Federated learning (FL) is an effective method when a single client cannot provide enough samples for multiple condition fault diagnosis of bearings since it can combine the information provided by multiple clients. However, some of the client's working conditions are different; for example, different clients are in different stages of the whole life cycle, and different clients have different loads. At this point, the status of each client is not equal, and the traditional FL approach will lead to some clients' useful information being ignored. The purpose of this paper is to investigate a multiscale recursive FL framework that makes the server more focused on the useful information provided by the clients to ensure the effectiveness of FL. The proposed FL method can build reliable multiple working condition fault diagnosis models due to the increased focus on useful information in the FL process and the full utilization of server information through local multiscale feature fusion. The validity of the proposed method was verified with the Case Western Reserve University benchmark dataset. With less local client training data and complex fault types, the proposed method improves the accuracy of fault diagnosis by 23.21% over the existing FL fault diagnosis.
Keywords: fault diagnosis; federated learning; multiple working condition; multiscale recursive.