinder & punch die assembly are considered. To solve the constraint-based optimization problems which are nonlinear and multi-objective in nature, novel techniques like Particle Swarm Optimization (PSO), and the nondominatedsorting Genetic algorithm II (NSGA II) have been used. The results of the piston-cylinder assembly have been compared to those of complicated and evolutionary techniques like Simulated (SA) and Genetic algorithms (GA). In addition, their performances have been examined.
The selection of model architecture and hyperparameters has a significant impact on the diagnostic performance of most deep learning models. Because training and evaluating the various architectures of deep learning m...
详细信息
The selection of model architecture and hyperparameters has a significant impact on the diagnostic performance of most deep learning models. Because training and evaluating the various architectures of deep learning models is a time-consuming procedure, manual selection of model architecture becomes infeasible. Therefore, we have proposed a novel framework for evolutionary deep neural networks that uses a policy gradient to guide the evolution of the DNN architecture towards maximum diagnostic accuracy. We have formulated a policy gradient-based controller that generates an action to sample the new model architecture at every generation so that optimality is obtained quickly. The fitness of the best model obtained is used as a reward to update the policy parameters. Also, the best model obtained is transferred to the next generation for quick model evaluation in the NSGA-II evolutionary framework. Thus, the algorithm gets the benefits of fast non-dominatedsorting as well as quick model evaluation. The effectiveness of the proposed framework has been validated on three datasets: the Air Compressor dataset, the Case Western Reserve University dataset, and the Paderborn University dataset.
暂无评论