Next Generation of Quench Detection Systems for the High-Luminosity Upgrade of the LHC

Denz, Reiner; Steckert, Jens; Matteis, Ernesto De; Siemko, A.

doi:10.1109/tasc.2016.2628031

Cited by 19 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The technologies used for reaching high magnetic field also implicate the development of a new protection system, and in particular of a dedicated detection system [16]. In fact, this kind of coils suffers from not only a quench but also from the so-called flux jumps [17], affecting the nature of voltage waveforms describing the state of superconducting magnets.…”

Section: Superconducting Magnetsmentioning

confidence: 99%

“…In the ongoing magnet tests, the occurrences of these with the relate voltage spikes at a low current rate (I < 4 kA) could represent an issue for the classical detection parameters (voltage threshold of ±100 mV and the evaluation time of 10 ms). As a consequence, the strategy for the quench detection should be replaced with a new one based on dynamically set detection parameters [16].…”

Section: Superconducting Magnetsmentioning

confidence: 99%

“…During the runs, the current and voltages in the coils of the magnet were measured using a device named uQDS (universal Quench Protection System) (ver. 1.0) [16]. The measurement setup is shown in the Fig.…”

Section: Source Of Data For This Studymentioning

confidence: 99%

See 2 more Smart Citations

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Wielgosz

Mertik

Skoczeń

et al. 2018

Engineering Applications of Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

A B S T R A C TThis paper focuses on an examination of an applicability of Recurrent Neural Network models for detecting anomalous behavior of the CERN superconducting magnets. In order to conduct the experiments, the authors designed and implemented an adaptive signal quantization algorithm and a custom Gated Recurrent Unit-based detector and developed a method for the detector parameters selection.Three different datasets were used for testing the detector. Two artificially generated datasets were used to assess the raw performance of the system whereas the dataset intended for real-life experiments and model training was composed of the signals acquired from a new type of magnet, to be used during High-Luminosity Large Hadron Collider project. Several different setups of the developed anomaly detection system were evaluated and compared with state-of-the-art One Class Support Vector Machine (OC-SVM) reference model operating on the same data. The OC-SVM model was equipped with a rich set of feature extractors accounting for a range of the input signal properties.It was determined in the course of the experiments that the detector, along with its supporting design methodology, reaches F1 equal or very close to 1 for almost all test sets. Due to the profile of the data, the setup with the lowest maximum false anomaly length of the detector turned out to perform the best among all five tested configuration schemes of the detection system. The quantization parameters have the biggest impact on the overall performance of the detector with the best values of input/output grid equal to 16 and 8, respectively. The proposed solution of the detection significantly outperformed OC-SVM-based detector in most of the cases, with much more stable performance across all the datasets.

show abstract

Section: Superconducting Magnetsmentioning

confidence: 99%

Section: Superconducting Magnetsmentioning

confidence: 99%

See 1 more Smart Citation

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Wielgosz

Mertik

Skoczeń

et al. 2018

Engineering Applications of Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similar to the space-and ground-level applications, indirect energy deposition (i.e., from protons in space, neutrons in ground-level applications, and protons, neutrons, and pions in accelerators) is assumed to dominate the SER; therefore, the possible contribution from low-energy singly charged particle direct ionization needs to be evaluated. This evaluation is particularly relevant when considering the broad range of digital and mixed signal critical sensing and control accelerator applications [10], [11], requiring the extensive use of commercial off-the-shelf (COTS, e.g., SRAMs, microprocessors, and FPGAs) components exposed to radiation.…”

Section: Direct Ionization Impact On Acceleratormentioning

confidence: 99%

Direct Ionization Impact on Accelerator Mixed-Field Soft-Error Rate

Alía

Gilardoni

Infantino

et al. 2020

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

show abstract

“…The scientific applications of high-resolution ADCs are very diverse. They include the readout of sensors [5] [8] [15], intrinsically low-noise devices like superconducting interferometers (SQUIDs) [16], particle accelerator beam instrumentation [17], digital integrators for pickup coil-based magnetic measurements [18] and quench detection in superconducting magnets [19]. Such applications are often driven by highly specific requirements that cannot be summarized.…”

Section: Applicationsmentioning

confidence: 99%

Analog-to-digital conversion beyond 20 bits

Beev

2018

2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

View full text Add to dashboard Cite

Analog-to-digital converters with resolution exceeding 20 bits are widely available today. They exist in two forms-flexible laboratory instruments and monolithic integrated circuits. We present an overview of application fields for such digitizers, the hardware architectures that implement them, and their limitations. We review the state of the art by comparing the best-performing devices reported in scientific literature, as well as those available commercially. Our focus is particularly on integrated circuit solutions, and among our aims are the disambiguation of the multiple performance metrics in use, as well as the presentation of a clear perspective on basic performance tradeoffs. Finally, we provide a discussion on the future prospects for highresolution digitizing measurement systems.

show abstract

Next Generation of Quench Detection Systems for the High-Luminosity Upgrade of the LHC

Cited by 19 publications

References 13 publications

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization

Direct Ionization Impact on Accelerator Mixed-Field Soft-Error Rate

Analog-to-digital conversion beyond 20 bits

Contact Info

Product

Resources

About