In this paper, a truncated hybrid method is proposed and developed for solving sparse large-scale nonlinear programming problems. In the hybrid method, a symmetric system of linear equations, instead of the usual quad...In this paper, a truncated hybrid method is proposed and developed for solving sparse large-scale nonlinear programming problems. In the hybrid method, a symmetric system of linear equations, instead of the usual quadratic programming subproblems, is solved at iterative process. In order to ensure the global convergence, a method of multiplier is inserted in iterative process. A truncated solution is determined for the system of linear equations and the unconstrained subproblems are solved by the limited memory BFGS algorithm such that the hybrid algorithm is suitable to the large-scale problems. The local convergence of the hybrid algorithm is proved and some numerical tests for medium-sized truss problem are given.展开更多
A novel data-driven, soft sensor based on support vector regression (SVR) integrated with a data compression technique was developed to predict the product quality for the hydrodesulfurization (HDS) process. A wid...A novel data-driven, soft sensor based on support vector regression (SVR) integrated with a data compression technique was developed to predict the product quality for the hydrodesulfurization (HDS) process. A wide range of experimental data was taken from a HDS setup to train and test the SVR model. Hyper-parameter tuning is one of the main challenges to improve predictive accuracy of the SVR model. Therefore, a hybrid approach using a combination of genetic algorithm (GA) and sequential quadratic programming (SQP) methods (GA-SQP) was developed. Performance of different optimization algorithms including GA-SQP, GA, pattern search (PS), and grid search (GS) indicated that the best average absolute relative error (AARE), squared correlation coefficient (R2), and computation time (CT) (AARE = 0.0745, R2 = 0.997 and CT = 56 s) was accomplished by the hybrid algorithm. Moreover, to reduce the CT and improve the accuracy of the SVR model, the vector quantization (VQ) technique was used. The results also showed that the VQ technique can decrease the training time and improve prediction performance of the SVR model. The proposed method can provide a robust, soft sensor in a wide range of sulfur contents with good accuracy.展开更多
This paper investigates the servo mechanism reconfiguration and fault tolerance control issue for a launch vehicle.Firstly,the servo reconfiguration algorithm is considered as an optimization model,and commonly used o...This paper investigates the servo mechanism reconfiguration and fault tolerance control issue for a launch vehicle.Firstly,the servo reconfiguration algorithm is considered as an optimization model,and commonly used optimization algorithms are analyzed and compared.An improved method based on Singular Value Decomposition(SVD)for solving the suboptimal solution of the direct assignment problem is proposed,being suitable for engineering application,while maintaining the advantages of existing algorithms.Theoretical analysis and simulation results confirm that the proposed method is able to provide the optimal reconfiguration strategy with higher computational efficiency.Finally,the numerical simulation of launch vehicle fault tolerance control fully verifies the feasibility and effectiveness of the improved method,which indicates that the method met the engineering application conditions.展开更多
The alternative working modes and flexible working states are the outstanding features of an adaptive cycle engine, with a proper control schedule design being the only way to exploit the performance of such an engine...The alternative working modes and flexible working states are the outstanding features of an adaptive cycle engine, with a proper control schedule design being the only way to exploit the performance of such an engine. However, unreasonable design in the control schedule causes not only performance deterioration but also serious aerodynamic stability problems. Thus, in this work,a hybrid optimization method that automatically chooses the working modes and identifies the optimal and smooth control schedules is proposed, by combining the differential evolution algorithm and the Latin hypercube sampling method. The control schedule architecture does not only optimize the engine steady-state performance under different working modes but also solves the control-schedule discontinuity problem, especially during mode transition. The optimal control schedules are continuous and almost monotonic, and hence are strongly suitable for a control system, and are designed for two different working conditions, i.e., supersonic and subsonic throttling,which proves that the proposed hybrid method applies to various working conditions. The evaluation demonstrates that the proposed control method optimizes the engine performance, the surge margin of the compression components, and the range of the thrust during throttling.展开更多
Purpose–The two main purposes of this paper are:first,the development of a new optimization algorithm called GHSACO by incorporating the global-best harmony search(GHS)which is a stochastic optimization algorithm rec...Purpose–The two main purposes of this paper are:first,the development of a new optimization algorithm called GHSACO by incorporating the global-best harmony search(GHS)which is a stochastic optimization algorithm recently developed,with the ant colony optimization(ACO)algorithm.Second,design of a new indirect adaptive recurrent fuzzy-neural controller(IARFNNC)for uncertain nonlinear systems using the developed optimization method(GHSACO)and the concept of the supervisory controller.Design/methodology/approach–The novel optimization method introduces a novel improvization process,which is different from that of the GHS in the following aspects:a modified harmony memory representation and conception.The use of a global random switching mechanism to monitor the choice between the ACO and GHS.An additional memory consideration selection rule using the ACO random proportional transition rule with a pheromone trail update mechanism.The developed optimization method is applied for parametric optimization of all recurrent fuzzy neural networks adaptive controller parameters.In addition,in order to guarantee that the system states are confined to the safe region,a supervisory controller is incorporated into the IARFNNC global structure.Findings–First,to analyze the performance of GHSACO method and shows its effectiveness,some benchmark functions with different dimensions are used.Simulation results demonstrate that it can find significantly better solutions when compared with the Harmony Search(HS),GHS,improved HS(IHS)and conventional ACO algorithm.In addition,simulation results obtained using an example of nonlinear system shows clearly the feasibility and the applicability of the proposed control method and the superiority of the GHSACO method compared to the HS,its variants,particle swarm optimization,and genetic algorithms applied to the same problem.Originality/value–The proposed new GHS algorithm is more efficient than the original HS method and its most known variants IHS and GHS.The proposed control method is applicable to any uncertain nonlinear system belongs in the class of systems treated in this paper.展开更多
文摘In this paper, a truncated hybrid method is proposed and developed for solving sparse large-scale nonlinear programming problems. In the hybrid method, a symmetric system of linear equations, instead of the usual quadratic programming subproblems, is solved at iterative process. In order to ensure the global convergence, a method of multiplier is inserted in iterative process. A truncated solution is determined for the system of linear equations and the unconstrained subproblems are solved by the limited memory BFGS algorithm such that the hybrid algorithm is suitable to the large-scale problems. The local convergence of the hybrid algorithm is proved and some numerical tests for medium-sized truss problem are given.
文摘A novel data-driven, soft sensor based on support vector regression (SVR) integrated with a data compression technique was developed to predict the product quality for the hydrodesulfurization (HDS) process. A wide range of experimental data was taken from a HDS setup to train and test the SVR model. Hyper-parameter tuning is one of the main challenges to improve predictive accuracy of the SVR model. Therefore, a hybrid approach using a combination of genetic algorithm (GA) and sequential quadratic programming (SQP) methods (GA-SQP) was developed. Performance of different optimization algorithms including GA-SQP, GA, pattern search (PS), and grid search (GS) indicated that the best average absolute relative error (AARE), squared correlation coefficient (R2), and computation time (CT) (AARE = 0.0745, R2 = 0.997 and CT = 56 s) was accomplished by the hybrid algorithm. Moreover, to reduce the CT and improve the accuracy of the SVR model, the vector quantization (VQ) technique was used. The results also showed that the VQ technique can decrease the training time and improve prediction performance of the SVR model. The proposed method can provide a robust, soft sensor in a wide range of sulfur contents with good accuracy.
文摘This paper investigates the servo mechanism reconfiguration and fault tolerance control issue for a launch vehicle.Firstly,the servo reconfiguration algorithm is considered as an optimization model,and commonly used optimization algorithms are analyzed and compared.An improved method based on Singular Value Decomposition(SVD)for solving the suboptimal solution of the direct assignment problem is proposed,being suitable for engineering application,while maintaining the advantages of existing algorithms.Theoretical analysis and simulation results confirm that the proposed method is able to provide the optimal reconfiguration strategy with higher computational efficiency.Finally,the numerical simulation of launch vehicle fault tolerance control fully verifies the feasibility and effectiveness of the improved method,which indicates that the method met the engineering application conditions.
基金funded by National Nature Science Foundation of China(Nos.51776010 and 91860205)supported by the Academic Excellence Foundation of BUAA for PhD Students,China。
文摘The alternative working modes and flexible working states are the outstanding features of an adaptive cycle engine, with a proper control schedule design being the only way to exploit the performance of such an engine. However, unreasonable design in the control schedule causes not only performance deterioration but also serious aerodynamic stability problems. Thus, in this work,a hybrid optimization method that automatically chooses the working modes and identifies the optimal and smooth control schedules is proposed, by combining the differential evolution algorithm and the Latin hypercube sampling method. The control schedule architecture does not only optimize the engine steady-state performance under different working modes but also solves the control-schedule discontinuity problem, especially during mode transition. The optimal control schedules are continuous and almost monotonic, and hence are strongly suitable for a control system, and are designed for two different working conditions, i.e., supersonic and subsonic throttling,which proves that the proposed hybrid method applies to various working conditions. The evaluation demonstrates that the proposed control method optimizes the engine performance, the surge margin of the compression components, and the range of the thrust during throttling.
文摘Purpose–The two main purposes of this paper are:first,the development of a new optimization algorithm called GHSACO by incorporating the global-best harmony search(GHS)which is a stochastic optimization algorithm recently developed,with the ant colony optimization(ACO)algorithm.Second,design of a new indirect adaptive recurrent fuzzy-neural controller(IARFNNC)for uncertain nonlinear systems using the developed optimization method(GHSACO)and the concept of the supervisory controller.Design/methodology/approach–The novel optimization method introduces a novel improvization process,which is different from that of the GHS in the following aspects:a modified harmony memory representation and conception.The use of a global random switching mechanism to monitor the choice between the ACO and GHS.An additional memory consideration selection rule using the ACO random proportional transition rule with a pheromone trail update mechanism.The developed optimization method is applied for parametric optimization of all recurrent fuzzy neural networks adaptive controller parameters.In addition,in order to guarantee that the system states are confined to the safe region,a supervisory controller is incorporated into the IARFNNC global structure.Findings–First,to analyze the performance of GHSACO method and shows its effectiveness,some benchmark functions with different dimensions are used.Simulation results demonstrate that it can find significantly better solutions when compared with the Harmony Search(HS),GHS,improved HS(IHS)and conventional ACO algorithm.In addition,simulation results obtained using an example of nonlinear system shows clearly the feasibility and the applicability of the proposed control method and the superiority of the GHSACO method compared to the HS,its variants,particle swarm optimization,and genetic algorithms applied to the same problem.Originality/value–The proposed new GHS algorithm is more efficient than the original HS method and its most known variants IHS and GHS.The proposed control method is applicable to any uncertain nonlinear system belongs in the class of systems treated in this paper.