To submit a request, click below on the link of the version you wish to order. Rules for end-users are available here.
| Program name | Package id | Status | Status date |
|---|---|---|---|
| PURSE | NEA-1936/01 | Arrived | 12-MAY-2025 |
Machines used:
| Package ID | Orig. computer | Test computer |
|---|---|---|
| NEA-1936/01 | Many Computers |
The PURSE Database (Purdue University Reactor Shutdown Event Database) contains multi-variate time series data collected from the PUR-1 research reactor at Purdue University, USA, during several shutdown events (SCRAM and Gang Lower) originating from different power levels.
The PURSE database contains data recorded at the PUR-1 research reactor at Purdue University, USA. The data were recorded to the second over a duration of six months, equating to roughly 15 million points for each signal type. Measured signals include neutron flux, rod positions, radiation levels, pool temperature, and power. The dataset contains several shutdown events and was prepared to benchmark artificial intelligence and machine learning applications.
William Richards, Zachery Dahm, Oliver Buss, Catalina Anghel, Kamal Moravej, Xingang Zhao, Basma Foad, Upendra Rohatgi, Gregory Delipei, Xu Wu, and Stylianos Chatzidakis (2024). Developing a Machine Learning Benchmark Using Real-Time Data from the PUR-1 Reactor for Nuclear Applications. Transactions of the American Nuclear Society. Volume 130, Number 1, June 2024, Pages 242-245.
Keywords: database, reactor shutdown.
