Digital Twin User Guide for Tacoma Public Utilities

Technical Report · Sun Mar 01 00:00:00 EST 2026

DOI:https://doi.org/10.2172/3009413· OSTI ID:3009413

Subedi, Sunil ^[1]; Wang, Hong ^[1]; Yin, Zhun ^[2]; Warnick, Scott ^[3]

---

1. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
2. New York Univ. (NYU), NY (United States)
3. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

This user manual offers a comprehensive guide for developing a Digital twin (DT) model of a Francis Turbine at the Tacoma Power plant using neural networks. The growing integration of variable renewable energy has necessitated that hydropower systems operate with greater adaptability. This shift in operational demand emphasizes the nonlinear behavior of the Francis Turbine, making traditional modeling difficult. To overcome this, the manual details a data-driven modeling and learning algorithm centered on structured neural networks. This approach is designed to accurately forecast critical operational parameters, including turbine shaft speed, penstock pressure, and generator power output, by leveraging real-time inputs like generator power control setpoint, field current, and field voltage. The neural network’s effectiveness is validated using authentic operational data from a Francis Turbine at the Tacoma Power (TPU) plant. The outcome is a robust modeling approach that captures the system’s complex dynamics, offering insights that enhance the operational efficiency and decision-making for the Tacoma Power plant.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Office of Electricity (OE)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 3009413
• Report Number(s): ORNL/TM--2025/4352
• Country of Publication: United States
• Language: English

Related Subjects

13 HYDRO ENERGY
97 MATHEMATICS AND COMPUTING