Li Zhu

Ms. Li Zhu


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
5 May 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SYsun yuefei
sun yuefei
孙波孙 波
孙 波
THTao Hu
Tao Hu
LZLi Zhu
Li Zhu
Despite the widespread use of artificial intelligence-based methods in detecting electricity theft by smart grid customers, current methods suffer from two main flaws: a limited amount of data on electricity theft customers compared to that on normal customers and an imbalanced dataset that can significantly affect the accuracy of the detection method. Additionally, most existing methods for detecting electricity theft rely solely on one-dimensional electricity consumption data, which fails to capture the periodicity of consumption and overlooks the temporal correlation of customers’ electricity consumption based on their weekly, monthly, or other time scales. To address the mentioned issues, this paper proposes a novel approach that first employed a time series generative adversarial network to balance the dataset by generating synthetic data for electricity theft customers. Then, a hybrid multi-time-scale neural network-based model was utilized to extract customers’ features and a CatBoost classifier was applied to achieve classification. Experiments were conducted on a real-world smart meter dataset obtained from the State Grid Corporation of China. The results demonstrated that the proposed method could detect electricity theft by customers with a precision rate of 96.64%, a recall rate of 96.87%, and a significantly reduced false detection rate of 3.77%.

9 April 2024 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
LZLi Zhu
Li Zhu
WLWei Liu
Wei Liu
HTHanzhong Tan
Hanzhong Tan
THTao Hu
Tao Hu
Robot joints are the main structure for controlling the motion of the machine body, where the motion state of them directly affects the performance of the industrial robot. Due to the difficulty of obtaining the joint torque information of industrial robots, it is very hard to monitor the motion state of them. Based on the velocity and force driven by current of motors, we propose a novel Bayesian optimization framework to predict the joint motion state of industrial robot in this paper. Based on the temporal correlation of joint current and the correlation between the current and motion state of joint, we use the LSTM and BiLSTM to regressing prediction of the current and state of joint motor first. Then, the Bayesian optimization method is used to adjust the hyperparameters of our network, which realize the analysis of the joint motor current under different motion states and improve the accuracy of the prediction of joint motion states. Finally, we design the joint current acquisition platform of industrial robot based on Hall current sensors, which can collect joint currents without contact and generate experimental dataset. Comparing with the popular intelligent methods, the results show that our Bayesian optimization framework realizes a more accurate prediction of motion state for the four-axis industrial robot on the basis of contact-less current acquisition.

24 March 2024 in Intelligent Systems with Applications
Verified
Journal Article
Open access
MZMinghu Zha
Minghu Zha
LZLi Zhu
Li Zhu
YZYunyun Zhu
Yunyun Zhu
JLJun Li
Jun Li
THTao Hu
Tao Hu

5 December 2025 in IEEE Access
Verified
Journal Article
Open access
XHXinyi He
Xinyi He
JTJianjun Tan
Jianjun Tan
THTao Hu
Tao Hu
LZLi Zhu
Li Zhu
Accurate photovoltaic module defect detection is hindered by limited single-modality information and weak feature representation under complex environmental conditions. To enhance defect identification in photovoltaic modules, a cross-modal attention and semantic-aware segmentation network is proposed herein. The framework introduces a cross-modal attention interaction module that adaptively balances visible and thermal features to strengthen inter-modal complementarity. A semantic-aware fusion module is also developed to refine semantic representation and improve feature fusion consistency. In addition, a dedicated multimodal dataset is constructed to support model evaluation. The proposed method demonstrates superior robustness and generalization capability across diverse scenarios. This work provides an effective and scalable approach for improving defect detection performance in photovoltaic systems via multimodal feature integration and attention-guided semantic learning.

1 January 2025 in International Journal of Distributed Sensor Networks
Verified
Journal Article
Open access
QLQinghai Li
Qinghai Li
LZLi Zhu
Li Zhu
MZMinghu Zha
Minghu Zha
THTao Hu
Tao Hu
With the rapid development of artificial intelligence (AI) and the broad deployment of the Internet of Things (IoT), the smart grid as a novel grid has become an essential power management system. Forecasting a household′s electricity consumption is crucial for optimizing the home energy management system. By collecting data and analyzing household electricity usage patterns, improper behaviors can be diagnosed more effectively. However, household electricity forecasting confronts many challenges due to the unpredictability of individual household consumption behavior. In this paper, we propose an intelligent electricity consumption prediction model based on CNN and a BiLSTM‐Attention mixture model is used to forecast the short‐ term household load for a single family. First, we use the CNN network to extract the feature of the time series data of household load consumption. Then, the BiLSTM‐Attention is used to predict the power consumption for each room and the total household based on the high dimensional feature data, which connects the time series data context and relationship. Next, we trained the BiLSTM‐Attention network on the personal household electricity consumption dataset by the University of California. Finally, we compared the predicted value with the actual value and the prediction model with the traditional algorithm regarding MAE, RMSE, and accuracy performance. Experimental results demonstrate the efficacy of our proposed BiLSTM‐Attention model in intelligent home electricity consumption prediction.