基于数字图像相关的动态结构损伤位置检测

Dynamic Structural Damage Localization Based on Digital Image Correlation

结构损伤严重威胁各类装备和设施的安全性,如何准确检测结构损伤位置成为一个亟待解决的问题。传统基于结构模态的损伤检测方法有着空间采样率低、依赖无损状态的基线数据等缺点。为了克服传统方法的不足,提出一种基于数字图像相关的全场振动测量方法,利用所提方法测量结构在固有频率激励下的模态振型,进而识别损伤导致的振型异常。借助图像测量高空间采样率优势,所提方法可以高精度定位损伤区域。通过切比雪夫多项式拟合获得结构的基线数据,进而计算结构损伤模态与基线数据的残差,实现对结构损伤的准确定位,无需结构无损伤时的基线数据。并采用频域噪声解耦技术分离振动信号和噪声,有效提高了模态数据的信噪比。最后通过在固有频率激励下悬臂板的损伤检测,验证了所提方法的有效性。

Objective The increasing complexity of mechanical structures and equipment,driven by industrial technology advancements,necessitates prompt damage repairs.Failure to address issues such as internal or surface cracks not only compromises structural integrity but also poses safety risks to operators.Identifying the precise location of structural damage has become an urgent issue.Vibration measurement techniques primarily include contact and non-contact methods.The contact measurement method involves attaching strain gauges or installing accelerometer sensors on the object’s surface to evaluate vibration response,which can alter the structure’s dynamic characteristics and limit data collection points.In contrast,the non-contact method provides high spatial resolution and accuracy but comes with a complex optical setup and limited environmental interference resistance.With image processing technology’s rapid progression,digital image correlation(DIC)has emerged as an effective non-contact measurement tool.Our study explores using DIC for structural dynamic response measurement and damage detection by comparing changes in modal parameters(frequency,damping,and modal shapes)between damaged and undamaged structures.Notably,modal shapes are sensitive indicators of local damage,closely related to its stiffness distribution.Once the structure is damaged,the stiffness in the damaged area changes,leading to abnormal changes in the displacement mode.However,traditional damage detection methods based on structural modal shape analysis face certain limitations:1)The spatial resolution of damage structure measurement depends largely on the spatial sampling rate of the measurement method.2)Damage identification methods rely on comparing the vibration response of the damaged structure with that of an undamaged structure.However,obtaining baseline data from undamaged structures is often challenging.3)Measurement data contains random noise,which not only makes signal processing complex but also significantly affects the accuracy of damage identification.We introduce a DIC full-field vibration measurement method that utilizes modal shapes to identify damage locations.We propose frequency domain noise decoupling technology that utilizes laser Doppler vibrometer(LDV)single-point data to assist the displacement field of DIC.Methods DIC is a non-contact optical measurement method that utilizes cameras to capture the patterns of the measured object at different times and derives displacement fields by matching image feature points.In this study,we employ DIC to measure the operating deflection shape(ODS)of the structure under natural frequency excitation to identify damaged regions.When the excitation signal of the structure is at its natural frequency,the vibration response of the structure is primarily dominated by that mode,making the ODS closely resemble the structural modal shape.However,DIC experiments are susceptible to systematic and random errors,leading to measurement data where displacement fields are mixed with random noise,complicating damage detection using DIC measurements.To address this,we propose a noise decoupling technology using a bandpass filter in the frequency domain to eliminate non-vibrational frequency components from the DIC results.Furthermore,LDV is utilized to accurately measure the vibration response,guiding the noise decoupling process for DIC data.By separating vibration signals from noise in the frequency domain,we enhance the signal-to-noise ratio of the modal shapes.Subsequently,Chebyshev polynomial fitting is used to remove high-frequency information from the displacement field,reconstructing the baseline data of the undamaged structure.The residual analysis method then locates abnormalities by calculating differences between modal shapes and fitted baseline data.In structures with uniform material distribution,peaks in residuals indicate damage locations.This approach takes full advantage of the high spatial sampling rate of image measurements for precise damage localization.The schematic diagram of the DIC measuring vibration modes to detect structural damage is presented in Fig.6.Results and Discussions Experiments are conducted on cantilever plates I and II to validate the efficacy of the proposed method.Firstly,we measure the natural frequency of the cantilever plates I and II with LDV.Then,DIC captures the modal shapes of the structure under excitation by the first four natural frequencies.The operational deflection shape of cantilever plate I is then processed with a bandpass filter to confirm the effectiveness of the LDV-guided DIC data noise decoupling technology(Fig.7).The Modal Assurance Criterion is used to compare Ansys simulation data with the DIC measurement results post bandpass filtering to verify the effectiveness of the proposed filtering method(Fig.8).Afterwards,the modal shapes derived after noise reduction are employed to detect structural damage locations.To ensure accuracy in fitting and to avoid overfitting,a seventh-order Chebyshev polynomial is used to establish the baseline data.The structural damage locations on cantilever plates I and II are ascertained by measuring the modal shape obtained under excitation at the fourth and eighth natural frequencies,respectively.Experimental results demonstrate that the modal shapes,once noise-decoupled,could pinpoint the damage locations on cantilever plates I and II with precision.In contrast,the modal shapes that were not filtered failed to reveal the damage locations(Figs.10 and 11).Conclusions We present a damage detection method that leverages DIC for measuring modal shapes.The technique capitalizes on the high spatial resolution of DIC to identify damaged areas within structures.By employing Chebyshev polynomial fitting,this method reconstructs baseline data,eliminating the need for prior baseline measurements.Additionally,frequency domain noise decoupling technology is utilized to remove random noise from the modal shapes,effectively reducing the influence of noise on damage detection.Experimental tests on cantilever plane damage detection confirm the efficacy of the proposed method in detecting structural defects.