11 July 2025 in IEEE Transactions on Power Electronics
Achieving a balance between accuracy and complexity remains a significant challenge for lithium batteries. The accuracy of the model is usually positively correlated with the complexity of the model. A simple model cannot capture more influencing factors, as simpler models often fail to capture the full range of influencing factors. This article presents an enhanced battery model that extends the traditional equivalent circuit model (ECM) by integrating a set of exogenous independent parameters, encompassing both internal and external battery characteristics, into the system matrix via a polynomial relationship. This results in a time-varying system matrix that allows for a comprehensive representation of battery parameters and effective data fusion while simplifying the model. The model also addresses aging and other time-varying phenomena through time-varying exogenous functions, thus simplifying the management of aging effects. Recursive least squares algorithms with an adaptive forgetting factor handle time-varying parameters and aging effects, ensuring rapid adaptation to data changes while preserving high performance and accuracy. Through simulation and aging battery experiments, the mean absolute error and root mean square error of the proposed scheme can be controlled within 13.6 and 16.0 mV, which proves its accuracy and superiority, and has great potential in aging battery applications.
28 January 2025 in Journal of Alloys and Compounds
1 May 2023 in IEEE Transactions on Instrumentation and Measurement
For using the infrared spectroscopy to conduct in-situ measurement of slurry component concentrations during batch crystallization or fermentation process in engineering practice, a novel just-in-time learning (JITL) based functional modelling method is proposed for spectral data analysis in this paper to improve on-line measurement accuracy, by addressing engineering issues of very limited assay samples, spectral absorption nonlinearity and high-dimensional spectral variables. The traditional univariate or multivariate partial least-squares (PLS) model is subtly extended to the corresponding functional form for describing the relationship between the measured spectra and slurry component concentrations, such that the salient problem of only a small number of slurry component concentration samples available in practice for spectral data modeling could be effectively solved. The wavelet functions are adopted to properly approximate the measured spectral curves owing to their multi-scale and orthogonal properties. Accordingly, a functional spectral data model is established by wavelet functional PLS for on-line measurement of single and multiple component concentrations, respectively. Meanwhile, a JITL strategy is introduced to select the most representative samples for such modeling, which could efficiently handle the disparity issue involved with real-time samples and guarantee the model validity. Experimental results show that root mean square error of model prediction on the solution concentration during L-glutamic acid cooling crystallization process and multiple componts of ethanol fermentation process, could be evidently reduced over 40% and 50%, respectively, compared with the traditional PLS and support vector regression methods.
1 May 2021 in Chemometrics and Intelligent Laboratory Systems
21 May 2025 in IEEE Transactions on Instrumentation and Measurement
The accurate measurement and monitoring of quality variables are crucial for optimizing productivity and efficiency in industrial processes. However, many existing data-driven methods fail to account for the dynamic nature of industrial data and the nonuniform distributions that arise due to fluctuating operational conditions. To address these challenges, attention-based dynamic latent variable models are proposed. This approach comprehensively considers time-variant relationships among latent variables using attention mechanisms for both samples and variables. An interactive iterative algorithm is introduced to compute model parameters efficiently. Experimental validation, conducted through both numerical simulations and real-world applications in an industrial ethylene oxychlorination process, demonstrates the effectiveness of the proposed approach in enhancing process modeling and prediction performance. Comparison results show that the fault detection rate (FDR) of the proposed attention-based methods is significantly higher than that of traditional approaches. The proposed bi-attention partial least squares (PLSs) achieves the highest FDR rate of 0.94 based on the squared prediction error (SPE) statistic in the application of industrial application.