Equipment health state assessment method and system under fault-free sample

The invention relates to the technical field of equipment health state assessment, and provides an equipment health state assessment method and system under a fault-free sample. The method comprises the following steps: constructing an autologous sample training set for historical data samples of a health state according to equipment state data; generating a boundary detector set from the autologous sample training set according to a nearest neighbor fixed boundary negative selection algorithm, wherein the boundary detector set comprises a plurality of boundary detectors; and taking to-be-evaluated equipment state data as a to-be-detected sample, and determining whether the equipment state data is healthy or not according to the relationship between the to-be-detected sample and the boundary detector set. According to the embodiment provided by the invention, the health state evaluation of the equipment under the condition of no fault sample can be realized, the application scene is enriched, and the detectio