[go: up one dir, main page]

CN119610795A - Warp classification and process control method, system and equipment for tile line outlet paperboard - Google Patents

Warp classification and process control method, system and equipment for tile line outlet paperboard Download PDF

Info

Publication number
CN119610795A
CN119610795A CN202411552933.1A CN202411552933A CN119610795A CN 119610795 A CN119610795 A CN 119610795A CN 202411552933 A CN202411552933 A CN 202411552933A CN 119610795 A CN119610795 A CN 119610795A
Authority
CN
China
Prior art keywords
warping
cardboard
produced
paperboard
vertical surface
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411552933.1A
Other languages
Chinese (zh)
Inventor
赵庆军
蒋勉
黄玮
黄淙琪
程晓琦
林建浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Fosber Intelligent Equipment Co Ltd
Original Assignee
Guangdong Fosber Intelligent Equipment Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Fosber Intelligent Equipment Co Ltd filed Critical Guangdong Fosber Intelligent Equipment Co Ltd
Priority to CN202411552933.1A priority Critical patent/CN119610795A/en
Publication of CN119610795A publication Critical patent/CN119610795A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B31—MAKING ARTICLES OF PAPER, CARDBOARD OR MATERIAL WORKED IN A MANNER ANALOGOUS TO PAPER; WORKING PAPER, CARDBOARD OR MATERIAL WORKED IN A MANNER ANALOGOUS TO PAPER
    • B31F—MECHANICAL WORKING OR DEFORMATION OF PAPER, CARDBOARD OR MATERIAL WORKED IN A MANNER ANALOGOUS TO PAPER
    • B31F1/00—Mechanical deformation without removing material, e.g. in combination with laminating
    • B31F1/20—Corrugating; Corrugating combined with laminating to other layers

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Paper (AREA)

Abstract

本发明涉及瓦楞纸板生产领域，公开了瓦楞纸板生产线出口纸板翘曲分类与过程控制方法、系统及设备，该方法用于实时采集并分析纸板生产过程的翘曲类型，并根据翘曲类型输出生产线控制参数。该方法包括：在线检测纸板的垂直面曲线轮廓图像并判断纸板类型；当纸板类型为非L型纸板时，在线计算纸板翘曲凸度；若翘曲凸度的绝对值不大于翘曲预设阈值，则判定生产纸板质量合格，若翘曲凸度的绝对值大于翘曲预设阈值时，则根据翘曲凸度的值与不同翘曲类型所对应的翘曲凸度预设范围值来确定并输出生产纸板的翘曲类型；将纸板翘曲类型输入预训练的神经网络模型以获取神经网络模型输出的生产线控制参数，并传输给生产线控制中心进行调整控制纸板质量。

The present invention relates to the field of corrugated cardboard production, and discloses a method, system and equipment for classifying and controlling the warping of cardboard at the exit of a corrugated cardboard production line. The method is used to collect and analyze the warping type of the cardboard production process in real time, and output the production line control parameters according to the warping type. The method includes: online detection of the vertical surface curve profile image of the cardboard and judging the cardboard type; when the cardboard type is a non-L-shaped cardboard, online calculation of the cardboard warping convexity; if the absolute value of the warping convexity is not greater than the preset warping threshold, the quality of the produced cardboard is determined to be qualified; if the absolute value of the warping convexity is greater than the preset warping threshold, the warping type of the produced cardboard is determined and output according to the value of the warping convexity and the preset range value of the warping convexity corresponding to different warping types; the cardboard warping type is input into a pre-trained neural network model to obtain the production line control parameters output by the neural network model, and transmitted to the production line control center for adjustment and control of the cardboard quality.

Description

Warp classification and process control method, system and equipment for tile line outlet paperboard
Technical Field
The invention relates to the technical field of paperboard production, in particular to a method, a system and equipment for classifying and controlling warping of a corrugated paperboard at a tile line outlet.
Background
The corrugated paper package is widely applied to downstream consumer industries such as household appliances, electronic products, IT, food and beverage, books, daily chemicals, textiles and the like, and logistics express companies.
The quality of the corrugated board production line is mainly related to the factors such as the material of the base paper, the moisture content, the temperature control in the production process and the like. The warpage of the export paper board is an important index for reflecting the product quality of the corrugated board production line. The process control of the corrugated board production line mainly monitors the warping degree of the paper board at the outlet of the production line on line in real time, and realizes the effective feedback control of the quality of the paper board. The on-line detection of the warping degree of the outlet paperboard of the production line and the recognition of the warping level are key to realizing the process control of the production line. At present, the quality detection and control of the output products of the domestic corrugated board production line mainly adopts the human eyes of field engineers to judge and identify, and implements the method of manually inputting parameters to adjust and control the quality of the products. However, the production speed of the existing corrugated board production line is generally hundreds of meters per minute, the on-line detection of the warpage of the output board and the identification of the warpage level are realized manually, and the rapid development of the industries such as online shopping and express delivery brings customized and personalized market demands to the production of the corrugated board, so that the corrugated board is required to be produced in batches and small batches, the quantity of orders is large, the material change frequency of the production process is very high, the labor cost occupied by the corrugated board industry is high, and the automation and intelligence level of the corrugated board manufacturing industry is influenced.
Disclosure of Invention
The invention provides a method, a system and equipment for classifying and controlling the warping of a corrugated board at a tile line outlet, which are used for collecting and analyzing the warping type of the produced corrugated board in real time and outputting corresponding production line control parameters according to the warping type.
The first aspect of the invention provides a tile line outlet paperboard warp classifying and process controlling method, which comprises the steps of acquiring a vertical plane curve outline image of a produced paperboard by using a linear light sensor, judging the paperboard type of the produced paperboard according to the vertical plane curve outline image, calculating warp convexity of the produced paperboard based on the vertical plane curve outline image when the type of the produced paperboard is a non-L-shaped paperboard, judging that the quality of the produced paperboard is qualified if the absolute value of the warp convexity is not larger than a warp preset threshold value, determining and outputting the type of the produced paperboard according to the warp convexity value and warp convexity preset range values corresponding to different warp types when the absolute value of the warp convexity is larger than the warp preset threshold value, inputting the type of the produced paperboard into a pre-trained neural network model to obtain production line control parameters output by the pre-trained neural network model, and outputting the production line control parameters to a production line control center for adjusting and controlling the quality of the paperboard.
The method comprises the steps of collecting vertical plane curve outline images of a produced paperboard by using a line structure light sensor, judging the paperboard type of the produced paperboard according to the vertical plane curve outline images, collecting vertical plane reflected light images of the produced paperboard for a plurality of times by using the line structure light sensor, preprocessing the collected vertical plane reflected light images to obtain a plurality of preprocessed images, extracting and integrating the vertical plane curve outline images of the produced paperboard from the preprocessed images, carrying out data fitting according to the extracted vertical plane curve outline images to obtain a unitary triple function of curve profile transverse pixel coordinates-curve profile longitudinal pixel coordinates, calculating the number of extreme points of the unitary triple function, judging that the produced paperboard is a normal paperboard when the number of the extreme points of the unitary triple function is 0, judging that the produced paperboard is a non-S type paperboard when the number of the extreme points of the unitary triple function is 1, judging that the produced paperboard is a S type paperboard when the number of the extreme points of the unitary triple function is 2, and sending an alarm reminding, calculating the difference value of derivatives on two sides of the produced paperboard based on the unitary triple function when the produced paperboard is the non-S type paperboard, calculating the preset derivative value, judging that the difference value exceeds the preset derivative value of the unitary value, and judging that the produced paperboard is L type, and the produced paperboard is not S type paperboard.
Preferably, the structural light sensor is used for collecting the vertical plane reflected light image of the produced paperboard for a plurality of times, and the collected vertical plane reflected light image is preprocessed to obtain a plurality of preprocessed images, wherein the preprocessing comprises the steps of projecting structural light to the vertical plane of the produced paperboard, collecting the vertical plane reflected light image of the produced paperboard for a plurality of times, and preprocessing the collected vertical plane reflected light image to obtain a plurality of preprocessed images.
Preferably, the vertical plane curve outline image of the produced paperboard is extracted from a plurality of preprocessed images and integrated, and the method comprises the steps of extracting light fringes in the preprocessed images to obtain a plurality of groups of light fringes, mapping the position of each group of light fringes to a space three-dimensional coordinate by using camera calibration parameters, converting and aligning the space three-dimensional coordinates of the plurality of groups of light fringes, fusing to obtain a vertical plane three-dimensional outline of the produced paperboard, and processing the vertical plane three-dimensional outline of the produced paperboard to obtain the vertical plane curve outline image of the produced paperboard.
Preferably, the unitary cubic function of the curve profile lateral pixel coordinates-the curve profile longitudinal pixel coordinates is expressed as:
f1(x)＝a1x3+b1x2+c1x+d
Where x represents the transverse pixel coordinates of the vertical plane curve profile, f 1 (x) represents the longitudinal pixel coordinates of the vertical plane curve profile at the corresponding location, and a 1、b1、c1 and d represent the fitting constants.
Preferably, the difference δ in derivatives of both sides of the produced board is expressed as:
Where x i denotes the horizontal pixel coordinates of the profile of the vertical plane curve, x 1,x2,x3...xn...xm denotes the horizontal coordinates of all pixels, m denotes the number of coordinate points of all pixels, f '1 (x) denotes the function value of the derivative function corresponding to the position x i, and x n denotes the point where f' 1 (x) =0.
Preferably, when the type of the produced paperboard is non-L-shaped paperboard, calculating the warping convexity of the produced paperboard based on the vertical plane curve profile image comprises performing data fitting based on the vertical plane curve profile image to obtain a unitary quadratic function of the vertical plane curve profile longitudinal pixel coordinates and the vertical plane curve profile transverse pixel coordinates when the type of the produced paperboard is non-L-shaped paperboard, wherein the unitary quadratic function relation is:
f(x)=ax2+bx+c
Wherein x represents the transverse pixel coordinate of the profile of the vertical plane curve, f (x) represents the longitudinal pixel coordinate of the profile of the vertical plane curve corresponding to the x position, and a, b and c represent constants;
According to the unitary quadratic function, the warping convexity theta corresponding to the produced paperboard is calculated by adopting the following formula, wherein the warping convexity theta is expressed as:
Where K (x) is an average value of curvature at a position where three quarters are located, f '(x) represents a slope, f' (x) is a derivative of a profile of a vertical plane curve, f '(x) represents a rate of change of curvature, f' (x) is a second derivative of the profile of the vertical plane curve, x a and x b respectively represent pixel coordinates at positions where two end points of a lateral pixel coordinate of a unitary quadratic function are located, and x 1、x2、x3 respectively represent pixel coordinates at positions where three quarters of the lateral pixel coordinate of the unitary quadratic function are located, respectively:
The method comprises the steps of establishing an input and output data set through the paperboard warping type or warping degree recorded on a corrugated paperboard production line and the production line quality control parameters, training the input and output data set through the neural network model to obtain a pre-trained neural network model, establishing a corresponding relation between the production line paperboard warping type and the production line control parameters, inputting the warping type of the production paperboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and outputting the production line control parameters to the production line control center to adjust and control the paperboard quality.
The invention provides a tile line outlet paperboard warping classification and process control system which comprises an acquisition module, a calculation module and a judgment module, wherein the acquisition module is used for acquiring a vertical plane curve outline image of a produced paperboard by using a linear light sensor and judging the paperboard type of the produced paperboard according to the vertical plane curve outline image, the calculation module is used for calculating the warping convexity of the produced paperboard based on the vertical plane curve outline image when the type of the produced paperboard is a non-L-shaped paperboard, the judgment module is used for judging that the quality of the produced paperboard is qualified when the absolute value of the warping convexity is not more than a warping preset threshold value, determining and outputting the type of the produced paperboard according to the value of the warping convexity and the warping convexity preset range value corresponding to different warping types when the absolute value of the warping convexity is more than the warping preset threshold value, and the control parameter output module is used for inputting the type of the produced paperboard into a pre-trained neural network model to obtain production line control parameters output by the pre-trained neural network model and outputting the production line control parameters to a production line control center for adjusting and controlling the quality.
A third aspect of the present invention provides a tile line outlet board warp classification and process control device comprising a memory and at least one processor, the memory having stored therein computer readable instructions, the memory and the at least one processor being interconnected by wires, the at least one processor invoking the computer readable instructions in the memory to cause the tile line outlet board warp classification and process control device to perform the steps of the tile line outlet board warp classification and process control method as described above.
According to the technical scheme provided by the invention, the type of the paperboard is intelligently judged and the warping convexity is calculated by accurately acquiring the profile image of the vertical plane curve of the paperboard, so that the quality of the paperboard is rapidly and accurately estimated, when the warping problem is found, the warping type can be automatically classified, and the targeted production line control parameters are output according to the pre-trained neural network model, so that the production is timely adjusted, the quality stability of the paperboard is ensured, and the overall production efficiency and the intelligent management level are improved.
Drawings
FIG. 1 is a first flowchart of a method for classification and process control of warp of a corrugated board for a corrugated board outlet according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for classification of warp and process control of a corrugated board output according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a tile line outlet board warp classifying and process controlling device according to an embodiment of the present invention.
Detailed Description
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, a method for classifying and controlling warpage of a corrugated board in a corrugated board outlet according to an embodiment of the present invention includes:
s101, acquiring a vertical plane curve outline image of a produced paperboard by using a linear structure light sensor, and judging the paperboard type of the produced paperboard according to the vertical plane curve outline image;
S102, calculating the warping convexity of the produced paperboard based on the vertical plane curve outline image when the type of the produced paperboard is a non-L paperboard;
s103, if the absolute value of the warping convexity is not larger than a warping preset threshold, judging that the quality of the produced paperboard is qualified, and if the absolute value of the warping convexity is larger than the warping preset threshold, determining and outputting the warping type of the produced paperboard according to the value of the warping convexity and the warping convexity preset range value corresponding to different warping types;
S104, inputting the warping type of the production paper board into the pre-trained neural network model to obtain production line control parameters output by the pre-trained neural network model, and outputting the production line control parameters to a production line control center.
It will be appreciated that the subject of the present invention may be a tile line exit board warp classification and process control system, as well as a terminal or server, and is not limited in this regard. The embodiment of the invention is described by taking a server as an execution main body as an example.
In the embodiment, in step S101, a line structure light sensor is used for collecting a vertical plane curve outline image of a produced paperboard, and the paperboard type of the produced paperboard is judged according to the vertical plane curve outline image; the method comprises the steps of extracting and integrating vertical plane curve outline images of a produced paperboard from a plurality of preprocessing images, carrying out data fitting according to the extracted vertical plane curve outline images to obtain a unitary tertiary function of a curve outline transverse pixel coordinate and a curve outline longitudinal pixel coordinate, calculating the number of extreme points of the unitary tertiary function, judging that the produced paperboard is a normal paperboard when the number of the extreme points of the unitary tertiary function is 0, judging that the produced paperboard is a non-S-shaped paperboard when the number of the extreme points of the unitary tertiary function is 1, judging that the produced paperboard is an S-shaped paperboard when the number of the extreme points of the unitary tertiary function is 2, and sending out alarm reminding, calculating the difference value of derivatives on two sides of the produced paperboard based on the unitary tertiary function when the produced paperboard is a non-S-shaped paperboard, judging that the produced paperboard is L-shaped when the difference value exceeds a preset derivative range value, and sending out alarm reminding, and otherwise judging that the produced paperboard is non-L-shaped.
In the embodiment, the vertical plane reflected light image of the produced paperboard is collected for a plurality of times, and the collected vertical plane reflected light image is preprocessed to obtain a plurality of preprocessed images, wherein the preprocessing comprises the steps of projecting structural light to the vertical plane of the produced paperboard, collecting the vertical plane reflected light image of the produced paperboard for a plurality of times by using a structural light sensor, and preprocessing the collected vertical plane reflected light image to obtain a plurality of preprocessed images.
Alternatively, the structured light may be a light source emitted by a linear laser, and the structured light sensor is an image pickup device.
It will be appreciated that when capturing the vertical plane reflected light image of the produced board, there may be areas without pixels, and therefore, it is necessary to capture the vertical plane reflected light image of the produced board multiple times using the image capturing device, and then analyze the captured multiple times.
In the embodiment, the vertical plane curve outline image of the produced paperboard is extracted from a plurality of preprocessed images and integrated, and the method comprises the steps of extracting light fringes in the preprocessed images to obtain a plurality of groups of light fringes, mapping the position of each group of light fringes to a space three-dimensional coordinate by using camera calibration parameters, converting and aligning the space three-dimensional coordinates of the plurality of groups of light fringes, fusing to obtain the vertical plane three-dimensional outline of the produced paperboard, and processing the vertical plane three-dimensional outline of the produced paperboard to obtain the vertical plane curve outline image of the produced paperboard.
In this embodiment, the light fringes in the image are identified by an image processing algorithm (such as edge detection, threshold segmentation, etc.), the edges in the image are detected using a Canny edge detector or Sobel operator, and the light fringes are separated from the background by setting an appropriate threshold.
In this embodiment, before performing the three-dimensional reconstruction, the camera needs to be calibrated to obtain the internal parameters and external parameters of the camera. Then, the camera calibration parameters and the positions of the light fringes in the image are utilized to map the positions of the light fringes into space three-dimensional coordinates through a perspective projection principle.
In this embodiment, three-dimensional coordinates of space under different viewing angles are converted and aligned and then fused to obtain three-dimensional profiles of a vertical plane of the produced paperboard, and if overlapping areas are encountered, the overlapping areas are optimized through a point cloud fusion algorithm (such as an ICP algorithm), so that continuity and accuracy of the three-dimensional profiles are ensured.
In this embodiment, a slice plane is selected from the perpendicular three-dimensional profile of the board to be produced, perpendicular to the plane of the board, which plane should be located at the desired cross-sectional position of the board. Then, on the slice plane, a contour extraction algorithm (e.g., canny edge detection, hough transform, etc.) is used to extract the curve contour of the cardboard. This contour will reflect the shape and size of the cardboard at that location. Finally, smoothing the vertical plane three-dimensional contour of the produced paperboard by a filtering algorithm (such as Gaussian filtering, median filtering and the like) to generate a vertical plane curve contour image, and smoothing the contour extracted by the curve by the filtering algorithm (such as Gaussian filtering, median filtering and the like) to eliminate tiny fluctuation caused by noise or measurement errors.
In this embodiment, the unitary cubic function of the curve profile horizontal pixel coordinates-the curve profile vertical pixel coordinates is expressed as:
f1(x)＝a1x3+b1x2+c1x+d
Where x represents the curve profile transverse pixel coordinates, f 1 (x) represents the vertical pixel coordinates of the vertical plane curve profile at the corresponding location, and a 1、b1、c1 and d represent the fitting constants.
The difference in derivative of both sides of the produced board, delta, is expressed as:
Where xi represents the horizontal pixel coordinates of the profile of the vertical plane curve, x 1,x2,x3...xn...xm represents the horizontal coordinates of all pixels, m represents the number of coordinate points of all pixels, f '1 (x) represents the function value of the derivative function corresponding to the position x i, and x n is the point where f' 1 (x) =0.
It will be appreciated that by calculating the difference in derivatives on both sides of the corrugated board and comparing the calculated difference with the preset range of derivative values, the reason for determining whether the board is an L-board or a non-L-board is that the L-board has a significant slope change at the bend (i.e., the corner of the L) but the non-L-board does not have such a feature.
The difference in derivatives on both sides of the corrugated board is calculated, i.e. the derivatives (slopes) are calculated on both sides of the suspected L-shaped region of the corrugated board, i.e. the region where corners may be present, respectively. The difference in the derivatives of these two sides is then calculated. This difference reflects the degree of change in slope in this region.
In this embodiment, before the actual production, the corrugated board is subjected to test production, and after the test production is completed, the difference values of the derivatives at the two sides of the non-L-shaped board are taken as the maximum value of the preset range values of the derivatives during the test production, and the difference values of the derivatives at the two sides of the L-shaped board are taken as the minimum value of the preset range values of the derivatives during the test production.
In the present embodiment, in step S102, when the type of the produced board is a non-L-shaped board, the warp convexity of the produced board is calculated based on the vertical plane curve profile image, including:
When the type of the produced paperboard is non-L-shaped paperboard, carrying out data fitting based on the profile image of the vertical plane curve to obtain a unitary quadratic function of the transverse pixel coordinate of the profile of the vertical plane curve and the longitudinal pixel coordinate of the profile of the vertical plane curve, wherein the unitary quadratic function relation is as follows:
f(x)=ax2+bx+c
Wherein x represents the transverse pixel coordinate of the profile of the vertical plane curve, f (x) represents the longitudinal pixel coordinate of the profile of the vertical plane curve corresponding to the x position, and a, b and c represent constants;
Where K (x) is an average value of curvature at a position where three quarters are located, f '(x) represents a slope, f' (x) is a derivative of a profile of a vertical plane curve, f '(x) represents a rate of change of curvature, f' (x) is a second derivative of the profile of the vertical plane curve, x a and x b respectively represent pixel coordinates at positions where two end points of a lateral pixel coordinate of a unitary quadratic function are located, and x 1、x2、x3 respectively represent pixel coordinates at positions where three quarters of the lateral pixel coordinate of the unitary quadratic function are located, respectively:
in the embodiment, in step S103, the method for determining the warp convexity preset range value specifically comprises the steps of collecting cross-sectional images of non-L-shaped paperboards with different warp directions and warp degrees as samples, identifying the warp directions and warp degrees of the samples, classifying the samples according to different warp types to obtain classification results, establishing sub-image libraries corresponding to different warp types and warp levels according to the classification results, calculating the warp convexity of each sample of each sub-image library one by one, and determining the warp convexity range value of the warp type and warp level corresponding to each sub-image library according to the minimum value and the maximum value of the warp convexity of each sub-image library sample.
It can be understood that the method for calculating the warp convexity of each sample of each sub-image library may be the method for calculating the warp convexity θ as described above, which is not described herein.
Illustratively, when identifying the warp direction and warp degree of a sample and classifying the sample according to different warp types and warp levels to obtain classification results, the classification results formed include up-type 1, up-type 2, up-type 3, down-type 1, down-type 2, down-type 3, and then six sub-image libraries are built according to the classification results, each image library corresponds to up-type 1, up-type 2, up-type 3, down-type 1, down-type 2, down-type 3, and then the warp convexity of each sample of the six sub-image libraries is calculated one by one, and then up-type 1, up-type 2, up-type 3, down-type 1, down-type 2, down-type 3 warp convexity range values are determined, including determining the warp convexity range values corresponding to up-type 1 according to the minimum and maximum values of the warp convexities of the samples of the image libraries corresponding to up-type 1Determining the warping convexity range value corresponding to the upwarp-type 2 according to the minimum value and the maximum value of the warping convexity of the sample of the upwarp-type 2 corresponding image libraryDetermining the warping convexity range value corresponding to the upwarp-type 3 according to the minimum value and the maximum value of the warping convexity of the sample of the upwarp-type 3 corresponding image libraryDetermining a warping convexity range value corresponding to the downward warping type 1 according to the minimum value and the maximum value of the warping convexity of the sample of the downward warping type 1 corresponding image libraryDetermining a warping convexity range value corresponding to the downward warping type 2 according to the minimum value and the maximum value of the warping convexity of the sample of the downward warping type 2 corresponding image libraryDetermining a warping convexity range value corresponding to the downward warping type 3 according to the minimum value and the maximum value of the warping convexity of the sample of the downward warping type 3 corresponding image library
In the present embodiment, the warp preset threshold isIf the absolute value of the warp convexity is not greater thanAnd judging that the quality of the produced paperboard is qualified.
9. In the embodiment, in step S104, the warp type of the production board is input into a pre-trained neural network model to obtain production line control parameters output by the pre-trained neural network model, the production line control parameters are output to a production line control center to adjust and control the quality of the board, specifically, an input-output data set is built through the warp type or warp degree of the board recorded on a corrugated board production line and the production line quality control parameters, the input-output data set is trained by adopting the neural network model to obtain the pre-trained neural network model, the pre-trained neural network model is built with a corresponding relation between the warp type of the production line board and the production line control parameters, the warp type of the production board is input into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and the production line control parameters are output to the production line control center to adjust and control the quality of the board.
In this embodiment, different warp types correspond to different production line control parameters, and the correspondence between the warp types and the production line control parameters is learned through a pre-trained neural network model and fed back to a production line control center through prediction to control the product quality.
In this embodiment, the neural network model adopts a convolutional neural network model, and the neural network model includes an input layer, a hidden layer, and an output layer, where the input layer receives a warp type of the board as an input feature. The hidden layer contains multiple layers of neurons for extracting useful information in the input features and learning complex relationships between warp types and line control parameters. The output layer outputs the predicted line control parameters.
Before training the neural network model, an input and output data set is established through the paperboard warping type or warping degree recorded on the corrugated paperboard production line and quality control parameters (such as temperature, pressure, speed and the like) of the production line, and preprocessing operations such as cleaning, normalization and the like are performed on collected data so as to ensure the quality and consistency of the data.
In this embodiment, the neural network model is trained using the pre-processed paperboard production data to obtain a pre-trained neural network model. During the training process, the model learns the correspondence between different warp types and the line control parameters and adjusts its internal parameters (e.g., weights and offsets) to minimize the prediction error.
Alternatively, new data may be continuously collected and the neural network model continuously optimized and updated as the production process proceeds. The method can be realized by incremental learning, transfer learning and other methods so as to improve the prediction performance and adaptability of the model.
In this embodiment, the predicted line control parameters are fed back to the line control center in real time, and the line control center adjusts the operation of the line, such as temperature, pressure, speed, etc., according to these parameters, so as to achieve accurate control over the quality of the board.
The embodiment provides a warp classification and process control method for a tile line outlet paperboard, which is used for intelligently judging the type of the paperboard and calculating warp convexity by accurately collecting a contour image of a vertical plane curve of the paperboard, so that the quality of the paperboard is rapidly and accurately evaluated, when a warp problem is found, the warp type can be automatically classified, and targeted production line control parameters are output according to a pre-trained neural network model, so that the production is timely adjusted, the quality stability of the paperboard is ensured, and the overall production efficiency and the intelligent management level are improved.
The above describes a method for classifying and controlling the warpage of a corrugated board for export, and the following describes an apparatus for implementing the method for classifying and controlling the warpage of a corrugated board for export, referring to fig. 2, and an implementation of the system for classifying and controlling the warpage of a corrugated board for export, according to the embodiment of the present invention includes:
the acquisition module 201 is configured to acquire a profile image of a vertical plane curve of the produced paperboard by using the line structure light sensor, and determine a paperboard type of the produced paperboard according to the profile image of the vertical plane curve;
a calculation module 202 for calculating a warp convexity of the produced board based on the vertical plane curve profile image when the type of the produced board is a non-L-shaped board;
The judging module 203 is configured to judge that the quality of the produced paperboard is qualified when the absolute value of the warp convexity is not greater than a warp preset threshold, and determine and output a warp type of the produced paperboard according to the value of the warp convexity and the warp convexity preset range value corresponding to different warp types when the absolute value of the warp convexity is greater than the warp preset threshold;
the control parameter output module 204 is configured to input the warp type of the produced board into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and output the production line control parameters to the production line control center for adjusting and controlling the quality of the board.
In the embodiment, through accurately collecting the vertical plane curve outline image of the paperboard, the paperboard type is intelligently judged and the warping convexity is calculated, so that the paperboard quality is rapidly and accurately evaluated, when the warping problem is found, the warping type can be automatically classified, and the targeted production line control parameters are output according to the pre-trained neural network model, so that the production is timely adjusted, the paperboard quality is ensured to be stable, and the overall production efficiency and the intelligent management level are improved. .
The construction of the tile line outlet board warp classification and process control system shown in fig. 2 is not limiting of the tile line outlet board warp classification and process control system, and the steps of the tile line outlet board warp classification and process control method provided by the above method embodiments may be implemented.
The above figure 2 describes the tile wire exit board warp classification and process control system of the embodiments of the present invention in detail from the point of view of the modular functional entity, and the below describes the tile wire exit board warp classification and process control device of the embodiments of the present invention in detail from the point of view of the hardware processing.
FIG. 3 is a schematic diagram of a construction of a tile line outlet board warp classification and process control device 300, which may vary widely in configuration or performance, and may include one or more processors (central processing units, CPU) 310 (e.g., one or more processors) and memory 320, one or more storage mediums 330 (e.g., one or more mass storage devices) storing applications 333 or data 332, according to an embodiment of the present invention. Wherein memory 320 and storage medium 330 may be transitory or persistent storage. The program stored on the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations in the device 300. Still further, the processor 310 may be configured to communicate with a storage medium 330 in which a series of instruction operations are performed on the device 300.
The device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input/output interfaces 360, and/or one or more operating systems 331, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
While the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that the foregoing embodiments may be modified or equivalents may be substituted for some of the features thereof, and that the modifications or substitutions do not depart from the spirit and scope of the embodiments of the invention.

Claims (10)

1.一种瓦线出口纸板翘曲分类与过程控制方法，其特征在于，所述瓦线出口纸板翘曲分类与过程控制方法包括：1. A method for classifying and controlling the warping of cardboard at the export of a corrugator line, characterized in that the method comprises: 使用线结构光传感器采集生产纸板的垂直面曲线轮廓图像，并根据所述垂直面曲线轮廓图像判断生产纸板的纸板类型；Using a line structured light sensor to collect a vertical surface curve profile image of the produced cardboard, and judging the cardboard type of the produced cardboard according to the vertical surface curve profile image; 当生产纸板的类型为非L型纸板时，基于垂直面曲线轮廓图像计算生产纸板的翘曲凸度；When the type of the produced cardboard is non-L-shaped cardboard, the warping convexity of the produced cardboard is calculated based on the vertical surface curve profile image; 若翘曲凸度的绝对值不大于翘曲预设阈值，则判定生产纸板质量合格，若翘曲凸度的绝对值大于翘曲预设阈值时，则根据翘曲凸度的值与不同翘曲类型所对应的翘曲凸度预设范围值来确定并输出生产纸板的翘曲类型；If the absolute value of the warping convexity is not greater than the preset warping threshold, the quality of the produced paperboard is determined to be qualified. If the absolute value of the warping convexity is greater than the preset warping threshold, the warping type of the produced paperboard is determined and output according to the value of the warping convexity and the preset range of the warping convexity corresponding to different warping types; 将生产纸板的翘曲类型输入预训练的神经网络模型以获取预训练的神经网络模型输出的生产线控制参数，并将生产线控制参数输出给生产线控制中心进行调整控制纸板质量。The warping type of the produced cardboard is input into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and the production line control parameters are output to the production line control center for adjustment to control the cardboard quality. 2.根据权利要求1所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，所述使用线结构光传感器采集生产纸板的垂直面曲线轮廓图像，并根据所述垂直面曲线轮廓图像判断生产纸板的纸板类型，包括：2. The method for warping classification and process control of corrugated board export according to claim 1, characterized in that the vertical surface curve profile image of the produced board is collected by using a line structured light sensor, and the board type of the produced board is determined according to the vertical surface curve profile image, comprising: 使用线结构光传感器多次采集生产纸板的垂直面反射光图像，并对采集的垂直面反射光图像进行预处理，得到多个预处理图像；A line structured light sensor is used to collect vertical surface reflected light images of the production cardboard for multiple times, and the collected vertical surface reflected light images are preprocessed to obtain multiple preprocessed images; 从多个预处理图像中提取并整合得到生产纸板的垂直面曲线轮廓图像；Extract and integrate the vertical surface curve profile image of the produced paperboard from multiple pre-processed images; 根据提取的垂直面曲线轮廓图像进行数据拟合以获取曲线轮廓横向像素坐标-曲线轮廓纵向像素坐标的一元三次函数；Perform data fitting based on the extracted vertical surface curve profile image to obtain a univariate cubic function of the curve profile transverse pixel coordinates-curve profile longitudinal pixel coordinates; 计算所述一元三次函数的极值点个数，当所述一元三次函数的极值点个数为0时，判定生产纸板为正常纸板，当所述一元三次函数的极值点个数为1时，判定生产纸板为非S型纸板，当所述一元三次函数的极值点个数为2时，判定生产纸板为S型纸板，并发出警报提醒工作人员；Calculate the number of extreme value points of the univariate cubic function. When the number of extreme value points of the univariate cubic function is 0, determine that the produced cardboard is a normal cardboard. When the number of extreme value points of the univariate cubic function is 1, determine that the produced cardboard is a non-S-shaped cardboard. When the number of extreme value points of the univariate cubic function is 2, determine that the produced cardboard is an S-shaped cardboard, and issue an alarm to remind the staff; 当生产纸板为非S型纸板时，基于所述一元三次函数计算生产纸板两侧导数的差值；When the production paperboard is a non-S-shaped paperboard, the difference of the derivatives on both sides of the production paperboard is calculated based on the univariate cubic function; 当差值超过导数预设范围值时，则判定生产纸板为L型纸板，并发出警报提醒，反之，则判定生产纸板为非L型纸板。When the difference exceeds the preset range of the derivative, the produced cardboard is determined to be an L-shaped cardboard and an alarm is issued. Otherwise, the produced cardboard is determined to be a non-L-shaped cardboard. 3.根据权利要求2所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，使用结构光传感器多次采集生产纸板的垂直面反射光图像，并对采集的垂直面反射光图像进行预处理，得到多个预处理图像，包括：3. The method for warping classification and process control of cardboard at the exit of a corrugated line according to claim 2 is characterized in that a structured light sensor is used to collect vertical surface reflected light images of the production cardboard for multiple times, and the collected vertical surface reflected light images are preprocessed to obtain multiple preprocessed images, including: 将结构光投射到生产纸板的垂直面；Projecting structured light onto the vertical surface of the production board; 使用结构光传感器多次采集生产纸板的垂直面反射光图像；Use a structured light sensor to collect reflected light images of the vertical surface of the production cardboard multiple times; 对采集的垂直面反射光图像进行预处理，得到多个预处理图像。The collected vertical surface reflected light images are preprocessed to obtain a plurality of preprocessed images. 4.根据权利要求3所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，从多个预处理图像中提取并整合得到生产纸板的垂直面曲线轮廓图像，包括：4. The method for warping classification and process control of corrugated board export according to claim 3 is characterized in that the vertical surface curve profile image of the production board is extracted and integrated from a plurality of pre-processed images, comprising: 提取多个预处理图像中的光条纹，得到多组光条纹；Extracting light streaks from a plurality of preprocessed images to obtain a plurality of groups of light streaks; 利用相机标定参数，将每组光条纹的位置映射到空间三维坐标；Using the camera calibration parameters, the position of each group of light fringes is mapped to three-dimensional spatial coordinates; 对多组光条纹的空间三维坐标进行转换和对齐后融合得到生产纸板的垂直面三维轮廓；The spatial three-dimensional coordinates of multiple groups of light stripes are transformed and aligned and then fused to obtain the three-dimensional contour of the vertical surface of the production cardboard; 对生产纸板的垂直面三维轮廓进行处理，得到生产纸板的垂直面曲线轮廓图像。The three-dimensional contour of the vertical surface of the produced cardboard is processed to obtain a vertical surface curve contour image of the produced cardboard. 5.根据权利要求2所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，曲线轮廓横向像素坐标-曲线轮廓纵向像素坐标的一元三次函数表示为：5. The method for warping classification and process control of corrugated board export according to claim 2, characterized in that the cubic function of the horizontal pixel coordinate of the curve profile - the vertical pixel coordinate of the curve profile is expressed as: f1(x)＝a1x3+b1x2+c1x+df 1 (x)＝a 1 x 3 +b 1 x 2 +c 1 x+d 式中，x表示垂直面曲线轮廓的横向像素坐标，f1(x)表示对应位置的垂直面曲线轮廓的纵向像素坐标，a1、b1、c1和d表示拟合常数。Wherein, x represents the horizontal pixel coordinate of the vertical surface curve profile, f 1 (x) represents the vertical pixel coordinate of the vertical surface curve profile at the corresponding position, and a 1 , b 1 , c 1 and d represent fitting constants. 6.根据权利要求5所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，所述生产纸板两侧导数的差值δ表示为：6. The warpage classification and process control method for corrugated board export according to claim 5, characterized in that the difference δ between the derivatives on both sides of the production board is expressed as: 式中，xi表示垂直面曲线轮廓的横向像素坐标，x1,x2,x3...xn...xm为所有像素横坐标，m表示所有像素坐标点的个数，f1′(x)表示导函数对应xi位置的函数值，xn为令f1′(x)＝0的点。Wherein, xi represents the horizontal pixel coordinates of the vertical surface curve profile, x1 , x2 , x3 ... xn ... xm are the horizontal coordinates of all pixels, m represents the number of all pixel coordinate points, f1 ′(x) represents the function value of the derivative function corresponding to the position xi , and xn is the point where f1 ′(x)＝0. 7.根据权利要求1所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，当生产纸板的类型为非L型纸板时，基于垂直面曲线轮廓图像计算生产纸板的翘曲凸度，包括：7. The method for warping classification and process control of corrugated board export according to claim 1, characterized in that when the type of the produced board is non-L-shaped board, the warping convexity of the produced board is calculated based on the vertical surface curve profile image, comprising: 当生产纸板的类型为非L型纸板时，基于垂直面曲线轮廓图像进行数据拟合以获取垂直面曲线轮廓横向像素坐标-垂直面曲线轮廓纵向像素坐标的一元二次函数，所述一元二次函数关系式为：When the type of paperboard produced is non-L-shaped paperboard, data fitting is performed based on the vertical surface curve profile image to obtain a one-dimensional quadratic function of the vertical surface curve profile transverse pixel coordinates-vertical surface curve profile longitudinal pixel coordinates, and the one-dimensional quadratic function relationship is: f(x)＝ax2+bx+cf(x)＝ax 2 +bx+c 式中，x表示垂直面曲线轮廓的横向像素坐标，f(x)表示对应x位置的垂直面曲线轮廓的纵向像素坐标，a、b、c表示常数；Where x represents the horizontal pixel coordinate of the vertical surface curve profile, f(x) represents the vertical pixel coordinate of the vertical surface curve profile corresponding to the x position, and a, b, and c represent constants; 根据所述一元二次函数，采用以下公式计算得到与生产纸板对应的翘曲凸度θ，翘曲凸度θ表示为：According to the quadratic function, the warping convexity θ corresponding to the produced paperboard is calculated using the following formula, and the warping convexity θ is expressed as: 式中，K(x)为三个四等分点所在位置曲率的平均值，f′(x)表示斜率，f′(x)为垂直面曲线轮廓的导数，f″(x)表示曲率的变化率，f″(x)为垂直面曲线轮廓的二阶导数，xa和xb分别表示一元二次函数的横向像素坐标的两个端点所在位置的像素坐标，x1、x2、x3分别表示一元二次函数的横向像素坐标的三个四等分点所在位置的像素坐标，分别为：Wherein, K(x) is the average value of the curvature at the three quarter-division points, f′(x) represents the slope, f′(x) is the derivative of the vertical surface curve profile, f″(x) represents the rate of change of the curvature, f″(x) is the second-order derivative of the vertical surface curve profile, xa and xb represent the pixel coordinates of the two endpoints of the horizontal pixel coordinates of the one-variable quadratic function, and x1 , x2 , and x3 represent the pixel coordinates of the three quarter-division points of the horizontal pixel coordinates of the one-variable quadratic function, respectively: 8.根据权利要求1所述的瓦线出口纸板翘曲分类与过程控制方法，其特征在于，所述将生产纸板的翘曲类型输入预训练的神经网络模型以获取预训练的神经网络模型输出的生产线控制参数，并将生产线控制参数输出给生产线控制中心进行调整控制纸板质量，包括：8. The method for warping classification and process control of cardboard at the exit of a corrugator line according to claim 1 is characterized in that the warping type of the produced cardboard is input into a pre-trained neural network model to obtain production line control parameters output by the pre-trained neural network model, and the production line control parameters are output to a production line control center for adjustment to control the quality of the cardboard, comprising: 通过瓦楞纸板生产线上记录的纸板翘曲类型或者翘曲度和生产线质量控制参数，建立输入输出数据集，采用神经网络模型对输入输出数据集进行训练，得到预训练的神经网络模型，预训练的神经网络模型建立有生产线纸板翘曲类型与生产线控制参数之间的对应关系；An input-output data set is established through the cardboard warping type or warping degree recorded on the corrugated cardboard production line and the production line quality control parameters, and the input-output data set is trained using a neural network model to obtain a pre-trained neural network model. The pre-trained neural network model establishes a corresponding relationship between the cardboard warping type of the production line and the production line control parameters; 将生产纸板的翘曲类型输入预训练的神经网络模型以获取预训练的神经网络模型输出的生产线控制参数；Inputting the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model; 将生产线控制参数输出给生产线控制中心进行调整控制纸板质量。The production line control parameters are output to the production line control center for adjustment to control the cardboard quality. 9.一种瓦线出口纸板翘曲分类与过程控制系统，其特征在于，包括：9. A corrugator line export cardboard warping classification and process control system, characterized by comprising: 采集模块，用于采集生产纸板的垂直面曲线轮廓图像，并根据所述垂直面曲线轮廓图像判断生产纸板的纸板类型；A collection module, used for collecting a vertical surface curve profile image of the production paperboard, and judging the paperboard type of the production paperboard according to the vertical surface curve profile image; 计算模块，用于当生产纸板的类型为非L型纸板时，基于垂直面曲线轮廓图像计算生产纸板的翘曲凸度；A calculation module, used for calculating the warping convexity of the produced paperboard based on the vertical surface curve profile image when the type of the produced paperboard is non-L-shaped paperboard; 判断模块，用于当翘曲凸度的绝对值不大于翘曲预设阈值，判定生产纸板质量合格，当翘曲凸度的绝对值大于翘曲预设阈值时，则根据翘曲凸度的值与不同翘曲类型所对应的翘曲凸度预设范围值来确定并输出生产纸板的翘曲类型；A judgment module is used to judge that the quality of the produced paperboard is qualified when the absolute value of the warping convexity is not greater than the preset warping threshold value, and to determine and output the warping type of the produced paperboard according to the value of the warping convexity and the preset range value of the warping convexity corresponding to different warping types when the absolute value of the warping convexity is greater than the preset warping threshold value; 过程控制模块，用于将生产纸板的翘曲类型输入预训练的神经网络模型以获取预训练的神经网络模型输出的生产线控制参数，并将生产线控制参数输出给生产线控制中心进行调整控制纸板质量。The process control module is used to input the warping type of the produced cardboard into the pre-trained neural network model to obtain the production line control parameters output by the pre-trained neural network model, and output the production line control parameters to the production line control center for adjustment to control the quality of the cardboard. 10.一种瓦线出口纸板翘曲分类与过程控制设备，其特征在于，包括存储器和至少一个处理器，所述存储器中存储有计算机可读指令；10. A corrugator line export paperboard warping classification and process control device, characterized in that it includes a memory and at least one processor, wherein the memory stores computer-readable instructions; 所述至少一个处理器调用所述存储器中的所述计算机可读指令，以执行如权利要求1-7中任一项所述瓦线出口纸板翘曲分类与过程控制方法的各个步骤。The at least one processor calls the computer-readable instructions in the memory to execute the various steps of the corrugator line outlet cardboard warping classification and process control method as claimed in any one of claims 1-7.
CN202411552933.1A 2024-11-01 2024-11-01 Warp classification and process control method, system and equipment for tile line outlet paperboard Pending CN119610795A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411552933.1A CN119610795A (en) 2024-11-01 2024-11-01 Warp classification and process control method, system and equipment for tile line outlet paperboard

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411552933.1A CN119610795A (en) 2024-11-01 2024-11-01 Warp classification and process control method, system and equipment for tile line outlet paperboard

Publications (1)

Publication Number Publication Date
CN119610795A true CN119610795A (en) 2025-03-14

Family

ID=94901125

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411552933.1A Pending CN119610795A (en) 2024-11-01 2024-11-01 Warp classification and process control method, system and equipment for tile line outlet paperboard

Country Status (1)

Country Link
CN (1) CN119610795A (en)

Similar Documents

Publication Publication Date Title
EP2843590B1 (en) System and method for package dimensioning
Cheng et al. Vision-based online process control in manufacturing applications
JP6749655B1 (en) Inspection device, abnormality detection method, computer program, learning model generation method, and learning model
US20130322733A1 (en) System for detection of non-uniformities in web-based materials
US20130208978A1 (en) Continuous charting of non-uniformity severity for detecting variability in web-based materials
US9031312B2 (en) Rapid processing and detection of non-uniformities in web-based materials
Zellinger et al. Multi-source transfer learning of time series in cyclical manufacturing
CN113239862A (en) Commodity identification method and device based on artificial intelligence
Sun et al. Embedded spectral descriptors: learning the point-wise correspondence metric via Siamese neural networks
CN118736724A (en) Smart vending machine status online monitoring and management system
CN118587223A (en) Textile defect detection method based on image processing
CN118808079A (en) A dispensing control system for intelligent conversion of visual templates and processing trajectories
Lins et al. Vision-based measurement for quality control inspection in the context of Industry 4.0: a comprehensive review and design challenges
Bründl et al. Semantic part segmentation of spatial features via geometric deep learning for automated control cabinet assembly
CN119610795A (en) Warp classification and process control method, system and equipment for tile line outlet paperboard
Wu et al. A measurement method of free-form tube based on multi-view vision for industrial assembly
CN118458461A (en) Article deviation correcting method and deviation correcting device
Di Angelo et al. C1 continuities detection in triangular meshes
CN114140409B (en) Online recognition method for warping degree of paperboard at outlet of paperboard production line
CN116883404B (en) Label attaching effect detection method for food production package
CN114238679B (en) A method for constructing a warped cardboard template library for a cardboard production line
Mak et al. Objective Evaluation of Seam Pucker on Textiles by Using Self-Organizing Map.
CN116416610A (en) Automatic 3D target component identification and analysis method and system
CN120268669A (en) A method, system, device and storage medium for parts sorting based on AR glasses
CN119794617B (en) Intelligent cutting device and cutting method for titanium alloy structural parts

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