In most current nondestructive testing systems, a magnetic flux leakage (MFL) method is widely used in various industry fields, where the structural integrity of specimens is of vital importance. The estimation of defect size in specimen from the MFL measurements is a key and difficult problem. The traditional methods have low precision because feature extraction procedure relies on prior knowledge and the ability of designer. Inspired by the idea of convolutional neural network (CNN), a novel visual transformation CNN (VT-CNN) is proposed in this paper to overcome the limitation of traditional method in a feature extraction procedure. By adding a visual transformation layer according to the characteristics of the MFL measurements, the VT-CNN can distinguish the defect feature with different sizes more accurately. Moreover, since the VT-CNN method is designed based on the deep learning theory, more industrial big data with accurate label should be used to train the network. Due to the difficulty of making real industrial big data, a novel mesher magnetic dipole model is designed to simulate this industrial process. A large simulated MFL measurement of irregular defects produced by this model can increase the number of training samples and improve the robustness of the network. Experiments to estimate natural corrosion defects on real industrial pipelines are performed to validate the proposed framework. The experimental results are illustrated in detail, which highlights the superiority of the proposed method in industrial applications.

Intelligent fault diagnosis is vital in smart manufacturing. And deep learning-based fault diagnosis has become a hot topic due to its strong feature extraction ability. However, traditional deep learning-based methods exist two limitations. One is that a large number of labeled samples are required to construct effective diagnosis models. Another is that these methods lack flexibility, especially for homologous multi-task problems.In this paper, a novel domain knowledge-based deep-broad learning framework (DK-DBLF) is proposed to overcome above limitations. DK-DBLF consists of two parts: task-specific feature extractor and flexible fault recognizer. The first part is constructed by several convolutional neural networks to obtain abstract features automatically, and the second part employs broad learning system to improve flexibility of DK-DBLF. To combine two parts more effectively, bridge label-based strategy is designed, which is a key connection that can integrate domain knowledge into learning process. The performance of DK-DBLF is tested on motor bearing and pipeline defect datasets, which are health condition classification and homologous multi-task estimation problems respectively. The results have demonstrated that our framework can significantly reduce the usage of labeled samples in learning process, and architecture adjustment can be easily performed when compared with traditional deep methods.

This paper proposes a quick and accurate method for reconstructing defect profiles in pipelines from magnetic flux leakage (MFL) signals employing a modified harmony search (MHS) algorithm. To improve the quality of the initial harmony memory, a multiple selection opposition-based learning strategy is presented in the MHS algorithm. Moreover, the pitch adjusting rate is set to increase linearly, and the distance bandwidth ( bw ) is designed to be dynamically adjusted to shorten the calculation time. A specially designed modified sum-squared error with weights is proposed and employed as the fitness function to improve the fitting degree between the reference and predicted signals in the defect response segment. The weights are determined by the characteristics of reference signals. We demonstrate the adequacy of the performance of the proposed model using both simulated and real MFL signals. We also present comparative results of the proposed model and other methods. The results prove that the proposed method can achieve higher efficiency while maintaining excellent accuracy.

Magnetic flux leakage (MFL) testing is coming into prominence as an inspection tool applied to pipeline evaluation. The MFL detectors are challenging to accurately evaluate pipe defects at high speed due to velocity effects. Current methods typically require detectors to operate at low speeds or compensate for detection data offline, but they reduce detection efficiency or require sophisticated algorithms. In this article, a novel double remote magnetic field synthesis (DRMFS) method is proposed to address the issue. First, we give a thorough analysis of the influence of velocity effects on high-speed MFL signals, reinterpreting its action mechanism. Second, the critical parameters are optimized to improve pipe magnetization. The relationships between the sensor layout and normalized signal similarity are studied at different speeds to reduce signal distortion. Finally, the usability of the DRMFS method in reducing signal distortion and its capability in detecting deep defects are validated by measuring defect depths. Results showed synthesis signals are highly similar to static MFL signals and approximately linear with the defect depth, which could improve the detection accuracy. Our results can enable the exploration of information utilization in limited space and the establishment of a balance between detection efficiency and signal accuracy.

At present, the method based on deep learning performs well in public object detection tasks. However, there are still two problems to be solved for industrial defect detection: 1) Industrial scenes requires real-time and lightweight; 2) Lightweight network accuracy is limited. In order to tackle these issues, based on knowledge distillation, this paper proposes an effective lightweight defect detection network (KD-LightNet) suitable for edge scene. First of all, a lightweight network (LightNet) is designed based on structure reparameterization, which can sufficiently improve the capability of network feature extraction and reduce the complexity of model inferring. Moreover, a well prepared self-distillation strategy is proposed, which utilize the pre-trained LightNet network as a teacher model to transfer knowledge in the same structure. Then, in order to fully utilize the logits predicted by teacher model, an improved KL divergence loss is proposed to enhance the accuracy of the student model. Finally, in the experiments, three industrial datasets (PKU-Market-PCB, NEU-DET and Magnetic tile defect dataset) were used to validate the proposed model performance. The KD-LightNet detection accuracy (mAP) is improved by an average of 6.87%, while the average detection speed reaches 72 FPS @3070Ti (Params 4.7M), which meets the requirements of industrial defect detection accuracy and real-time.

In this paper, a wind turbine anomaly detection method based on a generalized feature extraction is proposed. Firstly, wind turbine (WT) attributes collected from the Supervisory Control And Data Acquisition (SCADA) system are clustered with k-means, and the Silhouette Coefficient (SC) is adopted to judge the effectiveness of clustering. Correlation between attributes within a class becomes larger, correlation between classes becomes smaller by clustering. Then, dimensions of attributes within classes are reduced based on t-Distributed-Stochastic Neighbor Embedding (t-SNE) so that the low-dimensional attributes can be more full and more concise in reflecting the WT attributes. Finally, the detection model is trained and the normal or abnormal state is detected by the classification result 0 or 1 respectively. Experiments consists of three cases with SCADA data demonstrate the effectiveness of the proposed method.