Data requirements for an anomaly detector in an automated safeguards system using neural networks

Conference · Sun Aug 01 04:00:00 EDT 1993

OSTI ID:10183567

Whiteson, R ^[1]; Britschgi, J J ^[2]

---

1. Los Alamos National Lab., NM (United States)
2. Westinghouse Idaho Nuclear Co., Inc., Idaho Falls, ID (United States)

An automated safeguards system must be able to detect and identify anomalous events in a near-real-time manner. Our approach to anomaly detection is based on the demonstrated ability of neural networks to model complex, nonlinear, real-time processes. By modeling the normal behavior of processes, we can detect how a system should behave and, thereby, detect when an abnormal state or event occurs. In this paper, we explore the computational intensity of training neural networks, and we discuss the issues involved in gathering and preprocessing the safeguards data necessary to train a neural network for anomaly detection. We explore data requirements for training neural networks and evaluate how different features of the training data affect the training and operation of the networks. We use actual process data to train our previous 3-tank model and compare the results to those achieved using simulated safeguards data. Comparisons are made on the basis of required training times in addition to correctness of prediction.

• Research Organization: Los Alamos National Lab., NM (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 10183567
• Report Number(s): LA-UR--93-2604; CONF-930749--46; ON: DE93018544
• Country of Publication: United States
• Language: English

Related Subjects

055001
98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION
AUTOMATION
EXPERT SYSTEMS
NEURAL NETWORKS
NUCLEAR MATERIALS MANAGEMENT
REAL TIME SYSTEMS
SAFEGUARDS
SECURITY
TECHNICAL ASPECTS