Zhe Liu

Zhe Liu

Auto-generated profile, based on publicly available information

Zhe Liu

School of Mechanical Engineering and Vehicles, Beijing Institute of Technology, Beijing, China

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
1 January 2022 in Engineered Science
Verified
Journal Article
Open access
PDF file
Xiaolin WangXiaolin Wang
Xiaolin Wang
ZLZhe Liu
Zhe Liu
HWHui Wang
Hui Wang
CZChangChun Zeng
ChangChun Zeng
Direct 3D printing of piezoelectret with the designed structure for accurate control of morphology and piezoelectric sensor sensitivity and sensing range.

1 April 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
CGCheng Gong
Cheng Gong
LCLu Chao
Lu Chao
ZLZirui Li
Zirui Li
ZLZhe Liu
Zhe Liu
JGJianwei Gong
Jianwei Gong
XCXuemei Chen
Xuemei Chen
Model-free learning-based control methods have recently shown significant advantages over traditional control methods in avoiding complex vehicle characteristic estimation and parameter tuning. As a primary policy learning method, imitation learning (IL) is capable of learning control policies directly from expert demonstrations. However, the performance of IL policies is highly dependent on the data sufficiency and quality of the demonstrations. To alleviate the above problems of IL-based policies, a lifelong policy learning (LLPL) framework is proposed in this paper, which extends the IL scheme with lifelong learning (LLL). First, a novel IL-based model-free control policy learning method for path tracking is introduced. Even with imperfect demonstration, the optimal control policy can be learned directly from historical driving data. Second, by using the LLL method, the pre-trained IL policy can be safely updated and fine-tuned with incremental execution knowledge. Third, a knowledge evaluation method for policy learning is introduced to avoid learning redundant or inferior knowledge, thus ensuring the performance improvement of online policy learning. Experiments are conducted using a high-fidelity vehicle dynamic model in various scenarios to evaluate the performance of the proposed method. The results show that the proposed LLPL framework can continuously improve the policy performance with collected incremental driving data, and achieves the best accuracy and control smoothness compared to other baseline methods after evolving on a 7 km curved road. Through learning and evaluation with noisy real-life data collected in an off-road environment, the proposed LLPL framework also demonstrates its applicability in learning and evolving in real-life scenarios.

27 June 2025 in Control Engineering Practice
Verified
Journal Article
Closed access
ZLZhe Liu
Zhe Liu
CGCheng Gong
Cheng Gong
ZJZhiyang Ju
Zhiyang Ju
Zheng ZangZheng Zang
Zheng Zang
WWWenshuo Wang
Wenshuo Wang
JGJianwei Gong
Jianwei Gong

15 September 2023
Verified
Conference Paper
Closed access
WHWenguang Hu
Wenguang Hu
YZYanli Zeng
Yanli Zeng
GJGe Jiang
Ge Jiang
ZLZhe Liu
Zhe Liu
XGXiaoting Guo
Xiaoting Guo
YXYizhong Xu
Yizhong Xu
This paper introduces a new planar matrix pulsed eddy current sensor for non-destructive testing. The sensor consists of multiple independent excitation poles and an array of induction coils. Each induction coil can be regarded as an independent pixel unit. The simulation model of matrix pulsed eddy current sensor is established by finite element simulation software, and the characteristics of the sensor are analyzed. The excitation pole is driven by the pulse generator, and the voltage pulse signal of a certain induction coil in the array is selected by the multiplexer. Then the FPGA is used to perform fast Fourier transform on the collected pulse signal to obtain the frequency domain signal, and the processed signal is amplified and collected. In the experiment, the detected data corresponds to the pixel point to form the defect image of the detected object.

15 September 2023
Verified
Conference Paper
Closed access
LZLusha Zhou
Lusha Zhou
ZWZiqian Wu
Ziqian Wu
ZLZhe Liu
Zhe Liu
HSHaiiun She
Haiiun She
At present, the electromagnetic compatibility test of direct tire monitoring system is usually carried out by means of pressure tank activation sensor. The disadvantage of this method is that it can only provide a constant pressure value, which is inconvenient to observe the phenomenon, and it is difficult to simulate the real car environment. In this paper, a set of EMC test adjustable auxiliary device for direct tire pressure monitoring system is designed to simulate the tire pressure environment in the process of real vehicle driving. Built in an existing laboratory environment, the device can provide varying air pressure from 0 to 6bar, providing more accurate test conditions for tire pressure tests that are closer to the actual working environment.

28 March 2025
Verified
Conference Paper
Open access
SWShaobin Wu
Shaobin Wu
HJHaojian Jiang
Haojian Jiang
YHYu Huang
Yu Huang
YCYunfeng Chu
Yunfeng Chu
GXGuangming Xiong
Guangming Xiong
WXWei Xiang
Wei Xiang