Research Interests

1. Machine learning based power management of PHEV
2. Multiscale/multiphysics modeling and optimal design of Lithium ion battery
3. Machine learning based battery internal status estimation, failure prognostics and charging/discharging management
4. Powertrain hybridization and supervisory control development
5. Machine learning based smart home energy management system
6. Optimal design and health-conscious fast charging technology

Machine learning based power management of PHEV

Motivations :  the existing power management systems for PHEVs are developed base don pre-sampled driving cycles, while the real-world driving cycles can vary greatly depending on the traffic conditions, and therefore be much different comparing to the pre-sampled ones.

Method:  To reduce the energy consumption in real-world driving cycles, the real-time traffic data is fed into an machine learning algorithm to extract the optimal control policy given the real-time traffic conditions.

Results:   a 7.12% reduction in fuel consumption is achieved


Multiphysics modeling, optimal design and health conscious fast charging

  1. Multiphysics modeling of battery degradation

 

Motivation: How do Li-ion batteries degrade over long-term cycling (degradation analysis)

Method: Physics based modeling

 

2. Battery Life Optimization

 

Motivations: How should we design Li-ion batteries to achieve longer cycle life (optimal design)

Method: Physics based modeling, optimal design, and advanced control

Results: Battery capacity fade is reduced significantly from 60% to 20% after design optimization; optimal design parameters are derived.

 

3. Health conscious charging

Motivations: How should we control Li-ion batteries to achieve longer cycle life (optimal control)

Method: Physics based modeling, optimal design, and advanced control

 


Machine learning based battery internal status estimation, failure prognostics and charging/discharging management

Motivations :  advanced battery management systems must take into account the internal status of lithium ion batteries in order to ensure safe operation and to prolong the battery useful life.

Method:  Neural network based internal status estimation, such as, temperature, stress, lithium plating, SOC, etc… And also prediction (prognostics) of thermal runaway, or severe side reactions during operation.

Results:  high prediction accuracy of internal status based on machine learning method. High accurate prediction of severe side reactions.

 


Powertrain hybridization and supervisory control development

 

 

Motivations: Lithium ion batteries have high energy density, but low power density. While the hydraulic accumulator has high power density, but lower energy density. They can work together to achieve synergy. By hydraulic hybridization, all-electric range can be improved, battery life can be extended, and electric motor efficiency can be improved.

Method: Hydraulic hybridization of pure electric pickup. Hardware design, high fidelity modeling, and optimal power management policy development using dynamic programming.

Results:

1. extended the all-electric range by 21.8 miles or 64.8%

2. battery: improved usable capacity; extended life; lowered peak current by 15%;

3. Improved the operating efficiency of electric motor.

Zap.wmv