To solve the extremely harsh working environment in mines, optical fibers are prone to deformation due to foreign objects (such as falling coal blocks and mechanical equipment) after long-distance installation, resulting in abnormal light wave transmission and ineffective high-temperature alarm signals that interfere with normal coal mine safety production.
This paper proposes a segmented filtering model of temperature measurement band based on a nonlinear polynomial regression algorithm.
Experimental analysis proves that the effectiveness of this model in filtering abnormal temperature data is more than 90%. Compared with the common radial basis function neural network model, this model has the characteristics of simple implementation and high reliability, it has more advantages in solving the problem of error alarms caused by abnormal force on the fiber optic temperature measurement instrument.
This research topic is novel and highly original.
