Abstract

Maintenance is one of the most important aspects in industrial and production environments. Predictive maintenance is an approach that aims to schedule maintenance tasks based on historical data in order to avoid machine failures and reduce the costs due to unnecessary maintenance actions. Approaches for the implementation of a maintenance solution often differ depending on the kind of data to be analyzed and on the techniques and models adopted for the failure forecasts and for maintenance decision-making. Nowadays, Industry 4.0 introduces a flexible and adaptable manufacturing concept to satisfy a market requiring an increasing demand for customization. The adoption of vendor-specific solutions for predictive maintenance and the heterogeneity of technologies adopted in the brownfield for the condition monitoring of machinery reduce the flexibility and interoperability required by Industry 4.0. In this paper a novel approach for the definition of a generic and technology-independent model for predictive maintenance is presented. Such model leverages on the concept of the Reference Architecture Model for Industry (RAMI) 4.0 Asset Administration Shell, as a means to achieve interoperability between different devices and to implement generic functionalities for predictive maintenance.

Highlights

  • Maintenance is of paramount importance for industrial or production plants

  • predictive maintenance (PdM) is referred to in the literature as condition-based maintenance (CBM) since it uses actual operating conditions of the equipment to predict the future state of the machine, using a model defined on the basis of historical data [2]

  • This paper assesses the state of the art PdM and generalizes the steps and the functionalities needed for the definition of a model able to describe every PdM solution in terms of a combination of generic functionalities. This is of paramount importance in the context of Industry 4.0 and smart manufacturing, where production systems adapt their configuration on the basis of the enterprise needs; replacing machinery or adding new devices in the production configuration may harm the PdM program

Read more

Summary

Introduction

Maintenance is of paramount importance for industrial or production plants. The main aim of maintenance is maximizing the production of the plant whilst reducing the costs as much as possible. Another important aspect, is the transmission of heterogeneous data coming from devices to the enterprise levels; such data must be presented in a uniform manner to guarantee a vertical integration between the several components of the PdM solution To cope with this issue, the fourth industrial revolution introduced the concept of cyber-physical systems (CPS) and digital twins (DT) to create a uniform digital representation of assets in the production value chain. This digitalization process allowed the definition of further novel approaches to PdM, like those discussed in [10,11].

Related Studies
Background
Overview on Predictive Maintenance
Data Acquisition
Data Processing
Maintenance Decision-Making
Overview of Asset Administration Shell
Structure of the AAS
The “semantic repository”
AAS-Based Model for Predictive Maintenance
Logical Blocks for PdM
Schedule
AAS Submodel Supporting PdM
Description of the PdM Model
Case Study
Description of the Case Study
Representing the Case Study in Terms of the PdM Model
Findings
Conclusions and Outlook
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call