Obiettivo
Deep diving operations are carried out on a routine basis to 300 metres in Brazil, the Gulf of Mexico and Norway. This activity will extend to 450 metres in the years to come.
The aim of the project is to add a new dimension to diving safety and efficiency by providing the diving supervisor with the assistance of an Expert System (ES) during deep diving operations. The system is based on the existing monitoring system and works on the basis of "man in the loop".
The expert system was successfully implemented on an AT computer. A Comex monitoring system was connected to the expert system and worked perfectly.
The prototype ES was first validated using a bench test. It was connected to a divers monitoring system and a simulator. The simulator allowed to reproduce various dives conditions and scenario to test the system diagnosis.
The prototype ES was further validated during deep onshore simulated dives performed during the HYDRA IX experiment. A series of 15 dives, deeper than 200 m, were monitored by the SE which was used to control the diver's safety and comfort and to run equipment at optimum.
Finally, the ES was mobilized on board the Amethyst, a new built diving vessel, and validated during actual commercial diving operations on the Oseberg field. The most interesting feature of the system proved to be the thermal model of the diver which allowed to make predictions of the diver thermal status with a minimum of monitoring probes.
As aresult, it can be said that technical and hardware problems were well controlled throughout the project. The different modules of the expert system were designed and validated according to specifications. However, diffculties were encountered with the human aspects. The first one was the collection of the expertise. Experts easily provide trivial information but are very reluctant in giving out pertinent expertise. The second one was related to the man machine interface. It was found that friendly interfaces require a lot of development time, more than 40% of the project time and resources.
A last remark concerns the relevance of operational expert systems. Actual dives operations have shown limits to our system as situations occurred that were not considered during the design phase of the ES. It proved that our ES knowledge base will have to be enriched with expertise and experience collected during further operations to become more and more pertinent. It seems that expert system work just like human beings : the older they are, the wiser and more experienced they become.
The Expert System focuses on the problem of the working divers. It interfaces the monitoring system, that collects the information relevant to the dives, to the Diving Supervisor, who is in charge of the operations. The ES assists the Diving Supervisor but does not control the operations : the Supervisor can override its recommendations at any time.
The tasks specified for the ES included :
- Quality control of the incoming data
- Condition monitoring of the equipment during the various phases of dives
- Alarm generation in case of abnormal states, including early detection of
trends that might lead to such states
- Diagnosis of the causes for abnormal states
- Assistance in selecting appropriated procedures or setting the equipment
to correct the situation
- Educational programs for personnel training
The ES software was selected according to the following specifications :
- Capacity to run on time analysis of the process
- Capacity to cope with fast changing signals and to differentiate levels
of priorities in emergencies
- Ease of developing/adapting/modifying the knowledge base with experience
- Possibility of implemention on a small computer, compatible with the
offshore conditions of operation.
The project was carried out in 4 phases :
a) FEASIBILITY STUDY AND SPECIFICATIONS : Review of existing monitoring systems, establishment of a simple demonstration system and functional specifications of ES.
b) DEVELOPMENT : Development of the interfaces with monitoring system, interface with operators, prototype expert and knowledge base, test of prototype expert system on a bench test.
c) ONSHORE VALIDATION : Validation of the expert system during a Comex experimental dive to 300 at Marseille. The system was used during simulated dives in a wet pot with full scientific and medical monitoring of the dives.
d) OFFSHORE VALIDATION : Adaptation of the expert system to the actual case of the Amethyst diving support vessel. Offshore testing of the completesystem during one diving season in the North Sea, evaluation of the performances of the expert system.
Information from the knowledge base was provided by COMEX operational and diving personnel : Safety Officers. Methods Engineers and Medical Doctors, Equipment Engineers and Technicians. Barge Superintendents and Diving Superviosrs, Life Support Technicians and Divers. Operating and emergency procedures were derived from the Company procedures and manuals.
The hardware structure uses an IBM AT compatible micro computer, fitted with a special artificial intelligence card which hosts a 68020 microprocessor. This card implements the DIAGNEX software designed by ITMI for the development of expert systems. The expert system was structured using DIAGNEX tools and interfacing facilities with the assistance of ITMI as sub-contractor.
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.
Questo progetto non è ancora stato classificato con EuroSciVoc.
Suggerisci i campi scientifici che ritieni più rilevanti e aiutaci a migliorare il nostro servizio di classificazione.
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
13321 MARSEILLE
Francia
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.