Jingjing Shan

Ms. Jingjing Shan


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
6 October 2026 in Processes
Verified
Journal Article
Open access
PDF file
MLMenghan Liu
Menghan Liu
XMXinying Miao
Xinying Miao
PRPing Ren
Ping Ren
JSJingjing Shan
Jingjing Shan
JLJunhao Li
Junhao Li
JZJiankang Zhong
Jiankang Zhong
Reliable fault diagnosis of rolling bearings is essential for ensuring the safe and stable operation of rotating machinery. However, existing diagnostic models are often hindered by the strong non-stationarity and weak fault characteristics of vibration signals under complex operating conditions, as well as uneven sample distributions among fault categories, which compromise discriminative representation learning and lead to biased fault recognition. To address these challenges, this paper proposes a novel rolling bearing fault diagnosis framework, termed MOBO-VMD-SPD-ProSwinNet, which integrates adaptive signal decomposition, geometry-aware fault representation, and semantic-guided deep feature learning. Specifically, multi-objective Bayesian optimization (MOBO) is introduced to adaptively determine the key parameters of variational mode decomposition (VMD), while the selected high-energy intrinsic mode functions are transformed into Riemannian symmetric positive definite (SPD) recurrence images to preserve local statistical dependencies and temporal recurrence characteristics. On this basis, a convolutional neural network (CNN)-Swin Transformer architecture is combined with prompt-guided semantic prototype learning to capture complementary local–global fault information while enhancing class-oriented representation and reducing class-biased feature learning. Experiments on the Case Western Reserve University (CWRU), Jiangnan University (JNU), and Southeast University (SEU) bearing datasets demonstrate the effectiveness of the proposed framework. On the CWRU benchmark, the proposed method achieves mean Accuracy, Macro-Precision, Macro-Recall, and Macro-F1 of 99.59%, 99.61%, 99.60%, and 99.59%, respectively, improving the mean accuracy by 1.75 percentage points over the strongest evaluated comparison method. Moreover, mean accuracies of 99.64% and 98.86% are obtained on the JNU and SEU datasets, respectively, further demonstrating the robustness of the proposed framework across different operating conditions and data distributions.

13 October 2026 in Sensors
Verified
Journal Article
Open access
PDF file
JSJingjing Shan
Jingjing Shan
XMXinying Miao
Xinying Miao
MLMenghan Liu
Menghan Liu
HLHaoran Li
Haoran Li
ZHZhipeng He
Zhipeng He
HWHan Wang
Han Wang
Routine microalgal cell counting requires sampling and microscopy. We developed a low-cost portable machine-vision system (LPMVS) for non-destructive density estimation of visibly green Dunaliella sp. cultures. The compact benchtop LPMVS combines motorized flask loading, a light-isolated dark box with diffuse light-emitting diode (LED) illumination, fixed camera–flask geometry, red–green–blue (RGB) imaging through the flask, mask-derived liquid-region extraction, Raspberry Pi inference, and a local liquid-crystal display (LCD). A ready-state load-to-unload cycle required approximately 37 s, including 6 s of processing. The two 40-day flask trajectories yielded 240 image–hemocytometer pairs; 200 records were used to compare three regressors with 20 features selected from 339 descriptors. K-nearest neighbors (KNN) performed best in the flask-mixed record-level comparison (R2 = 0.98; mean absolute percentage error (MAPE) = 6.41%; n=40). Reciprocal leave-one-flask-out transfer analysis on complete trajectories with independently retrained pipelines gave KNN R2 values of 0.914 and 0.803. In the reverse direction, R2 was 0.936 within the overlapping range (n=79), but 41 above-range densities were systematically underestimated. Bootstrap resampling identified recurrent color-based features in both trajectories. An edge-device check using 10 additional measurements yielded preliminary reference-density tracking (R2 = 0.94). These findings support the feasibility of the LPMVS workflow for non-destructive monitoring under controlled laboratory conditions, but extrapolation and generalization to independent batches and optical configurations remain unestablished.