Functional link neural network-based intelligent sensors for harsh environments
As the use of sensors is wide spread, the need to develop intelligent sensors that can automatically carry out calibration, compensate for the nonlinearity and mitigate the undesirable influence of the environmental parameters, is obvious. Smart sensing is needed for accurate and reliable readout of...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/94318 http://hdl.handle.net/10220/7254 http://www.sensorsportal.com/HTML/DIGEST/P_SI_38.htm |
| _version_ | 1826117644416188416 |
|---|---|
| author | Patra, Jagdish Chandra Chakraborty, Goutam Mukhopadhyay, Subhas |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Patra, Jagdish Chandra Chakraborty, Goutam Mukhopadhyay, Subhas |
| author_sort | Patra, Jagdish Chandra |
| collection | NTU |
| description | As the use of sensors is wide spread, the need to develop intelligent sensors that can automatically carry out calibration, compensate for the nonlinearity and mitigate the undesirable influence of the environmental parameters, is obvious. Smart sensing is needed for accurate and reliable readout of the measurand, especially when the sensor is operating in harsh environments. Here, we propose a novel computationally-efficient functional link neural network (FLNN) that effectively linearizes the response characteristics, compensates for the nonidealities, and calibrates automatically. With an example of a capacitive pressure sensor and through extensive simulation studies, we have shown that the performance of the FLNN-based sensor model is similar to that of a multilayer perceptron (MLP)-based model although the former has much lower computational requirement. The FLNN model is capable of producing linearized readout of the applied pressure with a full-scale error of only ±1.0% over a wide operating range of −50 to 200 ˚C. |
| first_indexed | 2024-10-01T04:30:41Z |
| format | Journal Article |
| id | ntu-10356/94318 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:30:41Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/943182020-05-28T07:17:46Z Functional link neural network-based intelligent sensors for harsh environments Patra, Jagdish Chandra Chakraborty, Goutam Mukhopadhyay, Subhas School of Computer Engineering DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation As the use of sensors is wide spread, the need to develop intelligent sensors that can automatically carry out calibration, compensate for the nonlinearity and mitigate the undesirable influence of the environmental parameters, is obvious. Smart sensing is needed for accurate and reliable readout of the measurand, especially when the sensor is operating in harsh environments. Here, we propose a novel computationally-efficient functional link neural network (FLNN) that effectively linearizes the response characteristics, compensates for the nonidealities, and calibrates automatically. With an example of a capacitive pressure sensor and through extensive simulation studies, we have shown that the performance of the FLNN-based sensor model is similar to that of a multilayer perceptron (MLP)-based model although the former has much lower computational requirement. The FLNN model is capable of producing linearized readout of the applied pressure with a full-scale error of only ±1.0% over a wide operating range of −50 to 200 ˚C. Published Version 2011-10-13T01:05:28Z 2019-12-06T18:54:05Z 2011-10-13T01:05:28Z 2019-12-06T18:54:05Z 2008 2008 Journal Article Patra, J. C., Chakraborty, G., & Mukhopadhyay, S. (2008). Functional Link Neural Network-based Intelligent Sensors for Harsh Environments. Sensors & Transducers Journal, 90, 209-220. 1726-5479 https://hdl.handle.net/10356/94318 http://hdl.handle.net/10220/7254 http://www.sensorsportal.com/HTML/DIGEST/P_SI_38.htm 131267 en Sensors & transducers journal © 2008 IFSA. This paper was published in Sensors & Transducers Journal and is made available as an electronic reprint (preprint) with permission of IFSA. The paper can be found at the following official URL: [http://www.sensorsportal.com/HTML/DIGEST/P_SI_38.htm]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law. 20 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation Patra, Jagdish Chandra Chakraborty, Goutam Mukhopadhyay, Subhas Functional link neural network-based intelligent sensors for harsh environments |
| title | Functional link neural network-based intelligent sensors for harsh environments |
| title_full | Functional link neural network-based intelligent sensors for harsh environments |
| title_fullStr | Functional link neural network-based intelligent sensors for harsh environments |
| title_full_unstemmed | Functional link neural network-based intelligent sensors for harsh environments |
| title_short | Functional link neural network-based intelligent sensors for harsh environments |
| title_sort | functional link neural network based intelligent sensors for harsh environments |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation |
| url | https://hdl.handle.net/10356/94318 http://hdl.handle.net/10220/7254 http://www.sensorsportal.com/HTML/DIGEST/P_SI_38.htm |
| work_keys_str_mv | AT patrajagdishchandra functionallinkneuralnetworkbasedintelligentsensorsforharshenvironments AT chakrabortygoutam functionallinkneuralnetworkbasedintelligentsensorsforharshenvironments AT mukhopadhyaysubhas functionallinkneuralnetworkbasedintelligentsensorsforharshenvironments |