An application of neural networks to process and materials control
Process control consists of two basic elements: a model of the process and knowledge of the desired control algorithm. In some cases the level of the control algorithm is merely supervisory, as in an alarm-reporting or anomaly-detection system. If the model of the process is known, then a set of equations may often be solved explicitly to provide the control algorithm. Otherwise, the model has to be discovered through empirical studies. Neural networks have properties that make them useful in this application. They can learn (make internal models from experience or observations). The problem of anomaly detection in materials control systems fits well into this general control framework. To successfully model a process with a neutral network, a good set of observables must be chosen. These observables must in some sense adequately span the space of representable events, so that a signature metric can be built for normal operation. In this way, a non-normal event, one that does not fit within the signature, can be detected. In this paper, we discuss the issues involved in applying a neural network model to anomaly detection in materials control systems. These issues include data selection and representation, network architecture, prediction of events, the use of simulated data, and software tools. 10 refs., 4 figs., 1 tab.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-36
- OSTI ID:
- 5528167
- Report Number(s):
- LA-UR-91-2386; CONF-910774-62; ON: DE91016016
- Resource Relation:
- Conference: 32. Institute of Nuclear Materials Management (INMM) annual meeting, New Orleans, LA (United States), 28-31 Jul 1991
- Country of Publication:
- United States
- Language:
- English
Similar Records
Anomaly detection in an automated safeguards system using neural networks
Anomaly detection in an automated safeguards system using neural networks
Related Subjects
NEURAL NETWORKS
RADIOACTIVE MATERIALS
MONITORING
PROCESS CONTROL
ACCOUNTING
COMPUTERIZED SIMULATION
DETECTION
NUCLEAR MATERIALS MANAGEMENT
SAFEGUARDS
CONTROL
MANAGEMENT
MATERIALS
SIMULATION
055001* - Nuclear Fuels- Safeguards
Inspection
& Accountability- Technical Aspects