Method and device for identifying abnormal operation reasons of conveying pipeline

Abstract

The embodiment of the invention provides a conveying pipeline operation abnormity reason identification method and device. The method comprises the following steps: acquiring operation data of different positions of a conveying pipeline; clustering the operation data at different positions to obtain a preset number of operation data with different abnormal fluctuation types; labels are established for the preset number of operation data with different abnormal fluctuation types according to the corresponding relation between the abnormal fluctuation types and the abnormal reasons; the label is an abnormal reason corresponding to an abnormal fluctuation type occurring in the operation data; taking the operation data with the label as a training sample, and calculating a classification condition of the operation data in the training sample; and according to the classification condition, identifying the abnormal reason of the to-be-identified operation data, thereby improving the accuracy of identifying the abnormal reason of the operation of the conveying pipeline.

Description

technical field [0001] The embodiments of this specification relate to the technical field of petroleum transportation, and in particular to a method and device for identifying causes of abnormal operation of a transportation pipeline. Background technique [0002] With the development of oil and gas industry, pipeline transportation has become another important means of transportation after railway, highway, waterway and air transportation. Pipeline network transportation occupies an increasingly important position in the transportation of oil, natural gas and other fluids. Pipelines are used as carriers for the transmission of oil and other liquids, and are laid in various environments such as land and sea around the world; pipeline transportation is more convenient, but it is prone to damage during pipeline transportation, and oil pipelines will be damaged after long-term use If the oil pipeline leaks, it will not only cause major economic losses and environmental pollut...

AI Technical Summary

Problems solved by technology

[0004] However, the data collected by the indirect method generally has data uncertainties, such as measurement noise, transmission noise, sampling error, and there are observation blind spots, which make it impossible to intuitively detect the data of each point along the pipeline, which makes the measured data and standard theoretical analysis results often have large deviations

[0005] In the prior art, the direct method needs to judge the abnormality of the pipeline based on human experience, which is prone to misjudgment or inaccurate situations

The data collected by the indirect method is uncertain, and it takes a long time to process a large amount of data, and the real-time online detection capability for faults is limited

Images