Marine diesel engine porous spray image classification method based on compression and excitation network
A technology of marine diesel engine and classification method, which is applied in the field of image processing, can solve problems such as difficulty in classification of multiple conical spray shadows, achieve the effects of solving multiple variable interference, improving processing efficiency, and improving accuracy
Pending Publication Date: 2022-04-08
CSSC MARINE POWER
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The invention provides a method for classifying images of porous sprays of marine diesel engines based on compression and excitation networks to solve the problem of difficult classification caused by multiple cone-shaped spray shadows of porous sprays in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.
[0027] Such as figure 2 As shown, the embodiment of the present invention provides a method for classifying porous spray images of marine diesel engines based on compression and excitation networks, including the following steps:
[0028] Step 1: Use a high-speed camera or related equipment to collect relevant continuous pictures as a training set;
[0029...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a marine diesel engine porous spray image classification method based on a compression and excitation network, and the method comprises the following steps: 1, collecting continuous images of porous spray, and taking the continuous images as a training set; 2, preprocessing the training set; step 3, constructing an SE model module, wherein the SE model module sequentially comprises a Squeeze process, an Excitation process and a Reweight process; 4, training an SE model module by using the preprocessed training set obtained in the step 2; 5, classifying the preprocessed porous spraying real-time images by using the SE model module, collecting a training set of new class images when the new class images appear, updating the SE model module by incrementally adjusting the SE model module, and classifying the porous spraying real-time images by using the updated SE model module; and when the new category of images do not appear, classifying the real-time images of the porous spray. According to the method, the accuracy of the spray image is improved, the problem of interference of various variables is solved, and the processing efficiency is improved.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method for classifying porous spray images of marine diesel engines based on compression and excitation networks. Background technique [0002] Four-stroke diesel engine is currently the most widely used power device in ship power, but the use of fuel oil has caused large-scale energy consumption and environmental pollution problems. By adjusting the amount and timing of fuel spray reasonably, the combustion efficiency of the diesel engine can be improved and the internal energy loss can be reduced. It is of great significance for energy saving and emission reduction. [0003] Today's mainstream marine diesel engines use porous spray, so it is of great significance to analyze the porous spray characteristics of marine diesel engines. To analyze the characteristics of porous spray, the spray image needs to be classified first. Different from the traditional single-ho...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06V10/764G06V10/774G06K9/62
Inventor 阎宇杰张帝贾炜段后东李慧
Owner CSSC MARINE POWER