Defect depth is an essential indicator in magnetic flux leakage (MFL) detection and estimation. The quantification errors for defect depth are closely related to length and width errors, and this feature has always been used to support the operator's judgment in defect identification. However, the existing defect quantification algorithms based on shallow and deep neural networks only employed simple general network structures inspired by the field of artificial intelligence; consequently, these network structures lack the support of physical concepts and result in large quantification errors regarding defect size, especially depth. In this article, to describe and integrate the above theory into a deep neural network, we propose a physics-informed doubly fed cross-residual network (DfedResNet) suitable for MFL defect detection based on deep learning. Physics-based MFL defect quantification theory is studied and integrated into loss functions during the neural network training. DfedResNet quantifies defects in MFL data and automatically extracts deep features of defects. The experimental results show that it effectively achieves high-precision quantification of defect length, width, and depth simultaneously, especially defect depth. Moreover, it considers data from all three dimensions during network training, and use the originally measured magnetic signal data in place of recognized images to avoid defect information loss and further improve the quantification accuracy. The deep DfedResNet model proposed in this article reduces defect length and width quantification errors to within 0.3 mm and defect depth quantification errors to within 0.4% t . In addition, compared with other network structures and traditional algorithms, DfedResNet improves defect quantification accuracy by 1–2 orders of magnitude and thus achieves a high quantification performance.

For monitoring burst events in a kind of reactive wireless sensor networks (WSNs), a multipath routing protocol (MRP) based on dynamic clustering and ant colony optimization (ACO) is proposed.. Such an approach can maximize the network lifetime and reduce the energy consumption. An important attribute of WSNs is their limited power supply, and therefore some metrics (such as energy consumption of communication among nodes, residual energy, path length) were considered as very important criteria while designing routing in the MRP. Firstly, a cluster head (CH) is selected among nodes located in the event area according to some parameters, such as residual energy. Secondly, an improved ACO algorithm is applied in the search for multiple paths between the CH and sink node. Finally, the CH dynamically chooses a route to transmit data with a probability that depends on many path metrics, such as energy consumption. The simulation results show that MRP can prolong the network lifetime, as well as balance of energy consumption among nodes and reduce the average energy consumption effectively.

It is challenging to apply deep learning in professional fields that lack big data support, especially in industrial structure health assessments using ultrasonic guided wave nondestructive testing (NDT) method. To solve this problem, one feasible solution is to introduce the concept of NDT physics into a deep neural network to compensate for the network's poor predictive abilities when trained on small datasets. Therefore, we propose a physics-informed deep neural network, named GuwNet, based on a unidirectional oblique-focusing (UOF) high-frequency, high-order shear horizontal guided wave electromagnetic acoustic transducer (EMAT) to quantify microcrack defects more accurately. First, the designed focused-transmission omnidirectional-reception UOF-EMAT can produce pure high-frequency, high-order guided waves. Through a circumferential arrangement of multiple receiving transducers, the maximum amount of information can be obtained regarding the reflected waves of the defect. This method solves the inherent problems of an EMAT (i.e., low energy conversion efficiency) and achieves effective detection of microcrack defects. Second, we study the quantification principle of microcrack defects suitable for UOF-EMAT, and propose a deep neural network using physical knowledge regarding this theory. We rationally design the network structure based on the quantitative principles and logic obtained from this article. In addition, feedback and feedforward loss functions suitable for evaluating different forms of variables are proposed to integrate the physical concepts of ultrasonic guided wave testing into the neural network training. Finally, we verify the performance of the proposed GuwNet based on the UOF-EMAT. Compared with traditional nonphysics-informed methods, the length, depth, and direction of the quantification errors are reduced to 0.127 mm, 0.279% d_t , and 1.843°, respectively, and the average quantification error is reduced by more than 80%.

Recently, subsynchronous oscillations (SSOs) have occurred frequently due to the interaction between wind farm controllers and transmission networks. When an SSO occurs, subsynchronous and supersynchronous interharmonics are present in a voltage/current signal. Because SSOs are serious threats to power system safety and stability, it is important to study subsynchronous and supersynchronous interharmonic phasor and frequency estimators for SSO identification and monitoring (thus for mitigation equipment operation). The systematic errors of the Taylor-Fourier multifrequency model-based parameter estimator are analyzed theoretically. It is found that the key to high estimation accuracy is to select interharmonic and fundamental model frequencies as accurately as possible. To this end, the three-point interpolated discrete Fourier transform and an iteration scheme are used to select the initial model frequencies and modify them iteratively. Simulation tests show that the interharmonic total vector error (TVE) and frequency error (FE) of the proposed method are always below 0.6% and 25 mHz, respectively. The fundamental TVE and FE limits in the IEEE standard can also be fully met, and the computation time can meet the requirements of high reporting rate phasor measurement units. In addition, the current samples recorded in an SSO event are used to demonstrate the real benefits of the proposed method.

The pipeline in-service needs to be inspected in certain period to master its structural health status. Ultrasonic guided wave which can propagate along pipelines with less energy loss provides an efficient method for long-term in situ inspection. Guided wave can detect both corrosion and cracks existing in structures. To overcome the problem of huge amounts of data and to maintain defect identification accuracy, the compressed sensing method for guided wave inspection is proposed. The compression process is essentially a scheme of analog to information conversion to compress the signal. It is accomplished by random demodulation and the equivalent sampling rate below the Nyquist rate helps to save most of storage. The compressed data is recovered to the sparse spatial domain based on the constructed dictionary from a guided wave propagation model. To verify the effectiveness of proposed method, both numerical simulations and experimental investigations are conducted. The results indicate the availability of compression and high accuracy of defect location after recovery. The influences of different compression schemes and compression ratios are further analyzed. In addition, the comparisons with direct recovery without compression and traditional analysis methods demonstrate the advantageous performance of the proposed method.

This paper proposes a new omni-directional electromagnetic acoustic transducer (EMAT) for the ultrasonic Lamb wave (ULW) tomography imaging (TI) of defects in metallic plates. The proposed EMAT is composed of a permanent magnet and a coil with a contra-flexure structure. This new EMAT coil structure is used for omni-directional ULW transmission and reception and ULW TI for the first time. The theoretical background and the working principles of this EMAT are presented and analyzed. The experimental results of its use on a 3 mm thick aluminum plate indicate that the EMAT with a contra-flexure coil (CFC) can transmit and receive a pure single A0 mode ULW with a high signal-to-noise ratio (SNR). Thus, the extraction of the projection data used for ULW TI may be performed accurately. The circumferential consistency of the projection data is only slightly influenced by the distortion of the eddy current field that is induced by the new CFC with an irregular shape. When the new EMAT array is used for ULW TI using the cross-hole method and SIRT arithmetic, a desirable imaging quality can be achieved, and the estimated size of an artificial corrosion defect agreed well with its actual value. The relation between the reconstruction resolution and the number of the new EMATs used is analyzed. More TI experiments are carried out when the aluminum plate defect is in two different locations relative to the EMAT array, for the further investigation of the performances of the new EMATs.