FUDIPO is a project funded by the European Commission under the H2020 programme, SPIRE-02-2016: "Plant-wide monitoring and control of data-intensive processes", which started on October 1st, 2016 and ends on 30th September 2020.
The project is coordinated by Mälardalen University, and the consortium is composed of energy experts, applied mathematicians, and software engineering experts to face the SPIRE topic. The process industry needs solutions to reduce operating costs, environmental performance footprint and quality of the products. Thus, FUDIPO is developing and testing (in ﬁve case studies) advanced dynamic physical (complemented with soft sensors) and statistical models, like Bayesian networks and machine learning models, to form advanced diagnostic, decision support, optimization and model predictive control. The system developed will optimize all levels in a factory, integrating the different control levels from the separate production units to mill level by building blocks. Thus, the project aims energy and resource savings as well as better environmental performance in EU industries.
The developed system is implemented in full-scale, and validated in ﬁve case studies:
1. Oil reﬁnery (Tüpras)
Problem: Diesel is produced in a unit where focus is increased production within European standards for distillation point, S content, ﬂash point, etc., whose variation is unmeasured.
FUDIPO: the project brings better process control, reducing give-away product below or above European limits.
2. Large heat and power plant (Mälarenergi)
Problem: The heterogeneity of the waste used for cogeneration plant causes operational problems and challenges in emissions control.
FUDIPO: will improve the control, decreasing downtime, ﬂuctuations, corrosion, fouling and agglomeration.
3. Waste-water treatment plant (ABB)
Problem: the aeration demand constitutes 50% of the electric energy demand.
FUDIPO: development of control algorithms for a better performance, measuring quality of incoming waste.
4. Pulp and paper industry (Billerud-korsnäs)
Problem: the plant has three ﬁber lines with different pulp qualities. The most important parameter is Kappa number, which measures how much lignin is left in the pulp after the digester, and whose control is difﬁcult.
FUDIPO: more stable process and fault diagnostics due to better control of Kappa number.
5. Micro heat and power turbine (MTT)
Problem: the Total Cost of Ownership of the EnerTwin, as for all CHP systems, heavily depends on the maintenance cost. To reduce these even further improvement of the diagnostics and decision support for installers is needed.
FUDIPO: increasing efﬁciency by supporting-clients by developing condition-based preventive maintenance and planning.
In the FUDIPO project, one platform with primarily commercial software and one with open source software have been developed. In the open source software, the user does not need to pay any license fees, but does not get support to adjust codes or improved functions, which the commercial suppliers can give, but to a speciﬁed cost. In both cases new AI functions are continuously added. This includes ANN (artiﬁcial Neural nets), BN (Bayesian nets), PLS models and other regression models, multi-variate analysis, ML (machine learning), and simulation tools like Open Modelica for building physical models for any application.
This project has received funding from the European Union's Horizon 2020 Research and Innovation Programme Under Grant Agreement No 723523