Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks
The development of smart sensors involves the design of reconfigurable systemscapable of working with different input sensors. Reconfigurable systems ideally shouldspend the least possible amount of time in their calibration. An autocalibration algorithmfor intelligent sensors should be able to fix...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2007-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/7/8/1509/ |
| _version_ | 1798004086658826240 |
|---|---|
| author | Gilberto Bojorquez Gilberto Herrera Mario Chacón Mariano Carrillo José Rivera |
| author_facet | Gilberto Bojorquez Gilberto Herrera Mario Chacón Mariano Carrillo José Rivera |
| author_sort | Gilberto Bojorquez |
| collection | DOAJ |
| description | The development of smart sensors involves the design of reconfigurable systemscapable of working with different input sensors. Reconfigurable systems ideally shouldspend the least possible amount of time in their calibration. An autocalibration algorithmfor intelligent sensors should be able to fix major problems such as offset, variation of gainand lack of linearity, as accurately as possible. This paper describes a new autocalibrationmethodology for nonlinear intelligent sensors based on artificial neural networks, ANN.The methodology involves analysis of several network topologies and training algorithms.The proposed method was compared against the piecewise and polynomial linearizationmethods. Method comparison was achieved using different number of calibration points,and several nonlinear levels of the input signal. This paper also shows that the proposedmethod turned out to have a better overall accuracy than the other two methods. Besides,experimentation results and analysis of the complete study, the paper describes theimplementation of the ANN in a microcontroller unit, MCU. In order to illustrate themethod capability to build autocalibration and reconfigurable systems, a temperaturemeasurement system was designed and tested. The proposed method is an improvement over the classic autocalibration methodologies, because it impacts on the design process of intelligent sensors, autocalibration methodologies and their associated factors, like time and cost. |
| first_indexed | 2024-04-11T12:17:58Z |
| format | Article |
| id | doaj.art-2c7a9ca720714738b603958ddf1e2c86 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:17:58Z |
| publishDate | 2007-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2c7a9ca720714738b603958ddf1e2c862022-12-22T04:24:11ZengMDPI AGSensors1424-82202007-08-01781509152910.3390/s7081509Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural NetworksGilberto BojorquezGilberto HerreraMario ChacónMariano CarrilloJosé RiveraThe development of smart sensors involves the design of reconfigurable systemscapable of working with different input sensors. Reconfigurable systems ideally shouldspend the least possible amount of time in their calibration. An autocalibration algorithmfor intelligent sensors should be able to fix major problems such as offset, variation of gainand lack of linearity, as accurately as possible. This paper describes a new autocalibrationmethodology for nonlinear intelligent sensors based on artificial neural networks, ANN.The methodology involves analysis of several network topologies and training algorithms.The proposed method was compared against the piecewise and polynomial linearizationmethods. Method comparison was achieved using different number of calibration points,and several nonlinear levels of the input signal. This paper also shows that the proposedmethod turned out to have a better overall accuracy than the other two methods. Besides,experimentation results and analysis of the complete study, the paper describes theimplementation of the ANN in a microcontroller unit, MCU. In order to illustrate themethod capability to build autocalibration and reconfigurable systems, a temperaturemeasurement system was designed and tested. The proposed method is an improvement over the classic autocalibration methodologies, because it impacts on the design process of intelligent sensors, autocalibration methodologies and their associated factors, like time and cost.http://www.mdpi.com/1424-8220/7/8/1509/intelligent sensorsreconfigurable systemsautocalibrationlinearizationartificial neural network. |
| spellingShingle | Gilberto Bojorquez Gilberto Herrera Mario Chacón Mariano Carrillo José Rivera Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks Sensors intelligent sensors reconfigurable systems autocalibration linearization artificial neural network. |
| title | Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks |
| title_full | Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks |
| title_fullStr | Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks |
| title_full_unstemmed | Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks |
| title_short | Self-Calibration and Optimal Response in Intelligent Sensors Design Based on Artificial Neural Networks |
| title_sort | self calibration and optimal response in intelligent sensors design based on artificial neural networks |
| topic | intelligent sensors reconfigurable systems autocalibration linearization artificial neural network. |
| url | http://www.mdpi.com/1424-8220/7/8/1509/ |
| work_keys_str_mv | AT gilbertobojorquez selfcalibrationandoptimalresponseinintelligentsensorsdesignbasedonartificialneuralnetworks AT gilbertoherrera selfcalibrationandoptimalresponseinintelligentsensorsdesignbasedonartificialneuralnetworks AT mariochacaƒa3n selfcalibrationandoptimalresponseinintelligentsensorsdesignbasedonartificialneuralnetworks AT marianocarrillo selfcalibrationandoptimalresponseinintelligentsensorsdesignbasedonartificialneuralnetworks AT josaƒarivera selfcalibrationandoptimalresponseinintelligentsensorsdesignbasedonartificialneuralnetworks |