基于多模型融合的分布式光电仪器突变状态智能检测方法模型

Intelligent Detection Model for Catastrophe State of Distributed Photoelectric Instruments Based on Multimodel Fusion

为光电设备正常运行提供有效保障,设计基于多模型融合的分布式光电仪器突变状态智能检测方法模型。采用分布式光电仪器实时运行参数数据作为输入,分别构建KPCA、偏最小二乘算法和Elman神经网络的光电仪器突变状态检测模型,它们分别检测分布式光电仪器突变状态,将它们的输出结果作为输入,利用PSO-RBF神经网络模型对多模型分布式光电仪器检测结果进行融合处理,得到最终分布式光电仪器突变状态智能检测结果。实验结果表明:该模型采集分布式光电仪器电压运行数据较为准确,可有效检测分布式光电仪器突变状态,且其检测结果的决定系数数值较高,具备较为显著的应用效果。

To provide effective guarantee for the normal operation of photoelectric devices,a distributed intelligent detection method model for abrupt changes in photoelectric instruments based on multiple model fusion is designed.Using real-time operating parameter data of distributed photoelectric instruments as input,we construct photoelectric instrument mutation state detection models based on KPCA,partial least squares algorithm,and Elman neural network.They detect distributed photoelectric instrument mutation states respectively,and use their output results as input.We use PSO-RBF neural network models to fuse the detection results of multi-model distributed photoelectric instruments,finally,intelligent detection results of sudden changes in distributed photoelectric instruments are obtained.The experimental results show that the model is more accurate in collecting voltage operation data of distributed photoelectric instruments,and can effectively detect sudden changes in the state of distributed photoelectric instruments.Moreover,the determination coefficient value of the detection results is high,with relatively significant application effects.