High-precision plastic pelletizing equipment control method and system capable of automatically rectifying deviation

Abstract

The invention relates to the technical field of plastic particle cutting control, and discloses a high-precision plastic particle cutting equipment control method and system capable of automatically rectifying deviation, and the method comprises the following steps: obtaining a to-be-cut material image, a projection line image and the cutting amount of the current cutting stage; calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data; performing image preprocessing on the to-be-cut material image to obtain an initial sectional area of the to-be-cut material and a corresponding sectional image coordinate; calculating the optimal section coordinate of each to-be-cut material section according to the initial section area and the section image coordinate, and adjusting the initial section area according to the optimal section coordinate to obtain the section area of the to-be-cut material; performing least square fitting on the sectional area of the to-be-cut material and the coordinates of the sectional image to obtain an optimal sectional area; the optimal sectional area is substituted into a preset cutting speed formula to calculate cutting speed data, and the optimal cutting speed is obtained; and the cutting device is controlled to conduct cutting work according to the interval data, the optimal cutting speed and the optimal cutting amount.

Description

Technical Field

[0001] The invention relates to the technical field of plastic particle cutting control, and in particular to a control method and system for high-precision plastic particle cutting equipment with automatic deviation correction. Background Art

[0002] In the production process of plastic products, polymer raw materials usually need to go through a series of processing steps, including melting, extrusion molding and final product cutting. Among them, the plastic pelletizer is responsible for accurately cutting the long strip or sheet plastic material formed by the extruder or calender into particles or segments for subsequent processing or direct use. Since plastic materials have high viscosity and elastic recovery characteristics in the molten state, it is easy to have inconsistent sizes during the cutting process. In addition, with the continuous improvement of the industry's requirements for product quality, the requirements for the regularity of the shape and uniformity of the size of plastic particles are becoming increasingly stringent. However, existing plastic particle pelletizing equipment often finds it difficult to meet these high standards, especially when dealing with polymers of different types and characteristics. This low precision not only affects the quality of the product, but also leads to problems in the downstream processing process, such as poor filling during injection molding, product surface defects, etc., which in turn increases the scrap rate. Therefore, how to improve the working efficiency and cutting accuracy of plastic particle pelletizing equipment has become one of the technical problems that need to be solved in the industry.

[0003] In traditional plastic pelletizing technology, first, the polymer raw materials are fed into an extruder, where they are subjected to high temperature and pressure and transformed into a molten state. Subsequently, the molten polymer is extruded through the die of the extruder to form the desired long strip or sheet structure. During the extrusion process, the extrudate will directly enter a water cooling tank or other cooling device for rapid cooling for preliminary cooling, so that the extrudate maintains a certain hardness but is still soft. As the extrudate reaches the appropriate length or thickness, it will be guided to the working area of ​​the pelletizer. Here, the traditional method is to use rotating knives to continuously cut the moving extrudate. These knives are mounted on a high-speed rotating turntable and are arranged at a certain angle to the extrusion direction, so that each cut can produce relatively regular small plastic pellets. After cutting, the small plastic pellets fall into a collection container.

[0004] Although traditional pelletizing technology can meet the primary requirements of most industrial production, pelletizers are mainly cut through manual control. When faced with polymer materials of different types or characteristics, it is difficult to accurately adjust the cutting parameters in real time due to manual operation, which leads to dimensional inconsistency problems during high-speed production, thus affecting the accuracy of pelletizing. Summary of the invention

[0005] The invention provides a control method and system for high-precision plastic pelletizing equipment with automatic deviation correction, so as to avoid errors existing in human control and improve the pelletizing accuracy.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a high-precision plastic pelletizing equipment control method with automatic deviation correction, comprising:

[0007] Obtain the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage;

[0008] Calculate the distance between adjacent projection lines according to the projection line image to obtain spacing data;

[0009] Performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates;

[0010] Calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut;

[0011] Performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area;

[0012] Substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain an optimal cutting speed;

[0013] The cutting device is controlled to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

[0014] In an optional implementation, calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data includes:

[0015] The distance between adjacent projection lines is calculated using the following formula:

[0016]

[0017] Among them, Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, (x i ,y i ) represents the center position of the i-th projection line, (x i+1 ,y i+1 ) represents the center position of the i+1th projection line.

[0018] In an optional implementation, the performing image preprocessing on the image of the material to be cut to obtain the initial cross-sectional area of ​​the material to be cut and the corresponding cross-sectional image coordinates includes:

[0019] grayscale the image of the material to be cut to obtain a grayscale image;

[0020] Performing mean filtering on the grayscale image to obtain a filtered image;

[0021] Performing threshold segmentation processing on the filtered image to obtain a segmented image;

[0022] Marking connected components of the segmented image to obtain a marked image;

[0023] Performing closed contour extraction on the marked image to obtain a contour extraction result;

[0024] Morphological analysis is performed on the contour extraction result to obtain different initial cross-sectional areas and corresponding cross-sectional image coordinates.

[0025] In an optional implementation, the calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut includes:

[0026] Selecting the maximum initial cross-sectional area among the initial cross-sectional areas as the origin cross-sectional area;

[0027] Taking the cross-sectional image coordinates corresponding to the origin cross-sectional area as the coordinate origin;

[0028] Calculating the difference between the origin cross-sectional area and each of the initial cross-sectional areas to obtain difference data;

[0029] Calculate the gradient of the area change between two adjacent cross sections according to the difference data to obtain gradient data;

[0030] Selecting the cross-sectional image coordinates corresponding to the maximum value in the gradient data as the optimal cross-sectional coordinates;

[0031] Calculating the distance between the optimal cross-sectional coordinates and each cross-sectional image coordinate to obtain distance data;

[0032] Adjust the initial cross-sectional area according to the distance data to obtain the cross-sectional area of ​​the material to be cut;

[0033] Among them, the cross-sectional area of ​​the material to be cut is calculated by the following formula:

[0034]

[0035]

[0036] Among them, A′ i A represents the cross-sectional area of ​​the material to be cut at the i-th section. i represents the initial cross-sectional area of ​​the i-th section, di represents the distance from the i-th section image coordinates to the optimal section coordinates, σ represents the standard deviation of the distance, and μ represents the mean distance.

[0037] In an optional implementation, performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain the optimal cross-sectional area includes:

[0038] Establish a mathematical model of the relationship between the cross-sectional area of ​​the material to be cut and the coordinates of the cross-sectional image;

[0039] Calculate the sum of squares of the cross-sectional area of ​​the material to be cut and the cross-sectional area predicted by the model according to the relational mathematical model;

[0040] Solving the optimal parameters of the relationship mathematical model by Levenberg-Marquardt algorithm according to the sum of squared errors;

[0041] Determining an optimal mathematical model according to the optimal parameters, and calculating an optimal cross-sectional area according to the optimal mathematical model;

[0042] Among them, the relationship mathematical model is as follows:

[0043] A(x,y)=a0+a1x+a2y 2

[0044] The optimal cross-sectional area is calculated by the following formula:

[0045]

[0046] Where A(x, y) represents the predicted cross-sectional area, a0, a1 and a2 represent the parameters to be determined, (x, y) represents the cross-sectional image coordinates, and x max Indicates the maximum value of the x-axis direction in the cross-sectional image coordinates, x min Indicates the minimum value of the x-axis direction in the cross-sectional image coordinates, A opt Indicates the optimal cross-sectional area.

[0047] In an optional implementation, substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain the optimal cutting speed includes:

[0048] The cutting speed formula is as follows:

[0049] V=H·A opt α ·N β ·E γ

[0050] Among them, V represents the optimal cutting speed, A optrepresents the optimal cross-sectional area, H represents the speed weight adjustment factor, N represents the preset number of cutting wheels, E represents the power supply, and α, β and γ are preset empirical parameters.

[0051] In an optional implementation, controlling the cutting device to perform cutting according to the spacing data, the optimal cutting speed and the cutting amount includes:

[0052] Judging whether adjacent spacing data are equal according to the spacing data, if the adjacent spacing data are equal, it is determined that the sliding direction of the cutting device is correct;

[0053] If the adjacent spacing data are not equal, it is determined that the sliding direction is offset during the cutting process, and the sliding direction is adjusted, and the blade height is adjusted;

[0054] Calculating an estimated cutting time according to the optimal cutting speed and the cutting amount;

[0055] Allocate the cutting preparation phase time and the cutting working phase time according to the estimated cutting time;

[0056] Controlling the cutting device to perform cutting work according to the cutting preparation phase time and the cutting work phase time;

[0057] The blade height to be adjusted is calculated using the following formula:

[0058] Δh=k·(Z i,i+1 -Z i+1,i+2 )

[0059] The estimated cutting time is calculated using the following formula:

[0060]

[0061] Where Δh represents the blade height to be adjusted, k represents the adjustment amount of the blade height converted from the spacing difference, and Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, Z i+1,i+2 represents the distance between the i+1th projection line and the i+2th projection line, t represents the estimated cutting time, Q represents the cutting amount, and V represents the optimal cutting speed.

[0062] In a second aspect, the present invention provides a high-precision plastic pelletizing equipment control system with automatic deviation correction, comprising:

[0063] A data acquisition module is used to acquire the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage;

[0064] A spacing calculation module, used to calculate the distance between adjacent projection lines according to the projection line image to obtain spacing data;

[0065] An image preprocessing module, used for performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates;

[0066] A cross-sectional area calculation module, used to calculate the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjust the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut;

[0067] An optimal area analysis module, used for performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area;

[0068] A cutting speed calculation module, used for substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data and obtain an optimal cutting speed;

[0069] The cutting control module is used to control the cutting device to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

[0070] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for controlling high-precision plastic pelletizing equipment with automatic correction.

[0071] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned automatic deviation correction high-precision plastic pelletizing equipment control methods.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] The present invention discloses a control method for high-precision plastic pelletizing equipment with automatic deviation correction, comprising obtaining an image of a material to be cut, an image of a projection line and a cutting amount in a current cutting stage; calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data; performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates; calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut; performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain the optimal cross-sectional area; substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain the optimal cutting speed; and controlling a cutting device to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount. The present invention analyzes the image of the material to be cut and the projection line, calculates the optimal cross-sectional coordinates and area, optimizes the cross-sectional area using the least squares method, combines the spacing data and the cutting amount, and accurately controls the cutting speed, thereby realizing an efficient and accurate automated process from image processing to cutting execution. Compared with manual operation control, it can adapt to changes in the production process more timely and accurately, effectively reduce the problem of dimensional inconsistency caused by untimely parameter adjustment, avoid errors in human control, and improve the accuracy of pelletizing. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic flow chart of a control method for a high-precision plastic pelletizing equipment with automatic deviation correction provided by the first embodiment of the present invention;

[0075] Figure 2 It is a schematic diagram of the structure of a control system for a high-precision plastic pelletizing equipment with automatic deviation correction provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] Reference Figure 1 The first embodiment of the present invention provides a control method for a high-precision plastic pelletizing equipment with automatic deviation correction, comprising the following steps:

[0078] S11, obtaining the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage;

[0079] S12, calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data;

[0080] S13, performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates;

[0081] S14, calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut;

[0082] S15, performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area;

[0083] S16, substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain an optimal cutting speed;

[0084] S17, controlling the cutting device to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

[0085] In step S11, an image of the material to be cut, a projection line image and a cutting amount in the current cutting stage are obtained.

[0086] The process of acquiring images of the material to be cut relies on image acquisition devices installed on the equipment, such as cameras or industrial cameras. These devices are placed in a position where they can clearly capture the material to be cut so that the complete outline of the material to be cut and its surface features can be captured. When the extruder extrude the molten plastic material in the form of strips or sheets, the image acquisition device triggers the shutter at a specific time point to record the shape of the material at this moment as the image of the material to be cut.

[0087] The projection line image is produced by a laser line projector. This type of equipment can project multiple equally spaced rays of light onto the surface of the material to be cut, forming a series of parallel line segments. The projection formed by the intersection of each projection line with the surface of the material to be cut constitutes part of the projection line image.

[0088] The cutting volume in the current cutting stage is a parameter monitored and recorded by the control system. Before each cutting operation, the system will pre-set the expected cutting length or area. As the cutting process progresses, the actual cutting volume will be updated and stored in real time. In this way, the system can obtain the latest cutting volume data before each new cutting task begins.

[0089] In step S12, the distance between adjacent projection lines is calculated according to the projection line image to obtain spacing data.

[0090] In a specific implementation, calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data includes:

[0091] The distance between adjacent projection lines is calculated using the following formula:

[0092]

[0093] Among them, Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, (x i ,y i ) represents the center position of the i-th projection line, (x i+1 ,y i+1 ) represents the center position of the i+1th projection line.

[0094] Specifically, when the projection line is projected onto the surface of the material to be cut, a series of parallel lines will be formed, which intersect with the surface of the material to be cut, leaving a projection on the image. In order to accurately measure the distance between each pair of adjacent projection lines, it is first necessary to identify and locate the coordinates of the center point of each projection line. This step relies on image processing technology, such as edge detection algorithms or Hough transform methods to determine the position of each projection line. Once the center coordinates of all projection lines are obtained, the formula can be applied Perform distance calculation.

[0095] For any two consecutive projection lines i and i+1, the distance Z between them is i,i+1 It can be regarded as the straight-line distance between the two points in two-dimensional space. This distance is calculated by dividing the horizontal difference (x i+1 -x i ) and the longitudinal difference (y i+1 -y i ) are squared, summed, and then squared. This coordinate-based distance calculation method ensures the accuracy of the result and is applicable to projection line arrangements in any direction.

[0096] In step S13, image preprocessing is performed on the image of the material to be cut to obtain the initial cross-sectional area of ​​the material to be cut and the corresponding cross-sectional image coordinates.

[0097] In a specific implementation, the image preprocessing of the image of the material to be cut to obtain the initial cross-sectional area of ​​the material to be cut and the corresponding cross-sectional image coordinates includes:

[0098] grayscale the image of the material to be cut to obtain a grayscale image;

[0099] Performing mean filtering on the grayscale image to obtain a filtered image;

[0100] Performing threshold segmentation processing on the filtered image to obtain a segmented image;

[0101] Marking connected components of the segmented image to obtain a marked image;

[0102] Performing closed contour extraction on the marked image to obtain a contour extraction result;

[0103] Morphological analysis is performed on the contour extraction result to obtain different initial cross-sectional areas and corresponding cross-sectional image coordinates.

[0104] Specifically, first, the image of the material to be cut is grayed, that is, the color image is converted into a grayscale image. This step uses the weighted average method to convert the color value (RGB) of each pixel into a single grayscale value. The formula is as follows:

[0105] I=0.299R+0.587G+0.114B

[0106] Here, I represents the grayscale value of each pixel in the grayscale image, and R, G, and B represent the red, green, and blue components of the corresponding pixel in the original image, respectively. Through this linear combination method, the data dimension can be effectively reduced while retaining the main features of the image.

[0107] Next, the grayscale image is processed by applying mean filtering. Mean filtering is a simple smoothing technique used to remove noise from an image. Specifically, for each pixel, the average value of all pixel values ​​in its surrounding neighborhood is calculated as the new value of the point. If a window of size m×n is considered, the output f(x,y) after mean filtering can be expressed as:

[0108]

[0109] Where g(x,y) is the grayscale value of the input image at position (x,y), and i and j are the offsets within the window relative to position (x,y). This process helps eliminate random noise and makes subsequent processing more stable and reliable.

[0110] Then, threshold segmentation is performed on the mean-filtered image. Threshold segmentation is to divide the image into two parts, foreground and background, according to the set threshold. Let the threshold be T. For any pixel point p, if p>T, it is classified as foreground (e.g., white), otherwise it is regarded as background (e.g., black). In this way, the target object of interest, i.e., the cross section of the material to be cut, can be highlighted.

[0111] In the process of labeling connected components of the segmented binary image, the system scans the entire image pixel by pixel. For each non-background (i.e. foreground) pixel, if the pixel has not been labeled, a new connected component search is started. The search process uses breadth-first search (BFS) or depth-first search (DFS) to find all pixels connected to it and belonging to the same type starting from the current pixel, and mark these pixels as the same connected component. This means that when encountering an unlabeled foreground pixel, the algorithm recursively visits all adjacent foreground pixels and assigns them the same label. As the scan continues, each independent connected region is uniquely labeled to ensure that the pixels in each connected component are correctly identified. This process ensures that subsequent analysis is only performed on specific connected regions, improving efficiency and reducing the possibility of misjudgment.

[0112] Next, based on the results of connected component labeling, closed contour extraction is further implemented. In order to find the outermost boundary of each connected component, the system checks whether each pixel has at least one neighbor in one direction that belongs to the background pixel. For each connected component, starting from any boundary pixel, trace the boundary in a counterclockwise or clockwise direction until returning to the starting point, thus forming a closed loop. This process ensures that only external contours are selected and internal holes are ignored. Specifically, the system finds any boundary pixel in a connected component as the starting point, and then moves along the boundary step by step, recording the position of each boundary pixel until it reaches the starting point again. In this way, the closed contour of the connected component is constructed.

[0113] Finally, after obtaining closed contours, morphological analysis is used to improve the shapes of these contours. For example, dilation can connect small broken parts; erosion can remove small noise or unwanted small structures. The opening operation is to erode and then dilate, which is used to remove small objects without significantly changing the size of larger objects; the closing operation is to dilate and then erode to fill large holes. Dilation refers to applying a structural element B to the original image A so that when B is translated in the image, as long as any part of B overlaps with A, the translated position will be considered as part of the new image. In contrast, erosion means that the translated position will be retained in the new image only when the structural element B is completely contained in A. Opening and closing operations are the combination of erosion followed by dilation and dilation followed by erosion, respectively.

[0114] By performing the above morphological processing on the closed contour, a smoother cross-sectional contour that conforms to the actual physical properties can be obtained. This step can remove unnecessary details, fill possible holes, and connect disconnected parts, thereby calculating a more accurate initial cross-sectional area and the corresponding cross-sectional image coordinates. Such processing not only improves the quality of the final product, but also optimizes the entire production process.

[0115] In summary, the image preprocessing process not only effectively removes interference factors in the original image, but also accurately locates and describes each cross section of the material to be cut. This method ensures precision control during the cutting process, thereby improving the quality and consistency of plastic pelletizing.

[0116] In step S14, the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut are calculated according to the initial cross-sectional area and the cross-sectional image coordinates, and the initial cross-sectional area is adjusted according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut.

[0117] In a specific implementation, the calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut includes:

[0118] Selecting the maximum initial cross-sectional area among the initial cross-sectional areas as the origin cross-sectional area;

[0119] Taking the cross-sectional image coordinates corresponding to the origin cross-sectional area as the coordinate origin;

[0120] Calculating the difference between the origin cross-sectional area and each of the initial cross-sectional areas to obtain difference data;

[0121] Calculate the gradient of the area change between two adjacent cross sections according to the difference data to obtain gradient data;

[0122] Selecting the cross-sectional image coordinates corresponding to the maximum value in the gradient data as the optimal cross-sectional coordinates;

[0123] Calculating the distance between the optimal cross-sectional coordinates and each cross-sectional image coordinate to obtain distance data;

[0124] Adjust the initial cross-sectional area according to the distance data to obtain the cross-sectional area of ​​the material to be cut;

[0125] Among them, the cross-sectional area of ​​the material to be cut is calculated by the following formula:

[0126]

[0127] Among them, A′ i A represents the cross-sectional area of ​​the material to be cut at the i-th section. i represents the initial cross-sectional area of ​​the i-th section, d i represents the distance from the i-th section image coordinates to the optimal section coordinates, σ represents the standard deviation of the distance, and μ represents the mean distance.

[0128] Specifically, first, the maximum value of all initial cross-sectional areas is selected as the reference point, that is, the origin cross-sectional area. The reason for selecting this maximum cross-sectional area is that it usually represents the maximum expansion state of the material cross section and can be used as a stable reference point. Subsequently, the cross-sectional image coordinates corresponding to the maximum initial cross-sectional area are set as the origin of the coordinate system. The purpose of this is to establish a unified reference frame to facilitate subsequent distance and gradient calculations.

[0129] Next, the system calculates the difference between the origin cross-sectional area and each other initial cross-sectional area to generate a set of difference data. These differences reflect the changes in each cross-sectional area relative to the maximum cross-sectional area. Based on these difference data, the gradient of the area change between two adjacent cross-sectional areas is further calculated to form gradient data. The gradient calculation is achieved by solving the rate of change of the area of ​​adjacent cross-sectional areas, which helps to identify the location where the cross-sectional size changes most significantly. Among all the gradient data, the cross-sectional image coordinates corresponding to the maximum value are selected as the optimal cross-sectional coordinates. This is because the maximum gradient indicates where the cross-sectional shape or size changes sharply, and such a location is often the most suitable for use as a cutting starting point or key control point.

[0130] After determining the optimal cross-sectional coordinates, the next step is to calculate the Euclidean distance between this coordinate and the coordinates of each other cross-sectional image to generate a set of distance data. These distances are used to measure the spatial distribution of each cross section relative to the optimal cross section. In order to adjust the initial cross-sectional area, a Gaussian weighting function is introduced, and its formula is as follows:

[0131]

[0132] Among them, A′ i A represents the cross-sectional area of ​​the material to be cut at the i-th section. i represents the initial cross-sectional area of ​​the i-th section, d i represents the distance from the i-th section image coordinates to the optimal section coordinates, σ represents the standard deviation of the distance, and μ represents the mean distance.

[0133] According to the above formula, each initial cross-sectional area A i Converted into the new cross-sectional area A' of the material to be cut i , an exponential decay factor is applied in this process The farther the cross section is from the optimal cross section, the smaller its area is adjusted. This method not only takes into account the characteristics of each cross section, but also comprehensively considers their spatial relationship relative to the optimal cross section, thereby achieving a more reasonable cross-sectional area adjustment.

[0134] The final cross-sectional area of ​​the material to be cut is A' iIt not only reflects the actual size of the original section, but also incorporates the influence of spatial position, ensuring that the operation of each section during the cutting process is based on the optimal geometric parameters. This processing method not only improves cutting accuracy and reduces material waste, but also enhances the consistency and controllability of the production process. In this way, the system can dynamically adapt to materials of different shapes and sizes, providing a flexible and efficient cutting solution.

[0135] In step S15, the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates are fitted by the least square method to obtain the optimal cross-sectional area.

[0136] In a specific implementation, performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain the optimal cross-sectional area includes:

[0137] Establish a mathematical model of the relationship between the cross-sectional area of ​​the material to be cut and the coordinates of the cross-sectional image;

[0138] Calculate the sum of squares of the cross-sectional area of ​​the material to be cut and the cross-sectional area predicted by the model according to the relational mathematical model;

[0139] Solving the optimal parameters of the relationship mathematical model by Levenberg-Marquardt algorithm according to the sum of squared errors;

[0140] Determining an optimal mathematical model according to the optimal parameters, and calculating an optimal cross-sectional area according to the optimal mathematical model;

[0141] Among them, the relationship mathematical model is as follows:

[0142] A(x,y)=a0+a1x+a2y 2

[0143] The optimal cross-sectional area is calculated by the following formula:

[0144]

[0145] Where A(x, y) represents the predicted cross-sectional area, a0, a1 and a2 represent the parameters to be determined, (x, y) represents the cross-sectional image coordinates, and x max Indicates the maximum value of the x-axis direction in the cross-sectional image coordinates, x min Indicates the minimum value of the x-axis direction in the cross-sectional image coordinates, A opt Indicates the optimal cross-sectional area.

[0146] Specifically, first, a mathematical model of the relationship between the cross-sectional area of ​​the material to be cut and the coordinates of the cross-sectional image is established. A quadratic polynomial model is used as the assumed relationship expression:

[0147] A(x,y)=a0+a1x+a2y 2

[0148] In this formula, A(x, y) represents the predicted cross-sectional area based on the coordinates (x, y); and a0, a1, and a2 are parameters that need to be determined, which determine the specific form of the model. This model was chosen because it is simple and can capture the basic trend of the change of cross-sectional area with position.

[0149] Next, the sum of squares of the errors between the cross-sectional area of ​​the material to be cut and the cross-sectional area predicted by the model is calculated based on the above relationship mathematical model. The sum of squares of the errors is defined as the sum of the squares of the differences between the actual value and the predicted value at all observation points. For each data point (x i ,y i ), the corresponding error e i It can be expressed as:

[0150] e i =A observed (x i ,y i )-A(x i ,y i )

[0151] Among them, A observed (x i ,y i ) is the cross-sectional area actually measured, A(x i ,y i ) is the result predicted by the model. The error sum of squares S is:

[0152]

[0153] In order to minimize this sum of squared errors, the Levenberg-Marquardt algorithm is used to solve the optimal solution for the model parameters a0, a1, and a2. The Levenberg-Marquardt algorithm is an iterative optimization method that combines the advantages of the gradient descent method and the Gauss-Newton method, and is particularly suitable for nonlinear least squares problems. The algorithm gradually reduces the objective function (i.e., the sum of squared errors) by adjusting the parameters until the convergence condition is met or the maximum number of iterations is reached. To achieve this, the Levenberg-Marquardt algorithm combines the characteristics of the gradient descent method and the Gauss-Newton method, calculates the direction of parameter update according to the Jacobian matrix at each iteration, and introduces a damping factor λ to control the step size. The elements of the Jacobian matrix J represent the first-order partial derivatives of the residual with respect to each parameter:

[0154]

[0155] In each iteration, the Levenberg-Marquardt algorithm constructs an augmented Jacobian matrix J T J+λI, where I is the identity matrix and λ is a positive scalar used to adjust the behavior of the algorithm: when λ is close to zero, the behavior of the LM algorithm is similar to the Gauss-Newton method; when λ is large, it is closer to the gradient descent method. The update formula is:

[0156] Δa=-(J T J+λI) -1 J T e

[0157] Here a=[a0,a1,a2] T represents the parameter vector, e=[e1,e2,...,e N ] T Denotes the residual vector. Once the parameter increment Δa is calculated, the parameter value can be updated:

[0158] a new =a old +Δa

[0159] Then, the error sum of squares S is recalculated using the new parameters and compared with the previous value. If the new parameters cause S to decrease, the update is accepted and λ is reduced (for example, multiplied by a coefficient less than 1) so that a larger step size can be taken in the next iteration; conversely, if S increases, the update is rejected and λ is increased, forcing the next iteration to adopt a more conservative approach.

[0160] This process continues until certain convergence criteria are met, such as the parameter changes between consecutive iterations are very small, or the preset maximum number of iterations is reached. Eventually, the Levenberg-Marquardt algorithm will converge to a set of optimal parameters a0, a1, and a2 that enable the model A(x, y) to best fit the given data set, thereby achieving the optimization solution for the model parameters.

[0161] In the whole process, the Levenberg-Marquardt algorithm not only guarantees fast and stable convergence performance, but also can avoid falling into the problem of local minima to a certain extent, because by adjusting λ, a good balance can be found between exploration and stability.

[0162] Once the optimal parameters a0, a1 and a2 are found, the optimal mathematical model is determined. Based on this model, the optimal cross-sectional area A can be calculated. opt , the formula is as follows:

[0163]

[0164] The integral range here is from x min to x max , represents the maximum and minimum values ​​of the x-axis in the cross-sectional image coordinates. This formula calculates the average cross-sectional area along the x-axis. The purpose of this is to comprehensively consider the information on the entire cross-section, rather than relying solely on the data of a single point. The optimal cross-sectional area A obtained in this way opt More stable and representative, it helps guide subsequent cutting operations and ensures that each cut achieves the desired effect.

[0165] In summary, the least squares fitting of the cross-sectional area of ​​the material to be cut and the coordinates of the cross-sectional image can not only accurately depict the change law of the material cross-sectional area, but also provide a scientific basis for determining the optimal cross-sectional area. This method based on mathematical modeling and optimization algorithm enables every decision in the cutting process to be based on reliable data analysis, thereby improving the accuracy and efficiency of the overall production.

[0166] In step S16, the optimal cross-sectional area is substituted into a preset cutting speed formula to calculate cutting speed data to obtain the optimal cutting speed.

[0167] In a specific implementation, substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain the optimal cutting speed includes:

[0168] The cutting speed formula is as follows:

[0169] V=H·A opt α ·N β ·E γ

[0170] Among them, V represents the optimal cutting speed, A opt represents the optimal cross-sectional area, H represents the speed weight adjustment factor, N represents the preset number of cutting wheels, E represents the power supply, and α, β and γ are preset empirical parameters.

[0171] Specifically, the cutting speed formula used is:

[0172] V=H·A opt α ·N β ·E γ

[0173] In this formula, V represents the optimal cutting speed obtained, A optis the optimal cross-sectional area calculated in the previous step, H represents the speed weight adjustment factor, which is used to adjust the proportional relationship of the cutting speed under different conditions, N refers to the preset number of cutting rounds, which reflects the working frequency or number of repetitions of the cutting tool; E is the power supply, which reflects the energy supply intensity of the driving cutting equipment; and α, β and γ are parameters pre-set based on experience to describe the specific degree of influence of each variable on the cutting speed.

[0174] In step S17, the cutting device is controlled to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

[0175] In a specific embodiment, controlling the cutting device to perform cutting according to the spacing data, the optimal cutting speed and the cutting amount includes:

[0176] Judging whether adjacent spacing data are equal according to the spacing data, if the adjacent spacing data are equal, it is determined that the sliding direction of the cutting device is correct;

[0177] If the adjacent spacing data are not equal, it is determined that the sliding direction is offset during the cutting process, and the sliding direction is adjusted, and the blade height is adjusted;

[0178] Calculating an estimated cutting time according to the optimal cutting speed and the cutting amount;

[0179] Allocate the cutting preparation phase time and the cutting working phase time according to the estimated cutting time;

[0180] Controlling the cutting device to perform cutting work according to the cutting preparation phase time and the cutting work phase time;

[0181] The blade height to be adjusted is calculated using the following formula:

[0182] Δh=k·(Z i,i+1 -Z i+1,i+2 )

[0183] The estimated cutting time is calculated using the following formula:

[0184]

[0185] Where Δh represents the blade height to be adjusted, k represents the adjustment amount of the blade height converted from the spacing difference, and Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, Z i+1,i+2 represents the distance between the i+1th projection line and the i+2th projection line, t represents the estimated cutting time, Q represents the cutting amount, and V represents the optimal cutting speed.

[0186] Specifically, first, the system analyzes the spacing data, that is, the distance information between each projection line. By comparing whether the adjacent spacing data are equal, the directional accuracy of the cutting device when it moves along the predetermined trajectory can be determined. If the adjacent spacing data remain consistent, it means that the sliding direction of the cutting device is correct; conversely, if differences are found in the adjacent spacing data, it indicates that an offset in the sliding direction has occurred during the cutting process. At this point, immediate measures need to be taken to correct this deviation, including resetting the sliding direction of the cutting device and adjusting the height of the blade according to actual needs. To achieve this, the following formula is used to calculate the blade height to be adjusted:

[0187] Δh=k·(Z i,i+1 -Z i+1,i+2 )

[0188] Here, Δh represents the blade height change to be adjusted, k is a scaling factor used to convert the spacing difference into the corresponding blade height adjustment value, and Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, Z i+1,i+2 Represents the distance between the i+1th projection line and the i+2th projection line.

[0189] Next, based on the determined optimal cutting speed V and the given cutting volume Q, the system will further calculate the estimated cutting time t, which reflects the total time required to complete the entire cutting operation. The calculation formula for the estimated cutting time is as follows:

[0190]

[0191] Where t represents the estimated cutting time, Q represents the total amount of cutting, and V is the optimal cutting speed calculated in the previous step. This formula directly reflects the relationship between the amount of cutting and the cutting speed: the larger the cutting amount or the lower the cutting speed, the longer it takes.

[0192] After the estimated cutting time is obtained, the next step is to reasonably allocate the time for the cutting preparation phase and the cutting working phase. The preparation phase is mainly used to prepare for various settings before cutting, such as checking the equipment status, calibrating parameters, etc., while the working phase refers to the time period for the actual cutting operation. Reasonable allocation helps to ensure the continuity and stability of the cutting process and avoid unnecessary pauses or delays.

[0193] Finally, according to the above schedule, the control system will accurately command the cutting device to start and execute the cutting task. During the whole process, not only the cutting action is required to be carried out strictly in accordance with the established speed and direction, but also the changes in various parameters need to be continuously monitored and necessary adjustments need to be made in time to ensure that the final cutting result meets the design requirements. In addition, by dynamically adjusting the blade height, a more refined and smoother cutting effect can be achieved on different types of materials, thereby improving the overall quality of the product.

[0194] The following describes the working process of the present invention using a relatively common scenario as an example. Figure 1 , a high-precision plastic pelletizing equipment control method with automatic deviation correction, comprising the following steps:

[0195] In a plastic processing factory, in order to improve product quality and production efficiency, a set of high-precision plastic pelletizing equipment control system with automatic deviation correction was deployed. When preparing for cutting, the system first obtains the image of the plastic strip to be cut and the grid image formed by the laser projection line through the image acquisition device, and reads the specific cutting amount completed in the current cutting stage. The image preprocessing module then analyzes these data, determines the initial cross-sectional area of ​​the plastic strip to be cut and its corresponding cross-sectional image coordinates, and calculates the optimal cross-sectional coordinates based on this, and then adjusts to obtain the precise cross-sectional area to be cut.

[0196] Furthermore, the system determines the optimal cross-sectional area by fitting the cross-sectional area to the cross-sectional image coordinates using the least squares method. Based on this optimal cross-sectional area, the system applies a preset cutting speed formula to calculate the optimal cutting speed suitable for the current material characteristics.

[0197] When entering the actual cutting phase, the system uses the spacing data to verify whether the direction of the cutting device moving along the predetermined trajectory is accurate. If any deviation from the expected path is found, such as inconsistent spacing data, the system will respond immediately, adjust the sliding direction of the cutting device, and fine-tune the height of the blade accordingly to correct possible deviations. At the same time, based on the optimal cutting speed and total cutting volume, the system also calculates the expected cutting time, and reasonably allocates the time for the cutting preparation stage and the working stage to ensure that the entire cutting process is compact and orderly.

[0198] During the entire cutting process, the system continuously monitors changes in key indicators, including but not limited to cutting speed, blade height and position, and dynamically adjusts as needed to ensure that each cut is strictly carried out in accordance with established standards. This not only improves cutting accuracy and reduces the uncertainty caused by human intervention, but also significantly reduces the scrap rate, optimizes the overall production process, and ultimately achieves efficient and stable plastic pellet cutting operations. In this way, even when facing polymer materials of different types or characteristics, a high level of consistency and accuracy can always be maintained, achieving an efficient, precise and automated process from image processing to cutting execution, avoiding errors in human control, and improving pelletizing accuracy.

[0199] Reference Figure 2 The second embodiment of the present invention provides a high-precision plastic pelletizing equipment control system with automatic deviation correction, comprising:

[0200] A data acquisition module is used to acquire the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage;

[0201] A spacing calculation module, used to calculate the distance between adjacent projection lines according to the projection line image to obtain spacing data;

[0202] An image preprocessing module, used for performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates;

[0203] A cross-sectional area calculation module, used to calculate the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjust the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut;

[0204] An optimal area analysis module, used for performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area;

[0205] A cutting speed calculation module, used for substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data and obtain an optimal cutting speed;

[0206] The cutting control module is used to control the cutting device to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

[0207] It should be noted that the automatic deviation-correcting high-precision plastic pelletizing equipment control device provided in an embodiment of the present invention is used to execute all the process steps of the automatic deviation-correcting high-precision plastic pelletizing equipment control method of the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0208] The embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a high-precision plastic pelletizing equipment control program with automatic deviation correction. When the processor executes the computer program, the steps in the above-mentioned embodiments of the high-precision plastic pelletizing equipment control method with automatic deviation correction are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are realized, such as a high-precision plastic pelletizing equipment control module with automatic deviation correction.

[0209] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0210] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0211] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0212] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0213] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0214] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0215] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A control method for high-precision plastic pelletizing equipment with automatic deviation correction, characterized in that: Executed by the controller, including: Obtain the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage; Calculate the distance between adjacent projection lines according to the projection line image to obtain spacing data; Performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates; Calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut; Performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area; Substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain an optimal cutting speed; The cutting device is controlled to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

2. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: The step of calculating the distance between adjacent projection lines according to the projection line image to obtain spacing data includes: The distance between adjacent projection lines is calculated using the following formula: Among them, Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, (x i ,y i ) represents the center coordinate of the i-th projection line, (x i+1 ,y i+1 ) represents the center position coordinates of the i+1th projection line.

3. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: The image preprocessing of the image of the material to be cut to obtain the initial cross-sectional area of ​​the material to be cut and the corresponding cross-sectional image coordinates includes: grayscale the image of the material to be cut to obtain a grayscale image; Performing mean filtering on the grayscale image to obtain a filtered image; Performing threshold segmentation processing on the filtered image to obtain a segmented image; Marking connected components of the segmented image to obtain a marked image; Performing closed contour extraction on the marked image to obtain a contour extraction result; Morphological analysis is performed on the contour extraction result to obtain different initial cross-sectional areas and corresponding cross-sectional image coordinates.

4. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: The step of calculating the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjusting the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut includes: Selecting the maximum initial cross-sectional area among the initial cross-sectional areas as the origin cross-sectional area; Taking the cross-sectional image coordinates corresponding to the origin cross-sectional area as the coordinate origin; Calculating the difference between the origin cross-sectional area and each of the initial cross-sectional areas to obtain difference data; Calculate the gradient of the area change between two adjacent cross sections according to the difference data to obtain gradient data; Selecting the cross-sectional image coordinates corresponding to the maximum value in the gradient data as the optimal cross-sectional coordinates; Calculating the distance between the optimal cross-sectional coordinates and each cross-sectional image coordinate to obtain distance data; Adjust the initial cross-sectional area according to the distance data to obtain the cross-sectional area of ​​the material to be cut; Among them, the cross-sectional area of ​​the material to be cut is calculated by the following formula: Among them, A′ i A represents the cross-sectional area of ​​the material to be cut at the i-th section. i represents the initial cross-sectional area of ​​the i-th section, d i represents the distance from the i-th section image coordinate to the optimal section coordinate, σ represents the standard deviation of the distance, μ represents the mean distance, and N represents the total number of section images.

5. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: The least squares fitting of the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain the optimal cross-sectional area includes: Establish a mathematical model of the relationship between the cross-sectional area of ​​the material to be cut and the coordinates of the cross-sectional image; Calculate the sum of squares of the cross-sectional area of ​​the material to be cut and the cross-sectional area predicted by the model according to the relational mathematical model; Solving the optimal parameters of the relationship mathematical model by Levenberg-Marquardt algorithm according to the sum of squared errors; Determining an optimal mathematical model according to the optimal parameters, and calculating an optimal cross-sectional area according to the optimal mathematical model; Among them, the relationship mathematical model is as follows: A(x,y)=a0+a1x+a2y 2 The optimal cross-sectional area is calculated by the following formula: Where A(x, y) represents the predicted cross-sectional area, a0, a1 and a2 represent the parameters to be determined, (x, y) represents the cross-sectional image coordinates, and x max Indicates the maximum value of the x-axis direction in the cross-sectional image coordinates, x min Indicates the minimum value of the x-axis direction in the cross-sectional image coordinates, A opt Indicates the optimal cross-sectional area.

6. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: Substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data to obtain the optimal cutting speed includes: The cutting speed formula is as follows: V=H·A opt α ·N β ·E γ Among them, V represents the optimal cutting speed, A opt represents the optimal cross-sectional area, H represents the speed weight adjustment factor, N represents the preset number of cutting wheels, E represents the power supply, and α, β and γ are preset empirical parameters.

7. The automatic deviation-correcting high-precision plastic pelletizing equipment control method according to claim 1 is characterized in that: The step of controlling the cutting device to perform cutting according to the spacing data, the optimal cutting speed and the cutting amount includes: Judging whether adjacent spacing data are equal according to the spacing data, if the adjacent spacing data are equal, it is determined that the sliding direction of the cutting device is correct; If the adjacent spacing data are not equal, it is determined that the sliding direction is offset during the cutting process, and the sliding direction is adjusted, and the blade height is adjusted; Calculating an estimated cutting time according to the optimal cutting speed and the cutting amount; Allocate the cutting preparation phase time and the cutting working phase time according to the estimated cutting time; Controlling the cutting device to perform cutting work according to the cutting preparation phase time and the cutting work phase time; The blade height to be adjusted is calculated using the following formula: Δh=k·(Z i,i+1 -Z i+1,i+2 ) The estimated cutting time is calculated using the following formula: Where Δh represents the blade height to be adjusted, k represents the adjustment amount of the blade height converted from the spacing difference, and Z i,i+1 represents the distance between the i-th projection line and the i+1-th projection line, Z i+1,i+2 represents the distance between the i+1th projection line and the i+2th projection line, t represents the estimated cutting time, Q represents the cutting amount, and V represents the optimal cutting speed.

8. A high-precision plastic pelletizing equipment control system with automatic deviation correction, characterized in that: include: A data acquisition module is used to acquire the image of the material to be cut, the projection line image and the cutting amount in the current cutting stage; A spacing calculation module, used to calculate the distance between adjacent projection lines according to the projection line image to obtain spacing data; An image preprocessing module, used for performing image preprocessing on the image of the material to be cut to obtain an initial cross-sectional area of ​​the material to be cut and corresponding cross-sectional image coordinates; A cross-sectional area calculation module, used to calculate the optimal cross-sectional coordinates of each cross-sectional area of ​​the material to be cut according to the initial cross-sectional area and the cross-sectional image coordinates, and adjust the initial cross-sectional area according to the optimal cross-sectional coordinates to obtain the cross-sectional area of ​​the material to be cut; An optimal area analysis module, used for performing least squares fitting on the cross-sectional area of ​​the material to be cut and the cross-sectional image coordinates to obtain an optimal cross-sectional area; A cutting speed calculation module, used for substituting the optimal cross-sectional area into a preset cutting speed formula to calculate cutting speed data and obtain an optimal cutting speed; The cutting control module is used to control the cutting device to perform cutting work according to the spacing data, the optimal cutting speed and the cutting amount.

9. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the automatic deviation-correcting high-precision plastic pelletizing equipment control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the automatic deviation-correcting high-precision plastic pelletizing equipment control method according to any one of claims 1 to 7.

Images