Automatic feeding speed control method for template machine

Abstract

The invention discloses an automatic feeding speed control method for a template machine, which relates to the technical field of template machine control, and comprises the following steps: S1, when raw materials used for template machine processing are conveyed, reserving an adjustment amount for the conveyed raw materials by using a margin control module, the allowance control module is arranged on the front side of a path for raw materials to enter a working part of the template machine; s2, two tension monitoring units are arranged on the two sides of the working part of the template machine correspondingly, and inlet tension and outlet tension of the working part of the template machine are monitored and compared correspondingly; and S3, when the outlet tension is in the tension interval and the inlet tension is not in the inlet tension interval, judging whether the duration of the state reaches the preset early warning time or not. According to the technical scheme, the diversified sensors and modules are combined with a calculation model, the raw material conveying speed is accurately adjusted, the surface condition of the raw material can be monitored in real time, and the feeding speed is dynamically adjusted.

Description

Technical Field

[0001] The present invention relates to the technical field of template machine control, and specifically to an automatic feeding speed control method for a template machine. Background Art

[0002] With the rapid development of automated production technology, the application of template machines has become increasingly popular in various industrial production lines. Traditional template machines usually rely on simple mechanical transmission and fixed-rate control to ensure the supply of raw materials. These methods mostly adjust the conveying speed of raw materials through tension monitoring, speed sensors, or fixed control systems. However, these methods often fail to provide sufficient adaptability when faced with complex production environments or changes in the state of raw materials.

[0003] Most existing automatic feeding systems use a single sensor for monitoring and feedback. For example, traditional tension control systems adjust the feeding speed by monitoring the tension changes of raw materials. However, such systems are only limited to dealing with simple problems such as excessive or too small tension of raw materials and cannot handle problems such as uneven surfaces, wrinkles, and accumulations of raw materials. In addition, many systems simply match the feeding speed with the processing rhythm of the template machine without considering the possible minor fluctuations and changes that may occur to the raw materials during the processing.

[0004] Another common existing technology is to detect the position and movement speed of raw materials through laser or photoelectric sensors. However, this technology usually only issues an alarm when the conveying speed of raw materials exceeds the preset range and fails to deeply analyze the state of raw materials (such as surface wrinkles or tension changes). This simple control method based on position sensing cannot provide sufficient dynamic adjustment capabilities.

[0005] Therefore, the existing technology has poor dynamic response and adaptive adjustment capabilities to complex environmental changes during the production process. Moreover, if relying solely on preset thresholds and simple sensors, it has poor processing capabilities for real-time subtle changes. Therefore, the present invention proposes an automatic feeding speed control method for a template machine. Summary of the Invention

[0006] The purpose of the present invention is to provide an automatic feeding speed control method for a template machine to solve the problems mentioned in the above background art.

[0007] The present invention can be achieved through the following technical solutions: An automatic feeding speed control method for a template machine, the control method comprising the following steps:

[0008] S1. When conveying the raw materials used for template machine processing, use a margin control module to reserve an adjustment amount for the conveyed raw materials, and the margin control module is arranged on the front side of the path where the raw materials enter the working part of the template machine;

[0009] S2. Set two groups of tension monitoring units on both sides of the working part of the template machine, and monitor and compare the inlet tension and outlet tension of the working part of the template machine respectively, including:

[0010] When the outlet tension is not within the outlet tension range, the template machine issues a warning message.

[0011] When the outlet tension is within the tension range, compare the outlet tension with the inlet tension. The comparison results include:

[0012] If the inlet tension is within the preset inlet tension range, the raw material transportation is normal.

[0013] If the inlet tension is not within the inlet tension range, is greater than the outlet tension, and the difference between the inlet tension and the outlet tension is greater than the preset positive difference threshold, the raw material feeding may be too slow, and the raw material is pulled tighter before entering the template machine.

[0014] If the inlet tension is not within the inlet tension range, is less than the outlet tension, and the absolute value of the difference between the inlet tension and the outlet tension is greater than the preset negative difference threshold, the raw material feeding may be too fast, and it accumulates or relaxes before entering the template machine, and the inlet tension decreases.

[0015] S3. When the outlet tension is within the tension range and the inlet tension is not within the inlet tension range, judge whether the duration of this state reaches the preset warning time to avoid adverse effects on raw material transportation due to short-term fluctuations.

[0016] S4. At the same time, set a group of image monitoring modules after the processing part of the template machine. After the raw material is processed by the template machine, collect image monitoring data to monitor whether the processed part of the raw material conforms to the preset processing area.

[0017] On the other hand, use a raw material state monitoring module to monitor the raw material before it enters the processing part of the template machine, obtain the surface state of the raw material, and calculate whether the raw material has wrinkles to obtain raw material state data.

[0018] S5. Use a calculation module to collect and calculate the image monitoring data and raw material state data, and the calculation module corrects the warning time based on the calculation results to facilitate timely adjustment of the raw material transportation speed.

[0019] And after the warning time ends and the inlet tension has not returned to the inlet tension range, the calculation module adjusts the raw material transportation speed, and at the same time adjusts the adjustment amount of the raw material on the transportation path through the margin control module.

[0020] When the raw material feeding speed is higher than the processing rhythm of the template machine, the margin control module increases the path length of the raw material in front of the processing part of the template machine to temporarily accommodate the excess raw material.

[0021] When the raw material feeding speed is lower than the processing rhythm, the raw material tension increases, and the surplus control module releases the raw material surplus and maintains the processing rhythm.

[0022] A further technical improvement of the present invention lies in that: the image monitoring module includes a layer unit and a first acquisition unit;

[0023] The layer unit generates an image simulation of a preset processing trajectory or part based on the normal conveying speed of the raw material, forming a set of comparison layers for use as a standard image reference;

[0024] The first acquisition unit is used to acquire an image of the raw material processing part in the actual conveying state, forming an image layer corresponding to the current processing state as a verification layer;

[0025] The calculation module aligns the comparison layer with the verification layer and calculates the spatial deviation between the comparison layer and the verification layer to obtain deviation data .

[0026] A further technical improvement of the present invention lies in that: the calculation module compares the deviation data with a preset layer deviation threshold for comparison;

[0027] When the deviation data is not less than the layer deviation threshold , the calculation module immediately corrects the warning time, greatly shortens the warning time or immediately activates the surplus control module to release the surplus of the raw material and increase the conveying speed of the raw material;

[0028] When the deviation data is less than the layer deviation threshold , the calculation module collects deviation data at multiple moments through a time window, denoted as a deviation set , including , ,..., ;

[0029] The calculation module judges the deviation slope, fluctuation amplitude and abnormal point ratio of each deviation data in the deviation set. When any one of the three judgments is abnormal, the calculation module corrects the warning time.

[0030] A further technical improvement of the present invention lies in that the calculation formula of the deviation slope is: ;

[0031] The abnormal judgment condition of the deviation slope S is: the deviation slope S is greater than 0 and the deviation slope S is greater than a preset deviation slope threshold ;

[0032] The calculation formula for the fluctuation range is ; where is the maximum value in the deviation set ; is the minimum value in the deviation set ;

[0033] Fluctuation range The abnormal judgment condition is: the fluctuation range exceeds the preset fluctuation threshold ;

[0034] The abnormal judgment condition for the abnormal point ratio is: ; where is the deviation data at the i-th moment in the deviation set ; represents the average value of each deviation data in the current deviation set ; is the offset of the i-th deviation data from the average value; is the tolerance of the small perturbation (i.e., the small range error that is not counted as abnormal); is the number of points where the deviation exceeds in the current time window; N is the total number of deviation data in the deviation set ; is the abnormal point ratio threshold.

[0035] A further technical improvement of the present invention is that when the deviation data is less than the layer deviation threshold , and the conditions for the deviation slope judgment, the fluctuation range judgment, and the abnormal point ratio judgment are not triggered within the preset time period, the calculation module realigns the current verification layer with the comparison layer.

[0036] A further technical improvement of the present invention is that the raw material state monitoring module includes a plurality of light source units and a second acquisition unit;

[0037] A plurality of light source units are set at different angles with respect to the conveying path of the raw material, and the light intensities of each light source unit are the same, and each light source unit periodically irradiates the raw material in turn, that is, each light source unit irradiates the raw material in a fixed order within the same cycle;

[0038] After each light source unit is started, the second acquisition unit acquires the raw material state image corresponding to the angle of the raw material, generates the raw material state set of the same cycle, and the second acquisition unit uploads the raw material state set to the calculation unit;

[0039] After receiving the raw material state set, the calculation unit preprocesses each raw material state image inside it and converts each raw material state image into a grayscale image to more clearly see the difference between the shadow and the raw material surface;

[0040] The calculation unit uses the edge detection algorithm for each grayscale image in the same raw material state set to detect the shadow edge part in each grayscale image. By analyzing the differences in the edge parts from multiple angles, it compares the changes in the shadow edges at the same position of the raw material under different lighting angles;

[0041] When there are no wrinkles on the raw material surface, at multiple angles, if there are patterns on the raw material surface, the edges of the patterns should be regular and consistent and will not change significantly;

[0042] When there are wrinkles on the raw material surface, the edges of the wrinkled parts will show obvious irregularities at different lighting angles, and the shape and position of the shadow will change with the change of the lighting angle;

[0043] And the calculation unit judges whether there is a wrinkled area on the raw material by comparing the shadow change amplitude in each grayscale image in the same raw material state set with a preset change threshold;

[0044] If there is a wrinkled area on the raw material, the calculation module corrects the warning time.

[0045] A further technical improvement of the present invention lies in that the calculation formula for the shadow change amplitude Q in each grayscale image is ;

[0046] In the formula, is the change amount of the shadow edge position at different angles;

[0047] is the change in the size of the shadow area;

[0048] is the change in the geometric shape of the shadow edge.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The technical solution of the present invention realizes the precise adjustment of the raw material conveying speed through the combination of diversified sensors and modules with a calculation model. Compared with the prior art, this application can monitor the surface condition of the raw material in real time and dynamically adjust the feeding speed, greatly improving the stability and adaptability of the production process; especially through the synergistic effect of tension monitoring and image processing, it can discover and correct wrinkles or uneven tension problems in the raw material in real time, thereby effectively reducing production errors caused by raw material defects.

[0051] Through real-time feedback control, the present invention can ensure the stable operation of the template machine during the processing, avoid processing errors caused by too fast or too slow raw material transportation, and adjust the feeding path and speed according to real-time monitoring data. It can adapt to various production environments and the characteristics of different raw materials, improve the overall production efficiency, be more accurate and flexible, and is applicable to a variety of complex production scenarios.

[0052] In addition, the present invention precisely detects the surface of the raw material through image monitoring, can identify surface wrinkles in real time, and feedback this information to the control system for adjustment. This not only improves the product quality, but also enhances the automation level of the production line, reduces the need for manual intervention, and ultimately improves the efficiency and stability of the entire production process. Brief Description of the Drawings

[0053] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the drawings.

[0054] Figure 1 is the flowchart of the present invention;

[0055] Figure 2 is the mind map of the present invention. Detailed Embodiments

[0056] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the drawings and preferred embodiments, will describe in detail the specific embodiments, structures, features and their effects according to the present invention.

[0057] Please refer to Figure 1-2 As shown, the present invention provides an automatic feeding speed control method for a template machine, and this control method includes the following steps:

[0058] S1. When transporting the raw material used for the processing of the template machine, use the margin control module to reserve an adjustment amount for the transported raw material, and the margin control module is arranged on the front side of the path where the raw material enters the working part of the template machine;

[0059] In this embodiment, the margin control module adopts a tension arm structure or a floating roller structure. When the raw material passes through the tension arm structure or the floating roller structure, a bending path is formed on its outer side. The tension arm structure or the floating roller structure can float up and down according to the tension state of the raw material, so as to dynamically adjust the margin in the raw material path and realize the dynamic buffering of the raw material feeding rhythm:

[0060] Increase the path length to store the raw material when the feeding speed is too fast, and reduce the path length to release the raw material when the feeding speed is too slow, so as to assist in adjusting the raw material transportation speed;

[0061] S2. Set two groups of tension monitoring units on both sides of the working part of the template machine, and monitor and compare the inlet tension and outlet tension of the working part of the template machine respectively, including:

[0062] When the outlet tension is not within the outlet tension range, the template machine issues a warning message;

[0063] When the outlet tension is within the tension range, compare the outlet tension with the inlet tension. The comparison results include:

[0064] If the inlet tension is within the preset inlet tension range, the raw material transportation is normal;

[0065] If the inlet tension is not within the inlet tension range, is greater than the outlet tension, and the difference between the inlet tension and the outlet tension is greater than the preset positive difference threshold, the raw material feeding may be too slow, and the raw material is pulled tighter before entering the template machine;

[0066] If the inlet tension is not within the inlet tension range, is less than the outlet tension, and the absolute value of the difference between the inlet tension and the outlet tension is greater than the preset negative difference threshold, the raw material feeding may be too fast, and it accumulates or relaxes before entering the template machine, and the inlet tension decreases;

[0067] In this embodiment, the actual scenario examples include:

[0068] Outlet tension state Inlet-outlet tension difference Judgment conclusion Control suggestion Normal Normal Normal feeding Normal operation Normal Large difference (higher at the inlet) Feeding too slowly Increase the feeding speed Normal Small difference (lower at the inlet) Feeding too fast Decrease the feeding speed Abnormal Any Template machine or discharging failure Pause feeding, alarm

[0069] S3. When the outlet tension is within the tension range and the inlet tension is not within the inlet tension range, judge whether the duration of this state reaches the preset warning time to avoid adverse effects on raw material transportation due to short-term fluctuations;

[0070] S4. At the same time, set a group of image monitoring modules after the processing part of the template machine. After the raw material is processed by the template machine, collect image monitoring data to monitor whether the processed part of the raw material conforms to the preset processing area;

[0071] The image monitoring module includes a layer unit and a first collection unit;

[0072] The layer unit generates image simulations of the preset processing trajectory or part based on the normal transportation speed of the raw material to form a group of comparison layers for use as a standard image reference;

[0073] The first collection unit is used to collect images of the processed part of the raw material in the actual transportation state to form an image layer corresponding to the current processing state as a verification layer;

[0074] On the other hand, a raw material state monitoring module is used to monitor the raw material before it enters the processing part of the template machine, obtain the surface state of the raw material, and calculate whether the raw material has wrinkles to obtain raw material state data;

[0075] The raw material state monitoring module includes a plurality of light source units and a second acquisition unit;

[0076] Different angles are set between the plurality of light source units and the conveying path of the raw material, and the light intensity of each light source unit is the same, and each light source unit periodically irradiates the raw material in turn, that is, each light source unit irradiates the raw material in a fixed order within the same cycle;

[0077] S5. A calculation module is used to collect and calculate the image monitoring data and the raw material state data, and the calculation module corrects the warning time based on the calculation result to facilitate timely adjustment of the conveying speed of the raw material;

[0078] The calculation module aligns the comparison layer and the inspection layer in the image and calculates the spatial deviation between the comparison layer and the inspection layer to obtain deviation data ;

[0079] The calculation module compares the deviation data with a preset layer deviation threshold for comparison;

[0080] When the deviation data is not less than the layer deviation threshold then the calculation module immediately corrects the warning time, greatly shortens the warning time or immediately activates the margin control module to release the margin of the raw material and accelerate the conveying speed of the raw material;

[0081] When the deviation data is less than the layer deviation threshold the calculation module collects the deviation data at multiple moments through a time window, denoted as the deviation set , including , ,..., ;

[0082] The calculation module judges the deviation slope, the fluctuation amplitude and the abnormal point ratio of each deviation data in the deviation set. When any one of the three groups of judgments is abnormal, the calculation module corrects the warning time;

[0083] The calculation formula for the deviation slope is: ;

[0084] The abnormal judgment condition for the deviation slope S is: the deviation slope S is greater than 0, and the deviation slope S is greater than a preset deviation slope threshold ;

[0085] The calculation formula for the fluctuation range is ; where is the maximum value in the deviation set ; is the minimum value in the deviation set ;

[0086] Fluctuation range The abnormal judgment condition for is: the fluctuation range exceeds the preset fluctuation threshold ;

[0087] The abnormal judgment condition for the abnormal point ratio is: ; where is the deviation data at the i-th moment in the deviation set ; represents the average value of each deviation data in the current deviation set ; is the offset of the i-th deviation data from the average value; is the tolerance of the small perturbation (i.e., the small range of error that is not counted as abnormal); is the number of points where the deviation exceeds in the current time window; N is the total number of deviation data in the deviation set ; is the abnormal point ratio threshold. For example, when is 0.3, it means that when more than 30% of the points are abnormal, correction is triggered;

[0088] When the deviation data is less than the layer deviation threshold , and the conditions for deviation slope judgment, fluctuation range judgment, and abnormal point ratio judgment are not triggered within the preset time period, the calculation module realigns the current verification layer with the comparison layer, specifically including: using the currently collected image of the actual processing part of the raw material as a new standard image template, updating the original comparison layer, and completing the dynamic correction of the image monitoring benchmark;

[0089] After each light source unit is started, the second acquisition unit acquires the raw material state images at corresponding angles of the raw material, generates a raw material state set for the same cycle, and the second acquisition unit uploads the raw material state set to the calculation unit;

[0090] After receiving the raw material state set, the calculation unit preprocesses each raw material state image inside it. The preprocessing includes image smoothing and denoising, as well as color space conversion, and converts each raw material state image from RGB to grayscale to more clearly see the difference between the shadow and the raw material surface;

[0091] The calculation unit uses the edge detection algorithm for each grayscale image within the same raw material state set to detect the shaded edge parts in each grayscale image, conducts multi-angle edge part difference analysis, and compares the shaded edge changes of the same position on the raw material under different lighting angles;

[0092] When there are no wrinkles on the surface of the raw material, at multiple angles, if there are patterns on the surface of the raw material, the edges of the patterns should be regular and consistent and will not change significantly;

[0093] When there are wrinkles on the surface of the raw material, the edges of the wrinkled parts will show obvious irregularities at different lighting angles, and the shape and position of the shadows will change with the change of the lighting angle;

[0094] And the calculation unit judges whether there is a wrinkled area on the raw material by comparing the shaded change amplitude in each grayscale image in the same raw material state set with a preset change threshold;

[0095] If there is a wrinkled area on the raw material, the calculation module corrects the warning time;

[0096] The calculation formula for the shaded change amplitude Q in each grayscale image is ;

[0097] In the formula, is the change amount of the shaded edge position at different angles; in this embodiment, the Euclidean distance is used to calculate the position change, ; , and , respectively represent the positions of two points on the shaded edge at different lighting angles;

[0098] is the change in the size of the shaded area; in this embodiment, after extracting the shaded contour of the corresponding grayscale image through the edge detection algorithm, the area of the shaded contour is used as the shaded area, and the area size of the shaded area is obtained by using the binarization of the image. The binarized shaded area is "1", and the rest of the area is "0"; the area A of the shaded area is obtained through the formula ; where =1 means the pixel point belongs to the shaded area, =0 means the pixel point does not belong to the shaded area; finally, , and respectively represent the areas of the shaded areas at two different lighting angles;

[0099] For the geometric shape change of the shadow edge, the angle change is used to quantify the shadow edge, and its calculation formula is ; is the length of the original shadow edge to ensure that the calculation result is relatively standardized; and , where A and B are the shadow edge contours extracted under two illumination angles; represents the Euclidean distance between two points;

[0100] And after the warning time ends, if the inlet tension does not return to the inlet tension range, the calculation module adjusts the conveying speed of the raw material, and at the same time adjusts the adjustment amount of the raw material on the conveying path through the margin control module;

[0101] When the feeding speed of the raw material is higher than the processing rhythm of the template machine, the tension arm structure or the floating roller structure floats upward due to the reduced tension, correspondingly increasing the bending path length of the raw material outside it, so as to temporarily accommodate the excess raw material;

[0102] When the feeding speed of the raw material is lower than the processing rhythm, the raw material tension increases, the tension arm or the floating roller moves downward, and the bending path length decreases, so as to release the raw material margin and maintain the processing rhythm.

[0103] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to be equivalent embodiments with equivalent changes, but as long as it does not depart from the technical content of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An automatic feeding speed control method for a template machine, characterized in that: The control method includes the following steps: S1. When conveying the raw materials used for template machine processing, use the allowance control module to reserve an adjustment amount in front of the path of the working part of the template machine for the conveyed raw materials; S2. Set two groups of tension monitoring units on both sides of the working part of the template machine respectively, and monitor and compare the inlet tension and outlet tension of the working part of the template machine respectively; S3. When the outlet tension is within the tension range and the inlet tension is not within the inlet tension range, judge whether the duration of this state reaches the preset warning time; S4. At the same time, set a group of image monitoring modules after the processing part of the template machine. After the raw materials are processed by the template machine, collect image monitoring data to monitor whether the processed part of the raw materials conforms to the preset processing area; On the other hand, use the raw material state monitoring module to monitor the raw materials before they enter the processing part of the template machine, obtain the surface state data of the raw materials, and calculate whether the raw materials are wrinkled; S5. Use the calculation module to collect and calculate the image monitoring data and the raw material state data, and the calculation module corrects the warning time based on the calculation results; After the warning time ends and the inlet tension does not return to the inlet tension range, the calculation module adjusts the conveying speed of the raw materials, and at the same time adjusts the adjustment amount of the raw materials on the conveying path through the allowance control module.

2. The automatic feeding speed control method for a template machine according to claim 1, wherein The comparison results of the inlet tension and the outlet tension in step S2 include: When the outlet tension is not within the outlet tension range, the template machine issues a warning message; When the outlet tension is within the tension range, compare the outlet tension with the inlet tension: If the inlet tension is within the preset inlet tension range, the raw material conveying is normal; If the inlet tension is not within the inlet tension range, is greater than the outlet tension, and the difference between the inlet tension and the outlet tension is greater than the preset positive difference threshold, the raw material feeding is too slow; If the inlet tension is not within the inlet tension range, is less than the outlet tension, and the absolute value of the difference between the inlet tension and the outlet tension is greater than the preset negative difference threshold, the raw material feeding is too fast.

3. The automatic feeding speed control method for a template machine according to claim 1, wherein The image monitoring module includes a layer unit and a first acquisition unit; The layer unit generates image simulations of the preset processing trajectory or part based on the normal conveying speed of the raw materials to form a set of comparison layers; The first acquisition unit is used to collect images of the processed part of the raw materials in the actual conveying state to form an image layer corresponding to the current processing state as a calibration layer; The calculation module aligns the comparison layer with the inspection layer for image alignment, and calculates the spatial deviation between the comparison layer and the inspection layer to obtain deviation data .

4. The automatic feeding speed control method for a template machine according to claim 3, characterized in that, The calculation module compares the deviation data with a preset layer deviation threshold value for comparison; When the deviation data is not less than the layer deviation threshold the calculation module corrects the warning time.

5. The automatic feeding speed control method for a template machine according to claim 4, characterized in that, When the deviation data is less than the layer deviation threshold , the calculation module collects deviation data at multiple moments through a time window, denoted as the deviation set , including , ,..., ; The calculation module judges the deviation slope, the fluctuation amplitude and the abnormal point ratio of each deviation data in the deviation concentration. When any one of the three judgments is abnormal, the calculation module corrects the warning time.

6. The automatic feeding speed control method for a template machine according to claim 5, wherein, When the deviation data is less than the layer deviation threshold , and the conditions for deviation slope judgment, fluctuation amplitude judgment, and abnormal point ratio judgment are not triggered within a preset time period, the calculation module realigns the current verification layer with the comparison layer.

7. A method for automatically controlling the feeding speed of a template machine according to claim 1, characterized in that, The raw material state monitoring module includes multiple light source units and a second acquisition unit; Different angles are set between the multiple light source units and the conveying path of the raw materials, and the light intensity of each light source unit is the same, and each light source unit periodically irradiates the raw materials in turn; After each light source unit is started, the second acquisition unit collects the raw material state images at the corresponding angles of the raw materials to generate a raw material state set in the same cycle, and the second acquisition unit uploads the raw material state set to the calculation unit.

8. The automatic feeding speed control method for a template machine according to claim 7, characterized in that, After receiving the raw material state set, the calculation unit preprocesses each raw material state image inside it and converts each raw material state image into a grayscale image; The calculation unit detects the shadow edge parts in each grayscale image of the same raw material state set through an edge detection algorithm; And the calculation unit judges whether there is a wrinkled area on the raw material by judging the shadow change amplitude in each grayscale image of the same raw material state set and a preset change threshold; If the shadow change amplitude of each grayscale image in the same raw material state set of the raw material is greater than the change threshold, the calculation unit judges that there is a wrinkled area on the raw material and corrects the warning time.

9. The automatic feeding speed control method for a template machine according to claim 8, characterized in that The calculation formula for the shadow change amplitude Q in each grayscale image is ; where is the change amount of the shadow edge position at different angles; is the change in the size of the shadow area; is the change in the geometric shape of the shadow edge.

Images