机电工程技术2024，Vol.53Issue(7)：119-125,7.DOI:10.3969/j.issn.1009-9492.2024.07.024
基于SSA-CNN-CBAM的超声气固两相流浓度信息识别
Ultrasonic Gas-solid Two-phase Flow Concentration Information Identification Based on SSA-CNN-CBAM
张芮铭 1侯怀书1
作者信息
- 1. 上海应用技术大学机械工程学院,上海 201418
- 折叠
摘要
Abstract
Pneumatic transportation has always been an important part of some industrial production processes,and the accurate and real-time detection of gas-solid two-phase flow in metal pipelines has always been a major challenge with the continuous improvement of detection technology requirements in industrial environments.To solve this problem,a hybrid model is proposed combining Sparrow Optimization Algorithm(SSA),Convolutional Neural Network(CNN)and Attention Module(CBAM)to identify the concentration of gas-solid two-phase flow.SSA is used to optimize the parameters of the CNN-CBAM model,and the SSA-CNN-CBAM hybrid model is constructed for ultrasonic backscatter waveform recognition,and the classification results of concentration are obtained.Through repeated experiments,the experimental results of the mixed model are compared with the experimental results of the SSA-CNN model,the CNN-CBAM model and the CNN model,and the results show that the proposed model is more ideal for the classification and identification of gas-solid two-phase flow concentration.The test results show that the method can realize the real-time concentration detection of gas-solid two-phase flow transportation,which provides a reference for the detection of gas-solid two-phase flow transportation in industry,and provides new ideas and methods for the development and application of related technologies.关键词
超声后向散射/气固两相流/浓度/麻雀优化算法/卷积神经网络/注意力模块Key words
ultrasonic backscattering/gas-solid two-phase flow/concentration/sparrow optimization algorithm/convolutional neural network/attention module分类
信息技术与安全科学引用本文复制引用
张芮铭,侯怀书..基于SSA-CNN-CBAM的超声气固两相流浓度信息识别[J].机电工程技术,2024,53(7):119-125,7.
