Explainable Artificial Intelligence for Fault Diagnosis of Industrial Processes

Jang, Kyojin; Pilario, Karl Ezra S.; Lee, Nayoung; Moon, Il; Na, Jonggeol

doi:10.1109/tii.2023.3240601

Cited by 12 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bi et al [654] acknowledged the need for incorporating both human and machine intelligence to develop smart systems, emphasizing the role of interpretability to make humans trust in machine intelligence. The authors identified three approaches to achieve interpretability: intrinsic interpretable models, such as Bayesian neural networks [533]; enhancing black-box models, like deep neural networks, with interpretability capabilities [327,328,[666][667][668]; and employing model-agnostic methods [390,669,670] such as LIME (local interpretable model-agnostic explanations) [671] and SHAP (Shapley additive explanations) [672]. Several recent publications have surveyed interpretability techniques for machine learning models [673][674][675][676][677][678][679].…”

Section: Model Interpretabilitymentioning

confidence: 99%

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

Melo,

Câmara,

Pinto

2024

Processes

View full text Add to dashboard Cite

This paper presents a comprehensive review of the historical development, the current state of the art, and prospects of data-driven approaches for industrial process monitoring. The subject covers a vast and diverse range of works, which are compiled and critically evaluated based on the different perspectives they provide. Data-driven modeling techniques are surveyed and categorized into two main groups: multivariate statistics and machine learning. Representative models, namely principal component analysis, partial least squares and artificial neural networks, are detailed in a didactic manner. Topics not typically covered by other reviews, such as process data exploration and treatment, software and benchmarks availability, and real-world industrial implementations, are thoroughly analyzed. Finally, future research perspectives are discussed, covering aspects related to system performance, the significance and usefulness of the approaches, and the development environment. This work aims to be a reference for practitioners and researchers navigating the extensive literature on data-driven industrial process monitoring.

show abstract

Section: Model Interpretabilitymentioning

confidence: 99%

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

Melo,

Câmara,

Pinto

2024

Processes

View full text Add to dashboard Cite

show abstract

“…Togo et al 9 provided an Explainable framework for toxicity prediction. Jang et al 10 5 and has become very popular in prediction of complex machine learning models. Nguyen et al 12 employed LIME for Prediction of Parkinson's Disease Depression.…”

Section: Previous Work On Explainablementioning

confidence: 99%

“…Togo et al provided an Explainable framework for toxicity prediction. Jang et al augmented Fault Diagnosis of Industrial Processes modeling with SHAP explanations. Fatahi et.al .…”

Section: Explainable Ai Model For Drop Size Estimation In An Rdcmentioning

confidence: 99%

Interpretation of Drop Size Predictions from a Random Forest Model Using Local Interpretable Model-Agnostic Explanations (LIME) in a Rotating Disc Contactor

Prabhu

Sane

Dhadwal

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Drop size is a crucial parameter for the efficient design and operation of the rotating disc contactor (RDC) in liquid–liquid extraction. The current work focuses on providing local and global explanations for the prediction of the drop size in a rotating disc contactor (RDC). The Random Forest (RF) regression model is a robust machine learning algorithm that can accurately capture complex relationships in the data. However, the interpretability of the model is limited. In order to address the issue of interpretability of the developed RF model, in the current work, we employed Local Interpretable Model-Agnostic Explanations (LIME) of the predictions of the RF model. This provides both local and global views of the model and thereby helps one to gain insights into the factors influencing predictions. We have provided local explanations depicting the impact of different attributes on the prediction of the output for any given input example. We have also obtained global feature importance, providing the top subset of informative attributes. We have also developed local surrogate models incorporating second order attribute interactions. This has provided important information about the effect of interactions on the drop size prediction. By augmenting the random forest model with LIME, it is possible to develop a more accurate and interpretable model for estimating the drop size in RDCs, ultimately leading to improved performance and efficiency.

show abstract

Artificial intelligence and machine learning at various stages and scales of process systems engineering

Srinivasan,

Puliyanda,

Thosar

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

We review the utility and application of artificial intelligence (AI) and machine learning (ML) at various process scales in this work, from molecules and reactions to materials to processes, plants, and supply chains; furthermore, we highlight whether the application is at the design or operational stage of the process. In particular, we focus on the distinct representational frameworks employed at the various scales and the physics (equivariance, additivity, injectivity, connectivity, hierarchy, and heterogeneity) they capture. We also review AI techniques and frameworks important in process systems, including hybrid AI modelling, human‐AI collaborations, and generative AI techniques. In hybrid AI models, we emphasize the importance of hyperparameter tuning, especially in the case of physics‐informed regularization. We highlight the importance of studying human‐AI interactions, especially in the context of automation, and distinguish the features of human‐complements‐AI systems from those of AI‐complements‐human systems. Of particular importance in the AI‐complements‐human framework are model explanations, including rule‐based explanation, explanation‐by‐example, explanation‐by‐simplification, visualization, and feature relevance. Generative AI methods are becoming increasingly relevant in process systems engineering, especially in contexts that do not belong to ‘big data’, primarily due to the lack of high quality labelled data. We highlight the use of generative AI methods including generative adversarial networks, graph neural networks, and large language models/transformers along with non‐traditional process data (images, audio, and text).

show abstract

Explainable Artificial Intelligence for Fault Diagnosis of Industrial Processes

Cited by 12 publications

References 0 publications

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

Data-Driven Process Monitoring and Fault Diagnosis: A Comprehensive Survey

Interpretation of Drop Size Predictions from a Random Forest Model Using Local Interpretable Model-Agnostic Explanations (LIME) in a Rotating Disc Contactor

Artificial intelligence and machine learning at various stages and scales of process systems engineering

Contact Info

Product

Resources

About