Enhancing sensor linearity through the translinear circuit implementation of piecewise and neural network models

Sundararajan Seenivasaan; Naduvil Madhusoodanan Kottarthil; Sundararajan Seenivasaan; Naduvil Madhusoodanan Kottarthil

doi:10.3934/electreng.2023012

AIMS Electronics and Electrical Engineering

2023, Volume 7, Issue 3: 196-216. doi: 10.3934/electreng.2023012

Previous Article Next Article

Research article

Enhancing sensor linearity through the translinear circuit implementation of piecewise and neural network models

Department of Instrumentation, Cochin University of Science and Technology, Cochin, Kerala, India

Received: 27 May 2023 Revised: 17 July 2023 Accepted: 03 August 2023 Published: 09 August 2023

The performance of the control system relies on the linearity of the sensor, which can be influenced by various factors such as aging and alterations in material properties. However, current sensor linearization techniques, such as utilizing neural networks and piecewise regression models in the digital domain, suffer from issues like errors, excessive power consumption, and slow response times. To address these constraints, this investigation employs a translinear based analog circuit to realize neural networks and piecewise regression models for the purpose of linearizing the selected sensors. A conventional feed-forward back propagation network is constructed and trained using the Levenberg-Marquardt algorithm. The developed linearization algorithm is implemented using a translinear circuit, where the trained weights, biases, and sensor output are fed as input current sources into the current-mode circuit. Further in this work, the piecewise regression model is designed and implemented using a translinear circuit and the breakpoint is determined using 'R' language. The simulation results indicate that the implementation of the current-mode circuit with metal-oxide-semiconductor field-effect transistors (MOSFETs) for the neural network algorithm leads to a substantial reduction in full-scale error as compared to the piecewise current mode model. Additionally, a performance analysis was conducted to compare the utilization of current-mode circuits with digital approaches for the linearization of sensors. The proposed translinear implementation surpasses the other researcher's work by delivering notable results. It showcases a significant improvement in linearity, ranging from 60% to 80%, for the selected sensors. Furthermore, the proposed implementation excels not only in linearity but also in terms of both response speed and power consumption. The improvement in the linearity of the sensor can be enhanced further by replacing the MOSFETs with bipolar transistors or any versatile materials such as gallium arsenide or gallium nitride-based transistors.
- sensor,
- linearization,
- neural network,
- translinear circuit,
- power consumption
Citation: Sundararajan Seenivasaan, Naduvil Madhusoodanan Kottarthil. Enhancing sensor linearity through the translinear circuit implementation of piecewise and neural network models[J]. AIMS Electronics and Electrical Engineering, 2023, 7(3): 196-216. doi: 10.3934/electreng.2023012

Related Papers:

Abstract

The performance of the control system relies on the linearity of the sensor, which can be influenced by various factors such as aging and alterations in material properties. However, current sensor linearization techniques, such as utilizing neural networks and piecewise regression models in the digital domain, suffer from issues like errors, excessive power consumption, and slow response times. To address these constraints, this investigation employs a translinear based analog circuit to realize neural networks and piecewise regression models for the purpose of linearizing the selected sensors. A conventional feed-forward back propagation network is constructed and trained using the Levenberg-Marquardt algorithm. The developed linearization algorithm is implemented using a translinear circuit, where the trained weights, biases, and sensor output are fed as input current sources into the current-mode circuit. Further in this work, the piecewise regression model is designed and implemented using a translinear circuit and the breakpoint is determined using 'R' language. The simulation results indicate that the implementation of the current-mode circuit with metal-oxide-semiconductor field-effect transistors (MOSFETs) for the neural network algorithm leads to a substantial reduction in full-scale error as compared to the piecewise current mode model. Additionally, a performance analysis was conducted to compare the utilization of current-mode circuits with digital approaches for the linearization of sensors. The proposed translinear implementation surpasses the other researcher's work by delivering notable results. It showcases a significant improvement in linearity, ranging from 60% to 80%, for the selected sensors. Furthermore, the proposed implementation excels not only in linearity but also in terms of both response speed and power consumption. The improvement in the linearity of the sensor can be enhanced further by replacing the MOSFETs with bipolar transistors or any versatile materials such as gallium arsenide or gallium nitride-based transistors.

References

[1]	Murmu A, Bhattacharyya B, Munshi S (2018) A synergy of voltage-to-frequency converter and continued-fraction algorithm for processing thermocouple signals. Measurement 116: 514-522. https://doi.org/10.1016/j.measurement.2017.11.047 doi: 10.1016/j.measurement.2017.11.047
[2]	Ximin L (2010) A linear thermocouple temperature meter based on inverse reference function. International Conference on Intelligent Computation Technology and Automation 1: 138-143. https://doi.org/10.1109/ICICTA.2010.284 doi: 10.1109/ICICTA.2010.284
[3]	Mukherjee A, Sarkar D, Sen A, Dey D, Munshi S (2013) An analog signal conditioning circuit for thermocouple temperature sensor employing thermistor for cold junction compensation. International conference on control, automation, robotics and embedded systems, 1-5. https://doi.org/10.1109/CARE.2013.6733711
[4]	Mondal N, Abudhahir A, Jana SK, Munshi S, Bhattacharya DP (2009) A log amplifier based linearization scheme for thermocouples. Sensors & Transducers 100: 1.
[5]	Srinivasan K, Sarawade PD (2019) An included angle-based multilinear model technique for thermocouple linearization. IEEE Transactions on Instrumentation and Measurement 69: 4412-4424. https://doi.org/10.1109/TIM.2019.2947951 doi: 10.1109/TIM.2019.2947951
[6]	Wen D, Qing L, Qiang L (2007) Calibration system for thermocouple application based on technology of virtual instrument and neural network. 8th International Conference on Electronic Measurement and Instruments, 1-268. https://doi.org/10.1109/ICEMI.2007.4350439
[7]	Sundararajan S, Kottarthil Naduvil M, Abudhahir A, Karuna KG, Noble G (2022) Synthesis and study of evolutionary optimised sensor linearisation with translinear & FPGA circuits. International Journal of Electronics 109: 699-720. https://doi.org/10.1080/00207217.2021.1941287 doi: 10.1080/00207217.2021.1941287
[8]	Radetić R, Pavlov-Kagadejev M, Milivojević N (2015) The analog linearization of Pt100 working characteristic. Serbian Journal of Electrical Engineering 12: 345-357. https://doi.org/10.2298/SJEE1503345R doi: 10.2298/SJEE1503345R
[9]	Hotra O, Boyko O (2015) Analogue linearization of transfer function of resistive temperature transducers. In Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 9662: 1230-1237. https://doi.org/10.1117/12.2205449 doi: 10.1117/12.2205449
[10]	Abudhahir A, Baskar S (2008) Analogue linearization of transfer function of resistive temperature transducers. Measurement Science and Technology 19: 045103. https://doi.org/10.1088/0957-0233/19/4/045103 doi: 10.1088/0957-0233/19/4/045103
[11]	Ghaly SMA (2019) LabVIEW based implementation of resistive temperature detector linearization techniques. Engineering, Technology & Applied Science Research 9: 4530-4533. https://doi.org/10.48084/etasr.2894 doi: 10.48084/etasr.2894
[12]	Živanović D, Simić M (2021) Two-stage segment linearization as part of the thermocouple measurement chain. Measurement and Control 54: 141-151. https://doi.org/10.1177/0020294020986833 doi: 10.1177/0020294020986833
[13]	Anandanatarajan R, Mangalanathan U, Gandhi U (2022) Linearization of temperature sensors (K-type thermocouple) using polynomial non-linear regression technique and an IoT-based data logger interface. Experimental Techniques, 1-10. https://doi.org/10.1007/s40799-022-00599-w doi: 10.1007/s40799-022-00599-w
[14]	Phadnis, MG (2020) Real time linearization of sensor response using a novel polynomial estimation method. IEEE Instrumentation & Measurement Magazine 23: 73-78. https://doi.org/10.1109/MIM.2020.8979528 doi: 10.1109/MIM.2020.8979528
[15]	Khan SA, Shahani DT, Agarwala AK (2003) Sensor calibration and compensation using artificial neural network. ISA transactions 42: 337-352. https://doi.org/10.1016/S0019-0578(07)60138-4 doi: 10.1016/S0019-0578(07)60138-4
[16]	Sundararajan S, Kottarthil Naduvil M, Abudhahir A, Karuna KG, Noble G (2022) Synthesis and study of evolutionary optimised sensor linearisation with translinear & FPGA circuits. International Journal of Electronics 109: 699-720. https://doi.org/10.1080/00207217.2021.1941287 doi: 10.1080/00207217.2021.1941287
[17]	Van Ooyen A, Nienhuis B (1992) Improving the convergence of the back-propagation algorithm. Neural networks 5: 465-471. https://doi.org/10.1016/0893-6080(92)90008-7 doi: 10.1016/0893-6080(92)90008-7
[18]	Vujičić T, Matijevi T, Ljucović J, Balota A, Ševarac Z (2016) Comparative analysis of methods for determining number of hidden neurons in artificial neural network. In Central european conference on information and intelligent systems 219.
[19]	Shaterian M, Twigg CM, Azhari J (2013) An MTL-based configurable block for current-mode nonlinear analog computation. IEEE Transactions on Circuits and Systems Ⅱ: Express Briefs 60: 587-591. https://doi.org/10.1109/TCSII.2013.2268660 doi: 10.1109/TCSII.2013.2268660
[20]	Serrano-Gotarredona T, Linares-Barranco B, Andreou AG (1999) A general translinear principle for subthreshold MOS transistors. IEEE transactions on circuits and systems Ⅰ: fundamental theory and applications 46: 607-616. https://doi.org/10.1109/81.762926 doi: 10.1109/81.762926

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)