Monitoring reliability of sensors in an array by neural networks

Pardo, Matteo; Faglia, G.; Sberveglieri, G.; Corte, Marilene Gabriel Dalla; Masulli, Francesco; Riani, Massimo

doi:10.1016/s0925-4005(00)00402-0

Cited by 24 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…100,101 Improved filtering methods using ANN and sparse filtering will assist in the removal of unwanted noise and drift due to sensor degradation or variation from external factors (humidity, additional vapors). Selection of different sensors using ANN to determine which are responding first and the delay between responses can give additional information for analyte classification 27,102 as well as directional information for tracking an odor plume as demonstrated in mammals 94,96 and some robots 52,85 .…”

Section: -Additional Considerationsmentioning

confidence: 99%

Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Ryman

Bruce

Freund

2016

Sensors and Actuators B: Chemical

View full text Add to dashboard Cite

The human olfactory system can classify new odors in a dynamic environment with varying odor complexity and concentration, while simultaneously reducing the influence of stable background odors. Replication of this capability has remained an active area of research over the past 3 decades and has great potential to advance medical diagnostics, environmental monitoring and industrial monitoring, among others. New methods for rapid dynamic temporal evaluation of chemical sensor arrays for the monitoring of analytes is explored in this work. One such method is high and low bandpass filtering of changing sensor responses; this is applied to reduce the effects of background noise and sensor drift over time. Processed sensor array responses, coupled

show abstract

Section: -Additional Considerationsmentioning

confidence: 99%

Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Ryman

Bruce

Freund

2016

Sensors and Actuators B: Chemical

View full text Add to dashboard Cite

show abstract

“…Generally, fault diagnosis of commercial products would be conducted with standard gas sample off-line. Tin oxide gas sensors have been researched for several decades, but only a few works on the fault diagnosis have been reported [1].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of tin oxide gas sensor using energy barrier and ART-2 neural network

Lee¹,

Shim²

2024

RE&PQJ

View full text Add to dashboard Cite

We propose a method of fault diagnosis for tin oxide gas sensors using energy barriers at the contacting surfaces of the particles of tin oxide film and ART-2 NN (adaptive resonance theory 2 neural network) with uneven vigilance parameters. We diagnosed tin oxide gas sensors upon exposure to oil vapor, silicon vapor, and high humidity. The sensor feature for diagnosis was an energy barrier between particles extracted by temperature-simulated conductance measurement. The feature was manipulated by an ART-2 neural network and the performance was finally evaluated with real n-C 4 H 10 gas. This method proves to be helpful to diagnose a fault that was typically generated by oil vapor, silicon vapor, and high humidity.

show abstract

“…Finally, some models implement a closed-loop mechanism where feedbacks induce an updating of classifier parameters to follow the changes in sensor responses [17][18]. The so called adaptive or evolutionary algorithms belong to this category and have shown the capability to compensate the effects due to aging, poisoning [19][20][21][22][23] and malfunctioning [24][25].…”

Section: Introductionmentioning

confidence: 99%

Self-Repairing classification algorithms for chemical sensor array

Natale

Martinelli

2019

Sensors and Actuators B: Chemical

View full text Add to dashboard Cite

Chemical sensors are usually affected by drift, have low fabrication reproducibility and can experience failure or breaking events over the long term. Albeit improvements in fabrication processes are often slow and inadequate for completely surmounting these issues, data analysis can be used as of now to improve the available device performances. The present paper illustrates an algorithm, called Self-Repairing (SR), developed for repairing classification models after the occurrences of failures in sensor arrays. The procedure considers replacing broken sensors with replicas and eventually Self-Repairing algorithm trains these blank elements. Unlike the habitual alternatives reported in literature, SR performs this operation without the need of a whole new recalibration, references gas measurements or transfer dataset and, at the same time, without interrupting the on-going procedure of gas identification. Furthermore, Self-Repairing algorithm can utilize most of the standard classifiers as core algorithm; in this paper SR has been applied to k-NN, PLS-DA and LDA as examples. Models have been tested in a synthetic and real scenario considering sensor arrays affected by drift and eventually by failures. Real experiment has been performed with a set of metal oxide sensors over an 18-months period. Finally, the algorithm has been compared with standard version of chosen classifiers (k-NN, LDA and PLS-DA) showing superior performances of Self-Repairing and increasing the tolerance versus consecutive failures.

show abstract

Monitoring reliability of sensors in an array by neural networks

Cited by 24 publications

References 10 publications

Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Fault Diagnosis of tin oxide gas sensor using energy barrier and ART-2 neural network

Self-Repairing classification algorithms for chemical sensor array

Contact Info

Product

Resources

About