Particle Swarm optimization (PSO) is a stochastic computational evolutionary technique which is based on intelligence of swarms but its convergence and search accuracy still need to be improved. Chaotic search, averag...
详细信息
Particle Swarm optimization (PSO) is a stochastic computational evolutionary technique which is based on intelligence of swarms but its convergence and search accuracy still need to be improved. Chaotic search, average initiate particle location, variable search zone, anti-prematurity strategy, inflection algorithm and changeable momentum weights were combined with PSO algorithm in order to solve these problems. This modified chaotic PSO was used to identify values of the transfer function on a circulation fluidized bed boiler combustion system. simulation result shows that combining analytical, intelligent and experimental approach is an effective and practicable modeling approach.
The secondary reheat steam temperature system was designed and researched for the double reheat power unit. A simulator adopting modular modelling is chosen as the research platform to construct an ultra-supercritical...
详细信息
ISBN:
(纸本)9781845648572
The secondary reheat steam temperature system was designed and researched for the double reheat power unit. A simulator adopting modular modelling is chosen as the research platform to construct an ultra-supercritical double reheat unit. According to the analysis of the double reheat thermal system, the double reheat steam temperature control system is designed. The main control approach is surface type attemperator, which adopts cascade control loop and affiliates with spray type attemperator. After adding mathematical model of the second reheat steam temperature system into LN algorithm library, the system model is set up. According to the simulation results, the feasibility, advantages, and disadvantages of the surface type attemperator control is analyzed.
A novel regression algorithm of multi-output least squares support vector machine is proposed for the modeling of multi-output systems. The fitting error of each dimension output and the fitting error of overall outpu...
详细信息
A novel regression algorithm of multi-output least squares support vector machine is proposed for the modeling of multi-output systems. The fitting error of each dimension output and the fitting error of overall output are defined. And combined with the equality constraints of least squares support vector machine, the linear equation of multi-output least squares support vector machine is deduced. A multioutput combustion system model for utility boiler is established based on above algorithm and the prediction of NOx emission, carbon content of fly ash, exhaust flue gas temperature and desuperheating water of reheater is achieved. In addition, the parameters of the multi-output model are optimized by particle swarm optimization. The performance of the multi-output least squares support vector machine model and multiple single-output least squares support vector machine are compared. The effectiveness of the multi-output model is verified and it provides a good foundation for combustion optimization.
In order to solve the current difficulties of modeling for designing Intelligent Service Mobile Robot (ISMR), a new modeling method based on metasynthesis is proposed from the macro and micro levels. And the system an...
详细信息
For low NOx emission from coal-fired power plants, the computational intelligence(CI) technologies for NOx emission modeling and optimization are summarized. The modeling technologies of CI for NOx emission include ar...
详细信息
For low NOx emission from coal-fired power plants, the computational intelligence(CI) technologies for NOx emission modeling and optimization are summarized. The modeling technologies of CI for NOx emission include artificial neural networks and fuzzy systems. The optimization methods for low NOx emission combustion consist of evolutionary computation and swarm intelligence. Each method's advantage and disadvantage are comprised and the prospect of low NOx emission combustion is forecasted.
A coal ash fusion temperature model is constructed based on support vector machine(SVM). The compositions of coal ash are employed as the inputs and the ash fusion temperature is the output. A series of improvement is...
A coal ash fusion temperature model is constructed based on support vector machine(SVM). The compositions of coal ash are employed as the inputs and the ash fusion temperature is the output. A series of improvement is made on basic ant colony optimization(ACO) and it is used to optimize the parameters of the SVM model. The coal ash fusion temperature is predicted by the ACO-optimized SVM model. Some experiments are performed to compare the predicted and the measured temperature and the results show the ACO-optimized SVM model can achieve better predicting performance. The advantages of SVM model, such as small sampling, fast computing speed and real-time processing and predicting are also displayed.
In order to design H2/H∞ PID controller, this paper proposed a novel niche quantum genetic algorithm that was based on chaotic mutation operator. The simulation results show that, it can obtain better effect when ado...
详细信息
This paper is concerned with the problem of Hα filtering for a class of discrete-time linear parameter-varying (LPV) systems with Markovian switching under data missing and quantization. A stochastic variable is used...
详细信息
This paper is concerned with the problem of H ∞ filtering for a class of discrete-time linear parameter-varying (LPV) systems with Markovian switching under data missing and quantization. A stochastic variable is us...
详细信息
This paper is concerned with the problem of H ∞ filtering for a class of discrete-time linear parameter-varying (LPV) systems with Markovian switching under data missing and quantization. A stochastic variable is used to describe the model of the data missing phenomenon. Then a H ∞ filter is designed to guarantee the filtering error dynamics is stochastically stable with H ∞ performance. The existence of the desired H ∞ filter is ensured by some sufficient conditions expressed in terms of parameterized linear matrix inequalities (PLMIs). The proposed theoretical findings are validated by numerical results.
This paper investigates the problem of quantized filtering for a class of discrete-time linear parameter-varying systems with Markovian switching under data missing. The measured output of the plant is quantized by a ...
详细信息
暂无评论