The lifetime prediction of epoxy resin adhesive based on small-sample data. (August 2019)

• Record Type: Journal Article
• Authors: Zhu, Yipeng; Zhao, Tingdi; Jiao, Jian; Chen, Zhiwei
• Is Part Of: Engineering failure analysis. Volume 102(2019)
• Page Start: 111
• Page End: 122
• Publication Date: 2019-08
• Subjects: Epoxy resin adhesive -- Lifetime prediction -- Accelerated degradation test -- The three-variate degradation path model -- BP neural network; System failures (Engineering) -- Periodicals; Fracture mechanics -- Periodicals; Reliability (Engineering) -- Periodicals; Pannes -- Périodiques; Rupture, Mécanique de la -- Périodiques; Fiabilité -- Périodiques; Fracture mechanics; Reliability (Engineering); System failures (Engineering); Periodicals; Electronic journals; 620.112
• DOI: 10.1016/j.engfailanal.2019.04.007
• Languages: English
• ISSNs: 1350-6307

Abstract

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. Highlights: The whole process of lifetime prediction of epoxy adhesives was studied. An accelerated degradation test scheme was designed. A three-variate degenerate path model was proposed to predict product lifetime. BP neural network method was introduced into the model to improve accuracy.