The PUMP experiment

Predictive Upcycling Maintenance Platform

The PUMP project will apply existing non-intrusive energy monitoring tools and advanced ML models to analyse the patterns in electrical loads of machinery equipment, disaggregate component loads, and detect deviations from normal operation in a food processing plant. The project will use the services and technologies of KYKLOS 4.0 project for production optimization; PUMP focuses on Predictive maintenance and will harness the holistic approach of KYKLOS 4.0 to offer enhanced features through the collaborative platform. Data collected from the factory shop-floor regarding the production process and energy consumption of various equipment will be used alongside the technologies of the industrial partners and services of KYKLOS 4.0 platform. Services such as the Maintenance Scheduler will be combined with energy disaggregation and energy analytics to support energy efficiency and efficient machinery health monitoring (MhM). LCA simulations engine will support process efficiency and reduction of waste by producing useful LCA indicators and the Decision Support System will fuse data and enable circular economy features to the developed system. PUMP will utilize various KYKLOS 4.0 services and features and enhance already developed tools to tackle the problem of energy and process efficiency and circularity by combining the outputs of these tools with the DSS system of KYKLOS 4.0.

Energy Efficiency

The experiment will utilize KYKLOS 4.0 components along with the already developed tools to for real-time energy monitoring of the various process lines and deliver Energy Efficiency tips and increase the circular approach of the industry.

Fault detection

Utilizing the Energy Monitoring System and the advanced algorithms and methods for signal analysis and anomaly detection, alerts will be generated regarding possible faults in the monitored devices.

Process optimization

The whole process of the industrial shop floor is monitored and specific process modifications may be suggested following to optimize the process line in terms of efficiency, time, or waste reduction, utilizing the LCA component of KYKLOS 4.0

Maintenance planning

Utilizing the KYKLOS 4.0 component "Maintenance Scheduler" and the tools of the project partners, the end-users will be able to plan more efficiently their maintenance actions and ensure proper and timely service of the equipment.

Technology

The partners will combine their already developed tools and services, including the energy monitoring system, the IoT platform, the Machinery Health Monitoring algorithms, the energy disaggregation algorithms and the energy analytics tools, along with expertize from the industry experts, while also integrating several KYKLOS 4.0 components such as the Maintenance Scheduler, the LCA tool, the KYKLOS backend and the DSS. The combination of these technologies results towards EE recommendations, tips, optimal process and maintenance planning as well as equipment specific indicators that will allow the health monitoring process to identify possible signal anomalies.

LEAFLET

POSTER

VIDEO

VRUMP

PLEGMA LABS

HELIOS BAKERY

The PUMP Experiment

has indirectly received funding from the European Union’s Horizon 2020 research and innovation action programme, via the KYKLOS 4.0 Open Call #2 issued and executed under the KYKLOS 4.0 project (Grant Agreement No 872570)

More Info