Zilong Zhang

Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical applications. The former is that various and sufficient defects are difficult to obtain, while the latter is that specific defects cannot be located. To solve these problems, in this article, we focus on the few-shot semantic segmentation (FSS) method, which can locate unseen defects conditioned on a few annotations without retraining. Compared to common objects in natural images, the defects in VII are small. This brings two problems to current FSS methods: first, distortion of target semantics and second, many false positives for backgrounds. To alleviate these problems, we propose a small object few-shot segmentation (SOFS) model. The key idea for alleviating, first, is to avoid the resizing of the original image and correctly indicate the intensity of target semantics. SOFS achieves this idea via the nonresizing procedure and the prototype intensity downsampling of support annotations. To alleviate, second, we design an abnormal prior map in SOFS to guide the model in reducing false positives and propose a mixed normal dice loss to prevent the model from predicting false positives preferentially. SOFS can achieve FSS and few-shot anomaly detection determined by support masks. Diverse experiments substantiate the superior performance of SOFS.

Intelligent fault diagnosis is essential for downtime reduction in modern industries. However, domain (i.e., working condition) variants are unavoidable for fault diagnosis under changing environment. Though one can obtain a customized deep learning model for a given domain, it is not practical to design deep neural networks manually for multiple domains. Differentiable architecture search (DARTS), as an automatic machine learning technique, can automate the network design process for a specific domain efficiently by using hypernetwork and differentiable search strategy. Nevertheless, the representation of hypernetwork is restricted by several unfair factors, and the searched architecture of DARTS is overconfident. To address these issues, a one-shot neural architecture search approach, which involves two-stage learning, is proposed for efficient domain matching fault diagnosis. In the first training stage, the warmup and path-dropout strategies are taken to enhance the competitiveness of the parametric operators and alleviate the coadaptation problem to obtain an intuitively fair hypernetwork. In the second matching stage, variational inference is introduced into a differentiable search strategy to estimate the uncertainty of model matching, and a scale mixture prior is used to softly constrain the matching stage. Then, a candidate architectures set can be sampled and ordered from the posterior. Multidomain experiment is implemented by adding noise to the raw signal, and the proposed method outperforms four commonly used deep neural networks for aeroengine bevel gear fault diagnosis.

Study design A hospital-based retrospective epidemiological study. Objective To describe the demographic and epidemiological characteristics of patients with traumatic spinal cord injury (TSCI) in Xi’an to help health-related institutions formulate corresponding measures. Setting People with TSCI, all spine centres and orthopaedic centres in Xi’an, China. Methods We retrospectively reviewed the medical records of the all spine centers or orthopedic centers in Xi’an according to the International Classification of Disease Version 10 (ICD-10) and diagnostic code of TSCI. Variables included gender, age, medical insurance, etiology, occupation, level of injury, and severity of injury, multiple injury, complication, treatment, and so on. Results The study included the medical records of 1730 patients with TSCI from 2014 to 2018. The estimated annual incidence rate increased from 39.0 cases (95% CI, 34.7–43.3 cases) per 1 million persons in 2014 to 43.2 cases (95% CI, 39.0–47.5 cases) per 1 million persons in 2018. The leading cause of TSCI was high falls (35.5%, 614 cases). The most common injury site was the cervical spinal cord, accounting for 55.7% (963 cases). The degree of injury severity with the highest proportion was incomplete tetraplegia (47.2%, 816 cases). In addition, 71.4% (1236 cases) of TSCI cases had spinal fracture or dislocation. Conclusions There are specific epidemiological characteristics of TSCI patients in Xi’an, and preventive measures are suggested to be based on the characteristics of the different types of patients with TSCI and focused on high-risk groups.

Traction motor bearings are crucial components to guarantee stable operation. Thus, it is significant to monitor the bearing condition. Dictionary learning is a powerful method to extract the characteristic condition. Compared with ordinary dictionary learning, the multiscale dictionary learning method applied to transform coefficients performs well in extracting the impact signals and takes less learning time. However, it spends more time tuning parameters to make the algorithm more efficient, especially in practical industrial applications. Hence, a faster adaptive parameter multiscale dictionary learning (Faster AP-MSDL) method is proposed in this article which adaptively chooses the scales of learning and estimates the parameters of sparse coding in dictionary learning simultaneously, and it possesses two core traits including less learning time and adaptive parameter estimation, which make this method more suitable to practical industrial application. Finally, a simulation experiment and two practical industrial experiments including a bearing run-to-failure test and a fault experiment of traction motor rolling bearing are conducted using our proposed method to verify adaptive ability and superiority. The superiority of the proposed method is also verified by comparing with other state-of-the-art methods.

In communication systems, multi-path transmission could improve spectrum efficiency and reduce time delay markedly. In this paper, two transmission modes which employ the network coding and the data allocating jointly are proposed for multi-path communication systems, called the data allocating and network coding (DANC) mode and network coding and data allocating (NCDA) mode. The big different is, the former allocates data to each feasible path and then does network coding, while the latter swaps the order of two operations. Corresponding optimization problem are solved with an iterative process based on traditional branch and bound algorithm. The qualitative analyses of the operation order, reasons for the performance gap and advantages of different modes are also provided. Simulation results under different conditions demonstrate that the proposed transmission methods could improve the time delay performance effectively.