Analysis of the sources of scientific and technical literature shows that the main factors that cause the accident rate of lifting structures are factors of manmade, natural and «human» characters. The article proposes a methodology for identifying and assessing the significance of factors that are, at first glance, indirect, but have a significant impact on the causes of the accident rate of boom self-propelled cranes. The proposed methodology consists of three stages, each of which separately is quite well tested by other authors. At the first stage, based on the analysis of expert assessment according to the Hay method, it is proposed to identify significant factors. At the second stage, on the basis of the chi-squared criterion, the significance of the factor is assessed. At the third stage, a methodology for conducting a numerical experiment is proposed to assess the significance of factors based on the use of neural networks. Obviously, the proposed methodology can also be used in assessing the significance of factors of other events, and not only in case of accident rate of lifting structures.
Read full abstract