We present a general theory of the holographic image reconstruction with linear frequency modulation (LFM) radars. For the first time, the system limitations in terms of the object extent and distance are derived and explicitly related to the LFM radar frequency-modulation slope ɣ . The holographic inversion formula is improved to account for the spherical spread of the scattered wave. The theory and the generalized holographic inversion algorithm are validated by synthetic benchmark data as well as experimental data from an in-house LFM-radar prototype operating at 29.9-GHz central frequency and bandwidth of 5.8 GHz. Experiments confirm that the lateral spatial resolution is about 5 mm. For optimal performance, the system is calibrated using a simple but effective calibration approach based on a measurement with a metallic plate. Experiments, with a volunteer carrying metallic and nonmetallic objects, demonstrate very good performance in realistic scenarios.

General theory of holographic inversion with linear frequency modulation (GHI-LFM) has been proposed recently, providing the framework for further advances in the holographic methods for image reconstruction with millimeter-wave linear frequency modulation (LFM) radar. Here, accelerated holographic imaging (AHI)-LFM, an AHI method for LFM radar that exploits range stacking, is proposed. The method is developed and validated for the purpose of whole-body security screening. The image quality and the computational efficiency are compared with the original GHI-LFM algorithm. It is demonstrated that the AHI-LFM algorithm improves the reconstruction speed by at least an order of magnitude while preserving the same image quality for the image sizes arising in practical whole-body security screening.

An image-based real-time pantograph anomaly detection method is presented by combining unsupervised deep learning and nearest neighbor classification. The proposed method includes the following key steps. Firstly, an improved DeblurGAN-v2 deblurring algorithm is applied to the input pantograph image if there exists motion blur. Next, deep learning semantic segmentation with hybrid coding that combines lightweight convolutional neural network (CNN) and vision transformer (VIT) is employed to accurately segment the pantograph structure within the image. And multi-scale feature-dense aggregation network based on an attentional feature fusion (AFF) module has been designed to efficiently integrate information from different feature layers. Finally, a K-nearest neighbor classification algorithm with deep pre-trained features from the segmented pantograph mask image has been utilized to detect anomalies in the pantograph. Experimental results demonstrate that the proposed pantograph segmentation network outperforms several general segmentation algorithms, achieving high MIoU of 95.86% with parameter size of 7M and FPS of 81.7. And nearest neighbor classification with deep pre-trained features achieves excellent pantograph anomaly detection performance with area under the receiver operating characteristic curve of 0.987 and area under precision-recall curve of 0.998. It is verified that the proposed pantograph anomaly detection method does not rely on abnormal data, and can achieve a high anomaly detection accuracy of 98.75%.

Using traditional FMECA to analyze the hazard of subway sliding plug door system, there are problems such as easy-to-take repetitive values, irrational allocation of expert's weights, and failure to consider the weights of evaluation factors. Hence, this paper proposes to improve FMECA by using linear interpolation to increase the differentiation of the same fault probability occurrence among various fault modes. Apply the DUOWA to dynamically assign weights to different experts. The AHP is used to endow weights to diverse evaluation factors to make them more suitable for engineering needs. The operation records of metro trains were collected from the Shanghai subway manufacturing plant for 1836 days. The hazards of the 17 common faults of the door were first analyzed using an improved FMECA,the EDCU is the component most prone to failure. Next, use a RCM strategy to determine maintenance periods for different faults. Finally, through the Weibull distribution fitting test, the fault rate function of the door is obtained, and the RUL of the door is predicted.