铁路货运车辆车身携带异物容易造成重大安全隐患,出发前必须对车辆外观进行严格检查。采用深度学习方法对异物进行智能识别对提高货检工作效率具有重要意义。针对铁路货运车辆安全检测中异物识别准确率低、漏检率高等问题,以ResNet-50...铁路货运车辆车身携带异物容易造成重大安全隐患,出发前必须对车辆外观进行严格检查。采用深度学习方法对异物进行智能识别对提高货检工作效率具有重要意义。针对铁路货运车辆安全检测中异物识别准确率低、漏检率高等问题,以ResNet-50为基本特征提取网络,引入K-Means算法,构建了一种以交并比(Intersection over Union,IoU)为度量的锚框聚类算法,采用自建的异常目标数据集进行了实验测试,结果发现,与传统Faster RCNN相比,改进后的算法有效地增强了深度网络模型的目标特征提取能力,提高了复杂背景下铁路货运车辆异物的识别定位精度,异物的识别漏检率降低21.3%,模型具有较强的泛化能力,对异常目标精确定位研究具有一定的参考价值。展开更多
The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety.The current airborne fire detection technology mostly relies on single-parameter s...The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety.The current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared light.This often results in a high false alarm rate in complex air transportation envi-ronments.The traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire information.This paper proposes a multi-technology collaborative fire detection method based on an improved transformers model.Dual-wavelength optical sensors,flue gas analyzers,and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection accuracy.The improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective,which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN(recurrent neural network)and CNN(convolutional neural network).Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information,respectively,which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention mechanism.Finally,the output results of the two models are fused through the gate mechanism.The research results show that,compared with the traditional single-feature detection technology,the multi-technology collaborative fire detection method can better capture fire information.Compared with the traditional deep learning model,the multivariate fire pre-diction model constructed by the improved Transformer can better detect fires,and the accuracy rate is 0.995.展开更多
文摘铁路货运车辆车身携带异物容易造成重大安全隐患,出发前必须对车辆外观进行严格检查。采用深度学习方法对异物进行智能识别对提高货检工作效率具有重要意义。针对铁路货运车辆安全检测中异物识别准确率低、漏检率高等问题,以ResNet-50为基本特征提取网络,引入K-Means算法,构建了一种以交并比(Intersection over Union,IoU)为度量的锚框聚类算法,采用自建的异常目标数据集进行了实验测试,结果发现,与传统Faster RCNN相比,改进后的算法有效地增强了深度网络模型的目标特征提取能力,提高了复杂背景下铁路货运车辆异物的识别定位精度,异物的识别漏检率降低21.3%,模型具有较强的泛化能力,对异常目标精确定位研究具有一定的参考价值。
基金This work was funded by the National Science Foundation of China(Grant No.U2033206)the Project of Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province(Grant No.MZ2022KF05,Grant No.MZ2022JB01)+3 种基金the project of Key Laboratory of Civil Aviation Emergency Science&Technology,CAAC(Grant No.NJ2022022,Grant No.NJ2023025)the project of Postgraduate Project of Civil Aviation Flight University of China(Grant No X2023-1)the project of the undergraduate innovation and entrepreneurship training program(Grant No 202210624024)the project of General Programs of the Civil Aviation Flight University of China(Grant No J2020-072).
文摘The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight safety.The current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared light.This often results in a high false alarm rate in complex air transportation envi-ronments.The traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire information.This paper proposes a multi-technology collaborative fire detection method based on an improved transformers model.Dual-wavelength optical sensors,flue gas analyzers,and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection accuracy.The improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective,which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN(recurrent neural network)and CNN(convolutional neural network).Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information,respectively,which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention mechanism.Finally,the output results of the two models are fused through the gate mechanism.The research results show that,compared with the traditional single-feature detection technology,the multi-technology collaborative fire detection method can better capture fire information.Compared with the traditional deep learning model,the multivariate fire pre-diction model constructed by the improved Transformer can better detect fires,and the accuracy rate is 0.995.
