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 o...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.展开更多
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 ...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.展开更多
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 vari...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.展开更多
文摘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.
文摘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.
基金supported by the National Science and Technology Infrastructure Work Projects(2015FY210500)Key Research Program of Frontier Sciences,Chinese Academy of Sciences(QYZDY-SSW-DQC028)+5 种基金Strategic Priority Program of Chinese Academy of Sciences(XDB41000000)the National Natural Science Foundation of China(42102280,41972322,and 11941001)the Natural Science Foundation of Shandong Province(ZR2021QD016)the China Postdoctoral Science Foundation(2020M682164)the State Scholarship Fund(201706220310)。
基金This work was supported by the Fundamental Research Funds for the Central Universities of China(Grant No.N180304021)the National Science Foundation for Postdoctoral Scientists of China(Grant No.2019M651125)the National Natural Science Foundation of China(Grant No.U1708257)。
文摘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.