Proton Exchange Membrane Fuel Cells (PEMFCs) are the main focus of their current development as power sources because they are capable of higher power density and faster start-up than other fuel cells. The humidificat...Proton Exchange Membrane Fuel Cells (PEMFCs) are the main focus of their current development as power sources because they are capable of higher power density and faster start-up than other fuel cells. The humidification system and output performance of PEMFC stack are briefly analyzed. Predictive control of PEMFC based on Support Vector Regression Machine (SVRM) is presented and the SVRM is constructed. The processing plant is modelled on SVRM and the predictive control law is obtained by using Particle Swarm Optimization (PSO). The simulation and the results showed that the SVRM and the PSO re-ceding optimization applied to the PEMFC predictive control yielded good performance.展开更多
Motivated by the fact that automatic parameters selection for Support Vector Machine(SVM) is an important issue to make SVM practically useful and the common used Leave-One-Out(LOO) method is complex calculation and t...Motivated by the fact that automatic parameters selection for Support Vector Machine(SVM) is an important issue to make SVM practically useful and the common used Leave-One-Out(LOO) method is complex calculation and time consuming,an effective strategy for automatic parameters selection for SVM is proposed by using the Particle Swarm Optimization(PSO) in this paper.Simulation results of practice data model demonstrate the effectiveness and high efficiency of the proposed approach.展开更多
Since in most practical cases the processing time of scheduling is not deterministic, flow shop scheduling model with fuzzy processing time is established. It is assumed that the processing times of jobs on the machin...Since in most practical cases the processing time of scheduling is not deterministic, flow shop scheduling model with fuzzy processing time is established. It is assumed that the processing times of jobs on the machines are described by triangular fuzzy sets. In order to find a sequence that minimizes the mean makespan and the spread of the makespan, Lee and Li fuzzy ranking method is adopted and modified to solve the problem. Particle swarm optimization (PSO) is a population-based stochastic approximation algorithm that has been applied to a wide range of problems, but there is little reported in respect of application to scheduling problems because of its unsuitability for them. In the paper, PSO is redefined and modified by introducing genetic operations such as crossover and mutation to update the particles, which is called GPSO and successfully employed to solve the formulated problem. A series of benchmarks with fuzzy processing time are used to verify GPSO. Extensive experiments show the feasibility and effectiveness of the proposed method.展开更多
Biologic behaviors are the principal source for proposing new intelligent algorithms. Based on the mechanism of the bio-subsistence and the bio-migration, this paper proposes a novel algorithm—Living Migration Algori...Biologic behaviors are the principal source for proposing new intelligent algorithms. Based on the mechanism of the bio-subsistence and the bio-migration, this paper proposes a novel algorithm—Living Migration Algorithm (LMA). The original contributions of LMA are three essential attributes of each individual: the minimal life-needs which are the necessaries for survival, the migrating which is a basal action for searching new living space, and the judging which is an important ability of deciding whether to migrate or not. When living space of all individuals can satisfy the minimal life-needs at some generation, they are considered as the optimal living places where objective functions will obtain the optima. LMA may be employed in large-scale computation and engineering field. The paper mostly operates LMA to deal with four non-linear and heterogeneous optimizations, and experiments prove LMA has better performances than Free Search algorithm.展开更多
A novel design method for determining the proportional-integral-derivative(PID) controller gains of an anti-aircraft artillery servo system with multiple performance specifications based on a particle swarm optimizati...A novel design method for determining the proportional-integral-derivative(PID) controller gains of an anti-aircraft artillery servo system with multiple performance specifications based on a particle swarm optimization (PSO) algorithm is proposed. First, a performance criterion evolution function combined with the system maximum displacement settling time, rise time, overshoot, steady state error, constant velocity tracking error and sine wave tracking error is defined. Second, the optimization problem of PID controller parameters and the searching procedure of PSO algorithm are constructed. Finally, the optimal or near optimal PID controller parameters are fast and easily obtained by solving the above optimization problem on the given controller parameter space following the PSO searching procedure. The simulation results show the effectiveness of the proposed controllers.展开更多
基金Project (No. 2003AA517020) supported by the Hi-Tech Researchand Development Program (863) of China
文摘Proton Exchange Membrane Fuel Cells (PEMFCs) are the main focus of their current development as power sources because they are capable of higher power density and faster start-up than other fuel cells. The humidification system and output performance of PEMFC stack are briefly analyzed. Predictive control of PEMFC based on Support Vector Regression Machine (SVRM) is presented and the SVRM is constructed. The processing plant is modelled on SVRM and the predictive control law is obtained by using Particle Swarm Optimization (PSO). The simulation and the results showed that the SVRM and the PSO re-ceding optimization applied to the PEMFC predictive control yielded good performance.
文摘Motivated by the fact that automatic parameters selection for Support Vector Machine(SVM) is an important issue to make SVM practically useful and the common used Leave-One-Out(LOO) method is complex calculation and time consuming,an effective strategy for automatic parameters selection for SVM is proposed by using the Particle Swarm Optimization(PSO) in this paper.Simulation results of practice data model demonstrate the effectiveness and high efficiency of the proposed approach.
基金The National Natural Science Foundation of China ( No.60774078)Innovation Foundation of Shanghai University ,Scientific Research Special Fund of Shanghai Excellent Young Teachers , Chenguang Project ( No.2008CG48)Shanghai Leading Academic Discipline Project ( No.T0103)
文摘Since in most practical cases the processing time of scheduling is not deterministic, flow shop scheduling model with fuzzy processing time is established. It is assumed that the processing times of jobs on the machines are described by triangular fuzzy sets. In order to find a sequence that minimizes the mean makespan and the spread of the makespan, Lee and Li fuzzy ranking method is adopted and modified to solve the problem. Particle swarm optimization (PSO) is a population-based stochastic approximation algorithm that has been applied to a wide range of problems, but there is little reported in respect of application to scheduling problems because of its unsuitability for them. In the paper, PSO is redefined and modified by introducing genetic operations such as crossover and mutation to update the particles, which is called GPSO and successfully employed to solve the formulated problem. A series of benchmarks with fuzzy processing time are used to verify GPSO. Extensive experiments show the feasibility and effectiveness of the proposed method.
文摘Biologic behaviors are the principal source for proposing new intelligent algorithms. Based on the mechanism of the bio-subsistence and the bio-migration, this paper proposes a novel algorithm—Living Migration Algorithm (LMA). The original contributions of LMA are three essential attributes of each individual: the minimal life-needs which are the necessaries for survival, the migrating which is a basal action for searching new living space, and the judging which is an important ability of deciding whether to migrate or not. When living space of all individuals can satisfy the minimal life-needs at some generation, they are considered as the optimal living places where objective functions will obtain the optima. LMA may be employed in large-scale computation and engineering field. The paper mostly operates LMA to deal with four non-linear and heterogeneous optimizations, and experiments prove LMA has better performances than Free Search algorithm.
基金Sponsored by National Nature Science Foundation of China (60174028)
文摘A novel design method for determining the proportional-integral-derivative(PID) controller gains of an anti-aircraft artillery servo system with multiple performance specifications based on a particle swarm optimization (PSO) algorithm is proposed. First, a performance criterion evolution function combined with the system maximum displacement settling time, rise time, overshoot, steady state error, constant velocity tracking error and sine wave tracking error is defined. Second, the optimization problem of PID controller parameters and the searching procedure of PSO algorithm are constructed. Finally, the optimal or near optimal PID controller parameters are fast and easily obtained by solving the above optimization problem on the given controller parameter space following the PSO searching procedure. The simulation results show the effectiveness of the proposed controllers.
