Qianqian Zhang

Dr. Qianqian Zhang

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
12 November 2021 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
QZQianqian Zhang
Qianqian Zhang
YKYu Kang
Yu Kang
YZYunbo Zhao
Yunbo Zhao
PLPengfei Li
Pengfei Li
SYShiyi You
Shiyi You
Sequential decision-making (SDM) is a common type of decision-making problem with sequential and multistage characteristics. Among them, the learning and updating of policy are the main challenges in solving SDM problems. Unlike previous machine autonomy driven by artificial intelligence alone, we improve the control performance of SDM tasks by combining human intelligence and machine intelligence. Specifically, this article presents a paradigm of a human–machine traded control systems based on reinforcement learning methods to optimize the solution process of sequential decision problems. By designing the idea of autonomous boundary and credibility assessment, we enable humans and machines at the decision-making level of the systems to collaborate more effectively. And the arbitration in the human–machine traded control systems introduces the Bayesian neural network and the dropout mechanism to consider the uncertainty and security constraints. Finally, experiments involving machine traded control, human traded control were implemented. The preliminary experimental results of this article show that our traded control method improves decision-making performance and verifies the effectiveness for SDM problems.

12 January 2021 in Journal of Systems Science and Complexity
Verified
Journal Article
Closed access
PDF file
QZQianqian Zhang
Qianqian Zhang
YKYu Kang
Yu Kang
PYPeilong Yu
Peilong Yu
JZJin Zhu
Jin Zhu
CLChunhan Liu
Chunhan Liu
PLPengfei Li
Pengfei Li

1 January 2025 in IET Control Theory & Applications
Verified
Journal Article
Open access
QZQianqian Zhang
Qianqian Zhang
PLPengfei Li
Pengfei Li
YZYun‐Bo Zhao
Yun‐Bo Zhao
YKYu Kang
Yu Kang
Considering the importance of solder paste printing in the production process of surface mounted technology (SMT), as well as the decisive impact of key process parameters on the solder paste printing effect. Traditional methods, whether manual or machine tuning, suffer from significant production capacity losses due to long downtime, and machines cannot adaptively adjust parameters based on human expert knowledge, thereby affecting the qualification rate of solder paste printing and the efficiency of SMT production lines. This paper proposes a human–machine integration optimization method for key printing process parameters. By establishing a printing quality prediction model and a key process parameter strategy model, a closed‐loop control system has been formed to achieve machine autonomous parameter tuning with expert knowledge. And this paper has completed the establishment of the strategy model based on deep reinforcement learning methods, enabling the SMT production line to predict and adjust key process parameters in real time based on SPI data. In addition, the optimization method described in this paper retains the final decision‐making authority of human operators to ensure emergency correction of prediction bias and decision failure history in the system. The final experimental results of this paper indicate that the proposed optimization method performs well in terms of qualification rate, correction effect, SPI data prediction, etc. These demonstrate the effectiveness and value of the proposed human‐on‐the‐loop optimization method in SMT production lines.

13 February 2026 in Advanced Engineering Informatics
Verified
Journal Article
Closed access
YLYongheng Li
Yongheng Li
QZQianqian Zhang
Qianqian Zhang
YKYu Kang
Yu Kang
YZYunbo Zhao
Yunbo Zhao

1 January 2026 in Engineering Research Express
Verified
Journal Article
Closed access
NCNa Cheng
Na Cheng
YLYongheng Li
Yongheng Li
QZQianqian Zhang
Qianqian Zhang
YZYunbo Zhao
Yunbo Zhao
YKYu Kang
Yu Kang
ZWZihui Wu
Zihui Wu
In clinical EEG-based diagnosis, the acquisition of sufficient and well-labeled data is often hindered by high data collection costs, limited accessibility to subjects, and the inherent difficulty of expert labeling. These constraints result in insufficient data availability, significantly limiting the performance and reliability of traditional machine learning models. To address this challenge, we propose a hybrid human–machine diagnostic framework that integrates deep convolutional generative adversarial networks (DCGANs) and convolutional neural networks (CNNs) for depression detection under incomplete data conditions. The DCGAN module synthesizes realistic EEG samples to augment scarce datasets, while CNNs are employed for feature extraction and classification. A confidence-aware fusion strategy dynamically integrates expert assessments with model predictions, effectively improving diagnostic accuracy in scenarios with limited labeled data. Experimental results on real EEG datasets demonstrate that the proposed approach achieves superior performance, offering a practical solution for intelligent diagnosis in resource-constrained settings.

19 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YZYifan Zhang
Yifan Zhang
QZQianqian Zhang
Qianqian Zhang
ZDZhenhuan Ding
Zhenhuan Ding
Pei ZhangPei Zhang
Pei Zhang
Distribution system restoration requires coordinated switching decisions to recover de-energized loads subject to network operating constraints. Multi-agent deep reinforcement learning (MADRL) alleviates the scalability challenge of large switching action spaces, yet the decomposition of switching actions among agents remains an important factor. In reconfiguration-based restoration, this decomposition directly affects restoration performance by shaping the feasible restoration paths and supply routes. Existing MADRL-based restoration methods rarely incorporate the network topology into agent organization, leaving potential gains in restoration efficiency unexploited. This paper proposes a topology-driven multi-agent restoration framework that constructs an impedance-weighted graph and applies Leiden community detection to partition the network into agent control regions. Switches crossing community boundaries are assigned to adjacent agents, allowing both agents to operate the corresponding switches. The fault location is used to restrict exploration to fault-relevant agents during training. The resulting multi-agent decision framework is trained using the proposed learning method. Experiments on a practical 82-bus 10~kV distribution network demonstrate the effectiveness of the proposed framework.