In industrial production, flaws and defects inevitably appear on surfaces, resulting in unqualified products. Therefore, surface defect detection plays a key role in ensuring industrial product quality and maintaining industrial production lines. However, surface defects on different products have different manifestations, so it is difficult to regard all defective products as being within one category that has common characteristics. Defective products are also often rare in industrial production, making it difficult to collect enough samples. Therefore, it is appropriate to view the surface defect detection problem as a semi-supervised anomaly detection problem. In this paper, we propose an anomaly detection method that is based on dual attention and consistency loss to accomplish the task of surface defect detection. At the reconstruction stage, we employed both channel attention and pixel attention so that the network could learn more robust normal image reconstruction, which could in turn help to separate images of defects from defect-free images. Moreover, we proposed a consistency loss function that could exploit the differences between the multiple modalities of the images to improve the performance of the anomaly detection. Our experimental results showed that the proposed method could achieve a superior performance compared to the existing anomaly detection-based methods using the Magnetic Tile and MVTec AD datasets.

In the production process of metal industrial products, the deficiencies and limitations of existing technologies and working conditions can have adverse effects on the quality of the final products, making surface defect detection particularly crucial. However, collecting a sufficient number of samples of defective products can be challenging. Therefore, treating surface defect detection as a semi-supervised problem is appropriate. In this paper, we propose a method based on a Transformer with pruned and merged multi-scale masked feature fusion. This method learns the semantic context from normal samples. We incorporate the Vision Transformer (ViT) into a generative adversarial network to jointly learn the generation in the high-dimensional image space and the inference in the latent space. We use an encoder–decoder neural network with long skip connections to capture information between shallow and deep layers. During training and testing, we design block masks of different scales to obtain rich semantic context information. Additionally, we introduce token merging (ToMe) into the ViT to improve the training speed of the model without affecting the training results. In this paper, we focus on the problems of rust, scratches, and other defects on the metal surface. We conduct various experiments on five metal industrial product datasets and the MVTec AD dataset to demonstrate the superiority of our method.

The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.

Traditional methods of orthogonal basis function decomposition have been extensively used to detect magnetic anomaly signals. However, the determination of the relative velocity between the detection platform and the magnetic target remains elusive in practical detection. And, the non-ideal uniform motion of the magnetic target further complicates the process and adversely impacts the detector’s performance. To address this challenge, this paper introduces an adaptive scale factor method based on orthogonal basis function decomposition. This new method can be used to adjust the relative velocity between the detection platform and the magnetic target and to refine the characteristic time in the basis functions. In this paper, a mathematical relationship between the scale factor and the relative velocity is established, which is subsequently fitted into a Gauss function curve. The optimal scale factor, denoted as β, is adaptively chosen from the fitting curve when the magnetic target moves at a non-ideal uniform velocity with an unknown motion state. The results of simulations indicate that the scale factor improves the signal-to-noise ratio of the magnetic anomaly signals in a non-ideal state. And, this method can improve the energy value of OBF decomposition by 17.7%. Simultaneously, this method ensures that the moment the magnetic target passes the CPA coincides with the energy peak of the orthogonal basis detection, which improves the accuracy by 54.1% compared with the traditional method. The effectiveness and precision of the proposed method are verified using simulations and practical experiments.

This article reports on a millimeter-wave (MM-wave) signal down-conversion system with low phase noise for chip-scaled optical clocks. The system utilizes analog regenerative frequency division, low-noise fractional frequency division, and phase-locked frequency division techniques to down-convert a 100 GHz MM-wave signal to 100 MHz with phase noise of −117 dBc/Hz @100 Hz, −133 dBc/Hz @1 kHz, and 10 MHz with phase noise of −124 dBc/Hz @100 Hz and −143 dBc/Hz @1 kHz. The frequency stability of the signal down-converted to 100 MHz is 5.0 × 10⁻¹⁵ @ 1 s and 1.8 × 10⁻¹⁶ @ 1000 s, while the frequency stability of the 10 MHz signal is 5.7 × 10⁻¹⁴ @ 1 s and 5.9 × 10⁻¹⁶ @1000 s, both of which decrease to the 10⁻¹⁶ level at 10,000 s. This down-conversion system meets the frequency conversion requirements of state-of-the-art chip-based optical clocks and micro-cavity optical combs.