Indicator diagram fault diagnosis method based on generative adversarial neural network

Abstract

The invention discloses an indicator diagram fault diagnosis method based on a generative adversarial neural network, and belongs to the technical field of oil extraction fault diagnosis, and the method comprises the following steps: carrying out the data cleaning of indicator diagram sample library data; based on an oil production engineering theory and typical indicator diagram characteristics, performing feature extraction on indicator diagram data points; adopting a generative adversarial neural network to generate a small number of fault category samples, and performing conditional constraint on the output of a generator network in the generation process; dividing the data into a training set, a verification set and a test set based on the original sample and the generated sample; an Xgboost classification algorithm is adopted to classify the samples; comprehensively evaluating a fault diagnosis result by utilizing the accuracy rate and the recall rate; and performing real-time monitoring and diagnosis on the fault by using the trained classification model, and judging the fault type in real time. The method can significantly improve the specific recognition capability of the classification model for the fault sample, and reduces the false alarm / missing report rate of the fault.

Description

technical field [0001] The invention belongs to the technical field of oil production fault diagnosis, and in particular relates to a method for diagnosing faults of dynamometer diagrams based on a generative confrontational neural network. Background technique [0002] The fault analysis of rod pump oil production usually relies on the indicator diagram as the judgment basis. The traditional diagnosis method is that technicians establish typical dynamometer diagrams under different faults based on oil production engineering knowledge, and judge the current oil well fault by comparing the actual dynamometer diagram with the typical dynamometer diagram. [0003] In recent years, based on the development of artificial intelligence technology and the accumulation of a large amount of on-site data, relevant scholars have begun to apply machine learning and deep learning technology to the diagnosis of dynamometer diagrams to realize automatic diagnosis. The reporting / missing rat...

AI Technical Summary

Problems solved by technology

[0003] In recent years, based on the development of artificial intelligence technology and the accumulation of a large amount of on-site data, relevant scholars have begun to apply machine learning and deep learning technology to the diagnosis of dynamometer diagrams to realize automatic diagnosis. The reporting / missing rate is still high

Images