DC-4: Jingkang Liang

Contact

E-mail: jinlia@kt.dtu.dk
LinkedIn

Project

Statistical machine learning and big data analytics for online risk monitoring and fault diagnosis

Host organization

DTU

Supervisors

Prof. Gürkan Sin (Main, DTU); Prof. V. Venkatasubramanian (co-supervisor, COL); Dr. Claus Myllerup (co-supervisor, KAIROS)

Duration

36 months

Objectives

The overall objective is to investigate how quantitative methods can be utilized in a qualitative framework to provide online Quantitative Risk Assessments to operators for decision-making support. Furthermore, aiming to investigate how qualitative and quantitative evidence can be produced online from sensor signals in combination with a QRA, to guide operators’ decision-making in abnormal situations.

The DC will work on applying the results to a hydrogen liquefaction and processing facility as the industrial use case.

Expected results

  1. Online QRA for an operational plant or historical data from the very same plant,

  2. Identification and application of suitable quantitative methods for probabilistic estimation of individual risk per annum,

  3. Benchmarking of method(s) suitable for producing qualitative and quantitative evidence to reduce situational uncertainty about risk and severity,

  4. Development of a method for visualizing QRA results online for operators to aid with decision support.

Planned secondments

  1. KAIROS, M13, 3 months: Training on fault diagnosis and monitoring for process safety applications
  2. Risktec, M28, 2 months: Big data analytics validation on renewable hydrogen case study