基于CNN-LSTM混合驱动的焊接成形质量监测

Welding forming quality monitoring based on CNN-LSTM hybrid drive

焊接成形质量监测对于现代制造业至关重要,现有的质量识别方法大多基于单一传感器,识别精度难以进一步提升,面对复杂条件下的抗干扰能力较弱.针对单一传感器识别技术存在的不足,多源信息融合技术能够发挥不同类型传感器的自身优势,实现对焊接过程更为全面且准确的监测.在进行多信息融合过程中,深度学习模型的特征挖掘机制仍然欠缺解释,不同信息的互补性仍未明晰,为此,提出一种基于多源信息混合驱动的CNN-LSTM焊接成形质量监测模型.结果表明,通过融合图像和电压信号实现了99.72%的平均识别准确率,可视化结果还展示了不同信息之间的互补优势.

Welding forming quality monitoring is crucial for modern manufacturing industry,but most of the existing quality identification methods are based on single sensor,which makes it difficult to further improve the identification accuracy and has weak anti-interference ability under complex conditions.To overcome the shortcomings of single sensor identification technology,multi-source information fusion technology can make full use of the advantages of different types of sensors to achieve more comprehensive and accurate monitoring of the welding process.However,in the process of multi-information fusion,the feature mining mechanism of the deep learning model still lacks explanation,and the complementarity of different information is still unclear.In this paper,a multi-information hybrid-driven CNN-LSTM welding quality monitoring model is proposed.By fusing image and voltage signals,an average recognition accuracy of 99.72%is achieved.In addition,the visualization results show the complementary advantages between different information.