As the ocean engineering structure serves in the critical underwater environment, a variety of defects, such as cracks and corrosions, always cause damage to the structure. It is still a key challenge to identify and evaluate these defects accurately in the underwater environment. In this article, the visual and intelligent identification methods are presented for the inspection of defects in underwater structures using the alternating current field measurement (ACFM) technique. The current perturbation theory is developed to analyze the disturbed current field and the distorted magnetic field caused by defects. The gradient imaging algorithm is presented as an image preprocessing method to highlight the visual morphology of defects. The underwater intelligent ACFM system is set up. The experiments are carried out to verify the gradient imaging algorithm. The convolutional neural network (CNN) deep learning algorithm is presented to identify the grey-scale map samples preprocessed by the gradient imaging algorithm. The results show that the current perturbation theory clarifies the relationship between the characteristic signal and the morphology of various defects. The Bz image reflects the surface morphology of defects. The gradient imaging algorithm can achieve visual detection of defects. The single crack, the irregular crack, and the corrosion can be identified intelligently by the CNN deep learning algorithm. These defects can be evaluated accurately after classification.
28 October 2022 in IEEE Transactions on Industrial Informatics
The alternating current field measurement (ACFM) technique has been widely used in the defect detection of metal structures. However, the identification and reconstruction of defects depend on human experience or simple empirical formulas, which leads to misjudgment of defects and large quantization errors. In this article, we propose an end-to-end physics-informed neural network for defect identification and 3-D reconstruction. The high-precision automatic detection system with a specially designed probe is established to detect defects in any direction. The faster RCNN network is used to identify and classify defects. The physics-informed Pix2Pix network is constructed to realize 3-D reconstruction of defects with different types. The results show that the established end-to-end physics-informed neural network can realize the identification and 3-D reconstruction of defects in which the mean average precision is 0.9982, the average length error of cracks is 0.9249 mm, the average depth error of cracks is 0.3402 mm, the average volume error of corrosion is 0.0667, and the average maximum depth error of corrosion is 0.3464 mm.
11 October 2022 in Mechanical Systems and Signal Processing
As an important connection method between drill pipes, the thread is prone to fatigue cracks and stress corrosion cracks due to long-term exposure to complex forces and corrosive environments. The thread crack detection system of drill pipe based on altering current field measurement (ACFM) is proposed. The crack detection model of the drill pipe thread using ACFM is developed by the finite element software COMSOL. The distribution of the induced magnetic field above the thread is extracted. The relationships between the characteristic signal and the depth and angle of the crack are analyzed. The drill pipe thread detection probes and the detection system are established, and different types of cracks on two different specifications of threads are detected. The experimental results show that the detection system can achieve full coverage detection of the thread crest and root, and cracks at different angle can be identified effectively on the thread.
5 November 2021 in IEEE Transactions on Instrumentation and Measurement
The dynamic and static property assessment of industrial robot is of great significance to optimize its operation accuracy. A method for both the kinematic calibration and robot path error measurement based on camera-mirror binocular vision (CMBV) is proposed. First, the structural parameters of CMBV are investigated for identifying proper imaging parameters. Second, the high-accuracy all-in-one artifact, its image processing, and vision system calibration are introduced. Thereafter, a CMBV-matching model based on distance error constraint is proposed to identify robot kinematic parameters. Finally, by comparing the vision measured data and the nominal one, both the path error and kinematic model parameters are measured. The verification results based on artifact and laser tracker verify that the proposed vision system and method is accurate enough to assess the robot performance. The results of vision measurement show that at 1.5 m/min, the maximum circular trajectory error of vision measurement is 2.57 mm, and after compensating the determined robot kinematic model parameters, the average positioning accuracy of the robot end-effector is increased by more than 73.36%, which means that the CMBV-based method outperforms the monocular pose measurement (MPM) method.
Three-dimensional (3D) perception of deep-sea targets is the key to autonomous operation of underwater equipment (e.g., underwater robots). Underwater one-mirror galvanometric line-laser scanner has advantages for short-range measurement, but it is difficult to achieve high calibration accuracy due to installation errors and refraction effects. For this reason, in this paper, a high-accuracy refraction-considered and installation-error-independent calibration method is proposed for the vision system. Firstly, to address the difficulty of aligning the incident light plane with the galvanometer shaft, a high-accuracy land-based installation-error-independent model is proposed, which avoids the influence of the installation errors and allows the real shaft axis and the light-plane cluster poses to be calculated using only three light planes. Subsequently, considering the underwater refraction, a 3D model is established for simulating refractive behaviors of the light-plane cluster, and then a partition-based method is proposed for calibrating the underwater light-plane cluster, which further improves the calibration accuracy of the scanner in underwater measurement scenarios. Finally, a one-mirror galvanometric laser scanner is developed in the laboratory to verify the calibration accuracy and to perform the 3D measurement experiments of underwater targets. The results show that the calibration accuracy of the proposed land-based installation-error-independent model is improved 2 times more compared with the traditional installation-error-dependent model. Additionally, the measurement accuracy of the scanner for the standard sphere is 11.98 µm and 12.75 µm in the air and underwater measurement scenarios, and the two measurements are in good agreement. The above results comprehensively verify the high accuracy of the calibration method proposed in this paper.