A genetic neural fuzzy system (GNFS) is presented and introduced to quality prediction in the injection process. A hybrid-learning algorithm is proposed, which is divided into two stages to train GNFS. During the firs...
详细信息
A genetic neural fuzzy system (GNFS) is presented and introduced to quality prediction in the injection process. A hybrid-learning algorithm is proposed, which is divided into two stages to train GNFS. During the first learning stage, the genetic algorithm is used to optimize the structure of GNFS and the membership function of each fuzzy term because of its capability of parallel and global search. On the basis of the first optimized training stages, the back-propagation algorithm (bp algorithm) is adopted to update the parameters of the GNFS to improve its predicting precision and reduce the computation time. The process of constructing a quality prediction model for an injection process based on GNFS is described in detail. The predicted weight of the molded part from the model based on GNFS demonstrates that the proposed GNFS has superior performance and good generalization capability in quality prediction in the injection process.
Most pitch detection algorithms are based on the relationship between frequency and note, however, when the pitch is hummed by an untrained person, the accuracy of pitch recognition would decline obviously. A new inte...
详细信息
ISBN:
(纸本)0780386477
Most pitch detection algorithms are based on the relationship between frequency and note, however, when the pitch is hummed by an untrained person, the accuracy of pitch recognition would decline obviously. A new intelligent pitch recognition (IPR) method based on intelligent neural networks is presented. Using the ideas of intelligent neural networks, a complex task of pitch recognition can be divided into several simple ones, which can be easily implemented by some simple intelligent neuron respectively. Then a large network built out of those intelligent neurons can solve the original, complex problem and the work is much easier than those traditional neural network methods. Experimental results show it is a good way for the pitch recognition.
In this paper, firstly the influencing factors of contact stiffness of machine joint interfaces and their description method are introduced and discussed. Then a weight smoothing bp algorithm is introduced briefly. It...
详细信息
ISBN:
(纸本)0780386299
In this paper, firstly the influencing factors of contact stiffness of machine joint interfaces and their description method are introduced and discussed. Then a weight smoothing bp algorithm is introduced briefly. It has better generalization performance. Basing on this algorithm, the intelligent modeling method of contact stiffness of machine joint interfaces under multi-joint conditions is proposed for the first time. This method is proved feasible by the given modeling example.
In this paper potential seismic sources in coastal region of South China are identified by integration of genetic algorithm (GA) and back propagation (bp algorithm). GA is used for finding the best parameter combinati...
详细信息
In this paper potential seismic sources in coastal region of South China are identified by integration of genetic algorithm (GA) and back propagation (bp algorithm). GA is used for finding the best parameter combination rapidly in an infinite solution space for artificial neural networks (ANN). The results show that the distribution of potential seismic sources with different upper magnitude demarcated by this classifier is mostly satisfied the intrinsic relationship between seismic environment and earthquake occurrence, with less effect from subjective judgment of human being.
The artificial neural networks (ANN) which have broad application were proposed to develop multiphase ceramie cutting tool materials. Based on the back propagation algorithm of the forward multilayer perceptron, the m...
详细信息
The artificial neural networks (ANN) which have broad application were proposed to develop multiphase ceramie cutting tool materials. Based on the back propagation algorithm of the forward multilayer perceptron, the models to predict volume content of composition in particie reinforced ceramies are established. The Al2O3/TiN ceramie cutting tool material was developed by ANN, whose mechanicai properties fully satisfy the cutting requirements.
A trajectory recognition and simulation technique based on PSO (particle swarm optimizer) is proposed. According to trajectory centric motion equations, and taking CMAC neural network as its core, a trajectory recogni...
详细信息
A trajectory recognition and simulation technique based on PSO (particle swarm optimizer) is proposed. According to trajectory centric motion equations, and taking CMAC neural network as its core, a trajectory recognition network is built up. The PSO algorithm controls the realization of recognition and simulation. Simulation results reveal that the proposed recognition technique based on PSO has higher precision of recognition and better convergence than those based on bp algorithm.
The backpropagation (bp) algorithm is a learning algorithm for the multilayer perceptron. However, when this algorithm is applied to the pattern classification problem the generalization ability may not be maximized, ...
详细信息
The backpropagation (bp) algorithm is a learning algorithm for the multilayer perceptron. However, when this algorithm is applied to the pattern classification problem the generalization ability may not be maximized, even if the learning converges. This paper proposes an algorithm to improve the generalization ability by shifting the hyper-plane constructed by the bp algorithm on the basis of internal information. The basic properties of the algorithm are analyzed. Then, the algorithm is extended to the multi layer perceptron and its generalization ability is examined by computer simulation. The proposed method is shown to be useful when the training data are sparse. (C) 2004 Wiley Periodicals, Inc.
An energy-saving scheme for pumping units via intermission start-stop performance is proposed. Because of the complexity of the oil extraction process, Fuzzy Neural Network (FNN) intelligent control is adopted. The st...
详细信息
An energy-saving scheme for pumping units via intermission start-stop performance is proposed. Because of the complexity of the oil extraction process, Fuzzy Neural Network (FNN) intelligent control is adopted. The structure of the Takagi-Sugeno (T-S) fuzzy neural network model is introduced and modified. FNNs are trained with sample information from oil fields and expert knowledge. Finally, pumping unit energy-saving FNN software, which cuts down power costs substantially, is presented.
This paper analyses the defects of relay testing simulator based on Electromagnetic Transient Program (EMTP) and puts forward the design scheme of portable real-time transient digital simulator (RTDS) based on DSP. Co...
详细信息
This paper analyses the defects of relay testing simulator based on Electromagnetic Transient Program (EMTP) and puts forward the design scheme of portable real-time transient digital simulator (RTDS) based on DSP. Combined with a method of using wavelet to locate the transient fault and obtain its initial transient voltage U and phase θ, bp neural network is introduced to emulate transient fault progress. The study gives the following results: (I) Decreasing simulator parameters from four dimensions model f(R,L,θ,U) to one dimension f(R);(II) Simplifying algorithm of transient model and improving its real-time characteristic;(III) Simulating dynamically transient fault progress;(IV) Applying DSP into emulator and making (RTDS) portable in size.
pH regulation is a complicated and comprehensive technique in the crop fertigation system. In this paper, a method is put forward to improve the quality of pH regulation, using artificial neural network to map a nonli...
详细信息
pH regulation is a complicated and comprehensive technique in the crop fertigation system. In this paper, a method is put forward to improve the quality of pH regulation, using artificial neural network to map a nonlinear relationship between pH interfering factor and the switching frequency of pH control valve, which achieves the dynamic feedforward compensation to the main control system.
暂无评论