Device and method for diagnosing an evolutive industrial process

摘要

A device for diagnosing an evolutive industrial process comprise a plurality of technical steps for the production of a given industrial compound, for which a plurality of state or characterization technical data is available, the device including at least one microprocessor and one memory, an interface module, a counter module for verifying whether a calculation end criterion has been reached, a management module for managing operations and data exchanges between the different modules, a computational grid comprising a plurality of production window calculation modules in order to determine appropriate production windows, a clustering module for distributing parameter combinations between several clusters in order to perform convergence calculations, and a convergence module for verifying whether an expected convergence rate between clusters has been reached.

主权项

1. A method for automatically characterizing a process for manufacturing an industrial compound, wherein a plurality of technical data relating to at least one of a process state, a process material, and a process performance is available, comprising the steps of:
a) measuring, on an object manufacturing line, using a sensor, a plurality of data relating to a plurality of parameters related to at least one of the process state, the process material, and the process performance; b) receiving, by an interface module of an automatic characterization device, the data; c) receiving, by the interface module of the automatic characterization device, at least one of the plurality of parameters as a target improvement for the process; d) receiving, by the interface module of the automatic characterization device, a process optimization function; e) performing, by a computational grid comprising a plurality of processors, for a period determined by a calculation end criterion, a first characterization phase of the process to achieve characteristics of potential manufacturing windows; f) based on the characteristics of the best manufacturing windows obtained in the first characterization phase, determining, by a window selection threshold determination module of the automatic characterization device, a manufacturing window selection threshold; g) performing, by the computational grid, a second characterization phase of the process to achieve parameter combinations for the manufacturing windows within limits of an established threshold; h) distributing, by a clustering module of the automatic characterization device, the parameter combinations among several combination clusters; i) checking, by a convergence module of the automatic characterization device, the convergence rate between the plurality of combination clusters according to a target rate; j) if the target rate has not been reached, returning the method to “g”; and k) if the target rate has been reached, obtaining variation ranges of the parameter combinations for the manufacturing windows of the process which meet a convergence criterion.