Interactive Transformer for Small Object Detection

The detection of large-scale objects has achieved high accuracy,but due to the low peak signal to noise ratio(PSNR),fewer distinguishing features,and ease of being occluded by the surroundings,the detection of small objects,however,does not enjoy similar success.Endeavor to solve the problem,this paper proposes an attention mechanism based on cross-Key values.Based on the traditional transformer,this paper first improves the feature processing with the convolution module,effectively maintaining the local semantic context in the middle layer,and significantly reducing the number of parameters of the model.Then,to enhance the effectiveness of the attention mask,two Key values are calculated simultaneously along Query and Value by using the method of dual-branch parallel processing,which is used to strengthen the attention acquisition mode and improve the coupling of key information.Finally,focusing on the feature maps of different channels,the multi-head attention mechanism is applied to the channel attention mask to improve the feature utilization effect of the middle layer.By comparing three small object datasets,the plug-and-play interactive transformer(IT-transformer)module designed by us effectively improves the detection results of the baseline.

Artificial Monitoring of Eccentric Synchronous Reluctance Motors Using Neural Networks

This paper proposes an artificial neural network for monitoring and detecting the eccentric error of synchronous reluctance motors.Firstly,a 15 kWsynchronous reluctance motor is introduced and took as a case study to investigate the effects of eccentric rotor.Then,the equivalent magnetic circuits of the studied motor are analyzed and developed,in cases of dynamic eccentric rotor and static eccentric rotor condition,respectively.After that,the analytical equations of the studied motor are derived,in terms of its air-gap flux density,electromagnetic torque,and electromagnetic force,followed by the electromagnetic finite element analyses.Then,the modal analyses of the stator and the whole motor are performed,respectively,to explore the natural frequency and the modal shape of the motor,by which the further vibrational analysis is possible to be conducted.The vibration level of the housing is furtherly studied to investigate its relationship with the rotor eccentricity,which is validated by the prototype test.Furthermore,an artificial neural network,which has 3 layers,is proposed.By taking the air-gap flux density,the electromagnetic force,and the vibrational level as inputs,and taking the eccentric distance as output,the proposed neural network is trained till the error smaller than 5%.Therefore,this neural network is obtaining the input parameters of the tested motor,based on which it is automatically monitoring and reporting the eccentric error to the upper-level control center.

1:250万月球岩石类型图

人类对月表物质成分的科学认识始于20世纪60~70年代.大量的无人和载人月球探测获得了珍贵的历史数据.利用这些数据资料,美国地质勘探局编制了最早的一批月球地质图,但由于当时缺乏全面的月表物质成分探测数据,早期的月表地质单元划分多以形貌特征为依据而缺少成分约束. 20世纪90年代以来,新一轮的月球探测任务获取了全月球表面的物质成分探测数据,为开展月表物质成分编图提供了第一手资料.通过对月表物质成分分布信息的研究,本研究建立了月球内动力地质作用形成的岩石类型分类体系.基于GIS平台编制完成的1:250万月球岩石类型分布图及建立的月球物质成分数据库,为开展月球数字地质图编研和月球地质综合研究以及未来其他天体的编图工作奠定了基础.

Influence factors on natural frequencies of composite materials

Compared with traditional materials, composite materials have lower specific gravity, larger specific strength, larger specific modulus, and better designability structure and structural performance. However, the variability of structural properties hinders the control and prediction of the performance of composite materials. In this work, the Rayleigh–Ritz and orthogonal polynomial methods were used to derive the dynamic equations of composite materials and obtain the natural frequency expressions on the basis of the constitutive model of laminated composite materials. The correctness of the analytical model was verified by modal hammering and frequency sweep tests. On the basis of the established theoretical model, the influencing factors, including layers, thickness, and fiber angles, on the natural frequencies of laminated composites were analyzed. Furthermore, the coupling effects of layers, fiber angle, and lay-up sequence on the natural frequencies of composites were studied. Research results indicated that the proposed method could accurately and effectively analyze the influence of single and multiple factors on the natural frequencies of composite materials. Hence, this work provides a theoretical basis for preparing composite materials with different natural frequencies and meeting the requirements of different working conditions.