Combining Chronicle Mining and Semantics for Predictive Maintenance in Manufacturing Processes

Submitted by Qiushi Cao on 12/03/2019 - 02:20

Tracking #: 2386-3600

Authors: 
Qiushi Cao
Ahmed Samet
Cecilia Zanni-Merk
François de Bertrand de Beuvron
Christoph Reich

Responsible editor: 
Guest Editors SemWeb of Things for Industry 4.0 - 2019

Submission type: 
Full Paper
Abstract: 
Within manufacturing processes, faults and failures may cause severe economic loss. With the vision of Industry 4.0, artificial intelligence techniques such as data mining play a crucial role in automatic fault and failure prediction. However, data mining results normally lack both machine and human-understandable representation and interpretation of knowledge. This may cause the semantic gap issue, which stands for the incoherence between the knowledge extracted from industrial data and the interpretation of the knowledge from a user. To tackle this issue, in this paper we introduce a novel hybrid approach to facilitate predictive maintenance tasks in manufacturing processes. The proposed approach is a combination of data mining and semantics, within which chronicle mining is used to predict the future failures of the monitored industrial machinery, and a Manufacturing Predictive Maintenance Ontology (MPMO) with its rule-based extension is used to predict temporal constraints of failures and to represent the predictive results formally. As a result, Semantic Web Rule Language (SWRL) rules are constructed for predicting occurrence time of machinery failures in the future. The proposed rules provide explicit knowledge representation and semantic enrichment of failure prediction results, thus easing the understanding of the inferred knowledge. A case study on a semi-conductor manufacturing process is used to demonstrate our approach in detail.
Full PDF Version: 
PDF icon swj2386.pdf
Revised Version:
Combining Chronicle Mining and Semantics for Predictive Maintenance in Manufacturing Processes
Previous Version: 
Combining Chronicle Mining and Semantics for Predictive Maintenance in Manufacturing Processes
Tags: 
Reviewed

Decision/Status: 
Minor Revision

Solicited Reviews:
Click to Expand/Collapse
Review #1
Anonymous submitted on 24/Feb/2020
Suggestion:
Minor Revision
Review Comment:

This paper introduces a hybrid approach to facilitate predictive maintenance tasks in manufacturing processes. A case study on a semi-conductor manufacturing process is used to demonstrate the approach in detail.

The paper is well-structured and easy to follow. The followings are some of the suggestions, the authors may consider to revise the paper accordingly:
- Abstract should describe the state-of-the-art technology briefly.
- The evaluation results and their conclusion should be presented in the abstract briefly.
- The scope of the proposed approach should be mentioned. The limitations of the proposed approach should be mentioned clearly.
- It would be better if the paper should spend one separate section in the Introduction section on case study as the topic of the paper is very relevant to Industry 4.0.
- Time complexity of the proposed Algorithm (Algorithm 1) should be provided.
- The author may consider to provide a detailed description of tools used for the evaluation.
- What are the rationale behind to choose these tools for the evaluation?

Review #2
Anonymous submitted on 25/Feb/2020
Suggestion:
Accept
Review Comment:

This manuscript was submitted as 'full paper' and should be reviewed along the usual dimensions for research contributions which include (1) originality, (2) significance of the results, and (3) quality of writing.

I thank authors for considering my comments during the first revision and updating the paper accordingly. I am happy with the updates and glad to give an acceptance to this paper. I would recommend authors to carefully proof read for any overlooked typos or formatting issues.