The paper presents the modelling measurement results of the load-displacement relation for scaffold stands and bracings. In the case of stands, there are two sections of curves, i.e. a straight-line and curvilinear section, and in the case of bracings, two straight line sections as well as one curvilinear section are distinguished. As a result of analyses, it is concluded that the sections which can be approximated by means of linear functions should be distinguished in graphs, if possible. On the one hand, this results from the evaluation methods of scaffold components. Nevertheless, the determination of elastic-linear scope of components’ operation is useful in engineering practice during computer calculations. Moreover, the method of determining an intersection point between functions, approximating tests results, along with analysis of the impact of polynomial degree, approximating the research results, on the time and effectiveness of the process of approximating functions selection, are all demonstrated in this article. The proposed method can prove useful in all science fields where curves obtained from any research (laboratory test, in situ test, numerical analysis) require approximation or replacement with a simpler description.

Acoustic source localization using distributed microphone array is a challenging task due to the influences of noise and reverberation. In this paper, acoustic source localization using kernel-based extreme learning machine in distributed microphone array is proposed. Specifically, the space of interest is divided into some labeled positions, and the candidate generalized cross correlation function in each node is treated as the feature mapped into the hidden nodes of extreme learning machine. During the training phase, by the implementation of kernel function, the output weights of the classifier are calculated and do not need to be tuned. After the kernel-based extreme learning machine (K-ELM) is well trained, the measured generalized cross correlation data are fed into the K-ELM classifier, and the output is the estimated acoustic source position. The proposed method needs less human intervention for both training and testing and it does not need to calibrate the node in advance. Simulation and real-world experimental results reveal that the proposed method has extremely fast training and testing speeds, and can obtain better localization performance than steered response power, K-nearest neighbor, and support vector machine methods.