An adaptive soft sensor method of D-vine copula quantile regression for complex chemical processes

Ni, Jianeng; Li, Shaojun

doi:10.1016/j.ces.2020.116210

Cited by 9 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, compared with ML models, the JEHA model generally exhibited similar capabilities and potential in estimating daily ETref from radiation-based models across all climates. Relatively speaking, the high capability of ML models is attributed not only to the quantile value but also to the type of selected category used to model the dependency structure among the climatic input parameters (Nguyen et al 2021;Ni and Li 2021;Wu et al 2022;Sharafi and Ghaleni 2023). The MBE results in Fig.…”

Section: Statistical Metricsmentioning

confidence: 99%

Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models

Sharafi,

Mohammadi Ghaleni

2024

Appl Water Sci

View full text Add to dashboard Cite

This study examines the effectiveness of various quantile regression (QR) and machine learning (ML) methodologies developed for analyzing the relationship between meteorological parameters and daily reference evapotranspiration (ETref) across diverse climates in Iran spanning from 1987 to 2022. The analyzed models include D-vine copula-based quantile regression (DVQR), multivariate linear quantile regression (MLQR), Bayesian model averaging quantile regression (BMAQR), as well as machine learning algorithms such as extreme learning machine (ELM), random forest (RF), M5 model Tree (M5Tree), least squares support vector regression algorithm (LSSVR), and extreme gradient boosting (XGBoost). Additionally, empirical equations (EEs) such as Baier and Robertson (BARO), Jensen and Haise (JEHA), and Penman (PENM) models were considered. While the EEs demonstrated acceptable performance, the QR and ML models exhibited superior accuracy. Among these, the MLQR model displayed the highest accuracy compared to DVQR and BMAQR models. Moreover, LSSVR, XGBoost, and M5Tree models outperformed ELM and RF models. Notably, LSSVR, XGBoost, and MLQR models exhibited comparable performance (R2 and NSE > 0.92, MBE and RMSE < 0.5, and SI > 0.05) to M5Tree and BMAQR models across all climates. Importantly, these models significantly outperformed EEs, DVQR, ELM, and RF models in all climates. In conclusion, high-dimensional QR and ML models are recommended as promising alternatives for accurately estimating daily ETref in diverse global climate conditions.

show abstract

Section: Statistical Metricsmentioning

confidence: 99%

Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models

Sharafi,

Mohammadi Ghaleni

2024

Appl Water Sci

View full text Add to dashboard Cite

show abstract

“…Since chemical processes have become increasingly complex, it is critical to keep track of the variables in the system to guarantee the normal operation of such processes as well as the quality of the final product. Some variables can be automatically measured online using sensors, such as the flow rate and the temperature; however, other key variables, such as the reaction rate, the component concentration, and the viscosity, [1] cannot be measured in real-time due to technical limitations or high measurement cost. In such case, several soft sensor methods could be proposed to address this problem as they can perform online and real-time assessments of complex measurable key variables using readily available auxiliary variables.…”

Section: Introductionmentioning

confidence: 99%

Multi‐layer features ensemble soft sensor regression model based on stacked autoencoder and vine copula

Chen

2023

Can J Chem Eng

Self Cite

View full text Add to dashboard Cite

It is crucial in industrial processes to consider key variables to ensure safe operation and high product quality. Moreover, these variables are difficult to obtain using traditional measurement methods; hence, it makes sense to develop soft sensor regression models to process the variable prediction. However, there are numerous variables integrating noisy and redundant information in complex industrial processes. Using such variables in traditional regression models may result in reducing the model's efficiency and performance. Thus, this paper proposes a multi-layer feature ensemble soft sensor regression method using a stacked auto-encoder (SAE) and vine copula (ESAE-VCR) to address these problems. To do so, the number of neurons in the hidden layer of the SAE is determined by the principal component analysis (PCA). The multi-layer features of the process variables are extracted using a stacked AE, and the regression models are established for each feature layer. A linear regression ensemble method is used to combine the regression models with the multi-layer features to obtain the final predictive model that will estimate the values of the key variables. The effectiveness and practicality of the ESAE-VCR are validated by comparing them with several common soft measurement methods in two examples. In the numerical example, the ESAE-VCR yields an accuracy of prediction (R 2 ) of 0.9898 and a root mean square error (RMSE) of 0.1804. In the industrial example, the ESAE-VCR yields an R 2 of 0.9908 and an RMSE of 0.1205.

show abstract

“…Currently, data-driven SS have gained great relevance due to significant advances in data acquisition systems and machine-learning techniques. [5][6][7][8][9][10][11][12] Unfortunately, SS estimates are always affected by unavoidable errors caused by inaccurate mathematical models, uncertain model parameters, sensor drifts, measurement noises, etc. To compensate for estimation errors, several adaptive techniques have been developed to automatically update an SS.…”

Section: Introductionmentioning

confidence: 99%

“…Many other adaptive SS have been proposed in the literature. [7,[10][11][12] Several mathematical models related to the SBR process have been published. Broadhead and Hamielec developed a nonlinear dynamic model for the production of SBR in a CSTR.…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Soft Sensor for On‐Line Monitoring the Mass Conversion in the Emulsion Copolymerization of the Continuous SBR Process

Sanseverinatti

Perdomo

Clementi

et al. 2023

Macro Reaction Engineering

View full text Add to dashboard Cite

Soft sensors (SS) are of importance in monitoring polymerization processes because numerous production and quality variables cannot be measured online. Adaptive SSs are of interest to maintain accurate estimations under disturbances and changes in operating points. This study proposes an adaptive SS to online estimate the mass conversion in the emulsion copolymerization required for the production of Styrene‐Butadiene rubber (SBR). The SS includes a bias term calculated from sporadic laboratory measurements. Typically, the bias is updated every time a new laboratory report becomes available, but this strategy leads to unnecessarily frequent bias updates. The SS includes a statistic‐based tool to avoid unnecessary bias updates and reduce the variability of the bias with respect to classical approaches. A control chart (CC) for individual determinations combined with an algorithmic Cusum is used to monitor the statistical stability of the average prediction error. The adaptive SS enables a bias update only when a loss of said statistical stability is detected. Several bias update methods are tested on a simulated industrial train of reactors for the latex production in the SBR process. The best results are obtained by combining the proposed CC‐based approach with a previously developed Bayesian bias update strategy.

show abstract

An adaptive soft sensor method of D-vine copula quantile regression for complex chemical processes

Cited by 9 publications

References 33 publications

Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models

Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models

Multi‐layer features ensemble soft sensor regression model based on stacked autoencoder and vine copula

An Adaptive Soft Sensor for On‐Line Monitoring the Mass Conversion in the Emulsion Copolymerization of the Continuous SBR Process

Contact Info

Product

Resources

About