含能材料2025，Vol.33Issue(2)：136-147,12.DOI:10.11943/CJEM2024300
基于音频信号的含能材料撞击感度机器学习识别
Machine Learning Recognition of Impact Sensitivity of Energetic Materials Based on Acoustic Signals
摘要
Abstract
To improve the accuracy and objectivity of explosives’impact sensitivity testing,machine learning methods were ap-plied in the intelligent recognition of explosives’impact response acoustic signals.Experiments on mixed explosives were con-ducted using a drop-weight impact sensitivity test device,with an audio acquisition system synchronously capturing acoustic sig-nals during the impact process.One-dimensional time domain and frequency domain features,such as maximum value and bandwidth,were extracted.Short-Time Fourier Transform(STFT)was employed to convert audio data into frequency spectro-grams.Data augmentation for one-dimensional data was performed using a Conditional Generative Adversarial Network(cGAN),while a Deep Convolutional Generative Adversarial Network(DCGAN)was applied to enhance spectrogram data.Multiple machine learning models were employed for explosion classification,including Random Forest(RF),eXtreme Gradient Boosting(XGBoost),Back-propagation Neural Network(BPNN),Support Vector Machine(SVM),k-means clustering,Convo-lutional Neural Network(CNN),and Vision Transformer(ViT).Results demonstrate that RF,XGBoost,BPNN,and SVM achieve accuracy rates exceeding 99.5%on the real dataset and achieve 100%on the cGAN-augmented dataset.In contrast,k-means clustering initially reaches an accuracy of 98.5%on the real dataset,but accuracy shows a trend of increase followed by decline on augmented data.CNN and ViT achieve accuracies of 98.1%and 98.4%on the real dataset,respectively,and im-proved to 98.4%and 98.9%on augmented data.However,their accuracy still exhibited potential for improvement due to the constraints of small sample sizes and minor overfitting issues.The proposed machine learning-based intelligent recognition meth-od for explosives’impact sensitivity in this study achieved a high level of accuracy,demonstrating its reliability and practicality in the task of detecting explosive sound signals.At the same time,it effectively mitigates the subjectivity and inefficiency associat-ed with traditional manual recognition methods,providing a reliable technical solution for the safety use of explosives.关键词
撞击感度/机器学习/深度学习/数据增强/卷积神经网络/声信号识别Key words
impact sensitivity/machine learning/deep learning/data augmentation/convolutional neural network/acoustic signal recognition分类
军事科技引用本文复制引用
张炳儒,邓川,代晓淦,李明,文玉史,郭峰,于绍钧,纪春亮,林聪妹,郝利霄,韩勇..基于音频信号的含能材料撞击感度机器学习识别[J].含能材料,2025,33(2):136-147,12.基金项目
国家自然基金面上项目(12372342) （12372342）
院长基金自强项目(YZJJZQ2023008) Grant Support:National Natural Science Foundation of China(No.12372342) （YZJJZQ2023008）
Presidential Foundation of CAEP(YZJJZQ2023008) （YZJJZQ2023008）
