Soft sensor modelling by time difference, recursive partial least squares and adaptive model updating

Fu, Yuxi; Yang, Wuqiang; Xu, Ouguan; Zhou, Lian; Wang, J

doi:10.1088/1361-6501/aa57e2

Cited by 14 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former is commonly based on the first principle model but hard to be extensively used on account of its complicated processes and unquantifiable parametric relationships. The most popular modeling techniques for data-driven soft sensors include principal component regression (PCR) [12,13], partial least squares (PLS) [14,15], artificial neural networks (ANN) [16,17] and support vector machines (SVM) [18,19]. Wang et al [20] integrated random forest with Bayesian optimization to predict and maintain product quality and validated model superiorities through semiconductor production line data.…”

Section: Quality Control In Process Industriesmentioning

confidence: 99%

A digital twin–driven method for online quality control in process industry

Zhu

2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

To ensure the stability of product quality and production continuity, quality control is drawing increasing attention from the process industry. However, current methods cannot meet requirements with regard to time series data, high coupling parameters, delayed data acquisition and ambiguous operation control. A digital twin-driven (DTD) method for real-time monitoring, evaluation and optimization of process parameters that are strongly related to product quality is proposed. Based on a process simulation model, production status information and quality related data are obtained. Combined with an improved genetic algorithm (GA), a time sequential prediction model of bidirectional gated recurrent unit (bi-GRU) with attention mechanism (AM) is built to flexibly allocate parameter weights, accurately predict product quality, timely evaluate technical process and rapidly generate optimized control plans. A typical case study and relevant filed tests from the process industry are presented to prove the effectiveness of the method. Results indicate that the proposed method clearly outperforms its competitors.

show abstract

Section: Quality Control In Process Industriesmentioning

confidence: 99%

A digital twin–driven method for online quality control in process industry

Zhu

2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…The time difference modelling approach is based on the difference of an output variable in two moments in time (Δy ) according to the difference of the input values for those time moments (Δx). This time difference representation can avoid process linear changes in time, which causes degradation in the accuracy model [121,122].…”

Section: Model Maintenancementioning

confidence: 99%

Soft metrology based on machine learning: a review

Vallejo

Espriella

Gómez-Santamaría

et al. 2019

Meas. Sci. Technol.

View full text Add to dashboard Cite

Soft metrology has been defined as a set of measurement techniques and models that allow the objective quantification of properties usually determined by human perception such as smell, sound or taste. The development of a soft metrology system requires the measurement of physical parameters and the construction of a model to correlate them with the variables that need to be quantified. This paper presents a review of indirect measurement with the aim of understanding the state of development in this area, as well as the current challenges and opportunities; and proposes to gather all the different designations under the term soft metrology, broadening its definition. For this purpose, the literature on indirect measurement techniques and systems has been reviewed, encompassing recent as well as a few older key documents to present a time line of development and map out application contexts and designations. As machine learning techniques have been extensively used in indirect measurement strategies, this review highlights them, and also makes an effort to describe the state of the art regarding the determination of uncertainty. This study does not delve into developments and applications for human and social sciences, although the proposed definition considers the use that this term has had in these areas.

show abstract

“…In recent decades, various soft measurement methods have been widely used in different industries. By using the soft measurement technology, an inferential model can be constructed between some variables that can be measured online (also called auxiliary variables) and other variables that cannot be measured online (also called objective variables), and the inferential model can be used to estimate the objective variables to achieve the optimal control of industrial processes [3]. With the wide application of machine learning technology in soft measurement, Vallejo [4] presented a review on soft metrology systems based on machine learning techniques and defined the tendencies, challenges and opportunities in their development.…”

Section: Introductionmentioning

confidence: 99%

Soft measurement of ball mill load based on multi-classifier ensemble modelling and multi-sensor fusion with improved evidence combination

Huang¹,

Sang²,

Miao³

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming at the problem that the traditional Dempster–Shafer (D–S) evidence theory obtains counter-intuitive results when dealing with conflicting evidences, a new index of evidence dissimilarity measure and an improved evidence combination method are proposed in this paper, which are verified through numerical examples and UCI datasets by comparing with other methods. Then, based on the improved evidence combination method, an improved multi-classifier ensemble modelling is proposed in this paper, which is applied to the soft measurement of ball mill load. Experiments are performed with a laboratory ball mill, and the vibration signals of bearing seats are used as auxiliary variables for the mill load. The recognition results of multiple classifiers and multiple sensors are fused in turn. The recognition accuracy of the proposed method in multi-sensor fusion is significantly higher than that of a single sensor, and the overall classification accuracy is higher than that of other combination methods, which can be found that the proposed method effectively improves the accuracy of soft measurement of ball mill load.

show abstract

Soft sensor modelling by time difference, recursive partial least squares and adaptive model updating

Cited by 14 publications

References 15 publications

A digital twin–driven method for online quality control in process industry

A digital twin–driven method for online quality control in process industry

Soft metrology based on machine learning: a review

Soft measurement of ball mill load based on multi-classifier ensemble modelling and multi-sensor fusion with improved evidence combination

Contact Info

Product

Resources

About