[2D6] Integration of natural language-based information in intelligent condition monitoring
E Juuso
University of Oulu, Finland
Materials in natural language are increasingly important in many application areas. Artificial intelligence tools are introduced for working with this material. However, materials remain in natural language. A consistent representation is needed to use them together with data based on measurements. Generalised norms provide informative features from measurements and signals. Intelligent condition and stress indices in the range [–2, 2] are obtained using the norms in non-linear scaling. The procedure is, in principle, the same as in representing fuzzy rule-based systems. For information that does not contain numerical values, the corresponding scaled values can be obtained using interactions with labels such as {very low, low, normal, high, very high} or {fast decrease, decrease, constant, increase, fast increase}. The linguistic terms are fuzzy numbers, which can be made sharper or wider with powering modifiers, ‘extremely’, ‘very’, ‘more or less’ and ‘roughly’, and then processed with the conjunction, disjunction and negation. The methodology is used in the analysis of the event data: the information represented with these numbers produces a real-valued relationship base to be used to analyse interactions. Known relationships can also be handled with the fuzzy calculus and the extension principle to keep the uncertainty in the calculation.
Keywords: natural language, non-linear scaling, intelligent indices, fuzzy set systems, event data, condition monitoring.
Keywords: natural language, non-linear scaling, intelligent indices, fuzzy set systems, event data, condition monitoring.
