ICALEPCS2019 - List of Authors (Van Trappen, P.)

Paper	Title	Page
MOPHA152	Use of Multi-Network Fieldbus for Integration of Low-Level Intelligent Controller Within Control Architecture of Fast Pulsed System at CERN	589
	N. Voumard, C. Boucly, M.P. Pimentel, L. Strobino, P. Van Trappen CERN, Geneva, Switzerland
	Fieldbuses and Industrial Ethernet networks are extensively used for the control of fast-pulsed magnets at CERN. With the ongoing trend to develop increasingly more complex low-level intelligent controllers near to the actuators and sensors, the flexibility to integrate these within different control architectures grows in importance. In order to reduce development efforts and keep the fieldbus choice open, a multi-network field-bus technology has been selected for the network interfacing part of the controllers. Such an approach has been successfully implemented for several projects such as the development of high voltage capacitor chargers/dischargers, the surveillance of floating solid-state switch and the monitoring of a power triggering system that, today, are interfaced either to PROFIBUS-DP or PROFINET networks. The integration of various fieldbus interfaces within the controller and the required embedded software/gateware to manage to network communication are presented. The gain in flexibility, modularity and openness obtained through this approach is also reviewed.
	Poster MOPHA152 [0.587 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA152
About •	paper received ※ 27 September 2019 paper accepted ※ 10 October 2019 issue date ※ 30 August 2020
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPHA153	SoC Technology for Embedded Control and Interlocking Within Fast Pulsed Systems at CERN	592
	P. Van Trappen, E. Carlier, M. Gauthier, N. Magnin, E.J. Oltedal, J. Schipper CERN, Geneva, Switzerland
	The control of pulsed systems at CERN requires often the use of fast digital electronics to perform tight timing control and fast protection of high-voltage pulsed generators. For the implementation of such functionalities, a FPGA is the perfect candidate for the digital logic, however with limited integration potential within the control system. The market push for integrated devices, so called System on a Chip (SoC) - a tightly coupled ARM processing system and specific programmable logic in a single device, has allowed a better integration of the various components required for the control of pulsed systems. This technology is used for the implementation of fast switch interlocking logic, integrated within the CERN control framework by using embedded Linux running a Snap7 server. It is also used for the implementation of a lower-tier communication bridge between a front-end computer and a high fan-out multiplexing programmable logic for timing and analogue low-level control. This paper presents these two projects where the SoC technology has been deployed and discusses possible further applications within distributed real-time control architecture for distributed pulsed systems.
	Poster MOPHA153 [0.828 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA153
About •	paper received ※ 30 September 2019 paper accepted ※ 10 October 2019 issue date ※ 30 August 2020
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WEMPR010	Anomaly Detection for CERN Beam Transfer Installations Using Machine Learning	1066
WEPHA155	use link to see paper's listing under its alternate paper code
	T. Dewitte, W. Meert, E. Van Wolputte Katholieke Universiteit Leuven, Leuven, Belgium P. Van Trappen CERN, Geneva, Switzerland
	Reliability, availability and maintainability determine whether or not a large-scale accelerator system can be operated in a sustainable, cost-effective manner. Beam transfer equipment (e.g. kicker magnets) has potentially significant impact on the global performance of a machine complex. Identifying root causes of malfunctions is currently tedious, and will become infeasible in future systems due to increasing complexity. Machine Learning could automate this process. For this purpose a collaboration between CERN and KU Leuven was established. We present an anomaly detection pipeline which includes preprocessing, detection, postprocessing and evaluation. Merging data of different, asynchronous sources is one of the main challenges. Currently, Gaussian Mixture Models and Isolation Forests are used as unsupervised detectors. To validate, we compare to manual e-logbook entries, which constitute a noisy ground truth. A grid search allows for hyper-parameter optimization across the entire pipeline. Lastly, we incorporate expert knowledge by means of semi-supervised clustering with COBRAS.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-WEMPR010
About •	paper received ※ 30 September 2019 paper accepted ※ 09 October 2019 issue date ※ 30 August 2020
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Use of Multi-Network Fieldbus for Integration of Low-Level Intelligent Controller Within Control Architecture of Fast Pulsed System at CERN

589

N. Voumard, C. Boucly, M.P. Pimentel, L. Strobino, P. Van Trappen
CERN, Geneva, Switzerland

Fieldbuses and Industrial Ethernet networks are extensively used for the control of fast-pulsed magnets at CERN. With the ongoing trend to develop increasingly more complex low-level intelligent controllers near to the actuators and sensors, the flexibility to integrate these within different control architectures grows in importance. In order to reduce development efforts and keep the fieldbus choice open, a multi-network field-bus technology has been selected for the network interfacing part of the controllers. Such an approach has been successfully implemented for several projects such as the development of high voltage capacitor chargers/dischargers, the surveillance of floating solid-state switch and the monitoring of a power triggering system that, today, are interfaced either to PROFIBUS-DP or PROFINET networks. The integration of various fieldbus interfaces within the controller and the required embedded software/gateware to manage to network communication are presented. The gain in flexibility, modularity and openness obtained through this approach is also reviewed.

Poster MOPHA152 [0.587 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA152

About •

paper received ※ 27 September 2019 paper accepted ※ 10 October 2019 issue date ※ 30 August 2020

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

MOPHA153

SoC Technology for Embedded Control and Interlocking Within Fast Pulsed Systems at CERN

592

P. Van Trappen, E. Carlier, M. Gauthier, N. Magnin, E.J. Oltedal, J. Schipper
CERN, Geneva, Switzerland

The control of pulsed systems at CERN requires often the use of fast digital electronics to perform tight timing control and fast protection of high-voltage pulsed generators. For the implementation of such functionalities, a FPGA is the perfect candidate for the digital logic, however with limited integration potential within the control system. The market push for integrated devices, so called System on a Chip (SoC) - a tightly coupled ARM processing system and specific programmable logic in a single device, has allowed a better integration of the various components required for the control of pulsed systems. This technology is used for the implementation of fast switch interlocking logic, integrated within the CERN control framework by using embedded Linux running a Snap7 server. It is also used for the implementation of a lower-tier communication bridge between a front-end computer and a high fan-out multiplexing programmable logic for timing and analogue low-level control. This paper presents these two projects where the SoC technology has been deployed and discusses possible further applications within distributed real-time control architecture for distributed pulsed systems.

Poster MOPHA153 [0.828 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-MOPHA153

About •

paper received ※ 30 September 2019 paper accepted ※ 10 October 2019 issue date ※ 30 August 2020

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WEMPR010

Anomaly Detection for CERN Beam Transfer Installations Using Machine Learning

1066

WEPHA155

use link to see paper's listing under its alternate paper code

T. Dewitte, W. Meert, E. Van Wolputte
Katholieke Universiteit Leuven, Leuven, Belgium
P. Van Trappen
CERN, Geneva, Switzerland

Reliability, availability and maintainability determine whether or not a large-scale accelerator system can be operated in a sustainable, cost-effective manner. Beam transfer equipment (e.g. kicker magnets) has potentially significant impact on the global performance of a machine complex. Identifying root causes of malfunctions is currently tedious, and will become infeasible in future systems due to increasing complexity. Machine Learning could automate this process. For this purpose a collaboration between CERN and KU Leuven was established. We present an anomaly detection pipeline which includes preprocessing, detection, postprocessing and evaluation. Merging data of different, asynchronous sources is one of the main challenges. Currently, Gaussian Mixture Models and Isolation Forests are used as unsupervised detectors. To validate, we compare to manual e-logbook entries, which constitute a noisy ground truth. A grid search allows for hyper-parameter optimization across the entire pipeline. Lastly, we incorporate expert knowledge by means of semi-supervised clustering with COBRAS.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2019-WEMPR010

About •

paper received ※ 30 September 2019 paper accepted ※ 09 October 2019 issue date ※ 30 August 2020

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)