CN114062934B - Rechargeable battery capacity detection method based on X-ray image processing - Google Patents
Rechargeable battery capacity detection method based on X-ray image processing Download PDFInfo
- Publication number
- CN114062934B CN114062934B CN202111375640.7A CN202111375640A CN114062934B CN 114062934 B CN114062934 B CN 114062934B CN 202111375640 A CN202111375640 A CN 202111375640A CN 114062934 B CN114062934 B CN 114062934B
- Authority
- CN
- China
- Prior art keywords
- ray
- cell
- auxiliary
- main
- ray image
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 68
- 238000012545 processing Methods 0.000 title claims description 10
- 239000000463 material Substances 0.000 claims abstract description 24
- 238000007689 inspection Methods 0.000 claims abstract description 23
- 238000010586 diagram Methods 0.000 claims description 107
- 238000003384 imaging method Methods 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 2
- 239000011162 core material Substances 0.000 claims 13
- 238000012856 packing Methods 0.000 abstract description 3
- 238000012790 confirmation Methods 0.000 abstract 1
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 229910052744 lithium Inorganic materials 0.000 description 3
- 229920000642 polymer Polymers 0.000 description 3
- 238000003672 processing method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- OJIJEKBXJYRIBZ-UHFFFAOYSA-N cadmium nickel Chemical compound [Ni].[Cd] OJIJEKBXJYRIBZ-UHFFFAOYSA-N 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G01V5/22—
Abstract
The invention discloses a machine vision-based rechargeable battery capacity detection method, which comprises the steps of analyzing the material and the energy density of a rechargeable battery by using an equivalent atomic number, detecting an X-ray image of the rechargeable battery by using a double-view security inspection machine in a correlation manner, calculating the volume of the rechargeable battery, and then calculating the actual capacity of the rechargeable battery according to the energy density and the volume of the rechargeable battery. The invention can quickly detect the capacity of the battery in the luggage or the packing box, thereby avoiding the trouble of taking the battery out for confirmation, accelerating the security inspection efficiency and reducing the generation of the personnel congestion problem.
Description
Technical Field
The invention belongs to the field of size detection, and particularly provides a rechargeable battery capacity detection method based on X-ray image processing.
Background
The civil aviation administration stipulates that rechargeable batteries with total capacity exceeding 20000 milliamperes are not allowed to take the airplane. However, in practical implementation, the conventional X-ray detection device lacks an effective means for detecting and determining whether or not a rechargeable battery exceeding the allowable carrying specification is present in the baggage. Therefore, the name plate of the rechargeable battery can be checked only by opening the box by a worker for judgment, and the luggage is checked again through the X-ray detection device, so that the safety inspection time is prolonged seriously, the safety inspection efficiency is reduced, and the inconvenience of customers is caused.
In addition, the above problems also exist in the logistics, rail transportation industries, and the like, and the difference is only in the capacity limit for the rechargeable battery. Therefore, there is a need for a method for automatically detecting the capacity of a rechargeable battery without adding auxiliary devices. The existing rechargeable batteries are of nickel-cadmium, nickel-hydrogen, lithium ions, lithium polymers and lead-acid, the equivalent atomic number difference among the materials is large, and the materials and the energy density of the rechargeable batteries can be rapidly distinguished through the equivalent atomic number, so that a foundation is provided for a technology for automatically detecting the capacity of the rechargeable batteries.
Disclosure of Invention
In order to solve the problems, the invention provides a method for detecting the capacity of a rechargeable battery based on X-ray image processing. The invention can rapidly detect the battery capacity in the luggage or the packing box by an image processing method, thereby avoiding the trouble of taking out and confirming the battery, and greatly accelerating the security inspection efficiency.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a rechargeable battery capacity detection method based on X-ray image processing comprises the following steps:
firstly, charging batteries made of various different battery cell materials pass through an X-ray detection device to generate equivalent atomic number diagrams corresponding to different battery cells; obtaining equivalent atomic sequence number value intervals of various cell materials according to the equivalent atomic sequence number diagram;
step two, establishing an equivalent atomic sequence numerical value interval database of various cell materials;
measuring to obtain various cell energy densities, and establishing a corresponding cell energy density database;
fourthly, a main X-ray imaging system and an auxiliary X-ray imaging system are installed on the X-ray detection device, and the ray sources of the main X-ray imaging system and the auxiliary X-ray imaging system are respectively positioned at the adjacent sides of the X-ray inspection channel; x rays formed by the light sources of the main X-ray imaging system and the auxiliary X-ray imaging system after passing through the collimator are in the same plane;
step five, detecting the rechargeable battery through an X-ray detection device based on an article detection model of deep learning, calculating to obtain an equivalent atomic sequence value of the battery cell according to an article detection frame, associating the battery cell image in the main X-ray imaging system with the battery cell image of the auxiliary X-ray imaging system, and then calculating to obtain the volume of the battery cell of the rechargeable battery;
step six, obtaining the material of the battery cell through an equivalent atomic sequence value interval database according to the equivalent atomic sequence value of the battery cell; then obtaining the energy density of the battery cell through a battery cell energy density database according to the material of the battery cell;
and step seven, obtaining the predicted capacity of the rechargeable battery through the product of the energy density of the battery cell and the volume of the battery cell.
In a further improvement, in the seventh step, the predicted capacity of the rechargeable battery is compared with each capacity specification of the rechargeable battery on the market, and the capacity of the rechargeable battery on the market closest to the predicted capacity of the rechargeable battery is selected as the capacity of the rechargeable battery.
In a further improvement, in the fifth step, the method for detecting the cell volume is as follows:
step 5.1, establishing an imaging coordinate system of the main X-ray imaging system and an imaging coordinate system of the auxiliary X-ray imaging system;
step 5.2, passing the standard component through an X-ray inspection channel at different inclination angles, different heights and different horizontal positions perpendicular to the moving direction of the conveyor belt, and obtaining a plurality of groups of images, wherein each group of images comprises a main X-ray image and an auxiliary X-ray image;
step 5.3, calculating the actual length represented by the unit pixel at the corresponding position of the standard part in the X direction and the y direction of the main X-ray image and the auxiliary X-ray image, namely the pixel scale corresponding to the pixel, according to the measured actual length, width and height of the standard part and the number of the pixels of the main X-ray image and the auxiliary X-ray image of the standard part in the X direction, the y direction and the X direction and the z direction of the auxiliary X-ray image; taking the pixel scale of each pixel and the image coordinate of the pixel as a group of data, and forming a data set by a plurality of groups of data; wherein, the X direction is the horizontal direction of the plane of the main X-ray image, namely the moving direction of the conveyor belt of the X-ray inspection channel, and the y direction is the direction which is vertical to the X direction in the plane of the main X-ray image; the z direction is the direction perpendicular to the X direction in the plane of the auxiliary X-ray diagram;
and 5.4, fitting the data set to respectively obtain pixel scale functions p in the x, y and z directionsx(v)、py(y，z)、pz(y，z)；
Step 5.5, inputting the coordinates of each pixel point in the main X-ray diagram and the auxiliary X-ray diagram of the battery cell into the trained pixel scale functions in the X, y and z directions, then accumulating the lengths of the pixel points in the X, y and z directions respectively to obtain the actual lengths of the battery cell in the X, y and z directions, and then performing fusion calculation on the actual lengths of the battery cell in the X, y and z directions to obtain the longest edge l of the battery cellpredictActual length of (c):
wherein lpredictIndicating the longest side of the cellActual length of (c)angleRepresenting angle correction parameters, related to the cell placement angle, chIndicating a height correction parameter, related to the height position of the cell in the auxiliary X-ray diagram,/xIndicating the length of the charge core in the x-direction, lyDenotes the length of the cell in the y-direction, ryIs represented byyIs related to the position of the cell in the main X-ray image, lzDenotes the length of the cell in the z-direction, rzIs represented byzThe correction parameter of (2) is related to the position of the cell in the auxiliary X-ray diagram;
step 5.6, obtaining the maximum inscribed rectangle and the minimum circumscribed rectangle for the cell imaging in the main X-ray image and the auxiliary X-ray image; calculating the included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle; wherein the included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the main X-ray image and the auxiliary X-ray image is alpha1The included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the auxiliary X-ray image is alpha2Length d of two sides of the maximum inscribed rectangle of the main X-ray image1、d2Divided by cos alpha respectively1To obtain a two-pixel length p1、p2(ii) a Length d of two sides of maximum inscribed rectangle of auxiliary X-ray image3、d4Divided by cos alpha, respectively2To obtain a two-pixel length p3、p4(ii) a To p1、p2、p3、p4Carrying out comprehensive value calculation on the two nearest pixel length data to obtain a length value, wherein the length value is p1、p2、p3、p4The other two data are respectively used as the length l, the width w and the height h of the pixel length of the battery cell;
the method for detecting the comprehensive value of the two closest pixel length data comprises the following steps: length data of the main X-ray image a + length data of the auxiliary X-ray image b;
wherein the pixel length l is the maximum value of the three values, the width w is the middle value of the three values, and the height h is the minimum value of the three values;
where the pixel length is l and l in step 5.5predictDividing to obtain a ratio r;
the actual lengths of the other two sides of the cell are:
the volume V of the cell: l ═ Vpredict*wpredict*hpredict。
In a further improvement, cangleHas a value interval of [0.85, 1]]，chHas a value interval of [0.9, 1]]，ryHas a value interval of [0.4, 0.8 ]]，rzHas a value interval of [0.75, 1%](ii) a The value range of a is [0, 1]]And the value interval of b is [0, 1]]And a + b is 1.
In a further improvement, in the fifth step, the cell image in the main X-ray imaging system is used as a main X-ray image, and the cell image in the auxiliary X-ray imaging system is used as an auxiliary X-ray image; the method for associating the main X-ray image with the auxiliary X-ray image comprises the following steps:
5.1, whether the electric cores of the main X-ray diagram and the auxiliary X-ray diagram are the same material is judged through equivalent atomic number information, if so, the electric core images in the main X-ray diagram and the auxiliary X-ray diagram are judged as follows:
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram and is positioned at the same position, the electric core in the main X-ray diagram and the electric core in the auxiliary X-ray diagram belong to the same article, the pairing is completed, and the original result is reserved;
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram but the electric core is in different positions, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different electric core examples with only one visual angle for successful detection, and executing the step 5.3 on the two electric core examples respectively;
5.2 if the two cell examples are of different material types, if the main X-ray diagram and the auxiliary X-ray diagram both detect the cell and the cell is at the same position but the material types of the cell are different, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different cell examples respectively only having one visual angle for successful detection, and respectively executing the step 5.3 on the two cell examples;
5.3 if one of the main X-ray image and the auxiliary X-ray image is empty, the corresponding cell is not found in one of the images; when the main X-ray image does not detect the battery cell and the auxiliary X-ray image detects the battery cell, the following judgment is carried out:
if the cell detection frame is in the same position, searching a corresponding outline in the main X-ray image according to the cell detection frame in the auxiliary X-ray image, taking a circumscribed rectangle of the found corresponding outline as the cell detection frame and marking the circumscribed rectangle into the main X-ray image, wherein two sides of the cell detection frame are respectively parallel to the horizontal direction and the vertical direction of the image; if the number of the battery cell detection frames is multiple, selecting the battery cell detection frame which enables the position error function to be minimum, and enabling the articles in the detection frame to be the battery cells; the position error function is as follows:
wherein errorw，errorx，errormidRespectively representing the difference between the left and right vertex X coordinate differences between the cell detection frame searched out in the main X-ray diagram and the cell detection frame detected in the auxiliary X-ray diagram, the difference between the left vertex X coordinates and the difference between the central point X coordinates;
and if the cell is detected by the main X-ray diagram and the cell is not detected by the auxiliary X-ray diagram at the same position, obtaining the corresponding cell detection frame in the auxiliary X-ray diagram by the same method.
In a further improvement, in the fifth step, whether the battery cells detected in the main X-ray diagram and the auxiliary X-ray diagram are located at the same position is determined by:
calculating iou of the cell detection frame of the main X-ray diagram and the auxiliary X-ray diagram in the X direction, wherein the X direction is the moving direction of the conveyor belt of the X-ray inspection channel; if the iou is larger than the preset threshold value d, the electric cores of the main X-ray diagram and the auxiliary X-ray diagram are considered to be at the same position, wherein the calculation formula of the iou is as follows:
iou＝(xa2-xa1)+(xb2-xb1)-intersection，
xa1and xa2Respectively representing the left vertex abscissa and the right vertex abscissa, X, of the cell detection frame detected in the main X-ray diagramb1And xb2Respectively representing the left vertex abscissa and the vertex abscissa, min (X), of the cell detection frame detected in the auxiliary X-ray diagrama2，xb2) Represents taking xa2And xb2Of smaller value, max (x)a1，xb1) Represents taking xa1And xb1The larger of the values.
Further improvement, the value interval of d is [0.15, 0.4 ].
In a further improvement, the X-ray detection device is a double-light-source security inspection machine.
The invention has the advantages that:
the invention can rapidly detect the battery capacity in the luggage or the packing box by an image processing method, thereby avoiding the trouble of taking out and confirming the battery, and greatly accelerating the security inspection efficiency.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a main X-ray diagram with a cell arrangement angle of 0 degree;
fig. 3 is an auxiliary X-ray diagram with a cell arrangement angle of 0 degrees;
fig. 4 is a main X-ray diagram with a cell arrangement angle of 45 degrees;
fig. 5 is an auxiliary X-ray diagram with a cell arrangement angle of 45 degrees.
Detailed Description
The technical means of the present invention will be specifically described below by way of specific embodiments.
1. A rechargeable battery is taken to pass through a double-view angle security inspection machine, the length of a battery core of the rechargeable battery is 16.4cm, the width of the battery core is 8.1cm, the height of the battery core is 6cm, and the actual capacity of the rechargeable battery is 60000 mAh.
2. Detecting the X-ray images of the double visual angles by using a target detection model to detect the rechargeable batteries in the main and auxiliary X-ray images; and synchronously obtaining equivalent atomic sequence number graphs corresponding to the rechargeable battery images one by one.
3. And finding the position of the rechargeable battery in the main X-ray equivalent atomic number diagram according to the detected position of the rechargeable battery.
4. And finding a central point of a rechargeable battery image in the equivalent atomic number diagram, intercepting a 20-by-20 pixel block by taking the central point as the center, accumulating pixel values in the block, and averaging to obtain an equivalent atomic number value of the rechargeable battery cell of 69.8.
The X-rays enable the object to be imaged in the security machine, on the one hand on the basis of the properties of the X-rays, namely their penetration, fluorescence effects and photographic effects. On the other hand, based on the difference between the density and the thickness of various articles, when the X-ray penetrates through various articles, the X-ray quantity received by the detection plate of the X-ray security inspection machine generates intensity difference, and meanwhile, the X-ray security inspection machine gives different colors to the materials according to the fact that the materials have different equivalent atomic numbers. At this time, the detection board sends out signals to the CAC board, and after the signals are processed by the DSP, the ALU and the VGA board, the security inspection machine forms images to form images with different color contrasts.
Namely, the security check machine imaging is rendered based on the equivalent atomic number diagram, and the equivalent atomic number diagram of the machine-processed article can be obtained without adding other devices.
5. And using a double-view angle association strategy to associate the rechargeable batteries in the X-ray images of the main X-ray image and the auxiliary X-ray image. The correlation method comprises the following steps:
5.1, whether the cells of the main X-ray diagram and the auxiliary X-ray diagram are the same material is judged through equivalent atomic number information, if so, the cell images in the main X-ray diagram and the auxiliary X-ray diagram are judged as follows:
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram and is positioned at the same position, the electric core in the main X-ray diagram and the electric core in the auxiliary X-ray diagram belong to the same article, the pairing is completed, and the original result is reserved;
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram but the electric core is in different positions, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different electric core examples with only one visual angle for successful detection, and executing the step 5.3 on the two electric core examples respectively;
5.2 if the two cell examples are of different material types, if the main X-ray diagram and the auxiliary X-ray diagram both detect the cell and the cell is at the same position but the material types of the cell are different, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different cell examples respectively only having one visual angle for successful detection, and respectively executing the step 5.3 on the two cell examples;
5.3 if one of the main X-ray image and the auxiliary X-ray image is empty, that is, one of the images does not find the corresponding cell; when the main X-ray image does not detect the battery core and the auxiliary X-ray image detects the battery core, the following judgment is carried out:
if the same position is matched, according to the cell detection frame in the auxiliary X-ray image, a corresponding outline is searched in the main X-ray image, the found external rectangle corresponding to the outline is used as the cell detection frame and is marked in the main X-ray image, and two sides of the cell detection frame are respectively parallel to the horizontal direction and the vertical direction of the image. If the number of the battery cell detection frames is multiple, selecting the battery cell detection frame which enables the position error function to be minimum, and enabling the articles in the detection frame to be the battery cells; the position error function is as follows:
wherein errorw，errorx，errormidRespectively representing the difference between the left and right vertex X coordinate differences between the cell detection frame searched out in the main X-ray diagram and the cell detection frame detected in the auxiliary X-ray diagram, the difference between the left vertex X coordinates and the difference between the central point X coordinates;
and if the cell is detected by the main X-ray diagram and the cell is not detected by the auxiliary X-ray diagram at the same position, obtaining the corresponding cell detection frame in the auxiliary X-ray diagram by the same method.
Whether the electric cores detected in the main X-ray diagram and the auxiliary X-ray diagram are at the same position or not is judged in the following mode:
calculating the iou of the cell detection frame of the main X-ray image and the auxiliary X-ray image in the X direction, wherein the X direction is the movement direction of the conveyor belt of the X-ray inspection channel. If iou is greater than a preset threshold value d, and d is 0.25, the electric cores of the main X-ray image and the auxiliary X-ray image are considered to be at the same position, wherein the calculation formula of iou is as follows:
iou＝(xa2-xa1)+(xb2-xb1)-intersection，
xa1and xa2Respectively representing the left vertex abscissa and the right vertex abscissa, X, of the cell detection frame detected in the main X-ray diagramb1And xb2Respectively representing the left vertex abscissa and the vertex abscissa, min (X), of the cell detection frame detected in the auxiliary X-ray diagrama2，xb2) Represents taking xa2And xb2Of smaller value, max (x)a1，xb1) Represents taking xa1And xb1The larger of the values.
6. And carrying out volume calculation on the associated rechargeable battery by the following method:
6.1, establishing an imaging coordinate system of the main X-ray imaging system and an imaging coordinate system of the auxiliary X-ray imaging system;
step 6.2, passing the standard component through an X-ray inspection channel at different inclination angles, different heights and different horizontal positions perpendicular to the moving direction of the conveyor belt, and obtaining a plurality of groups of images, wherein each group of images comprises a main X-ray image and an auxiliary X-ray image;
6.3, calculating the actual length represented by the unit pixel at the corresponding position of the standard part in the X and y directions on the main X-ray image and the auxiliary X-ray image in the X and z directions, namely the pixel scale corresponding to the pixel according to the measured actual length, width and height of the standard part and the number of the pixels of the main X-ray image and the auxiliary X-ray image of the standard part in the X, y and z directions; taking the pixel scale of each pixel and the image coordinate of the pixel as a group of data, and forming a data set by a plurality of groups of data; wherein, the X direction is the horizontal direction of the plane of the main X-ray image, namely the moving direction of the conveyor belt of the X-ray inspection channel, and the y direction is the direction which is vertical to the X direction in the plane of the main X-ray image; the z direction is a direction perpendicular to the X direction in the plane of the auxiliary X-ray diagram;
6.4, fitting the data set to respectively obtain pixel scale functions p in the x, y and z directionsx(v)、py(y，z)、pz(y，z)；
6.5, inputting the coordinates of each pixel point in the main X-ray diagram and the auxiliary X-ray diagram of the battery cell into the trained pixel scale functions in the X, y and z directions, then accumulating the lengths of the pixel points in the X, y and z directions respectively to obtain the actual lengths of the battery cell in the X, y and z directions, and then performing fusion calculation on the actual lengths of the battery cell in the X, y and z directions to obtain the longest edge l of the battery cellpredictActual length of (c):
wherein lpredictDenotes the actual length of the longest side of the cell, cangleRepresenting angle correction parameters, related to the cell placement angle, chIndicating a height correction parameter related to the height position of the cell in the auxiliary X-ray diagram, lx indicating the length of the charge cell in the X-direction, lyDenotes the length of the cell in the y-direction, ryIs represented byyIs related to the position of the cell in the main X-ray diagram,/zDenotes the length of the cell in the z-direction, rzIs represented byzThe correction parameter of (2) is related to the position of the cell in the auxiliary X-ray diagram; c. CangleHas a value of 1, chIs taken to be 0.95, ryIs taken to be 0.5, rzIs 0.4;
6.6, obtaining a maximum inscribed rectangle and a minimum circumscribed rectangle for cell imaging in the main X-ray image and the auxiliary X-ray image; computing maximum inscribedThe included angle between the rectangle and the minimum circumscribed rectangle; wherein the included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the main X-ray image and the auxiliary X-ray image is alpha1The included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the auxiliary X-ray image is alpha2Length d of two sides of the maximum inscribed rectangle of the main X-ray image1、d2Divided by cos alpha, respectively1To obtain a two-pixel length p1、p2(ii) a Length d of two sides of maximum inscribed rectangle of auxiliary X-ray image3、d4Divided by cos alpha, respectively2To obtain a two-pixel length p3、p4(ii) a To p1、p2、p3、p4Carrying out comprehensive value calculation on the two nearest pixel length data to obtain a length value, wherein the length value is p1、p2、p3、p4The other two data are respectively used as the length l, the width w and the height h of the pixel length of the battery cell;
the method for detecting the comprehensive value of the two closest pixel length data comprises the following steps: length data of the main X-ray image a + length data of the auxiliary X-ray image b, wherein the value of a is 0.7, and the value of b is 0.3;
wherein the pixel length l is the maximum value of the three values, the width w is the middle value of the three values, and the height h is the minimum value of the three values;
where the pixel length is l and l in step 6.5predictDividing to obtain a ratio r;
the actual lengths of the other two sides of the cell are:
the volume V of the cell: l ═ Vpredict*wpredict*hpredict。
7. As shown in fig. 2 and 3, the placing angle of the rechargeable battery is 0 degree; the length, width and height of the rechargeable battery are calculated to be 16.48cm, 8.19cm and 6.06 cm.
8. Then the volume is 16.48 8.19 6.06 817.9255.
9. If the equivalent atomic number value of the rechargeable battery is 69.8 and the rechargeable battery belongs to the lithium polymer battery interval, the material of the rechargeable battery is judged to be lithium polymer.
10. And obtaining the energy density corresponding to the battery cell to be 75 through the energy density database.
11. The capacity of the rechargeable battery is calculated to be 817.9255 × 75 — 61344.41mAh according to the energy density and the volume.
12. Compared with the capacity of a rechargeable battery on the market, the closest capacity is 60000 mah.
13. That is, the capacity of the rechargeable battery was 60000 mah.
14. As shown in fig. 4 and 5, the placement angle of the rechargeable battery was 45 degrees, and the length, width, and height of the rechargeable battery were calculated to be 16.51cm, 8.23cm, and 6.07 cm. The calculated capacity was 61858.14mAh, and the compared capacity was 60000 mAh.
The above description is only one specific guiding embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modification of the present invention using this concept shall fall within the scope of the invention.
Claims (7)
1. A rechargeable battery capacity detection method based on X-ray image processing is characterized by comprising the following steps:
step one, generating equivalent atomic sequence number diagrams corresponding to different battery cores by using rechargeable batteries made of different battery core materials through an X-ray detection device; obtaining equivalent atomic sequence number value intervals of various cell materials according to the equivalent atomic sequence number diagram;
establishing an equivalent atomic sequence value regional database of various cell materials;
measuring to obtain various cell energy densities, and establishing a corresponding cell energy density database;
fourthly, a main X-ray imaging system and an auxiliary X-ray imaging system are installed on the X-ray detection device, and the ray sources of the main X-ray imaging system and the auxiliary X-ray imaging system are respectively positioned at the adjacent sides of the X-ray inspection channel; x rays formed by the light sources of the main X-ray imaging system and the auxiliary X-ray imaging system after passing through the collimator are in the same plane;
step five, detecting the rechargeable battery through an X-ray detection device based on an article detection model of deep learning, calculating to obtain an equivalent atomic sequence value of the battery cell according to an article detection frame, associating the battery cell image in the main X-ray imaging system with the battery cell image of the auxiliary X-ray imaging system, and then calculating to obtain the volume of the battery cell of the rechargeable battery:
step 5.1, establishing an imaging coordinate system of the main X-ray imaging system and an imaging coordinate system of the auxiliary X-ray imaging system;
step 5.2, passing the standard component through an X-ray inspection channel at different inclination angles, different heights and different horizontal positions perpendicular to the moving direction of the conveyor belt, and obtaining a plurality of groups of images, wherein each group of images comprises a main X-ray image and an auxiliary X-ray image;
step 5.3, calculating the actual length represented by the unit pixel at the corresponding position of the standard part in the X and y directions on the main X-ray image and the auxiliary X-ray image, namely the pixel scale corresponding to the pixel according to the measured actual length, width and height of the standard part and the number of the pixel points of the main X-ray image and the auxiliary X-ray image of the standard part in the X, y and z directions; taking the pixel scale of each pixel and the image coordinate of the pixel as a group of data, and forming a data set by a plurality of groups of data; wherein, the X direction is the horizontal direction of the plane of the main X-ray image, namely the moving direction of the conveyor belt of the X-ray inspection channel, and the y direction is the direction which is vertical to the X direction in the plane of the main X-ray image; the z direction is a direction perpendicular to the X direction in the plane of the auxiliary X-ray diagram;
and 5.4, fitting the data set to respectively obtain pixel scale functions p in the x, y and z directionsx(v)、py(y，z)、pz(y，z)；
Step 5.5, inputting the coordinates of each pixel point in the main X-ray image and the auxiliary X-ray image of the battery cell into the trained pixel scale functions in the X, y and z directions, and then dividing the length of the pixel points in the X, y and z directions into the lengthRespectively accumulating to obtain the actual lengths of the battery cell in the x, y and z directions, and then performing fusion calculation on the actual lengths of the battery cell in the x, y and z directions to obtain the longest edge l of the battery cellpredictActual length of (c):
wherein lpredictDenotes the actual length of the longest side of the cell, cangleRepresenting angle correction parameters, related to the cell placement angle, chIndicating a height correction parameter, related to the height position of the cell in the auxiliary X-ray diagram,/xIndicating the length of the charge core in the x-direction, lyDenotes the length of the cell in the y-direction, ryIs represented byyIs related to the position of the cell in the main X-ray diagram,/zDenotes the length of the cell in the z-direction, rzIs represented byzThe correction parameter of (2) is related to the position of the cell in the auxiliary X-ray diagram;
step 5.6, solving the maximum inscribed rectangle and the minimum circumscribed rectangle of the cell imaging in the main X-ray image and the auxiliary X-ray image; calculating the included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle; wherein the included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the main X-ray image and the auxiliary X-ray image is alpha1The included angle between the maximum inscribed rectangle and the minimum circumscribed rectangle in the auxiliary X-ray image is alpha2Length d of two sides of the maximum inscribed rectangle of the main X-ray image1、d2Divided by cos alpha, respectively1To obtain a two-pixel length p1、p2(ii) a Length d of two sides of maximum inscribed rectangle of auxiliary X-ray image3、d4Divided by cos alpha, respectively2To obtain a two-pixel length p3、p4(ii) a To p1、p2、p3、p4Carrying out comprehensive value calculation on the two nearest pixel length data to obtain a length value, wherein the length value is p1、p2、p3、p4The other two data are respectively used as the length l, the width w and the height h of the pixel length of the battery cell;
the method for detecting the comprehensive value of the two closest pixel length data comprises the following steps: length data of the main X-ray image a + length data of the auxiliary X-ray image b; the value interval of a is [0, 1], the value interval of b is [0, 1], and a + b is 1;
wherein the pixel length l is the maximum value of the three values, the width w is the middle value of the three values, and the height h is the minimum value of the three values;
where the pixel length is l and l in step 5.5predictDividing to obtain a ratio r;
the actual lengths of the other two sides of the cell are:
the volume V of the cell: l ═ Vpredict*wpredict*hpredict；
Step six, obtaining the material of the battery cell through an equivalent atomic sequence value interval database according to the equivalent atomic sequence value of the battery cell; then obtaining the energy density of the battery cell through a battery cell energy density database according to the material of the battery cell;
and step seven, obtaining the predicted capacity of the rechargeable battery through the product of the energy density of the battery cell and the volume of the battery cell.
2. The method for detecting the capacity of a rechargeable battery based on X-ray image processing as claimed in claim 1, wherein in the seventh step, the predicted capacity of the rechargeable battery is compared with each capacity specification of the rechargeable battery on the market, and the capacity of the rechargeable battery on the market closest to the predicted capacity of the rechargeable battery is selected as the capacity of the rechargeable battery.
3. The method for detecting the capacity of a rechargeable battery based on X-ray image processing according to claim 1,canglehas a value interval of [0.85, 1]]，chHas a value interval of [0.9, 1]]，ryHas a value interval of [0.4, 0.8 ]]，rzHas a value range of [0.75, 1%]。
4. The method for detecting the capacity of a rechargeable battery based on X-ray image processing according to claim 1, wherein in the fifth step, the cell image in the main X-ray imaging system is used as the main X-ray map, and the cell image in the auxiliary X-ray imaging system is used as the auxiliary X-ray map; the method for associating the main X-ray image with the auxiliary X-ray image comprises the following steps:
5.1, whether the electric cores of the main X-ray diagram and the auxiliary X-ray diagram are the same material is judged through equivalent atomic number information, if so, the electric core images in the main X-ray diagram and the auxiliary X-ray diagram are judged as follows:
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram and is positioned at the same position, the electric core in the main X-ray diagram and the electric core in the auxiliary X-ray diagram belong to the same article, the pairing is completed, and the original result is reserved;
if the electric core is detected in both the main X-ray diagram and the auxiliary X-ray diagram but the electric core is in different positions, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different electric core examples with only one visual angle for successful detection, and executing the step 5.3 on the two electric core examples respectively;
5.2 if the two cell examples are of different material types, if the main X-ray diagram and the auxiliary X-ray diagram both detect the cell and the cell is at the same position but the material types of the cell are different, regarding the main X-ray diagram and the auxiliary X-ray diagram as two different cell examples respectively only having one visual angle for successful detection, and respectively executing the step 5.3 on the two cell examples;
5.3 if one of the main X-ray image and the auxiliary X-ray image is empty, the corresponding cell is not found in one of the images; when the main X-ray image does not detect the battery cell and the auxiliary X-ray image detects the battery cell, the following judgment is carried out:
if the cell detection frame is in the same position, searching a corresponding outline in the main X-ray image according to the cell detection frame in the auxiliary X-ray image, taking a circumscribed rectangle of the found corresponding outline as the cell detection frame and marking the circumscribed rectangle into the main X-ray image, wherein two sides of the cell detection frame are respectively parallel to the horizontal direction and the vertical direction of the image; if the number of the battery cell detection frames is multiple, selecting the battery cell detection frame which enables the position error function to be minimum, wherein articles in the detection frame are battery cells; the position error function is as follows:
wherein errorw，errorx，errormidRespectively representing the difference between the left and right vertex X coordinate differences between the cell detection frame searched out in the main X-ray diagram and the cell detection frame detected in the auxiliary X-ray diagram, the difference between the left vertex X coordinates and the difference between the central point X coordinates;
and if the cell is detected by the main X-ray diagram and the cell is not detected by the auxiliary X-ray diagram at the same position, obtaining the corresponding cell detection frame in the auxiliary X-ray diagram by the same method.
5. The method for detecting the capacity of a rechargeable battery based on X-ray image processing as claimed in claim 4, wherein in the fifth step, whether the cells detected in the main X-ray image and the cells detected in the auxiliary X-ray image are at the same position is determined by:
calculating iou of the cell detection frame of the main X-ray diagram and the auxiliary X-ray diagram in the X direction, wherein the X direction is the moving direction of the conveyor belt of the X-ray inspection channel; if the iou is larger than the preset threshold value d, the electric cores of the main X-ray diagram and the auxiliary X-ray diagram are considered to be at the same position, wherein the calculation formula of the iou is as follows:
iou＝(xa2-xa1)+(xb2-xb1)-intersection，
xa1and xa2Respectively representing the left vertex abscissa and the right vertex abscissa, X, of the cell detection frame detected in the main X-ray diagramb1And xb2Respectively representing left vertex abscissa of cell detection frame detected in auxiliary X-ray diagramAnd vertex abscissa, min (x)a2，xb2) Represents taking xa2And xb2Of smaller value, max (x)a1，xb1) Represents taking xa1And xb1The larger of the values.
6. The method according to claim 5, wherein the value range of d is [0.15, 0.4 ].
7. The method according to claim 1, wherein the X-ray detection device is a dual-light source security inspection machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375640.7A CN114062934B (en) | 2021-11-19 | 2021-11-19 | Rechargeable battery capacity detection method based on X-ray image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375640.7A CN114062934B (en) | 2021-11-19 | 2021-11-19 | Rechargeable battery capacity detection method based on X-ray image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114062934A CN114062934A (en) | 2022-02-18 |
| CN114062934B true CN114062934B (en) | 2022-05-06 |
Family
ID=80278557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111375640.7A Active CN114062934B (en) | 2021-11-19 | 2021-11-19 | Rechargeable battery capacity detection method based on X-ray image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114062934B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113790685B (en) * | 2021-11-17 | 2022-01-18 | 湖南苏科智能科技有限公司 | Automatic size detection method of to-be-detected article for double-light-source X-ray security inspection machine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105651795A (en) * | 2016-03-31 | 2016-06-08 | 无锡日联科技股份有限公司 | Security check machine with weighing and dimension measuring functions and dimension measuring method |
| CN108008305A (en) * | 2017-10-31 | 2018-05-08 | 华南理工大学 | A kind of automobile-used lithium iron phosphate dynamic battery capacity attenuation detecting system |
| CN108387594A (en) * | 2018-02-09 | 2018-08-10 | 中国电力科学研究院有限公司 | A kind of method and system of non-destructive testing stack type lithium ion battery |
| CN110945709A (en) * | 2017-05-30 | 2020-03-31 | 泰坦先进能源解决方案公司 | Battery life estimation and capacity recovery |
| WO2021091236A1 (en) * | 2019-11-04 | 2021-05-14 | 주식회사 엘지화학 | Method for predicting lifespan characteristic of secondary battery including carbon-based hybrid anode |
| CN113030136A (en) * | 2021-03-24 | 2021-06-25 | 广东宏远新科自动化技术开发有限公司 | Battery detection method and system |
| CN113433470A (en) * | 2021-06-10 | 2021-09-24 | 的卢技术有限公司 | Device and method for measuring cell parameters |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013146207A1 (en) * | 2012-03-30 | 2013-10-03 | 住友大阪セメント株式会社 | Electrode active material, lithium-ion battery, electrode active material discharge state detection method, and electrode active material manufacturing method |
-
2021
- 2021-11-19 CN CN202111375640.7A patent/CN114062934B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105651795A (en) * | 2016-03-31 | 2016-06-08 | 无锡日联科技股份有限公司 | Security check machine with weighing and dimension measuring functions and dimension measuring method |
| CN110945709A (en) * | 2017-05-30 | 2020-03-31 | 泰坦先进能源解决方案公司 | Battery life estimation and capacity recovery |
| CN108008305A (en) * | 2017-10-31 | 2018-05-08 | 华南理工大学 | A kind of automobile-used lithium iron phosphate dynamic battery capacity attenuation detecting system |
| CN108387594A (en) * | 2018-02-09 | 2018-08-10 | 中国电力科学研究院有限公司 | A kind of method and system of non-destructive testing stack type lithium ion battery |
| WO2021091236A1 (en) * | 2019-11-04 | 2021-05-14 | 주식회사 엘지화학 | Method for predicting lifespan characteristic of secondary battery including carbon-based hybrid anode |
| CN113030136A (en) * | 2021-03-24 | 2021-06-25 | 广东宏远新科自动化技术开发有限公司 | Battery detection method and system |
| CN113433470A (en) * | 2021-06-10 | 2021-09-24 | 的卢技术有限公司 | Device and method for measuring cell parameters |
| CN113466706A (en) * | 2021-07-26 | 2021-10-01 | 上海伟翔众翼新能源科技有限公司 | Lithium battery echelon utilization residual life prediction method based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 锂离子电池安全性测试与评价方法分析;田君 等;《储能科学与技术》;20181130;第7卷(第6期);1128-1134 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114062934A (en) | 2022-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020253308A1 (en) | Human-machine interaction behavior security monitoring and forewarning method for underground belt transportation-related personnel | |
| CN106238350B (en) | A kind of solar battery sheet method for separating and system based on machine vision | |
| CN105404867B (en) | A kind of substation isolating-switch state identification method of view-based access control model | |
| CN114062934B (en) | Rechargeable battery capacity detection method based on X-ray image processing | |
| CN110298265A (en) | Specific objective detection method in a kind of elevator based on YOLO neural network | |
| CN107392247A (en) | Atural object safe distance real-time detection method below a kind of power line | |
| CN102590222A (en) | Photovoltaic component defect detection method and system | |
| EP4350621A1 (en) | Bare cell appearance inspection method and apparatus, computer device, and storage medium | |
| CN107481237A (en) | A kind of infrared array image hot spot detection method based on multiframe temperature characterisitic | |
| CN109848073A (en) | A kind of apparatus and method for sorting coal and gangue | |
| WO2023193213A1 (en) | Method and apparatus for detecting defect of insulating coating of battery electrode plate, and computer device | |
| CN108629230A (en) | A kind of demographic method and device and elevator scheduling method and system | |
| CN102819733A (en) | Rapid detection fuzzy method of face in street view image | |
| CN109886937A (en) | Defects of insulator detection method based on super-pixel segmentation image recognition | |
| CN110378246A (en) | Ground detection method, apparatus, computer readable storage medium and electronic equipment | |
| CN109525329A (en) | A kind of detection method of conveyer belt type assembly line communication module, system, device | |
| CN103632368A (en) | Metal plate strip surface image defect merging method | |
| CN111539251B (en) | Security check article identification method and system based on deep learning | |
| CN110673038B (en) | Battery detection method, device and system | |
| CN116773559A (en) | Laminated lithium ion battery detection method and device and image processing equipment | |
| CN114723942A (en) | Method, device and equipment for detecting size of lithium battery pole piece and storage medium | |
| CN115131583A (en) | X-Ray detection system and detection method for lithium battery core package structure | |
| CN109794425B (en) | Device and method for classifying retired batteries based on phase measurement three-dimensional profilometry | |
| CN114724094A (en) | System for measuring number of people in gateway vehicle based on three-dimensional image and radar technology | |
| CN113960075A (en) | Security check equipment, article size determination method, storage medium and equipment |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Rechargeable Battery Capacity Detection Method Based on X-ray Image Processing Granted publication date: 20220506 Pledgee: Bank of Changsha Limited by Share Ltd. Wangcheng branch Pledgor: Hunan Ke Ke Intelligent Technology Co.,Ltd. Registration number: Y2024980001307 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |