Operations, maintenance, safety and security
Operations, maintenance, safety and security
The basis for the program area on operation, maintenance, safety & security is the opportunities and challenges we see in light of the digitalization & automation taking place these days. Within the field of operation and maintenance this includes predictive maintenance/real-time monitoring of asset condition, with application of big data analytics and artificial intelligence/machine learning as well as “physical” achievements like use of drones and other autonomous tools. Another aspect covered in this program area is cyber security and safety of instrumented systems – areas that are even more important than before...read more
Program area team
- Jørn Vatn, Prof. Maintenance, Risk & Optimization
- Mary Ann Lundteigen, Prof. Safety of Automation Systems
- Per Schjølberg, Prof. Maintenance Management and Industry 4.0
- Shen Yin, Prof. Fault diagnosis and fault-tolerance
- Pierluigi Salvi Rossi, Prof. Data fusion, sensor networks, communication and more
- Stephen Wolthusen, Prof. Cyber Security
- Sokratis Katsikas, Prof. Cyber Security
- Bálint Zoltán Téglásy, PhD candidate
- Tom Ivar Pedersen, PhD candidate
- Abu Md Ariful Islam, PhD candidate
- Ewa Maria Laskowska, PhD candidate
- Endre Sølvsberg, PhD candidate
- Markus Bratland Kvammen, PhD canidate
- Gianluca Tabella, PhD candidate
Current projects
Industry 4.0 and Smart Predictive Maintenance

PhD Candidate Tom Ivar Pedersen
Main Supervisor Per Schjølberg
Sponsor: Lundin Energy Norway AS
Recent developments in sensor technology combined with improvements in systems for collecting, storing and analyzing large amounts of data, often associated with the term Industry 4.0, are expected to bring substantial changes to how maintenance and asset management will be conducted in the upcoming years. One example of this is predictive maintenance which has the potential to reduce maintenance costs by allowing maintenance organizations to focus resources on the right equipment at the right time, and improve safety and availability by reducing the level of unplanned corrective maintenance. Outcome of the project: Methods and models that explore how digital solutions can be used to improve the economic value generated from a production asset.
Project result: Predictive maintenance on centrifugal pumps
A study case predicting remaining useful life using head degradation data which allows to plan timely maintenance operations considering uncertainty
Maintenance optimization in remote operations
PhD Candidate Ariful Islam Abu
Main Supervisor Jørn Vatn
Sponsor: Aker BP
The project focuses on the optimization of the maintenance activities in the context of unmanned/minimum manned platforms in remote offshore operations, where physical maintenance opportunities are limited. The main objective of the research is to investigate and develop optimal maintenance strategies for critical assets to efficiently utilize such limited opportunities. The focus of the research is to utilize available condition monitoring data of selected assets to develop failure prediction models and maintenance decision models to support maintenance in remote operations.
Project result: Maintenance decision support in remote operations
A framework using predictive maintenance and grouping optimization to find best inspection and maintenance dates
Predictive maintenance
PhD Candidate Ewa Laskowska
Main Supervisor Jørn Vatn
Sponsor: Lundin Energy Norway AS
Modelling of degradation of safety valves (ESVs). The methodology is based on stochastic processes such as the Markov process or Wiener process. The idea is to enable prediction of Remaining Useful Lifetime (RUL) distribution, given the current degradation level of valve is known. Next, the obtained RUL can be used for optimization of inspection regimes. Degradation models assuming constant inspection intervals have been developed. The aim is to extend the modelling framework to treat the situation where inspection intervals depend on the current condition and the predicted RUL. Outcome of the project: Stochastic degradation models enabling RUL prediction and real-time optimization models taking condition and operational
constraints into account.
Project result: Optimization of testing strategy for Emergency Shutdown Valves
A study case where condition-based testing allows to reduce the number of tests and repairs without increasing the probability of failure on demand
Safety and security in design and operation of ICS systems

PhD Candidate Bálint Zoltán Téglásy
Main Supervisor Mary Ann Lundteigen
Sponsor: NTNU
New networking applications are now to be implemented in the oil and gas industry. These digital technologies provide unique opportunities and pose unique threats to critical infrastructures. The functional safety regulation stemming from the industrial sphere and the cyber security policies enforced in enterprise-grade information technologies will be interfacing through electronic communication. Clarifying the design, verification and operation procedures for future control systems will allow companies to retain sufficient control of their facilities while taking advantage of IoT and Industry 4.0 functionalities. Outcome of the project: Design philosophies and architectures that minimize the threats while retaining the opportunities of networked control systems. This will allow for long-term accident-free, economically viable and environment- friendly operation.
Project result: The interconnection of information technology (IT) and operational technology (OT) poses a security threat through logical access, also called a cyber threat, for the energy industry. As the digital space is becoming accessible – and often unavoidable - to everyone, Ph.D. candidate Bálint Z. Téglásy is providing standardizable security solutions for challenging operational circumstances.
Extending lifetime of Norwegian oil installations using predictive maintenance through condition and remaining useful life estimation.
PhD Candidate Endre Sølvsberg
Main Supervisor Per Schjølberg
Sponsor: OKEA
The goal of the project with OKEA is to extend the lifetime of existing, ageing oil platforms using classical statistical and mathematical methods for estimating condition and remaining useful life (RUL) of machines and processes. This allows for a predictive maintenance (PdM) approach, which will help optimize the maintenance strategy for the oil platforms and aid in extending their lifetime. A hybrid approach, using both classical and AI methods, has been proposed in the beginning of this project. This has caught the interest of standardization organizations and will most likely be part of a future standard.
Risk based maintenance
PhD Candidate Markus Bratland Kvammen
Main Supervisor Per Schjølberg
Sponsor: Equinor
Risk based maintenance is emerging as a key method for obtaining world class maintenance planning and execution. It integrates a reliability approach and a risk assessment strategy to obtain an optimum maintenance schedule for an asset. This type of maintenance is linked to an operational concept that determines the most economical way to distribute resources, so that the maintenance effort is optimized to minimize the risk and consequences of failures. Expected outcome of the project: Artificial Intelligence/smart algorithms and development and implementation of new digital technologies.
Subsea Leak Detection and Localization
PhD Candidate Gianluca Tabella
Main Supervisor Pierluigi Salvi Rossi
Sponsor: NTNU
The project consists of developing algorithms for detection and localization of subsea oil spill through sensor fusion and statistical signal processing techniques. In order to maximize the performances of such methodologies, the detection and localization problem is approached by taking advantage of reliability analysis performed on the Subsea Production System. Such information can be used as prior knowledge for improved results. The work aims also at integrating the real-time results of such algorithms into a Dynamic Risk Analysis, in order to create a cyclic exchange of information between the Leak Detection/Localization System and the other safety/monitoring/maintenance systems in place.