Method and automatic control for regulating a multiple-stage industrial production controlling random chained stress, application to noise and value at risk control of a clearing house

Abstract

The invention concerns a probabilistic method and automatic control () for preventing and regulating an interruption of a multistage and multilink industrial production glow, to optimise said production flow while controlling industrial impact resulting from random chained stress, and applications to factory noise and value at risk of a clearing house. The invention consists in regulating production by means of a probabilistic automatic control () with action loop () and feedback loop (). Industrially speaking, said regulating automatic control () can be electronically produced by means of a programmed and cabled computer. The action loop () of the automatism () consists of an inductive probabilistic simulator () evaluating the chaining of random stresses in the production chain leading to a probabilistic measurement of the industrial impact I(r) resulting, on the basis of the adjustable level of an industrial stock parameter (r). The method used in the action loop () of the automatic control (), is of the type called 'Value at Risk' or 'VaR'. The feedback loop () of the automatic control () adjusts in course of time (t) the industrial action parameter (r) to an extremal value, maintaining said estimator of VaR effect (p,T(r)) below its authorised nuisance level M. This is aimed at making the industrial production level F(r) extremal but nevertheless at a level compatible with the respect of regulatory or stock out conditions. The method and device of the invention can be advantageously used in numerous industries whether manufacturing, financial, agricultural where risks of pollution and other risks resulting from random chained stress need to be controlled.