Recognition of Multi-Sensor Output Signal Using Modular Neural Networks Approach

2006 ◽  
Author(s):  
Iryna Turchenko ◽  
Volodymyr Kochan ◽  
Anatoly Sachenko
Keyword(s):  
Neural Networks ◽  
Output Signal ◽  
Sensor Output ◽  
Modular Neural Networks

SENSOR PVDF DENGAN POLARISASI PERMUKAAN SEBAGAI PENDETEKSI GAYA POTONG PADA MESIN GURDI

2020 ◽  
Vol 1 (2) ◽  
Author(s):  
Aditya Nugraha ◽  
Masri Bin Ardin
Keyword(s):  
Cutting Force ◽  
Output Signal ◽  
Axial Loading ◽  
Force Sensor ◽  
Maximum Deviation ◽  
Drilling Machine ◽  
Sensor Output ◽  
Sensor Surface ◽  
Surface Polarization ◽  
Tangential Directions

PVDF sensor is a sensor that is often used to measure force, strain, vibration and heat. In this study, PVDF sensors with surface polarization are used to detect cutting forces on the machine. The PVDF sensor that has been polarized on the surface is placed in the chuck part of the engine. Measuring instrumen for testing and calibrating PVDF sensors is oscilloscope with increased loading and reduced axial and tangential directions. After the calibration process, the PVDF sensor was used to measure cutting force on drilling machine, and then the results were compared with the PCB piezotronics force sensor. The PVDF sensor output signal is measured and studied for its voltage using an oscilloscope, where the output signal is compared to the weight given to the PVDF sensor. From the results of these tests indicate that the maximum deviation in axial loading is 0.32V while the tangential loading is 0.31VKeywords. PVDF sensor, Surface polarization, Drilling machine, Cutting force

Analysis of neural networks efficiency when accounting for weight coefficients jitter, leading to reduction in output signal/noise ratio

2021 ◽  
Author(s):  
S.V. Zimina
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Output Signal ◽  
Signal To Noise Ratio ◽  
Signal To Noise ◽  
Useful Signal ◽  
Artificial Neural ◽  
Noise Ratio ◽  
Weight Coefficients

Setting up artificial neural networks using iterative algorithms is accompanied by fluctuations in weight coefficients. When an artificial neural network solves the problem of allocating a useful signal against the background of interference, fluctuations in the weight vector lead to a deterioration of the useful signal allocated by the network and, in particular, losses in the output signal-to-noise ratio. The goal of the research is to perform a statistical analysis of an artificial neural network, that includes analysis of losses in the output signal-to-noise ratio associated with fluctuations in the weight coefficients of an artificial neural network. We considered artificial neural networks that are configured using discrete gradient, fast recurrent algorithms with restrictions, and the Hebb algorithm. It is shown that fluctuations lead to losses in the output signal/noise ratio, the level of which depends on the type of algorithm under consideration and the speed of setting up an artificial neural network. Taking into account the fluctuations of the weight vector in the analysis of the output signal-to-noise ratio allows us to correlate the permissible level of loss in the output signal-to-noise ratio and the speed of network configuration corresponding to this level when working with an artificial neural network.

Sign in / Sign up

Export Citation Format

Share Document