Jiacan Xu

Dr. Jiacan Xu

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
10 April 2021 in Energies
Verified
Journal Article
Open access
PDF file
YJYing Ji
Ying Ji
JWJianhui Wang
Jianhui Wang
JXJiacan Xu
Jiacan Xu
DLDonglin Li
Donglin Li
The proliferation of distributed renewable energy resources (RESs) poses major challenges to the operation of microgrids due to uncertainty. Traditional online scheduling approaches relying on accurate forecasts become difficult to implement due to the increase of uncertain RESs. Although several data-driven methods have been proposed recently to overcome the challenge, they generally suffer from a scalability issue due to the limited ability to optimize high-dimensional continuous control variables. To address these issues, we propose a data-driven online scheduling method for microgrid energy optimization based on continuous-control deep reinforcement learning (DRL). We formulate the online scheduling problem as a Markov decision process (MDP). The objective is to minimize the operating cost of the microgrid considering the uncertainty of RESs generation, load demand, and electricity prices. To learn the optimal scheduling strategy, a Gated Recurrent Unit (GRU)-based network is designed to extract temporal features of uncertainty and generate the optimal scheduling decisions in an end-to-end manner. To optimize the policy with high-dimensional and continuous actions, proximal policy optimization (PPO) is employed to train the neural network-based policy in a data-driven fashion. The proposed method does not require any forecasting information on the uncertainty or a prior knowledge of the physical model of the microgrid. Simulation results using realistic power system data of California Independent System Operator (CAISO) demonstrate the effectiveness of the proposed method.

21 October 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
PZPeng Zhou
Peng Zhou
DWDengshuai Wu
Dengshuai Wu
JXJiacan Xu
Jiacan Xu
ZWZinan Wang
Zinan Wang
Ma DazhongMa Dazhong
Ma Dazhong
Rolling bearing fault diagnosis is significant to the stable operation of rotating machinery systems. However, the fault data collected in practical engineering is seriously imbalanced, which degrades the diagnosis performance. A DRNet intelligent fault diagnosis model was proposed in this paper based on the probabilistic diffusion model to enhance fault diagnosis performance under imbalanced data. This paper utilized a probabilistic diffusion model to learn a deep semantic representation of fault data, which in turn generates high-quality fault features to balance the number of fault samples. Moreover, we utilized the deep features of fault signals to build a feature metric module that optimized the features of the generated samples. This enhances the accuracy and diversity of the generated data. Finally, the fault categories of the samples were identified using the residual network after data enhancement. The experimental results indicate that compared to other common methods, our method can more effectively fit the feature distribution of real samples resulting in generated samples with higher similarity and exhibiting good stability and accuracy when processing bearing unbalanced fault data.

1 January 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
DLDonglin Li
Donglin Li
YYYuqi Yao
Yuqi Yao
YZYuxian Zhang
Yuxian Zhang
JXJiacan Xu
Jiacan Xu
QWQisen Wang
Qisen Wang

15 July 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JXJiacan Xu
Jiacan Xu
DLDonglin Li
Donglin Li
PZPeng Zhou
Peng Zhou
YZYuxian Zhang
Yuxian Zhang
ZWZinan Wang
Zinan Wang
Ma DazhongMa Dazhong
Ma Dazhong
The ability to decode between subjects without the additional data recorded for training is crucial for brain-computer interface (BCI) applications. However, electroencephalogram (EEG) data have cross-session and cross-subject variability due to external factors and individual differences. Therefore cross-domain EEG signal recognition remains challenging. To solve this problem, we propose a feature relation contrastive network (FRCN) in this article. First, we use covariance matrices to align the data distribution between in source and target domains to reduce the difference. Second, we extract feature representations by the pretrained embedding network and align the correlations of the features using a nonlinear transformation. Then, we propose a source domain selection method to measure the similarity of motion-related data distributions between domains by utilizing resting-state data from different domains and the selected appropriate source domain data for fine-tuning. Finally, we propose a metric learning-based interdomain relation contrastive module (RCM) to learn multiple nonlinear distance metrics based on different levels of features simultaneously, which enables interdomain comparison learning and accurately compares the relations between samples to reduce the negative migration. For testing the target task, effective matching and similarity comparison function from multiple abstraction-level features jointly alleviates the reliance on the embedded ability to generate linearly separable features. The experimental results show that the FRCN achieves better results on the BCI Competition IV II-a and II-b dataset, and the ablation experiments validate the effectiveness of the method.

28 October 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DLDonglin Li
Donglin Li
JXJiacan Xu
Jiacan Xu
YZYuxian Zhang
Yuxian Zhang
Ma DazhongMa Dazhong
Ma Dazhong
JWJianhui Wang
Jianhui Wang
The identification of EEG signals cross sessions and subjects remains challenging due to the variability of data caused by extraneous factors and individual differences in EEG signals. Existing domain-adaptive transfer methods using cross-domain labelled samples for classification are too coarse could lead to negative transfer problems. To solve this problem, we propose a prototypical contrastive domain adaptation (PCDA) network in this paper. Firstly, we align the data from different domains to reduce the data distribution differences for supporting the subsequent model construction. Then, a conditional domain adversarial network is used in the feature extraction stage to achieve domain alignment and learn deep feature representations. Secondly, we propose a scoring method to equivalently quantify the similarity of data from different domains using resting-state data and select similar source domain data to fine-tune the model. Finally, we propose a prototypical contrastive learning module. In-domain PC learning captures and compares the category-wise semantic structure of the data and the learned representations to enable the clustering of similar features. Cross-domain PC learning encodes and compares the semantic structure in shared embedding space to enable self-supervised feature alignment and reduce negative transfer. The experimental results show that the PCDA network achieves better results on the datasets of Brain-Computer Interface Competition IV II-a and II-b, and the ablation experiments validate the efficacy of the method.

28 October 2024 in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
Verified
Journal Article
Closed access
PZPeng Zhou
Peng Zhou
WLWen Li
Wen Li
ZWZinan Wang
Zinan Wang
JXJiacan Xu
Jiacan Xu
QWQian Wang
Qian Wang
The load capacity and lubrication performance of the slewing bearing are fairly sensitive to edge effects at both ends of the main thrust rollers. Therefore, quantitative investigations of the edge effect at both ends of slewing bearing is practically important. In this study, an elastic fluid lubrication model of the slewing bearing that considered the external load and internal structural parameters is established. A modification function of rollers is included in a finite long-line contact elastic fluid lubrication model to perform the dynamic analysis. The simulated oil film’s thickness and pressure distributions are compared under different working conditions. And the edge effect is eliminated by modifying the rollers’ construction. The results indicate that under the large eccentric load, the speed of the slewing bearing must be decreased to ensure elastic fluid lubrication performance. A genetic algorithm that used to discover the optimal modification length shows the best busbar of the main thrust roller is 12 μm, which could decrease the vibration amplitude of the unmodified roller by 8.13%. This result gives a significant way for slewing bearing’s structural design.