Compound fault diagnosis has been a challenge in rotating machinery health management. Current compound fault diagnosis methods rely on a substantial number of labeled samples, which are impractical to obtain for every type of compound fault and pose safety risks when collected in industrial settings. To address these issues, we have built a bearing fault dataset that includes compound faults under multiple conditions. We propose a zero-shot compound fault identification model, which can be established solely using vibration data from single faults under no-load conditions and is suitable for multiple unknown load conditions. Firstly, we design a compound fault logical semantic (CFLS) construction method based on statistical indicators from vibration data of single faults under no-load conditions. Secondly, we develop a multi-head self-attention based feature extraction approach that extracts features from vibration data under various load conditions. Thirdly, we train a semantic embedding model using the semantics and features derived from single faults. By inputting the extracted features of compound faults into the model, we can get the compound fault dynamic semantic (CFDS) under multiple load conditions. Finally, the compound faults are identified by using semantics regression to compare the Euclidean distance between CFLS and CFDS. This method has been validated on two cases using both self-built HDU dataset and the Paderborn dataset. The results show that it can recognize compound faults across multiple unknown domains and the identification accuracy has reached 78.17%.

This research focuses on the load characteristics of piezoelectric transducers in the process of longitudinal vibration ultrasonic welding. We are primarily interested in the impedance characteristics of the piezoelectric transducer during loading, which is studied by leveraging the equivalent circuit theory of piezoelectric transducers. Specifically, we propose a cross-value mapping method. This method can well map the load change in ultrasonic welding to the impedance change, aiming to obtain an equivalent model of impedance and load. The least-squares strategy is used for parameter identification during data fitting. Extensive simulations and physical experiments are conducted to verify the proposed model. As a result, we can empirically find that the result from our model agrees with the impedance characteristics from the real-life data measured by the impedance meter, indicating its potential for real practice in controller research and transducer design.

In rotary ultrasonic machining (RUM), the utiliza-tion of contactless energy transfer (CET) theory addresses the limitations imposed by traditional contact power supply systems on rotational speed, however, it also introduces the challenge of inadequate transmission performance. Specifically, impedance variations of oscillator pose challenges for the contactless energy transfer system (CETS). These challenges include maintaining high transmission efficiency and desirable impedance charac-teristics, which can impact the performance of system and the quality of workpiece. To address the issue, this paper proposes the implementation of a bi-lateral compensation network using an LC-CL structure to against the low output power and poor anti-interference capabilities of series-series (SS) topology. Addi-tionally, a variable loads parameter optimization (VLPO) model, based on the fluctuations of equivalent dynamic component parameters during actual machining, is proposed. This model integrates an efficiency evaluation function aimed at achieving higher transmission efficiency and reducing fluctuations, as well as evaluation functions for the quality factor, admittance circle radius, and bandwidth to enhance impedance characteristics. Through the implementation of VLPO, the system impedance characteristics of LC-CL are significantly improved in compar-ison to SS and carrying capacity is effectively enhanced. The effectiveness of this scheme is validated through the construction of CETS experimental platform.

Colorectal cancer is a common malignant tumor in the gastrointestinal tract, which usually evolves from adenomatous polyps. However, due to the similarity in color between polyps and their surrounding tissues in colonoscopy images, and their diversity in size, shape, and texture, intelligent diagnosis still remains great challenges. For this reason, we present a novel dense residual-inception network (DRI-Net) which utilizes U-Net as the backbone. Firstly, in order to increase the width of the network, a modified residual-inception block is designed to replace the traditional convolutional, thereby improving its capacity and expressiveness. Moreover, the dense connection scheme is adopted to increase the network depth so that more complex feature inputs can be fitted. Finally, an improved down-sampling module is built to reduce the loss of image feature information. For fair comparison, we validated all method on the Kvasir-SEG dataset using three popular evaluation metrics. Experimental results consistently illustrates that the values of DRI-Net on IoU, Mcc and Dice attain 77.72%, 85.94% and 86.51%, which were 1.41%, 0.66% and 0.75% higher than the suboptimal model. Similarly, through ablation studies, it also demonstrated the effectiveness of our approach in colorectal semantic segmentation.