Abstract
AbstractTo ensure consistent durability estimation, the engineers should create the so-called Generalized block of loading. It is based on the loading recording and the time-share of the exploitation modes during the service. In this paper, for the first time in engineering, the building of the Generalized loading block for the machine parts is considered from the mathematical point of view. Here we can see an innovative combination of techniques from cluster analysis of the time series and the specific problem of longevity estimation. This problem is important in estimating the agriculture machines longevity and reliability. To solve the problem of distinguishing the different service modes and estimating their share-time, the authors applied a popular machine learning tool, namely, cluster analysis. Because the service loading is un-stationary, selecting the modes is an important decision-making problem: the modes list should be neither too long nor too short. Because the generalized block of loading is created for the longevity estimation, the employed parameters are connected with process traits influencing fatigue damage accumulation. The semi-empirical modelled process, partly based on real loadings in service, was investigated for the case study. At the final stage, the so-called “teacher” was invoked; the result was checked using prior information.KeywordsRandom loadingGeneralized blockLongevityAgriculture machineryMachine-learningCluster analysis
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.