Yuanjun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yuanjun Li has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Yuanjiang Li
Jiangsu University of Science and Technology
3 shared publications - Jinglin Zhang
School of Control Science and Engineering, Shandong University, Jinan, Shandong, China
2 shared publications - Zhiyu Zhu
Automation Academy, Jiangsu University of Science and Technology, Zhenjiang, China
2 shared publications - Andrei Popa
National Institute for Research and Development in Forestry “Marin Drăcea” Bucharest Romania
1 shared publication - Denghao Yang
School of Oceanography, Jiangsu University of Science and Technology, Zhenjiang, People’s Republic of China
1 shared publication - Dewen Zhu
Ocean College, Jiangsu University of Science and Technology, Zhenjiang, China
1 shared publication
Latest Publications
- 14 November 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (11) , 116116
DMSA-Unet: a novel method combining dual-channel features and spatial attention modeling for remote sensing object classification
The significant advancement of modern remote sensing technologies enables the collection of multispectral, hyperspectral, and spatio-temporal data. In earth observation, accurate delineation of features such as shorelines and intertidal zones is crucial for quantitative measurements, involving area estimation and long-term environmental monitoring. However, semantic segmentation (SS) of optical remote sensing images remains challenging because of high intra-class variability, subtle inter-class differences, and complex backgrounds. Thus, an enhanced SS method based on an optimized U-Net architecture was established in our study to address these issues. Specifically, a hybrid feature extraction module was introduced in the encoder to strengthen shallow feature representation. Meanwhile, a multiscale spatial attention module was embedded in the skip connections to adaptively capture spatial dependencies across scales and improve feature fusion. Experiments on the WHDLD and Potsdam datasets demonstrate the effectiveness of the method. This method achieved mIoU scores of 61.33% and 77.47%, with pixel accuracies of 88.02% and 86.72%. Furthermore, the results on the Waterseg dataset confirm its robustness and relevance for accurate geospatial measurements in diverse environments.
- 14 November 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (11) , 116116
DMSA-Unet: a novel method combining dual-channel features and spatial attention modeling for remote sensing object classification
The significant advancement of modern remote sensing technologies enables the collection of multispectral, hyperspectral, and spatio-temporal data. In earth observation, accurate delineation of features such as shorelines and intertidal zones is crucial for quantitative measurements, involving area estimation and long-term environmental monitoring. However, semantic segmentation (SS) of optical remote sensing images remains challenging because of high intra-class variability, subtle inter-class differences, and complex backgrounds. Thus, an enhanced SS method based on an optimized U-Net architecture was established in our study to address these issues. Specifically, a hybrid feature extraction module was introduced in the encoder to strengthen shallow feature representation. Meanwhile, a multiscale spatial attention module was embedded in the skip connections to adaptively capture spatial dependencies across scales and improve feature fusion. Experiments on the WHDLD and Potsdam datasets demonstrate the effectiveness of the method. This method achieved mIoU scores of 61.33% and 77.47%, with pixel accuracies of 88.02% and 86.72%. Furthermore, the results on the Waterseg dataset confirm its robustness and relevance for accurate geospatial measurements in diverse environments.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2064-2069
Identification of Nonlinear Multi-Input Multi-Output Systems Based on Maximum Likelihood Principle
Identification of multi-input multi-output (MIMO) industrial system with block structure is helpful to analyze the dynamic characteristics of the system, and beneficial to design the controller based on the model and the operation monitoring. Based on the identification strategy, the model of MIMO Hammerstein structure has a unique advantage to fit the dynamic input and output data of the process. A parameterized identification algorithm without increasing the number of parameters to be identified is proposed based on the maximum likelihood principle (MLC). Compared with the conventional parameterized identification method, the proposed identification algorithm can effectively separate the coupled nonlinear static parameters from the system dynamic parameters, and reduce the compute calculation amount of the identification algorithm and the variance of parameter estimation error. Besides, an adaptive forgetting factor is also constructed to improve the convergence rate and stability. Finally, the superiority and advantage of the proposed algorithm is verified by a chemical process.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2064-2069
Identification of Nonlinear Multi-Input Multi-Output Systems Based on Maximum Likelihood Principle
Identification of multi-input multi-output (MIMO) industrial system with block structure is helpful to analyze the dynamic characteristics of the system, and beneficial to design the controller based on the model and the operation monitoring. Based on the identification strategy, the model of MIMO Hammerstein structure has a unique advantage to fit the dynamic input and output data of the process. A parameterized identification algorithm without increasing the number of parameters to be identified is proposed based on the maximum likelihood principle (MLC). Compared with the conventional parameterized identification method, the proposed identification algorithm can effectively separate the coupled nonlinear static parameters from the system dynamic parameters, and reduce the compute calculation amount of the identification algorithm and the variance of parameter estimation error. Besides, an adaptive forgetting factor is also constructed to improve the convergence rate and stability. Finally, the superiority and advantage of the proposed algorithm is verified by a chemical process.
- Open Access
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 10148-10161
CTMU-Net: An Improved U-Net for Semantic Segmentation of Remote-Sensing Images Based on the Combined Attention Mechanism
With the development of remote-sensing technology, it is important to use semantic segmentation methods to obtain detailed information in remote-sensing images. However, the objects in the images reveal significant intra-class differences and slight inter-class differences, thus affecting the acquisition of terrain information. To tackle the problems, this paper proposes an improved U-Net for the semantic segmentation of remote-sensing images. Firstly, the local importance-based pooling is introduced to alleviate the loss of feature details in the coding part. Secondly, a combined attention module with a double-branch structure is designed, which models the local relationship and the global relationship at the same time to obtain more typical features. Finally, in order to make full use of the feature information extracted from the coding part, the combined attention module and the channel attention module are added to different positions in U-Net. In order to validate the proposed method, we conduct experiments on the WHDLD dataset and compare the experimental results with other semantic segmentation methods. On the WHDLD dataset, the MPA, MIOU, and FWIOU of the proposed method reach 76%, 64.11%, and 75.64%, respectively, revealing its priority. To demonstrate the generalization of the proposed method, generalization experiments are conducted via the LandCover.ai dataset and the Massachusetts-building dataset. The simulation results testify that the proposed method provides an excellent generalization ability.
- 23 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 10148-10161
Open AccessCTMU-Net: An Improved U-Net for Semantic Segmentation of Remote-Sensing Images Based on the Combined Attention Mechanism
With the development of remote-sensing technology, it is important to use semantic segmentation methods to obtain detailed information in remote-sensing images. However, the objects in the images reveal significant intra-class differences and slight inter-class differences, thus affecting the acquisition of terrain information. To tackle the problems, this paper proposes an improved U-Net for the semantic segmentation of remote-sensing images. Firstly, the local importance-based pooling is introduced to alleviate the loss of feature details in the coding part. Secondly, a combined attention module with a double-branch structure is designed, which models the local relationship and the global relationship at the same time to obtain more typical features. Finally, in order to make full use of the feature information extracted from the coding part, the combined attention module and the channel attention module are added to different positions in U-Net. In order to validate the proposed method, we conduct experiments on the WHDLD dataset and compare the experimental results with other semantic segmentation methods. On the WHDLD dataset, the MPA, MIOU, and FWIOU of the proposed method reach 76%, 64.11%, and 75.64%, respectively, revealing its priority. To demonstrate the generalization of the proposed method, generalization experiments are conducted via the LandCover.ai dataset and the Massachusetts-building dataset. The simulation results testify that the proposed method provides an excellent generalization ability.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 10 (2) , 3870-3887
A Fault Diagnosis Method Based on an Improved Deep Q-Network for the Interturn Short Circuits of a Permanent Magnet Synchronous Motor
With the rapid development of artificial intelligence, deep learning has become widely used to monitor the state of permanent magnet synchronous motors (PMSMs). However, to achieve accurate condition detection, datasets with large quantities of labeled data must be used for model training. Accuracy decreases considerably when the quantity of labeled data is insufficient. To address this problem, a fault diagnosis method based on an improved deep Q-network (DQN) is designed in this study to detect inter-turn short circuit (ITSC) faults. In this method, first, a one-dimensional group convolutional neural network–based conditional generative adversarial network is used to expand the collected dataset. Subsequently, a DQN-based fault diagnosis method is applied. A one-dimensional deep residual shrinkage network and the prioritized experience replay strategy are introduced into the original network structure, and the sampling strategy of the original network is optimized. Finally, the fault diagnosis capability of the proposed method was evaluated in several experiments. The proposed method considerably outperformed competing algorithms: it had a diagnosis rate of 98.49% for the ITSC faults of PMSMs and a diagnosis rate of 99.50% on the bearing dataset of Case Western University with certain generalizations. The proposed method is promising for use in circuit fault detection.
- 18 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Transportation Electrification
- Vol. 10 (2) , 3870-3887
A Fault Diagnosis Method Based on an Improved Deep Q-Network for the Interturn Short Circuits of a Permanent Magnet Synchronous Motor
With the rapid development of artificial intelligence, deep learning has become widely used to monitor the state of permanent magnet synchronous motors (PMSMs). However, to achieve accurate condition detection, datasets with large quantities of labeled data must be used for model training. Accuracy decreases considerably when the quantity of labeled data is insufficient. To address this problem, a fault diagnosis method based on an improved deep Q-network (DQN) is designed in this study to detect inter-turn short circuit (ITSC) faults. In this method, first, a one-dimensional group convolutional neural network–based conditional generative adversarial network is used to expand the collected dataset. Subsequently, a DQN-based fault diagnosis method is applied. A one-dimensional deep residual shrinkage network and the prioritized experience replay strategy are introduced into the original network structure, and the sampling strategy of the original network is optimized. Finally, the fault diagnosis capability of the proposed method was evaluated in several experiments. The proposed method considerably outperformed competing algorithms: it had a diagnosis rate of 98.49% for the ITSC faults of PMSMs and a diagnosis rate of 99.50% on the bearing dataset of Case Western University with certain generalizations. The proposed method is promising for use in circuit fault detection.
- 15 September 2021
- Published by Society of Petroleum Engineers (SPE)
Well Connectivity Analysis with Deep Learning
Knowledge of well connectivity in a reservoir is crucial, especially for early-stage field development and water injection management. However, traditional interference tests can often take several weeks or even longer depending on the distance between wells and the hydraulic diffusivity of the reservoir. Therefore, instead of physically shutting in production wells, we can take advantage of deep learning methods to perform virtual interference tests. In this study, we first used the historical field data to train the deep learning model, a modified Long- and Short-term Time-series network (LSTNet). This model combines the Convolution Neural Network (CNN) to extract short-term local dependency patterns, the Recurrent Neural Network (RNN) to discover long-term patterns for time series trends, and a traditional autoregressive model to alleviate the scale insensitive problem. To address the time-lag issue in signal propagation, we employed a skip-recurrent structure that extends the existing RNN structure by connecting a current state with a previous state when the flow rate signal from an adjacent well starts to impact the observation well. In addition, we found that wells connected to the same manifold usually have similar liquid production patterns, which can lead to false causation of subsurface pressure communication. Thus we enhanced the model performance by using external feature differences to remove the surface connection in the data, thereby reducing input similarity. This enhancement can also amplify the weak signal and thus distinguish input signals. To examine the deep learning model, we used the datasets generated from Norne Field with two different geological settings: sealing and nonsealing cases. The production wells are placed at two sides of the fault to test the false-negative prediction. With these improvements and with parameter tuning, the modified LSTNet model could successfully indicate the well connectivity for the nonsealing cases and reveal the sealing structures in the sealing cases based on the historical data. The deep learning method we employed in this work can predict well pressure without using hand-crafted features, which are usually formed based on flow patterns and geological settings. Thus, this method should be applicable to general cases and more intuitive. Furthermore, this virtual interference test with a deep learning framework can avoid production loss.
- 15 September 2021
- Published by Society of Petroleum Engineers (SPE)
Well Connectivity Analysis with Deep Learning
Knowledge of well connectivity in a reservoir is crucial, especially for early-stage field development and water injection management. However, traditional interference tests can often take several weeks or even longer depending on the distance between wells and the hydraulic diffusivity of the reservoir. Therefore, instead of physically shutting in production wells, we can take advantage of deep learning methods to perform virtual interference tests. In this study, we first used the historical field data to train the deep learning model, a modified Long- and Short-term Time-series network (LSTNet). This model combines the Convolution Neural Network (CNN) to extract short-term local dependency patterns, the Recurrent Neural Network (RNN) to discover long-term patterns for time series trends, and a traditional autoregressive model to alleviate the scale insensitive problem. To address the time-lag issue in signal propagation, we employed a skip-recurrent structure that extends the existing RNN structure by connecting a current state with a previous state when the flow rate signal from an adjacent well starts to impact the observation well. In addition, we found that wells connected to the same manifold usually have similar liquid production patterns, which can lead to false causation of subsurface pressure communication. Thus we enhanced the model performance by using external feature differences to remove the surface connection in the data, thereby reducing input similarity. This enhancement can also amplify the weak signal and thus distinguish input signals. To examine the deep learning model, we used the datasets generated from Norne Field with two different geological settings: sealing and nonsealing cases. The production wells are placed at two sides of the fault to test the false-negative prediction. With these improvements and with parameter tuning, the modified LSTNet model could successfully indicate the well connectivity for the nonsealing cases and reveal the sealing structures in the sealing cases based on the historical data. The deep learning method we employed in this work can predict well pressure without using hand-crafted features, which are usually formed based on flow patterns and geological settings. Thus, this method should be applicable to general cases and more intuitive. Furthermore, this virtual interference test with a deep learning framework can avoid production loss.
- 22 October 2019
- Published by Society of Petroleum Engineers (SPE) in SPE Reservoir Evaluation & Engineering
- Vol. 23 (01) , 001-012
Reservoir Geostatistical Estimates of Imprecise Information Using Fuzzy-Kriging Approach
Summary: This paper presents a methodology for the geostatistical estimation of reservoir properties to handle uncertainties in observation and modeling. Given certain known well-log data in a geological region, the Kriging methodology is used to estimate or predict spatial phenomena at nonsampled locations from the estimated random function. The approach assumes that the data are accurate and precise, and the random function is generated from a thorough descriptive analysis of the known data set. Regarding the assumptions considered in classic Kriging, it is realistic to assume that spatial data contain a certain amount of imprecision, mostly because of measurement errors, and information is lacking to properly assess a unique random-function model. A methodology is presented for the geostatistical estimation of reservoir properties to handle uncertainties in observation and modeling. A combination of regular, or classic, Kriging and the fuzzy-logic method is proposed. As such, imprecise input data and variogram parameters are modeled on the basis of fuzzy-logic theory, while the predictions and variances are computed from Kriging analysis characterized by membership functions. Last, an optimization method is included to solve the constrained fuzzy-nonlinear-equation system. The proposed methodology was implemented, and a user-friendly integrated tool was developed, which enables the user to create a grid structure on the basis of the input data, conduct statistical analysis, and run fuzzy Kriging for various problems. We used the tool to run a test case using the SPE 10 (SPE Comparative Solution Project, Model-II 2000) porosity data. With the fuzzy-Kriging methodology, two maps are generated with upper-bound values and lower-bound values. Compared with true data, the upper-bound map trends to include higher values better, while the lower-bound map trends to include lower-value parts better. In addition, a case study has been conducted using measured core-permeability data in a heterogeneous reservoir to demonstrate the viability of the technology.
- 22 October 2019
- Published by Society of Petroleum Engineers (SPE) in SPE Reservoir Evaluation & Engineering
- Vol. 23 (01) , 001-012
Reservoir Geostatistical Estimates of Imprecise Information Using Fuzzy-Kriging Approach
Summary: This paper presents a methodology for the geostatistical estimation of reservoir properties to handle uncertainties in observation and modeling. Given certain known well-log data in a geological region, the Kriging methodology is used to estimate or predict spatial phenomena at nonsampled locations from the estimated random function. The approach assumes that the data are accurate and precise, and the random function is generated from a thorough descriptive analysis of the known data set. Regarding the assumptions considered in classic Kriging, it is realistic to assume that spatial data contain a certain amount of imprecision, mostly because of measurement errors, and information is lacking to properly assess a unique random-function model. A methodology is presented for the geostatistical estimation of reservoir properties to handle uncertainties in observation and modeling. A combination of regular, or classic, Kriging and the fuzzy-logic method is proposed. As such, imprecise input data and variogram parameters are modeled on the basis of fuzzy-logic theory, while the predictions and variances are computed from Kriging analysis characterized by membership functions. Last, an optimization method is included to solve the constrained fuzzy-nonlinear-equation system. The proposed methodology was implemented, and a user-friendly integrated tool was developed, which enables the user to create a grid structure on the basis of the input data, conduct statistical analysis, and run fuzzy Kriging for various problems. We used the tool to run a test case using the SPE 10 (SPE Comparative Solution Project, Model-II 2000) porosity data. With the fuzzy-Kriging methodology, two maps are generated with upper-bound values and lower-bound values. Compared with true data, the upper-bound map trends to include higher values better, while the lower-bound map trends to include lower-value parts better. In addition, a case study has been conducted using measured core-permeability data in a heterogeneous reservoir to demonstrate the viability of the technology.