冷轧带钢屈服强度的脉冲涡流检测方法研究
|
摘要
目前冷轧带钢屈服强度的检测主要依赖于有损检测,大大增加了检测成本。将BP神经网络引入基于脉冲涡流的冷轧带钢屈服强度预测,首先提取脉冲涡流响应信号的时域、频域特征,分析了各个脉冲涡流信号特征的稳定性,然后建立信号特征与材料屈服强度的BP神经网络模型,最后用建立的模型对材料的屈服强度进行预测。实验表明,采用BP神经网络对冷轧带钢进行屈服强度预测的误差为6%及以下,这种方法对于降低工业生产的检测成本、提高检测效率有一定的实用价值。
At present, the detection of the yield strength of cold-rolled strip steel mainly depends on the damage detection, which greatly increases the detection cost. In this paper, the BP neural network is introduced into the yield strength prediction of cold rolled strip steel based on pulse eddy current. Firstly, the time domain and frequency domain characteristics of the pulse eddy current response signal are extracted. The stability of the characteristics of each pulse eddy current signal is analyzed, and the BP neural network model for signal characteristics and material yield strength is established, and the yield strength of the material is predicted using the established model. Experiments show that yield strength prediction error is 6% or less using the BP neural network to predict the yield strength of cold-rolled strip steel. This method has certain practical value for reducing the detection cost of industrial production and improving the detection efficiency.
At present, the detection of the yield strength of cold-rolled strip steel mainly depends on the damage detection, which greatly increases the detection cost. In this paper, the BP neural network is introduced into the yield strength prediction of cold rolled strip steel based on pulse eddy current. Firstly, the time domain and frequency domain characteristics of the pulse eddy current response signal are extracted. The stability of the characteristics of each pulse eddy current signal is analyzed, and the BP neural network model for signal characteristics and material yield strength is established, and the yield strength of the material is predicted using the established model. Experiments show that yield strength prediction error is 6% or less using the BP neural network to predict the yield strength of cold-rolled strip steel. This method has certain practical value for reducing the detection cost of industrial production and improving the detection efficiency.
引文
[1] 周德强,田贵云,尤丽华,等.基于频谱分析的脉冲涡流缺陷检测研究[J].仪器仪表学报,2011,32(9):1948-1953.
[2] LI J, WU X, ZHANG Q, et al. Pulsed eddy current testing of ferromagnetic specimen based on variable pulse width excitation[J]. NDT & E International, 2015, 69(69):28-34.
[3] 武新军,张卿,沈功田.脉冲涡流无损检测技术综述[J].仪器仪表学报,2016,37(8):1698-1712.
[4] 陈骁.基于脉冲涡流技术的多层导电结构内层缺陷检测研究[D].杭州:浙江大学,2015.
[5] 周海婷,厚康,潘红良,等.基于有限元仿真电涡流传感器的结构优化[J].电子测量技术,2016,39(7):15-19.
[6] LIU X CH, SHANG W L, HE C F, et al. Simultaneous quantitative prediction of tensile stress, surface hardness and case depth in medium carbon steel rods based on multifunctional magnetic testing techniques[J]. Measurements, 2018(128): 445-463.
[7] 朱红运,王长龙,江涛,等.激励电流对脉冲涡流检测的影响研究[J].仪器仪表学报,2016,37(1):1-8.
[8] TIAN G Y, HE Y, ADEWALE I, et al. Research on spectral response of pulsed eddy current and NDE applications[J]. Sensors and Actuators A Physical, 2013, 189(2):313-320.
[9] 周德强,左晓芳,尤丽华,等.脉冲涡流铁磁性材料缺陷检测系统设计[J].传感器与微系统,2012,31(10):121-124.
[10] XU Z Y, WU X J, HUANG C, et al. Analysis of excitation current parameters in pulsed eddy current testing for ferromagnetic metallic materials[J]. International J Application Electromagn, 2012, 39:213-219.
[11] YU Y, YAN Y, WANG F, et al. An approach to reduce lift-off noise in pulsed eddy current nondestructive technology[J]. NDT & E International, 2014, 63:1-6.
[12] 张斌强.脉冲涡流检测系统的设计与研究[D].南京:南京航空航天大学,2009.
[13] HE Y, TIAN G, ZHANG H, et al. Steel corrosion characterization using pulsed eddy current systems[J]. IEEE Sensors Journal, 2012, 12(6):2113-2120.
[14] 高军哲,潘孟春,张琦,等.基于调频激励和细化谱分析的多频涡流检测技术研究[J].仪器仪表学报,2011,32(11):2628-2634.
[15] LIU B, HUANG P, ZENG X, et al. Hidden defect recognition based on the improved ensemble empirical decomposition method and pulsed eddy current testing[J]. NDT & E International, 2017, 86(Complete):175-185.
[16] FAN M, CAO B, SUNNY A I, et al. Pulsed eddy current thickness measurement using phase features immune to liftoff effect[J]. NDT & E International, 2017, 86(Complete):123-131.
[2] LI J, WU X, ZHANG Q, et al. Pulsed eddy current testing of ferromagnetic specimen based on variable pulse width excitation[J]. NDT & E International, 2015, 69(69):28-34.
[3] 武新军,张卿,沈功田.脉冲涡流无损检测技术综述[J].仪器仪表学报,2016,37(8):1698-1712.
[4] 陈骁.基于脉冲涡流技术的多层导电结构内层缺陷检测研究[D].杭州:浙江大学,2015.
[5] 周海婷,厚康,潘红良,等.基于有限元仿真电涡流传感器的结构优化[J].电子测量技术,2016,39(7):15-19.
[6] LIU X CH, SHANG W L, HE C F, et al. Simultaneous quantitative prediction of tensile stress, surface hardness and case depth in medium carbon steel rods based on multifunctional magnetic testing techniques[J]. Measurements, 2018(128): 445-463.
[7] 朱红运,王长龙,江涛,等.激励电流对脉冲涡流检测的影响研究[J].仪器仪表学报,2016,37(1):1-8.
[8] TIAN G Y, HE Y, ADEWALE I, et al. Research on spectral response of pulsed eddy current and NDE applications[J]. Sensors and Actuators A Physical, 2013, 189(2):313-320.
[9] 周德强,左晓芳,尤丽华,等.脉冲涡流铁磁性材料缺陷检测系统设计[J].传感器与微系统,2012,31(10):121-124.
[10] XU Z Y, WU X J, HUANG C, et al. Analysis of excitation current parameters in pulsed eddy current testing for ferromagnetic metallic materials[J]. International J Application Electromagn, 2012, 39:213-219.
[11] YU Y, YAN Y, WANG F, et al. An approach to reduce lift-off noise in pulsed eddy current nondestructive technology[J]. NDT & E International, 2014, 63:1-6.
[12] 张斌强.脉冲涡流检测系统的设计与研究[D].南京:南京航空航天大学,2009.
[13] HE Y, TIAN G, ZHANG H, et al. Steel corrosion characterization using pulsed eddy current systems[J]. IEEE Sensors Journal, 2012, 12(6):2113-2120.
[14] 高军哲,潘孟春,张琦,等.基于调频激励和细化谱分析的多频涡流检测技术研究[J].仪器仪表学报,2011,32(11):2628-2634.
[15] LIU B, HUANG P, ZENG X, et al. Hidden defect recognition based on the improved ensemble empirical decomposition method and pulsed eddy current testing[J]. NDT & E International, 2017, 86(Complete):175-185.
[16] FAN M, CAO B, SUNNY A I, et al. Pulsed eddy current thickness measurement using phase features immune to liftoff effect[J]. NDT & E International, 2017, 86(Complete):123-131.