SAFE-OCC: A novelty detection framework for Convolutional Neural Network sensors and its application in process control

Herein 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...

Full description

Saved in:
Bibliographic Details
Published in:Journal of process control 2022-07, Vol.117 (C)
Main Authors: Pulsipher, Joshua L., Coutinho, Luke D. J., Soderstrom, Tyler A., Zavala, Victor M.
Format: Article
Language:English
Subjects:
Automation & Control Systems
Computer vision
Deep learning
Engineering
INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Novelty detection
Process control
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Herein 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.
ISSN:0959-1524
1873-2771