Mechanical Engineering in Uncertainties From Classical Approaches to Some Recent Developments. Группа авторов
Чтение книги онлайн.

Читать онлайн книгу Mechanical Engineering in Uncertainties From Classical Approaches to Some Recent Developments - Группа авторов страница 18

СКАЧАТЬ distributions). One of the fundamental questions that then arises is how to deal with divergent expert opinions. For this purpose, different rules for combining possibility distributions have been established.

      Let Π1 and Π2 be two possibility distributions. These distributions can be aggregated according to the following rules:

       – the conjunctive mode: this is the equivalent of the intersection of events. It corresponds to retaining only the consensus (the common area under the two distributions). This consensus is typically renormalized in order to satisfy the possibilistic axioms;

       – the disjunctive mode: this is the equivalent of the union of events. It corresponds to the union of the two distributions;

       – the intermediate mode (proposed by Dubois and Prade 1992): as its name indicates, this is an intermediate mode between the two previous ones. By defining the consensus, that is, the upper possibility bound following the intersection of the two distributions, by h, the distribution of the intermediate mode is defined by:

      [1.19]image

      These three modes of combination usually make it possible to combine distributions of possibility from different sources (experts, for example). If there is good agreement between the sources (for example, trapezoidal distributions with overlapping cores), then either the connective or disjunctive modes are both well suited. The choice between the two depends on whether one wishes to consider only consensus or whether one wishes to integrate divergent views as well.

      The theory of belief functions (or evidence theory) is another theory for modeling uncertainties of an epistemic nature. It was developed by Dempster (1967) and Shafer (1976) and is consequently sometimes known as the Demspter–Shafer theory. This approach is similar in spirit to the probability box theory and possibility theory, in that it seeks to obtain a bounding for a CDF.

      1.8.1. Theoretical context

      Formally, evidence theory is defined on a belief space EE defined as follows:

      DEFINITION 1.20.– Letbe a set and E the set of the subsets of Ω. A function m : E → ℝ is called belief mass function if it satisfies the following axioms:

       – the function has values between 0 and 1: ∀A ∈ E,0 ≤ m(A) ≤ 1;

       – the image of the empty set is 0: m(∅) = 0;

       – the image of all the events in the universe is 1:m(Ω) = 1;

       – the sum of the masses of the events of E is 1: ∀An ∈ E,

      DEFINITION 1.21.– Letbe a set, called universe, E the set of subsets ofand m a belief mass function. The triplet (Ω, E, m) is called the belief space EE.

      Note that the belief mass function m provides, as was the case for the possibility distribution, a measure of the relative likelihood of each element of E. In the terminology of the theory of belief functions, an element of E that has a non-zero mass is called a focal element, denoted Ωi. Note that these focal elements are, most of the time, defined such as to form a set of disjoint elements. The quantity mi = m(Ωi) is then called mass (or sometimes basic probability assignment [BPA]) associated with this focal element.

      In order to be able to compare the likelihood of different events, two quantities, plausibility and belief of the event, are introduced.

      DEFINITION 1.22.– Let (Ω, E, m) be a belief space. We call belief (noted Bel) and plausibility (denoted Pl) of an event eE, respectively:

      [1.20]image

      [1.21]image

      From a conceptual point of view, the mass of a focal element m (Ωi) provides the true likelihood that is attributed to that focal element, but without specifying how this likelihood is distributed among the subsets of Ωi. Therefore, the belief Bel(e) of an event e represents the minimal likelihood that can be associated with e, while the plausibility Pl(e) represents the maximum likelihood that can be associated with e.