Introduction. The development of the agro-industrial complex until 2030 requires increasing the efficiency of the machine and tractor fleet with account for corrosion processes accelerating equipment wear. Existing assessment methods are based on empirical data and do not provide accurate forecasting. The introduction of AI and digital solutions will automate testing, reduce costs and improve the accuracy of assessing degradation caused by corrosion processes. Aim of the Study. The aim is to determine the compliance of experimental data on the effect of salt spray on the corrosion of agricultural machinery components with the distribution law through the example of reversing light switches. Materials and Methods. The object of study was reversing light switches widely used in agricultural machinery. The studies were carried out in a salt spray chamber with parameters corresponding to GOST R 52230 and GOST 9.302 for 200 hours with intermediate inspections every 48 hours. During the tests, the degree of corrosion was determined, calculated by the area of damaged sections. Using mathematical methods there was calculated the mean deviation, median, variance, standard deviation, skewness, kurtosis, and range of the sample. Results. As a result of the tests, the operability of the samples was confirmed and the obtained data compliance with the Weibull distribution law was assessed. It was experimentally established that the active phase of surface degradation of reversing light switches increases starting from 96 hours of exposure in the salt spray chamber that is caused by the destruction of protective coatings and progress of pitting corrosion. The use of a quadratic regression model made it possible to describe the dependence of corrosion damage on exposure time. Discussion and Conclusion. The statistical analysis of the sample confirmed Weibull distribution fit that makes it possible to predict further corrosion progress and improve performance assessment of products in salt spray conditions. Obtained parameters allow predicting the resource of components. The results of the study provide a basis for creating digital twins and adaptive maintenance systems using artificial intelligence, which minimize machinery downtime.
Limarenko et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: