Multifrequency Inductive Sensor System for Classification of Bimetallic Coins

Munjal, Rohan; Sajjad, Farhan Ahmad; Wendler, Frank; Kanoun, Olfa

doi:10.1109/tim.2020.3011489

Cited by 7 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, ‘EUR 2 and TRY 1’ bi-metallic coins are chosen, which consist of two metal layers in the centerpiece with similar geometrical and mechanical properties [ 16 ]. The outer ring of a EUR 2 coin is made from copper and nickel while the center layer consists of nickel and brass.…”

Section: Principle Of Eddy Current Sensor and Application In Coin Cla...mentioning

confidence: 99%

“…The sensor coil was placed co-axially over the coin so that the center of the coin overlaps with the center of the coil to physically measure the inductance values in the presence of both coins as shown in Figure 2 a. The measurement process was carried out using an Impedance Analyzer in the frequency range of 1 kHz to 10 MHz to extract the information from different layers of the coin with varying penetration depths depending upon the frequency [ 16 ] as shown in Figure 2 b.…”

Section: Principle Of Eddy Current Sensor and Application In Coin Cla...mentioning

confidence: 99%

“…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. 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.…”

Section: Introductionmentioning

confidence: 99%

“…The selected coins have nearly the same mechanical and geometrical properties and thus the coin with a lower economic value, i.e., TRY 1 can be used as a counterfeit coin for the coin with higher economical value, i.e., EUR 2 in the vending machines. Thus, there is a need for coin classification with upgraded technology to avoid counterfeiting and misusing of lower economical value coins in place of higher economical values coins [ 16 ]. Moreover, bi-metallic coin consists of security features within the layered structure of coins with different properties.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Self Cite

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

Section: Principle Of Eddy Current Sensor and Application In Coin Cla...mentioning

confidence: 99%

Section: Principle Of Eddy Current Sensor and Application In Coin Cla...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to the PEC, the MEC has better signal-to-noise ratio (SNR) particularly under high working frequencies [ 23 ]). By using multiple frequency channels [ 24 ] and curve-matching functions (e.g., polynomials), online real-time monitoring of parameters can be achieved. However, like other EC techniques, MEC can be significantly affected by coating variations that manifest in the lift-off distance between the sensor and test piece.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Coating Thickness Using Lift-Off Insensitivity of Eddy Current Sensor

Meng

Lü

Yin

et al. 2021

Sensors

View full text Add to dashboard Cite

Defect detection in ferromagnetic substrates is often hampered by nonmagnetic coating thickness variation when using conventional eddy current testing technique. The lift-off distance between the sample and the sensor is one of the main obstacles for the thickness measurement of nonmagnetic coatings on ferromagnetic substrates when using the eddy current testing technique. Based on the eddy current thin-skin effect and the lift-off insensitive inductance (LII), a simplified iterative algorithm is proposed for reducing the lift-off variation effect using a multifrequency sensor. Compared to the previous techniques on compensating the lift-off error (e.g., the lift-off point of intersection) while retrieving the thickness, the simplified inductance algorithms avoid the computation burden of integration, which are used as embedded algorithms for the online retrieval of lift-offs via each frequency channel. The LII is determined by the dimension and geometry of the sensor, thus eliminating the need for empirical calibration. The method is validated by means of experimental measurements of the inductance of coatings with different materials and thicknesses on ferrous substrates (dual-phase alloy). The error of the calculated coating thickness has been controlled to within 3% for an extended lift-off range of up to 10 mm.

show abstract

Machine Vision Using Cellphone Camera: A comparison of deep networks for classifying three challenging denominations of Indian coins

Joshi

Shah

et al. 2022

2022 28th International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

View full text Add to dashboard Cite

Multifrequency Inductive Sensor System for Classification of Bimetallic Coins

Cited by 7 publications

References 26 publications

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

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

Evaluation of Coating Thickness Using Lift-Off Insensitivity of Eddy Current Sensor

Machine Vision Using Cellphone Camera: A comparison of deep networks for classifying three challenging denominations of Indian coins

Contact Info

Product

Resources

About