Explainability and Transparency of Classifiers for Air-Handling Unit Faults Using Explainable Artificial Intelligence (XAI)

被引:19
作者
Meas, Molika [1 ,2 ]
Machlev, Ram [3 ]
Kose, Ahmet [1 ]
Tepljakov, Aleksei [4 ]
Loo, Lauri [1 ]
Levron, Yoash [3 ]
Petlenkov, Eduard [4 ]
Belikov, Juri [2 ]
机构
[1] R8Technol OU, EE-11415 Tallinn, Estonia
[2] Tallinn Univ Technol, Dept Software Sci, EE-12618 Tallinn, Estonia
[3] Technion Israel Inst Technol, Andrew & Erna Viterbi Fac Elect & Comp Engn, IL-3200003 Haifa, Israel
[4] Tallinn Univ Technol, Dept Comp Syst, EE-12618 Tallinn, Estonia
基金
以色列科学基金会;
关键词
buildings; HVAC; fault detection and diagnosis; machine learning; explainable artificial intelligence; XAI; SHAP; XGBoost; NEURAL-NETWORK; DIAGNOSIS; SYSTEM; STRATEGY;
D O I
10.3390/s22176338
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
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.
引用
收藏
页数:29
相关论文
共 33 条
[1]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[2]   Hourly performance forecast of a dew point cooler using explainable Artificial Intelligence and evolutionary optimisations by 2050 [J].
Akhlaghi, Yousef Golizadeh ;
Aslansefat, Koorosh ;
Zhao, Xudong ;
Sadati, Saba ;
Badiei, Ali ;
Xiao, Xin ;
Shittu, Samson ;
Fan, Yi ;
Ma, Xiaoli .
APPLIED ENERGY, 2021, 281
[3]   Explaining anomalies detected by autoencoders using Shapley Additive Explanations [J].
Antwarg, Liat ;
Miller, Ronnie Mindlin ;
Shapira, Bracha ;
Rokach, Lior .
EXPERT SYSTEMS WITH APPLICATIONS, 2021, 186
[4]   Explainable AI based Fault Detection and Diagnosis System for Air Handling Units [J].
Belikov, Juri ;
Meas, Molika ;
Machlev, Ram ;
Kose, Ahmet ;
Tepljakov, Aleksei ;
Loo, Lauri ;
Petlenkov, Eduard ;
Levron, Yoash .
PROCEEDINGS OF THE 19TH INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS (ICINCO), 2022, :271-279
[5]   Intelligent Fault Detection System for Microgrids [J].
Cepeda, Cristian ;
Orozco-Henao, Cesar ;
Percybrooks, Winston ;
Diego Pulgarin-Rivera, Juan ;
Montoya, Oscar Danilo ;
Gil-Gonzalez, Walter ;
Carlos Velez, Juan .
ENERGIES, 2020, 13 (05)
[6]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[7]   Fault detection and diagnosis for Air Handling Unit based on multiscale convolutional neural networks [J].
Cheng, Fanyong ;
Cai, Wenjian ;
Zhang, Xin ;
Liao, Huanyue ;
Cui, Can .
ENERGY AND BUILDINGS, 2021, 236
[8]   Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks [J].
Du, Zhimin ;
Fan, Bo ;
Chi, Jinlei ;
Jin, Xinqiao .
ENERGY AND BUILDINGS, 2014, 72 :157-166
[9]   Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis [J].
Du, Zhimin ;
Fan, Bo ;
Jin, Xinqiao ;
Chi, Jinlei .
BUILDING AND ENVIRONMENT, 2014, 73 :1-11
[10]   Multiple faults diagnosis for sensors in air handling unit using Fisher discriminant analysis [J].
Du, Zhimin ;
Jin, Xinqiao .
ENERGY CONVERSION AND MANAGEMENT, 2008, 49 (12) :3654-3665