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.

The intelligent fault diagnosis of main circulation pumps is crucial for ensuring their safe and stable operation. However, limited research has been conducted on this topic, and applying existing fault diagnosis methods designed for other equipment may not yield optimal results when directly used for main circulation pump fault diagnosis. To address this issue, we propose a novel ensemble fault diagnosis model for the main circulation pumps of converter valves in voltage source converter-based high voltage direct current transmission (VSG-HVDC) systems. The proposed model employs a set of base learners already able to achieve satisfying fault diagnosis performance and a weighting model based on deep reinforcement learning that synthesizes the outputs of these base learners and assigns different weights to obtain the final fault diagnosis results. The experimental results demonstrate that the proposed model outperforms alternative approaches, achieving an accuracy of 95.00% and an F₁ score of 90.48%. Compared to the widely used long and short-term memory artificial neural network (LSTM), the proposed model exhibits improvements of 4.06% in accuracy and 7.85% in F₁ score. Furthermore, it surpasses the latest existing ensemble model based on the improved sparrow algorithm, with enhancements of 1.56% in accuracy and 2.91% in F₁ score. This work presents a data-driven tool with high accuracy for the fault diagnosis of main circulation pumps, which plays a critical role in maintaining the operational stability of VSG-HVDC systems and satisfying the unmanned requirements of offshore flexible platform cooling systems.