Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS
Content archived on 2024-05-07

Monitoring and control of chemical and biochemical processes based on the utilization of neural networks

Objective

The aim of this project is to develop a software package capable of assisting design engineers in the setting up and tuning of control algorithms for complex, non-linear chemical processes.

The design of algorithms will make use of neural network techniques, that do not require any specific knowledge of the process physico-chemical mechanisms. The software will be PC-based Computer Aided Engineering (CAE) tools composed of sophisticated modules for the identification of the process behaviour and for the design of efficient control algorithms. It will be interfaced with the Distributed Control Systems (DCS) in charge of process control, in order to provide optimal on-line control of the process.

The MONNET CAE tool will allow chemical and biochemical processes to be run with a high level of accuracy and minimum deviation from prescribed operating conditions, enabling the standards imposed by the product markets and public authorities to be met easily, thus facilitating the acquisition of ISO9002 certification. In order to demonstrate the capability of the software package to derive generic non-linear control strategies, as well as the wide dissemination possibilities of the new product in the biochemical and chemical industries, the MONNET package will be implemented and tested on two industrial applications:
- Penicillin production at Antibioticos
- Epichlorhydrine production at Solvay

The first application is a typical fed-batch process such as those found in the bioprocess or fine chemistry industries; the second features a reactive distillation unit, that may be representative of complex continuous chemical processes. For the implementation of the MONNET CAE tools, the consortium will make use of techniques based upon artificial neural network methodologies and fuzzy sets.

Two neural network topologies developed by the university partner will be studied and compared, both of which are highly innovative but at a stage that they can be evaluated and applied in a robust way to both batch and continuous plants exemplified by those at Antibioticos and Solvay. These two approaches will be combined to form a new powerful neuro-controller.

The use of MONNET as a process controller is expected to yield the following benefits:
- reduction of raw material consumption
- reduction of lost commercial product in the effluents
- improvement of product capability
- reduction in process development time

An assessment of the existing operations at the industrial-users leads them to believe that the application of MONNET will provide them with high annual gains approaching 1 MECU per production plant. With this commitment it is easy to envisage the high level of profitability that the MONNET project should provide, when installed on several hundreds of chemical reactors, which constitutes the potential market for the software package in Europe.

It is intended that the MONNET package will be made available to chemical and biochemical industries by the consortium through licence concessions and support services offered by the partners in the field of control design.

Programme(s)

Multi-annual funding programmes that define the EU’s priorities for research and innovation.

Topic(s)

Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.

Call for proposal

Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.

Data not available

Funding Scheme

Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.

CSC - Cost-sharing contracts

Coordinator

Bertin & Cie Sa
EU contribution
No data
Address
Rue Pierre Curie 59/3
78373 Plaisir
France

See on map

Total cost

The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.

No data

Participants (4)

My booklet 0 0