Data analysis and feature selection for predictive maintenance: A case-study in the metallurgic industry

Fernandes, Marta; Canito, Alda; Bolón-Canedo, Verónica; Conceição, Luís; Praça, Isabel; Marreiros, Goreti

doi:10.1016/j.ijinfomgt.2018.10.006

Cited by 44 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Literature shows that data-driven analytics can be used to gain knowledge for decision-making and thereby help companies their operation's productivity [34]. In this context, there are different types of machine learning (ML) techniques that have been used in various phases of PdM implementation [19], [38]. Recent review studies performed by G. -Y.…”

Section: Related Workmentioning

confidence: 99%

Multi-Machine Gaussian Topic Modeling for Predictive Maintenance

2021

View full text Add to dashboard Cite

In this paper, we propose a coherent framework for multi-machine analysis, using a group clustering model, which can be utilized for predictive maintenance (PdM). The framework benefits from the repetitive structure posed by multiple machines and enables for assessment of health condition, degradation modeling and comparison of machines. It is based on a hierarchical probabilistic model, denoted Gaussian topic model (GTM), where cluster patterns are shared over machines and therefore it allows one to directly obtain proportions of patterns over the machines. This is then used as a basis for cross comparison between machines where identified similarities and differences can lead to important insights about their degradation behavior. The framework is based on aggregation of data over multiple streams by a predefined set of features extracted over a time window. Moreover, the framework contains a clustering schema which takes uncertainty of cluster assignments into account and where one can specify a desirable degree of reliability of the assignments. By using a multi-machine simulation example, we highlight how the framework can be utilized in order to obtain cluster patterns and inherent variations of such patterns over machines. Furthermore, a comparative study with the commonly used Gaussian mixture model (GMM) demonstrates that GTM is able to identify inherent patterns in the data while the GMM fails. Such result is a consequence of the group level being modeled by the GTM while being absent in the GMM. Hence, the GTM are trained with a view on the data that is not available to the GMM with the consequence that the GMM can miss important, possibly even key, cluster patterns. Therefore, we argue that more advanced cluster models, like the GTM, can be key for interpreting and understanding degradation behavior across machines and ultimately for obtaining more efficient and reliable PdM systems.INDEX TERMS exploratory data analysis, cluster analysis, Gaussian topic modeling, hierarchical modeling, multi-machine analysis, multiple data streams, predictive maintenance

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Machine Gaussian Topic Modeling for Predictive Maintenance

2021

View full text Add to dashboard Cite

show abstract

“…State-of-the art PdM often rely on data-driven analysis, as modern physical asset's are growing increasingly more complex and it is often intractable to apply classical engineering methods to mathematically describe such an asset's conditions [15,17]. In data-driven PdM analysis, the asset's condition is monitored directly from sensor measurement data, and the data observations are analyzed using numerical methods (e.g.…”

Section: Shannonmentioning

confidence: 99%

“…Machine learning (ML) is a computer system's use of algorithms to adapt to new environments or scenarios, and to identify and make inference on patterns [20][21][22]. Through many successful applications of ML algorithms in domains such as computer vision and robotics, ML continues to gain attention in the PdM domain and is widely applied across a broad range of maintenance applications [13,17,23]. However, classical and modern ML algorithms are not exempt to errors.…”

Section: Shannonmentioning

confidence: 99%

“…The current ML algorithm research proves that the data form or representation used to train and test ML algorithms has a great impact on algorithm performance and accuracy [17,24]. Generally, ML algorithms trained and tested on poor quality data generate poor performance and accuracy [20].…”

Section: Shannonmentioning

confidence: 99%

“…Poorly trained ML-based PdM models, from improper asset data representation, can leave some ML-based PdM tools vulnerable to high rates of inaccurate fault identification and/or time-of-failure prediction results [17,18,31]. This could potentially lead to value loss during an asset's life cycle.…”

Section: Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

Achieving a representation of asset data conducive to machine learning driven predictive maintenance

Aremu¹

View full text Add to dashboard Cite

The success of an operation in industries such as mining, aviation, and industrial manufacturing is heavily dependent on the continuous functioning of complex systems. These complex systems are often considered critical physical assets and their reliability is significantly correlated to a successful and productive operation. The unexpected failure of an asset results in high maintenance costs, loss in profits, reduced human safety, and hazardous environmental impacts.

show abstract

Predictive models with end user preference

Zhao

Yang

Bolnykh

et al. 2021

Statistical Analysis

View full text Add to dashboard Cite

Classical machine learning models typically try to optimize the model based on the most discriminatory features of the data; however, they do not usually account for end user preferences. In certain applications, this can be a serious issue as models not aware of user preferences could become costly, untrustworthy, or privacy‐intrusive to use, thus becoming irrelevant and/or uninterpretable. Ideally, end users with domain knowledge could propose preferable features that the predictive model could then take into account. In this paper, we propose a generic modeling method that respects end user preferences via a relative ranking system to express multi‐criteria preferences and a regularization term in the model's objective function to incorporate the ranked preferences. In a more generic perspective, this method is able to plug user preferences into existing predictive models without creating completely new ones. We implement this method in the context of decision trees and are able to achieve a comparable classification accuracy while reducing the use of undesirable features.

show abstract

Data analysis and feature selection for predictive maintenance: A case-study in the metallurgic industry

Cited by 44 publications

References 20 publications

Multi-Machine Gaussian Topic Modeling for Predictive Maintenance

Multi-Machine Gaussian Topic Modeling for Predictive Maintenance

Achieving a representation of asset data conducive to machine learning driven predictive maintenance

Predictive models with end user preference

Contact Info

Product

Resources

About