欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
讨论了仿射不变矩的原理，通过改进仿射不变矩的积分因子，保证了积分因子在仿射变换下的不变性，将仿射不变矩应用于水电机组轴心轨迹特征的提取．通过计算轴心轨迹的仿射不变矩作为特征向量，结合人工神经网络方法，提出了一种高效的轴心轨迹自动识别新方法．对3类典型的轴心轨迹的自动识别进行了仿真试验，并与Hu氏不变矩方法的识别效果进行对比．试验结果表明：采用仿射不变矩方法的轴心轨迹识别率达到95％，明显高于Hu氏不变矩的识别率，仿射不变矩具有比Hu氏不变矩更好的轴心轨迹识别能力．
英文摘要：
The affine moment invariants （AMIs） were discussed. By modifying the integral factor, the affine invariance of the integral factor for the curves was kept. AMIs were used to the feature extraction of shaft orbit based on the modification. A new method based on AMIs combined with Artificial Neural Network is presented to recognize the shaft orbits of hydropower generating sets. A simulation experiment of automatic identification for three typical axis orbits is provided. The experimental resuits reveal that the ratio of recognition by AMIs, which achieves 95 %, is much superior to that of Hu moment invariants （HMIs）. The performance of the proposed method is better than that of HMIs.
同期刊论文项目
同项目期刊论文
Using fuzzy theory and information entropy for water quality assessment in Three Gorges region, Chin
Design of PID parameters self-tuning fuzzy control system and its application in hydroelectric syste
Research on spot power market equilibrium model considering the electric power network characteristi
Adaptive Hybrid Differential Evolution Algorithm for Dynamic Economic Dispatch with Valve-Point Effe
位置：