The most significant advantage of composite structures compared to structures made of traditional materials is the ability to control the characteristics of the structure in order to obtain an optimal design. In the general case, the initial physical characteristics of the material of the composite structure are random variables. Consequently, the required quantities (stresses, strains, critical loads, etc.) are also random variables. The problem of statistical modeling of a composite structure is ultimately reduced to the problem of transforming random variables. To solve this problem, the Monte Carlo method is used. The object of study is a multi-walled plate under the action of compressive loads. The purpose of this work is to construct point estimates of the coefficients of both general and local stability for a multi-walled plate, as well as to test statistical hypotheses about the equality of the stability coefficients to their theoretical values. The initial parameters are the elastic moduli in the longitudinal and transverse directions, as well as the shear modulus of the construction material. The following were used as output values: sample mean, standard deviation, skewness and kurtosis coefficients. All calculations were carried out in the environment of the MAXIMA package. It is shown that the distribution of the overall stability coefficient practically does not differ from the normal distribution. The coefficient of local stability has a slight positive asymmetry and a steeper peak compared to the normal curve. The results obtained allow us to conclude that the spread of the elastic characteristics of the material does not significantly affect the coefficients of the general and local stability of the multi-walled plate.

Keywords: statistical modeling, statistical hypothesis, multiwall plate, stability, critical load, composite material