Adaptive nearest neighbor reconstruction with deep contractive sparse filtering for fault diagnosis of roller bearings. (May 2022)

• Record Type: Journal Article
• Authors: Qian, Weiwei; Li, Shunming; Lu, Jiantao
• Is Part Of: Engineering applications of artificial intelligence. Volume 111(2022)
• Publication Date: 2022-05
• Subjects: Intelligent fault diagnosis -- Roller bearing -- Deep sparse contractive filtering -- Adaptive nearest neighbor -- Local contractive -- Sparse coding; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.104749
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Case-based intelligent fault diagnosis has had some notable successes in recent years. However, compared with parameter-based methods, they pay less attention to automatic and powerful feature extraction. Meanwhile, most approaches use k -nearest neighbor (KNN) algorithms or related variants, which fail in adaptive nearest neighbor location. To deal with these shortcomings, an algorithm called adaptive nearest neighbor reconstruction (ANNR) is proposed, which can take advantage of both parameter- and case-based diagnosis methods. Firstly, ANNR offers sparse and robust feature extraction by designed deep contractive sparse filtering (DCSF), which fuses a local contractive term to learn robust feature manifolds. Secondly, to locate the nearest neighbors for diverse testing samples adaptively, a case-based reconstruction algorithm is developed to obtain correlation vectors between training and testing samples. Finally, according to correlation vector of each testing sample, its optimized nearest neighbors are located, enabling precise feature classification. Extensive experiments were conducted on two roller bearing vibration signal datasets and verified its effectiveness.