Search

Data-driven soft sensor technology has been widely used in process monitoring, quality prediction, etc. However, there are dynamic time-varying and concept drift problems in industrial processes, making the accurate modeling of the soft sensor is still a challenging task. To solve the above problems, this paper proposes a concept drift adaptive dynamic partial least squares method. The method maps high-dimensional process data into a low-dimensional latent variable subspace. Dynamic information is introduced by establishing the dynamic regression relationship between process latent variables and quality latent variables. At the same time, transfer learning is used to align second-order statistics between latent variables of data from different distributions to solve the concept drift problem. The experiments on multiple industrial datasets show that the method proposed in this paper can effectively reduce prediction errors and improve the generalization ability of the model. [Display omitted] • Distribution alignment and dynamic system modeling are realized under NIPALS. • The objective function is organized into the form of Rayleigh quotient. • There are few hyperparameters and they have better interpretability. • Experiments show that our method can adapt to the change of data distribution well. [ABSTRACT FROM AUTHOR]

The traditional soft sensor models are based on the independent and identical distribution assumption, which are difficult to adapt to changes in data distribution under multiple operating conditions, resulting in model performance deterioration. The domain adaptive transfer learning methods learn knowledge in different domains by means of distribution alignment, which can reduce the impact of data distribution differences, and effectively improve the generalization ability of the model. However, most of the existing models established by domain adaptation methods are static models, which cannot reflect the dynamic characteristics of the system, and have limited prediction accuracy when applied to dynamic system modeling under multiple operating conditions. The dynamic system modeling methods can effectively extract the dynamic characteristics of the data, but they cannot deal with the concept drift problem caused by the change of data distribution. This paper proposes a new dynamic transfer partial least squares method, which maps the high-dimensional process data into the low-dimensional latent variable subspace, establishes the dynamic regression relationship between the latent variables and the labels, and realizes the systematic dynamic modeling, at the same time, the model adds regular terms for distribution alignment and structure preservation, which realizes dynamic alignment of data distribution difference. The effectiveness of the proposed method is validated on three publicly available industrial process datasets. [Display omitted] • This paper proposes a novel dynamic transfer partial least squares algorithm (DTPLS). • DTPLS can solve the concept drift problem under the multiple working conditions. • Distribution alignment regularization is designed based on distribution differences. • Structure preservation regularization is designed based on smoothness assumptions. [ABSTRACT FROM AUTHOR]

In order to deal with the unknown data drift problem caused by the change of working conditions in the process of industrial soft sensor modeling, this paper proposes a semi-supervised soft sensor modeling algorithm based on instance transfer learning, named instance transfer partial least squares. Under the framework of nonlinear partial least squares, the algorithm introduces the instance transfer inner model, and realizes the distribution adaptation of the modeling data and the data to be predicted through sample importance weighting. First, a nonlinear partial least squares model is constructed by using labeled samples in the source domain, which consists of a linear outer model and a nonlinear inner model. The linear outer model maps the original data to the hidden variable space, and the nonlinear inner model realizes the nonlinear modeling of hidden variables through kernel ridge regression. Second, a small number of labeled samples from the target domain are used to update the model weights of the nonlinear inner model, enabling adaptation of the latent variable distribution. The effectiveness of the algorithm is verified on a toy dataset, a simulation dataset and a real pulverized coal power plant dataset. • A new instance transfer soft sensor method is proposed to solve data drift problem. • The method aligns the data distribution of latent variable while nonlinear modeling. • The algorithm uses sample importance weighting to achieve distribution alignment. • The algorithm is suitable for multiple working conditions and few-sample scenarios. [ABSTRACT FROM AUTHOR]

Soft sensor technology has found widespread application in the real-time detection of challenging variables like product quality and key process parameters. However, changes in working conditions can lead to alterations in data distribution, resulting in model inaccuracies. Furthermore, data from new working conditions arrive sequentially and online. Due to technical difficulties, time-consuming measurements, and high costs, there is often a lack of sufficient new data for modeling in the initial phase. Moreover, industrial processes often exhibit dynamic, nonlinear, variable coupling and other factors, posing significant challenges for model establishment. To address these challenges, this study proposed an online transfer kernel recursive algorithm for soft sensor modeling under changing working conditions. The algorithm consists of an offline phase and an online phase. In the offline phase, the algorithm considers the dynamic features of the process and variable coupling, resulting in the establishment of a dynamic inner model. The original data is then projected onto a latent variable space. In the online phase, the proposed method incorporates the concept of online transfer learning and takes into account the nonlinearity of the process. This allows for the establishment of a kernel online recursive method in the latent variable space, integrating parameter transfer and sample transfer. Experimental results conducted on multiple industrial datasets validate the effectiveness of the proposed approach. [Display omitted] • Online transfer learning enables real-time updates with single samples. • A forgetting mechanism gradually weakens old knowledge as new data arrives. • KDiPLS with unified goals for inner model, outer model, and deflation process. [ABSTRACT FROM AUTHOR]