Explainable AI for Chiller Fault-Detection Systems: Gaining Human Trust

Srinivasan, Seshadhri; Arjunan, Pandarasamy; Jin, Baihong; Sangiovanni-Vincentelli, A.; Sultan, Zuraimi; Poolla, Kameshwar

doi:10.1109/mc.2021.3071551

Cited by 25 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting result observed by the authors is the possibility of removing weather sensors and using climate time-series data instead. Srinivasan et al [169] used LIME for chiller FDD, inspecting issues such as scaling in condenser fins, sensor errors caused by flow pulsations, and false alarms. They showed that the LIME's ability to provide contradicting information plays a dual role: it assists decision-makers in identifying faults and can identify false alarms generated by "black box" models.…”

Section: Local Interpretable Model-agnostic Explanationsmentioning

confidence: 99%

A Future Direction of Machine Learning for Building Energy Management: Interpretable Models

Gugliermetti,

Cumo,

Agostinelli

2024

Energies

View full text Add to dashboard Cite

Machine learning (ML) algorithms are now part of everyday life, as many technological devices use these algorithms. The spectrum of uses is wide, but it is evident that ML represents a revolution that may change almost every human activity. However, as for all innovations, it comes with challenges. One of the most critical of these challenges is providing users with an understanding of how models’ output is related to input data. This is called “interpretability”, and it is focused on explaining what feature influences a model’s output. Some algorithms have a simple and easy-to-understand relationship between input and output, while other models are “black boxes” that return an output without giving the user information as to what influenced it. The lack of this knowledge creates a truthfulness issue when the output is inspected by a human, especially when the operator is not a data scientist. The Building and Construction sector is starting to face this innovation, and its scientific community is working to define best practices and models. This work is intended for developing a deep analysis to determine how interpretable ML models could be among the most promising future technologies for the energy management in built environments.

show abstract

Section: Local Interpretable Model-agnostic Explanationsmentioning

confidence: 99%

A Future Direction of Machine Learning for Building Energy Management: Interpretable Models

Gugliermetti,

Cumo,

Agostinelli

2024

Energies

View full text Add to dashboard Cite

show abstract

“…For chiller malfunction detection systems, Srinivasan et al [15] showed the rank of understandable AI (XAI). One-dimensional convolutional neural networks (CNNs) were created by Li et al [16] for defect identification in HVAC systems.…”

Section: Related Workmentioning

confidence: 99%

“…Consequently, to get any meaningful information from the cleaned IoT sensor data, the raw sensor data must be cleaned [12,13]. A constrained IoT sensor network can also lead to high computational expenses and overuse of resources because of the vast amount of unwanted and worthless data [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Using Data Fusion with Ensemble Deep Learning Technique in IIoT

Venkatasubramanian¹,

Raja

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Detecting the breakdown of industrial IoT devices is a major challenge. Despite these challenges, real-time sensor data from the industrial internet of things (IIoT) present several advantages, such as the ability to monitor and respond to events in real time. Sensor statistics from the IIoT can be processed, fused with other data sources, and used for rapid decision-making. The study also discusses how to manage denoising, missing data imputation, and outlier discovery using preprocessing. After that, data fusion techniques like the direct fusion technique are used to combine the cleaned sensor data. Fault detection in the IIoT can be accomplished by using a variety of deep learning models such as PropensityNet, deep neural network (DNN), and convolution neural networks-long short term memory network (CNS-LSTM). According to various outcomes, the suggested model is tested with Case Western Reserve University (CWRU) data. The results suggest that the method is viable and has a good level of accuracy and efficiency.

show abstract

“…However, the black-box nature of the proposed data-driven-based technique prevents the field engineers from considering them trustworthy enough for real-life deployment. To overcome this issue, explainable AI (XAI) [22,23] has been used to interpret the internal processing and decision-making process of the proposed fault isolation model in human-understandable terms.…”

Section: Introductionmentioning

confidence: 99%

An explainable deep learning approach for detection and isolation of sensor and machine faults in predictive maintenance paradigm

Sinha,

Das

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The predictive health maintenance techniques identify the machine faults by analyzing the data collected by low-cost sensors assuming that sensors are free from any faults. However, aging and environmental condition cause sensors also be faulty, leading to incorrect interpretations of the collected data and subsequently resulting in erroneous machine health predictions. To mitigate this problem, this paper proposes a hybrid model that can differentiate between sensor and system faults. The data used for training the model is collected from a power system hardware setup by experimental procedures. A Convolutional Neural Network (CNN) model is used to extract optimized features from the raw data automatically, which are then fed to the XGBoost model for sensor and machine fault isolation with an overall accuracy of 98.15%. The data having sensor fault was then fed to a Deep Autoencoder (DAE), which eliminated the sensor fault components and reconstructed the data with an average RMSE of 0.0576. Thereafter, the corrected signal was used to detect the system fault using the hybrid CNN-XGBoost model with 99.77% accuracy. Therefore, by isolating the sensor faults, the proposed technique establishes better confidence in predictive maintenance. Further, Explainable AI has been utilized to interpret the model prediction in human-understandable terms in order to increase trustworthiness. 

show abstract

Explainable AI for Chiller Fault-Detection Systems: Gaining Human Trust

Cited by 25 publications

References 16 publications

A Future Direction of Machine Learning for Building Energy Management: Interpretable Models

A Future Direction of Machine Learning for Building Energy Management: Interpretable Models

Fault Diagnosis Using Data Fusion with Ensemble Deep Learning Technique in IIoT

An explainable deep learning approach for detection and isolation of sensor and machine faults in predictive maintenance paradigm

Contact Info

Product

Resources

About