A Soft Sensor Modeling of Cement Rotary Kiln Temperature Field Based on Model-Driven and Data-Driven Methods

Xu, Jinhao; Fu, Dongmei; Shao, Lizhen; Zhang, Xiaojun; Liu, Gang

doi:10.1109/jsen.2021.3116937

Cited by 13 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preheated material is subsequently broken down in the decomposition furnace [30,31]. The decomposed material is calcined and undergoes a chemical reaction in the rotary kiln [32], and the calcination time lasts about 25 min. Finally, the clinker enters the grate cooler, where the fan blows cooling air to cool the clinker.…”

Section: Selection Of Process Variablesmentioning

confidence: 99%

Soft sensor modeling of cement clinker quality: a novel timing matching technique and data decoupling approach

Zhao¹,

Wu²,

Zhang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Clinker f-CaO content is an important indicator of cement quality. Considering the production characteristics (strong coupling, time-varying delay) in the cement process industry, a soft sensor model was developed by combining various methods. First, a new decoupling method is proposed to deal with the strong coupling between variables, which achieves data decoupling between process variables through the attention mechanism and the LSTM network. Second, a novel time-series matching technique is proposed to handle the time-varying delays, which utilizes a window selection mechanism to adaptively select the time period in which each process variable influences the target variable. Third, the critical features of the variables are extracted by a one-dimensional convolution network(1D-CNN). Last, a combination of the data decoupling method, window selection mechanism, and 1D-CNN is applied to develop a soft sensor model (ADM-WGM-CNN), which implements the measurement of f-CaO content. The experimental results demonstrate that the ADM-WGM-CNN model has better measurement performance.

show abstract

Section: Selection Of Process Variablesmentioning

confidence: 99%

Soft sensor modeling of cement clinker quality: a novel timing matching technique and data decoupling approach

Zhao¹,

Wu²,

Zhang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Hay dos enfoques importantes usados para el desarrollo de un sistema de soft metrología: el primero se establece como un enfoque basado en modelos físicos, el cual parte del conocimiento fenomenológico del proceso analizado (12)(13)(14); el segundo es un enfoque a partir de datos que recurre a la información observada del proceso analizado (bases de datos estructuradas) para la generación del modelo (15)(16)(17)(18). Si bien, con las fortalezas que ofrecen los sistemas de cómputo de última generación, el enfoque derivado de los datos ha sido ampliamente investigado y probado (19,20), el procesamiento de datos históricos mediante inteligencia computacional trae consigo diferentes retos, que actualmente siguen abiertos en la comunidad científica, para lograr cada vez mejores modelos de medición indirecta en cuanto a costo y precisión (1).…”

Section: Análisis De Incertidumbre En Soft Metrologíaunclassified

Incertidumbre epistémica y aleatoria en soft metrología: una perspectiva desde el aseguramiento de la validez de los resultados

Agudelo-Cardona,

Barbosa,

Vallejo

et al. 2023

Ing.

View full text Add to dashboard Cite

Contexto: En ingeniería, el modelado para el análisis de riesgo y confiabilidad de los procesos de medición que incluyen rutinas de cómputo exige el análisis de las fuentes y categorías de la incertidumbre, la cual, en este contexto, puede ser clasificada como aleatoria y epistémica. Método: Se presenta una revisión de la literatura obtenida de bases de datos como Google Scholar, IEEEXplore y ScienceDirect en cuanto a tendencias y enfoques relacionados con el concepto de incertidumbre, en el marco de la soft metrología, a fin de mejorar la comprensión cuando se tienen restricciones adicionales debido al aseguramiento de la validez de los resultados. Resultados: Se exponen conceptos y comparaciones que ayudan a mejorar la comprensión de la incertidumbre epistémica y aleatoria en los procesos de medición de soft metrología y su relación con el aseguramiento de la validez de los resultados, en el marco de las máquinas de aprendizaje. Conclusiones: Se concluye que la calidad en la representación de los sistemas de soft metrología es influenciada de manera constante por la incertidumbre aleatoria, y la incertidumbre epistémica exhibe una dinámica descendente cuanto mejor sea el ajuste del modelo con suficientes datos de entrenamiento.

show abstract

“…There are different approaches to soft sensor development, but the complexity of the production process and uncertainties in determining the connection between laboratory values and signals that are measured in the process are reasons why soft sensors in the process industry are mainly based on black box or gray box models. The black box approach is successfully applied to different processes, from the cement industry [ 1 , 2 , 3 , 4 ] and chemical processes [ 5 , 6 , 7 ] to water treatment [ 8 , 9 , 10 ], energy production [ 11 ] and the oil industry [ 12 , 13 , 14 ]. Since it proved appropriate for the development of soft sensors for a variety of industrial processes, the black box approach has the potential to be used as a basis for a wide industrial implementation of soft sensors.…”

Section: Introductionmentioning

confidence: 99%

An Algorithm for Soft Sensor Development for a Class of Processes with Distinct Operating Conditions

Stanišić,

Mejić,

Jorgovanović

et al. 2024

Sensors

View full text Add to dashboard Cite

Soft sensors are increasingly being used to provide important information about production processes that is otherwise only available through off-line laboratory analysis. However, usually, they are developed for a specific application, for which thorough process analysis is performed to provide information for the appropriate selection of model type and model structure. Wide industrial application of soft sensors, however, requires a method for soft sensor development that has a high level of automatism and is applicable to a significant number of industrial processes. A class of processes that is very common in the industry are processes with distinct operating conditions. In this paper, an algorithm that is suitable for the development of soft sensors for this class of processes is presented. The algorithm possesses a high level of automatism, as it requires minimal user engagement regarding the structure of the model, which makes it suitable for implementation as a customary industrial solution. The algorithm is based on a radial basis function artificial neural network, and it enables the automatic selection of the model structure and the determination of model parameters, only based on the training data set. The testing of the presented algorithm is done on the cement production process, since it represents a process with distinct operating conditions. The results of the test show that, besides providing a high level of automatism in model development, the presented algorithm generates a soft sensor with high estimation performance.

show abstract

A Soft Sensor Modeling of Cement Rotary Kiln Temperature Field Based on Model-Driven and Data-Driven Methods

Cited by 13 publications

References 31 publications

Soft sensor modeling of cement clinker quality: a novel timing matching technique and data decoupling approach

Soft sensor modeling of cement clinker quality: a novel timing matching technique and data decoupling approach

Incertidumbre epistémica y aleatoria en soft metrología: una perspectiva desde el aseguramiento de la validez de los resultados

An Algorithm for Soft Sensor Development for a Class of Processes with Distinct Operating Conditions

Contact Info

Product

Resources

About