Fanjun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fanjun Li has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jiayue Feng
University of Jinan
6 shared publications - Xinyu Shen
University of Jinan
5 shared publications - Shanshan Xue
School of mathematical sciences, University of Jinan, Jinan, China
3 shared publications - Shaoqi Cheng
School of mathematical sciences, University of Jinan, Jinan, China
3 shared publications Qianwen Liu
2 shared publicationsYing Li
2 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 372-383
A DWT-LSTM Hybrid Model for Temperature Prediction in the Cement Kiln
- 2 July 2026
- Published by Springer Nature
- p. 372-383
A DWT-LSTM Hybrid Model for Temperature Prediction in the Cement Kiln
- 17 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 343
Self-organizing cascaded echo state network for time series prediction
- 17 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 343
Self-organizing cascaded echo state network for time series prediction
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (5) , 3788-3798
NOx Concentration Prediction in Cement Kilns Under Unbalanced Working Conditions
Accurately predicting nitrogen oxides (NOx) concentration in cement kilns is crucial for controlling pollutant emissions. However, due to the variable and unbalanced distribution of working conditions, achieving precise prediction of NOx concentration remains challenging. To address this issue, this study proposes an echo state network with ensemble modular outputs (EMOESN) for NOx concentration prediction under unbalanced working condition distribution. First, a two-stage working condition recognition framework is proposed. In the first stage, for the problem of multiple working conditions in cement kilns, the k-means++ clustering approach combined with calcination mechanism is adopted to generate multiple datasets with different working condition characteristics. In the second stage, to address the problem of unbalanced working condition distribution, a block bootstrap sampling method with sliding window is applied to subdivide the larger datasets into more balanced subdatasets. Second, an EMOESN is established for NOx concentration prediction during the process of cement clinker calcination, where the optimal outputs under different working conditions are determined using a variance-based weighting method. Finally, the effectiveness of the proposed prediction model is validated using a dataset from an actual cement clinker calcination process. Experimental results show that the suggested method outperforms various well-known NOx prediction methods.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (5) , 3788-3798
NOx Concentration Prediction in Cement Kilns Under Unbalanced Working Conditions
Accurately predicting nitrogen oxides (NOx) concentration in cement kilns is crucial for controlling pollutant emissions. However, due to the variable and unbalanced distribution of working conditions, achieving precise prediction of NOx concentration remains challenging. To address this issue, this study proposes an echo state network with ensemble modular outputs (EMOESN) for NOx concentration prediction under unbalanced working condition distribution. First, a two-stage working condition recognition framework is proposed. In the first stage, for the problem of multiple working conditions in cement kilns, the k-means++ clustering approach combined with calcination mechanism is adopted to generate multiple datasets with different working condition characteristics. In the second stage, to address the problem of unbalanced working condition distribution, a block bootstrap sampling method with sliding window is applied to subdivide the larger datasets into more balanced subdatasets. Second, an EMOESN is established for NOx concentration prediction during the process of cement clinker calcination, where the optimal outputs under different working conditions are determined using a variance-based weighting method. Finally, the effectiveness of the proposed prediction model is validated using a dataset from an actual cement clinker calcination process. Experimental results show that the suggested method outperforms various well-known NOx prediction methods.
- 28 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
NOx Concentration Prediction for Cement Rotary Kiln Under Multiworking Conditions Based on an Echo State Network With Modular Output
The cement industry is the third-largest source of nitrogen oxides (NOx) emissions. Accurately predicting the concentration of NOx in cement kilns is crucial for reducing pollutant emissions through optimizing the calcination process of cement clinker. However, due to the complex physical and chemical reactions and variable working conditions inside rotary kilns, it is difficult to predict the NOx concentration accurately. To address this problem, this article develops a prediction model based on a novel echo state network with modular output (MOESN) for NOx concentration prediction in cement rotary kilns under different working conditions. First, the k-means++ clustering method is used for working condition recognition according to the calcination process data. Then, a novel echo state network (ESN) with modular outputs is proposed to predict the NOx concentration in the cement rotary kiln under different working conditions. Meanwhile, the hyperparameters of the proposed model are optimized using the particle swarm optimization (PSO) algorithm to determine the best network configuration for different working conditions. Finally, the effectiveness of the prediction model is evaluated using a dataset from an actual cement clinker calcination process. Experimental results show that the proposed model achieves higher prediction accuracy compared to several widely recognized NOx prediction models.
- 28 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
NOx Concentration Prediction for Cement Rotary Kiln Under Multiworking Conditions Based on an Echo State Network With Modular Output
The cement industry is the third-largest source of nitrogen oxides (NOx) emissions. Accurately predicting the concentration of NOx in cement kilns is crucial for reducing pollutant emissions through optimizing the calcination process of cement clinker. However, due to the complex physical and chemical reactions and variable working conditions inside rotary kilns, it is difficult to predict the NOx concentration accurately. To address this problem, this article develops a prediction model based on a novel echo state network with modular output (MOESN) for NOx concentration prediction in cement rotary kilns under different working conditions. First, the k-means++ clustering method is used for working condition recognition according to the calcination process data. Then, a novel echo state network (ESN) with modular outputs is proposed to predict the NOx concentration in the cement rotary kiln under different working conditions. Meanwhile, the hyperparameters of the proposed model are optimized using the particle swarm optimization (PSO) algorithm to determine the best network configuration for different working conditions. Finally, the effectiveness of the prediction model is evaluated using a dataset from an actual cement clinker calcination process. Experimental results show that the proposed model achieves higher prediction accuracy compared to several widely recognized NOx prediction models.
- 22 July 2025
- Published by Springer Nature
- p. 272-282
Computational Analysis of Synaptic Plasticity in Echo State Network
- 22 July 2025
- Published by Springer Nature
- p. 272-282
Computational Analysis of Synaptic Plasticity in Echo State Network
- 23 May 2025
- Published by Springer Nature
- p. 287-299
NOx Concentration Prediction with Modular Echo State Network in a Cement Clinker Calcination System
- 23 May 2025
- Published by Springer Nature
- p. 287-299
NOx Concentration Prediction with Modular Echo State Network in a Cement Clinker Calcination System
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Hybrid Data-Driven Model for Predicting NOx Concentration in a Cement Clinker Calcination System
Predicting nitrogen oxide (NOx) concentrations accurately is critical for pollution monitoring and control in a cement clinker calcination system (CCCS). However, due to the harsh environment and complex physical and chemical reactions, this is a complicated task for traditional measurement methods. Therefore, a hybrid data-driven model (HDDM) is proposed for real-time prediction of NOx concentration in CCCS, by integrating random forest (RF), temporal convolutional network (TCN) and deep echo state network (DESN). First, to reduce noise interference in process data, a RF is used for input variable selection based on mechanism knowledge. Subsequently, to efficiently capture the temporal dependency of sequence data, a TCN with multi-convolutional kernels is used for reconstructing input samples. Finally, a DESN is designed to establish a dynamic correlation between NOx concentration and extracted temporal features. The experimental results indicate that the prediction accuracy of HDDM is better than the comparative models.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
A Hybrid Data-Driven Model for Predicting NOx Concentration in a Cement Clinker Calcination System
Predicting nitrogen oxide (NOx) concentrations accurately is critical for pollution monitoring and control in a cement clinker calcination system (CCCS). However, due to the harsh environment and complex physical and chemical reactions, this is a complicated task for traditional measurement methods. Therefore, a hybrid data-driven model (HDDM) is proposed for real-time prediction of NOx concentration in CCCS, by integrating random forest (RF), temporal convolutional network (TCN) and deep echo state network (DESN). First, to reduce noise interference in process data, a RF is used for input variable selection based on mechanism knowledge. Subsequently, to efficiently capture the temporal dependency of sequence data, a TCN with multi-convolutional kernels is used for reconstructing input samples. Finally, a DESN is designed to establish a dynamic correlation between NOx concentration and extracted temporal features. The experimental results indicate that the prediction accuracy of HDDM is better than the comparative models.
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (7) , 9644-9654
NOx Concentration Prediction With a Flexible Cascaded Echo-State Network in a Cement Clinker Calcination System
Measuring nitrogen oxide (NOx) concentration accurately and timely is critical for pollution control during cement clinker calcination. However, due to the harsh environment and complex reactions, NOx concentration in calcination systems cannot be directly measured. In this article, a flexible cascaded echo-state network (FCESN) is developed for online measurement of the NOx concentration during the cement clinker calcination. First, a flexible cascaded network structure is proposed, where some echo-state networks (ESNs) as basic modules are added to the network in the form of cascade one by one until the learning error is satisfied. Then, based on the idea of gradual approximation, a novel training algorithm is proposed to pretrain ESN modules for extracting the dynamic feature of the NOx sequence. With the increase of ESN modules, the learning error is monotonically decreasing. Finally, the proposed approach is implemented for online prediction of the NOx concentration in an actual cement clinker calcination system. The prediction results indicate that FCESN is superior to other popular prediction methods in training speed and accuracy.
- 23 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (7) , 9644-9654
NOx Concentration Prediction With a Flexible Cascaded Echo-State Network in a Cement Clinker Calcination System
Measuring nitrogen oxide (NOx) concentration accurately and timely is critical for pollution control during cement clinker calcination. However, due to the harsh environment and complex reactions, NOx concentration in calcination systems cannot be directly measured. In this article, a flexible cascaded echo-state network (FCESN) is developed for online measurement of the NOx concentration during the cement clinker calcination. First, a flexible cascaded network structure is proposed, where some echo-state networks (ESNs) as basic modules are added to the network in the form of cascade one by one until the learning error is satisfied. Then, based on the idea of gradual approximation, a novel training algorithm is proposed to pretrain ESN modules for extracting the dynamic feature of the NOx sequence. With the increase of ESN modules, the learning error is monotonically decreasing. Finally, the proposed approach is implemented for online prediction of the NOx concentration in an actual cement clinker calcination system. The prediction results indicate that FCESN is superior to other popular prediction methods in training speed and accuracy.
- Open Access
- 1 January 2024
- Published by Francis Academic Press Ltd. in International Journal of New Developments in Education
- Vol. 6 (9)
An analysis on the application of flipped classroom under cognitive load theory
With the continuous development of The Times, the combination of online and offline education model has become more and more important in practical teaching. Among them, flipped classroom can enable students to prepare lessons beforehand efficiently after class and discuss independently in class, which can enrich students' way of learning mathematics and can also enhance students' interest in mathematics learning. However, students in junior middle school are facing the problem of excessive cognitive load due to the difficulty of the subject, the lack of time and the low willingness to learn mathematics actively. The flipped classroom teaching mode under the guidance of cognitive load theory can reduce the internal and external cognitive load of students to a certain extent, improve the associated cognitive load of students, and improve the mathematics learning efficiency of junior middle school students within a limited time, which has a good role in promoting the educational effect of flipped classroom.
- 1 January 2024
- Published by Francis Academic Press Ltd. in International Journal of New Developments in Education
- Vol. 6 (9)
Open AccessAn analysis on the application of flipped classroom under cognitive load theory
With the continuous development of The Times, the combination of online and offline education model has become more and more important in practical teaching. Among them, flipped classroom can enable students to prepare lessons beforehand efficiently after class and discuss independently in class, which can enrich students' way of learning mathematics and can also enhance students' interest in mathematics learning. However, students in junior middle school are facing the problem of excessive cognitive load due to the difficulty of the subject, the lack of time and the low willingness to learn mathematics actively. The flipped classroom teaching mode under the guidance of cognitive load theory can reduce the internal and external cognitive load of students to a certain extent, improve the associated cognitive load of students, and improve the mathematics learning efficiency of junior middle school students within a limited time, which has a good role in promoting the educational effect of flipped classroom.
- Open Access
- 1 January 2024
- Published by Francis Academic Press Ltd. in International Journal of New Developments in Education
- Vol. 6 (2)
Evaluation methods for graduation requirements under the background of teacher education professional certification
The basic concept of teacher education professional certification is "students-centered, export-oriented, and continuous improvement". The evaluation of graduation requirements strictly controls the "export" of higher teacher education, which is a key link in teacher education professional certification. It is an important guarantee for deepening the reform of the evaluation system of higher teacher education and improving the training quality of normal students. Comprehensive and objective evaluation results provide important basis for continuous improvement of the teacher education professional training system. The evaluation of the graduation requirements for teacher education majors involves various aspects of training teacher education student, which is a closed-loop system, including evaluable and testable indicator systems, reliable evaluation criteria, reasonable evaluation methods, timely feedback, and continuous improvement.
- 1 January 2024
- Published by Francis Academic Press Ltd. in International Journal of New Developments in Education
- Vol. 6 (2)
Open AccessEvaluation methods for graduation requirements under the background of teacher education professional certification
The basic concept of teacher education professional certification is "students-centered, export-oriented, and continuous improvement". The evaluation of graduation requirements strictly controls the "export" of higher teacher education, which is a key link in teacher education professional certification. It is an important guarantee for deepening the reform of the evaluation system of higher teacher education and improving the training quality of normal students. Comprehensive and objective evaluation results provide important basis for continuous improvement of the teacher education professional training system. The evaluation of the graduation requirements for teacher education majors involves various aspects of training teacher education student, which is a closed-loop system, including evaluable and testable indicator systems, reliable evaluation criteria, reasonable evaluation methods, timely feedback, and continuous improvement.