Tianhao Qie

Dr. Tianhao Qie

department of ee, City University of Hong Kong, Hong Kong, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 June 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Tianhao QieTianhao Qie
Tianhao Qie
XZXinan Zhang
Xinan Zhang
CXchaoqun xiang
chaoqun xiang
YYYANG YU
YANG YU
Herbert Ho-Ching IuHerbert Ho-Ching Iu
Herbert Ho-Ching Iu
TFTyrone Fernando
Tyrone Fernando
This article proposes a novel online integral reinforcement learning (IRL) based data-driven control algorithm for interleaved dc/dc boost converter. The proposed algorithm is independent of system model due to the usage of a three-layer neural network (NN). Furthermore, its controller gains are autonomously adjusted online through the value function based NN weights updating mechanism, which simplifies the controller gain tuning process. Compared to the conventional model-dependent control approaches, it provides superior control performance. Additionally, the proposed method contributes to significantly reduce the computational burden of classical IRL algorithm by removing the disturbance updating process. Experimental results are presented to verify the efficacy of the proposed algorithm.

12 May 2022 in IEEE Journal of Emerging and Selected Topics in Power Electronics
Verified
Journal Article
Closed access
CXchaoqun xiang
chaoqun xiang
XZXinan Zhang
Xinan Zhang
Tianhao QieTianhao Qie
Tianhao Qie
TCTat Kei Chau
Tat Kei Chau
JYJian Ye
Jian Ye
TFTyrone Fernando
Tyrone Fernando
This paper proposes a novel deep deterministic policy gradient (DDPG) assisted integral reinforcement learning (IRL) based control algorithm for the three-phase DC/AC inverter feeding a resistive-inductive (RL) load. The proposed controller autonomously updates its control gains online without the need to know the system model. Excellent steady-state and dynamic system responses are achieved by the proposed control algorithm with reasonably low computational complexity. Moreover, the important initial stabilizing control problem is solved through offline training that uses the DDPG technique. Details of the DDPG based training procedures are presented. Experimental results are presented to verify the efficacy of the proposed IRL based control method.

23 November 2022 in IEEE Transactions on Sustainable Energy
Verified
Journal Article
Closed access
YLYulin Liu
Yulin Liu
Tianhao QieTianhao Qie
Tianhao Qie
YYYANG YU
YANG YU
YWYuxuan Wang
Yuxuan Wang
TCTat Kei Chau
Tat Kei Chau
TFTyrone Fernando
Tyrone Fernando
This paper proposes a new online integral reinforcement learning (IRL)-based control algorithm for the solid oxide fuel cell (SOFC) to overcome the long-lasting problems of model dependency and sensitivity to offline training dataset in the existing SOFC control approaches. The proposed method automatically updates the optimal control gains through the online neural network training. Unlike the other online learning-based control methods that rely on the assumption of initial stabilizing control or trial-and-error based initial control policy search, the proposed method employs the offline twin delayed deep deterministic policy gradient (TD3) algorithm to systematically determine the initial stabilizing control policy. Compared to the conventional IRL-based control, the proposed method contributes to greatly reduce the computational burden without compromising the control performance. The excellent performance of the proposed method is verified by hardware-in-the-loop experiments.

18 March 2024 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Tianhao QieTianhao Qie
Tianhao Qie
XZXinan Zhang
Xinan Zhang
WJWentao Jiang
Wentao Jiang
JYJian Ye
Jian Ye
Herbert Ho-Ching IuHerbert Ho-Ching Iu
Herbert Ho-Ching Iu
TFTyrone Fernando
Tyrone Fernando
The interleaved dc/dc boost converter (IBC) has been widely used to interface the solar photovoltaic panels and fuel cells to dc microgrids. With the penetration of self-regulated power electronic loads, which tend to consume constant power, the stability of dc microgrids is severely challenged. To guarantee the large signal stability of IBC fed dc microgrids with constant power loads, this article proposes a novel data-driven linear quadratic regulator. It provides model-free online control optimization with very low computational burden. To verify the effectiveness of the proposed method, experiments are carried out using the low cost Texas Instrument C2000 series digital signal processor.

27 February 2023 in Journal of Cleaner Production
Verified
Journal Article
Open access
SSShaokun Song
Shaokun Song
MGManeesha P. Ginige
Maneesha P. Ginige
Ka Yu ChengKa Yu Cheng
Ka Yu Cheng
Tianhao QieTianhao Qie
Tianhao Qie
CPChristopher S. Peacock
Christopher S. Peacock
Anna KaksonenAnna Kaksonen
Anna Kaksonen

16 February 2024 in IEEE Transactions on Power Electronics
Verified
Journal Article
Closed access
Tianhao QieTianhao Qie
Tianhao Qie
XZXinan Zhang
Xinan Zhang
Jian ZhuJian Zhu
Jian Zhu
MVMahinda Vilathgamuwa
Mahinda Vilathgamuwa
Herbert Ho-Ching IuHerbert Ho-Ching Iu
Herbert Ho-Ching Iu
TFTyrone Fernando
Tyrone Fernando
This paper proposes a novel data-driven linear quadratic regulator for interleaved boost DC/DC converter. The proposed method utilizes policy iteration and a simple fixed weight recurrent neuron network to simultaneously achieve model independent control and autonomous online optimal control gain update. Compared to the existing model-based control approaches, the proposed method is totally model-free. Additionally, the proposed method updates the neural network without any offline pre-training, which is a key advantage for industrial applications. The experimental results, which are obtained using the Texas Instrument C2000 series digital signal processor, are presented to demonstrate the effectiveness of the proposed method.