Weimin Huang

Weimin Huang

Auto-generated profile, based on publicly available information

Weimin Huang

School of Information Science and Technology, Beijing University of Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
12 September 2023 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
WHWeimin Huang
Weimin Huang
HDHaixu Ding
Haixu Ding
JQJunfei Qiao
Junfei Qiao
Municipal solid waste incineration (MSWI) process is a complex industrial process with strong nonlinearity. It is a challenge to build a model for the MSWI process and carry out the corresponding optimization works. To solve this problem, the multiobjective optimization studies are conducted for both modeling and concerned indexes of the MSWI process, including the nitrogen oxides (NOx) emissions and the combustion efficiency (CE). First, a data-driven-based multiple-input multiple-output model is established for the NOx emissions and the CE of the MSWI process based on Takagi–Sugeno–Kang fuzzy neural network. Second, an adaptive large-scale multiobjective competitive swarm optimization (ALMOCSO) algorithm is designed for solving the multiobjective optimization problems (MOPs) of the MSWI process. A comprehensive evaluation system is proposed to complete the optimization foundation, and an adaptive scheme and multistrategy learning are proposed to improve the optimization effect of the ALMOCSO algorithm in solving complex MOPs. Then, a Pareto optimal set obtained from massive historical data is utilized as optimization reference to realize the dynamic multiobjective optimization for the NOx emissions and the CE of the MSWI process. Finally, the feasibility and effectiveness of the proposed methodology for optimizing the MSWI process are confirmed by the experiments using the data collected from a real MSWI plant. The results indicate that the modeling accuracy is satisfactory, and the CE is improved over 10% and the reduction of the NOx emissions is achieved 15.58%.

3 April 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
HDHaixu Ding
Haixu Ding
JQJunfei Qiao
Junfei Qiao
WHWeimin Huang
Weimin Huang
TYTao Yu
Tao Yu
Municipal solid waste incineration (MSWI) is an industrial process with multiple mechanism reactions, which has strong coupling and time-varying dynamics. It is extremely difficult to design a feasible multivariable controller for MSWI process due to the complex composition of municipal solid waste and fluctuation of calorific value. To solve these problems, a cooperative event-triggered fuzzy-neural multivariable controller with multitask learning (CETFNMC-MTL) is proposed to realize the adaptive multivariable control of MSWI process. First, a fuzzy-neural multivariable controller is established to control furnace temperature and oxygen content synchronously. Second, a dynamic self-organizing mechanism based on multitask learning is designed, which splits and merges neurons by calculating the dynamic time warping distance and cumulative contribution of neurons in the continuous time. Third, a cooperative event-triggered mechanism is introduced to improve controller update efficiency while reducing mechanical wear and computational burden. Then, the stability of parameters learning and structure self-organizing process is analyzed to guarantee the successful application of CETFNMC-MTL. Finally, the effectiveness of the controller is tested with process data from an MSWI plant in Beijing, China. The results show that the proposed CETFNMC-MTL has adaptive learning ability, while reducing energy consumption and improving control accuracy.

2 August 2023 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
HDHaixu Ding
Haixu Ding
JQJunfei Qiao
Junfei Qiao
WHWeimin Huang
Weimin Huang
TYTao Yu
Tao Yu
Affected by high temperature and serious pollution, some key parameters in incinerator are difficult to obtain directly, and the detectable data also contain outliers and noise, which makes it extremely difficult to mine the relationship between variables and derive control rules. To solve these problems, an event-triggered online learning fuzzy-neural robust controller is proposed and applied to the furnace temperature control of municipal solid waste incineration (MSWI) process. First, the outliers are eliminated by the box-plot method, and the data is denoised with a Gaussian filter. Second, the controlled object model based on T-S fuzzy neural network is constructed by data-driven method. Third, an online learning fuzzy neural controller is designed to be imposed on the established controlled object model, which adaptively adjusts the network structure by calculating the information transmission strength of the rule neurons. Meanwhile, an event-triggered mechanism is introduced to reduce actuator wear and save energy while maintaining control effectiveness. Then, the convergence of the controller is deduced by Lyapunov’s second law. Finally, the validity of the proposed method is verified by process data from a real MSWI plant in Beijing, China. The results show that the method proposed in this paper can build the furnace temperature model from imperfect data, and the controller can grow and prune neurons autonomously, which improves the control accuracy and efficiency of the furnace temperature under external disturbances. Note to Practitioners —Municipal solid waste (MSW) has complex and variable components, and its incineration process relies on manual operations. However, manual operations have hysteresis and subjectivity, which will increase the workload of workers and also cause problems such as unstable incineration. Furnace temperature is the main controlled variable of MSWI process, which is closely related to MSW burnout rate and pollutant emission concentration. Therefore, an event-triggered online leaning fuzzy-neural robust controller is designed in this paper, which can keep the furnace temperature stable by automatically adjusting the primary air volume and drying grate speed under external disturbances. In addition, the controller can adjust its structure adaptively according to different operating conditions, and it is equipped with an event-triggered mechanism to meet the control requirements while reducing the frequency of controller updates, which improves equipment life and reduces energy consumption. Finally, the controller is validated by the process data of a real MSWI plant.

1 August 2012
Verified
Conference Paper
Closed access
WHW. Huang
W. Huang
ZTZ. M. Tan
Z. M. Tan
ZLZhiping Lin
Zhiping Lin
GHG.-B. Huang
G.-B. Huang
JZJinyun Zhou
Jinyun Zhou
Shu-Chun ChangShu-Chun Chang
Shu-Chun Chang
This paper presents a semi-automatic approach to segmentation of liver parenchyma from 3D computed tomography (CT) images. Specifically, liver segmentation is formalized as a pattern recognition problem, where a given voxel is to be assigned a correct label - either in a liver or a non-liver class. Each voxel is associated with a feature vector that describes image textures. Based on the generated features, an Extreme Learning Machine (ELM) classifier is employed to perform the voxel classification. Since preliminary voxel segmentation tends to be less accurate at the boundary, and there are other non-liver tissue voxels with similar texture characteristics as liver parenchyma, morphological smoothing and 3D level set refinement are applied to enhance the accuracy of segmentation. Our approach is validated on a set of CT data. The experiment shows that the proposed approach with ELM has the reasonably good performance for liver parenchyma segmentation. It demonstrates a comparable result in accuracy of classification but with a much faster training and classification speed compared with support vector machine (SVM).

2 June 2025 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
WHWeimin Huang
Weimin Huang
XMXi Meng
Xi Meng
JQJunfei Qiao
Junfei Qiao
Municipal solid waste incineration (MSWI) process is a complex industrial process characterized by multiple subsystems, inherent nonlinearities, and stochastic and time-varying dynamic behaviors, posing significant challenges for operational optimization. It is the first time to report an attempt toward tackling the operational optimization with multi-time-scale for the MSWI process. First, a cooperative dynamic optimization scheme is developed to achieve operational optimization of multiple subsystems by the integration of two-level optimizations, characterized by performance indices and time scales. Second, a two-layer multiobjective competitive swarm optimization algorithm, comprising stochastic learning mode and explosive learning mode, is proposed to improve both global exploration and local exploitation abilities and simultaneously to handle the constraints. Moreover, a novel dynamic response strategy, typically designed based on the relationship between data-driven surrogate models and optimal Pareto solutions, is proposed to address the stochastic changes of environment. Finally, the proposed method is deployed and validated in a real MSWI plant, and the simulation results further demonstrate that the proposed algorithm achieves superior performance, specifically with the nitrogen oxides (NOx), SO2, and HCl emissions reduced by 12.72%, 22.81%, and 15.97%, respectively, the main steam flow and its stability improved by 5.25% and 59.62%, respectively, and the usages of urea solution and limestone slurry decreased by 17.23%and 11.74%, respectively.

28 July 2025 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
JQJunfei Qiao
Junfei Qiao
WHWeimin Huang
Weimin Huang
XMXi Meng
Xi Meng
Simultaneous optimization of both pollutant emissions and power generation holds significant importance for the municipal solid waste incineration (MSWI) process. Nevertheless, the inherent uncertainty and time-varying dynamics of the MSWI process induce the optimization problem into a complicated dynamic multiobjective optimization problem (DMOP) with stochastic changes, challenging the acquisition of optimal set-points. To address this problem, a novel data-driven dynamic multiobjective optimization scheme is proposed with response to stochastic changes. First, surrogate models for performance indices are established using fuzzy neural networks, assisted with an online learning method developed by an adaptive Levenberg-Marquardt algorithm to ensure model applicability. Second, an adaptive multiobjective triple competitive swarm optimization algorithm is proposed specifically designed for the DMOP of the MSWI process, incorporating comprehensive triple competition and a multi-mode learning strategy to effectively balance global exploration and local exploitation. Furthermore, in response to the stochastic changes of optimization environment, a stochastic dynamic response strategy is designed to establish dynamic mapping relationships for Pareto optimal solutions, thereby enhancing optimization efficiency in evolving environments. Finally, experimental validation using operational data from a real-world MSWI plant demonstrates the effectiveness of the proposed method, with comparative studies confirming its superior performance.