基于多源信号与混合注意力的伺服阀故障诊断
|
|
杨晨,严建文,李磊,李贵闪
|
Fault diagnosis of servo valve based on multi-source signal and hybrid attention
|
|
Chen YANG,Jianwen YAN,Lei LI,Guishan LI
|
|
| 表 6 不同噪声强度下的模型诊断准确率及标准差 |
| Tab.6 Model diagnostic accuracy and standard deviation under different noise intensity |
|
| 模型 | 高斯噪声 | | 复合噪声 | | SNR = −8 dB | SNR = −4 dB | SNR = −2 dB | SNR = 2 dB | SNR = 4 dB | SNR = 8 dB | | λ = 0.5 | λ = 1 | λ = 2 | | A | 94.60(±1.41) | 97.95(±1.20) | 98.90(±0.70) | 99.91(±0.12) | 98.10(±2.48) | 98.10(±2.48) | | 96.87(±6.84) | 94.49(±4.47) | 93.94(±7.11) | | A1 | 85.13(±1.63) | 92.36(±2.20) | 95.36(±2.80) | 97.31(±1.77) | 95.20(±3.56) | 86.47(±16.37) | | 93.88(±6.35) | 89.22(±12.98) | 93.94(±7.11) | | A2 | 90.90(±1.54) | 90.00(±2.92) | 84.72(±13.87) | 88.63(±11.16) | 90.06(±9.02) | 74.03(±15.35) | | 89.82(±8.04) | 82.05(±21.49) | 86.90(±10.93) | | A3 | 83.33(±1.58) | 89.66(±3.98) | 84.72(±13.87) | 88.63(±11.16) | 90.06(±9.02) | 74.03(±15.35) | | 86.80(±14.54) | 81.92(±12.71) | 85.23(±12.34) | | A4 | 63.78(±1.63) | 68.72(±9.41) | 71.88(±12.78) | 69.89(±15.94) | 71.64(±14.56) | 74.65(±11.77) | | 74.34(±16.39) | 63.68(±17.95) | 84.59(±12.22) |
|
|
|