A fault detection method and system

Abstract

The present invention discloses a fault detection method and system. The method includes the following steps that: an existing training data set in an industrial process is mapped into a non-linear feature space, so that a mapped training sample data set can be generated; data collected in the industrial process are mapped into the non-linear feature space, so that mapped test data can be generated; and whether the test data are fault data can be judged based on the training sample data set. According to the fault detection method and system provided by the technical scheme provided by the present application, the data collected in the industrial process are mapped into the nonlinear feature space through non-linear mapping, and the training sample data set in the nonlinear feature space are adopted to carry out efficient fault detection on the test data, fault detection accuracy can be improved, and a higher fault detection rate can be achieved.

Description

technical field

[0001] The present application relates to the technical field of detection, and more particularly relates to a fault detection method and system. Background technique

[0002] With the development of modern production and the advancement of science and technology, modern production equipment is developing in the direction of large-scale, complex and automated, and industrial processes are becoming more and more complex. Once an abnormality occurs, it may affect production safety, efficiency or product quality. Therefore, higher requirements are put forward for the process monitoring of industrial production, such as operation status supervision, process change and fault detection.

[0003] In the actual industrial process, there are many uncertain factors and the process is complex, generally including nonlinear, time-varying, variable coupling, time correlation, multi-modal, multi-time, large-scale and other characteristics, making it difficult to establish ...

Images