Marine fixed point observation equipment operation state abnormity detection method and device

Abstract

The invention provides a marine fixed point observation equipment operation state abnormity detection method and device. The method comprises the steps: acquiring a first observation sequence collected by the marine fixed-point observation equipment in the normal operation state; training the preset first initial wavelet neural network prediction model set based on the first observation sequence so as to determine a first wavelet neural network prediction model including the first optimal structure with the minimum global error; constructing the prediction interval corresponding to the prediction value according to the synthetical uncertainty of the first wavelet neural network prediction model; processing the second observation sequence to be predicted by the first wavelet neural networkprediction model and outputting the prediction result according to the comparison result between the processing result and the prediction interval; and if the prediction interval is not exceeded, thepotential abnormity can be determined by cooperation of multiple observation sequences. Therefore, the disturbance caused by the non-equipment fault factors in the abnormity detection result can be removed and the false alarm rate can be reduced, and the operability of the fault detection method for the marine observation instrument can be greatly improved.

Description

technical field [0001] The present application relates to the technical field of ocean observation, and in particular, to a method and device for detecting abnormal operation status of ocean fixed-point observation equipment. Background technique [0002] Marine fixed-point observation equipment generally refers to a comprehensive observation platform fixed somewhere in the sea, which plays an important role in marine disaster prevention and mitigation, protection of marine rights and interests, and promotion of marine scientific research. Whether the equipment is normal or not directly affects the reliability of the operation of my country's operational marine observation system, and the complex and harsh marine environment and equipment aging make the failure of observation equipment inevitable. [0003] Based on this, related technologies provide a method for abnormal detection of equipment: after knowing the detailed composition and structure of the equipment, then clari...

AI Technical Summary

Problems solved by technology

This type of method does not need to express the mechanism of the system, and requires less complex and detailed information, but it cannot distinguish the potential anomalies caused by environmental factors outside the equipment. Therefore, after identifying the anomalies of the ocean observation sequence through this method, the It is necessary to manually further judge whether the identified abnormality is caused by equipment factors, which to a certain extent leads to a disconnect between the abnormality detection and equipment fault identification process, and the accuracy of abnormal factors depends entirely on the professional level and work experience of the on-site personnel in the support center

Images