Abstract: A shield harness manufacturing device includes a sheet feeder, a conductor-winding mold, an insulator-winding mold, and a control unit. The conductor-winding mold winds an ALS sheet as an electrically conductive sheet around a wire bundle including at least one covered wire and at least one drain wire. The insulator-winding mold folds a PET sheet as an electrically insulating sheet into two halves and then wraps the ALS-wound wire bundle in the PET sheet over the entire length of the wire bundle. The sheet feeder feeds the ALS sheet into the conductor-winding mold through which the covered wire and the drain wire are passed. The ALS sheet is wound around the covered wire and the drain wire over the entire length of the wires. Thereafter, the ALS-wound wire bundle is inserted into the insulator-winding mold and the sheet feeder feeds the PET sheet into the insulator-winding mold.

Abstract: Estimation sections which have beforehand learned a relationship between known connection data pertaining to connection design and unknown connection data pertaining to connection design for the known connection data estimate the unknown connection data for the known connection data in accordance wit an input of the known connection data, on the basis of the result of learning. The respective estimation sections are formed from a multilayer feedforward neural network in which layers constituted of a plurality of neurons are coupled together in a direction in which the layer runs from an input layer to an output layer by way of an intermediate layer.

Abstract: Estimation sections (20, 30, 40, 50, 60) which have beforehand learned a relationship between known connection data pertaining to connection design and unknown connection data pertaining to connection design for the known connection data estimate the unknown connection data for the known connection data in accordance with an input of the known connection data, on the basis of the result of learning. The respective estimation sections are formed from a multilayer feedforward neural network in which layers constituted of a plurality of neurons are coupled together in a direction in which the layer runs from an input layer to an output layer by way of an intermediate layer.