Obiettivo
The academic/industrial consortium of proposers (involving two universities, a research institute and a control-systems supplier) aims to address the above industrial process problems. Such a project should exploit fully the firm theoretical background of the partners as well as their experience in developing particular decision-support tools for complex industrial processes.
Primarily, the decision-support tool will be based on clustering multidimensional process data acquired from industrial machinery using the novel, effective and computationally efficient Mean-Tracking (M-T) clustering algorithm. The located clusters of data points will then be used to determine good and erroneous plant operating regions to help operators predict and avoid system failures.
Since much of the M-T algorithm parameter tuning still depends on experts, the theoretical aim of the project involves investigating the fusion between clustering and Bayesian probabilistic approaches, so that not only can the possibility of incorrect tuning be minimised, but also that it can be generalised to cater for a wide range of industrial applications.
The practical side of the project will begin with performing cluster analysis of process data acquired from a metal strip producer machinery (COMPUREG) using the innovated M-T algorithm. Such an analysis will be closely linked with the theoretical ideas which may emerge from the fusion between data clustering and Bayesian probabilistic approaches. Upon a set of promising/encouraging results, implementation of the algorithm on the actual industrial machinery is anticipated. Successful implementation may lead to further implementation on other similar industrial applications.
As the case with many decision-support tools, an adequate graphical interface is needed. Although its design should be kept relatively simple, it can be appropriately detailed to prevent loss of information gained from the internal multivariate analysis algorithm. Being more appropriately seen as a long term aim, a graphical interface of such a design will make the M-T algorithm an efficient aid to the perator.
Approach to achieve the objectives
The academic partners will investigate data clustering and probabilistic approaches to the complex "information mining" problem. The industrial partner COMPUREG will provide the necessary industrial plant data along with the technical knowledge to lead investigations in the direction consistent with real industrial requirements.
Expected Results
From the results of the first phase, it will be possible to measure the degree of success in both the practical and theoretical aspects of the project, namely:
- By the quality of results of M-T cluster analysis on the metal strip producer data (also assessed in terms of alternative machine performances employing other state-of-the-art techniques such as; statistical process control, finite mixtures of distribution and other density search clustering algorithms). The potential of the M-T approach for real implementation on the metal strip producer itself as well as other similar industrial applications will be assessed.
- How "information mining" using clustering and bayesian probabilistic approaches can be employed to established a rigorous foundation for, and possible expansion to the M-T cluster algorithm and its parameter tuning. In addition, the efficiency and accuracy in performance of the algorithm will also be measured.
A possible second phase would aim at developing a full decision support tool.
Currently there exists an urgent need for industrial producers to minimise down time caused by process malfunction and maintenance. Large amounts of multivariable process data acquired from modern control systems contain hidden valuable, and complex information which is often left un-analysed until such time as system failures/problems occur and diagnosis for rectification is needed. The objective of the overall project is to build an advanced decision-support tool to mine such information automatically, effectively and efficiently. Theoretically, such a tool will be based on clustering and Bayesian Probabilistic approaches from which located clusters will be used to determine good and erroneous plant operating regions. In practical terms, the tool will provide operators with highly-concentrated, on-line information about the controlled/monitored processes to help them predict and avoid system failures, as well as provide real-time feedback for quality control.
Campo scientifico (EuroSciVoc)
CORDIS classifica i progetti con EuroSciVoc, una tassonomia multilingue dei campi scientifici, attraverso un processo semi-automatico basato su tecniche NLP. Cfr.: Il Vocabolario Scientifico Europeo.
CORDIS classifica i progetti con EuroSciVoc, una tassonomia multilingue dei campi scientifici, attraverso un processo semi-automatico basato su tecniche NLP. Cfr.: Il Vocabolario Scientifico Europeo.
- ingegneria e tecnologia ingegneria elettrica, ingegneria elettronica, ingegneria informatica ingegneria elettronica sistemi di controllo
È necessario effettuare l’accesso o registrarsi per utilizzare questa funzione
Programma(i)
Programmi di finanziamento pluriennali che definiscono le priorità dell’UE in materia di ricerca e innovazione.
Programmi di finanziamento pluriennali che definiscono le priorità dell’UE in materia di ricerca e innovazione.
Argomento(i)
Gli inviti a presentare proposte sono suddivisi per argomenti. Un argomento definisce un’area o un tema specifico per il quale i candidati possono presentare proposte. La descrizione di un argomento comprende il suo ambito specifico e l’impatto previsto del progetto finanziato.
Gli inviti a presentare proposte sono suddivisi per argomenti. Un argomento definisce un’area o un tema specifico per il quale i candidati possono presentare proposte. La descrizione di un argomento comprende il suo ambito specifico e l’impatto previsto del progetto finanziato.
Invito a presentare proposte
Procedura per invitare i candidati a presentare proposte di progetti, con l’obiettivo di ricevere finanziamenti dall’UE.
Dati non disponibili
Procedura per invitare i candidati a presentare proposte di progetti, con l’obiettivo di ricevere finanziamenti dall’UE.
Meccanismo di finanziamento
Meccanismo di finanziamento (o «Tipo di azione») all’interno di un programma con caratteristiche comuni. Specifica: l’ambito di ciò che viene finanziato; il tasso di rimborso; i criteri di valutazione specifici per qualificarsi per il finanziamento; l’uso di forme semplificate di costi come gli importi forfettari.
Meccanismo di finanziamento (o «Tipo di azione») all’interno di un programma con caratteristiche comuni. Specifica: l’ambito di ciò che viene finanziato; il tasso di rimborso; i criteri di valutazione specifici per qualificarsi per il finanziamento; l’uso di forme semplificate di costi come gli importi forfettari.
Coordinatore
RG6 6AH Reading
Regno Unito
I costi totali sostenuti dall’organizzazione per partecipare al progetto, compresi i costi diretti e indiretti. Questo importo è un sottoinsieme del bilancio complessivo del progetto.