Intelligent and Predictive Maintenance in Manufacturing Systems
In industrial production environments, generally characterized by being stochastic, dynamic and chaotic, maintenance is essential to guarantee production efficiency, since the occurrence of unexpected disturbances leads to losses in productivity and business opportunities, essential points to achieve competitiveness.
The Maintenance 4.0 project is an implementation in a real environment of intelligent and predictive maintenance through the development of advanced data analysis applications. These applications will make it possible to reduce unplanned downtime by predicting possible failures.
The goal is to develop industrial applications capable of performing data analysis in real-time to increase productivity and, consequently, business opportunities.
The Project
Within the production reality maintenance is crucial to ensure the production efficiency, since the occurrence of failures leads to a degradation of the system performance, causing the loss of productivity. Traditionally, the implementation of maintenance strategies does not consider the huge amount of data being generated in the shop floor and the emergent ICT technologies, e.g., Internet of Things, Big data, advanced data analytics, cloud computing and augmented reality. Maintenance 4.0 project intends to contribute for the development of a new intelligent and predictive maintenance approach, comprising applied R&D activities focusing the experimental proof-of-concept of new applications based on emergent ICT technologies, developing a prototype to be tested in laboratorial and industrial environments.
The project will introduce intelligent and predictive mechanisms to support the industrial maintenance, minimizing the effects and impact of unexpected failures in the production system, and consequently increasing the competitiveness of manufacturing enterprises, especially the SMEs (Small and Medium Enterprises) where the environment volatility is higher. Maintenance 4.0 idea, depicted in the picture below, comprises data collection using Big Data and loT technologies, advanced data analysis by the use of data mining, machine learning and cloud technologies and early detection of failures and a decision support system implemented by the integration of predictive maintenance algorithms and augmented reality, respectively. All these technologies will interact with the operator through a Human-Machine Interface (HMI).
In short Maintenance 4.0 project aims to develop an intelligent approach for the industrial maintenance, aligned with Industry 4.0 principles, that:
- Considers advanced analysis of the data collected from the shop floor to monitor and detect earlier the occurrence of disturbances at the shop floor and consequently the need to implement maintenance interventions.
- Supports the maintenance technician during the maintenance interventions by providing guided intelligent decision support articulated using human-machine interaction technologies.
This approach will contribute to reduce the unplanned production downtime and to optimize the maintenance interventions and will be evaluated in Catraport, an industrial metal stamping production unit.
Workplan
The Maintenance 4.0 project will last 18 months (October 1st, 2017 – April 1st, 2019) and it comprehends six activities.
Activity 1 is a crucial activity for setting the specification of requirements and the case study scenario.
Activity 2, 3 and 4 receive the input from Activity 1 and the output of these activities will be the input for Activity 5, where the applications will be integrated and validated.
- Activity 2 provides a distributed data collection system.
- Activity 3 implements an advanced data analytics approach to support preventive and predictive maintenance.
- Activity 4 creates interactive and intelligent decision support to maintenance operations.
Activity 5 is specifically devoted to the use case. This activity manages the integration and validation of the developed applications and systems.
Activity 6 covers project management and coordination.
Poster
Partners
