Daye Li

Daye Li

Auto-generated profile, based on publicly available information

Daye Li

Key Laboratory of Knowledge Automation for Industrial Processes of the Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 February 2016 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
PMPeng-Cheng Ma
Peng-Cheng Ma
DLDaye Li
Daye Li
SLShuo Li
Shuo Li

11 April 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
DLDaye Li
Daye Li
JDJie Dong
Jie Dong
Kaixiang PengKaixiang Peng
Kaixiang Peng
In the field of fault detection, the nonstationary characteristics caused by external disturbances of wind turbines and other reasons can mask the fault signals, while the inconsistent data distribution between training data and test data due to equipment loss and other reasons can lead to model mismatch problems, both of which can lead to the degradation of fault detection performance. In order to solve the above problems, a novel adaptive fault detection framework is proposed in this work. First, the stationary features of nonstationary variables are extracted based on short-time Fourier analysis, after which the features are combined with the stationary variables. Second, isolation-based anomaly detection using nearest-neighbor ensembles is introduced as monitoring metrics for designing the statistic for the slow feature analysis method. Then, the differences between online normal data and training data are calculated, the model update factor and update strategy are designed, and an adaptive fault detection framework based on short-time Fourier transform-slow feature analysis (STFT-SFA) is proposed. Finally, the effectiveness of the proposed fault detection framework is verified using the Tennessee-Eastman process and actual wind turbine data. The results show that the proposed STFT-SFA method has a 94.0% correct monitoring rate (CMR) for Tennessee Eastman process failures, and the proposed adaptive STFT-SFA method has a 95.6% CMR for wind turbine failures, which are better than other comparative fault detection methods.

13 November 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JDJie Dong
Jie Dong
DLDaye Li
Daye Li
YWYanmei Wei
Yanmei Wei
Kaixiang PengKaixiang Peng
Kaixiang Peng
With the integrated and scaled development of modern industrial processes, multiple control units are strongly coupled, forming a complex interconnected network. This leads to the propagation and evolution of faults within the network, which will affect the quality of products and the safety of industrial processes. This article proposes a novel process monitoring and root cause diagnosis strategy for complex industrial processes based on knowledge?data integrated causal digraph. Compared with traditional single data-driven methods, this strategy combines process data and knowledge to improve the ability of fault detection and diagnosis. First, an attention-based time convolutional network is performed on process variables to construct causal digraph. The causal digraph is trimmed and refined using the process knowledge to solve the problem of redundant causality and enhance the interpretability. Second, the complex industrial process is decomposed into multiple sub-blocks and the causal relationship between sub-blocks is obtained. On this basis, a process monitoring model for collaborative analysis of temporal and spatial information is established, where spatial information among sub-blocks is obtained through the interaction of information between them, and the temporal information within sub-blocks is captured by kernel canonical variate analysis. Subsequently, a fault diagnosis method based on global and local causal digraphs is designed. Process data and causal digraphs are used to select fault variables and analyze causality relationship respectively, which can infer the fault root cause and propagation path. Finally, the experimental results on the real dataset of float glass production process demonstrate that our strategy not only achieves significant improvements than other methods, but also has a favorable application in industrial processes.

7 August 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
DLDaye Li
Daye Li
HZHongjun Zhang
Hongjun Zhang
LALisha An
Lisha An
JDJie Dong
Jie Dong
Kaixiang PengKaixiang Peng
Kaixiang Peng
Modern manufacturing processes typically comprise multiple subprocesses, and the temporal-spatial features of process variables are difficult to extract, which bring significant challenges for traditional quality-related fault diagnosis. To solve this problem, we propose a fault detection model driven by graph attention networks integrated gated recurrent unit-canonical variable analysis (GATRU-CVA). Firstly, the knowledge of domain experts and historical data are used to construct a sub-block knowledge graph. Next, a spatial feature extractor for the graph attention network is constructed for global variables. In addition, the sub-block knowledge graph is used to divide the global spatial features into sub-blocks, and the corresponding temporal feature extractor is constructed. Then, taking the process dynamic characteristic into account, CVA is used to model the process based on the spatial-temporal features, upon which the corresponding statistics are calculated. The threshold is determined by the kernel density estimation method. Finally, actual production data of the hot strip mill process (HSMP) are used to validate the proposed model. The results show that the proposed method has a 97% correct monitoring rate for HSMP, which is better than the other comparative fault detection methods.

9 January 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
DLDaye Li
Daye Li
JDJie Dong
Jie Dong
CZCuicui Zhang
Cuicui Zhang
Kaixiang PengKaixiang Peng
Kaixiang Peng
Data distributions of normal and abnormal operational conditions may overlap to some extent, making it challenging for traditional fault detection models to extract the intrinsic features of normal data, which brings serious challenge to fault detection. Against this background, we propose a new two-stage feature-extraction (TSFE)-based fault detection method with variable missing repair mechanism for industrial processes with imperfect data. The proposed method can effectively compress the data feature-space to extract intrinsic features. First, an out-of-distribution (OOD) data generation method is designed. Second, a new feature compression auto-encoder (FCAE) is constructed for stage-one feature extraction. Positive and negative sample feature pairs are constructed based on normal data and OOD data. Then, a new feature compression supervised contrastive learning (FCSCL) network is constructed for stage-two feature extraction. In addition, the proposed method includes a variable missing repair mechanism to handle imperfect data. Finally, the effectiveness of the proposed method is verified using a real hot strip mill process dataset. The experimental results indicate that the proposed method achieves an average correct monitoring rate of up to 95.5%, with a false alarm rate of only 1%. This demonstrates that high fault detection performance can still be maintained even in the presence of variable signals missing.

25 November 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
DHDongjie Hua
Dongjie Hua
JDJie Dong
Jie Dong
Kaixiang PengKaixiang Peng
Kaixiang Peng
Silvio SimaniSilvio Simani
Silvio Simani
DLDaye Li
Daye Li
JHJianing Hou
Jianing Hou
As large-scale industrial processes evolve toward greater complexity, the increasing interdependence of networked and dynamic process data has a critical impact on product quality, creating significant challenges for quality-related fault diagnosis. Causal graphs (CGs) are effective in modeling structural relationships among nodes in large-scale industrial processes. However, traditional causal discovery methods are limited in their ability to represent hierarchical and dynamic causal structures with spatiotemporal features. To overcome these limitations, a dynamic causal entropy (DCE)-spatiotemporal convolutional network is designed in this article. First, the proposed DCE method enables the construction of hierarchical dynamic CGs that accurately represent dynamic interactions among process variables, effectively mitigating confounding factors and enhancing interpretability. Second, a 3-D squeeze-and-excitation (SE) convolutional neural network is designed to adaptively recalibrate channel-wise information and deeply analyze the spatiotemporal characteristics embedded in the hierarchical dynamic CGs. Furthermore, a local–global quality-related fault detection approach is introduced, along with a novel causal anomaly vector that facilitates precise recognition of fault root causes across multiple hierarchical levels. Finally, the effectiveness and practical advantages of the proposed method are thoroughly demonstrated using both numerical simulations and real-world data from a hot strip mill process (HSMP), achieving a fault detection accuracy of 95.78%.