Real-time detection of uncalibrated sensors using Neural Networks

TL;DR

This paper presents a real-time neural network-based method for detecting sensor uncalibrations in temperature, humidity, and pressure sensors, enabling quick identification of calibration issues in various environments.

Contribution

The work introduces an online machine learning approach using neural networks for detecting sensor uncalibrations, adaptable through transfer learning for different sensors and environments.

Findings

Detects uncalibrations with deviations of 0.25°C, 1% RH, and 1.5 Pa

Operates in real-time for online monitoring

Can be adapted to new sensors with minimal data

Abstract

Nowadays, sensors play a major role in several contexts like science, industry and daily life which benefit of their use. However, the retrieved information must be reliable. Anomalies in the behavior of sensors can give rise to critical consequences such as ruining a scientific project or jeopardizing the quality of the production in industrial production lines. One of the more subtle kind of anomalies are uncalibrations. An uncalibration is said to take place when the sensor is not adjusted or standardized by calibration according to a ground truth value. In this work, an online machine-learning based uncalibration detector for temperature, humidity and pressure sensors was developed. This solution integrates an Artificial Neural Network as main component which learns from the behavior of the sensors under calibrated conditions. Then, after trained and deployed, it detects uncalibrations once they take place. The obtained results show that the proposed solution is able to detect uncalibrations for deviation values of 0.25 degrees, 1% RH and 1.5 Pa, respectively. This solution can be adapted to different contexts by means of transfer learning, whose application allows for the addition of new sensors, the deployment into new environments and the retraining of the model with minimum amounts of data.