CN106908452A - Engine lubricating oil quality monitoring device based on machine vision - Google Patents

Engine lubricating oil quality monitoring device based on machine vision Download PDF

Info

Publication number
CN106908452A
CN106908452A CN201710272713.7A CN201710272713A CN106908452A CN 106908452 A CN106908452 A CN 106908452A CN 201710272713 A CN201710272713 A CN 201710272713A CN 106908452 A CN106908452 A CN 106908452A
Authority
CN
China
Prior art keywords
lubricating oil
early warning
processing unit
image
unit
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710272713.7A
Other languages
Chinese (zh)
Inventor
董明望
杨帆
闫君懿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University of Technology WUT
Original Assignee
Wuhan University of Technology WUT
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan University of Technology WUT filed Critical Wuhan University of Technology WUT
Priority to CN201710272713.7A priority Critical patent/CN106908452A/en
Publication of CN106908452A publication Critical patent/CN106908452A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Lubrication Details And Ventilation Of Internal Combustion Engines (AREA)

Abstract

The invention discloses a kind of engine lubricating oil quality monitoring device based on machine vision, including lighting unit, image acquisition units, graphics processing unit, early warning unit, early warning unit includes lamp driving circuit and early warning lamp, the signal output part of image acquisition units is connected with the signal input part of graphics processing unit, the signal output part of graphics processing unit is connected with the signal input part of lamp driving circuit, and the signal output part of lamp driving circuit is connected with early warning lamp.The present invention is monitored based on computer vision to engine lubricating oil, and by detecting that the conventional apparatus that the physicochemical properties of lubricating oil are detected to quality of lubrication oil are contrasted, has the advantages that the simple and convenient, accuracy of implementation is high, sensitivity is high.

Description

Engine lubricating oil quality monitoring device based on machine vision
Technical field
The present invention relates to engine lubricating oil detection means field, more specifically to a kind of based on machine vision Engine lubricating oil quality monitoring device.
Background technology
Engine lubricating oil has the four big major functions such as lubrication, sealing, cleaning, cooling, and the quality of lubricating oil is straight Connect the fault rate of the job stability and engine system that are related to engine.Lubricating oil is within the engine with the duration of runs Accumulation, is aoxidized due to lubricating oil, fuel-steam moisture is invaded, the wearer of parts etc., ultimately results in profit by high temperature Lubricating oil is influenceed and is polluted by them.So need often irregularly more oil change be ensure engine work must Want condition.The quality to engine lubricating oil detect mainly thering is two kinds at present:It is online and offline.Off-line technology mainly passes through Collection engine lubricating oil sample, its performance and state are analyzed by certain instrument and equipment, and these Instrument measuring precisions are high, but It is bulky, it is more long the time required to being not suitable for on-the-spot test, and detection.On-line monitoring method is mainly by electrical conductivity to hair Motivation quality of lubrication oil is monitored, and in carrying out detection method to engine lubricating oil by electrical conductivity, sensor tube wall is to electricity The propagation of magnetic wave has certain interference, and this causes that measurement result is inaccurate.
Machine vision is one and is related to the new branch of science of numerous areas, covers psychophysics, computer science, artificial intelligence The contents such as energy, Neurobiology, image procossing and pattern-recognition.It utilizes the anthropomorphic visual performance of computer mould, from objective thing Useful information is extracted in the image of thing, is acted upon and is understood, be eventually used for engineering survey and control.Make in engine lubricating oil During, when the chemical composition of oil changes or mixes mixture, can be along with the change of color.The present invention is based on The engine lubricating oil quality detection device of machine vision monitors quality of lubrication oil by observing the change of lube color, essence Exactness is high, sensitivity is strong.
The content of the invention
The technical problem to be solved in the present invention is, there is provided a kind of engine lubricating oil quality-monitoring based on machine vision Device.
The technical solution adopted for the present invention to solve the technical problems is:A kind of engine profit based on machine vision of construction Lubricating oil quality monitoring device, including lighting unit, image acquisition units, graphics processing unit, early warning unit, the early warning Tip element includes lamp driving circuit and early warning lamp, at the signal output part and described image of described image collecting unit The signal input part connection of unit is managed, the signal output part of described image processing unit is defeated with the signal of the lamp driving circuit Enter end connection, the signal output part of the lamp driving circuit is connected with the early warning lamp;Described image collecting unit is used In the collection lubricating oil original state image under the irradiation of lighting unit;Described image processing unit is used to set up lubricating oil to be measured With original state lubricating oil image pair, image is extracted to the characteristic vector based on hsv color space, calculate image to characteristic vector Correlation coefficient value, judge whether lubricating oil changes according to correlation coefficient value;The early warning unit is used in picture Control and startup lamp driving circuit, light early warning lamp automatically when processing unit judges that lubricating oil changes.
In such scheme, the lighting unit is LED, is arranged on the position that can be illuminated lubricating oil.
In such scheme, described image collecting unit be high temperature resistant ccd video camera and the corresponding camera lens of video camera, if Putting can shoot the position of lubricating oil.
In such scheme, described image processing unit is arm processor.
Implement engine lubricating oil quality monitoring device of the present invention based on machine vision, have the advantages that:
1st, the present invention is monitored based on computer vision to engine lubricating oil, can effectively monitor the matter of lubricating oil Amount, prevents the quality of lubrication oil engine failure for causing not up to standard, has ensured the stationarity of engine work;
2nd, the present invention gathers engine lubricating oil image by high temperature resistant ccd video camera, is extracted according to graphics processing unit Color of image characteristic vector, is carried out lubricating oil characteristics of image with original state lubricating oil characteristics of image using coefficient correlation algorithm Matching, draws the similarity degree of color of image, according to the similarity degree of color of image, judges whether the quality of lubricating oil meets mark It is accurate.
3rd, the present invention is monitored based on computer vision to engine lubricating oil, with the physical chemistry by detecting lubricating oil The contrast of conventional apparatus that property is detected to quality of lubrication oil, it is excellent with implementing that simple and convenient, accuracy is high, sensitivity is high etc. Point.
Brief description of the drawings
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing:
Fig. 1 is the structural representation of engine lubricating oil quality monitoring device of the present invention based on machine vision;
Fig. 2 is schematic flow sheet of the graphics processing unit to picture processing in the present invention.
Specific embodiment
In order to be more clearly understood to technical characteristic of the invention, purpose and effect, now compare accompanying drawing and describe in detail Specific embodiment of the invention.
As shown in figure 1, the present invention provides a kind of engine lubricating oil quality monitoring device based on machine vision, including shine Bright unit, image acquisition units, graphics processing unit, early warning unit.Early warning unit include lamp driving circuit and Early warning lamp, the signal output part of image acquisition units is connected with the signal input part of graphics processing unit, image procossing list The signal output part of unit is connected with the signal input part of lamp driving circuit, and signal output part and the early warning of lamp driving circuit are carried Show that lamp is connected.Preferably, lighting unit is the aid of image acquisition units, and it uses LED, and being arranged on can be by lubricating oil The position illuminated, it is therefore an objective to obtain high-quality view data.
Image acquisition units are high temperature resistant ccd video camera and the corresponding camera lens of video camera, and being arranged on can shoot lubricating oil Position.The present invention gathers lubricating oil image by high temperature resistant ccd video camera, and image is conveyed into graphics processing unit.
Graphics processing unit is arm processor, and it is used to set up lubricating oil to be measured and original state lubricating oil image pair, carries Image is taken to the characteristic vector based on hsv color space, correlation coefficient value of the image to characteristic vector is calculated, according to coefficient correlation Value judges whether lubricating oil changes.
Early warning unit is used for control and startup light fixture when picture processing unit judges lubricating oil changes and drives Circuit, lights early warning lamp automatically.
The course of work of the invention is as follows:
Image acquisition units gather lubricating oil original state image under the irradiation of lighting unit, and image is transmitted at image Reason unit.Graphics processing unit storage gathers lubricating oil original state image.
In monitoring process, image acquisition units obtain lubrication under the irradiation of lighting unit by high temperature resistant ccd video camera Oily image, graphics processing unit is transmitted by image.
Graphics processing unit obtains the RGB color information of image, and is transformed into hsv color space.Hsv color is empty Between chromatic component H distribution axles be divided into 8 spaces, be 3 spaces saturation degree S point, luminance component V points is 3 spaces.According to It is G=9H+3S that tri- components of H, S, V determine that color characteristic quantifies to integrate in color-aware on the significance level of visual signature influence +V.So tri- components of H, S, V are distributed on a n dimensional vector n and, and the span of G is 0~71.Statistics obtains the HSV of image Color Statistical histogram, in histogram,
In above formula, i is that color characteristic quantifies to concentrate element, niIt is that color feature value is the number of pixels of i, N is pixel Sum.After being counted to G, image obtains 72 one-dimensional characteristic vectors of color component, and this feature vector is image Characteristic vector.
As shown in Fig. 2 graphics processing unit sets up lubricating oil to be measured and original state lubricating oil image pair, image pair is extracted Characteristic vector based on hsv color space and after being normalized, using coefficient correlation algorithm by lubricating oil characteristics of image to be measured Matched with original state lubricating oil characteristics of image, drawn two kinds of correlation coefficient value of color feature vector.Two image normalizings Characteristic vector after change is respectively A and B, then the coefficient correlation between A and B is:
Extracting many parts needs replacing lubricating oil sample to be tested with original state lubricating oil sample, it is determined that needing to change profit Lubricating oil is based on the coefficient correlation ω of the characteristic vector in hsv color space with original state lubricating oil.In the lubricating oil course of work, When its color characteristic reaches ω values to the coefficient correlation with original state color feature vector, system judges that quality of lubrication oil is not inconsistent Standardization.
When picture processing unit judges quality of lubrication oil is not inconsistent standardization, control early warning unit starting light fixture drives Circuit, early warning lamp is lighted automatically.
Embodiments of the invention are described above in conjunction with accompanying drawing, but the invention is not limited in above-mentioned specific Implementation method, above-mentioned specific embodiment is only schematical, rather than restricted, one of ordinary skill in the art Under enlightenment of the invention, in the case of present inventive concept and scope of the claimed protection is not departed from, can also make a lot Form, these are belonged within protection of the invention.

Claims (4)

1. a kind of engine lubricating oil quality monitoring device based on machine vision, including lighting unit, image acquisition units, figure As processing unit, early warning unit, it is characterised by,
The early warning unit includes lamp driving circuit and early warning lamp, the signal output part of described image collecting unit Signal input part with described image processing unit is connected, and the signal output part of described image processing unit drives with the light fixture The signal input part connection of circuit, the signal output part of the lamp driving circuit is connected with the early warning lamp;
Described image collecting unit is used to gather lubricating oil original state image under the irradiation of lighting unit;
Described image processing unit is used to set up lubricating oil to be measured and original state lubricating oil image pair, extracts image to being based on The characteristic vector in hsv color space, calculates image to the coefficient correlation of characteristic vector, judges that lubricating oil is according to correlation coefficient value It is no to change;
The early warning unit is used for control and startup light fixture when picture processing unit judges lubricating oil changes and drives Circuit, lights early warning lamp automatically.
2. the engine lubricating oil quality monitoring device based on machine vision according to claim 1, it is characterised in that institute It is LED to state lighting unit, is arranged on the position that can be illuminated lubricating oil.
3. the engine lubricating oil quality monitoring device based on machine vision according to claim 1, it is characterised in that institute Image acquisition units are stated for high temperature resistant ccd video camera and the corresponding camera lens of video camera, the position that can shoot lubricating oil is arranged on.
4. the engine lubricating oil quality monitoring device based on machine vision according to claim 1, it is characterised in that institute Graphics processing unit is stated for arm processor.
CN201710272713.7A 2017-04-24 2017-04-24 Engine lubricating oil quality monitoring device based on machine vision Pending CN106908452A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710272713.7A CN106908452A (en) 2017-04-24 2017-04-24 Engine lubricating oil quality monitoring device based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710272713.7A CN106908452A (en) 2017-04-24 2017-04-24 Engine lubricating oil quality monitoring device based on machine vision

Publications (1)

Publication Number Publication Date
CN106908452A true CN106908452A (en) 2017-06-30

Family

ID=59210281

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710272713.7A Pending CN106908452A (en) 2017-04-24 2017-04-24 Engine lubricating oil quality monitoring device based on machine vision

Country Status (1)

Country Link
CN (1) CN106908452A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108680579A (en) * 2018-03-30 2018-10-19 武汉理工大学 Crane hydraulic oil on-line monitor for pollution based on machine vision and method
CN111373258A (en) * 2017-12-05 2020-07-03 国际商业机器公司 Discriminating fluids based on determining and analyzing digital image color space characteristics
CN113614513A (en) * 2019-03-29 2021-11-05 出光兴产株式会社 Lubricating oil degradation determination system and lubricating oil degradation determination method
CN115115621A (en) * 2022-08-24 2022-09-27 聊城市泓润能源科技有限公司 Lubricating oil pollution degree detection method based on image processing

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0571295A1 (en) * 1992-05-21 1993-11-24 A.D.D.S. Concept Device for evaluating a lubricant, especially of a car engine
CN101196510A (en) * 2007-12-25 2008-06-11 深圳市亚泰光电技术有限公司 Method and device for detecting pollution degree of lubricating oil
CN101539528A (en) * 2009-04-22 2009-09-23 西安交通大学 Method for detecting lubricating oil water content by utilizing image sensor
CN102360431A (en) * 2011-10-08 2012-02-22 大连海事大学 Method for automatically describing image
CN202522512U (en) * 2011-12-24 2012-11-07 国家粮食储备局成都粮食储藏科学研究所 Device for automatically detecting color and luster as well as transparency of grease
CN103744976A (en) * 2014-01-13 2014-04-23 北京工业大学 Secure image retrieval method based on homomorphic encryption
CN104303042A (en) * 2012-05-17 2015-01-21 纳博特斯克有限公司 Decelerator damage state notification device, mechanical system with decelerator damage state notification function, and medium on which decelerator damage state notification program is recorded
CN106127756A (en) * 2016-06-21 2016-11-16 西安工程大学 A kind of insulator recognition detection method based on multicharacteristic information integration technology

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0571295A1 (en) * 1992-05-21 1993-11-24 A.D.D.S. Concept Device for evaluating a lubricant, especially of a car engine
CN101196510A (en) * 2007-12-25 2008-06-11 深圳市亚泰光电技术有限公司 Method and device for detecting pollution degree of lubricating oil
CN101539528A (en) * 2009-04-22 2009-09-23 西安交通大学 Method for detecting lubricating oil water content by utilizing image sensor
CN102360431A (en) * 2011-10-08 2012-02-22 大连海事大学 Method for automatically describing image
CN202522512U (en) * 2011-12-24 2012-11-07 国家粮食储备局成都粮食储藏科学研究所 Device for automatically detecting color and luster as well as transparency of grease
CN104303042A (en) * 2012-05-17 2015-01-21 纳博特斯克有限公司 Decelerator damage state notification device, mechanical system with decelerator damage state notification function, and medium on which decelerator damage state notification program is recorded
CN103744976A (en) * 2014-01-13 2014-04-23 北京工业大学 Secure image retrieval method based on homomorphic encryption
CN106127756A (en) * 2016-06-21 2016-11-16 西安工程大学 A kind of insulator recognition detection method based on multicharacteristic information integration technology

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111373258A (en) * 2017-12-05 2020-07-03 国际商业机器公司 Discriminating fluids based on determining and analyzing digital image color space characteristics
CN108680579A (en) * 2018-03-30 2018-10-19 武汉理工大学 Crane hydraulic oil on-line monitor for pollution based on machine vision and method
CN113614513A (en) * 2019-03-29 2021-11-05 出光兴产株式会社 Lubricating oil degradation determination system and lubricating oil degradation determination method
CN115115621A (en) * 2022-08-24 2022-09-27 聊城市泓润能源科技有限公司 Lubricating oil pollution degree detection method based on image processing
CN115115621B (en) * 2022-08-24 2022-11-11 聊城市泓润能源科技有限公司 Lubricating oil pollution degree detection method based on image processing

Similar Documents

Publication Publication Date Title
CN106908452A (en) Engine lubricating oil quality monitoring device based on machine vision
CN111242123B (en) Power equipment fault diagnosis method based on infrared image
EP1742016B1 (en) Apparatus and method for inspecting screw portions
EP2980557B1 (en) System and method for oil monitoring
US20200049603A1 (en) Intelligent Rolling Contact Fatigue Testing System and Testing Method Therefor
CN104198324A (en) Computer vision-based method for measuring proportion of cut leaves in cut tobacco
CN104198325A (en) Method for measuring ratio of cut stem to cut tobacco based on computer vision
CN104034733A (en) Service life prediction method based on binocular vision monitoring and surface crack image recognition
CN102175692A (en) System and method for detecting defects of fabric gray cloth quickly
CN104634592A (en) Train running gear fault diagnosis method and train running gear fault diagnosis device
CN107966449A (en) A kind of oil cleanliness detector and its detection method
CN201828932U (en) Appearance quality detecting device of capacitor
CN108195847A (en) A kind of relief pattern Online Video detection device and its detection method
CN208334373U (en) Marine diesel lubricating oil moisture prior-warning device
CN102589415A (en) Metering type digital image plane equal thickness interferometer and method for measuring flatness of object surface by employing the same
CN109272484A (en) A kind of rainfall detection method based on video image
CN108180871A (en) A kind of method of quantitative assessment surface of composite insulator dusting roughness
CN105424708B (en) Plate glass insurance fiber tube fusable links mass defect detection method
CN104515472A (en) Portable nondestructive detection method and device of pork dyad backfat thickness
CN112489017A (en) Intelligent identification method and system for power equipment faults
CN115656202B (en) Multiband optical detection device for surface state of insulator
CN115077722B (en) Partial discharge and temperature comprehensive monitoring system and method applied to high-voltage cabinet
JP2001022433A (en) Monitoring device and monitoring method
CN204630546U (en) A kind of automatic measure on line visualization detection system of wind power equipment securing member
CN109975686B (en) Circuit board short circuit automatic identification method based on infrared image processing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170630