A Sliding Window Based Dynamic Spatiotemporal Modeling for Distributed Parameter Systems With Time-Dependent Boundary Conditions

Many industrial thermal processes are large-scale time-varying nonlinear distributed parameter systems (DPSs). To effectively model such systems, dual extreme learning machine based online spatiotemporal modeling with adaptive forgetting factor (AFFD-ELM) is proposed in this paper. This method can recursively update the parameters of the low-order temporal model by using newly arriving data under Karhunen-Loè ve (KL) based space/time separation. In this way, the time-varying dynamics can be tracked real-time very well as output data increases over time. Besides, since the training samples are usually timeliness, adaptive forgetting factor (AFF) is also embedded in this method to improve the online learning effects by adding a reasonable weight to previous data. This online learning strategy makes the process promising for online modeling under continuously samples environment. The proposed method is utilized for online temperature prediction of the curing oven. Simulation results verify the efficiency and viability of the online spatiotemporal model.

Section: A Modeling Frameworkmentioning

confidence: 99%

“…There are many spatiotemporal modeling methods researched in recent years [13]- [16]. Among them, space/time separation-based modeling methods have been widely used and proven viable and practical to model DPSs.…”

Section: Introductionmentioning

confidence: 99%

Dual Extreme Learning Machine Based Online Spatiotemporal Modeling With Adaptive Forgetting Factor

Xu¹,

Tan²,

Fan³

et al. 2021

“…Although SOC estimation results can be obtained, the number of input vectors of LSSVM may also affect the estimation results. Therefore, a sliding window method [27][28][29] is firstly applied to update input vectors of LSSVM model to improve the estimation accuracy of SOC.…”

Section: A the Soc Estimation Of The Lssvm Model Based On A Single Fmentioning

confidence: 99%

A Novel State of Charge Approach of Lithium Ion Battery Using Least Squares Support Vector Machine

Min

Wei

et al. 2020

Lithium-ion batteries(LIBs) have been used in electric vehicles(EVs) because of its high energy density and no pollution. As one of the important parameters of battery management system(BMS), accurately estimating the state-of-charge (SOC) can ensure the energy distribution and safe use of the battery. Therefore, in order to obtain accurate SOC estimation，this paper improves the estimation accuracy of SOC from four aspects. Firstly, to overcome the dependence of the model on the internal parameters of the battery, this paper uses the least squares support vector machine (LSSVM) to establish the battery model. The current, voltage, temperature are used as input vectors to estimate the SOC. Besides, the parameters of LSSVM are determined by a grey wolf optimizer(GWO). The GWO can improve the ability of LSSVM model by finding the global optimal solution. Thirdly, in order to improve the estimation accuracy of SOC, a novel LSSVM model based on the sliding window is proposed. The SOC estimated at the previous time, together with voltage, current and temperature measured at the current time are selected as the input vectors by sliding window method to improve the SOC accuracy. Finally, the effectiveness of the proposed model is verified under different driving conditions at different temperatures by comparing with other estimators. The comparison results indicate that the SOC estimation error(MAE) can be controlled within 1%, the root mean square error (RMSE) decreases from 0.89% to 0.22%, which are verified the effectiveness and robustness of the model. INDEX TERMS Lithium-ion batteries(LIBs); electric vehicles(EVs); state-of-charge (SOC); sliding window method; least-squares-support-vector-machine (LSSVM); grey wolf optimizer(GWO)

“…TE process is a widely used benchmark process in the field of industrial control and monitoring [43]. The whole process consists of five major units.…”

Section: B Case Study On Te Processmentioning

confidence: 99%

STA-APSNFIS: STA-Optimized Adaptive Pre-Sparse Neuro-Fuzzy Inference System for Online Soft Sensor Modeling

Liu

Jiang

et al. 2020

In complex industrial processes (CIPs), due to technical and economic limitations, key performance indicators (KPIs), especially the chemical content-related KPIs, are often difficult to measure in real time, which hinders the propagation of advanced process control technologies. This paper presents a soft sensor-based online KPI inference scheme by a state transition algorithm (STA)-optimized adaptive pre-sparse neuro-fuzzy inference system model, called STA-APSNFIS. It introduces a pre-sparse neural network to the traditional adaptive neuro-fuzzy inference system (ANFIS) model to establish an adaptive pre-sparse neuro-fuzzy inference system (APSNFIS) model to alleviate the adverse effects of data redundancy and noise interference in the detectable process monitoring data, which can effectively reduce the complexity of neuro-fuzzy inference system (NFIS) and speed up its convergence. Successively, to avoid being trapped at a local optimum, the STA-based optimization algorithm is adopted to replace the traditional gradient-based optimization approach to achieve an optimal APSNFIS model. Extensive validation and comparative experiments on nonlinear numeric simulation systems, benchmark Tenessee Eastman (TE) process and a real industrial bauxite flotation process demonstrated that the proposed STA-APSNFIS performed favorably against traditional ANFIS model as well as its variants, e.g., PSO-ANFIS, GA-ANFIS, and some other soft sensor-based KPI inference models.