Method for measuring content of water in oil product based on deep learning and measuring instrument
A deep learning and water content technology, applied in measurement devices, scientific instruments, instruments, etc., can solve problems such as deterioration of low temperature flow performance, oil supply interruption, short circuit, etc., and has strong ability to achieve nonlinear problems, problem solving efficiency, Good transfer characteristics
Inactive Publication Date: 2018-12-11
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] (1) Light fuel oil contains water, which will increase the freezing point and deteriorate the low-temperature fluidity. If aviation fuel flies at high altitude, ice will block the oil pipeline and interrupt the fuel supply.
[0004] (2) If the lubricating oil contains water, it will freeze into ice particles in winter, which will block the oil pipeline and filter screen. After some parts of the engine freeze, it will also increase the wear of the parts
[0005] (3) If there is water in the electrical oil, its dielectric properties will be reduced due to the existence of water, which will cause a short circuit or even burn the equipment if it is serious.
However, these two methods are not ideal in terms of applicable occasions and nonlinear fitting accuracy.
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 1
[0044] Embodiment one: a kind of method for measuring the water content of the oil product to be tested comprises the following steps:
[0045] Put the oil to be tested in a container.
[0046] The sensing light source emits light waves, passes through the sensing optical fiber, and irradiates the oil to be tested through the optical fiber probe.
[0047] The middle molecules or particles in the oil to be tested have an infrared absorption effect on the light wave, and the infrared absorbed light is reflected and returned to the optical fiber sensitive structure through the optical fiber probe;
[0048] The infrared absorption light is incident on the infrared spectrum acquisition module, and converted into electrical signals after being split.
[0049] The obtained electrical signal contains information about the intensity of infrared light absorption, and is analyzed by the deep learning model in the signal processing module to obtain the concentration of oil in the two-pha...
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 provides a method for measuring the content of water in an oil product based on deep learning and measuring instrument, and the measuring instrument comprises a sensing light source module, an optical fiber sensing structure and a signal processing module. The sensing light source module outputs infrared broad spectrum rays of a certain power; an optical fiber probe in the optical fiber sensing structure transmits the rays in the sensing light source module to an oil product to be tested on the one hand, thereby generating infrared absorption, and on the other hand collects and transmits absorbed rays into the signal processing module; the signal processing module obtains a infrared spectrum characteristic curve through an infrared spectrum acquisition module, and analyzes the infrared spectrum characteristic curve through an artificial intelligence analysis algorithm based on deep learning to obtain a content of water of the oil product to be tested.
Description
technical field [0001] The invention relates to a method for measuring water content of oil products based on infrared spectrum detection combined with deep learning artificial intelligence analysis and a water content measuring instrument, belonging to the technical field of sensors and detection. Background technique [0002] Water in oil directly affects the production, transportation, storage and use of oil. Generally speaking, water in oil products has the following hazards: [0003] (1) Light fuel oil contains water, which will increase the freezing point and deteriorate the low-temperature fluidity. If aviation fuel is flying at high altitude, ice will block the oil pipeline and interrupt the fuel supply. [0004] (2) If the lubricating oil contains water, it will freeze into ice particles in winter, which will block the oil pipeline and filter screen, and will increase the wear and tear of parts after some parts of the engine freeze. [0005] (3) If there is water ...
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): G01N21/3577
CPCG01N21/3577
Inventor 代志勇王毅
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA