A Machine Learning Based Health Indicator Construction in Implementing Predictive Maintenance: A Real World Industrial Application from Manufacturing

Kurrewar, Harshad; Bekar, Ebru Turanouglu; Skoogh, Anders; Nyqvist, Per

doi:10.1007/978-3-030-85906-0_65

Cited by 2 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This should consist of various steps such as business understanding and formulation of analysis goals, data understanding using exploratory data analysis (EDA), pre-processing of data, designing of predictive algorithms, and evaluation of performance [17]. In this context, to answer industry (business) requirements and data-related questions, CRISP-DM, a reference model for data mining projects has been applied in some studies related to PdM by using industrial data coming from only one data source which is mainly sensors [8,7]. At the same time, the challenge is to structure and integrate heterogeneous data coming from multiple data sources for building more robust PdM solutions [18].…”

Section: Related Literaturementioning

confidence: 99%

“…The implementation of PdM practices is widely accepted among the manufacturing industries. However, there are some challenges in implementing PdM in real-world industrial environments such as how to structure, analyze, integrate multi-source industrial big data sets, and build robust predictive models enabling maintenance decision support [7]. Therefore, there is a need for more scalable and systematic approaches for analyzing industrial big data and investigating what type of predictive algorithms can be designed for implementation of PdM in real-world industrial environments [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Data Scientific Approach Towards Predictive Maintenance Application in Manufacturing Industry

Duan

Vasudevan

Bekar

et al. 2022

Advances in Transdisciplinary Engineering

Self Cite

View full text Add to dashboard Cite

Most industries have recently started to harness the power of data to assess their performance and improve their production systems for future competitiveness and sustainability. Therefore, utilization of data for obtaining insights through data-driven approaches is invading every domain of industrial applications. Predictive maintenance (PdM) is one of the highest impacted industrial use cases in data-driven applications due to its ability to predict machine failures by implementing machine learning algorithms. This study aims to propose a systematic data scientific approach to provide valuable insights by analysing industrial alarm and event log data, which might further be used for investigation in root cause understanding and planning of necessary maintenance activities. To do that, a Cross-Industry Standard Process for Data Mining (CRISP-DM) is followed as a reference model in this study. The results are presented by first understanding the relationship between alarms and product types being processed in the selected machines by using exploratory data analysis (EDA). Along with this, the behavior of problematic alarms is identified. Afterward, a predictive analysis formulated as a multi-class classification problem is performed using various Machine Learning (ML) models to predict the category of alarm and generate rules to be used for further investigation in maintenance planning. The performance of the developed models is evaluated based on the different metrics and the decision tree model is selected with the higher accuracy score among them. As a theoretical contribution, this study presents an implementation of predictive modeling in a structured way, which uses a systematic data scientific approach based on industrial alarm and event log data. On the other hand, as a practical contribution, this study provides a set of decision rules that can act as decision support for further exploration of possible in-depth root causes through the other contextual data, and hence it gives an initial foundation towards PdM application in the case company.

show abstract