Blind Estimation of Spreading Sequence Based on Neural Network by a Novel Information Criterion

2008 ◽  
Author(s):  
Guo Lin ◽  
Lv Ming ◽  
Tang Bin
Keyword(s):  
Neural Network ◽  
Information Criterion ◽  
Blind Estimation ◽  
Spreading Sequence

Aircraft Health Diagnosis Method Based on ARMA Model and Probabilistic Neural Network

2011 ◽  
Vol 225-226 ◽  
pp. 527-530 ◽  
Author(s):  
Jian Guo Cui ◽  
Bo Han Song ◽  
Shi Liang Dong ◽  
Hai Gang Liu ◽  
Qing Zhao
Keyword(s):  
Neural Network ◽  
Probabilistic Neural Network ◽  
Arma Model ◽  
Information Criterion ◽  
Model Parameters ◽  
Health State ◽  
Feature Vectors ◽  
Emission Signal ◽  
Diagnosis Method ◽  
Health Diagnosis

In order to diagnose the health state of Aircraft effectively, a new method based on ARMA Model and probabilistic neural network(PNN) is proposed in this paper. First, an ARMA model is built using the original acoustic emission signal of aircraft crucial components, then use the autoregressive approximation theory to estimate model parameters, and order of the model is calculated according to Akaike Information Criterion(AIC). Use the autoregressive parameters to build feature vectors, then the probabilistic neural network is used to carry out the recognition of these feature vectors, and the health state of aircraft crucial components is effectively diagnosed. After the application on certain type of real aircraft, this method is proved to be capable of detecting the fatigue crack on crucial structural components. And we can conclude that the method is an effective way to carry out aircraft health diagnosis.

Health Monitoring and Degradation Prognostics in Gas Turbine Engines Using Dynamic Neural Networks

2015 ◽  
Author(s):  
A. Vatani ◽  
K. Khorasani ◽  
N. Meskin
Keyword(s):  
Neural Network ◽  
Gas Turbine ◽  
Health Monitoring ◽  
Network Architecture ◽  
Information Criterion ◽  
Turbine Engines ◽  
Prediction Errors ◽  
Gas Turbine Engines ◽  
Dynamic Neural Networks ◽  
Turbine Engine

In this paper two artificially intelligent methodologies are proposed and developed for degradation prognosis and health monitoring of gas turbine engines. Our objective is to predict the degradation trends by studying their effects on the engine measurable parameters, such as the temperature, at critical points of the gas turbine engine. The first prognostic scheme is based on a recurrent neural network (RNN) architecture. This architecture enables ONE to learn the engine degradations from the available measurable data. The second prognostic scheme is based on a nonlinear auto-regressive with exogenous input (NARX) neural network architecture. It is shown that this network can be trained with fewer data points and the prediction errors are lower as compared to the RNN architecture. To manage prognostic and prediction uncertainties upper and lower threshold bounds are defined and obtained. Various scenarios and case studies are presented to illustrate and demonstrate the effectiveness of our proposed neural network-based prognostic approaches. To evaluate and compare the prediction results between our two proposed neural network schemes, a metric known as the normalized Akaike information criterion (NAIC) is utilized. A smaller NAIC shows a better, a more accurate and a more effective prediction outcome. The NAIC values are obtained for each case and the networks are compared relatively with one another.

scholarly journals Prediction by neural network and information criterion on daily inflow in a dry season

1996 ◽  
Vol 40 ◽  
pp. 359-364
Author(s):  
Masashi NAGAO ◽  
Takakazu TAZAWA ◽  
Masasi SANO ◽  
Masato SUZUKI
Keyword(s):  
Neural Network ◽  
Information Criterion ◽  
Dry Season

scholarly journals Modified election algorithm in hopfield neural network for optimal random k satisfiability representation

2020 ◽  
Vol 11 ◽  
pp. 16
Author(s):  
Hamza Abubakar ◽  
Shamsul Rijal Muhammad Sabri ◽  
Sagir Abdu Masanawa ◽  
Surajo Yusuf
Keyword(s):  
Neural Network ◽  
Mean Absolute Error ◽  
Search Algorithm ◽  
Optimal Solution ◽  
Information Criterion ◽  
Hopfield Neural Network ◽  
Absolute Error ◽  
Current Standard ◽  
Election Algorithm ◽  
Logical Representation

Election algorithm (EA) is a novel metaheuristics optimization model motivated by phenomena of the socio-political mechanism of presidential election conducted in many countries. The capability and robustness EA in finding an optimal solution to optimization has been proven by various researchers. In this paper, modified version of EA has been utilized in accelerating the searching capacity of Hopfield neural network (HNN) learning phase for optimal random-kSAT logical representation (HNN-R2SATEA). The utility of the proposed approach has been contrasted with the current standard exhaustive search algorithm (HNN-R2SATES) and the newly developed algorithm HNN-R2SATICA. From the analysis obtained, it has been clearly shown that the proposed hybrid computational model HNN-R2SATEA outperformed other existing model in terms of global minima ratio (Zm), mean absolute error (MAE), Bayesian information criterion (BIC) and execution time (ET). The finding portrays that the MEA algorithm surpassed the other two algorithms for optimal random-kSAT logical representation.

Sign in / Sign up

Export Citation Format

Share Document