Soft sensor for real-time cement fineness estimation

Stanisic, Darko; Jorgovanović, Nikola; Popov, Nikola; Čongradac, Velimir

doi:10.1016/j.isatra.2014.09.019

Cited by 27 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Virtual sensor or soft sensor is a software module that enables the reliable real-time estimation of the value that cannot be measured directly, by calculating it from directly measured values [20]. In this experiment virtual sensor is designed to calculate the displacement down the sloped plane using the tilt measured with tiltmeter (Fig.…”

Section: Experimental Workmentioning

confidence: 99%

Generalized Model of Real-Time Deformation Measurements and its Experimental Verification

et al. 2020

View full text Add to dashboard Cite

Technology development enabled real-time monitoring of terrain and artificial structures through the use of the systems comprised of geodetic and geotechnical sensors. Although the structure and the architecture of those systems can vary, they have many common features: automated measurements which provide monitoring and alarming when tolerances are exceeded, systems robustness involving hot-swapping sensors, its redundancy and error detection. Also, they can be structured and configured to achieve desired functionality and performance. Generalized model of real-time deformation measurements, presented in this paper, involves these common characteristics. The model is presented as a flowchart, and later applied within an experiment carried out in laboratory environment. The established system includes geodetic and geotechnical sensors and measurements are done on a physical model of a landslide. Several functions included in generalized model were implemented in the experiment. Results show that system designed using the proposed model can provide required functionality, accuracy, robustness and configurability. Aim of the paper is to propose a general procedure which, with minor modifications, can be applied as a starting point in designing various systems for monitoring landslides, bridges, high buildings etc., and which overcomes some limitations that can be found in commercial software solutions.

show abstract

Section: Experimental Workmentioning

confidence: 99%

Generalized Model of Real-Time Deformation Measurements and its Experimental Verification

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The ball mill load, the outlet temperature, the hot air pressure, the recycle air pressure, the negative inlet pressure, the different inlet-outlet pressure, and the outlet pressure of the fine and coarse separators are just some of those influential variables [6][7][8][9][10]. However, few studies have explored the possible relationships between operating variables and ventilation for an industrial ball mill in a cement plant [11,12].…”

Section: Introductionmentioning

confidence: 99%

Ventilation Prediction for an Industrial Cement Raw Ball Mill by BNN—A “Conscious Lab” Approach

et al. 2021

View full text Add to dashboard Cite

In cement mills, ventilation is a critical key for maintaining temperature and material transportation. However, relationships between operational variables and ventilation factors for an industrial cement ball mill were not addressed until today. This investigation is going to fill this gap based on a newly developed concept named “conscious laboratory (CL)”. For constructing the CL, a boosted neural network (BNN), as a recently developed comprehensive artificial intelligence model, was applied through over 35 different variables, with more than 2000 records monitored for an industrial cement ball mill. BNN could assess multivariable nonlinear relationships among this vast dataset, and indicated mill outlet pressure and the ampere of the separator fan had the highest rank for the ventilation prediction. BNN could accurately model ventilation factors based on the operational variables with a root mean square error (RMSE) of 0.6. BNN showed a lower error than other traditional machine learning models (RMSE: random forest 0.71, support vector regression: 0.76). Since improving the milling efficiency has an essential role in machine development and energy utilization, these results can open a new window to the optimal designing of comminution units for the material technologies.

show abstract

“…SSs' industrial use ranges over a number of different types of processes, such as refineries [6][7][8][9][10][11], chemical plants [12], cement kilns [13,14], power plants [15,16], pulp and paper mills [17,18], food processing [2,19], nuclear plants [20,21], pollution monitoring [22], polymerization processes [23][24][25] or wastewater treatment systems [26][27][28][29], just to mention a few. In Figure 2, a distillation column process from a refinery is shown through its control software: displayed online measurements are collected in a historical database for future use.…”

Section: Introductionmentioning

confidence: 99%

Input Selection Methods for Soft Sensor Design: A Survey

2020

View full text Add to dashboard Cite

Soft Sensors (SSs) are inferential models used in many industrial fields. They allow for real-time estimation of hard-to-measure variables as a function of available data obtained from online sensors. SSs are generally built using industries historical databases through data-driven approaches. A critical issue in SS design concerns the selection of input variables, among those available in a candidate dataset. In the case of industrial processes, candidate inputs can reach great numbers, making the design computationally demanding and leading to poorly performing models. An input selection procedure is then necessary. Most used input selection approaches for SS design are addressed in this work and classified with their benefits and drawbacks to guide the designer through this step.

show abstract

Soft sensor for real-time cement fineness estimation

Cited by 27 publications

References 26 publications

Generalized Model of Real-Time Deformation Measurements and its Experimental Verification

Generalized Model of Real-Time Deformation Measurements and its Experimental Verification

Ventilation Prediction for an Industrial Cement Raw Ball Mill by BNN—A “Conscious Lab” Approach

Input Selection Methods for Soft Sensor Design: A Survey

Contact Info

Product

Resources

About