CN107020917B - A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique - Google Patents
A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique Download PDFInfo
- Publication number
- CN107020917B CN107020917B CN201710242162.XA CN201710242162A CN107020917B CN 107020917 B CN107020917 B CN 107020917B CN 201710242162 A CN201710242162 A CN 201710242162A CN 107020917 B CN107020917 B CN 107020917B
- Authority
- CN
- China
- Prior art keywords
- defrosting
- frosting
- computer vision
- image
- low
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25B—REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS
- F25B47/00—Arrangements for preventing or removing deposits or corrosion, not provided for in another subclass
- F25B47/02—Defrosting cycles
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The pump type heat electric automobile air conditioner defrosting control system and method, the system that the invention discloses a kind of based on computer vision technique include low pressure heat transmitter, master controller, computer vision system；Low pressure sensor detection low voltage value simultaneously feeds back to master controller, and it is determined whether to enable computer vision systems according to low voltage value for master controller；The evaporator picture of shooting is passed to image storage system and stored by camera, image recognition analysis system carries out analysis identification to image, calculate the frosting rate of evaporator, when evaporimeter frosting rate reaches 50%, master controller issues defrosting instruction, and air-conditioning system enters defrosting logic, when frosting rate is reduced to 0%, defrosting instruction is exited in master controller sending, and air-conditioning system defrosting terminates, and exits defrosting.The present invention carries out intelligent decision to evaporimeter frosting degree using computer vision technique, overcomes defect existing for traditional Defrost method, can accurately judge the frosting situation of evaporator, makes correct defrosting movement.
Description
Technical Field
The invention relates to a heat pump type electric automobile air conditioner defrosting control method, in particular to a heat pump type electric automobile air conditioner defrosting control system and method based on a computer vision technology.
Background
The existing defrosting control method of the traditional heat pump air conditioner is roughly as the following table 1 shows:
TABLE 1
The traditional defrosting control methods have certain defects, the defrosting judgment is inaccurate, and false operations such as 'defrosting is not removed' or 'defrosting without frost' can be generated.
Disclosure of Invention
The invention aims to provide a heat pump type electric automobile air conditioner defrosting control system and method based on a computer vision technology, and aims to solve the problems of evaporator defrosting detection and defrosting control of a heat pump type electric automobile air conditioner in winter.
In order to achieve the purpose, the invention adopts the technical scheme that:
a heat pump type electric automobile air conditioner defrosting control system based on a computer vision technology comprises a low-pressure heat transmitter, a master controller and a computer vision system; wherein,
the low-voltage sensor is connected with the master controller and is used for monitoring the low voltage of the air conditioning system in real time;
the master controller is used for making judgment of entering and exiting defrosting control logic;
and the computer vision system is connected with the master controller and is used for judging the frosting degree of the evaporator.
The low-voltage sensor stores a low-voltage value in a low-voltage storage period and feeds the low-voltage value back to the master controller.
The master controller judges whether to start the computer vision system or not according to the low-pressure value fed back by the low-pressure sensor, photographs the evaporator, analyzes the frosting degree of the evaporator, judges whether to enter defrosting control or not according to the analysis result, and judges when to quit defrosting according to the image analysis result when defrosting occurs.
The computer vision system comprises an auxiliary light source, a camera, an image storage system and an image recognition analysis system; the auxiliary light source and the camera are both connected with a master controller, the image storage system is connected with the camera, and the image recognition analysis system is connected with the image storage system; the camera is used for photographing the evaporator, the image storage system is used for storing images, the image recognition analysis system is used for carrying out image recognition analysis, the frosting rate of the evaporator is calculated, and the result is fed back to the master controller.
A heat pump type electric automobile air conditioner defrosting control method based on a computer vision technology comprises the following steps:
step S1: the low-voltage sensor monitors the low-voltage value LP of the air-conditioning system in real time, and the low-voltage value LP of the air-conditioning system is stored every other low-voltage storage period;
step S2: determining whether the following logic is satisfied: in a plurality of continuous periods, the low voltage value LP is less than 2.93Bar, if the low voltage value LP is less than 2.93Bar, the auxiliary light source and the camera are started, and if the low voltage value LP is not less than 2 Bar, the auxiliary light source and the camera are not started, and the low voltage is continuously monitored;
step S3: the camera transmits the shot evaporator picture to an image storage system, and the picture is stored every other image storage period;
step S4: the image identification and analysis system analyzes the pictures transmitted by the image storage system, and identifies and analyzes the images in different periods through a mathematical model to obtain the frosting rate;
step S5: determining whether the following logic holds: the frosting rate is more than or equal to 50%, if the frosting rate is more than or equal to 50%, the master controller sends a defrosting instruction, and the air-conditioning system enters a defrosting control logic; if not, returning to step S1;
step S6: determining whether the following logic holds: and (4) setting the frosting rate to be 0%, if yes, giving an instruction of quitting the defrosting, finishing the defrosting, and if not, continuing the defrosting.
In step S4, the steps of performing recognition analysis on the images in different periods are:
s41: establishing a mathematical model
S411: through a large number of experiments, N groups of evaporator pictures under different frosting degrees are obtained, R, G, B values of the pictures are extracted, R, G, B is normalized to obtain chromaticity coordinates, and the calculation method comprises the following steps:
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)
extracting texture features of the image frosting area by adopting a gray level co-occurrence matrix method, wherein the texture features comprise energy, contrast, correlation and entropy;
s412: counting the parameter information values of the experimental sample plate: counting R, G, B the maximum and minimum value ranges of energy, contrast, correlation and entropy of the N groups of sample images;
s413: a discriminant function is established and calculated by
Wherein i is 1-8, X1, X2, X3, X4, X5, X6, X7 and X8 are respectively R, G, B, and Y1, Y2, Y3, Y4, Y5, Y6, Y7 and Y8 are coefficients according to the formulaCarrying out fitting on a statistical experiment sample to obtain;
s42: image processing
S421: dispersing the image, and obtaining R, G, B values of energy, contrast, correlation and entropy for each discrete region according to the formulaF is calculated, and if f is less than 0, frosting is judged;
and S422, counting the number n of the discrete areas meeting the frosting condition, wherein the frosting rate is n divided by the total number of the discrete areas.
Has the advantages that: the invention adopts the computer vision technology to intelligently judge the frosting degree of the evaporator, overcomes the defects of the traditional defrosting method, can accurately judge the frosting condition of the evaporator and make correct defrosting action. The invention adopts the computer vision technology to visually judge the frosting condition of the evaporator, can make up for the defects of the traditional defrosting method and has more accurate defrosting action. The computer vision technology is a mature detection technology, operates in various industrial and agricultural aspects, can be applied to heat pump defrosting, photographs evaporators with different frosting degrees through a large number of experiments, extracts effective information through an image analysis technology, establishes a mathematical model during frosting, compares a photographed picture during frosting of the evaporators with the mathematical model established by experimental data during actual application, and can obtain the frosting condition of the evaporators, so that key information such as frosting positions and frosting area of the evaporators can be clearly obtained, and the information cannot be obtained by adopting a traditional defrosting detection method. Compared with the traditional defrosting method, the method has the following advantages:
1. the judgment is accurate and cannot be influenced by air humidity, temperature and the like.
2. The obtained effective information is more. The frosting position and the frosting area of the evaporator can be accurately obtained, and effective information is provided for formulating correct entering/exiting defrosting logic.
3. The reliability is high. When the frosting mathematical model is established, the condition of dust accumulation can be considered, and the defrosting judgment is not influenced by the dust accumulation.
Drawings
FIG. 1 is a schematic diagram of a system of the present invention;
FIG. 2 is a flow chart of the method of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings.
As shown in FIG. 1, the heat pump type electric vehicle air conditioner defrosting control system based on the computer vision technology of the invention comprises a low-pressure heat transmitter 1, a master controller 2 and a computer vision system 7; wherein,
the low-voltage sensor 1 is connected with the master controller 2 and used for monitoring the low voltage of the air conditioning system in real time, storing a low-voltage value in a low-voltage storage period and feeding the low-voltage value back to the master controller 2.
The master controller 2 is used for making judgment of entering and exiting defrosting control logic; according to the low pressure value fed back by the low pressure sensor 1, whether a computer vision system is started or not is judged, the evaporator is photographed, the frosting degree of the evaporator is analyzed, whether defrosting control is started or not is judged according to the analysis result, and when defrosting occurs, whether defrosting is quitted is judged according to the image analysis result.
The computer vision system 7 is connected with the master controller 2 and is used for judging the frosting degree of the evaporator; the computer vision system 7 comprises an auxiliary light source 3, a camera 4, an image storage system 5 and an image recognition analysis system 6; the auxiliary light source 3 and the camera 4 are both connected with the master controller 2, the image storage system 5 is connected with the camera 4, and the image recognition analysis system 6 is connected with the image storage system 5; the camera 4 is used for photographing the evaporator, the image storage system 5 is used for storing images, the image recognition analysis system 6 is used for performing image recognition analysis, calculating the frosting rate of the evaporator, and feeding the result back to the master controller.
As shown in fig. 2, the heat pump type electric vehicle air conditioner defrosting control method based on the computer vision technology of the present invention includes the following steps:
step S1: the low-voltage sensor monitors the low-voltage value LP of the air-conditioning system in real time, and the low-voltage value LP of the air-conditioning system is stored every other low-voltage storage period; wherein the low-voltage storage period is 20 s;
step S2: determining whether the following logic is satisfied: in 5 continuous periods, the low voltage value LP is less than 2.93Bar, if the low voltage value LP is less than 2.93Bar, the auxiliary light source and the camera are started, and if the low voltage value LP is not less than 2 Bar, the auxiliary light source and the camera are not started, and the low voltage is continuously monitored;
step S3: the camera transmits the shot evaporator picture to an image storage system, and the picture is stored every other image storage period; wherein the image storage period is 1 min; in order to reduce the required memory, only the image in the latest 10 periods needs to be stored, namely when the image in the 1 st period is deleted in the 11 th period;
step S4: the image identification and analysis system analyzes the pictures transmitted by the image storage system, and identifies and analyzes the images in different periods through a mathematical model to obtain the frosting rate; the frosting rate is the frosting area divided by the evaporator area;
the method comprises the following specific steps:
s41: establishing a mathematical model
S411: through a large number of experiments, 100 groups of evaporator pictures under different frosting degrees are obtained, R, G, B values of the pictures are extracted, R, G, B is normalized to obtain chromaticity coordinates, and the calculation method comprises the following steps:
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)
extracting texture features of the image frosting area by adopting a gray level co-occurrence matrix method, wherein the texture features comprise energy, contrast, correlation and entropy;
s412: counting the parameter information values of the experimental sample plate: counting R, G, B, maximum and minimum value ranges of energy, contrast, correlation, entropy of the 100 sets of sample images;
s413: a discriminant function is established and calculated by
Wherein i is 1-8, X1, X2, X3, X4, X5, X6, X7 and X8 are respectively R, G, B, energy, contrast, correlation and entropy, Y1, Y2, Y3, Y4, Y5, Y6, Y7 and Y8 are coefficients, and the coefficients are obtained by fitting according to a statistical experiment sample;
s42: image processing
S421: dispersing the image, and obtaining R, G, B values of energy, contrast, correlation and entropy for each discrete region according to the formulaF is calculated, and if f is less than 0, frosting is judged;
and S422, counting the number n of the discrete areas meeting the frosting condition, wherein the frosting rate is n divided by the total number of the discrete areas.
Step S5: determining whether the following logic holds: the frosting rate is more than or equal to 50%, if the frosting rate is more than or equal to 50%, the master controller sends a defrosting instruction, and the air-conditioning system enters a defrosting control logic; if not, returning to step S1;
step S6: determining whether the following logic holds: and (4) setting the frosting rate to be 0%, if yes, giving an instruction of quitting the defrosting, finishing the defrosting, and if not, continuing the defrosting.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (5)
1. A heat pump type electric automobile air conditioner defrosting control method based on a computer vision technology is characterized by comprising the following steps: the method comprises the following steps:
step S1: the low-voltage sensor monitors the low-voltage value LP of the air-conditioning system in real time, and the low-voltage value LP of the air-conditioning system is stored every other low-voltage storage period;
step S2: determining whether the following logic is satisfied: in a plurality of continuous periods, the low voltage value LP is less than 2.93Bar, if the low voltage value LP is less than 2.93Bar, the auxiliary light source and the camera are started, and if the low voltage value LP is not less than 2 Bar, the auxiliary light source and the camera are not started, and the low voltage is continuously monitored;
step S3: the camera transmits the shot evaporator picture to an image storage system, and the picture is stored every other image storage period;
step S4: the image identification and analysis system analyzes the pictures transmitted by the image storage system, and identifies and analyzes the images in different periods through a mathematical model to obtain the frosting rate;
in step S4, the steps of performing recognition analysis on the images in different periods are:
s41: establishing a mathematical model
S411: acquiring N groups of evaporator pictures under different frosting degrees, extracting R, G, B values of the pictures, and normalizing R, G, B to obtain chromaticity coordinates, wherein the calculation method comprises the following steps:
r＝R/(R+G+B)
g＝G/(R+G+B)
b＝B/(R+G+B)
extracting texture features of the image frosting area by adopting a gray level co-occurrence matrix method, wherein the texture features comprise energy, contrast, correlation and entropy;
s412: counting the parameter information values of the experimental sample plate: counting R, G, B the maximum and minimum value ranges of energy, contrast, correlation and entropy of the N groups of sample images;
s413: a discriminant function is established and calculated by
Wherein i is 1-8, X1, X2, X3, X4, X5, X6, X7 and X8 are respectively R, G, B, energy, contrast, correlation and entropy, Y1, Y2, Y3, Y4, Y5, Y6, Y7 and Y8 are coefficients, and the coefficients are obtained by fitting according to a statistical experiment sample;
s42: image processing
S421: dispersing the image, and obtaining R, G, B values of energy, contrast, correlation and entropy for each discrete region according to the formulaF is calculated ifIf f is less than 0, judging that frosting occurs;
s422, counting the number n of the discrete areas meeting the frosting condition, wherein the frosting rate is n divided by the total number of the discrete areas;
step S5: determining whether the following logic holds: the frosting rate is more than or equal to 50%, if the frosting rate is more than or equal to 50%, the master controller sends a defrosting instruction, and the air-conditioning system enters a defrosting control logic; if not, returning to step S1;
step S6: determining whether the following logic holds: and (4) setting the frosting rate to be 0%, if yes, giving an instruction of quitting the defrosting, finishing the defrosting, and if not, continuing the defrosting.
2. A heat pump type electric vehicle air conditioner defrosting control method based on computer vision technology according to claim 1, characterized in that: in step S1, the low-voltage holding period is 20S.
3. A heat pump type electric vehicle air conditioner defrosting control method based on computer vision technology according to claim 1, characterized in that: in step S2, the number of the cycles is 5.
4. A heat pump type electric vehicle air conditioner defrosting control method based on computer vision technology according to claim 1, characterized in that: in step S3, the images in the last 10 cycles are saved.
5. A heat pump type electric vehicle air conditioner defrosting control method based on computer vision technology according to claim 1, characterized in that: in step S3, the image saving period is 1 min.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710242162.XA CN107020917B (en) | 2017-04-12 | 2017-04-12 | A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710242162.XA CN107020917B (en) | 2017-04-12 | 2017-04-12 | A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107020917A CN107020917A (en) | 2017-08-08 |
| CN107020917B true CN107020917B (en) | 2019-02-12 |
Family
ID=59526840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710242162.XA Active CN107020917B (en) | 2017-04-12 | 2017-04-12 | A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107020917B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107576111A (en) * | 2017-09-14 | 2018-01-12 | 天津大学 | One kind is based on infrared thermal imaging detection air source heat pump defrosting method and control system |
| CN108426345A (en) * | 2018-04-04 | 2018-08-21 | 陕西建工安装集团有限公司 | A kind of multi-connected machine outdoor unit defrosting control system and method |
| CN113743428A (en) * | 2020-05-27 | 2021-12-03 | 广东芬尼克兹节能设备有限公司 | Method and device for performing accurate defrosting control by combining camera |
| CN111707030A (en) * | 2020-06-05 | 2020-09-25 | 广东纽恩泰新能源科技发展有限公司 | Heat pump control system and method based on visual defrosting |
| CN111811202A (en) * | 2020-07-17 | 2020-10-23 | 山东神舟制冷设备有限公司 | Defrosting control method, device and equipment and computer storage medium |
| CN117387298A (en) * | 2022-07-04 | 2024-01-12 | 雪链物联网技术服务有限公司 | An intelligent visual defrost controller for air-cooled evaporator defrost in cold storage |
| CN116587806A (en) * | 2023-06-16 | 2023-08-15 | 上汽通用汽车有限公司 | Evaporator frosting early warning method, device and system and storage medium |
| CN118952938B (en) * | 2024-08-02 | 2025-09-23 | 东风汽车有限公司东风日产乘用车公司 | Automobile defrosting control method, device, storage medium and air conditioning heat pump system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110064309A (en) * | 2009-12-07 | 2011-06-15 | 엘지이노텍 주식회사 | Defroster of refrigerator |
| CN202947395U (en) * | 2012-12-04 | 2013-05-22 | 王秀利 | Defrosting device and heat control equipment |
| CN104813119A (en) * | 2012-07-31 | 2015-07-29 | 开利公司 | Frozen evaporator coil detection and defrost initiation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110044014A (en) * | 2009-10-22 | 2011-04-28 | 엘지이노텍 주식회사 | Defrosting system of the refrigerator and its method |
-
2017
- 2017-04-12 CN CN201710242162.XA patent/CN107020917B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110064309A (en) * | 2009-12-07 | 2011-06-15 | 엘지이노텍 주식회사 | Defroster of refrigerator |
| CN104813119A (en) * | 2012-07-31 | 2015-07-29 | 开利公司 | Frozen evaporator coil detection and defrost initiation |
| CN202947395U (en) * | 2012-12-04 | 2013-05-22 | 王秀利 | Defrosting device and heat control equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107020917A (en) | 2017-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107020917B (en) | A kind of pump type heat electric automobile air conditioner defrosting control system and method based on computer vision technique | |
| EP3904777B1 (en) | Air-conditioner system and method for operating the same | |
| CN103471213B (en) | Air conditioner and control method for air conditioner | |
| CN107091548A (en) | A kind of air source heat pump defrosting control system and method | |
| CN103528162B (en) | Air conditioner | |
| CN112665116B (en) | Multi-online defrosting method and device, multi-online air conditioning system and readable storage medium | |
| CN115435457B (en) | Air conditioner control method, system and server based on edge calculation | |
| CN107368014A (en) | Machine room monitoring system and method | |
| CN109636835B (en) | Foreground object detection method based on template optical flow | |
| CN104266312A (en) | Air conditioner and control method and system thereof | |
| CN113158730A (en) | Multi-person on-duty identification method and device based on human shape identification, electronic device and storage medium | |
| JP2016040519A (en) | Air conditioner | |
| CN108960169A (en) | Instrument and equipment state on_line monitoring method and system based on computer vision | |
| CN117928051B (en) | Energy-saving carbon reduction control system of central air conditioner | |
| CN118553067A (en) | Behavior supervision method for intelligent station | |
| CN111156655A (en) | Air conditioner main control board fault self-detection method and air conditioner | |
| CN110673720A (en) | Eye protection display method and learning machine with eye protection mode | |
| CN116866515A (en) | Intelligent park AI monitoring system | |
| CN112079430A (en) | Method for effectively controlling growth of microorganisms in water system | |
| CN119399196B (en) | Intelligent weaving defect image recognition and automatic classification method and system | |
| CN118283232B (en) | Video monitoring method and monitoring system based on smart building | |
| CN119580190A (en) | Air conditioning defrosting method based on AI image processing | |
| JP2009109114A (en) | Air conditioner | |
| CN119915840A (en) | Two-step circuit board plug-in defect anomaly detection method and system | |
| CN120507148A (en) | Multi-parameter-based machine room equipment state monitoring method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |