Description and comparison of fault detection algorithms based on a selected building automation device

• Autorzy: Włostowska Sandra , Kawa Bartłomiej , Borkowski Piotr

Identyfikatory

DOI

10.24425/bpasts.2025.153832

• Języki publikacji: EN

Abstrakty

EN

The article compares selected classification algorithms and those dedicated to anomaly detection. The models used temperature measurements in four rooms simulated in the MATLAB Simscape environment as test signals. The empirical part of the work consists of two parts. In the first one, an example data from the simulated building heating model object, models were built using unsupervised and supervised machine learning algorithms. Then, data from the facility was collected again with changed parameters (failures occurred at times other than the test ones, and the temperature patterns differed from those recorded and used to train the models). The algorithm effects and test signals (temperature changes) were saved in the database. The results were presented graphically in the Grafana program. The second part of the work presents a solution in which the analysis of the operating status of the heating system takes place in real time. Using an OPC server, data was exchanged between the MATLAB environment and the database installed on a virtual machine in the Ubuntu system. The conclusions present the results and collect the authors’ suggestions regarding the practical applications of the discussed classification models.

Słowa kluczowe

EN

fault detection; machine learning; building automation; smart metering

PL

wykrywanie usterki; uczenie maszynowe; automatyzacja budynku; inteligentny licznik

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2025
• Tom: Vol. 73, nr 3
• Strony: art. no. e153832
• Opis fizyczny: Bibliogr. 33 poz., rys., tab.

Twórcy

autor

Włostowska Sandra

• Department of Electrical Apparatus, Faculty of Electrical, Electronics, Computer and Control Engineering, Lodz University of Technology, Łódź, Poland

• https://orcid.org/0009-0004-0738-3136

autor

Kawa Bartłomiej

• Department of Electrical Apparatus, Faculty of Electrical, Electronics, Computer and Control Engineering, Lodz University of Technology, Łódź, Poland

autor

Borkowski Piotr

• Department of Electrical Apparatus, Faculty of Electrical, Electronics, Computer and Control Engineering, Lodz University of Technology, Łódź, Poland

Bibliografia

• [1] V. Chandola, D. Cheboli, and V. Kumar, “Detecting anomalies in a time series database,” Computer Science & Engineering (CS&E) Technical Reports, 2009.
• [2] K. Różanowski, “Sztuczna inteligencja rozwój, szanse i zagrożenia,” Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki, vol. 2, no. 2, pp. 109–135, 2007, (in Polish).
• [3] H. Chaouch, A.S. Bayraktar, and C. Çeken, “Energy Management in Smart Buildings by Using M2M Communication,” International Istanbul Smart Grids and Cities Congress and Fair (ICSG), Istanbul, Turkey, 2019, pp. 31–35, doi: 10.1109/SGCF.2019.8782357.
• [4] P. Borkowski, B. Bolanowski, and E. Walczuk, Inteligentne systemy zarządzania budynkiem, Wydawnictwo Politechniki Łódzkiej, 2011
• [5] M. Szeliga, “Data Science i uczenie maszynowe”, Wydawnictwo Naukowe PWN, 2017.
• [6] A. Duraj, E. Korzeniewska, and A. Krawczyk, “Classification algorithms to identify changes in resistance,” Prz. Elektrotechn., vol. 91, no. 12, pp. 80–83, 2015.
• [7] V. Nasteski, “An overview of the supervised machine learning methods,” Horizons B, vol. 4, no. 51–62, p. 56, 2017.
• [8] F. Hahne, W. Huber, R. Gentleman, S. Falcon, R. Gentleman, and V.J. Carey, “Unsupervised machine learning,” in Bioconductor Case Studies, Springer, 2008, pp. 137–157.
• [9] P. Fatyga and R. Podraza, “Klasyfikacja danych – przegląd wybranych metod,” Zeszyty Naukowe Wydziału ETI Politechniki Gdańskiej, 2010, (in Polish).
• [10] V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: A survey,” ACM Comput. Surv. (CSUR), vol. 41, no. 3, pp. 1–58, 2009.
• [11] P. Lula, “Wykorzystanie sztucznej inteligencji w prognozowaniu,” Seminarium Statsoft “Prognozowanie w przedsiębiorstwie”, Warszawa, Poland, 2000, pp. 39–69, (in Polish).
• [12] M. Walesiak, “Wybór grup metod normalizacji wartości zmiennych w skalowaniu wielowymiarowym,” Prz. Stat., vol. 63, no. 1, pp. 7–18, 2016, (in Polish).
• [13] “MATLAB – MathWorks”. [Online]. Available: https://www.mathworks.com/products/matlab.html, [Accessed: 13. Sep. 2024]
• [14] “House Heating System - MATLAB & Simulink”. [Online]. Available: https://www.mathworks.com/help/simulink/ug/modela-house-heating-system.html, [Accessed: 13. Sep. 2024].
• [15] “KEPServerEX/ThingWorx Kepware Server,” INEE Sp. z o.o. [Online]. Available: https://inee.pl/produkty/kepserverex-thing worx-kepware-server, [Accessed: 13. Sep. 2024].
• [16] “Simscape.” Mathworks. [Online]. Available: https://www.mathworks.com/products/simscape.html [Accessed: 13. Sep. 2024].
• [17] “Simulink – Simulation and Model-Based Design.” Mathworks. [Online]. Available: https://www.mathworks.com/products/simulink.html [Accessed: 13. Sep. 2024].
• [18] M. Mamczur, “Jak działa regresja logistyczna?,” 20/03/2023. [Online]. Available: https://miroslawmamczur.pl/jak-dziala-regresja-logistyczna/, [Accessed: 13. Sep. 2024].
• [19] M. Jukiewicz, “Wykorzystanie maszyny wektorów nośnych oraz liniowej analizy dyskryminacyjnej jako klasyfikatorów cech w interfejsach mózg-komputer,” Poznan Univ. Technol. Acad. J.-Electr. Eng., vol. 79, pp. 25–30, 2014.
• [20] T. Pamuła, “Ocena predykcji natężenia ruchu pojazdów z użyciem algorytmu kNN-najbliższych sąsiadów i sieci neuronowych,” Logistyka, vol. 6, pp. 8313–8320, 2014, (in Polish).
• [21] E. Szpunar-Huk, “Pozyskiwanie wiedzy z danych przy wykorzystaniu klasyfikatorów złożonych,” Prace Naukowe Akademii Ekonomicznej we Wrocławiu, pp. 268–279, 2005, (in Polish).
• [22] J. Tchórzewski and K. Leszko, “Artificial neural networks as models neuronal electronic state offices,” Inf. Syst. Manag., vol. 4, no. 3, pp. 219–227, 2015.
• [23] P. Lula and R. Tadeusiewicz, Introduction to Neural Networks. Kraków: StatSoft Polska Sp. z o.o., 2001. [24] B. Całka, “Grupowanie nieruchomości lokalowych za pomocą metody K-średnich,” Prz. Geodezyjny, vol. 84, no. 11, pp. 3–8, 2012, (in Polish).
• [25] Y. Chen, X.S. Zhou, and T.S. Huang, “One-class SVM for learning in image retrieval,” in Proc. 2001 International Conference on Image Processing, vol. 1, pp. 34–37, 2001.
• [26] X. Zhao, Y. Wu, D.L. Lee, and W. Cui, “iForest: Interpreting random forests via visual analytics,” IEEE Trans. Vis. Comput. Graph., vol. 25, no. 1, pp. 407–416, 2018.
• [27] “InfluxDB Time Series Data Platform,” InfluxData. [Online]. Available: https://www.influxdata.com/, [Accessed: 13. Sep. 2024].
• [28] S. Włostowska, J. Szabela, A. Chojecki, and P. Borkowski, “Comparison of SQL NoSQL and TSDB database systems for smart buildings and smart metering applications,” Prz. Elektrotechn., vol. 99, pp. 7–12, 2023.
• [29] “PostgreSQL,” P.G.D. Group. [Online]. Available: https://www. postgresql.org/, [Accessed: 13. Sep. 2024].
• [30] “Grafana: The open observability platform,” Grafana Labs. [Online]. Available: https://grafana.com/, [Accessed: 13. Sep. 2024].
• [31] L. Deri, S. Mainardi, and F. Fusco, “TSDB: A compressed database for time series,” in I Traffic Monitoring and Analysis: 4th International Workshop, TMA 2012, Vienna, Austria, 2012, pp. 143–156.
• [32] Y. Ma, Q. Zhang, J. Ding, Q. Wang, and J. Ma, “Short term load forecasting based on iForest-LSTM,” 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2019, pp. 2278–2282.
• [33] D. Conway, Uczenie maszynowe dla programistów, Helion, 2014, (in Polish).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).