Performance Evaluation of Stratified TES using Sigmoid Dose Response Function

Waluyo, Joko; Majid, Mohd Amin Abd

doi:10.3923/jas.2011.1642.1647

Cited by 6 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average error between the ANN predicted and actual values is 2.4%. Figure 14 shows the comparison between the calculated and ANN predicted values of

; it can be seen that the

has increased with respect to charging time as expected [ 9 , 41 , 55 , 56 ].…”

Section: Resultssupporting

confidence: 55%

See 1 more Smart Citation

Machine Learning Approach to Predict the Performance of a Stratified Thermal Energy Storage Tank at a District Cooling Plant Using Sensor Data

Soomro

Mokhtar

Salilew

et al. 2022

Sensors

View full text Add to dashboard Cite

In the energy management of district cooling plants, the thermal energy storage tank is critical. As a result, it is essential to keep track of TES results. The performance of the TES has been measured using a variety of methodologies, both numerical and analytical. In this study, the performance of the TES tank in terms of thermocline thickness is predicted using an artificial neural network, support vector machine, and k-nearest neighbor, which has remained unexplored. One year of data was collected from a district cooling plant. Fourteen sensors were used to measure the temperature at different points. With engineering judgement, 263 rows of data were selected and used to develop the prediction models. A total of 70% of the data were used for training, whereas 30% were used for testing. K-fold cross-validation were used. Sensor temperature data was used as the model input, whereas thermocline thickness was used as the model output. The data were normalized, and in addition to this, moving average filter and median filter data smoothing techniques were applied while developing KNN and SVM prediction models to carry out a comparison. The hyperparameters for the three machine learning models were chosen at optimal condition, and the trial-and-error method was used to select the best hyperparameter value: based on this, the optimum architecture of ANN was 14-10-1, which gives the maximum R-Squared value, i.e., 0.9, and minimum mean square error. Finally, the prediction accuracy of three different techniques and results were compared, and the accuracy of ANN is 0.92%, SVM is 89%, and KNN is 96.3%, concluding that KNN has better performance than others.

show abstract

“…The average error between the ANN predicted and actual values is 2.4%. Figure 14 shows the comparison between the calculated and ANN predicted values of

; it can be seen that the

has increased with respect to charging time as expected [ 9 , 41 , 55 , 56 ].…”

Section: Resultssupporting

confidence: 55%

“…The input to the machine learning models is the temperature distribution collected from the sensors installed vertically in the tank, and the output data for the machine learning models model is

. The outputs were obtained using the non-linear regression technique proposed by [ 41 , 42 ]. Equation (1) has been used to predict

.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Approach to Predict the Performance of a Stratified Thermal Energy Storage Tank at a District Cooling Plant Using Sensor Data

Soomro

Mokhtar

Salilew

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The values range from 2.248 meter to 5.445 meter, with an average of 3.251 meter. These values are very much higher than that was obtained by [4] and [11], and the result close to that was obtained by [10]. One possible reason is due to higher flow rates in comparison to [4].…”

Section: Resultscontrasting

confidence: 51%

Evaluations of thermocline and half cycle figure of merit of a thermal energy storage tank

Majid

Kin

2017

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. Two main criteria that are commonly used to evaluate thermal energy storage systems are thermocline thickness and half cycle figure of merit. For the thermocline thickness, the preference is to achieve as thin as possible the thermocline thickness. While the preference for half cycle figure of merit is to achieve the value of greater than 90 per cent. These two criteria were used to evaluate a thermal storage system at University Teknologi PETRONAS district cooling plant. The capacity of the thermal energy storage tank of the plant is 10,000 RTh. Operating data was used for the evaluation. The values of evaluated thermocline thickness ranges from 2.248 meters to 5.445 meters with an average of 3.251 meters. These values are very much higher in comparison to findings of other studies. One possible reason is due to higher flow rates. For the half cycle figure of merit the evaluated values ranges from 0.9469 to 0.9847, with the average of 0.9698, which are within the acceptable range. For future work a model should be developed which could automatically evaluate both the thermocline thickness and half cycle figure of merit. This would enable both of these parameters to be continuously evaluated.

show abstract

“…The dimensionless variables adopted are quite common in dimensional analysis of heat transfer problems [12]: The tank temperature field of a vertical fluid column inside a thermal storage tank can be described by sigmoidal functions following the approach adopted by [11], [13] and [14]. In particular, the logistic CDF shows a great degree of agreement with experimental data obtained by molten salts storage tank operation for solar thermal power plants [11].…”

Section: Analytical Functionmentioning

confidence: 99%

“…)𝑑𝑧 (14) The stratified temperature 𝑇 is a function of the non-dimensional z coordinate and this quantity should be integrated using the appropriate numerical technique. On the other hand, the two other temperatures can be defined in the following way:…”

Section: Second-law Performance Analysismentioning

confidence: 99%

CFD-based reduced model for the simulation of thermocline thermal energy storage systems

Pizzolato

Donato

Verda

et al. 2015

Applied Thermal Engineering

View full text Add to dashboard Cite

Performance Evaluation of Stratified TES using Sigmoid Dose Response Function

Cited by 6 publications

References 0 publications

Machine Learning Approach to Predict the Performance of a Stratified Thermal Energy Storage Tank at a District Cooling Plant Using Sensor Data

Machine Learning Approach to Predict the Performance of a Stratified Thermal Energy Storage Tank at a District Cooling Plant Using Sensor Data

Evaluations of thermocline and half cycle figure of merit of a thermal energy storage tank

CFD-based reduced model for the simulation of thermocline thermal energy storage systems

Contact Info

Product

Resources

About