In industrial production, the efficiency of fault diagnosis is seriously affected by such problems as lack of data, complex data types and low popularity of machine learning models. Therefore, to solve the above problems, we developed a novel wind turbine fault diagnosis model with high universality and strong generalization ability. Firstly, the one-dimensional original vibration data under different working conditions are divided into large-scale data, mid-scale data, small-scale data and class imbalance data. At the same time, all kinds of one-dimensional data are reshaped into two-dimensional form. Then, the residual network structure was redesigned to implement deep transfer learning in a pre-training-fine-tuning manner based on the sensitivity of vibration data features to the size of the convolutional kernel. In addition, a super parameter optimizer is added in this study to optimize some super parameter settings. In addition, the optimization of some hyperparameter settings was achieved by adding a hyperparameter search mechanism in this study. Finally, we used the developed deep transfer learning model for fault diagnosis of different types of target data of wind turbine. Experiments show that the model proposed in this study can show superior diagnostic performance in the face of different data sizes, unbalanced data types and various working conditions, and has excellent universality and reliability.

No abstract

No abstract

A prototype of the forward tracking array consisting of three multiwire drift chambers (MWDC) for the external target experiment (CEE) at the Heavy Ion Research Facility at the Lanzhou -Cooling Storage Ring (HIRFL-CSR) has been assembled and tested using cosmic rays. The signals from the anode wires are amplified and fed to a Flash-ADC to deliver the drift time and charge integration. The performances of the array prototype are investigated under various high voltages. For the tracking performances, after the space-time relation (STR) calibration and the detector displacement correction, the standard deviation of 223 μm of the residue is obtained. The performances of the forward MWDCs tracking array meets the requirements of CEE in design.

The high-efficiency excavation of mole cricket is associated to their motion pattern and the action mode of digging force. In this paper, we present a kinematic and mechanical test system for synchronously acquiring the excavation motion and digging force of mole crickets. This system can realize the synchronous acquisition of mechanical data and image data during the excavation of mole crickets. According to the excavation characteristics of the mole cricket, the structure of the mechanical test system was designed to realize the capturing of the digging force. Based on LabVIEW software, a host computer control interface of the software system was designed, which can realize the data acquisition, calibration and playback. A synchronous trigger module was designed to ensure the synchronism of high-speed image and digging force acquisition. The results show that proposed test system can synchronously obtain the kinematic and mechanical data of the excavation of mole crickets, and provide the equipment guarantee for further study.