Due to the rapid growth and spread of fire,it poses a major threat to human life and property.Timely use of fire detection technology can reduce disaster losses.The traditional threshold segmentation method is unstabl...Due to the rapid growth and spread of fire,it poses a major threat to human life and property.Timely use of fire detection technology can reduce disaster losses.The traditional threshold segmentation method is unstable,and the flame recognition methods of deep learning require a large amount of labeled data for training.In order to solve these problems,this paper proposes a new method combining You Only Look Once version 5(YOLOv5)network model and improved flame segmentation algorithm.On the basis of the traditional color space threshold segmentation method,the original segmentation threshold is replaced by the proportion threshold,and the characteristic information of the flame is maximally retained.In the YOLOv5 network model,the training module is set by combining the ideas of Bootstrapping and cross validation,and the data distribution of YOLOv5 network training is adjusted.At the same time,the feature information after segmentation is added to the data set.Different from the training method that uses large-scale data sets for model training,the proposed method trains the model on the basis of a small data set,and achieves better model detection results,and the detection accuracy of the model in the validation set reaches 0.96.Experimental results show that the proposed method can detect flame features with faster speed and higher accuracy compared with the original method.展开更多
This study seeks to determine the similarities in plume radiation between reduced and full-scale solid rocket models in ground test conditions through investigation of flow and radiation for a series of scale ratios r...This study seeks to determine the similarities in plume radiation between reduced and full-scale solid rocket models in ground test conditions through investigation of flow and radiation for a series of scale ratios ranging from 0.1 to 1. The radiative transfer equation (RTE) considering gas and particle radiation in a non-uniform plume has been adopted and solved by the finite volume method (FVM) to compute the three dimensional, spectral and directional radiation of a plume in the infrared waveband 2-6 mu m. Conditions at wavelengths 2.7 mu m and 4.3 mu m are discussed in detail, and ratios of plume radiation for reduced-scale through full-scale models are examined. This work shows that, with increasing scale ratio of a computed rocket motor, area of the high-temperature core increases as a 2 power function of the scale ratio, and the radiation intensity of the plume increases with 2-2.5 power of the scale ratio. The infrared radiation of plume gases shows a strong spectral dependency, while that of Al2O3 particles shows spectral continuity of gray media. Spectral radiation intensity of a computed solid rocket plume's high temperature core increases significantly in peak radiation spectra of plume gases CO and CO2 center dot Al2O3 particles are the major radiation component in a rocket plume. There is good similarity between contours of plume spectral radiance from different scale models of computed rockets, and there are two peak spectra of radiation intensity at wavebands 2.7-3.0 lm and 4.2-4.6 lm. Directed radiation intensity of the entire plume volume will rise with increasing elevation angle. (C) 2016 Chinese Society of Aeronautics and Astronautics. Production and hosting by Elsevier Ltd.展开更多
基金supported by Hainan Natural Science Foundation of China(No.620RC602)National Natural Science Foundation of China(No.61966013,12162012)Hainan Provincial Key Laboratory of Ecological Civilization and Integrated Land-sea Development.
文摘Due to the rapid growth and spread of fire,it poses a major threat to human life and property.Timely use of fire detection technology can reduce disaster losses.The traditional threshold segmentation method is unstable,and the flame recognition methods of deep learning require a large amount of labeled data for training.In order to solve these problems,this paper proposes a new method combining You Only Look Once version 5(YOLOv5)network model and improved flame segmentation algorithm.On the basis of the traditional color space threshold segmentation method,the original segmentation threshold is replaced by the proportion threshold,and the characteristic information of the flame is maximally retained.In the YOLOv5 network model,the training module is set by combining the ideas of Bootstrapping and cross validation,and the data distribution of YOLOv5 network training is adjusted.At the same time,the feature information after segmentation is added to the data set.Different from the training method that uses large-scale data sets for model training,the proposed method trains the model on the basis of a small data set,and achieves better model detection results,and the detection accuracy of the model in the validation set reaches 0.96.Experimental results show that the proposed method can detect flame features with faster speed and higher accuracy compared with the original method.
基金co-supported by the National Natural Science Foundation of China (Nos. 51376065 and 51176052)Guangdong Key Scientific Project (No. 2013B010405004)
文摘This study seeks to determine the similarities in plume radiation between reduced and full-scale solid rocket models in ground test conditions through investigation of flow and radiation for a series of scale ratios ranging from 0.1 to 1. The radiative transfer equation (RTE) considering gas and particle radiation in a non-uniform plume has been adopted and solved by the finite volume method (FVM) to compute the three dimensional, spectral and directional radiation of a plume in the infrared waveband 2-6 mu m. Conditions at wavelengths 2.7 mu m and 4.3 mu m are discussed in detail, and ratios of plume radiation for reduced-scale through full-scale models are examined. This work shows that, with increasing scale ratio of a computed rocket motor, area of the high-temperature core increases as a 2 power function of the scale ratio, and the radiation intensity of the plume increases with 2-2.5 power of the scale ratio. The infrared radiation of plume gases shows a strong spectral dependency, while that of Al2O3 particles shows spectral continuity of gray media. Spectral radiation intensity of a computed solid rocket plume's high temperature core increases significantly in peak radiation spectra of plume gases CO and CO2 center dot Al2O3 particles are the major radiation component in a rocket plume. There is good similarity between contours of plume spectral radiance from different scale models of computed rockets, and there are two peak spectra of radiation intensity at wavebands 2.7-3.0 lm and 4.2-4.6 lm. Directed radiation intensity of the entire plume volume will rise with increasing elevation angle. (C) 2016 Chinese Society of Aeronautics and Astronautics. Production and hosting by Elsevier Ltd.
