The lifetime prediction of epoxy resin adhesive based on small-sample data

Abstract

Epoxy resin adhesive is widely used for equipment connection and sealing in the aerospace industry. The performance degradation of epoxy resin adhesive has a significant impact on the reliability and safety of products, so it is important to predict its lifetime under the performance requirements. Due to the slow degradation speed in the normal or working environment, accelerated degradation test is an important way to study the lifetime of epoxy resin adhesive. However, restrained by the actual test time and cost, the amount of test data is often very few which makes the statistics and assessment difficult. This paper studies the whole process of lifetime prediction of epoxy adhesives, including accelerated degradation test scheme, degradation path model construction, and test data processing. In particular, this paper focuses on the construction of the degradation path model and the processing method of small sample test data. The proposed three-variate degenerate path model and the data processing method combined with BP neural network can effectively improve and supplement the classical epoxy adhesive life prediction.