CN110793722B - Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning - Google Patents
Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning Download PDFInfo
- Publication number
- CN110793722B CN110793722B CN201911087221.6A CN201911087221A CN110793722B CN 110793722 B CN110793722 B CN 110793722B CN 201911087221 A CN201911087221 A CN 201911087221A CN 110793722 B CN110793722 B CN 110793722B
- Authority
- CN
- China
- Prior art keywords
- liquid leakage
- image
- lead
- leakage
- temperature
- 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
- 239000002253 acid Substances 0.000 title claims abstract description 39
- 238000003860 storage Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000010801 machine learning Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 title abstract description 16
- 239000007788 liquid Substances 0.000 claims abstract description 28
- 238000012417 linear regression Methods 0.000 claims abstract description 18
- 238000007477 logistic regression Methods 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 6
- 238000012884 algebraic function Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 5
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/002—Investigating fluid-tightness of structures by using thermal means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Abstract
The invention discloses a non-contact type leakage detection device and method for a lead-acid storage battery based on machine learning, and belongs to the field of battery detection. The device comprises a rack, and an image processor arranged on the rack is connected with an infrared camera, a longitudinal rotating motor and a transverse rotating motor and controls the operation of the infrared camera, the longitudinal rotating motor and the transverse rotating motor. The method comprises the following steps: 1) the infrared camera on the rack adjusts the angle and aims at the lead-acid storage battery; 2) controlling an infrared camera to acquire a plurality of images through an image processor; 3) denoising the image obtained in the step 2); 4) identifying a liquid leakage area in the image in the step 3); 5) marking the leakage area in the step 4). The invention adopts a non-contact method to detect leakage, and has high detection speed, stability and high efficiency; the method adopts the logistic regression and linear regression algorithm of machine learning to judge the leakage state and identify the leakage area, and the identification rate is high; the invention has the advantages of low cost, simple installation and construction and wide application range.
Description
Technical Field
The invention relates to the field of battery detection, in particular to a non-contact type leakage detection method for a lead-acid storage battery based on machine learning.
Background
With the development of society and the advancement of technology, reserve power supplies become an important part in daily life and production, which can be classified into button cells, dry cells, lithium cells, lead-acid storage batteries, etc. according to their electric capacities from small to large, button cells are commonly used in small electronic mechanical devices, such as electronic watches, dry cells are commonly used in small old electronic devices, such as radios, electronic toys, etc., lithium cells are commonly used in small mobile electronic devices, such as mobile phones, notebook computers, etc., and lead-acid storage batteries are commonly used in small mobile electric devices and large non-mobile devices, such as backup power supplies of electric vehicles, automobiles, production centers, etc. Among them, lead-acid batteries are the most widely used and are currently irreplaceable in many production fields.
The most common fault of the lead-acid storage battery is battery leakage, and the battery leakage can cause short circuit of a circuit, so that fire or even explosion is caused. Therefore, the detection of the leakage of the battery is a very necessary safety guarantee.
The method comprises the following steps that firstly, whether the leakage condition exists or not is judged by observing whether the shell of the lead-acid storage battery is broken or not and whether the terminal and the safety valve of the battery are corroded or not; secondly, through the specific electronic equipment contact lead acid battery position that easily takes place the weeping, if take place the weeping, electrolyte can be adsorbed by electronic equipment, and the circuit is closed to reach the detection mesh. The first method cannot automatically detect leakage, the second method can only be used for quality detection in the production process of the battery, and the problem of non-contact leakage detection of the lead-acid storage battery as a standby power supply in the production process cannot be solved. In foreign countries, the leakage situation is researched by detecting the temperature distribution characteristics of the surface of the battery through an infrared image and the color distribution characteristics through a visible light image, but the leakage situation is still in a theoretical research stage, the principle is complex, the requirements on scenes are strict, and the engineering realizability is poor.
The method can automatically detect the leakage condition of the lead-acid storage battery by a non-contact method, has a wide application range, detects the leakage area at the first time when the battery leaks, marks the leakage area in an image, and has the advantages of high detection speed, stability, high efficiency and high recognition rate.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a technical scheme of a non-contact type leakage detection method of a lead-acid storage battery based on machine learning, solves the problem that the leakage of the lead-acid storage battery cannot be detected automatically in a non-contact manner when the lead-acid storage battery is used as a standby power supply to participate in industrial production, realizes the non-contact type leakage detection of the lead-acid storage battery, and has the advantages of wide application scene and simple installation.
In order to achieve the purpose, the invention adopts the following technical scheme:
the utility model provides a lead acid battery non-contact weeping detection device based on machine learning, includes frame, image processor and infrared camera set up in the frame, and the frame below is equipped with vertical rotating electrical machines and horizontal rotating electrical machines, image processor connects infrared camera, vertical rotating electrical machines and horizontal rotating electrical machines.
Furthermore, the infrared camera is rotated through the longitudinal rotating motor and the transverse rotating motor to be aligned to the lead-acid storage battery.
Further, the image processor controls the infrared camera, after the infrared image of the lead-acid storage battery is collected, the infrared camera transmits infrared image data to the image processor, and the image processor processes the data to finally obtain the infrared image marked by the liquid leakage area.
A non-contact type leakage detection method for a lead-acid storage battery based on machine learning comprises the following steps:
step 1) an infrared camera on a rack aligns to a lead-acid storage battery by rotating a longitudinal rotating motor and a transverse rotating motor, adjusts the focal length and the magnification of the infrared camera, and controls the focal point and the magnification of an image;
step 2) controlling an infrared camera to collect a plurality of images through an image processor, wherein the images comprise areas which are easy to leak, such as a positive terminal, a safety valve and a negative terminal of a lead-acid storage battery;
step 3) denoising the image obtained in the step 2), and removing particle noise and a small-area isolated region in the infrared image by using a median filtering algorithm;
step 4) identifying a leakage area in the image in the step 3), performing logistic regression on the temperature characteristic vectors and the leakage states of the multiple leaked and non-leaked infrared images to obtain a logistic regression function, performing linear regression on the highest temperature, the lowest temperature and the leakage area temperature of the multiple leaked infrared images to obtain a linear regression function, and calculating the leakage state and the leakage area temperature of a new image according to the logistic regression function and the linear regression function;
and 5) marking the leakage area in the step 4), finding out the infrared image with leakage according to the leakage state calculated in the step 4), carrying out binarization and canny edge detection on the infrared image according to the temperature of the leakage area to obtain the edge of the leakage area, and marking the edge of the leakage area to be green.
Further, in the step 1), the focal length and the magnification of the infrared camera only need to be adjusted once at the beginning.
Further, in the step 3), the denoising effect of the median filtering algorithm is realized by adjusting the size of a convolution kernel of the median filtering.
Further, in the step 4), the parameters of the logistic regression function and the linear regression function only need to be calculated once by using a plurality of images.
Further, in the step 5), the binarized threshold value is a ratio of a difference value between the temperature of the liquid leakage area and the lowest temperature and the maximum temperature difference, and the threshold value of the edge detection is 0.2.
The invention has the following beneficial effects: the invention adopts a non-contact method to detect leakage, and has high detection speed, stability and high efficiency; the method adopts the logistic regression and linear regression algorithm of machine learning to judge the leakage state and identify the leakage area, and the identification rate is high; the invention has the advantages of low cost, simple installation and construction and wide application range.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a flow chart of the detection method of the present invention;
in the figure: the device comprises a rack 1, a lead-acid storage battery 2, an image processor 3, an infrared camera 4, a longitudinal rotating motor 5, a transverse rotating motor 6, a positive terminal 7, a safety valve 8 and a negative terminal 9.
Detailed Description
The following description will further explain the embodiments of the present invention with reference to the drawings.
As shown in figure 1, the non-contact type leakage detection device of the lead-acid storage battery based on machine learning comprises a frame 1, wherein an image processor 3, an infrared camera 4, a longitudinal rotating motor 5 and a transverse rotating motor 6 are installed on the frame 1, the infrared camera 4 and the image processor 3 are fixedly installed at the top end of the frame, the infrared camera 4 is arranged in front of the image processor 3, the longitudinal rotating motor 5 is arranged below the bottom plates of the infrared camera 4 and the image processor 3, the transverse rotating motor 6 is arranged below the longitudinal rotating motor 5, the image processor 3 is connected with the infrared camera 4, the longitudinal rotating motor 5 and the transverse rotating motor 6, the angle of the infrared camera 4 is adjusted by controlling the longitudinal rotating motor 5 and the transverse rotating motor 6, the infrared camera 4 is controlled to shoot an infrared image of the lead-acid storage battery 2, and infrared image data are returned to the image processor 3, the image processor 3 processes the data, thereby realizing non-contact automatic leakage detection.
As shown in fig. 2, the non-contact leakage detection method for the lead-acid storage battery based on machine learning includes the following steps:
1) an image processor 3 on the frame 1 controls a longitudinal rotating motor 5 and a transverse rotating motor 6 to adjust the angle of the infrared camera 4, align the lead-acid storage battery 2, adjust the focal length and the magnification of the infrared camera 4 and control the focal point and the magnification of the image;
2) the image processor 3 controls the infrared camera 4 to collect a plurality of images, wherein the images comprise regions which are easy to leak, such as a positive terminal 7, a safety valve 8, a negative terminal 9 and the like of the lead-acid storage battery 2;
3) denoising the image obtained in the step 2), and removing particle noise and a small-area isolated region in the infrared image by using a median filtering algorithm;
4) identifying a leakage area in the image in the step 3), performing logistic regression on temperature characteristic vectors and leakage states of a plurality of leaked and non-leaked infrared images to obtain a logistic regression function, performing linear regression on the highest temperature, the lowest temperature and the leakage area temperature of a plurality of leaked infrared images to obtain a linear regression function, and calculating the leakage state and the leakage area temperature of a new image according to the logistic regression function and the linear regression function;
5) marking the position of the leakage area in the step 4), finding out the infrared image with leakage according to the leakage state calculated in the step 4), carrying out binarization and canny edge detection on the infrared image according to the temperature of the leakage area to obtain the edge of the leakage area, and marking the edge of the leakage area to be green. The image processor 3 controls the infrared camera 4, after the infrared image of the lead-acid storage battery 2 is collected, the infrared camera 4 transmits infrared image data to the image processor 3, the image processor 3 carries out the processing of the step 3), the step 4) and the step 5) on the data, and finally the infrared image marked by the leakage area is obtained.
In the step 1), the angle of the infrared camera 4 is adjusted to align the lead-acid storage battery 2, the image processor 3 controls the infrared camera 4 to adjust the focal length, so that the image returned from the infrared camera 4 to the image processor 3 is in the clearest state, and the relative positions of the lead-acid storage battery 2 and the infrared camera 4 are fixed, so that the focal length of the infrared camera 4 is not changed any more only by adjusting once at the beginning, and the multiplying power of the infrared camera 4 is adjusted to enable the visual field to include the regions which are easy to leak liquid, such as the positive terminal 7, the safety valve 8, the negative terminal 9 and the like of the lead-acid storage battery;
in the step 2), the image processor 3 controls the infrared camera 4 to collect the infrared image under the current view field to obtain an infrared image with 388 x 288 pixels, the view field is the outer surface of the wiring end face of the lead-acid storage battery 2, and after the collection is finished, the infrared camera 4 returns the infrared data to the image processor 3;
in the step 3), small particle noise and a small-area isolated region smaller than 1 square centimeter can appear in the infrared image due to the influence of electromagnetic noise, thermal noise and the like, the small particle noise and the small-area isolated region can be removed by using a median filtering method, and the size of the removed particles and the isolated region can be controlled by adjusting the size of a convolution kernel of the median filtering;
in step 4), the highest temperature and the lowest temperature of 1000 leaked liquid and non-leaked liquid infrared images are used as the input of logistic regression, the leaked liquid state is used as the output, the logistic regression is carried out on the data by using a sigmoid function, 0.4 is selected as a probability threshold value with leaked liquid, the logistic regression function with the highest prediction accuracy is obtained, the highest temperature and the lowest temperature in a plurality of leaked liquid infrared images are used as the input of linear regression, the temperature of a leaked liquid area is used as the output of the linear regression, the accumulated deviation of a predicted value and an actual value is calculated by using an algebraic function, and the minimum value of the algebraic function is calculated by using a gradient descent method, finding the optimal parameter to obtain a linear regression function with the best fitting effect, calculating the leakage state of a new image by using the logistic regression function judged by the leakage state, detecting whether leakage exists, and if so, further calculating the temperature of the leakage area by using the linear regression function for calculating the temperature of the leakage area;
in the step 5), according to the calculation result of the step 4), binarization and canny edge detection are carried out on the infrared image with the leakage according to the temperature of the leakage area, the threshold value of binarization is the ratio of the difference value between the temperature of the leakage area and the lowest temperature to the maximum temperature difference, the threshold value of edge detection is 0.2, the edge of the leakage area is obtained, the infrared image is converted into HSV space from RGB space, the pixel value of the edge of the leakage area is set to be 0.3 in an H channel of the HSV space and is marked to be green, the marked HSV image is converted into an RGB image, and finally the infrared image marked by the leakage area is obtained.
Claims (3)
1. A non-contact type leakage detection method for a lead-acid storage battery based on machine learning comprises the following steps:
step 1), an infrared camera (4) on a rack is aligned to a lead-acid storage battery (2) by rotating a longitudinal rotating motor (5) and a transverse rotating motor (6), the focal length and the magnification of the infrared camera (4) are adjusted, and the focus and the magnification of an image are controlled;
step 2), controlling an infrared camera (4) to collect a plurality of images through an image processor (3), wherein the images comprise areas which are easy to leak and comprise a positive terminal (7), a safety valve (8) and a negative terminal (9) of the lead-acid storage battery (2);
step 3) denoising the image obtained in the step 2): removing particle noise and small-area isolated regions in the infrared image by using a median filtering algorithm;
step 4) identifying a liquid leakage area in the image in the step 3): taking the highest temperature and the lowest temperature of a plurality of infrared images with liquid leakage and without liquid leakage as the input of logistic regression, taking the liquid leakage state as the output, carrying out logistic regression on data by using a sigmoid function, selecting 0.4 as a probability threshold value with liquid leakage to obtain a logistic regression function with the highest prediction accuracy, taking the highest temperature and the lowest temperature of the plurality of infrared images with liquid leakage as the input of linear regression, taking the temperature of a liquid leakage area as the output of the linear regression, calculating the accumulated deviation of a predicted value and an actual value by using an algebraic function, solving the minimum value of the algebraic function by using a gradient descent method to find the optimal parameter to obtain the linear regression function, calculating the liquid leakage state of a new image by using the logistic regression function judged by the liquid leakage state, detecting whether liquid leakage exists, and further calculating the temperature of the liquid leakage area by using the linear regression function for calculating the temperature of the liquid leakage area if the liquid leakage state exists;
step 5) marking the leakage area in the step 4): finding out an infrared image with leaked liquid according to the liquid leakage state calculated in the step 4), carrying out binarization and canny edge detection on the infrared image according to the temperature of the liquid leakage area to obtain the edge of the liquid leakage area, and marking the edge to be green;
in the step 1), the focal length and the multiplying power of the infrared camera (4) only need to be adjusted once at the beginning;
in the step 5), the binary threshold is the ratio of the difference value between the temperature of the liquid leakage area and the lowest temperature to the maximum temperature difference, and the threshold of the edge detection is 0.2.
2. The machine learning-based lead-acid battery non-contact leakage detection method according to claim 1, characterized in that: in the step 3), the denoising effect of the median filtering algorithm is realized by adjusting the size of a convolution kernel of the median filtering.
3. The machine learning-based lead-acid battery non-contact leakage detection method according to claim 1, characterized in that: in the step 4), the parameters of the logistic regression function and the linear regression function only need to be calculated once by using a plurality of images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911087221.6A CN110793722B (en) | 2019-11-08 | 2019-11-08 | Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911087221.6A CN110793722B (en) | 2019-11-08 | 2019-11-08 | Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110793722A CN110793722A (en) | 2020-02-14 |
| CN110793722B true CN110793722B (en) | 2021-11-30 |
Family
ID=69443502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911087221.6A Active CN110793722B (en) | 2019-11-08 | 2019-11-08 | Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110793722B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445462A (en) * | 2020-03-30 | 2020-07-24 | 国家计算机网络与信息安全管理中心 | Storage battery leakage detection method based on neural network and thermography |
| CN112164051A (en) * | 2020-09-29 | 2021-01-01 | 中国船舶重工集团公司第七二四研究所 | Radar antenna area array liquid leakage detection device and method based on image analysis |
| CN112614115B (en) * | 2020-12-28 | 2024-03-26 | 中国第一汽车股份有限公司 | Power battery water seepage monitoring method |
| CN112666219A (en) * | 2020-12-29 | 2021-04-16 | 厦门理工学院 | Blade detection method, device and equipment based on infrared thermal imaging |
| CN112686860A (en) * | 2020-12-29 | 2021-04-20 | 厦门理工学院 | Blade detection method, device and equipment based on infrared thermal imaging |
| CN117033063B (en) * | 2023-10-08 | 2024-02-09 | 浪潮(山东)计算机科技有限公司 | Server liquid leakage processing method, system, device, electronic equipment and medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11076113B2 (en) * | 2013-09-26 | 2021-07-27 | Rosemount Inc. | Industrial process diagnostics using infrared thermal sensing |
| CA2847707C (en) * | 2014-03-28 | 2021-03-30 | Intelliview Technologies Inc. | Leak detection |
| WO2018122589A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for detecting degree of development of asphalt pavement fracture based on infrared thermal image analysis |
| CN206472232U (en) * | 2017-02-21 | 2017-09-05 | 西安沃弘达电子科技有限公司 | A kind of device based on video detecting technology for detection leakage speed |
| US10386260B2 (en) * | 2017-03-07 | 2019-08-20 | Accenture Global Solutions Limited | Leak detection for fluid distribution networks using hyperspectral imaging |
| CN108520517A (en) * | 2018-04-10 | 2018-09-11 | 四川超影科技有限公司 | Method for detecting leakage based on machine vision |
-
2019
- 2019-11-08 CN CN201911087221.6A patent/CN110793722B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110793722A (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110793722B (en) | Non-contact type leakage detection device and method for lead-acid storage battery based on machine learning | |
| CN109613000B (en) | Lithium battery coating defect detection method, system, equipment and storage medium | |
| CN104537650A (en) | Polarity direction judging method and device for aluminum electrolytic capacitor | |
| CN111445462A (en) | Storage battery leakage detection method based on neural network and thermography | |
| CN102818998B (en) | Method for detecting analyzed lithium of lithium ion power battery | |
| CN108333188A (en) | A kind of online apparent visual detection device of battery pole piece | |
| CN116523921B (en) | Detection method, device and system for tab turnover condition | |
| CN115829921B (en) | Method, apparatus and computer readable storage medium for detecting cell defects | |
| CN106099158A (en) | The method of waste and old electric automobile power battery echelon utilization and compact power thereof | |
| WO2023193213A1 (en) | Method and apparatus for detecting defect of insulating coating of battery electrode plate, and computer device | |
| CN106004137A (en) | Method for controlling silk-screen printing quality and production process based on EL detection | |
| CN115656197A (en) | Optical detection device, detection method and device, electronic device and storage medium | |
| CN114549393B (en) | Image labeling method, device, equipment and computer storage medium | |
| CN203606301U (en) | Visual hardware for defect detection of power lithium ion battery pole piece | |
| CN210924614U (en) | Battery cell positive and negative electrode identification equipment based on machine vision | |
| CN113654493A (en) | Quality detection method and system for laminated soft package lithium battery | |
| CN114871140B (en) | Electrode double-sided detection device, detection method and electrode comprehensive detection equipment | |
| CN115541491A (en) | Shell corrosion detection method and system of battery and shell corrosion detection device | |
| CN111833309B (en) | Photovoltaic cell detection method and device | |
| CN109655463A (en) | Image-pickup method, system, equipment and the storage medium of lithium battery pole piece coating | |
| CN115639211A (en) | Automatic high-speed detection equipment for battery cover plate | |
| CN115797254A (en) | Pole piece defect detection method and device, computer equipment and storage medium | |
| KR102426275B1 (en) | Image classification method and apparatus for solar cell | |
| CN104779675A (en) | Mobile terminal current control method and device thereof | |
| CN113240658A (en) | Battery charging system and method based on machine vision |
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 |