scholarly journals BOOSTR: A Dataset for Accelerator Control Systems

Data ◽  
2021 ◽  
Vol 6 (4) ◽  
pp. 42
Author(s):  
Diana Kafkes ◽  
Jason St. John
Keyword(s):  
Artificial Intelligence ◽  
Time Series ◽  
Reinforcement Learning ◽  
Control Systems ◽  
Power Supply ◽  
Cycle Time ◽  
Rapid Cycling ◽  
Operation Optimization ◽  
Advanced Control ◽  
Rapid Cycling Synchrotron

The Booster Operation Optimization Sequential Time-series for Regression (BOOSTR) dataset was created to provide a cycle-by-cycle time series of readings and settings from instruments and controllable devices of the Booster, Fermilab’s Rapid-Cycling Synchrotron (RCS) operating at 15 Hz. BOOSTR provides a time series from 55 device readings and settings that pertain most directly to the high-precision regulation of the Booster’s gradient magnet power supply (GMPS). To our knowledge, this is one of the first well-documented datasets of accelerator device parameters made publicly available. We are releasing it in the hopes that it can be used to demonstrate aspects of artificial intelligence for advanced control systems, such as reinforcement learning and autonomous anomaly detection.

scholarly journals Power Supply Systems for Rapid Cycling Synchrotron

2006 ◽  
Vol 126 (5) ◽  
pp. 681-689 ◽  
Author(s):  
Yasuhiro Watanabe ◽  
Toshikazu Adachi ◽  
Hirohiko Someya ◽  
Shoichiro Koseki ◽  
Shinichi Ogawa
Keyword(s):  
Power Supply ◽  
Rapid Cycling ◽  
Supply Systems ◽  
Rapid Cycling Synchrotron

scholarly journals Analysis of methods to optimize control systems for power supply of marine vessels using fuzzy logic and fractal analysis

2021 ◽  
Vol 2061 (1) ◽  
pp. 012088
Author(s):  
E V Khekert ◽  
A I Epikhin
Keyword(s):  
Time Series ◽  
Fuzzy Logic ◽  
Control Systems ◽  
Fractal Analysis ◽  
Power Supply ◽  
Effective Control ◽  
Air Cooling ◽  
Short Term ◽  
Depth Analysis ◽  
Marine Vessels

Abstract The paper considers the features of promising methods to optimize the control systems for power supply of marine vessels using fuzzy logic and fractal analysis. In order to design an effective control contour for the power supply system (PSS), it is proposed to use synergistic mechantronic systems based on intelligent technologies with fundamentally new properties that allow for a more effective solution of control problems using fractal analysis of time series to increase the adequacy of forecasting through in-depth analysis of the causes of emergency situations. The synergistic effect SE of the control within such systems is a set of effects obtained as a result of their combination and synchronization in time and space. Practical aspects of fractal analysis are considered on the example of a two-cycle engine with supercharging and air cooling. In the study of fractal processes, a method is proposed for identifying and eliminating the short-term dependence of the value of the time series of the process S(t), which is characteristic of autoregressive processes, using regression with respect to S(t-1) and conducting the R/S analysis of the remainder X(t). Short-term dependence is eliminated provided that long-term dependence is maintained. Autoregressive AR(1) differences are analyzed at a certain time interval for various engine operating modes. The results of the R/S analysis of the engine operation and the determination of the Hurst exponent are used to increase the efficiency of forecasting and control of the PSS in the period of the detected chaotic behavior of the time series.

Power supply systems for rapid cycling synchrotron

2007 ◽  
Vol 160 (1) ◽  
pp. 49-60
Author(s):  
Yasuhiro Watanabe ◽  
Toshikazu Adachi ◽  
Hirohiko Someya ◽  
Shoichiro Koseki ◽  
Shinichi Ogawa
Keyword(s):  
Power Supply ◽  
Rapid Cycling ◽  
Supply Systems ◽  
Rapid Cycling Synchrotron
Sign in / Sign up

Export Citation Format

Share Document