Finite Gaussian Mixture Model Based Multimodeling for Nonlinear Distributed Parameter Systems

Xu, Kangkang; Yang, Haidong; Zhu, Chengjiu; Hu, Lei

doi:10.1109/tii.2019.2923917

Cited by 16 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To enhance the modelling capability, a spatial‐temporal multi‐modelling method is required to obtain a global model in a large operating range. Recently, methods of multi‐modelling, such as the finite gaussian mixture model [43], the membership functions [44] and the collocation method [45], are usually adopted to describe spatio‐temporal dynamics of DPS. Based on the spatio‐temporal multi‐modelling methodology, the spatial distribution of the strip temperature can be obtained by constructing the functional relationship between the reference point and the state in the subspace.…”

Section: Spatio‐temporal Modelling For Laminar Cooling Processmentioning

confidence: 99%

Integrated spatio‐temporal process monitoring and fault spatial location for the laminar cooling of hot‐rolled strip steel

Wang

Peng

2023

IET Control Theory & Appl

View full text Add to dashboard Cite

Laminar cooling process is crucial for the production and the quality of the strip steel in the hot‐rolled strip steel. Abnormalities or faults influence the temperature distributions in the direction of the length and the thickness, which determine the mechanical and physical performance of the strip steel. Considering that the spatial distribution of the strip temperature is hardly measured, the distributed parameter model can be constructed to deal with the problem of the abnormality detection and location. In this paper, a process monitoring and fault spatial location method with spatio‐temporal integration is proposed for the laminar cooling. First, a spatio‐temporal model is constructed by multi‐modelling method to monitor the spatial distribution of the strip temperature, and the dimension of the local thermodynamic model is reduced by time‐space separation. Then, a residual generator is provided for fault detection in the data‐driven realization, and the statistic and the threshold are formed to evaluate it. Next, the spatial location of the fault can be identified by reconstruction based contribution method. Finally, an experiment is conducted to demonstrate the practical application effects by a real laminar cooling process data.

show abstract

Section: Spatio‐temporal Modelling For Laminar Cooling Processmentioning

confidence: 99%

Integrated spatio‐temporal process monitoring and fault spatial location for the laminar cooling of hot‐rolled strip steel

Wang

Peng

2023

IET Control Theory & Appl

View full text Add to dashboard Cite

show abstract

“…To enhance the modeling capability, spatial integration with the multi-modeling method is required to obtain a global model with a scheduling weight function at a large operating range [34]. Some studies in multi-modeling of DPSs are available in the literature, such as membership functions [35], finite Gaussian mixture models [36], kernel models [37], and collocation methods [38]. The membership function method can realize the smooth transition of the subspace and system identification of the working conditions.…”

Section: Global Modeling For Laminar Cooling Processmentioning

confidence: 99%

Modeling and Monitoring for Laminar Cooling Process of Hot Steel Strip Rolling with Time–Space Nature

2022

View full text Add to dashboard Cite

The laminar cooling process is an important procedure in hot steel strip rolling. The spatial distribution and the drop curve of the strip temperature are crucial for the production and the quality of the steel strip. Traditionally, lumped parameter methods are often used for the modeling of the laminar cooling process, making it difficult to consider the impact of the variation of state variables and related parameters on the system, which seriously affect the stability of the steel strip quality. In this paper, a modeling and monitoring method with a time–space nature for the laminar cooling process is proposed to monitor the spatial variation of the strip temperature. Firstly, the finite-dimensional model is obtained by time–space separation to describe the temperature variation of the steel strip. Next, a global model is constructed by using the multi-modeling integration method. Then, a residual generator is designed to monitor the strip temperature where the statistics and the threshold are calculated. Finally, the superiority and reliability of the proposed method are verified by the actual-process data of the laminar cooling process for hot steel strip rolling, and different types of faults are detected successfully.

show abstract

“…Lu et al adopted a least-squares support vector machine (LS-SVM) to model nonlinear time dynamics successfully and applied this spatiotemporal method on a practical curing thermal process [27]. Xu et al proposed a spatiotemporal model which integrated the finite Gaussian mixture model (FGMM) with principal component regression (PCR) for complex nonlinear DPSs, and this model showed strong ability to track and handle the complex nonlinear dynamics [28]. However, all the aforementioned temporal models do not consider the intrinsic structure of low-order models.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Modeling for Nonlinear Distributed Thermal Processes Based on KL Decomposition, MLP and LSTM Network

Yang

et al. 2020

IEEE Access

Self Cite

159

View full text Add to dashboard Cite

Estimation of absolute temperature distributions is crucial for many thermal processes in the nonlinear distributed parameter systems, such as predicting the curing temperature distribution of the chip, the temperature distribution of the catalytic rod, and so on. In this work, a spatiotemporal model based on the Karhunen-Loève (KL) decomposition, the multilayer perceptron (MLP), and the long short-term memory (LSTM) network, named KL-MLP-LSTM, is developed for estimating temperature distributions with a three-step procedure. Firstly, the infinite-dimensional model is transformed into a finitedimensional model, where the KL decomposition method is used for dimension reduction and spatial basis functions extraction. Secondly, a novel MLP-LSTM hybrid time series model is constructed to deal with the two inherently coupled nonlinearities. Finally, the spatiotemporal temperature distribution model can be reconstructed through spatiotemporal synthesis. The effectiveness of the proposed model is validated by the data from a snap curing oven thermal process. Satisfactory agreement between the results of the current model and the other well-established model shows that the KL-MLP-LSTM model is reliable for estimating the temperature distributions during the thermal process. INDEX TERMS Spatiotemporal modeling, nonlinear distributed thermal processes, Karhunen-Loève decomposition, multilayer perceptron, long short-term memory.

show abstract

Finite Gaussian Mixture Model Based Multimodeling for Nonlinear Distributed Parameter Systems

Cited by 16 publications

References 37 publications

Integrated spatio‐temporal process monitoring and fault spatial location for the laminar cooling of hot‐rolled strip steel

Integrated spatio‐temporal process monitoring and fault spatial location for the laminar cooling of hot‐rolled strip steel

Modeling and Monitoring for Laminar Cooling Process of Hot Steel Strip Rolling with Time–Space Nature

Spatiotemporal Modeling for Nonlinear Distributed Thermal Processes Based on KL Decomposition, MLP and LSTM Network

Contact Info

Product

Resources

About