{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T05:20:00Z","timestamp":1726377600339},"reference-count":33,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T00:00:00Z","timestamp":1661212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Norway Grants \u201cGreen ICT\u201d program"},{"DOI":"10.13039\/501100002301","name":"Estonian Research Council","doi-asserted-by":"publisher","award":["PRG658","PRG1463"],"id":[{"id":"10.13039\/501100002301","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["1227\/18"],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"In recent years, explainable artificial intelligence (XAI) techniques have been developed to improve the explainability, trust and transparency of machine learning models. This work presents a method that explains the outputs of an air-handling unit (AHU) faults classifier using a modified XAI technique, such that non-AI expert end-users who require justification for the diagnosis output can easily understand the reasoning behind the decision. The method operates as follows: First, an XGBoost algorithm is used to detect and classify potential faults in the heating and cooling coil valves, sensors, and the heat recovery of an air-handling unit. Second, an XAI-based SHAP technique is used to provide explanations, with a focus on the end-users, who are HVAC engineers. Then, relevant features are chosen based on user-selected feature sets and features with high attribution scores. Finally, a sliding window system is used to visualize the short history of these relevant features and provide explanations for the diagnosed faults in the observed time period. This study aimed to provide information not only about what occurs at the time of fault appearance, but also about how the fault occurred. Finally, the resulting explanations are evaluated by seven HVAC expert engineers. The proposed approach is validated using real data collected from a shopping mall.<\/jats:p>","DOI":"10.3390\/s22176338","type":"journal-article","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T06:55:34Z","timestamp":1661324134000},"page":"6338","source":"Crossref","is-referenced-by-count":16,"title":["Explainability and Transparency of Classifiers for Air-Handling Unit Faults Using Explainable Artificial Intelligence (XAI)"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-2780-7109","authenticated-orcid":false,"given":"Molika","family":"Meas","sequence":"first","affiliation":[{"name":"R8Technologies O\u00dc, 11415 Tallinn, Estonia"},{"name":"Department of Software Science, Tallinn University of Technology, 12618 Tallinn, Estonia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8003-4248","authenticated-orcid":false,"given":"Ram","family":"Machlev","sequence":"additional","affiliation":[{"name":"The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion\u2014Israel Institute of Technology, Haifa 3200003, Israel"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1439-2837","authenticated-orcid":false,"given":"Ahmet","family":"Kose","sequence":"additional","affiliation":[{"name":"R8Technologies O\u00dc, 11415 Tallinn, Estonia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7158-8484","authenticated-orcid":false,"given":"Aleksei","family":"Tepljakov","sequence":"additional","affiliation":[{"name":"Department of Computer Systems, Tallinn University of Technology, 12618 Tallinn, Estonia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1266-1386","authenticated-orcid":false,"given":"Lauri","family":"Loo","sequence":"additional","affiliation":[{"name":"R8Technologies O\u00dc, 11415 Tallinn, Estonia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9775-1406","authenticated-orcid":false,"given":"Yoash","family":"Levron","sequence":"additional","affiliation":[{"name":"The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion\u2014Israel Institute of Technology, Haifa 3200003, Israel"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2167-6280","authenticated-orcid":false,"given":"Eduard","family":"Petlenkov","sequence":"additional","affiliation":[{"name":"Department of Computer Systems, Tallinn University of Technology, 12618 Tallinn, Estonia"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8243-7374","authenticated-orcid":false,"given":"Juri","family":"Belikov","sequence":"additional","affiliation":[{"name":"Department of Software Science, Tallinn University of Technology, 12618 Tallinn, Estonia"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"59800","DOI":"10.1109\/ACCESS.2021.3070212","article-title":"A review on explainability in multimodal deep neural nets","volume":"9","author":"Joshi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Nomm, S., Bardos, K., Toomela, A., Medijainen, K., and Taba, P. (2018, January 17\u201320). Detailed analysis of the Luria\u2019s alternating SeriesTests for Parkinson\u2019s disease diagnostics. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00219"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Machlev, R., Heistrene, L., Perl, M., Levy, K., Belikov, J., Mannor, S., and Levron, Y. (2022). Explainable Artificial Intelligence (XAI) techniques for energy and power systems: Review, challenges and opportunities. Energy AI, 9.","DOI":"10.1016\/j.egyai.2022.100169"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5127","DOI":"10.1109\/TII.2021.3126111","article-title":"Measuring explainability and trustworthiness of power quality disturbances classifiers using XAI\u2014Explainable artificial intelligence","volume":"18","author":"Machlev","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/MC.2021.3071551","article-title":"Explainable AI for chiller fault-detection systems: Gaining human trust","volume":"54","author":"Srinivasan","year":"2021","journal-title":"Computer"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Guerra-Manzanares, A., Nomm, S., and Bahsi, H. (2019, January 16\u201319). Towards the integration of a post-hoc interpretation step into the machine learning Workflow for IoT botnet detection. Proceedings of the 18th IEEE International Conference On Machine Learning and Applications (ICMLA), Boca Raton, FL, USA.","DOI":"10.1109\/ICMLA.2019.00193"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.rser.2019.04.021","article-title":"Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future","volume":"109","author":"Zhao","year":"2019","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.enbuild.2003.10.002","article-title":"AHU sensor fault diagnosis using principal component analysis method","volume":"36","author":"Wang","year":"2004","journal-title":"Energy Build."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3654","DOI":"10.1016\/j.enconman.2008.06.032","article-title":"Multiple faults diagnosis for sensors in air handling unit using Fisher discriminant analysis","volume":"49","author":"Du","year":"2008","journal-title":"Energy Convers. Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2698","DOI":"10.1016\/j.buildenv.2010.05.031","article-title":"A hybrid FDD strategy for local system of AHU based on artificial neural network and wavelet analysis","volume":"45","author":"Fan","year":"2010","journal-title":"Build. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1016\/j.enbuild.2011.06.011","article-title":"Automated FDD of multiple-simultaneous faults (MSF) and the application to building chillers","volume":"43","author":"Han","year":"2011","journal-title":"Energy Build."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.buildenv.2013.11.021","article-title":"Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis","volume":"73","author":"Du","year":"2014","journal-title":"Build. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.enbuild.2013.12.038","article-title":"Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks","volume":"72","author":"Du","year":"2014","journal-title":"Energy Build."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liao, H., Cai, W., Cheng, F., Dubey, S., and Rajesh, P.B. (2021). An online data-driven fault diagnosis method for air handling units by rule and convolutional neural networks. Sensors, 21.","DOI":"10.3390\/s21134358"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/j.ijrefrig.2020.10.023","article-title":"Novel chiller fault diagnosis using deep neural network (DNN) with simulated annealing (SA)","volume":"121","author":"Han","year":"2021","journal-title":"Int. J. Refrig."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.ijrefrig.2020.08.014","article-title":"A hybrid deep forest approach for outlier detection and fault diagnosis of variable refrigerant flow system","volume":"120","author":"Zeng","year":"2020","journal-title":"Int. J. Refrig."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, G., Yao, Q., Fan, C., Zhou, C., Wu, G., Zhou, Z., and Fang, X. (2021). An explainable one-dimensional convolutional neural networks based fault diagnosis method for building heating, ventilation and air conditioning systems. Build. Environ., 203.","DOI":"10.1016\/j.buildenv.2021.108057"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Montazeri, A., and Kargar, S.M. (2020). Fault detection and diagnosis in air handling using data-driven methods. J. Build. Eng., 31.","DOI":"10.1016\/j.jobe.2020.101388"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kaplan, H., Tehrani, K., and Jamshidi, M. (2021). A fault diagnosis design based on deep learning approach for electric vehicle applications. Energies, 14.","DOI":"10.3390\/en14206599"},{"key":"ref_21","unstructured":"Sairam, S., Srinivasan, S., Marafioti, G., Subathra, B., Mathisen, G., and Bekiroglu, K. (2020). Explainable Incipient Fault Detection Systems for Photovoltaic Panels. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Cepeda, C., Orozco-Henao, C., Percybrooks, W., Pulgar\u00edn-Rivera, J.D., Montoya, O.D., Gil-Gonz\u00e1lez, W., and V\u00e9lez, J.C. (2020). Intelligent fault detection system for microgrids. Energies, 13.","DOI":"10.3390\/en13051223"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.mechatronics.2013.11.009","article-title":"Data-driven design of robust fault detection system for wind turbines","volume":"24","author":"Yin","year":"2014","journal-title":"Mechatronics"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cheng, F., Cai, W., Zhang, X., Liao, H., and Cui, C. (2021). Fault detection and diagnosis for Air Handling Unit based on multiscale convolutional neural networks. Energy Build., 236.","DOI":"10.1016\/j.enbuild.2021.110795"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Calvaresi, D., Najjar, A., Schumacher, M., and Fr\u00e4mling, K. (2019). Explainable artificial intelligence based heat recycler fault detection in air handling unit. Lecture Notes in Computer Science, Springer Nature Switzerland AG.","DOI":"10.1007\/978-3-030-30391-4"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.enbuild.2016.09.039","article-title":"A decision tree based data-driven diagnostic strategy for air handling units","volume":"133","author":"Yan","year":"2016","journal-title":"Energy Build."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Belikov, J., Meas, M., Machlev, R., Kose, A., Tepljakov, A., Loo, L., Petlenkov, E., and Levron, Y. (2022, January 14\u201316). Explainable AI based fault detection and diagnosis system for air handling units. Proceedings of the International Conference on Informatics in Control, Automation and Robotics, Lisbon, Portugal.","DOI":"10.5220\/0011350000003271"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_29","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Akhlaghi, Y.G., Aslansefat, K., Zhao, X., Sadati, S., Badiei, A., Xiao, X., Shittu, S., Fan, Y., and Ma, X. (2021). Hourly performance forecast of a dew point cooler using explainable Artificial Intelligence and evolutionary optimisations by 2050. Appl. Energy, 281.","DOI":"10.1016\/j.apenergy.2020.116062"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Antwarg, L., Miller, R.M., Shapira, B., and Rokach, L. (2021). Explaining anomalies detected by autoencoders using Shapley Additive Explanations. Expert Syst. Appl., 186.","DOI":"10.1016\/j.eswa.2021.115736"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"740","DOI":"10.3390\/make3030037","article-title":"Explainable artificial intelligence for human decision support system in the medical domain","volume":"3","author":"Malhi","year":"2021","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1016\/j.enbuild.2014.06.042","article-title":"A review of fault detection and diagnosis methodologies on air-handling units","volume":"82","author":"Yu","year":"2014","journal-title":"Energy Build."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6338\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T09:31:09Z","timestamp":1722763869000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,23]]},"references-count":33,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22176338"],"URL":"https:\/\/doi.org\/10.3390\/s22176338","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,8,23]]}}}