This paper considers networked control systems with time varying delays. The main idea is to apply a variable sampling period in order to compensate for the time delay. A feedforwrd multilayered neural network is firs...
详细信息
ISBN:
(纸本)9781424417339
This paper considers networked control systems with time varying delays. The main idea is to apply a variable sampling period in order to compensate for the time delay. A feedforwrd multilayered neural network is first properly developed to estimate the time delay at each sampling period. Then, this predicted time delay is taken as the sampling period between the current and the next sampling steps. The simulation results show that the proposed approach makes the controller more robust for stabilizing the system by reducing remarkably the influence of the closed loop time delay.
An intelligent pattern recognition used artificial neural networks is presented in this paper to meet the requirement of controlling stripe shape in cold rolling. The cold-rolled products are characterize into several...
详细信息
ISBN:
(纸本)9787506292207
An intelligent pattern recognition used artificial neural networks is presented in this paper to meet the requirement of controlling stripe shape in cold rolling. The cold-rolled products are characterize into several types based on its irregularity, 'left wave', 'right wave', 'center buckle', 'edge wave', 'W-type', and 'M-type'. The developed identification algorithm calculates for each type of irregular strip shape using neural network and experiment data. The work is studied by taking a double-stand reversing cold rolling mill as example. The method improves the speed and the accuracy of strip shape identification.
Presently, electromagnetic field numerical value analysis methods such as finite difference time-domain (FDTD) method are generally used to calculate the DGS, although these methods are accurate, they are also computa...
详细信息
ISBN:
(纸本)9781424418855
Presently, electromagnetic field numerical value analysis methods such as finite difference time-domain (FDTD) method are generally used to calculate the DGS, although these methods are accurate, they are also computationally expensive. In this paper, a neural network model of a novel defected ground structure is established. Since the neural network model has the advantages of great precision and effectiveness, the developed design model can be used to take the place of the FDTD method of the DGS, being a kind of aid tool of circuit design. The neural network models of two different non-periodic DGS have been developed, at the same time the circuit of the according DGS is designed and manufactured. The result of computer simulation and product measurements are obtained to demonstrate the effectiveness of the method.
PID (Proportional Integral Derivative) controllers are widely used in industrial process control system. Tuning the parameters of PID controller is very important in PID control. Neural network algrithm is a massively...
详细信息
ISBN:
(纸本)9781424416738
PID (Proportional Integral Derivative) controllers are widely used in industrial process control system. Tuning the parameters of PID controller is very important in PID control. Neural network algrithm is a massively parallel, distributed information processing system;it has self-learning, adaptive, non-linear mapping capabilities and fault-tolerance, and achieved certain results in the field of control. Ordinary bp neural networks PID controller was mentioned in document [1], it had a good robust performance. But its precision and performance can be improved by high-order bp neural - networks which is introduced and used in this document. The simulation result shows that Frequency Control System Compared to regular high bp network convergence speed, high precision control, fast response, achieve the purpose of raising the quality and effectiveness of control.
In this paper, a new L-M optimized bp algorithm combining Levenbery-Marquardt optimized algorithm and neural network model is successfully developed after analyzing the deficiency of the traditional B
In this paper, a new L-M optimized bp algorithm combining Levenbery-Marquardt optimized algorithm and neural network model is successfully developed after analyzing the deficiency of the traditional B
bp neural network model has been applied broadly. The output of bp model is always supposed into a certain range, such as [0,1]. However, the output usually doesn’t satisfy this condition in practical
bp neural network model has been applied broadly. The output of bp model is always supposed into a certain range, such as [0,1]. However, the output usually doesn’t satisfy this condition in practical
Based on the studying of the AC adjustment speed system and the complicated AC motor as controlled object, the method of fuzzy controller based neural-network is proposed in this paper. Simulations show that this meth...
详细信息
ISBN:
(纸本)9787900719706
Based on the studying of the AC adjustment speed system and the complicated AC motor as controlled object, the method of fuzzy controller based neural-network is proposed in this paper. Simulations show that this method improved the ability of self-learning and anti-jamming of the AC adjustment speed system. The resumptive time of rotate speed in neural-network fuzzy control system is shorter than that in PID control system and the overshooting and oscillation during the recovery period are also weakened when the loads are suddenly increased or decreased. For systems with complicated structure, this method works well and also possesses high control accuracy under strong disturbances.
The fuzzy logic was pulled in the neural network and the application of fault diagnosis for boiler system with the integrated fuzzy neural network is researched on the basic of the introductions of the basic principle...
详细信息
ISBN:
(纸本)9781424421138
The fuzzy logic was pulled in the neural network and the application of fault diagnosis for boiler system with the integrated fuzzy neural network is researched on the basic of the introductions of the basic principle of artificial neural network (ANN) and the principle of fault diagnosis for boiler system based on neural network. A example of training progress and testing results about the sample of boiler was given. And at last, it is proved that this integrated method can acquire a better result on fault diagnosis for boiler through error analysis compared with the traditional standard bp network.
This paper presents the bp algorithm to solve non-linear equations in one variable, and proves the convergence theorem of the algorithm, shows the application example. The simulation results show that
This paper presents the bp algorithm to solve non-linear equations in one variable, and proves the convergence theorem of the algorithm, shows the application example. The simulation results show that
The intrusion detection technology took one of computer network information security measures important methods, the invasion detection took one kind of dynamic safe protection technology,has provided to the internal ...
详细信息
The intrusion detection technology took one of computer network information security measures important methods, the invasion detection took one kind of dynamic safe protection technology,has provided to the internal attack, exterior attack and the disoperation real-time protection,receives before the endangerment in the network system interception and response *** on the characteristic to the computer network data to withdraw, proposed used the Genetic algorithms and the Neural Network unifies the invasion detection *** Genetic algorithms have the computation to be simple,the optimized effect good *** the bp algorithm using the Genetic algorithms the local minimum point,thus achieves a minimum point of RMS error,also solved the bp algorithm to restrain the slow question;At the same time also solved has alone used GA algorithm often not to be able to seek in the short time to approaches the optimal solution this *** confirmed the invasion detection effect through the computer experiment,enhanced the recognition rate,causes reporting mistakenly rate and failing to report rate reduces.
暂无评论