Abstract: Disclosed is a friction-stir welded structure in which corrosion resistance of a peeling region is ensured when a film coating is peeled away from a steel sheet. In a sub-frame, an aluminum alloy member is laid over a steel member that has been electropainted, and the overlaid part where the member is laid over is friction-stir welded at inner and outer welds. The aluminum alloy member has an aluminum layered part which together with the steel member constitutes the overlaid part due to being laid over the steel member, and aluminum extending parts provided to the aluminum layered part. The aluminum extending parts have aluminum extending parts that are orthogonal to the extending direction of the inner and outer welds and that protrude outward from the steel member.

Abstract: Disclosed is a friction-stir welded structure in which corrosion resistance of a peeling region is ensured when a film coating is peeled away from a steel sheet. In a sub-frame, an aluminum alloy member is laid over a steel member that has been electropainted, and the overlaid part where the member is laid over is friction-stir welded at inner and outer welds. The aluminum alloy member has an aluminum layered part which together with the steel member constitutes the overlaid part due to being laid over the steel member, and aluminum extending parts provided to the aluminum layered part . The aluminum extending parts have aluminum extending parts that are orthogonal to the extending direction of the inner and outer welds and that protrude outward from the steel member.

Abstract: According to the present invention, a method for recognition of normal and abnormal conditions can be performed with at least one neural network. First, trend data of an object system, before a recognition-step, are entered as input data to an input layer of each neural network and data of this system at the recognition-step are entered as objective output data to an output layer of the neural network. Thus, multiple sets of trend data showing at least one normal condition of this system are formed in the neural network in order to obtained learned weights and biases. Next, output data at every recognition-step are predicted by entering actual trend data as input data to the neural network, while the learned weights and biases are utilized. Then, the predicted output data are compared with actual output data at every recognition-step.