公开(公告)号：US11488071B2

公开(公告)日：2022-11-01

申请号：US16837428

申请日：2020-04-01

申请人： Jiangnan University

发明人： Weili Xiong ,  Xudong Shi ,  Bingbin Gu ,  Xiaoqing Che ,  Xiaochen Sheng

IPC分类号： G06N20/20 ,  G06F17/16

摘要： The present disclosure provides a novel advanced ensemble learning strategy for soft sensor development with semi-supervised model. The main target of the soft sensor is to improve the prediction performance with a limited number of labeled data samples, under the ensemble learning framework. Firstly, in order to improve the prediction accuracy of sub-models for ensemble modeling, a novel sample selection mechanism is established to select the most significantly estimated data samples. Secondly, the Bagging method is employed to both of the labeled and selected data-set, and the two different kinds of datasets are matched based on the Dissimilarity (DISSIM) algorithm. As a result, the proposed method guarantees the diversity and accuracy of the sub-models which are two significant issues of the ensemble learning. In this work, the soft sensor is constructed upon the Gaussian Process Regression (GPR) model.

公开(公告)号：US11164095B2

公开(公告)日：2021-11-02

申请号：US16710710

申请日：2019-12-11

申请人： Jiangnan University

发明人： Weili Xiong ,  Yanjun Li ,  Mingchen Xue

IPC分类号： G06N5/04

摘要： The invention provides a fuzzy curve analysis based soft sensor modeling method using time difference Gaussian process regression, it is suitable for application in chemical process with time delay characteristics. This method can extract stable delay information from the historical database of process and introduce more relevant modeling data sequence to the dominant variable sequence. First of all, the method of fuzzy curve analysis (FCA) can intuitively judge the importance of the input sequence to the output sequence, estimate the time-delay parameters of process, and such offline time-delay parameter set can be utilized to restructure the modeling data. For the new input data, based on the historical variable value before a certain time, the current dominant value can be predicted by time difference Gaussian Process Regression (TDGPR) model. This method does not encounter the problem of model updating and can effectively track the drift between input and output data. Compared with steady-state modeling methods, this invention can achieve more accurate predictions of the key variable, thus improving product quality and reducing production costs.

公开(公告)号：US20170061305A1

公开(公告)日：2017-03-02

申请号：US15174389

申请日：2016-06-06

申请人： Jiangnan University

发明人： Weili Xiong ,  Yanjun Li ,  Mingchen Xue

IPC分类号： G06N5/04 ,  G06N5/02

CPC分类号： G06N5/048

摘要： The invention provides a fuzzy curve analysis based soft sensor modeling method using time difference Gaussian process regression, it is suitable for application in chemical process with time delay characteristics. This method can extract stable delay information from the historical database of process and introduce more relevant modeling data sequence to the dominant variable sequence. First of all, the method of fuzzy curve analysis (FCA) can intuitively judge the importance of the input sequence to the output sequence, estimate the time-delay parameters of process, and such offline time-delay parameter set can be utilized to restructure the modeling data. For the new input data, based on the historical variable value before a certain time, the current dominant value can be predicted by time difference Gaussian Process Regression (TDGPR) model. This method does not encounter the problem of model updating and can effectively track the drift between input and output data. Compared with steady-state modeling methods, this invention can achieve more accurate predictions of the key variable, thus improving product quality and reducing production costs.

摘要翻译： 本发明提供了一种使用时差高斯过程回归的基于模糊曲线分析的软传感器建模方法，适用于具有延时特性的化学过程。 该方法可以从过程的历史数据库中提取稳定的延迟信息，并将更多相关的建模数据序列引入到主要变量序列中。 首先，模糊曲线分析（FCA）的方法可以直观地判断输入序列对输出序列的重要性，估计过程的延时参数，可以利用这种离线时间延迟参数集来重组 建模数据。 对于新输入数据，基于一定时间之前的历史变量值，可以通过时差高斯过程回归（TDGPR）模型预测当前的主导值。 该方法不会遇到模型更新的问题，可以有效地跟踪输入和输出数据之间的漂移。 与稳态建模方法相比，本发明可以更准确地预测关键变量，从而提高产品质量，降低生产成本。