AUTOMATIC REGENERATION OF SEQUENCE PROGRAMS FOR OPERATING PLANTS

Today, many plants built in the 1960s will probably be replaced or mai ntained, However, it is difficult to replace or maintain them because the installed sequential control logic documents am seldom still in ex istence, Therefore, we have preposed an automatic regeneration method (SPAIR) in order to solve this problem, SPAIR regenerates sequential c ontrol logic that is expressed on a ladder diagram from the input and output data of a target control unit and its supplementary specificati ons, which indicate the information about timers and interior coils, T ime series data is compressed and translated into training data using the specifications, The training data are processed by inductive learn ing and transformed into control logic, We have developed the SPAR-Sys tem in order to edit all kinds of data, generate target logic for plan ts, and to easily verify the inferred logic simulation plant, Simulati on experiments confirmed that control logic that is regenerated by SPA IR behaves in the same way as the installed control logic of a target plant model.