Geometric parameter measurement of tubing internal thread is critical for oil pipeline safety. In response to the shortcomings of existing methods for measuring internal thread geometric parameters, such as low efficiency, poor accuracy, and poor accessibility, this paper proposes a vision system for measuring internal thread geometric parameters based on double-mirrored structured light. Compared to previous methods, our system can completely reproduce the internal thread tooth profiles and allows multi-parameter measurement in one setup. To establish the correlation between the structural and imaging parameters of the vision system, three-dimensional (3D) optical path models (OPMs) for the vision system considering the mirror effect of the prism is proposed, which extends the scope of the optical path analysis and provides a theoretical foundation for designing the structural parameters of the vision system. Moreover, modeling and three-step calibration methods for the vision system are proposed to realize high-accuracy restoration from the two-dimensional (2D) virtual image to the actual 3D tooth profiles. Finally, a vision measurement system is developed, and experiments are carried out to verify the accuracy and measure the three geometric parameters (i.e., taper, pitch, and tooth height) of typical internal threads. Based on the validation results using the reference system, the vision measurement accuracy and efficiency are 6.7 and 120 times that of the traditional system, which verifies the measurement effectiveness and accuracy of the vision system proposed in this paper.

In the actual operation process, some of the power system bad data identification methods have the problem of low accuracy, for this reason, a deep learning-based power system bad data identification method is designed to improve this defect. The data is collected from power system users, the phase deviation caused by non-integer sampling is reduced by high sampling rate, the measurement signal period is obtained, the operational state of the distribution network is evaluated based on deep learning, the state vector is calculated, the maximum standard residual value is found, the location of the bad data is obtained, and the bad data identification method is designed. Experimental results: The mean accuracy of the power system bad data identification method in the paper is: 78.26%, which indicates that the designed power system bad data identification method performs better after fully integrating the deep learning.

Oilfield pipes with out-of-tolerance internal thread can lead to failures, so the internal thread geometric parameters need to be measured. To tackle the problem of the low efficiency, poor accuracy, easy wear, and poor accessibility of existing methods, a single-lens multi-mirror laser stereo vision-based system for measuring geometric parameters of the internal thread is proposed, which allows the measurement of three parameters in one setup by completely reproducing the three-dimensional (3D) tooth profiles of the internal thread. In the system design, to overcome the incomplete representation of imaging parameters caused by insufficient consideration of dimensions and structural parameters of the existing models, an explicit 3D optical path model without a reflecting prism is first proposed. Then, considering the intervention of the reflecting prism, a calculation model for the suitable prism size and the final imaging parameters of the vision system is proposed, which ensures the measurement accessibility and accuracy by solving the problem that the existing system design only depends on experience without theoretical basis. Finally, based on the American Petroleum Institute standard, internal thread geometric parameters are obtained from the vision-reconstructed 3D tooth profiles. According to the optimized structural parameters, a vision system is built for measuring the internal thread geometric parameters of two types of oilfield pipes. Accuracy verification and typical internal thread measurement results show that the average measurement errors of the vision system proposed for the pitch, taper, and tooth height are 0.0051 mm, 0.6055 mm/m, and 0.0071 mm, respectively. Combined with the vision measurement time of 0.5 s for the three parameters, the above results comprehensively verify the high accuracy and high efficiency of the vision-based system.