Existing technology has limitations in the implementation of predictive maintenance strategies, particularly the condition monitoring systems of presses or forming machines. Robust and flexible industrial technological solutions equipped with smart self-monitoring functions are needed that will allow companies and operators to more effectively plan when maintenance activities are necessary or when components have to be replaced. This will result in reduced downtime, costs and energy consumption. The EU-funded project 'A novel decision support system for intelligent maintenance' (IMAIN) is developing an advanced cloud-based monitoring and predictive maintenance solution for forming machines. The system will integrate embedded information devices, artificial intelligence methods and an eMaintenance cloud for collecting data with novel reliability and maintenance practices. Work began with an analysis of production equipment and key components of the overall system, followed by the creation of a condition and energy monitoring plan. Simulation models have been developed for the virtual sensors. These innovative sensors are expected to provide an entirely holistic and novel approach to predictive maintenance. They will support sensors currently fitted in forming machines by delivering an accurate and optimal way to virtually monitor stress and strain. Project partners have defined the hardware and software architecture of the embedded condition and energy monitoring system (ECEM). They also delivered prototypes and chose condition and energy evaluation parameters for both components. The self-sufficient ECEM will be part of the envisaged predictive maintenance system. The team is developing the required information technology infrastructure and interface that will be included in ECEM. This will also support the IMAIN system. Work is also underway on a cloud solution for the sharing and storage of monitored data like mechanical stresses, guidance temperatures, bearing vibrations, oil parameters, air and energy consumptions as well as technological parameters like ram tilting and forming forces. In the eMaintenance cloud these data will be long-term evaluated regarding trends as well as remaining useful life (RUL). A major benefit of the cloud approach is the possibility to learn from differently located machines for improved RUL estimation. The overall system architecture has been developed and the hardware and software have been specified. IMAIN will ultimately lead to increased system lifetime for production equipment, lower maintenance costs, and greater reliability of the entire operation, production and maintenance process.
Production equipment, predictive maintenance, presses, forming machines, intelligent maintenance, Industry 4.0