Based on fuzzy mathematics and the neural network method, with the combination of fault datas of B737NG aircraft flight control system and experts experiences, this paper built a fuzzy neural network (FNN) fault diagn...
详细信息
Based on fuzzy mathematics and the neural network method, with the combination of fault datas of B737NG aircraft flight control system and experts experiences, this paper built a fuzzy neural network (FNN) fault diagnosis model which can intuitively express the relevance of fault symptoms and fault reasons. By Simulation and analysis, the fault diagnosis accuracy of FNN is much higher than only bp neural network, The research makes fault positioning more accurate and valid, improves the efficiency of maintenance, as well as ensures flight safety and provides a new point of view for establishing the aviation maintenance auxiliary decision system.
According to the floatation processing characteristic with time-variation, uncertainty and complicated nonlinear relations, a prediction method of concentrate grade and prediction model of ore dressing date is propose...
详细信息
According to the floatation processing characteristic with time-variation, uncertainty and complicated nonlinear relations, a prediction method of concentrate grade and prediction model of ore dressing date is proposed. This article establish a prediction model of ore dressing date based on Jordan neural network including input of influence factors and dynamic time sequence feedback of concentrate grade, by combining bp algorithm with the temporal difference methods. The results applied in industry indicate that predictive precision is high, error is small, and stability is high. It has practical value, the application is successful.
Searching the predictors in each level of the NCEP data by use the long time series data of NCEP and short time sequence data of wind observation. And filtering the information and extraction the components for th...
详细信息
Searching the predictors in each level of the NCEP data by use the long time series data of NCEP and short time sequence data of wind observation. And filtering the information and extraction the components for these primary predictors using the method of partial least-squares regression (PLS), then takes the new comprehensive variables (names components) as predictors and using the neural network with the features including adaptive and learning and the logical reasoning ability of fuzzy system to establish the wind field calculation model with fuzzy neural network(FNN) through combining fuzzy neural network system and adjustment the system parameters using bp algorithm. Comparing the calculation result shows that the errors of combining model with partial least-square regression(PLS) and fuzzy neural network(FNN) is smaller than that the multiple linear regression model. The length time sequence data of wind could be calculated according to the short time sequence data of observation wind and the long time series data of NCEP by the combining model with PLS and FNN in practical, therefore this model is better practicability and popularize value for it provide the basis to research the exploitation wind resources.
The bp network which based on the gradient descent algorithm has some disadvantages,such as it is very time-consuming.A new algorithm named Extreme Learning Machine(ELM)can solve the problems of *** the Extreme Learni...
详细信息
The bp network which based on the gradient descent algorithm has some disadvantages,such as it is very time-consuming.A new algorithm named Extreme Learning Machine(ELM)can solve the problems of *** the Extreme Learning Machine(ELM)in the intrusion detection,use the KDDCUP99 dataset to compare bp neural network and ELM neural network separately by simulation *** results indicate that ELM has a high convergence speed,and the detection accuracy can reach as high as 98 percent.
In conventional bit-interleaved coded modulation (BICM) system with convolutional codes, Gray mapping has been proved to be the best candidate over the additive white Gaussian noise (AWGN) channel. However, when it co...
详细信息
In conventional bit-interleaved coded modulation (BICM) system with convolutional codes, Gray mapping has been proved to be the best candidate over the additive white Gaussian noise (AWGN) channel. However, when it comes to LDPC-coded BICM and BICM with iterative decoding (BICMID) systems, Gray mapping doesn’t always promise better performance. A simple class of labeling maps that significantly improves the bit error rates (BER) is presented. Meanwhile, we found out that in these systems the overall performance of modulation depends not merely on the constellation schemes, but also the decoding strategy. Compared with the conventional parameters based Euclidean distance, mutual information theory is proved to be a more accurate tool. The simulation results show that only when combined with the suitable mapping and the “state-of-art” decoding algorithms, the BICM system can give full play to their potential.
In this paper a new neural network model with weight-function is *** the model,the weight is a function with adjustable parameters,and the sum of these weight functions as the neuron *** according to bp algorithm,the ...
详细信息
In this paper a new neural network model with weight-function is *** the model,the weight is a function with adjustable parameters,and the sum of these weight functions as the neuron *** according to bp algorithm,the learning algorithm of feed-forward neural network with weight-function neurons is *** results show that,applying the back-propagation algorithm to the new neural network the better convergence rate can be obtained and in some applications the new neural network based on the weight-function neurons is superior to the bp network based on the MP neuron model,so that it has a significant value in further research and application.
According to the floatation processing characteristic with time-variation, uncertainty and complicated nonlinear relations, a prediction method of concentrate grade and prediction model of ore dressing date is propose...
详细信息
ISBN:
(纸本)9781612848396
According to the floatation processing characteristic with time-variation, uncertainty and complicated nonlinear relations, a prediction method of concentrate grade and prediction model of ore dressing date is proposed. This article establish a prediction model of ore dressing date based on Jordan neural network including input of influence factors and dynamic time sequence feedback of concentrate grade, by combining bp algorithm with the temporal difference methods. The results applied in industry indicate that predictive precision is high, error is small, and stability is high. It has practical value, the application is successful.
In order to improve the efficiency and decoding performance of LDPC-coded BICM system, the joint de-modulation Belief Propagation(JMbp) algorithm is proposed in this paperDue to the good sparse structure of LDPC code,...
详细信息
In order to improve the efficiency and decoding performance of LDPC-coded BICM system, the joint de-modulation Belief Propagation(JMbp) algorithm is proposed in this paperDue to the good sparse structure of LDPC code, the JMbp algorithm can be derived from the generalized optimal bp algorithm based on the generalized distributive law(GDL)The JMbp algorithm has comparably low complexity while provides better decoding performance when compared with the traditional BICM-bp algorithm in highary modulated BICM systemsAnd the simulation results confirm that the JMbp algorithm outperforms the traditional BICM-bp algorithm over both the AWGN and Rayleigh fading channel.
This paper is devoted to the study and the implementation of a joint source/channel decoding algorithm of VLC (Variable Length Code) and LDPC (Low Density Parity Check codes) codes. The principle of joint decoding...
详细信息
This paper is devoted to the study and the implementation of a joint source/channel decoding algorithm of VLC (Variable Length Code) and LDPC (Low Density Parity Check codes) codes. The principle of joint decoding is the information transfer between the source and channel decoder. Then, we can’t apply the classic VLC decoding algorithm. So, we implemented MAP decoding algorithm basing on trellis description. Simulations results showed that the performances of this algorithm are better than those of a classic decoding. Then, we introduced a LDPC code into the considered communication chain (source coded using a VLC code) and we proceed to an iterative joint decoding of VLC and LDPC codes. Simulation results show that iterative joint source/channel decoding provide an important gain compared to classic communication schema.
For fire detection and alarm system with simple function,positioning difficulties,false positive and false negative in traditional intelligent building,the fire detection and alarm systems based on intelligent neural ...
详细信息
For fire detection and alarm system with simple function,positioning difficulties,false positive and false negative in traditional intelligent building,the fire detection and alarm systems based on intelligent neural network have been *** can do integrated estimation with a variety of fire detection information detected by the microcontroller,neural network intelligent algorithm was joined in the software design,MATLAB simulation realize multiple synchronous intelligent detection,which effectively detect various types of early fire and reduce the fire.
暂无评论