To accurately simulate realistic pedestrian evacuation from a fire, a cellular automaton model of the dynamic changes in pedestrian movement parameters is developed in conjunction with fire dynamics software. The fire dynamics software is used to simulate the spread of smoke within the scene to obtain visibility and CO concentration data within the scene. We imported the smoke data into the cellular automata and adjusted the pedestrian movement speed over time, resulting in simulation data that closely align with reality. The results show that for the single-room scenario, as pedestrian density increased from 0.1 to 0.5 persons per square meter ($\mathrm{p}/{\mathrm{m}}^2$), the influence of the percentage of pedestrians familiar with their location on evacuation efficiency decreased from 44.93% to 24.52%. Conversely, in the multi-room scenario, it increased from 23.68% to 38.79%. The proportion of pedestrians less affected by smoke decreases and stabilizes as the CO yield increases. In the single-room scenario, when the CO yield is below 10%, the crowd with a low percentage of pedestrians familiar with the site is more affected by smoke than those with a high percentage. In the multi-room scenario, the victimization rate of the crowd follows an increasing-then-decreasing curve, ultimately stabilizing with changes in CO yield.

This study aims to study the safety of oil and gas pipelines under stress corrosion conditions and grasp the corrosion damage situation timely and accurately. Consequently, a non-destructive testing method combining magnetic flux leakage testing technology and a kernel function extreme learning machine improved by genetic algorithm (GA-KELM) is proposed. Firstly, the variation of the corrosion defect dimension and profile with time is obtained by numerical simulation. At the same time, the distribution of the magnetic flux leakage signal under different defect conditions is analyzed and studied. Finally, feature selection is carried out on the magnetic flux leakage signal distribution curve, and GA-KELM is used to predict the depth and length of corrosion defects so as to realize the non-destructive testing of the pipeline defects. The results show that different geometric features result in different magnetic flux leakage signal distributions. There is a corresponding relationship between the defect dimension and extreme value, area, and peak width of the magnetic flux leakage signal distribution curve. The GA-KELM prediction model can effectively predict the depth and length of corrosion defects, and the prediction accuracy is better than the traditional extreme learning machine prediction model.

It is well known that the safety and reliability of pipeline transportation are crucial. We are aiming at the problem that the residual life and residual strength of the defective elbow pipes are difficult to predict and usually need to be obtained through experiments. Consequently, a combined method of numerical simulation technology combined with a genetic algorithm to optimize neural network extreme learning machine (GA-ELM) is proposed. Firstly, the erosion characteristics of elbow pipes with different defects under the conditions of different impurity particle flow rates, particle sizes, and mass flow rates are analyzed by numerical simulation. At the same time, the effects of erosion defects of different sizes on the equivalent stress and residual strength of elbow pipes are also studied. Based on numerical simulation data, the extreme learning machine prediction model optimized by a genetic algorithm is used to predict the erosion rate, residual life, and residual strength and compared with the traditional ELM network model. The results show that residual strength of the elbow pipes with the increase of the depth and length of the defect, and increases with the increase of the width of the defect; the GA-ELM model can not only effectively predict the erosion rate, residual life and residual strength of defective elbow pipes, moreover its prediction accuracy is better than the traditional ELM model.

Traditional methods are using FDS and Pathfinder for numerical simulation of fire evacuation and do not consider the impact of fire products on pedestrians, which will lead to erroneous evacuation results. In order to explore the impact of fire products on pedestrian evacuation when a fire occurs in a building, the pedestrian evacuation risk assessment results are closer to the actual situation. By establishing a full-scale model based on the pedestrian evacuation speed coefficient, a numerical simulation of the evacuation of pedestrians under the influence of fire products is carried out, and the influence of spray intensity and smoke exhaust rate on pedestrian evacuation is analysed at the same time. The results show that, compared with traditional methods, the fire evacuation model based on the evacuation speed coefficient can better reflect the evacuation effect of the real fire scene. At the same time, adding spray and smoke exhaust devices can give pedestrians more time to escape.

A spherical array is not limited to providing an acoustic map in all directions by the azimuth of the array. In this paper, spherical reverse beamforming for sound source localization based on spherical harmonic beamforming and the principle of sound field reconstruction is proposed in order to output a sharper scanning beam. It is assumed that there is an imaginary sound source at each scan point, and the acoustic map of a spherical array to the actual sound source is regarded as the combination of all of the imaginary sound sources. Sound source localization can be realized by calculating the contribution of each imaginary sound source to the sound field. Also in this work, the non-convex constrained optimization problem is established using p-norm. Combined with the norm method, the sparse solution of the imaginary sources is obtained through iterative weighted techniques, and the resolution of sound source localization is improved significantly. The performance of this method is investigated in comparison to conventional spherical beamforming. The numerical results show that the proposed method can achieve higher resolution for the localization of sound sources without being limited by the frequency and array aperture, and has a stronger ability to suppress fluctuations in background noise.

Aiming to solve the problem that the residual life of defective elbows is difficult to predict and the prediction accuracy of a traditional extreme learning machine (ELM) is unsatisfactory, a genetic algorithm optimization neural network extreme learning machine method (GA-ELM) that can effectively predict erosion rate and residual life is proposed. In this method, the input weight and hidden layer node threshold of the hidden layer node is mapped to GA, and the input weight and threshold of the ELM network error is selected by GA, which improves the generalization performance of the ELM. Firstly, the effects of solid particle velocity, particle size, and mass flow rate on the erosion of elbow are studied, and the erosion rates under the conditions of point erosion defect, groove defect, and double groove erosion defect are calculated. On this basis, the optimized GA-ELM network model is used to predict the residual life of the pipelines and then compared with the traditional ELM network model. The results show that the maximum erosion rate of defect free elbow is linearly correlated with solid particle velocity, particle size, and mass flow rate; The maximum erosion rate of defective bend is higher than that of nondefective bends, and the maximum erosion rate of defective bend is linearly related to mass flow rate, but nonlinear to solid particle flow rate and particle size; the GA-ELM model can effectively predict the erosion residual life of a defective elbow. The prediction accuracy and generalization ability of the GA-ELM model are better than those of the traditional ELM model.