Gaussian Mixture Model-Based Ensemble Kalman Filter for Machine Parameter Calibration

Journal Article · Sat Sep 01 00:00:00 EDT 2018 · IEEE Transactions on Energy Conversion

DOI:https://doi.org/10.1109/TEC.2018.2849856· OSTI ID:1511578

Fan, Rui ^[1]; Huang, Renke ^[1]; Diao, Ruisheng ^[2]

---

1. BATTELLE (PACIFIC NW LAB)
2. Global Energy Interconnection Research Institute North America

This letter proposes a novel Gaussian mixture model-based ensemble Kalman filter (GMM-EnKF) approach to the accurate calibration of the parameters of machine dynamic models. This approach aims to overcome some practical challenges of machine parameter calibration. Results show the proposed approach can provide high-accuracy calibrated parameters even when the machine operates under unbalanced network conditions and the measurement noises are non-Gaussian.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1511578
• Report Number(s): PNNL-SA-132149
• Journal Information: IEEE Transactions on Energy Conversion, Vol. 33, Issue 3
• Country of Publication: United States
• Language: English