Identification of Disturbances for a Room Temperature Conditions Model Using a Neural Network
Keywords:
neural networks, LSTM-networks, least squares method, data filtering, heating systems, building thermal conditions
Abstract
The use of IoT devices for building heating systems opens the possibility of collecting a large amount of various data about room temperature conditions. At the level of individual rooms, there are factors that can have a significant effect on the temperature conditions, the measurement of which involves difficulties. As a consequence, the models of room temperature conditions are identified incorrectly. In view of this circumstance, the consideration of unknown disturbances becomes of issue.
A method to identify the building room temperature conditions is proposed that allows unknown disturbing inputs in dynamic systems to be taken into account. The unknown disturbance action time is described using indicator functions. The indicator function time characteristics are identified using neural LSTM networks by solving the problem of performing binary classification of whether the measured data sample time tags belong to unknown disturbances. The sequence in which unknown disturbances are taken into account in the model is found by sorting the evaluated degree to which the time tags belong to the onset of a certain unknown disturbance that is obtained by solving the binary classification problem.
The application of the proposed approach is illustrated on the temperature conditions identification problem using test data with two samples of unknown disturbances with random action degree and time. The study results demonstrate correctness of the proposed approach, the use of which makes it possible to more accurately identify the static and dynamic parameters of system models under the effect of unknown disturbances.
References
1. Панферов С.В., Тренин Н.А., Панферов В.И. Об одном решении задачи построения общей модели теплового режима здания и его системы отопления // Вестник Южно-Уральского гос. ун-та. Серия «Компьютерные технологии, управление, радиоэлектроника». 2017. № 17. Вып. 3. С. 24—33.
2. Кычкин А.В., Дерябин А.И., Викентьева О.Л. и др. Автоматизация процессов компенсационно-предиктивного управления климат-системами интеллектуального здания // Вестник МГСУ. 2019. № 6(129). С. 734—747.
3. He X., Kong Q., Xiao Z. Fast Simulation Methods for Dynamic Heat Transfer through Building Envelope Based on Model-order-Reduction // Proc. Eng. 2015. V. 121. Pp. 1764—1771.
4. Preka M., Kreseb G. Experimental Analysis of an Improved Regulation Concept for Multi-Panel Heating Radiators: Proof-of-Concept // Energy. 2018. V. 161. Pp. 52—59.
5. An. J. e. a. An Improved Method for Direct Incident Solar Radiation Calculation from Hourly Solar Insolation Data in Building Energy Simulation // Energy and Buildings. 2020. V. 227. Pp. 1—20.
6. Darula S., Christoffersen J., Malikova M. Sunlight and Insolation of Building Interiors // Energy Procedia. 2015. V. 78. Pp. 1245—1250.
7. Веснин В.И. Инфильтрация воздуха и тепловые потери помещений через оконные проемы // Градостроительство и архитектура. 2016. № 3(24). С. 10—16.
8. Happle G., Fonseca J., Schlueter A. Effects of Air Infiltration Modeling Approaches in Urban Building Energy Demand Forecasts // Energy Proc. 2014. V. 122. Pp. 283—288.
9. Goubran S. e. a. Comparing Methods of Modeling Air Infiltration Through Building Entrances and Their Impact on Building Energy Simulations // Energy and Buildings. 2017. V. 138. Pp. 579—590.
10. Elsland R., Peksen I., Wietschel M. Are Internal Heat Gains Underestimated in Thermal Performance Evaluation of Buildings? // Energy Procedia. 2014. V. 62. Pp. 32—41.
11. Basalaev A., Kazarinov L., Shnayder D. Heating Management System Based on Wireless Sensor Networks // Proc. Global Smart Industry Conf. 2018. Pp. 1—8.
12. Idowu S. e. a. Applied Machine Learning: Forecasting Heat Load in District Heating System // Energy and Buildings. 2016. V. 133. Pp. 478—488.
13. Zhao Y. e. a. A Review of Data Mining Technologies in Building Energy Systems: Load Prediction, Pattern Identification, Fault Detection and Diagnosis // Energy and Built Environment. 2020. V. 1. Iss. 2. Pp. 149—164.
14. Ahmad T., Chen H., Huang Y. Short-Term Energy Prediction for District-Level Load Management Using Machine Learning Based Approaches // Energy Proc. 2019. V. 158. Pp. 3331—3338.
15. Turner W., Staino A., Basu B. Residential HVAC Fault Detection Using a System Identification Approach // Energy and Buildings. 2017. V. 151. Pp. 1—17.
16. Zhao Y. e. a. Artificial Intelligence-Based Fault Detection and Diagnosis Methods for Building Energy Systems: Advantages, Challenges and the Future // Renewable and Sustainable Energy Rev. 2019. V. 109. Pp. 85—101.
17. Шалимов А.С., Тимошенков С.П. Разработка универсального способа удаления случайной постоянной составляющей из входного сигнала в условиях априорной неопределенности // Известия ЮФУ. Серия «Технические науки». 2018. № 1(195). С. 104—116.
18. Yan K., Ji Zh., Shen W. Online Fault Detection Methods for Chillers Combining Extended Kalman Filter and Recursive One-Class SVM // Neurocomputing. 2017. V. 228. Pp. 205—212.
19. Самойленко М.В. Томографический метод восстановления сигнала после прохождения через фильтр с известной характеристикой // Автоматизация процессов управления. 2017. № 2(48). С. 22—29.
20. Арановский С.В., Бардов В.М. Метод оптимальной идентификации параметров линейного динамического объекта в условиях возмущения // Проблемы управления. 2012. № 3. C. 35—40.
21. Basalaev A., Tochilkin M., Shnayder D. Enhancing Room Thermal Comfort Conditions Modeling in Buildings Through Schedule-Based Indicator Functions for Possible Variable Thermal Perturbation Inputs // Proc. Intern. Conf. Industrial Eng., Appl. and Manufacturing. 2019. Pp. 1—8
---
Для цитирования: Басалаев А.А. Идентификация возмущающих воздействий для модели температурного режима помещений с использованием нейронной сети // Вестник МЭИ. 2021. № 6. С. 137—147. DOI: 10.24160/1993-6982-2021-6-137-147
#
1. Panferov S.V., Trenin N.A., Panferov V.I. Ob Odnom Reshenii Zadachi Postroeniya Obshchey Modeli Teplovogo Rezhima Zdaniya i Ego Sistemy Otopleniya. Vestnik Yuzhno-Ural'skogo Gos. Un-ta. Seriya «Komp'yuternye Tekhnologii, Upravlenie, Radioelektronika». 2017;17;3:24—33. (in Russian).
2. Kychkin A.V., Deryabin A.I., Vikent'eva O.L. i dr. Avtomatizatsiya Protsessov Kompensatsionno-Prediktivnogo Upravleniya Klimat-sistemami Intellektual'nogo Zdaniya. Vestnik MGSU. 2019;6(129):734—747. (in Russian).
3. He X., Kong Q., Xiao Z. Fast Simulation Methods for Dynamic Heat Transfer through Building Envelope Based on Model-order-Reduction. Proc. Eng. 2015;121:1764—1771.
4. Preka M., Kreseb G. Experimental Analysis of an Improved Regulation Concept for Multi-Panel Heating Radiators: Proof-of-Concept. Energy. 2018;161:52—59.
5. An. J. e. a. An Improved Method for Direct Incident Solar Radiation Calculation from Hourly Solar Insolation Data in Building Energy Simulation. Energy and Buildings. 2020; 227:1—20.
6. Darula S., Christoffersen J., Malikova M. Sunlight and Insolation of Building Interiors. Energy Procedia. 2015;78:1245—1250.
7. Vesnin V.I. Infil'tratsiya Vozdukha i Teplovye Poteri Pomeshcheniy Cherez Okonnye Proemy. Gradostroitel'stvo i Arkhitektura. 2016;3(24):10—16. (in Russian).
8. Happle G., Fonseca J., Schlueter A. Effects of Air Infiltration Modeling Approaches in Urban Building Energy Demand Forecasts. Energy Proc. 2014;122:283—288.
9. Goubran S. e. a. Comparing Methods of Modeling Air Infiltration Through Building Entrances and Their Impact on Building Energy Simulations. Energy and Buildings. 2017;138:579—590.
10. Elsland R., Peksen I., Wietschel M. Are Internal Heat Gains Underestimated in Thermal Performance Evaluation of Buildings?. Energy Procedia. 201;62:32—41.
11. Basalaev A., Kazarinov L., Shnayder D. Heating Management System Based on Wireless Sensor Networks. Proc. Global Smart Industry Conf. 2018:1—8.
12. Idowu S. e. a. Applied Machine Learning: Forecasting Heat Load in District Heating System. Energy and Buildings. 2016;133:478—488.
13. Zhao Y. e. a. A Review of Data Mining Technologies in Building Energy Systems: Load Prediction, Pattern Identification, Fault Detection and Diagnosis. Energy and Built Environment. 2020;1;2:149—164.
14. Ahmad T., Chen H., Huang Y. Short-Term Energy Prediction for District-Level Load Management Using Machine Learning Based Approaches. Energy Proc. 2019;158:3331—3338.
15. Turner W., Staino A., Basu B. Residential HVAC Fault Detection Using a System Identification Approach. Energy and Buildings. 2017;151:1—17.
16. Zhao Y. e. a. Artificial Intelligence-Based Fault Detection and Diagnosis Methods for Building Energy Systems: Advantages, Challenges and the Future. Renewable and Sustainable Energy Rev. 2019;109:85—101.
17. Shalimov A.S., Timoshenkov S.P. Razrabotka Universal'nogo Sposoba Udaleniya Sluchaynoy Postoyannoy Sostavlyayushchey iz Vkhodnogo Signala v Usloviyakh Apriornoy Neopredelennosti. Izvestiya YUFU. Seriya «Tekhnicheskie Nauki». 2018;1(195):104—116. (in Russian).
18. Yan K., Ji Zh., Shen W. Online Fault Detection Methods for Chillers Combining Extended Kalman Filter and Recursive One-Class SVM. Neurocomputing. 2017;228:205—212.
19. Samoylenko M.V. Tomograficheskiy Metod Vosstanovleniya Signala Posle Prokhozhdeniya Cherez Fil'tr s Izvestnoy Kharakteristikoy. Avtomatizatsiya Protsessov Upravleniya. 2017;2(48):22—29. (in Russian).
20. Aranovskiy S.V., Bardov V.M. Metod Optimal'noy Identifikatsii Parametrov Lineynogo Dinamicheskogo Ob′ekta v Usloviyakh Vozmushcheniya. Problemy Upravleniya. 2012;3:35—40. (in Russian).
21. Basalaev A., Tochilkin M., Shnayder D. Enhancing Room Thermal Comfort Conditions Modeling in Buildings Through Schedule-Based Indicator Functions for Possible Variable Thermal Perturbation Inputs. Proc. Intern. Conf. Industrial Eng., Appl. and Manufacturing. 2019:1—8.
---
For citation: Basalaev A.A. Identification of Disturbances for a Room Temperature Conditions Model Using a Neural Network. Bulletin of MPEI. 2021;6:137—147. (in Russian). DOI: 10.24160/1993-6982-2021-6-137-147
2. Кычкин А.В., Дерябин А.И., Викентьева О.Л. и др. Автоматизация процессов компенсационно-предиктивного управления климат-системами интеллектуального здания // Вестник МГСУ. 2019. № 6(129). С. 734—747.
3. He X., Kong Q., Xiao Z. Fast Simulation Methods for Dynamic Heat Transfer through Building Envelope Based on Model-order-Reduction // Proc. Eng. 2015. V. 121. Pp. 1764—1771.
4. Preka M., Kreseb G. Experimental Analysis of an Improved Regulation Concept for Multi-Panel Heating Radiators: Proof-of-Concept // Energy. 2018. V. 161. Pp. 52—59.
5. An. J. e. a. An Improved Method for Direct Incident Solar Radiation Calculation from Hourly Solar Insolation Data in Building Energy Simulation // Energy and Buildings. 2020. V. 227. Pp. 1—20.
6. Darula S., Christoffersen J., Malikova M. Sunlight and Insolation of Building Interiors // Energy Procedia. 2015. V. 78. Pp. 1245—1250.
7. Веснин В.И. Инфильтрация воздуха и тепловые потери помещений через оконные проемы // Градостроительство и архитектура. 2016. № 3(24). С. 10—16.
8. Happle G., Fonseca J., Schlueter A. Effects of Air Infiltration Modeling Approaches in Urban Building Energy Demand Forecasts // Energy Proc. 2014. V. 122. Pp. 283—288.
9. Goubran S. e. a. Comparing Methods of Modeling Air Infiltration Through Building Entrances and Their Impact on Building Energy Simulations // Energy and Buildings. 2017. V. 138. Pp. 579—590.
10. Elsland R., Peksen I., Wietschel M. Are Internal Heat Gains Underestimated in Thermal Performance Evaluation of Buildings? // Energy Procedia. 2014. V. 62. Pp. 32—41.
11. Basalaev A., Kazarinov L., Shnayder D. Heating Management System Based on Wireless Sensor Networks // Proc. Global Smart Industry Conf. 2018. Pp. 1—8.
12. Idowu S. e. a. Applied Machine Learning: Forecasting Heat Load in District Heating System // Energy and Buildings. 2016. V. 133. Pp. 478—488.
13. Zhao Y. e. a. A Review of Data Mining Technologies in Building Energy Systems: Load Prediction, Pattern Identification, Fault Detection and Diagnosis // Energy and Built Environment. 2020. V. 1. Iss. 2. Pp. 149—164.
14. Ahmad T., Chen H., Huang Y. Short-Term Energy Prediction for District-Level Load Management Using Machine Learning Based Approaches // Energy Proc. 2019. V. 158. Pp. 3331—3338.
15. Turner W., Staino A., Basu B. Residential HVAC Fault Detection Using a System Identification Approach // Energy and Buildings. 2017. V. 151. Pp. 1—17.
16. Zhao Y. e. a. Artificial Intelligence-Based Fault Detection and Diagnosis Methods for Building Energy Systems: Advantages, Challenges and the Future // Renewable and Sustainable Energy Rev. 2019. V. 109. Pp. 85—101.
17. Шалимов А.С., Тимошенков С.П. Разработка универсального способа удаления случайной постоянной составляющей из входного сигнала в условиях априорной неопределенности // Известия ЮФУ. Серия «Технические науки». 2018. № 1(195). С. 104—116.
18. Yan K., Ji Zh., Shen W. Online Fault Detection Methods for Chillers Combining Extended Kalman Filter and Recursive One-Class SVM // Neurocomputing. 2017. V. 228. Pp. 205—212.
19. Самойленко М.В. Томографический метод восстановления сигнала после прохождения через фильтр с известной характеристикой // Автоматизация процессов управления. 2017. № 2(48). С. 22—29.
20. Арановский С.В., Бардов В.М. Метод оптимальной идентификации параметров линейного динамического объекта в условиях возмущения // Проблемы управления. 2012. № 3. C. 35—40.
21. Basalaev A., Tochilkin M., Shnayder D. Enhancing Room Thermal Comfort Conditions Modeling in Buildings Through Schedule-Based Indicator Functions for Possible Variable Thermal Perturbation Inputs // Proc. Intern. Conf. Industrial Eng., Appl. and Manufacturing. 2019. Pp. 1—8
---
Для цитирования: Басалаев А.А. Идентификация возмущающих воздействий для модели температурного режима помещений с использованием нейронной сети // Вестник МЭИ. 2021. № 6. С. 137—147. DOI: 10.24160/1993-6982-2021-6-137-147
#
1. Panferov S.V., Trenin N.A., Panferov V.I. Ob Odnom Reshenii Zadachi Postroeniya Obshchey Modeli Teplovogo Rezhima Zdaniya i Ego Sistemy Otopleniya. Vestnik Yuzhno-Ural'skogo Gos. Un-ta. Seriya «Komp'yuternye Tekhnologii, Upravlenie, Radioelektronika». 2017;17;3:24—33. (in Russian).
2. Kychkin A.V., Deryabin A.I., Vikent'eva O.L. i dr. Avtomatizatsiya Protsessov Kompensatsionno-Prediktivnogo Upravleniya Klimat-sistemami Intellektual'nogo Zdaniya. Vestnik MGSU. 2019;6(129):734—747. (in Russian).
3. He X., Kong Q., Xiao Z. Fast Simulation Methods for Dynamic Heat Transfer through Building Envelope Based on Model-order-Reduction. Proc. Eng. 2015;121:1764—1771.
4. Preka M., Kreseb G. Experimental Analysis of an Improved Regulation Concept for Multi-Panel Heating Radiators: Proof-of-Concept. Energy. 2018;161:52—59.
5. An. J. e. a. An Improved Method for Direct Incident Solar Radiation Calculation from Hourly Solar Insolation Data in Building Energy Simulation. Energy and Buildings. 2020; 227:1—20.
6. Darula S., Christoffersen J., Malikova M. Sunlight and Insolation of Building Interiors. Energy Procedia. 2015;78:1245—1250.
7. Vesnin V.I. Infil'tratsiya Vozdukha i Teplovye Poteri Pomeshcheniy Cherez Okonnye Proemy. Gradostroitel'stvo i Arkhitektura. 2016;3(24):10—16. (in Russian).
8. Happle G., Fonseca J., Schlueter A. Effects of Air Infiltration Modeling Approaches in Urban Building Energy Demand Forecasts. Energy Proc. 2014;122:283—288.
9. Goubran S. e. a. Comparing Methods of Modeling Air Infiltration Through Building Entrances and Their Impact on Building Energy Simulations. Energy and Buildings. 2017;138:579—590.
10. Elsland R., Peksen I., Wietschel M. Are Internal Heat Gains Underestimated in Thermal Performance Evaluation of Buildings?. Energy Procedia. 201;62:32—41.
11. Basalaev A., Kazarinov L., Shnayder D. Heating Management System Based on Wireless Sensor Networks. Proc. Global Smart Industry Conf. 2018:1—8.
12. Idowu S. e. a. Applied Machine Learning: Forecasting Heat Load in District Heating System. Energy and Buildings. 2016;133:478—488.
13. Zhao Y. e. a. A Review of Data Mining Technologies in Building Energy Systems: Load Prediction, Pattern Identification, Fault Detection and Diagnosis. Energy and Built Environment. 2020;1;2:149—164.
14. Ahmad T., Chen H., Huang Y. Short-Term Energy Prediction for District-Level Load Management Using Machine Learning Based Approaches. Energy Proc. 2019;158:3331—3338.
15. Turner W., Staino A., Basu B. Residential HVAC Fault Detection Using a System Identification Approach. Energy and Buildings. 2017;151:1—17.
16. Zhao Y. e. a. Artificial Intelligence-Based Fault Detection and Diagnosis Methods for Building Energy Systems: Advantages, Challenges and the Future. Renewable and Sustainable Energy Rev. 2019;109:85—101.
17. Shalimov A.S., Timoshenkov S.P. Razrabotka Universal'nogo Sposoba Udaleniya Sluchaynoy Postoyannoy Sostavlyayushchey iz Vkhodnogo Signala v Usloviyakh Apriornoy Neopredelennosti. Izvestiya YUFU. Seriya «Tekhnicheskie Nauki». 2018;1(195):104—116. (in Russian).
18. Yan K., Ji Zh., Shen W. Online Fault Detection Methods for Chillers Combining Extended Kalman Filter and Recursive One-Class SVM. Neurocomputing. 2017;228:205—212.
19. Samoylenko M.V. Tomograficheskiy Metod Vosstanovleniya Signala Posle Prokhozhdeniya Cherez Fil'tr s Izvestnoy Kharakteristikoy. Avtomatizatsiya Protsessov Upravleniya. 2017;2(48):22—29. (in Russian).
20. Aranovskiy S.V., Bardov V.M. Metod Optimal'noy Identifikatsii Parametrov Lineynogo Dinamicheskogo Ob′ekta v Usloviyakh Vozmushcheniya. Problemy Upravleniya. 2012;3:35—40. (in Russian).
21. Basalaev A., Tochilkin M., Shnayder D. Enhancing Room Thermal Comfort Conditions Modeling in Buildings Through Schedule-Based Indicator Functions for Possible Variable Thermal Perturbation Inputs. Proc. Intern. Conf. Industrial Eng., Appl. and Manufacturing. 2019:1—8.
---
For citation: Basalaev A.A. Identification of Disturbances for a Room Temperature Conditions Model Using a Neural Network. Bulletin of MPEI. 2021;6:137—147. (in Russian). DOI: 10.24160/1993-6982-2021-6-137-147
Published
2021-05-19
Section
Mathematical Modeling, Numerical Methods and Program Complexe (05.13.18)
