Ocean current machine blade attachment recognition method based on VGG16-SegUnet and dropout

Abstract

The invention belongs to the field of ocean current machine fault diagnosis, and particularly relates to an ocean current machine blade attachment recognition method based on VGG16-SegUnet and dropout. The method includes the following steps that an ocean current machine image is semantically annotated, and an original data set is created; the original data set is rotationally enhanced, and standardization preprocessing is carried out; the VGG16-SegUnet network is built; the network is trained through an Adadelta optimizer; the trained network is tested, the positions and the sizes of ocean current machine blade attachments are recognized, and meanwhile the uncertainty of the recognition result is estimated; and finally the accurate attachment area ratio and the average combination ratio are calculated. The problems that by means of an existing ocean current machine blade attachment diagnosis method based on image signals, the attachments cannot be positioned, the accurate attachment ratio cannot be output, and the recognition uncertainty cannot be estimated are solved, and instructive suggestions are provided for ocean current machine blade condition maintenance and following fault-tolerant control.

Description

technical field [0001] The invention relates to the field of fault diagnosis of sea current machines, in particular to a method for identifying attachments of sea current machine blades based on VGG16-SegUnet and dropout. Background technique [0002] Ocean current energy is a renewable and clean energy known as "blue oil field" and "Saudi Arabia on the Sea". Regular sea water flow. Compared with wind energy and solar energy, ocean current energy has the advantages of predictability and high energy density. As a kind of ocean current power generation device, the sea current machine has the advantages of low noise, reliable operation and no strict site selection requirements. Its power generation principle is: absorb the energy of flowing sea water through rotating machinery, convert it into electrical energy and transmit it to the grid Realize grid-connected power generation. Different from wind turbines installed on land, once the sea current machine is officially put in...

AI Technical Summary

Problems solved by technology

Different from wind turbines installed on land, once the sea current machine is officially put into operation, it will be placed underwater for a long time, which will cause the following potential problems: (1) Small marine organisms are likely to be attached to the blades of the sea current machine in the form of attachments. The surface is propagated, which may cause blade imbalance; (2) The blades of sea current machine are generally made of metal, so the long-term seawater immersion will rust the blades, thus affecting the mechanical performance

However, in the face of the complex underwater environment, simply analyzing the stator current and voltage signals is not enough to complete the accurate diagnosis of the degree of attachment

In addition, the existing methods for diagnosing attachments on sea current machine blades based on image signals have the following problems: (1) The position and size of attachments are not identified; (2) The accurate area ratio of attachments is not diagnosed; (3) ) cannot identify different attachment distributions, and lacks an analysis of the uncertainty of diagnostic results

Images