Community Research and Development Information Service - CORDIS

Qualitative representation of process trends

The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes.

The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes.

The toolbox “Qualitative representation of process trends variables” has the objective of converting numeric signals into qualitative representations. The developed tool obtains information from directly measured, pre-processed or estimated process variables and is capable of deriving and showing the qualitative process perception that expert operators could have (e.g. “the pressure dropped abruptly”).

Trends of numeric variables are symbolically represented by means of qualitative descriptions of signals composed by episodes that characterise a constant state over a specific time interval with constant signal behaviour. It allows a compact representation of process variables from the temporal point of view (periods of time with constant behaviour) and from the point of view of signal behaviour (qualitative description). The trends representation in episodes can be used for monitoring, as additional simplified information for operators and as a pre-processing tool for detection and fault diagnosis.

The toolbox is delivered as a software library in G2 that can be used to build customized applications in an easy way. It can be configured in a way that only the interesting characteristics of the signal behaviour, from the expert operator point of view, are used to obtain its description. The representation of a variable can be obtained off-line (from a recorded signal, useful in order to choose the configuration parameters or to analyse past situations), or on-line, generating episodes when significant changes occur. A representation is obtained for each variable; but it is possible to obtain representations of several variables at the same time.

Reported by

Campus Montilivi, Edifici P4
17071 Girona
Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top