Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From real-time calibrations to smart HV tuning for FAIR

Valentin Kladov, Johan Messchendorp, James Ritman

TL;DR

Real-time calibration for FAIR-era gaseous trackers is addressed by predicting calibration constants from environmental and operational data. The method extends a neural-network predictor with expanded input features, trainable normalization, and a Landau0Gaussian target (Langaus) for more stable fits, enabling HV-aware operation. By merging beam-time and cosmic-ray datasets, learned dependencies transfer across data-taking scenarios, allowing both real-time calibration and inference of optimal HV settings. The results show $RMSE ≈ 1.5σ$, precision ≈ 60%, robustness ≈ 10% with low latency, supporting a practical framework for real-time detector control during data acquisition.

Abstract

Real-time data processing of the next generation of experiments at FAIR requires reliable event reconstruction and thus depends heavily on in-situ calibration procedures. Previously, we developed a neural-network-based approach that predicts calibration parameters from continuously available environmental and operational data and validated it on the HADES Multiwire Drift Chambers (MDCs), achieving fast predictions as accurate as offline calibrations. In this work, we introduce several methodological improvements that enhance both accuracy and the ability to adapt to new data. These include changes to the input features, better offline calibration and trainable normalizations. Furthermore, by combining beam-time and cosmic-ray datasets, we demonstrate that the learned dependencies can be transferred between very different data-taking scenarios. This enables the network not only to provide real-time calibration predictions, but also to infer optimal high-voltage settings, thus establishing a practical framework for a real-time detector control during data acquisition process.

From real-time calibrations to smart HV tuning for FAIR

TL;DR

Real-time calibration for FAIR-era gaseous trackers is addressed by predicting calibration constants from environmental and operational data. The method extends a neural-network predictor with expanded input features, trainable normalization, and a Landau0Gaussian target (Langaus) for more stable fits, enabling HV-aware operation. By merging beam-time and cosmic-ray datasets, learned dependencies transfer across data-taking scenarios, allowing both real-time calibration and inference of optimal HV settings. The results show , precision ≈ 60%, robustness ≈ 10% with low latency, supporting a practical framework for real-time detector control during data acquisition.

Abstract

Real-time data processing of the next generation of experiments at FAIR requires reliable event reconstruction and thus depends heavily on in-situ calibration procedures. Previously, we developed a neural-network-based approach that predicts calibration parameters from continuously available environmental and operational data and validated it on the HADES Multiwire Drift Chambers (MDCs), achieving fast predictions as accurate as offline calibrations. In this work, we introduce several methodological improvements that enhance both accuracy and the ability to adapt to new data. These include changes to the input features, better offline calibration and trainable normalizations. Furthermore, by combining beam-time and cosmic-ray datasets, we demonstrate that the learned dependencies can be transferred between very different data-taking scenarios. This enables the network not only to provide real-time calibration predictions, but also to infer optimal high-voltage settings, thus establishing a practical framework for a real-time detector control during data acquisition process.

Paper Structure

This paper contains 3 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Results
  3. Conclusion and Outlook

Figures (1)

  • Figure 1: Average Time-over-Threshold (ToT) as a function of high voltage for one MDC chamber. Shown are offline calibration results from cosmic data (black points), network predictions after fine-tuning on cosmic data (red circles), and beam-time data with artificially varied HV values (blue squares). The agreement between tests demonstrates that HV dependencies can be transferred between datasets.