| 引用本文: | 谭君洋,夏丹,董世运,吕瑞阳,徐滨士.特征参量选择对磁巴克豪森噪声评价材料硬度的影响∗[J].中国表面工程,2021,34(1):8~15 |
| Tan Junyang,Xia Dan,Dong Shiyun,Lv Ruiyang,Xu Binshi.Influence of Characteristic Parameter Selection on Material Hardness Evaluation by Magnetic Barkhausen Noise[J].China Surface Engineering,2021,34(1):8~15 |
|
| 摘要: |
| 硬度是材料力学性能的重要指标之一,传统的压痕法测量方式会对材料产生破坏,因此硬度的无损评价成为该领域研究热点。 针对合金钢表面硬度快速定量无损检测需求,设计 6 种不同热处理的 24CrNiMo 合金钢试件,采用磁巴克豪森噪声检测系统测量试件的无损检测信号,并提取 3 个不同的信号特征参量,分别建立不同评价参量与硬度之间的映射关系,得到 3 种硬度单参量评价模型,验证和对比单参量评价模型的相关系数和评价精度,分析模型存在问题和缺陷。 为进一步提高合金钢硬度评价精度和可靠性,提出基于信号全量特征的多元评价参量,建立硬度多元参量评价模型,并对评价模型进行验证和对比分析。 结果显示:基于卷积神经网络的多元参量评价模型效果好于单参量评价模型,其评价结果的平均误差为 0. 97%,最大误差为 2. 78%。 研究成果为合金钢硬度快速定量无损检测提供了新方法,提高了评价精度、可靠性和稳定性。 |
| 关键词: 合金钢 表面硬度 磁巴克豪森噪声 定量无损评价 卷积神经网络 |
| DOI：10.11933/j.issn.1007-9289.20200729002 |
| 分类号:TG142 |
| 基金项目:国家重点研发计划 (2016YFB100205)、国家自然科学基金(51705532)和国家重点研发计划 (2017YFB1105002)资助项目 |
|
| Influence of Characteristic Parameter Selection on Material Hardness Evaluation by Magnetic Barkhausen Noise |
|
Tan Junyang1,2, Xia Dan1, Dong Shiyun1, Lv Ruiyang1, Xu Binshi1
|
|
1.National Key Laboratory for Remanufacturing, Army Academy of Armored Forces, Beijing 100072 , China;2.The Department of 6392 6.Troops, Beijing 100096 , China
|
| Abstract: |
| The hardness is one of the important indexes of mechanical properties of materials. The traditional indentation method will damage the materials, so the nondestructive evaluation of hardness has become a research hotspot in this field. Aiming at the requirements of rapid quantitative nondestructive testing of alloy steel surface hardness, six 24CrNiMo alloy steel specimens with different heat treat- ment are designed to be measured. The nondestructive testing signals of the specimens are measured by magnetic Barkhausen noise testing system, and three different signal characteristic parameters are extracted. Then, the mapping relationship between different evaluation pa- rameters and hardness is established respectively to obtain three kinds of single parameter evaluation models of hardness. The correlation coefficient and evaluation accuracy of the single parameter evaluation model are verified and compared, and the existing problems and de- fects of the model are proposed. In order to further improve the accuracy and reliability of hardness evaluation of alloy steel, the multiple evaluation parameters based on the total signal characteristics are proposed, and the evaluation model of multiple parameters is estab- lished. The results show that the multivariate evaluation model based on convolution neural network with the average error 0. 97% and the maximum error 2. 78% performs better than single parameter and multiple linear regression models. The research provides a new method for rapid quantitative nondestructive evaluation of alloy steel hardness, and the evaluation accuracy, reliability and stability are improved. |
| Key words: alloy steel surface hardness magnetic Barkhausen noise quantitative nondestructive evaluation convolutional neural network |
