Permanent magnet synchronous motors (PMSM) have been substantially used in electric vehicles (EVs) due to their advantages such as low loss, large torque, and high power density. With the continuous improvement of the...
详细信息
Permanent magnet synchronous motors (PMSM) have been substantially used in electric vehicles (EVs) due to their advantages such as low loss, large torque, and high power density. With the continuous improvement of the PMSM performance requirements, its heat dissipation has also attracted increasing attention. This paper proposes a cooling system to realize the heat dissipation of the motor through internal oil circulation and external water circulation. Meanwhile, to obtain the best cooling system parameters, an optimization framework is developed for heat dissipation optimization of the motor. First, the most suitable Latin hypercube sampling (LHS) method is selected for sampling through the Coordinates exchange algorithm. Second, we separately study the modeling accuracy of thirteen surrogate models and finally select the back propagation (BP) neural network model. Then, we use six multi-objective optimization algorithms (MOOAs) to optimize the model, and select the optimal solution via the utopian point method. Finally, the motor heat dissipation situation is effectively improved, and the effectiveness and reliability of the optimization framework are proved, which provides an alternative mean for the heat dissipation design optimization of the motor and has prominent practical significance.
Evaporation is a crucial component to be established in agriculture management and water engineering. Evaporation prediction is thus an essential issue for modeling researchers. In this study, the multilayer perceptro...
详细信息
Evaporation is a crucial component to be established in agriculture management and water engineering. Evaporation prediction is thus an essential issue for modeling researchers. In this study, the multilayer perceptron (MLP) was used for predicting daily evaporation. MLP model is as one of the famous ANN models with multilayers for predicting different target variables. A new strategy was used to enhance the accuracy of the MLP model. Three multi-objectivealgorithms, namely, the multi-objective salp swarm algorithm (MOSSA), the multi-objective crow algorithm (MOCA), and the multi-objective particle swarm optimization (MOPSO), were respectively and separately coupled to the MLP model for determining the model parameters, the best input combination, and the best activation function. In this study, three stations in Malaysia, namely, the Muadzam Shah (MS), the Kuala Terengganu (KT), and the Kuantan (KU), were selected for the prediction of the respective daily evaporation. The spacing (SP) and maximum spread (MS) indices were used to evaluate the quality of generated Pareto front (PF) by the algorithms. The lower SP and higher MS showed better PF for the models. It was observed that the MOSSA had higher MS and lower SP than the other algorithms, at all stations. The root means square error (RMSE), mean absolute error (MAE), percent bias (PBIAS), and Nash Sutcliffe efficiency (NSE) quantifiers were used to compare the ability of the models with each other. The MLP-MOSSA had reduced RMSE compared to the MLP-MOCA, MLP-MOPSO, and MLP models by 18%, 25%, and 35%, respectively, at the MS station. The MAE of the MLP-MOSSA was 2.7%, 4.1%, and 26%, respectively lower than those of the MLP-MOCA, MLP-MOPSO, and MLP models at the KU station. The MLP-MOSSA showed lower MAE than the MLP-MOCA, MLP-MOPSO, and MLP models by 16%, 18%, and 19%, respectively, at the KT station. An uncertainty analysis was performed based on the input and parameter uncertainty. The results indicated that
Current large-scale green cloud data centers (GCDCs) tend to consume a huge amount of energy and generate enormous carbon emissions. Existing studies have tried to solve this problem by either realizing prediction of ...
详细信息
Current large-scale green cloud data centers (GCDCs) tend to consume a huge amount of energy and generate enormous carbon emissions. Existing studies have tried to solve this problem by either realizing prediction of green energy, or optimizing task scheduling. In contrast, this work seamlessly combines green energy prediction and task scheduling to jointly optimize revenue and energy cost of GCDCs. Specifically, this work designs a prediction method, named Savitzky-Golay and Long Short-Term Memory network (SG-LSTM), to realize noise filtering and forecast green energy. Based on such prediction, a bi-objectiveoptimization method, named Decomposition-based multi-objective evolutionary algorithm with Gaussian mutation and Crowding distance (DMGC), is developed to optimize the revenue and energy cost of GCDCs. Its performance is demonstrated over real-life datasets including Google cluster traces, wind speeds, solar irradiance and prices of electricity. Experimental results show that SG-LSTM outperforms its two peers, back propagation neural network and gated recurrent unit, in terms of root mean square errors and mean absolute errors. In addition, DMGC surpasses its such peers as NSGA-II, SPEA2, and MOEA/D in terms of revenue, energy cost and average execution time. Particularly, DMGC's revenue is 18%, 20% and 13.1% higher, energy cost is 16%, 19.8% and 15.2% lower, and average execution time is 60.02%, 38.47% and 24.17% lower than those of NSGA-II, SPEA2, and MOEA/D, respectively.
A controllable multi-frequency absorption structure predicated on a one-dimensional magnetized ferrite photonic crystals (MFPCs) that achieves coherent perfect absorption is designed and further analyzed by utilizing ...
详细信息
A controllable multi-frequency absorption structure predicated on a one-dimensional magnetized ferrite photonic crystals (MFPCs) that achieves coherent perfect absorption is designed and further analyzed by utilizing the transfer matrix method. By introducing the filter structures to the MFPC and using the gradient descent optimizationalgorithms to optimize its layer parameters, the multi-frequency coherent absorption curve is obtained. The suggested MFPC brings out about six absorption peaks whose absorptance can be higher than 0.99 at the same time under the transverse electric mode. Moreover, the absorptance can be regulated from 0.99 to less than 0.1 by merely changing the phase deviation between the two incident waves to the front and rear surfaces. Besides, the studied results demonstrate that the intensity of coherent absorption and the position of absorption peaks can be adapted by altering the magnetic field and the thicknesses of ferrite layers. It follows that the absorption peaks can cover most frequency points from 58.6 to 65.9 THz via changing the thicknesses of the external magnetic field and ferrite layers. Moreover, the structure also has the potential for wide-angle absorption. This research furnishes a significant reference for the design of the multi-frequency absorption optoelectronic device and phase sensor.
Trading strategies are usually employed for finding trading signals for increasing returns as well as reducing risks. As a result, many approaches have been proposed for obtaining trading strategy portfolio. The group...
详细信息
ISBN:
(纸本)9783030732790;9783030732806
Trading strategies are usually employed for finding trading signals for increasing returns as well as reducing risks. As a result, many approaches have been proposed for obtaining trading strategy portfolio. The group trading strategy portfolio (GTSP) optimization approaches that can be used to provide various trading strategy portfolios were also proposed. Because different criteria should be considered to derive GTSPs, a MOGA (multi-objective genetic algorithm) based approach has been presented for searching non-dominated solutions. In this paper, to extract a better set of non-dominated solutions, we propose a SPEA-based algorithm for deriving GTSPs with two objective functions. Since the goal of trading is to get profit, the first objective function is utilized to evaluate the return and risk of a candidate GTSP. The second objective function is used to evaluate whether the numbers of strategies between groups are similar and weights of groups as well. Experiments were conducted on a financial dataset to show the effectiveness of the proposed approach and comparison results of the proposed approach and the previous approach.
Featured Application This paper proposes a computationally efficient algorithm for base placement in automatic multi-robot vehicle painting. The proposed algorithm incorporates the CAD model of the vehicle the manufac...
详细信息
Featured Application This paper proposes a computationally efficient algorithm for base placement in automatic multi-robot vehicle painting. The proposed algorithm incorporates the CAD model of the vehicle the manufacturer is interested in painting and the kinematic parameters of the robotic manipulators (e.g., their Denavit-Hartenberg parameters). The algorithm computes the robot's optimal fixed base positions. The base positions can subsequently be utilized by already available robotic path/motion *** This paper investigates the problem of optimal base placement in collaborative robotic car painting. The objective of this problem is to find the optimal fixed base positions of a collection of given articulated robotic arms on the factory floor/ceiling such that the possibility of vehicle paint coverage is maximized while the possibility of robot collision avoidance is minimized. Leveraging the inherent two-dimensional geometric features of robotic car painting, we construct two types of cost functions that formally capture the notions of paint coverage maximization and collision avoidance minimization. Using these cost functions, we formulate a multi-objectiveoptimization problem, which can be readily solved using any standard multi-objective optimizer. Our resulting optimal base placement algorithm decouples base placement from motion/trajectory planning. In particular, our computationally efficient algorithm does not require any information from motion/trajectory planners a priori or during base placement computations. Rather, it offers a hierarchical solution in the sense that its generated results can be utilized within already available robotic painting motion/trajectory planners. Our proposed solution's effectiveness is demonstrated through simulation results of multiple industrial robotic arms collaboratively painting a Ford F-150 truck.
The hybrid microgrid system is based principally on renewable energy resources to avoid problems encountered from the use of conventional energy sources. The paper deals with the sizing problem of the hybrid microgrid...
详细信息
The hybrid microgrid system is based principally on renewable energy resources to avoid problems encountered from the use of conventional energy sources. The paper deals with the sizing problem of the hybrid microgrid system that consists of multiple resources, otherwise, a method to compare the multi-objectivealgorithms is proposed based on the Six Sigma approach. Three multi-objective optimization algorithms, namely MOPSO, PESA II, and SPEA2 are applied to design the hybrid PV/wind/diesel/battery system. Furthermore, three objective functions are considered;the Net Present Cost, the penalty cost of emission and the quantity of the CO2 released into the atmosphere, subject to multiple constraints such as LPSP (system reliability), the availability and renewable fraction. Besides that, this paper evaluated the project feasibility by calculating the LCOE and the dumped energy quantity that will be consumed by a dump load. The results showed that the SPEA2 is the better algorithm using the probabilistic and statistical approach of Six Sigma with a hybrid power system of 24445 $ as NPC. It is observed that the microgrid design which respect the reliability and availability both has more credibility. However, the microgrid designed satisfied all constraints with a competitive cost of energy.
In order to raise the quality of higher order mutation testing, in this paper, we propose an approach for effect improving of multi-objective optimization algorithms which can be used in the field of higher order muta...
详细信息
ISBN:
(纸本)9783030383640;9783030383633
In order to raise the quality of higher order mutation testing, in this paper, we propose an approach for effect improving of multi-objective optimization algorithms which can be used in the field of higher order mutation testing in order to reduce the number of generated mutant, generate the hard-to-kill mutant and construct the quality higher order mutants. We have performed an empirical evaluation with 20 real-word, open-source projects and 10 multi-objective optimization algorithms (including 5 original algorithms and 5 corresponding modification algorithms) to evaluate experimental results as well as bring out some opinions to effectiveness apply multi-objective optimization algorithms into higher order mutation testing. The study results indicate that our approach is an effectiveness one to get better the quality of higher order mutation testing.
Resource consumption in the production line has become an important consideration. The energy consumption and processing time of the jobs meet the resource consumption function in the production line with variable ser...
详细信息
ISBN:
(纸本)9781728176871
Resource consumption in the production line has become an important consideration. The energy consumption and processing time of the jobs meet the resource consumption function in the production line with variable service rate. This paper applies NSGAII to the conveyor-serviced production station (CSPS) considering energy consumption, and establishes a detailed semi-Markov decision process (SMDP) that optimizes the maximum processing rate and the minimum energy consumption at the same time. This paper proposes a two-population co-evolution algorithm(TPCA), which is applied to the NSGAII algorithm. On this basis, this paper also proposes a divergence strategy(DS) to improve the exploration ability of multi-objectiveoptimization algorithm .The experimental results reveal that the proposed algorithms are more adequate for pareto front exploration and find more solutions for decision makers.
This study proposes a novel multi-objective integer programming model for a collision-free discrete drone path planning problem. Considering the possibility of bypassing obstacles or flying above them, this study aims...
详细信息
ISBN:
(纸本)9781728169293
This study proposes a novel multi-objective integer programming model for a collision-free discrete drone path planning problem. Considering the possibility of bypassing obstacles or flying above them, this study aims to minimize the path length, energy consumption, and the accumulated maximum path risk simultaneously. The static environment is represented as 3D grid cells. Due to the NP-hardness nature of the problem, several state-of-the-art evolutionary multi-objectiveoptimization (EMO) algorithms with customized crossover and mutation operators are applied to find a set of non-dominated solutions. The results show the effectiveness of applied algorithms in solving several generated test cases.
暂无评论