Dissertation Defense – Hanlong Wan


Author: Hanlong Wan

Date/Time: 9/2/21 | 2:00PM-4:00PM

Location/Room: EGR4164B Martin Hall (CEEE’s conference room).

Advisory Committee:
Prof. Reinhard K. Radermacher, Chair
Prof. Peter Sunderland, Dean’s Representative
Research Prof. Yunho Hwang
Prof. Nikhil Chopra
Prof. Jelena Srebric
Prof. Bao Yang

Energy consumption of Heat Pump (HP) systems plays a significant role in the world residential building energy sector. The conventional HP system evaluation method focused on the energy efficiency during a given time scale (e.g., hourly, seasonally, or annually). Nevertheless, these evaluation methods or test metrics are unable to properly reflect the thermodynamic characteristics of the system (e.g., the start-up process). In addition, previous researchers typically conducted HP field tests within one year period. Only limited studies conducted the system performance over multiple years. Furthermore, the climate is changing faster than previously predicted beyond the irreversible and catastrophic tipping point. HP systems are the main contributor to global warming but also can be a part of the solution. A holistic evaluation of the HP system’s global warming impact during its life cycle needs to account for the direct refrigerant greenhouse gas (GHG) emissions, indirect fossil fuel GHG emissions and embodied equipment emissions. This dissertation leverages machine learning, deep learning, data digging, and Life Cycle Analysis (LCA) approaches to develop next generation HP system evaluation methodologies with three thrusts: 1) field test data analysis, 2) data-driven modeling, and 3) Enhanced Life Cycle Climate Performance (En-LCCP) analysis. This study found that first, time-average performance metrics can save time in extensive data calculation, while quasi-steady-state performance metrics can elucidate some details of the studied system. Second, deep-learning-based algorithms have higher accuracy than conventional modeling approaches and can be used to analyze the system’s dynamic performance. However, the complicated structure of the networks, numerous parameters needing to be optimized, and longer training time are the main drawbacks of these methods. Third, this dissertation improved current environmental impact evaluation method considering ambient conditions variation, local grid source structure, and next-generation low-GWP refrigerants, which led the results closer to reality and provided alternative methods for limited-data cases. Future work could be studying the uncertainty within the deep learning networks and a general process for modeling settings. People may develop a multi-objective optimization model for HP system design considering both the LCCP and cost.