SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control

TL;DR

This paper introduces SAFE-OCC, a framework that enhances CNN sensor reliability in process control by detecting novel visual data in real-time using features from the CNN itself.

Contribution

SAFE-OCC is a novel framework that utilizes CNN convolutional features for real-time novelty detection, improving safety in process control applications.

Findings

Effective novelty detection demonstrated in simulated environments

Utilizes CNN features directly, avoiding separate latent space

Enhances safety and reliability of CNN sensors in control systems

Abstract

We present a novelty detection framework for Convolutional Neural Network (CNN) sensors that we call Sensor-Activated Feature Extraction One-Class Classification (SAFE-OCC). We show that this framework enables the safe use of computer vision sensors in process control architectures. Emergent control applications use CNN models to map visual data to a state signal that can be interpreted by the controller. Incorporating such sensors introduces a significant system operation vulnerability because CNN sensors can exhibit high prediction errors when exposed to novel (abnormal) visual data. Unfortunately, identifying such novelties in real-time is nontrivial. To address this issue, the SAFE-OCC framework leverages the convolutional blocks of the CNN to create an effective feature space to conduct novelty detection using a desired one-class classification technique. This approach engenders a feature space that directly corresponds to that used by the CNN sensor and avoids the need to derive an independent latent space. We demonstrate the effectiveness of SAFE-OCC via simulated control environments.