Today, there are many needs to replace or maintain many plants built in the 1960s. However, it is difficult to replace or
maintain them, because the documents of installed sequential control logic are seldom remain.
Therefore, we propose an automatic regeneration method(SPAIR) in or- der to solve this problem. SPAIR regenerates sequential
control logic that is expressed on a ladder diagram from the input and output data of a target control unit and its supplementary
specifications, which in- dicate the information about timers, etc. SPAIR consists of two parts, namely basic logic inferring
engine and interior coil logic inferring en- gine. In basic logic inferring engine, time series data is compressed and translated
into training data using the specifications. The training data are processed by inductive learning and transformed into control
logic. In the interior coil logic inferring, the target logic of the interior coil is acquired by the selective attachment
of logic parts.