Search

Incipient faults for analogue circuits in modern electronic systems are difficult to diagnose due to poor fault features. To address this issue, a method based on the attention weighted graph convolution network (Att-GCN) is proposed in this paper. The structural and data features of samples are jointly extracted to mine the effective characteristics from incipient faults. First, a wavelet packet energy transform and a probabilistic principal component analysis (ProbPCA) are employed to enhance the sample fault information. Then, the distance clustering method is deployed to construct the sample set into a non-European structure sample graph, where the structural features of fault samples are preserved. Second, an Att-GCN, which combines the spatial-domain graph convolution network and improved self-attention mechanism, is constructed to extract the structural features and data features to obtain more effective fault information. Additionally, the multisample dropout method is introduced to reduce network overfitting in the training process. To assess the method’s actual performance for fault diagnosis, experiments are carried out in the Sallen–Key bandpass filter circuit, the four-op-amp biquadratic filter circuit and the amplifier board circuit. The outcomes indicate that this method improves the incipient fault diagnosis accuracy for analogue circuits.

The pressure-sensitive paint (PSP) technique has shown superiorities in its large coverage area capability and high spatial resolution. The process of the PSP technique usually requires sufficient illumination that covers the entire test object, and a camera that acquires the particular excited fluorescence. Applications in internal flow study, like the compressor cascade, may fail as the optical access is heavily limited due to the closely adjacent components, which creates a high demand for spatial positioning arrangement of optical devices in the visualization system. In this work, a pre-positioning method was proposed to help determine the arrangement of optical devices of an internal flow PSP measurement system in advance. It was applied to the measurement of a linear compressor cascade with large solidity. The results showed that with the optical layout arrangement determined using this pre-positioning method, a full-field pressure distribution of the cascade blade can be acquired successfully.

In view of the problem that the current update flashing of the traditional automotive electronic control unit (ECU) software highly relies on professional maintenance personnel and external equipment, a method for ECU remote data flashing is proposed to achieve remote and efficient upgrade of ECU software. Furthermore, through the introduction of backup partitions and differential upgrade methods, the problems of lack of fault-tolerant processing, high bandwidth requirements and low efficiency in traditional ECU software update flashing are also solved. In this article, a remote update system is built, including the server-side and the vehicle, and the interface and communication protocols are defined based on HTTPS. The above methods have been verified on NXP IMX 6 platform. Associated testing of the simulation of the ECU by the STM32 and ROCKCHIP demo board has been made based on the CAN and Ethernet simulating the vehicle network architecture. By the real data catching from Ethernet and the CAN, the details of the log file of the programs’ event tracking information are analyzed to obtain the experimental results. The results indicated that the incremental remote data updating system built in this article can remotely update the CAN software accurately and efficiently in all simulation tests, which proved the practicability, accuracy, and efficiency of this method.

The paper aims to test the integrity of offshore cages. In this paper, offshore robots are used to collect video images. Through preprocessing methods such as color space conversion and Retinex algorithm of fusion-oriented filtering, the color distortion of the image is improved and the edge information of the image is maintained, so that the collected cage image is better recognized and calculated by the computer. And the paper uses the Canny algorithm to accurately locate the edge of the image, so that the boundary information can be reflected in more detail. In this paper, the adaptive threshold segmentation algorithm combined with mathematical morphology processing method is used to segment the offshore cage image, and extract the skeleton of the decomposed image to realize the detection of the integrity of the offshore net. Finally, a ROV equipped with a camera was used to verify the proposed method in a wave-flow water tank, which confirmed the effectiveness of the method and optimized the integrity recognition and image processing of the cage.