CN111369509B - Product detection compensation method, device, product monitoring system and storage medium - Google Patents

Abstract

The present application provides a detection and compensation method, a device, a product monitoring system and a storage medium for a product. The detection and compensation method for a product includes: during the product winding process, a visual detection device acquires an image of a target product under a fixed field of view. The first collected image; the spacing parameter of the target product is obtained according to the first collected image, which is used as the detection data of the target product on the winding material under the current layer, and the spacing parameter is used to indicate the winding material of each layer and the selected According to the current layer number of the target product corresponding to the first captured image, the compensation data of the target product in the current layer is determined; according to the compensation data of the target product in the current layer, The detection data of the coiled material corresponding to the target product under the current layer is calibrated to obtain the detection result of the target product at the current layer. In this way, the problem of low product detection accuracy in the prior art can be improved.

Description

Product detection compensation method, device, product monitoring system and storage medium

technical field

The present application relates to the technical field of processing detection, and in particular, to a detection compensation method, device, product monitoring system and storage medium for products.

Background technique

For products formed by winding, in order to improve the processing quality of the product, some product parameters during the winding process are usually detected to facilitate processing adjustment.

However, for the method of image acquisition by means of a fixed field of view to realize detection, it is easy to cause the problem of unclear focus as the product winding process progresses, thereby affecting the detection accuracy of the product.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a product detection compensation method, device, product monitoring system and storage medium, so as to improve the problem of low product detection accuracy in the prior art.

In a first aspect, the embodiment provides a detection compensation method for a product, the method comprising:

During the product winding process, obtain the first captured image obtained by the visual inspection equipment capturing the image of the target product under a fixed field of view;

The distance parameter of the target product is obtained according to the first captured image, which is used as the detection data of the target product on the winding material under the current layer, and the distance parameter is used to indicate the difference between the winding material of each layer and the selected the gap between the reference positions;

Determine the compensation data of the target product at the current layer according to the current layer number of the target product corresponding to the first captured image;

According to the compensation data of the target product in the current layer, the detection data of the coiled material corresponding to the target product in the current layer is calibrated to obtain the detection result of the target product in the current layer.

In the above method, during the winding process of the product, images are collected on each layer of the product with a fixed field of view, so as to obtain the preliminary detection data of the target product on each layer according to the first collected image, and then according to the target product's initial detection data. The number of layers corresponding to each test data is used to calibrate the test data of the target product on the coiled material in each layer state to obtain test results with high detection accuracy. In this way, even with the advancement of the winding process, more and more winding materials are surrounded on the outer surface of the reel, and the thickness of the target product changes accordingly, resulting in unclear focus. Effectively compensate the detection data, thereby reducing the impact of focusing problems on the measurement accuracy and improving the overall detection accuracy.

In an optional implementation manner, the determining the compensation data of the target product in the current layer includes:

The compensation data of the target product in the current layer is determined by using the pre-calculated compensation expression and the current layer number of the target product.

Through the above implementation manner, the measurement deviation of each layer can be determined during the real-time winding detection process of the product, so that the detection data of each layer can be compensated and corrected to improve the final detection accuracy.

In an optional implementation manner, before determining the compensation data of the target product in the current layer by using the pre-calculated compensation expression and the current layer number of the target product, the method further includes:

Acquiring multiple sets of measurement deviation data of the winding test product, where each set of data in the multiple sets of measurement deviation data includes a deviation amount and the number of product layers corresponding to the deviation amount;

Based on each deviation in the multiple sets of measured deviation data and the number of product layers corresponding to each deviation, the compensation expression is obtained by fitting and calculation.

Through the above implementation manner, the measurement deviation law caused by the change of product thickness can be obtained, and then the detection data obtained during the product winding process can be effectively compensated based on the determined deviation law, thereby improving the detection accuracy.

In an optional embodiment, the acquisition of multiple sets of measurement deviation data of the winding test product includes:

determining a fixed field of view of the visual inspection device when the focusing surface of the visual inspection device is gathered at the designated layer position of the rolled test product;

In the process of adjusting the number of layers of the winding test product, the checkerboard image collected by the visual inspection device in the fixed field of view is obtained, and the checkerboard image corresponding to each layer thickness of the winding test product is obtained. ;

The winding test product is determined based on the number of pixels corresponding to the specified number of checkerboards in the checkerboard image obtained under the thickness of each layer, and the theoretical image accuracy of the visual inspection device under the fixed field of view According to the corresponding deviation amounts of each layer thickness, multiple sets of measurement deviation data of the winding test product are obtained.

Through the above implementation manner, the measurement deviation amount caused by the deviation of the product surface from the imaging focusing clear surface of the visual inspection device due to the change of the product thickness can be obtained, which is beneficial to obtain compensation data with high reliability.

In an optional embodiment, the method further includes:

Before image acquisition, the theoretical image accuracy of the visual inspection device under the fixed field of view is calculated.

Through the above implementation manner, it is beneficial to provide data support for the calculation process of the compensation data.

In a second aspect, the embodiment provides a detection and compensation device for a product, the device comprising:

The image acquisition module is used to acquire the first acquired image obtained by the visual inspection equipment performing image acquisition of the target product under a fixed field of view during the product winding process;

The detection module is used to obtain the distance parameter of the target product according to the first collected image, as the detection data of the target product on the winding material under the current layer, and the distance parameter is used to indicate the winding of each layer the gap between the material and the selected reference position;

a determining module, configured to determine the compensation data of the target product at the current layer according to the current layer number of the target product corresponding to the first captured image;

The compensation module is used to calibrate the detection data of the coiled material corresponding to the target product under the current layer according to the compensation data of the target product in the current layer, and obtain the detection result of the target product in the current layer .

The method provided in the first aspect can be executed by the above-mentioned device, and the accuracy of product detection can be improved.

In an optional implementation manner, the determining module is further configured to:

The compensation data of the target product in the current layer is determined by using the pre-calculated compensation expression and the current layer number of the target product.

In an optional implementation manner, the apparatus further includes a computing module for:

Acquiring multiple sets of measurement deviation data of the winding test product, where each set of data in the multiple sets of measurement deviation data includes a deviation amount and the number of product layers corresponding to the deviation amount;

Based on each deviation in the multiple sets of measured deviation data and the number of product layers corresponding to each deviation, the compensation expression is obtained by fitting and calculation.

In a third aspect, the embodiments provide a product monitoring system, including a visual inspection device and a control device connected to the visual inspection device;

The visual inspection device is used to capture images of the wound product with a fixed field of view during the product winding process;

The control device includes a memory and a processor;

A computer program executable by the processor is stored in the memory, and when the computer program is executed by the processor, the method provided in the foregoing first aspect is executed.

In a fourth aspect, an embodiment provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method provided in the foregoing first aspect is executed.

Description of drawings

In order to explain the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, therefore It should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a flowchart of a method for detecting and compensating a product according to an embodiment of the present application.

FIG. 2 is a schematic diagram of a wound cell in an example provided by an embodiment of the present application from a first viewing angle.

FIG. 3 is a schematic diagram of a position between a visual inspection device and a wound cell in an example provided by an embodiment of the present application.

FIG. 4 is a schematic diagram of the winding of the wound cell in an example provided by the embodiments of the present application from a second viewing angle.

FIG. 5 is a schematic diagram of an image acquisition area in an example provided by an embodiment of the present application.

FIG. 6 is a schematic diagram of focus adjustment of a visual inspection device in an example provided by an embodiment of the present application.

FIG. 7 is a functional block diagram of a detection and compensation device for a product according to an embodiment of the present application.

FIG. 8 is a structural block diagram of a product monitoring system provided by an embodiment of the present application.

FIG. 9 is a structural block diagram of a control device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

After research, the inventor found that, in the prior art, the product thickness changes with the advancement of the product winding process, which in turn causes the product winding surface to deviate from the fixed imaging clear surface of the visual inspection equipment, resulting in the product being unreliable. The focus of the winding surface is not clear, which ultimately affects the measurement accuracy of the winding surface of the product.

In view of this, the inventor proposes the following embodiments to improve the measurement accuracy problem caused by the change in the thickness of the product causing the detection surface of the product to deviate from the fixed imaging clear surface of the visual inspection device. In each embodiment provided by the inventor, The image acquisition of the winding process of the product is still carried out with a fixed field of view, but it can effectively compensate the various detection data obtained during the winding process, thereby improving the measurement accuracy and the detection accuracy of the entire system, which is beneficial for subsequent processing. Adjustment provides data reference to improve product quality.

Please refer to FIG. 1. FIG. 1 is a flowchart of a method for detecting and compensating a product according to an embodiment of the present application. The solution provided by the embodiment of the present application will be described in detail below with reference to FIG. 1 .

In the product winding process of the embodiment of the present application, the winding material can be wound around the reel, thereby forming layers of wrapping surfaces around the reel, and the layer-by-layer wrapping surfaces are the image acquisition objects of the embodiment of the present application .

As shown in Figure 1, the detection and compensation method of the product includes steps S11-S14. The method can be applied to a control device, which is connected to a visual inspection device for image acquisition, and can also be connected to an actuator that controls the rotation of the reel.

S11: During the product winding process, acquire a first captured image obtained by the visual inspection device performing image capture of the target product under a fixed field of view.

Wherein, the visual inspection device may be a camera, and by adjusting the lens focusing ring of the camera, the camera can have a clear focusing surface (a clear rectangular focusing surface) when imaging. During the entire product winding process in the embodiments of the present application, the visual field of view of the visual inspection device is fixed, for example, the shooting angle and the shooting distance may be fixed.

As an implementation manner of maintaining a fixed field of view, the position of the visual inspection device may be fixed, and after the position of the focal plane of the visual inspection device is determined, the focal plane of the visual inspection device will not be changed.

It can be understood that there may be one or more visual inspection devices for image acquisition of the target product, and multiple visual inspection devices can be used to capture images of different areas of interest of the target product, thereby obtaining more inspection data.

As an image acquisition method, the control device can know the current number of layers of the target product according to the winding parameters of the product. For example, when the reel rotates 360 degrees, it can be regarded as one layer, and the target product can be obtained through the rotation angle of the reel. The current number of layers, each winding layer, the visual inspection device performs an image capture to obtain a set of first captured images, and sends the first captured images to the control device, so that the control device can perform image recognition on the first captured image . With this principle, each layer of the target product can be inspected.

For each obtained first captured image, S12 may be performed.

S12: Obtain the spacing parameter of the target product according to the first collected image, as the detection data of the target product on the winding material under the current layer, the spacing parameter is used to represent the gap between the winding material of each layer and the selected reference position .

In S12, for each acquired first captured image, the control device may perform image recognition on the first captured image, so as to obtain the distance parameter of the target product reflected in the image according to the first captured image. Among them, the number of spacing parameters is related to factors such as the type of winding material and the area collected by the visual inspection equipment.

Alternatively, each layer of wound material may be one or more layers, ie, each layer of material wound to form the target product may be a composite material. Each spacing parameter may represent a gap between a wound material and a selected virtual reference line.

Among them, the size of the spacing parameter can determine whether each winding material deviates during the winding process, resulting in the phenomenon that the winding is not up to standard. It can be understood that the spacing parameter can also be used to represent the gaps between the individual materials in the combined material of each layer, that is, the spacing parameter can also be used to determine whether the coiled materials are aligned.

It should be noted that since the thickness of the target product is changing during the product winding process, and the field of view of the same visual capture device is fixed, and the focusing surface is fixed, part of the first captured image is based on a clear focusing surface. However, some of the first captured images are obtained when the surface of the target product is far away from the focal plane. Therefore, the results obtained only by the image recognition of S12 may have higher accuracy in some results and higher accuracy in some results. low degree.

Therefore, S13 and S14 need to be performed after each time detection data is obtained, so as to perform detection compensation on the detection data, thereby improving the detection accuracy of each layer.

S13: Determine the compensation data of the target product at the current layer according to the current layer number of the target product corresponding to the first captured image.

As an implementation manner, it can be determined, according to the acquisition time of the first acquired image, which layer the target product has been wound to when the first acquired image is acquired, so as to determine the current state of the target product corresponding to the first acquired image. layers. Based on the determined current layer number of the target product, the compensation data of the target product at the current layer can be queried or calculated.

S14: According to the compensation data of the target product in the current layer, calibrate the detection data of the winding material corresponding to the target product in the current layer, and obtain the detection result of the target product in the current layer.

Wherein, according to the compensation data determined in S13, the detection data on the winding material corresponding to the target product under the current layer can be calibrated, so as to obtain the detection result of the target product at the current layer, so as to realize the target product in the winding process. The surface detection of each layer in the system, and the detection accuracy is high.

In the above method, during the winding process of the product, images are collected on each layer of the product with a fixed field of view, so as to obtain the preliminary detection data of the target product on each layer according to the first collected image, and then according to the target product's initial detection data. The number of layers corresponding to each test data is used to calibrate the test data of the target product on the coiled material in each layer state to obtain test results with higher detection accuracy and improve the detection accuracy. Through the above method, even if more and more winding materials surround the outer surface of the reel with the advancement of the winding process, and the thickness of the target product changes accordingly, resulting in unclear focus, the number of layers of the target product can be adjusted according to the number of layers of the target product. Effectively compensate the detection data, thereby reducing the impact of focusing problems on the measurement accuracy and improving the overall detection accuracy.

In one example, the target product is a wound cell, which may be referred to as a cell.

FIG. 2 shows a schematic diagram of a wound cell in an example from a first viewing angle, as a side view of the cell during the winding process. As shown in FIG. 2 , the wound cell includes a cell winding needle D (ie, a reel), and the winding material wound around the cell winding needle D includes an anode sheet T1, a cathode sheet T2 and a separator T3, which are used to form The material of each layer of the wound cell is a composite material (anode sheet T1, cathode sheet T2 and separator T3), wherein the separator T3 is used to achieve isolation between the cathode sheet T2 and the anode sheet T1.

Before the winding needle D of the battery cell starts to rotate, the anode sheet T1, the separator T3, and the cathode sheet T2 can be arranged in the middle gap of the winding needle D (the rectangular area in the center of Fig. 2) according to the layout of FIG. material is fixed. Then, the rolling needle D clamps the anode sheet T1, the separator T3, and the cathode sheet T2 and rotates, thereby forming the surface of each layer of the cell and increasing the thickness of the wound cell.

Among them, in the winding process of the battery cell shown in FIG. 2, “A”, “B”, and “C” in FIG. 2 respectively represent the positions of the winding battery core under different layers. For the convenience of description, "A" represents the inner side of the wound cell, "B" represents the outer side of the wound cell, and "C" represents the middle surface of the wound cell.

When testing the cell shown in FIG. 2 , a schematic diagram of the position between the visual inspection device and the wound cell is shown in FIG. 3 . “P” in FIG. 3 may represent the lens position of the visual inspection device. In FIG. 3 , the dotted rectangular area corresponding to the visual inspection device represents the fixed field of view area of the visual inspection device.

During the winding process of a cell, please refer to FIG. 4 for a schematic diagram of the cell obtained from a second perspective. The second viewing angle is the direction indicated by the arrow “E” in FIG. 2 , and the direction of the second viewing angle is perpendicular to the direction of the first viewing angle (not shown).

Based on the positional layout of the visual inspection equipment shown in Figure 3, the visual inspection equipment can be controlled to capture images of the areas of interest such as "CCD1" and "CCD2" in Figure 4, so that the corresponding areas of "CCD1" and "CCD2" can be obtained respectively. of the first acquired image. By analyzing and identifying the first captured image corresponding to the area "CCD2", the distance parameters d1 and d2 as shown in Fig. 5 can be obtained. Among them, d1 represents the distance between the separator T3 forming the Lth layer and a reference reference line K when the cell is wound to the Lth layer, and d1 represents the cathode of the Lth layer when the cell is wound to the Lth layer The distance between one edge of the sheet T2 and a reference reference line K.

When the areas at "CCD1" and "CCD2" in Fig. 4 and Fig. 5 are detected by the methods of S11-S14 above, the spacing parameters identified in the image are adjusted according to the compensation data corresponding to the Lth layer, so as to improve the Detection accuracy. For example, when the cathode sheet T2, diaphragm T3, anode sheet T1 and other winding materials are blurred in the first captured image due to unclear focus, the d1 and d2 identified in the blurred first captured image may be Compared with the actual situation, there are some deviations (larger or smaller), after compensation through the above S13-S14, adjust d1, d2 to d1', d2' with higher accuracy, which is beneficial to make the cell's The winding materials (cathode sheet T1, separator T3, anode sheet T1) can be accurately wound to improve product quality.

The process of determining the compensation data will be described below.

In this embodiment of the present application, in order to determine the compensation data of the target product at the current layer, the above S13 may include step S131.

S131: Determine the compensation data of the target product at the current layer by using the pre-calculated compensation expression and the current layer number of the target product.

The pre-calculated compensation expression can be a linear compensation expression obtained by fitting. When the current number of layers of the target product is determined, the current number of layers of the target product is substituted into the compensation expression to calculate the current number of layers of the target product. compensation data for the layer.

其中，

表示补偿数据，

是线性补偿参数，x表示产品层数。The compensation expression can be:

in,

represents the compensation data,

is the linear compensation parameter, and x represents the number of product layers.

Through the above implementation manner, the measurement deviation of each layer can be determined during the real-time winding detection process of the product, so that the detection data of each layer can be compensated and corrected to improve the final detection accuracy.

In order to obtain reliable compensation data, the compensation expression can be obtained through steps S101-S102 before executing S131.

S101: Acquire multiple sets of measurement deviation data of the winding test product, and each set of data in the multiple sets of measurement deviation data includes the deviation and the number of product layers corresponding to the deviation.

Wherein, before the actual winding production is performed to obtain the target product (ie, before S11 ), the winding test product is tested to obtain multiple sets of measurement deviation data of the winding test product. The winding test product is a product of the same type as the target product. For example, the winding test product and the target product may be wound cells of the same type.

As an implementation manner of S101, S101 includes sub-steps S1011-S1013.

S1011: Determine a fixed field of view of the visual inspection device when the focal plane of the visual inspection device gathers at the designated layer position of the winding test product.

S1012: In the process of adjusting the number of layers of the winding test product, acquire the checkerboard image collected by the visual inspection equipment in the fixed field of view, and obtain the checkerboard image corresponding to each layer thickness of the winding test product.

S1013: Based on the number of pixels corresponding to the specified number of checkerboards in the checkerboard image obtained under the thickness of each layer, and the theoretical image accuracy of the visual inspection equipment under a fixed field of view, determine the respective thicknesses of the winding test products under each layer thickness. Corresponding deviations are obtained, and multiple sets of measurement deviation data of the winding test product are obtained.

Since the test has not been formally carried out when S1011 is executed, according to the depth of field characteristics of the lens, combined with the principle of pinhole imaging, the focus adjustment can be performed through the lens focusing ring of the visual inspection device, so that the visual inspection device can focus on the focus shown in Figure 6. The clear surface Q2 (P in Figure 6 represents the lens position of the visual inspection device), the focusing clear surface Q2 can correspond to the specified layer position of the battery cell product, for example, the specified layer position can be on the inner side of the wound battery core, or it can be a roll The middle surface of the wound cell can also be the outer side of the wound cell. If the focusing clear surface Q2 is focused on the middle surface of the wound cell, it can be compatible with a certain thickness of the inner and outer sides based on the position of the focusing surface, so that more images are clear in the subsequent testing process.

When the fixed field of view is determined, the theoretical image accuracy of the visual inspection device under the fixed field of view may also be calculated before image acquisition.

As an implementation manner, the visual field parameter of the visual inspection device and the number of chip pixels of the visual inspection device can be obtained first, and then the theoretical image accuracy of the visual inspection device can be calculated according to the field of view parameter and the number of chip pixels, as The theoretical image accuracy of the visual inspection device under the fixed field of view.

Among them, each visual inspection device has a chip for imaging, the ratio of the long side of the physical size of the chip to the long side of the physical size of the pixel is the number of pixels in the direction of the long side of the chip, and the ratio of the wide side of the physical size of the chip to the physical size of the pixel The aspect ratio is the number of pixels in the width direction of the chip. Based on this principle, if the size of the fixed field of view is adjusted to H*W, and the unit is mm, the field of view parameters of the visual inspection device are obtained. The obtained number of camera chip pixels is M*N, and the unit is pixel. As the number of chip pixels of the visual inspection device, the theoretical calculation of the image in the length and width directions of the visual inspection device can be calculated by the following precision calculation expressions. The accuracy is η1 and η2 respectively, so as to obtain the theoretical image accuracy of the visual inspection equipment under the fixed field of view. The calculated theoretical image accuracy can be used to participate in the calculation of S1013 to obtain compensation data.

Precision calculation expressions include:

η1=H/M (mm/pixel);

η2=W/N (mm/pixel).

Regarding S1012-S1013, after the focal plane of the visual inspection equipment is determined to obtain a fixed field of view, the number of layers is adjusted for the winding test product. In the process of adjusting the number of layers, at the selected number of layers, control the visual inspection equipment to take pictures of the checkerboard calibration board within the fixed field of view (replace the checkerboard calibration board for each layer and take pictures), and obtain the checkerboard corresponding to each layer. grid image. And based on each group of images of the checkerboard calibration board within the fixed field of view, the number of pixels corresponding to the specified number of checkerboards in each group of images is obtained.

Assuming that the focus clear surface Q2 corresponds to the fifth layer of the winding test product, the checkerboard calibration plate placed on the fifth layer is photographed by the visual inspection equipment, and a checkerboard image is obtained. At this time, the pixels corresponding to the specified number of checkerboards are obtained. The number (the value measured at this time can be regarded as the real value).

For example, a standard 1mm*1mm checkerboard calibration board can be placed in the field of view corresponding to the clear focus surface of the visual inspection equipment under a fixed field of view, and 10 horizontal checkerboards are taken, that is, 10 1mm*1mm checkerboards , and measure the pixel number M0 of 10 checkerboards by using a software measurement tool matched with the checkerboard calibration board (for example, a Cognex software measurement tool matched with the Cognex checkerboard calibration board).

Combined with the pre-obtained theoretical image accuracy η1 of the visual inspection device under the fixed field of view H*W, it is assumed that the winding test product (cell) has n layers, and the clear focus surface Q2 is gathered at n/2 corresponding to the middle surface layer (for example, the fifth layer), then the actual measurement value of 10 1mm*1mm checkerboards under the visual inspection equipment can be obtained: S(n/2)=M0*η1, unit: mm.

According to the same principle of calculating S(n/2), in the process of adjusting the number of layers of the winding test product, each selected layer (the 1st, 2nd, 3rd...n-1, n layers) can be adjusted separately. The checkerboard is photographed, and the measured values S1, S2, S3... Sn-1, Sn corresponding to the selected layers are calculated respectively, and the unit of these measured values is mm.

When the number of layers increases or decreases, for example, the product becomes thicker and thicker, and the winding increases to the 7th layer (possibly corresponding to the Q1 position in Figure 6), since the surface of the product deviates from the focusing plane Q2, the result obtained at the 7th layer In the checkerboard image, the number of pixels corresponding to 10 checkerboard calibration plates may not be M0, and the measured value is no longer S(n/2). Similarly, when the number of layers is reduced, the product surface may be at the position of Q3 in Figure 6. Since the surface of the product deviates from the focus plane Q2, in the checkerboard image obtained at this time, the pixels corresponding to the 10 checkerboard calibration plates are The number may not be M0, and the measured value is no longer S(n/2).

When the above principle is used to measure the number of pixels corresponding to 10 checkerboards in the fixed field of view of H*W for each layer from the inner side of the cell to the outer side of the cell, and calculate the measured value of each layer. After S1, S2, S3...Sn-1, Sn, compare these measured values with the value S(n/2) measured under the sharp focus surface, according to the expression ΔSn=Sn–S(n/2) Obtain the deviations of the measured values S1, S2, S3...Sn-1, Sn of each layer from S(n/2) respectively: ΔS1, ΔS2, ΔS3...ΔSn-1, ΔSn, as the winding test in S1013 The corresponding deviation of the product under each layer thickness is obtained, and multiple sets of measurement deviation data of the winding test product are obtained.

Based on these deviations ΔS1, ΔS2, ΔS3...ΔSn-1, ΔSn and the number of product layers corresponding to each deviation: 1, 2, 3...n-1, n, a compensation coordinate system can be established to obtain the winding test Multiple sets of measurement deviation data of the product (1, ΔS1), (2, ΔS2)...(n-1, ΔSn-1), (n, ΔSn).

The aforementioned implementations of S1011-S1013 are described in terms of one dimension of the fixed field of view (only the precision η1 is used). When there is a deviation in one dimension, it is only necessary to change the placement direction of the checkerboard calibration plate, and replace the accuracy η1 with η2. The deviation in the other dimension can be used to compensate the spacing parameters in other measurement directions.

Through the above implementation methods, the implementation methods of S1011-S1013 can obtain the measurement deviation caused by the deviation of the product surface from the imaging focusing clear surface of the visual inspection device due to the change of the product thickness, which is beneficial to obtain compensation data with high reliability.

S102: Based on each deviation in the multiple sets of measurement deviation data and the number of product layers corresponding to each deviation, a compensation expression is obtained by fitting and calculation.

Wherein, in S102, according to the multiple sets of measurement deviation data (1, ΔS1), (2, ΔS2)...(n-1, ΔSn-1), (n, ΔSn) obtained in the foregoing embodiments, based on each ΔS1 , ΔS2, ΔS3...ΔSn-1, ΔSn and the number of product layers corresponding to each deviation: 1, 2, 3...n-1, n, and the aforementioned compensation expression is calculated by fitting.

The fitting calculation process can include:

分别表示层数平均值、补偿数据的平均值，n表示产品层数，ΔSn表示第n层的偏差量；

表示线性补偿参数。将前述的多组测量偏差数据代入上述拟合计算过程中，计算得出线性回归方程

即为前述的补偿表达式，以此得到视觉检测设备在实际测量过程中因产品厚度变化所对应的偏差规律。in,

Represents the average value of layers and the average value of compensation data, n represents the number of product layers, and ΔSn represents the deviation of the nth layer;

Indicates the linear compensation parameter. Substitute the aforementioned multiple sets of measurement deviation data into the above fitting calculation process, and calculate the linear regression equation

It is the aforementioned compensation expression, so as to obtain the deviation law of the visual inspection equipment due to the change of product thickness during the actual measurement process.

According to the law corresponding to the compensation expression, in the actual winding production process of S11-S14, the compensation data corresponding to each layer can be determined according to the number of product layers wound in the actual production process, so that the compensation data can be used for the first captured image. The obtained detection data is compensated, and the detection data corresponding to the first captured image of each layer is added to the deviation of the visual detection equipment in the corresponding layer, so as to obtain the actual detection result, that is,

表示前述步骤S13中确定出的补偿数据。Wherein Sx represents the final detection result in the aforementioned step S14, and represents the spacing parameter obtained in the aforementioned step S12,

Indicates the compensation data determined in the aforementioned step S13.

以实现检测补偿效果。In the actual winding production process of S11-S14, if the cell is wound to the first layer, the value of a measurement item (which can be d1 or d2 in Figure 5) is measured according to the first captured image as: Sx0, since the position of the clear focus surface in the aforementioned embodiment is not in the first layer, the Sx0 measured by the first captured image is not the real value. To obtain the real value of the first layer, it is necessary to superimpose the The offset determined by the compensation expression

In order to achieve the detection compensation effect.

It can be understood that, in other embodiments, in the process of determining the compensation data, the surface corresponding to other layers can be used as the fixed focusing clear surface, but it is necessary to ensure the image acquisition conditions of S11-S14 and the acquisition conditions when determining the compensation data. The same, as long as the deviation law of the product surface deviating from the focused clear surface can be obtained under a fixed field of view.

Based on the same inventive concept, please refer to FIG. 7 , an embodiment of the present application further provides a product detection and compensation device 700 , which can be used to execute the aforementioned product detection and compensation method, thereby improving the detection of products in the actual winding production process Accuracy, improve the surface detection accuracy of coiled products, and facilitate subsequent deviation correction.

As shown in FIG. 7 , the apparatus includes: an image acquisition module 701 , a detection module 702 , a determination module 703 , and a compensation module 704 .

An image acquisition module 701, configured to acquire a first captured image obtained by a visual inspection device performing image capture of a target product under a fixed field of view during the product winding process;

The detection module 702 is used to obtain the distance parameter of the target product according to the first collected image, as the detection data of the target product on the winding material under the current layer, the distance parameter is used to indicate the volume of each layer the gap between the wound material and the selected reference position;

A determination module 703, configured to determine the compensation data of the target product at the current layer according to the current layer number of the target product corresponding to the first captured image;

The compensation module 704 is configured to calibrate the detection data of the coiled material corresponding to the target product under the current layer according to the compensation data of the target product at the current layer to obtain the detection data of the target product at the current layer result.

Optionally, the determining module 703 is further configured to: determine the compensation data of the target product at the current layer by using the pre-calculated compensation expression and the current layer number of the target product.

Optionally, the device may also include a calculation module, the calculation module is used to: obtain multiple sets of measurement deviation data of the winding test product, and each set of data in the multiple sets of measurement deviation data includes the deviation and the number of product layers corresponding to the deviation. ; Based on each deviation in the multiple sets of measurement deviation data and the number of product layers corresponding to each deviation, the compensation expression is obtained by fitting calculation.

Optionally, the computing module may further include an initialization module, which is used to determine the fixed field of view of the visual inspection device when the focusing surface of the visual inspection device is gathered at the designated layer position of the winding test product. ; The image acquisition module 701 can also be used to acquire the checkerboard image collected by the visual inspection equipment in the fixed field of view during the adjustment process of the number of layers of the winding test product, and obtain the results of the winding test product in each The corresponding checkerboard images under the layer thicknesses; the initialization module can also be used for the number of pixels corresponding to the specified number of checkerboards in the checkerboard images obtained under the thickness of each layer, and the visual detection device in the The theoretical image accuracy under a fixed field of view is used to determine the corresponding deviations of the winding test product under each layer thickness, and multiple sets of measurement deviation data of the winding test product are obtained.

Optionally, the initialization module can also be used to calculate the theoretical image accuracy of the visual detection device under the fixed field of view.

For other details of the detection and compensation device 700 of the product, please refer to the above-mentioned relevant description of the detection and compensation method of the product, which will not be repeated here.

In addition to the above embodiments, referring to FIG. 8 , an embodiment of the present application further provides a product monitoring system, which includes a visual inspection device 110 and a control device 120 connected to the visual inspection device 110 .

The visual inspection device 110 is used to capture images of the wound product with a fixed field of view during the product winding process.

Among them, the visual inspection device 110 may include a camera body, an industrial lens, an industrial light source, and other structures required for image acquisition. The camera body and the industrial lens are installed together. According to the principle of pinhole imaging, when the shooting object remains unchanged, the lens is adjusted. The distance from the object to be photographed can obtain fields of view of different sizes, but in the embodiment of the present application, image acquisition is performed under the condition of a fixed field of view.

The control device 120 has an arithmetic processing capability, and can be built into the visual inspection device 110 , or can be used as an external device of the visual inspection device 110 . For example, the control device 120 may be an industrial computer connected to the visual inspection device 110 in communication, which can acquire images collected by the visual inspection device 110, analyze and recognize the images according to the existing visual processing software, and also control the visual inspection device 110. Perform image acquisition.

As shown in FIG. 9 , the control device 120 includes a memory 121 , a processor 122 , and a communication unit 123 , and the memory 121 , the processor 122 , and the communication unit 123 are directly or indirectly connected to realize data interaction.

The memory 121 is a storage medium, which may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 121 can be used to store various functional modules and corresponding computer programs in the aforementioned product detection and compensation device 700 . The processor 122 may execute the software function modules stored in the memory 121 to perform the aforementioned methods.

The processor 122 has computing processing capability, and can be a general-purpose processor such as a central processing unit (CPU), a network processor (NP), or the like; it can also be a special-purpose processor or a processor built by other programmable logic devices. device. The processor 122 may implement the methods, steps, and logical block diagrams provided by the embodiments of the present application. A computer program executable by the processor 122 is stored in the memory 121, and when the computer program is executed by the processor 122, the aforementioned method for detecting and compensating a product is executed.

The communication unit 123 may include a communication bus, a communication bayonet, a communication chip, etc. for realizing wired or wireless communication. The winding product is wound by the actuator for data interaction.

The structure shown in FIG. 9 is only for illustration, and there may be more components in specific applications, or other configuration modes different from those shown in FIG. 9 . For example, the control device 120 may further have a display unit for displaying data such as images obtained during the detection process, measurement values obtained according to the images, and final detection results.

In addition to the above embodiments, the embodiments of the present application also provide a storage medium, where a computer program is stored thereon, and the computer program is executed by the processor 122 to execute the aforementioned product detection and compensation method. The storage medium may be any available medium that can be accessed by the processor 122, which may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state drives, Solid State Drives) Disk (SSD)) and so on.

In the embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the mutual connection discussed may be through some communication interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

Furthermore, each functional module in each embodiment of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

In this document, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such existence between these entities or operations. The actual relationship or sequence.

The above are only examples of the present application, and are not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims (9)

1. A method for detection compensation of a product, the method comprising:

in the product winding process, acquiring a first acquisition image obtained by acquiring an image of a target product by a visual detection device under a fixed visual field;

obtaining a distance parameter of the target product according to the first collected image, wherein the distance parameter is used as detection data of the target product for the winding material under the current layer, and the distance parameter is used for representing a gap between the winding material of each layer and a selected reference position;

determining compensation data of the target product on the current layer according to the current layer number of the target product corresponding to the first collected image;

calibrating the detection data of the winding material corresponding to the target product on the current layer according to the compensation data of the target product on the current layer to obtain the detection result of the target product on the current layer;

and calculating the theoretical image precision of the visual detection equipment under the fixed vision field before image acquisition.

2. The method of claim 1, wherein determining compensation data for the target product at a current layer comprises:

and determining the compensation data of the target product on the current layer according to the pre-calculated compensation expression and the current layer number of the target product.

3. The method of claim 2, wherein before the determining the compensation data of the target product at the current layer according to the pre-calculated compensation expression and the current layer number of the target product, the method further comprises:

acquiring a plurality of groups of measurement deviation data of a winding test product, wherein each group of data in the plurality of groups of measurement deviation data comprises a deviation amount and a product layer number corresponding to the deviation amount;

and fitting and calculating to obtain the compensation expression based on each deviation amount in the multiple groups of measured deviation data and the number of product layers corresponding to each deviation amount.

4. The method of claim 3, wherein said obtaining a plurality of sets of measured deviation data for a coiled test product comprises:

determining a fixed field of view of the visual inspection device while a focal plane of the visual inspection device is focused at a designated layer location of the coiled test product;

acquiring checkerboard images collected by the visual detection equipment in the fixed view during the layer number adjusting process of the winding test product, and acquiring checkerboard images respectively corresponding to the winding test product under each layer thickness;

and determining deviation amounts respectively corresponding to the winding test product under each layer thickness based on the number of pixels corresponding to the specified number of checkerboards in the checkerboard image obtained under each layer thickness and the theoretical image precision of the visual detection equipment under the fixed visual field, so as to obtain multiple groups of measurement deviation data of the winding test product.

5. An apparatus for compensating for the detection of a product, the apparatus comprising:

the image acquisition module is used for acquiring a first acquisition image obtained by acquiring an image of a target product under a fixed view by visual detection equipment in the product winding process;

the detection module is used for obtaining a distance parameter of the target product according to the first collected image, the distance parameter is used as detection data of the target product for the winding material under the current layer, and the distance parameter is used for representing a gap between the winding material of each layer and a selected reference position;

the determining module is used for determining compensation data of the target product on the current layer according to the current layer number of the target product corresponding to the first collected image;

the compensation module is used for calibrating the detection data of the winding material corresponding to the target product on the current layer according to the compensation data of the target product on the current layer to obtain the detection result of the target product on the current layer;

the detection compensation device of the product is also used for calculating the theoretical image precision of the visual detection equipment under the fixed visual field before image acquisition.

6. The apparatus of claim 5, wherein the determining module is further configured to:

and determining the compensation data of the target product on the current layer according to the pre-calculated compensation expression and the current layer number of the target product.

7. The apparatus of claim 6, further comprising a computing module to:

acquiring a plurality of groups of measurement deviation data of a winding test product, wherein each group of data in the plurality of groups of measurement deviation data comprises a deviation amount and a product layer number corresponding to the deviation amount;

and fitting and calculating to obtain the compensation expression based on each deviation amount in the multiple groups of measured deviation data and the number of product layers corresponding to each deviation amount.

8. A product monitoring system is characterized by comprising a visual detection device and a control device connected with the visual detection device;

the visual detection equipment is used for acquiring images of the wound product in a fixed view during the winding process of the product;

the control device comprises a memory and a processor;

the memory has stored therein a computer program executable by the processor, the computer program, when executed by the processor, performing the method of any of claims 1-4.

9. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, performs the method of any one of claims 1-4.

Images