ICALEPCS2017 - List of Authors (Bradu, B.)

Paper	Title	Page
MODPL02	Virtual Control Commissioning for a Large Critical Ventilation System: The CMS Cavern Use Case	92
	W. Booth, E. Blanco Viñuela, B. Bradu, S. Sourisseau CERN, Geneva, Switzerland
	The current cavern ventilation control system of the CMS experiment at CERN is based on components which are already obsolete: the SCADA system, or close to the end of life: the PLCs. The control system is going to be upgraded during the CERN Long Shutdown 2 (2019-2020) and will be based on the CERN industrial control standard: UNICOS employing WinCC OA as SCADA and Schneider PLCs. Due to the critical nature of the CMS ventilation installation and the short allowed downtime, the approach was to design an environment based on the virtual commissioning of the new control. This solution uses a first principles model of the ventilation system to simulate the real process. The model was developed with the modelling and simulation software EcosimPro. In addition, the current control application of the cavern ventilation will also be re-engineered as it is not completely satisfactory in some transients where many sequences are performed manually and some pressure fluctuations observed could potentially cause issues to the CMS detector. The plant model will also be used to validate new regulation schemes and transient sequences offline in order to ensure a smooth operation in production.
	Talk as video stream: https://youtu.be/NVzClA1dSxc
	Slides MODPL02 [3.318 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-MODPL02
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUCPA04	Model Learning Algorithms for Anomaly Detection in CERN Control Systems	265
	F.M. Tilaro, B. Bradu, M. Gonzalez-Berges, F. Varela CERN, Geneva, Switzerland M. Roshchin Siemens AG, Corporate Technology, München, Germany
	At CERN there are over 600 different industrial control systems with millions of deployed sensors and actuators and their monitoring represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge while the other two mine historical data to create a simple model of the system, which is then used to detect anomalies. The methods presented can be categorized as dynamic unsupervised anomaly detection; "dynamic" since the behaviour of the system is changing in time, "unsupervised" because they predict faults without reference to prior events. Consistent deviations from the historical evolution can be seen as warning signs of a possible future anomaly that system experts or operators need to check. The paper also presents some results, obtained from the analysis of the LHC Cryogenic system. Finally the paper briefly describes the deployment of Spark and Hadoop into the CERN environment to deal with huge datasets and to spread the computational load of the analysis across multiple nodes.
	Slides TUCPA04 [1.965 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA04
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

WEAPL02	Automatic PID Performance Monitoring Applied to LHC Cryogenics	1017
	B. Bradu, E. Blanco Viñuela, R. Marti, F.M. Tilaro CERN, Geneva, Switzerland
	At CERN, the LHC (Large Hadron Collider) cryogenic system employs about 4900 PID (Proportional Integral Derivative) regulation loops distributed over the 27 km of the accelerator. Tuning all these regulation loops is a complex task and the systematic monitoring of them should be done in an automated way to be sure that the overall plant performance is improved by identifying the poorest performing PID controllers. It is nearly impossible to check the performance of a regulation loop with a classical threshold technique as the controlled variables could evolve in large operation ranges and the amount of data cannot be manually checked daily. This paper presents the adaptation and the application of an existing regulation indicator performance algorithm on the LHC cryogenic system and the different results obtained in the past year of operation. This technique is generic for any PID feedback control loop, it does not use any process model and needs only a few tuning parameters. The publication also describes the data analytics architecture and the different tools deployed on the CERN control infrastructure to implement the indicator performance algorithm.
	Talk as video stream: https://youtu.be/7dCglp2Pn_c
	Slides WEAPL02 [1.651 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-WEAPL02
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA016	The UNICOS-CPC Vacuum Controls Package	1370
	S. Blanchard, M. Bes, E. Blanco Viñuela, W. Booth, B. Bradu, R. Ferreira, P. Gomes, A. Gutierrez, A.P. Rocha, T.H. van Winden CERN, Geneva, Switzerland L. Kopylov IHEP, Moscow Region, Russia
	The vacuum control of the Large Hadron Collider and its injectors is based on PLC and SCADA off-the-shelf components. Since late '90s, CERN's vacuum group has developed a dedicated control framework to drive, monitor and log the more than 10 000 vacuum instruments. Also, in 1998, CERN's industrial controls group developed the UNICOS framework (UNified Industrial Control System), becoming a de facto standard of industrial control systems and gradually deployed in different domains at CERN (e.g. Cryogenics, HVAC…). After an initial prototype applying the UNICOS-CPC (Continuous Process Control) framework to the controls of some vacuum installations, both teams have been working on the development of vacuum-specific objects and their integration, together with new features, into the UNICOS framework. Such convergence will allow this generic framework to better fit the vacuum systems, while offering the advantages of using a widespread and well-supported framework. This paper reports on the experience acquired in the development and deployment of vacuum specific objects in running installations, as a prototype for the vacuum controls convergence with UNICOS.
	Poster THPHA016 [1.062 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA016
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA030	Online Analysis for Anticipated Failure Diagnostics of the CERN Cryogenic Systems	1412
	Ph. Gayet, E. Blanco Viñuela, B. Bradu, R. Cirillo CERN, Geneva, Switzerland
	The cryogenic system is one of the most critical component of the CERN Large Hadron Collider (LHC) and its associated experiments ATLAS and CMS. In the past years, the cryogenic team has improved the maintenance plans, the operation procedures and achieved a very high reliability. However, as the recovery time after failure remains the major issue for the cryogenic availability new developments must take place. A new online diagnostic tool is developed to identify and anticipate failures of cryogenics field equipment, based on the acquired knowledge on dynamic simulation for the cryogenic equipment and on previous data analytic studies. After having identified the most critical components, we will develop their associated models together with the signature of their failure modes. The proposed tools will detect deviation between the actual systems and their model or identify preliminary failure signatures. This information will allow the operation team to take early mitigating actions before the failure occurrence.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA030
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

Virtual Control Commissioning for a Large Critical Ventilation System: The CMS Cavern Use Case

92

W. Booth, E. Blanco Viñuela, B. Bradu, S. Sourisseau
CERN, Geneva, Switzerland

The current cavern ventilation control system of the CMS experiment at CERN is based on components which are already obsolete: the SCADA system, or close to the end of life: the PLCs. The control system is going to be upgraded during the CERN Long Shutdown 2 (2019-2020) and will be based on the CERN industrial control standard: UNICOS employing WinCC OA as SCADA and Schneider PLCs. Due to the critical nature of the CMS ventilation installation and the short allowed downtime, the approach was to design an environment based on the virtual commissioning of the new control. This solution uses a first principles model of the ventilation system to simulate the real process. The model was developed with the modelling and simulation software EcosimPro. In addition, the current control application of the cavern ventilation will also be re-engineered as it is not completely satisfactory in some transients where many sequences are performed manually and some pressure fluctuations observed could potentially cause issues to the CMS detector. The plant model will also be used to validate new regulation schemes and transient sequences offline in order to ensure a smooth operation in production.

Talk as video stream: https://youtu.be/NVzClA1dSxc

Slides MODPL02 [3.318 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-MODPL02

Export •

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

TUCPA04

Model Learning Algorithms for Anomaly Detection in CERN Control Systems

265

F.M. Tilaro, B. Bradu, M. Gonzalez-Berges, F. Varela
CERN, Geneva, Switzerland
M. Roshchin
Siemens AG, Corporate Technology, München, Germany

At CERN there are over 600 different industrial control systems with millions of deployed sensors and actuators and their monitoring represents a challenging and complex task. This paper describes three different mathematical approaches that have been designed and developed to detect anomalies in CERN control systems. Specifically, one of these algorithms is purely based on expert knowledge while the other two mine historical data to create a simple model of the system, which is then used to detect anomalies. The methods presented can be categorized as dynamic unsupervised anomaly detection; "dynamic" since the behaviour of the system is changing in time, "unsupervised" because they predict faults without reference to prior events. Consistent deviations from the historical evolution can be seen as warning signs of a possible future anomaly that system experts or operators need to check. The paper also presents some results, obtained from the analysis of the LHC Cryogenic system. Finally the paper briefly describes the deployment of Spark and Hadoop into the CERN environment to deal with huge datasets and to spread the computational load of the analysis across multiple nodes.

Slides TUCPA04 [1.965 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA04

Export •

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

WEAPL02

Automatic PID Performance Monitoring Applied to LHC Cryogenics

1017

B. Bradu, E. Blanco Viñuela, R. Marti, F.M. Tilaro
CERN, Geneva, Switzerland

At CERN, the LHC (Large Hadron Collider) cryogenic system employs about 4900 PID (Proportional Integral Derivative) regulation loops distributed over the 27 km of the accelerator. Tuning all these regulation loops is a complex task and the systematic monitoring of them should be done in an automated way to be sure that the overall plant performance is improved by identifying the poorest performing PID controllers. It is nearly impossible to check the performance of a regulation loop with a classical threshold technique as the controlled variables could evolve in large operation ranges and the amount of data cannot be manually checked daily. This paper presents the adaptation and the application of an existing regulation indicator performance algorithm on the LHC cryogenic system and the different results obtained in the past year of operation. This technique is generic for any PID feedback control loop, it does not use any process model and needs only a few tuning parameters. The publication also describes the data analytics architecture and the different tools deployed on the CERN control infrastructure to implement the indicator performance algorithm.

Talk as video stream: https://youtu.be/7dCglp2Pn_c

Slides WEAPL02 [1.651 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-WEAPL02

Export •

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

THPHA016

The UNICOS-CPC Vacuum Controls Package

1370

S. Blanchard, M. Bes, E. Blanco Viñuela, W. Booth, B. Bradu, R. Ferreira, P. Gomes, A. Gutierrez, A.P. Rocha, T.H. van Winden
CERN, Geneva, Switzerland
L. Kopylov
IHEP, Moscow Region, Russia

The vacuum control of the Large Hadron Collider and its injectors is based on PLC and SCADA off-the-shelf components. Since late '90s, CERN's vacuum group has developed a dedicated control framework to drive, monitor and log the more than 10 000 vacuum instruments. Also, in 1998, CERN's industrial controls group developed the UNICOS framework (UNified Industrial Control System), becoming a de facto standard of industrial control systems and gradually deployed in different domains at CERN (e.g. Cryogenics, HVAC…). After an initial prototype applying the UNICOS-CPC (Continuous Process Control) framework to the controls of some vacuum installations, both teams have been working on the development of vacuum-specific objects and their integration, together with new features, into the UNICOS framework. Such convergence will allow this generic framework to better fit the vacuum systems, while offering the advantages of using a widespread and well-supported framework. This paper reports on the experience acquired in the development and deployment of vacuum specific objects in running installations, as a prototype for the vacuum controls convergence with UNICOS.

Poster THPHA016 [1.062 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA016

Export •

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

THPHA030

Online Analysis for Anticipated Failure Diagnostics of the CERN Cryogenic Systems

1412

Ph. Gayet, E. Blanco Viñuela, B. Bradu, R. Cirillo
CERN, Geneva, Switzerland

The cryogenic system is one of the most critical component of the CERN Large Hadron Collider (LHC) and its associated experiments ATLAS and CMS. In the past years, the cryogenic team has improved the maintenance plans, the operation procedures and achieved a very high reliability. However, as the recovery time after failure remains the major issue for the cryogenic availability new developments must take place. A new online diagnostic tool is developed to identify and anticipate failures of cryogenics field equipment, based on the acquired knowledge on dynamic simulation for the cryogenic equipment and on previous data analytic studies. After having identified the most critical components, we will develop their associated models together with the signature of their failure modes. The proposed tools will detect deviation between the actual systems and their model or identify preliminary failure signatures. This information will allow the operation team to take early mitigating actions before the failure occurrence.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA030

Export •

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