A5068673597- Risk and Safety Analysis
- Fault Detection and Control Systems
- Bayesian Modeling and Causal Inference
- Multi-Criteria Decision Making
- Reservoir Engineering and Simulation Methods
- AI-based Problem Solving and Planning
- Software Reliability and Analysis Research
- Advanced Data Processing Techniques
Yutong (China)
2023
Tsinghua University
2021
Beihang University
2017
The dynamic uncertain causality graph (DUCG) is a newly presented framework for representation and probabilistic reasoning. It has been successfully applied to online fault diagnoses of large, complex industrial systems, decease diagnoses. This paper extends the DUCG model more cases than what could be previously modeled, e.g., case in which statistical data are different groups with or without overlap, some domain knowledge actions (new variables causalities) introduced. In other words,...
Intelligent diagnosis system are applied to fault in spacecraft. Dynamic Uncertain Causality Graph (DUCG) is a new probability graphic model with many advantages. In the knowledge expression of spacecraft diagnosis, feedback among variables frequently encountered, which may cause directed cyclic graphs (DCGs). Probabilistic graphical models (PGMs) such as bayesian network (BN) have been widely uncertain causality representation and probabilistic reasoning, but BN does not allow DCGs. this...
Intelligent diagnosis system is applied to fault in spacecraft. Dynamic Uncertain Causality Graph (DUCG) a new probability graphic model with many advantages. In this paper, DUGG spacecraft: introducing conditional functional events into ordinary DUCG deal spacecraft multi-conditions. Now, has been tested 16 typical faults 100% accuracy.
Shale-gas sweet-spot evaluation as a critical part of shale-gas exploration and development has always been the focus experts scholars in unconventional oil gas field. After comprehensively considering geological, engineering, economic factors affecting sweet spots, dynamic uncertainty causality graph (DUCG) is applied for first time to evaluation. A graphical modeling scheme presented reduce difficulty model construction. The based on expert knowledge does not depend data. Through rigorous...
In order to solve the problems of intelligent fault diagnosis spacecraft, this paper builds a diagnostic model based on Dynamic Uncertain Causality Graph (DUCG). This solves issues with data-driven and model-based methods, such as poor interpretability, high data dependence, low correctness. The DUCG methodology relies expertise domain experts demonstrate uncertainties between spacecraft telemetry parameters possible faults in graphic way. Notably, exhibits accuracy even absence existing...