Full scale measurements are being conducted on fixed platforms according to the regulations issued by the Norwegian Petroleum Directorate on the collection of environmental and platform performance (E-and P-) data.

This paper is mainly concerned with the quasistatic and dynamic behaviour of the platforms. First, a short description of the E-and P-data programme is given followed by some more detailed information on the particular instrumentation installed on typical platforms. Thereafter, the methods of analysis are described and, finally, samples of some of the results of the data analysis are presented and discussed.

Only a limited amount of data has been analyzed, however, the results obtained so far indicate a fair correlation between the analytical models used in the design and the measured behaviour of the platforms.

It should be noted that the techniques presently used for time series analysis all suffer from poor confidence levels, due to the short duation of the measured time series. However, more sophisticated methods for time series analysis have been proposed and they will be applied to the data in the future.

Keywords:
machine learning, platform, articulated platform, frequency, parent distribution, deck level, instrumentation, sensor, Artificial Intelligence, strain response
Subjects:
Information Management and Systems
Copyright 1980, European Offshore Petroleum Conference and Exhibition
You can access this article if you purchase or spend a download.