Managing the Impact of Sensor's Thermal Noise in Machine Learning for Nuclear Applications

TL;DR

This paper examines how thermal noise in sensors affects machine learning models in nuclear power plant applications, offering recommendations and insights on selecting resilient models to mitigate accuracy loss.

Contribution

It identifies the impact of sensor thermal noise on machine learning accuracy in nuclear applications and proposes mitigation strategies and model selection guidelines.

Findings

Thermal noise varies between sensors affecting SNR.

Different machine learning algorithms are impacted differently by thermal noise.

Selecting more resilient models can mitigate accuracy degradation.

Abstract

Sensors such as accelerometers, magnetometers, and gyroscopes are frequently utilized to perform measurements in nuclear power plants. For example, accelerometers are used for vibration monitoring of critical systems. With the recent rise of machine learning, data captured from such sensors can be used to build machine learning models for predictive maintenance and automation. However, these sensors are known to have thermal noise that can affect the sensor's accuracy. Thermal noise differs between sensors in terms of signal-to-noise ratio (SNR). This thermal noise will cause an accuracy drop in sensor-fusion-based machine learning models when deployed in production. This paper lists some applications for Canada Deuterium Uranium (CANDU) reactors where such sensors are used and therefore can be impacted by the thermal noise issue if machine learning is utilized. A list of recommendations to help mitigate the issue when building future machine learning models for nuclear applications based on sensor fusion is provided. Additionally, this paper demonstrates that machine learning algorithms can be impacted differently by the issue, therefore selecting a more resilient model can help in mitigating it.