DEVELOPMENT OF A REAL-TIME EXPERT SYSTEM TO IMPROVE INDUSTRIAL PLANTS ELECTRICAL ENERGY EFFICIENCY

Project facts

Project promoter:
CYSNERGY SL
Project Number:
ES02-0089
Target groups
Small and medium-sized enterprises (SME)
Status:
Completed
Initial project cost:
€269,738
Final project cost:
€215,980
From EEA Grants:
€ 31,946
The project is carried out in:
Spain

Description

LEAN CONSUMPTION proposes to measure individual industrial electric charges consumption by means of dedicated, easily installed RF sensors, which allows managers and controllers to know in an exact and transparent manner how their plants are energetically performing in terms of Euros/Unit. It aims to develop a cloud-based computer platform to relate electrical data with sensitive production variables, integrating with systems already existing in plants. Through the implementation of the project results in industry, significant energy savings will be achieved (15-40%). The easiness and speed of hardware deployment will enable a software as a Service Business Model (SaaS), that in upcoming years may even be useful at domestic scale. LEAN CONSUMPTION software will allow managers to gain a deeper understanding of energy efficiency in industrial plants and its relation with productive variables, and a useful multi-platform real time tool devoted to save energy by improving efficiency.

Summary of project results

This project has developed new technical tools for energy efficiency measrument using a wide range of sensors and providing decision criteria, not only based on energy consumption, but also other variables such as production or cost associated with the process, integrating them into an intelligent platform, intuitive and easily accessible to enable company executives to know in detail the energy costs of their business and make decisions on the basis of efficiency strategies suggested by the system. This solution will reduce the power consumption of industrial plants in more than 20%. The system implements Artificial Intelligence techniques to enable their learning as you integrate more data on the entire plant and raises trading strategies based on the series of historical data and user preferences. In addition, the system is safe from unwanted intrusion attempts, and is based on Cloud Computing horizontal elasticity to provide strength and flexibility to the system.

Summary of bilateral results