A comprehensive diagnostic system for vehicle suspensions based on a neural classifier and wavelet resonance estimators. (15th August 2022)

• Record Type: Journal Article
• Authors: Burdzik, Rafał
• Is Part Of: Measurement. Volume 200(2022)
• Publication Date: 2022-08-15
• Subjects: Vibrations -- Suspension -- Shock absorber -- Wavelet transform -- Neural network -- Defect detection; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.111602
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Concept of a comprehensive diagnostic system for vehicle suspension. Innovative method of damage prediction and application of neural classifier. Method of quantitative damage identification using wavelet resonance estimators of the shock absorber technical condition. Recognition of combined failures of shock absorber. Abstract: The problem of distinguishing combined failures in technical diagnostics is still a very difficult research issue and a scientific challenge. This paper presents an investigation into a comprehensive diagnostic system for a vehicle suspension based on an advanced algorithm for multidimensional analysis of the vibration accelerations and a neural classifier. The novelty of this paper and its contributions are the innovative method for damage prediction and application of neural classifier. The developed system is essentially important for preventative vehicle suspension maintenance and its easy-to-implement inspection. The most important findings and achievements of the presented study are the testing of actual suspension components with real damage under controlled conditions, development of a method of quantitative damage identification using wavelet resonance measures estimators, preparation of a wavelet classifier for combined damage recognition, and the concept of a comprehensive system for diagnosing vehicle suspensions using vibration methods.