Zhu Wang
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
Research Subjects
Zhu Wang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Qian Wang
College of Information Science and Engineering, China University of Petroleum, Beijing 102249, China
2 shared publications - Shaokang Zhang
Department of Electrical Instrument, Sinopec Shijiazhuang Refine & Chemical Company, Shijiazhuang 052160, China
2 shared publications Xionglin Luo
2 shared publications- Jia-Xuan Liu
PetroChina Company Limited
1 shared publication - Jiale Zhan
College of Information Science and Engineering, China University of Petroleum, Beijing 102249, China
1 shared publication - Jiale Zhan1 shared publication
Latest Publications
- Open Access
Branch Voting and Hierarchical Activation for Anomaly Inference in Refinery Units
Anomaly inference in refinery units is challenged by hierarchical propagation, branch interactions, and limited prior knowledge of node activation. This study proposes a branch voting and hierarchical activation method for refinery anomaly inference. Anomaly phenomenon nodes, anomaly cause nodes, and their connections are constructed from process mechanisms, field investigations, technical documents, and expert knowledge. A full test set is expanded from highly credible cases under process constraints, and a graded loss rule library is established according to the minimum evidence required for cause activation. During online inference, upstream nodes vote within each branch, and anomaly cause nodes are activated based on accumulated support and minimum activation values before propagating to deeper layers. A PSO Greedy algorithm is further developed to optimize connection weights and minimum activation values through global search and local refinement. Case studies show that the method preserves expert-specified activation logic and supports hierarchical inference from anomaly phenomena to deeper causes. Compared with conventional PSO, PSO Greedy achieves lower mean loss and a higher zero loss success rate.
Open AccessBranch Voting and Hierarchical Activation for Anomaly Inference in Refinery Units
Anomaly inference in refinery units is challenged by hierarchical propagation, branch interactions, and limited prior knowledge of node activation. This study proposes a branch voting and hierarchical activation method for refinery anomaly inference. Anomaly phenomenon nodes, anomaly cause nodes, and their connections are constructed from process mechanisms, field investigations, technical documents, and expert knowledge. A full test set is expanded from highly credible cases under process constraints, and a graded loss rule library is established according to the minimum evidence required for cause activation. During online inference, upstream nodes vote within each branch, and anomaly cause nodes are activated based on accumulated support and minimum activation values before propagating to deeper layers. A PSO Greedy algorithm is further developed to optimize connection weights and minimum activation values through global search and local refinement. Case studies show that the method preserves expert-specified activation logic and supports hierarchical inference from anomaly phenomena to deeper causes. Compared with conventional PSO, PSO Greedy achieves lower mean loss and a higher zero loss success rate.
- 22 April 2026
- Published by Wiley in The Canadian Journal of Chemical Engineering
- Vol. 104 (11) , 6177-6192
Melt flow index prediction for batch polypropylene based on temporal feature matching
Due to the delay in the laboratory results of the melt flow index (MFI) for polypropylene (PP) batch processes, production personnel are unable to observe MFI changes in a timely manner and guide the production of the next batch. To obtain the MFI values in a timely manner, a prediction method based on time‐series feature matching for MFI is proposed. First, the process mechanism is analyzed to determine the process variables affecting MFI, and the corresponding historical data is collected. Then, in the offline training phase, expert rules based on the process mechanism are constructed to extract historical batch data and integrate batch MFI values. Next, for the extracted long time‐series data, it is transformed into a spatiotemporal matrix, and singular value decomposition (SVD) is used to extract features. In the online prediction phase, considering the peak characteristics of hydrogenation times, a similarity calculation method using a pseudo‐4th‐order central moment (P4CM) is proposed. This is combined with Euclidean distance to compare the similarity between online and historical batches for prediction. Finally, a comparative experiment with Kernel principal component analysis (KPCA) is conducted, demonstrating the feasibility of the proposed prediction method.
- 22 April 2026
- Published by Wiley in The Canadian Journal of Chemical Engineering
- Vol. 104 (11) , 6177-6192
Melt flow index prediction for batch polypropylene based on temporal feature matching
Due to the delay in the laboratory results of the melt flow index (MFI) for polypropylene (PP) batch processes, production personnel are unable to observe MFI changes in a timely manner and guide the production of the next batch. To obtain the MFI values in a timely manner, a prediction method based on time‐series feature matching for MFI is proposed. First, the process mechanism is analyzed to determine the process variables affecting MFI, and the corresponding historical data is collected. Then, in the offline training phase, expert rules based on the process mechanism are constructed to extract historical batch data and integrate batch MFI values. Next, for the extracted long time‐series data, it is transformed into a spatiotemporal matrix, and singular value decomposition (SVD) is used to extract features. In the online prediction phase, considering the peak characteristics of hydrogenation times, a similarity calculation method using a pseudo‐4th‐order central moment (P4CM) is proposed. This is combined with Euclidean distance to compare the similarity between online and historical batches for prediction. Finally, a comparative experiment with Kernel principal component analysis (KPCA) is conducted, demonstrating the feasibility of the proposed prediction method.
- Open Access
Modeling and Evaluation of Attention Mechanism Neural Network Based on Industrial Time Series Data
Chemical process control systems are complex, and modeling the controlled object is the first task in automatic control and optimal design. Most chemical process modeling experiments require test signals to be applied to the process, which may lead to production interruptions or cause safety accidents. Therefore, this paper proposes an improved transformer model based on a self-attention mechanism for modeling industrial processes. Then, an evaluation mechanism based on root mean square error (RMSE) and Kullback–Leibler divergence (KLD) metrics is designed to obtain more appropriate model parameters. The Variational Auto-Encoder (VAE) network is used to compute the associated KLD. Finally, a real nonlinear dynamic process in the petrochemical industry is modeled and evaluated using the proposed methodology to predict the time series data of the process. This study demonstrates the validity of the proposed transformer model and illustrates the versatility of using an integrated modeling, evaluation, and prediction scheme for nonlinear dynamic processes in process industries. The scheme is of great importance for the field of industrial soft measurements as well as for deep learning-based time series prediction. In addition, the issue of a suitable time domain for the prediction is discussed.
Open AccessModeling and Evaluation of Attention Mechanism Neural Network Based on Industrial Time Series Data
Chemical process control systems are complex, and modeling the controlled object is the first task in automatic control and optimal design. Most chemical process modeling experiments require test signals to be applied to the process, which may lead to production interruptions or cause safety accidents. Therefore, this paper proposes an improved transformer model based on a self-attention mechanism for modeling industrial processes. Then, an evaluation mechanism based on root mean square error (RMSE) and Kullback–Leibler divergence (KLD) metrics is designed to obtain more appropriate model parameters. The Variational Auto-Encoder (VAE) network is used to compute the associated KLD. Finally, a real nonlinear dynamic process in the petrochemical industry is modeled and evaluated using the proposed methodology to predict the time series data of the process. This study demonstrates the validity of the proposed transformer model and illustrates the versatility of using an integrated modeling, evaluation, and prediction scheme for nonlinear dynamic processes in process industries. The scheme is of great importance for the field of industrial soft measurements as well as for deep learning-based time series prediction. In addition, the issue of a suitable time domain for the prediction is discussed.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2025 (1)
The Abnormal Diagnosis Method for Process Parameter Fluctuation Based on Power Spectral Density and Statistical Characteristics
In processes of refining and chemical productions, alarm systems are generally centralized alarm management systems for process parameters. However, in order to address the challenges of advanced manipulation and maintenance during emergencies, there has been limited research on timely alarming for individual critical process parameters. This paper proposes a method based on the combination of power spectral density and statistical characteristics, which can quickly and accurately diagnose large‐scale trend changes and short‐term nonstationary abnormal trends in process parameters. First, the method employs incremental data from historical records of critical process parameters for volatility analysis. Second, the historical data of critical process parameters are segmented into multiple appropriately sized datasets. We employ a combined analysis of power spectral density and statistical characteristics to extract features from multitude of incremental data. Meanwhile, we have designed a tuning scheme for critical frequencies and their threshold parameters, which can be used for testing and online diagnostics. Experimental validation is performed using actual critical process parameters data from Chinese refineries. The experimental results indicate that the method can detect large‐scale trends and short‐term nonstationary abnormal trends in process parameters, demonstrating good diagnostic performance.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 2025 (1)
Open AccessThe Abnormal Diagnosis Method for Process Parameter Fluctuation Based on Power Spectral Density and Statistical Characteristics
In processes of refining and chemical productions, alarm systems are generally centralized alarm management systems for process parameters. However, in order to address the challenges of advanced manipulation and maintenance during emergencies, there has been limited research on timely alarming for individual critical process parameters. This paper proposes a method based on the combination of power spectral density and statistical characteristics, which can quickly and accurately diagnose large‐scale trend changes and short‐term nonstationary abnormal trends in process parameters. First, the method employs incremental data from historical records of critical process parameters for volatility analysis. Second, the historical data of critical process parameters are segmented into multiple appropriately sized datasets. We employ a combined analysis of power spectral density and statistical characteristics to extract features from multitude of incremental data. Meanwhile, we have designed a tuning scheme for critical frequencies and their threshold parameters, which can be used for testing and online diagnostics. Experimental validation is performed using actual critical process parameters data from Chinese refineries. The experimental results indicate that the method can detect large‐scale trends and short‐term nonstationary abnormal trends in process parameters, demonstrating good diagnostic performance.
- Open Access
A Novel Nonlinear Filter-Based Robust Adaptive Control Method for a Class of Nonlinear Discrete-Time Systems
This paper introduces an innovative adaptive control approach utilizing a nonlinear filter for a specific subset of nonlinear discrete-time systems, considering the presence of both input and output noise. The system can be transformed into a nonlinear autoregressive moving average with exogenous inputs (NARMAX) model. The concept of discrete Nussbaum gain is introduced to address the theoretical constraint associated with unknown directions of feed-forward or control gains, and the extended adaptive tuning sequence is introduced to facilitate the acceleration of parameter updating. In the case of no noise, asymptotical output tracking and global stability are achieved with the adaptive control. Further, in the presence of input noise and output noise, a novel nonlinear filter is designed to generate a more accurate filtered output, which improves the control system’s ability to adapt and track accurately. Finally, examples are provided to showcase the effectiveness and precision of the method.
Open AccessA Novel Nonlinear Filter-Based Robust Adaptive Control Method for a Class of Nonlinear Discrete-Time Systems
This paper introduces an innovative adaptive control approach utilizing a nonlinear filter for a specific subset of nonlinear discrete-time systems, considering the presence of both input and output noise. The system can be transformed into a nonlinear autoregressive moving average with exogenous inputs (NARMAX) model. The concept of discrete Nussbaum gain is introduced to address the theoretical constraint associated with unknown directions of feed-forward or control gains, and the extended adaptive tuning sequence is introduced to facilitate the acceleration of parameter updating. In the case of no noise, asymptotical output tracking and global stability are achieved with the adaptive control. Further, in the presence of input noise and output noise, a novel nonlinear filter is designed to generate a more accurate filtered output, which improves the control system’s ability to adapt and track accurately. Finally, examples are provided to showcase the effectiveness and precision of the method.
- Open Access
An Expert System Based on Data Mining for a Trend Diagnosis of Process Parameters
In order to diagnose abnormal trends in the process parameters of industrial production, the Expert System based on rolling data Kernel Principal Component Analysis (ES-KPCA) and Support Vector Data Description (ES-SVDD) are proposed in this paper. The expert system is capable of identifying large-scale trend changes and abnormal fluctuations in process parameters using data mining techniques, subsequently triggering timely alarms. The system consists of a rule-based assessment of process parameter stability to evaluate whether the process parameters are stable. Also, when the parameters are unstable, the rolling data-based KPCA and SVDD methods are used to diagnose abnormal trends. ES-KPCA and ES-SVDD methods require adjusting seven threshold parameters during the offline parameter adjustment phase. The system obtains the adjusted parameters and performs a real-time diagnosis of process parameters based on the set diagnosis interval during the online diagnosis phase. The ES-KPCA and ES-SVDD methods emphasize the real-time alarms and the first alarm of process parameter abnormal trends, respectively. Finally, the system validates the experimental data from UniSim simulation and a chemical plant. The results show that the expert system has an outstanding diagnostic performance for abnormal trends in process parameters.
Open AccessAn Expert System Based on Data Mining for a Trend Diagnosis of Process Parameters
In order to diagnose abnormal trends in the process parameters of industrial production, the Expert System based on rolling data Kernel Principal Component Analysis (ES-KPCA) and Support Vector Data Description (ES-SVDD) are proposed in this paper. The expert system is capable of identifying large-scale trend changes and abnormal fluctuations in process parameters using data mining techniques, subsequently triggering timely alarms. The system consists of a rule-based assessment of process parameter stability to evaluate whether the process parameters are stable. Also, when the parameters are unstable, the rolling data-based KPCA and SVDD methods are used to diagnose abnormal trends. ES-KPCA and ES-SVDD methods require adjusting seven threshold parameters during the offline parameter adjustment phase. The system obtains the adjusted parameters and performs a real-time diagnosis of process parameters based on the set diagnosis interval during the online diagnosis phase. The ES-KPCA and ES-SVDD methods emphasize the real-time alarms and the first alarm of process parameter abnormal trends, respectively. Finally, the system validates the experimental data from UniSim simulation and a chemical plant. The results show that the expert system has an outstanding diagnostic performance for abnormal trends in process parameters.
- Open Access
An Adaptive-Noise-Bound-Based Set-Membership Method for Process Identification of Industrial Control Loops
Modeling of key variable data needs to consider the complex characteristics of systems in the catalytic cracking unit (CCU) of petroleum refining process, such as slow time-varying behavior, complex dynamic properties, distributed traits, and unknown stochastic noise. To fully capture the dynamics of a linear ordinary dynamic process without introducing incremental components, an adaptive-noise-bound-based set-membership method (RSMI) is proposed in this paper. Under the set-membership framework, the output set is typically represented as an ellipsoid based on the assumed conditions. Firstly, a CARMA model is considered; longer-duration historical data are selected to capture the intricate dynamic characteristics of industrial control loops. Secondly, RSMI introduces am approach to determine allowance factor, optimizing the noise bound for better suitability in real-world noise environments. The adaptive noise bound is achieved by designing an optimization algorithm that seeks the optimal parameters within the optimization framework. The stability of the RSMI algorithm is demonstrated through the application of the Lyapunov method. Next, the RSMI algorithm has been applied in engineering practice and designed for offline and online training stages of control processes. Finally, simulation experiments are performed to model and predict real-time data of flow, pressure, and liquid-level control loops within a catalytic cracking unit. Furthermore, the effectiveness of the RSMI algorithm is validated through two general examples, and frequency domain analysis is performed.
Open AccessAn Adaptive-Noise-Bound-Based Set-Membership Method for Process Identification of Industrial Control Loops
Modeling of key variable data needs to consider the complex characteristics of systems in the catalytic cracking unit (CCU) of petroleum refining process, such as slow time-varying behavior, complex dynamic properties, distributed traits, and unknown stochastic noise. To fully capture the dynamics of a linear ordinary dynamic process without introducing incremental components, an adaptive-noise-bound-based set-membership method (RSMI) is proposed in this paper. Under the set-membership framework, the output set is typically represented as an ellipsoid based on the assumed conditions. Firstly, a CARMA model is considered; longer-duration historical data are selected to capture the intricate dynamic characteristics of industrial control loops. Secondly, RSMI introduces am approach to determine allowance factor, optimizing the noise bound for better suitability in real-world noise environments. The adaptive noise bound is achieved by designing an optimization algorithm that seeks the optimal parameters within the optimization framework. The stability of the RSMI algorithm is demonstrated through the application of the Lyapunov method. Next, the RSMI algorithm has been applied in engineering practice and designed for offline and online training stages of control processes. Finally, simulation experiments are performed to model and predict real-time data of flow, pressure, and liquid-level control loops within a catalytic cracking unit. Furthermore, the effectiveness of the RSMI algorithm is validated through two general examples, and frequency domain analysis is performed.
- 6 May 2019
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 41 (14) , 3970-3978
Levy-particle swarm optimization intelligent search-based iterative identification for nonparametric models of bilinear systems with Gaussian mixture noises
Motivated by the fact that the model-based robust identification has not been studied extensively, a novel iterative identification method is proposed for the nonparametric model of bilinear systems with Gaussian mixture noises. The proposed method is robust to the impulsive disturbances, and combines intelligent search techniques with robust estimation theories. Firstly, the block-oriented Wiener-Hammerstein model is adopted to achieve the fast modeling, and the Levy-particle swarm optimization intelligent search is exploited for the parameter estimation. Secondly, according to re-descending M-estimators, the weighted cost function is designed to suppress the influence of outliers. Thirdly, based on the Levy-PSO intelligent search and the weighted cost function, the iterative identification procedure is conducted to obtain the robust and accurate parameter estimates. Finally, the simulation tests demonstrate the effectiveness of the proposed model and the proposed method.
- 6 May 2019
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 41 (14) , 3970-3978
Levy-particle swarm optimization intelligent search-based iterative identification for nonparametric models of bilinear systems with Gaussian mixture noises
Motivated by the fact that the model-based robust identification has not been studied extensively, a novel iterative identification method is proposed for the nonparametric model of bilinear systems with Gaussian mixture noises. The proposed method is robust to the impulsive disturbances, and combines intelligent search techniques with robust estimation theories. Firstly, the block-oriented Wiener-Hammerstein model is adopted to achieve the fast modeling, and the Levy-particle swarm optimization intelligent search is exploited for the parameter estimation. Secondly, according to re-descending M-estimators, the weighted cost function is designed to suppress the influence of outliers. Thirdly, based on the Levy-PSO intelligent search and the weighted cost function, the iterative identification procedure is conducted to obtain the robust and accurate parameter estimates. Finally, the simulation tests demonstrate the effectiveness of the proposed model and the proposed method.
- Open Access
- 1 July 2016
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 10 (5) , 549-556
Iteratively reweighted correlation analysis method for robust parameter identification of multiple‐input multiple‐output discrete‐time systems
In the engineering practices, the distributions of measurements are non‐Gaussian as they contain outliers. As some slight deviations from the Gaussian assumption would probably cause the performance of an estimator to degrade significantly, a novel iteratively reweighted correlation analysis method is proposed for robust parameter estimation of multiple‐input multiple‐output (MIMO) systems, in the presence of Student's t‐ noises. The iterative method achieves good robustness and high efficiency by the combination of multivariable correlation analysis and t‐ distribution based M‐ estimators. The appropriate updating weights are able to enter into the sample cross‐correlation function, so that the heavy tails are lowered, and the impact of outliers is weakened to the greatest extent. Based on the robust finite impulse response models, the identification procedure is then to reconstruct the noise‐free estimates to identify the parameters of an MIMO system. The theoretical discussions and simulation results demonstrate that the proposed method works well.
- 1 July 2016
- Published by Institution of Engineering and Technology (IET) in IET Signal Processing
- Vol. 10 (5) , 549-556
Open AccessIteratively reweighted correlation analysis method for robust parameter identification of multiple‐input multiple‐output discrete‐time systems
In the engineering practices, the distributions of measurements are non‐Gaussian as they contain outliers. As some slight deviations from the Gaussian assumption would probably cause the performance of an estimator to degrade significantly, a novel iteratively reweighted correlation analysis method is proposed for robust parameter estimation of multiple‐input multiple‐output (MIMO) systems, in the presence of Student's t‐ noises. The iterative method achieves good robustness and high efficiency by the combination of multivariable correlation analysis and t‐ distribution based M‐ estimators. The appropriate updating weights are able to enter into the sample cross‐correlation function, so that the heavy tails are lowered, and the impact of outliers is weakened to the greatest extent. Based on the robust finite impulse response models, the identification procedure is then to reconstruct the noise‐free estimates to identify the parameters of an MIMO system. The theoretical discussions and simulation results demonstrate that the proposed method works well.