Artificial Neural Network Assisted Compact Inductive Distance Sensor

Kántor, Z.; Pólik, Zoltán

doi:10.1016/j.proeng.2016.11.121

Cited by 1 publication

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A wide range of applications for eddy current sensors with machine-learning has been implemented, such as proximity sensing [ 13 ], force sensing, distance sensing [ 14 ], and metal thickness estimation [ 15 ]. For instance, in [ 16 ], a support vector machine ‘supervised machine-learning algorithm’ has been implemented for classifying bi-metallic coins using an eddy current sensor.…”

Section: Introductionmentioning

confidence: 99%

“…Ramos et al [ 15 ] used inductive sensors to determine metal plate thickness together with a support vector machine (SVM) that classified their data into multiple classes of different thickness levels. Kantor et al [ 14 ] showed that ANNs could be used for material independent distance estimation with output errors from 1% to 3% depending on the sensor-to-target distance. Since eddy current sensors are useful in the characterization of metals with different magnetic properties, therefore, in this paper an application for the classification of bi-metallic coins is selected to separate the coins with similar mechanical properties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study of Machine-Learning Frameworks for the Elaboration of Feed-Forward Neural Networks by Varying the Complexity of Impedimetric Datasets Synthesized Using Eddy Current Sensors for the Characterization of Bi-Metallic Coins

Munjal

Arif

Wendler

et al. 2022

Sensors

View full text Add to dashboard Cite

A suitable framework for the development of artificial neural networks is important because it decides the level of accuracy, which can be reached for a certain dataset and increases the certainty about the reached classification results. In this paper, we conduct a comparative study for the performance of four frameworks, Keras with TensorFlow, Pytorch, TensorFlow, and Cognitive Toolkit (CNTK), for the elaboration of neural networks. The number of neurons in the hidden layer of the neural networks is varied from 8 to 64 to understand its effect on the performance metrics of the frameworks. A test dataset is synthesized using an analytical model and real measured impedance spectra by an eddy current sensor coil on EUR 2 and TRY 1 coins. The dataset has been extended by using a novel method based on interpolation technique to create datasets with different difficulty levels to replicate the scenario with a good imitation of EUR 2 coins and to investigate the limit of the prediction accuracy. It was observed that the compared frameworks have high accuracy performance for a lower level of difficulty in the dataset. As the difficulty in the dataset is raised, there was a drop in the accuracy of CNTK and Keras with TensorFlow depending upon the number of neurons in the hidden layers. It was observed that CNTK has the overall worst accuracy performance with an increase in the difficulty level of the datasets. Therefore, the major comparison was confined to Pytorch and TensorFlow. It was observed for Pytorch and TensorFlow with 32 and 64 neurons in hidden layers that there is a minor drop in the accuracy with an increase in the difficulty level of the dataset and was above 90% until both the coins were 80% closer to each other in terms of electrical and magnetic properties. However, Pytorch with 32 neurons in the hidden layer has a reduction in model size by 70% and 16.3% and predicts the class, 73.6% and 15.6% faster in comparison to TensorFlow and Pytorch with 64 neurons.

show abstract