scholarly journals NEURAL NET USING TO DETERMINE DEPTH AND FREQUENCY OF SIGNALS’ MODULATION FOR ELECTRICAL EQUIPMENT ULTRASONIC VIBROCONTROL

2021 ◽  
pp. 21-30
Author(s):  
Anatoly V. Bychkov ◽  
Irina Yu. Bychkova ◽  
Nadezhda N. Suslova ◽  
Kurbangali K. Alimov
Keyword(s):  
Neural Network ◽  
Signal Processing ◽  
Vibration Control ◽  
Sampling Rate ◽  
Vibration Signal ◽  
Electrical Equipment ◽  
Neural Net ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Mean Square Errors

The apparatus of artificial neural networks (ANN) is proposed to be used for signal processing in active ultrasonic (US) vibration control of electrical equipment. A feature of the applied neural network algorithm is that the required information about vibration parameters is embedded in the ultrasound signal’s phase change at its constant amplitude. Under these conditions, traditional spectral analysis of signals requires a high sampling rate and a significant recording duration. When using the direct propagation’s ANN with three hidden layers, it was shown that it is sufficient to use a sampling frequency of 5-6 points for the period of an ultrasonic wave and a recording duration of 4-5 periods to estimate the nonstationary frequency and amplitude of the vibration signal. Estimates of the error in determining the amplitude, frequency and phase of vibrations are obtained. The root-mean-square errors of the neural network algorithm do not exceed units of percent. The possibilities of using a trained neural network for signal processing in a «sliding window» are demonstrated. The accuracy characteristics of the proposed neural network algorithm of signal processing and the possibility of its optimization for electrical equipment’s vibration control are discussed.

scholarly journals Penggunaan Algoritma Jaringan Syaraf Tiruan Propagasi Balik Pada Klasifikasi Data Penggunaan Daya Listrik

2020 ◽  
Vol 5 (2) ◽  
pp. 1-6
Author(s):  
Zeni Permatasari ◽  
Agus Sifaunajah ◽  
Nur Khafidhoh
Keyword(s):  
Neural Network ◽  
Electrical Power ◽  
Back Propagation ◽  
Electrical Equipment ◽  
Training Data ◽  
Large Contribution ◽  
Data Set ◽  
Operational Costs ◽  
Network Algorithm ◽  
Neural Network Algorithm

Electrical Energy has a large contribution to the operational costs that must be incurred. The selection of electrical equipment can be one alternative that might be implemented to reduce operational costs incurred. In its use sometimes users do not know any electrical equipment that uses high electrical power and low electrical power. Therefore a system was made to classify data on electric power usage. This data will be classified into four classes, such as: very efficient, efficient, quite efficient and wasteful. Data classification is done using a back propagation neural network algorithm. The training data set used is 190 data and the test data set is 30 data. Based on the training that has been done, the optimal parameters are learning rate 0.5, target error 0.001, max epoch 10000, and 25 hidden neurons. Tests show that the system is able to recognize data with an accuracy level of 96.67% and MSE of 0.03333. Of the 30 data that have been tested obtained 29 data in accordance with the target. Where the 29 data are classified into 4 classes, namely 9 data classes are very efficient, 6 data classes are efficient, 5 data classes are quite efficient and 9 data classes are wasteful. The results of this study can be concluded that the backpropagation neural network algorithm can be implemented to classify electrical power usage data.

A NEURAL NETWORK ALGORITHM FOR DENSITY MEASUREMENT OF MULTIPHASE FLOW

2012 ◽  
Vol 24 (2) ◽  
pp. 89-103 ◽  
Author(s):  
Nabeel Al-Rawahi ◽  
Mahmoud Meribout ◽  
Ahmed Al-Naamany ◽  
Ali Al-Bimani ◽  
Adel Meribout
Keyword(s):  
Neural Network ◽  
Multiphase Flow ◽  
Density Measurement ◽  
Network Algorithm ◽  
Neural Network Algorithm
Sign in / Sign up

Export Citation Format

Share Document