Method, system and storage medium for automatically adjusting a conveying posture of a raw material batching device

Abstract

The application relates to the technical field of conveying control, and discloses a conveying posture automatic adjusting method and system of a raw material batching device and a storage medium. The method obtains a real-time image of a conveying line based on a raw material batching instruction, extracts a conveying target and the conveying line from the real-time image, calculates real-time posture data of the conveying target and conveying line marks of the conveying line through an image recognition algorithm, matches posture reference data and conveying direction data from a preset database according to the conveying line marks, and sets a first controlled part and a second controlled part of the conveying target according to the posture reference data and the conveying direction data. Posture deviation data is calculated according to the real-time posture data and the posture reference data by using a posture comparison algorithm. First force control data and second force control data are obtained through a deviation control algorithm, the force of the conveying line on the two controlled parts is adjusted, and the control trends of the two controlled parts are opposite. The method can automatically correct the posture skew of the batching frame caused by the roller body problem during the conveying process, guarantee the stable transfer of raw materials, and improve the conveying efficiency and batching accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of conveying control, and in particular to a conveying posture automatic adjusting method, system and storage medium of a raw material batching device. BACKGROUND

[0002] In a traditional Chinese medicine production line, the automation of the batching and conveying link has become a development trend in the industry. The traditional manual batching method is inefficient and has large errors, and it is difficult to meet the needs of large-scale production. At present, most enterprises have introduced automatic conveying equipment to realize the continuous transfer of raw materials through mechanical transmission.

[0003] Traditional Chinese medicine dry materials are usually quantitatively dropped into a batching frame by a feeding mechanism. The batching frame filled with raw materials is placed on a conveying roller, and is conveyed along a predetermined path by the friction generated by the rotation of the roller body. Finally, it reaches the side of the processing equipment and is transferred to the next process by a mechanical arm or manually. The stable posture of the batching frame is the key to ensuring the accurate transfer of raw materials and avoiding spilling and smooth connection of subsequent processes.

[0004] The conveying roller is driven by a plurality of independent roller bodies through chain or gear linkage. If the height of a certain section of the roller body is inconsistent due to wear, jamming or installation error, especially when the weight of the traditional Chinese medicine dry materials is relatively light, the batching frame will not be pressed on the conveying roller, and the driving force received by different positions at the bottom of the batching frame will be uneven, which can easily cause the posture of the batching frame to be skewed. Long-term use can further exacerbate the synchronization deviation of the roller bodies due to problems such as wear of the roller body bearings and loosening of the chain, resulting in more obvious skewing of the batching frame, which not only affects the conveying efficiency, but also affects the accuracy of batching. SUMMARY

[0005] In order to make the posture of the batching frame on the conveying roller more stable, the present application provides a conveying posture automatic adjusting method, system and storage medium of a raw material batching device.

[0006] In a first aspect, the present application provides a conveying posture automatic adjusting method of a raw material batching device, which adopts the following technical solution:

[0007] A conveying posture automatic adjusting method of a raw material batching device, comprising the following steps:

[0008] Based on a raw material batching instruction, real-time images of a conveying line are obtained;

[0009] A conveying target and a conveying line are extracted from the real-time images;

[0010] The real-time posture data of the conveying target and the conveying line mark of the conveying line are calculated by an image recognition algorithm;

[0011] According to the conveying line mark, posture reference data are matched from a preset posture database;

[0012] According to the conveying line mark, conveying direction data is matched from a preset conveying database;

[0013] According to the conveying direction data, two side positions of the conveying target along the conveying direction are set as a first controlled position and a second controlled position;

[0014] According to the real-time posture data and the posture reference data, posture deviation data is calculated through a posture comparison algorithm;

[0015] According to the posture deviation data, first force control data is calculated through a deviation control algorithm, and the force of the conveying line on the first controlled position is adjusted according to the first force control data; and / or, second force control data is calculated through a posture force algorithm according to the posture deviation data, and the force of the conveying line on the second controlled position is adjusted according to the second force control data, and the control trend of the first force control data is opposite to that of the second force control data.

[0016] By using the above technical scheme, the conveying line image is obtained in real time, the conveying target and the conveying line information are extracted, the reference data is matched in combination with the preset database, the posture deviation is calculated, and the force of the conveying line on the two sides of the batching frame is adjusted accordingly, so as to automatically correct the posture skew caused by the roller body problem, ensure the stable transfer of raw materials, and improve the conveying efficiency and batching accuracy.

[0017] Optionally, the image recognition algorithm comprises:

[0018] The contour line of the part of the conveying target close to the conveying line is extracted;

[0019] The intersection center and the intersection angle are calculated according to the contour line, and the intersection center and the intersection angle are one-to-one corresponding;

[0020] The conveying edge line of the conveying line is extracted; and the conveying line mark is fitted according to the conveying edge line;

[0021] The pair of intersection center and intersection angle closest to the conveying edge line is selected;

[0022] The offset distance between the conveying edge line and the intersection center is calculated;

[0023] The offset data is calculated according to the offset distance and the preset reference distance;

[0024] The posture included angle between the conveying edge line and the bisector of the intersection angle is calculated;

[0025] The included angle difference value is calculated according to the posture included angle and the preset first reference included angle;

[0026] The real-time posture data is composed of the included angle difference value and the offset data, and the real-time posture data is output.

[0027] By adopting the technical scheme, the position offset and angle deviation of the conveying target can be accurately captured by extracting the key features of the conveying target and the conveying line, calculating the offset distance and the attitude included angle to generate the real-time attitude data, and the accuracy of attitude recognition is improved.

[0028] Optionally, the image recognition algorithm comprises:

[0029] extracting a conveying edge line of the conveying line;

[0030] extracting a conveying center line according to the conveying edge line;

[0031] extracting a target contour of the conveying target on the conveying line;

[0032] fitting a projection line of the conveying center line on the surface of the target contour according to the relative position of the conveying center line and the target contour;

[0033] calculating the volume of the part on both sides of the projection line as a first volume and a second volume;

[0034] calculating the volume difference between the first volume and the second volume;

[0035] calculating the offset data according to the volume difference and a preset volume reference value;

[0036] extracting a contour center line of the target contour, the contour center line being parallel to the conveying center line when the conveying target is in a standard attitude;

[0037] calculating an attitude included angle between the conveying center line and the contour center line;

[0038] calculating an included angle difference according to the attitude included angle and a preset second reference included angle;

[0039] composing real-time attitude data according to the included angle difference and the offset data, and outputting the real-time attitude data.

[0040] By adopting the technical scheme, the attitude deviation of the conveying target can be accurately recognized from the overall shape and the gravity distribution by analyzing the relative position relationship between the conveying center line and the target contour, and calculating the real-time attitude data in combination with the volume difference and the attitude included angle, and the accuracy of attitude recognition is improved.

[0041] Optionally, the attitude comparison algorithm comprises:

[0042] extracting the included angle difference and the offset data from the real-time attitude data;

[0043] extracting an included angle reference difference and offset reference data from the attitude reference data;

[0044] calculating first deviation data according to the included angle difference and the included angle reference difference;

[0045] The second deviation data is calculated according to the offset data and the offset reference data;

[0046] The attitude deviation data is calculated according to the first deviation value and the second deviation value.

[0047] By using the above technical scheme, the comprehensive attitude deviation data is obtained by comparing and calculating the included angle difference value in the real-time attitude data and the offset data with the reference data respectively, which can comprehensively consider the deviation of the angle and the position, and make the final deviation evaluation more comprehensive and accurate.

[0048] Optionally, the deviation control algorithm comprises:

[0049] The difference value between the attitude deviation data and the preset deviation control data is calculated as a control difference value;

[0050] The control average value is obtained by using a preset filtering algorithm based on the plurality of control difference values;

[0051] The control data is calculated according to the control average value and a preset correction reference value;

[0052] If the control data is less than a preset first reference data, and the control data is used to adjust the first force receiving part, the control data is taken as the first force control data;

[0053] If the control data is greater than a preset second reference data, and the control data is used to adjust the second force receiving part, the control data is taken as the second force control data;

[0054] The second reference data is greater than the first reference data.

[0055] By using the above technical scheme, the control average value is obtained by calculating the control difference value and filtering, the control data is determined in combination with the preset reference value, and the differential threshold is set according to different force receiving parts, which can effectively filter interference, smooth the control process, and realize accurate force adjustment of different parts.

[0056] Optionally, the step of adjusting the force of the conveying line on the first controlled part and / or the second controlled part comprises the following steps:

[0057] The first control conveying roller is arranged at the set position on the conveying line, and the first control conveying roller comprises two groups of driving small rollers, which are independently arranged and respectively connected with driving assemblies capable of independently controlling the rotating speed;

[0058] The rotating speeds of the two groups of driving small rollers are initialized as the preset conveying rotating speed of the conveying line;

[0059] when the force of the conveying line on the first controlled part is adjusted according to the first force control data, the rotational speed increment of the active small roller corresponding to the first controlled part is adjusted according to the first force control data in a positive correlation, so as to adjust the driving force on the first controlled part;

[0060] when the force of the conveying line on the second controlled part is adjusted according to the second force control data, the rotational speed increment of the active small roller corresponding to the second controlled part is adjusted according to the second force control data in a positive correlation, so as to adjust the driving force on the second controlled part;

[0061] wherein the rotational speed adjustment trend of the active small roller corresponding to the first controlled part is opposite to that of the active small roller corresponding to the second controlled part.

[0062] By adopting the above technical solution, the first control conveying roller containing two groups of independently controllable active small rollers is set, the rotational speed increment of the small roller corresponding to the part is adjusted according to the force control data in a positive correlation based on the conveying rotational speed, and the adjustment trends of the two sides are opposite, so that the driving forces of the two sides can be accurately and quickly changed by the rotational speed difference, the real-time and accurate correction of the conveying target posture is realized, and the conveying stability is ensured.

[0063] Optionally, adjusting the force of the conveying line on the first controlled part and / or the second controlled part comprises the following steps:

[0064] The second control conveying roller is arranged at the set position on the conveying line, and the second control conveying roller comprises two groups of driven small rollers, the two groups of driven small rollers are independently arranged and are respectively connected with an adjustable assembly capable of being individually controlled in lifting;

[0065] The height of the two groups of driven small rollers is initialized to be lower than the height of other conveying rollers on the conveying line;

[0066] when the force of the conveying line on the first controlled part is adjusted according to the first force control data, the lifting time of the driven small roller corresponding to the first controlled part from lowering to the set height is adjusted according to the first force control data in a positive correlation, so as to adjust the friction time of the first controlled part;

[0067] when the force of the conveying line on the second controlled part is adjusted according to the second force control data, the lifting time of the driven small roller corresponding to the second controlled part from lowering to the set height is adjusted according to the second force control data in a positive correlation, so as to adjust the friction time of the second controlled part;

[0068] wherein the lifting time adjustment trend of the driven small roller corresponding to the first controlled part is opposite to that of the driven small roller corresponding to the second controlled part.

[0069] By adopting the technical scheme, the second control conveying roller comprising two groups of driven small rollers capable of being independently lifted is arranged, the lifting time of the small rollers at corresponding positions is adjusted according to the positive correlation of force control data, the adjustment trends on both sides are opposite, the difference in friction time is controlled to change the stress on both sides, and the flexible adjustment of the conveying target posture is realized.

[0070] In a second aspect, the application provides a conveying posture automatic adjustment system of a raw material batching device, which adopts the following technical scheme:

[0071] A conveying posture automatic adjustment system of a raw material batching device, comprising a processor, wherein the processor executes the steps of the raw material batching device conveying posture automatic adjustment method according to any one of the above.

[0072] In a third aspect, the application provides a storage medium, which adopts the following technical scheme:

[0073] A storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the steps of the raw material batching device conveying posture automatic adjustment method according to any one of the above.

[0074] In summary, the application has at least one of the following beneficial technical effects:

[0075] Through the design of two image recognition algorithms, the key contact positions of the conveying target and the conveying line can be focused, and the detailed features of the position deviation and the angle deviation can be accurately captured; in addition, the overall shape is considered, the center line angle and the volume difference are analyzed, and the gravity distribution and the overall deflection trend are analyzed. The dual recognition logic covers local details and overall shape, effectively improves the accuracy of the posture data, and provides a reliable basis for subsequent adjustment.

[0076] The posture comparison algorithm compares the real-time angle difference, the deviation data and the reference data, and obtains the comprehensive deviation data through weighted average, which eliminates the interference of different physical dimensions, and reflects the influence difference of the angle and the position deviation on the overall posture through weight distribution. This quantitative method makes the deviation evaluation more in line with the actual production needs, avoiding the one-sidedness of single-dimensional judgment.

[0077] The deviation control algorithm smoothes the instantaneous interference through filtering processing, and realizes the targeted adjustment of different controlled positions through the differential threshold judgment, which filters the false actions caused by noise signals, and ensures the accuracy of the adjustment direction through direction differentiation. At the same time, the two adjustment methods realize stress control through the speed difference of the driving small roller and the friction time difference of the driven small roller, taking into account the rapid response and flexible adaptation of the adjustment, and can select the appropriate method according to the characteristics of the conveying target to ensure efficient and stable posture correction. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 is a step diagram of a conveying posture automatic adjustment method of a raw material batching device.

[0079] Figure 2 is a step diagram of a first image recognition algorithm.

[0080] Figure 3 is a step diagram of a second image recognition algorithm. DETAILED DESCRIPTION

[0081] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0082] In the description of the present specification, the description of the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "example", "specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the described embodiments or examples are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0083] The embodiment of the present application discloses a conveying posture automatic adjustment method of a raw material batching device, referring to Figure 1 , comprising the following steps:

[0084] Based on the raw material batching instruction, the real-time image of the conveying line is acquired; when the raw material batching instruction is received, the image acquisition device deployed at the key position of the conveying line is triggered to start working. The image acquisition device can adopt an industrial-grade high-definition camera, which can clearly capture the overall shape of the conveying target, i.e. the batching frame loaded with traditional Chinese medicine dry materials and the surrounding conveying line structure.

[0085] The collected image is preprocessed, including operations such as graying, denoising filtering and contrast enhancement, to eliminate image interference caused by factors such as environmental light changes and equipment vibration. After preprocessing, the pixel area of the conveying target and the conveying line is extracted by using an image segmentation algorithm based on deep learning or a combination of traditional edge detection and morphological processing: for the conveying target, the complete batching frame area is separated from the image background by identifying the characteristic outline (such as a rectangular frame) and color identification (such as a pre-set distinguishing color) of the batching frame; for the conveying line, the overall area of the conveying line composed of multiple roller bodies is extracted according to the arrangement rule (such as the parallel distribution feature) and material reflection characteristics of the roller bodies.

[0086] The real-time posture data of the conveying target and the conveying line mark of the conveying line are calculated by an image recognition algorithm; for the conveying line, a straight line fitting algorithm such as Hough transformation is used to process the extracted conveying line region, and a reference straight line that can represent the overall extension direction of the conveying line, i.e. the conveying line mark, is fitted, which can be quantitatively represented in the image coordinate system through its slope and intercept. For the conveying target, real-time posture data is generated by calculating the geometric center coordinates of the batching frame, the long side direction angle and other parameters: the geometric center coordinates are obtained by calculating the pixel barycenter of the batching frame outline region, and the long side direction angle is calculated by fitting the straight line slope of the two long sides of the batching frame. The above parameters are converted into actual physical parameters through the conversion relationship between the preset pixel size and the actual physical size (such as 1 pixel corresponding to 0.5 mm) to accurately reflect the spatial posture of the batching frame.

[0087] The posture reference data is matched from the preset posture database according to the conveying line mark; the standard posture parameters corresponding to different conveying line marks are pre-stored in the posture database, which are set based on the posture characteristics of the batching frame in the ideal conveying state (i.e. no skew, center aligned with the conveying line), including the reference center offset (usually 0) and the reference long side angle (parallel to the conveying line mark, with an angle difference of 0). The system automatically matches the corresponding posture reference data by comparing the currently calculated conveying line mark with the conveying line mark features stored in the database, which serves as the reference basis for judging whether the posture of the batching frame is abnormal.

[0088] The actual conveying direction information corresponding to each conveying line mark is recorded in the conveying database, including the horizontal angle of the conveying direction, the inclination direction and other parameters; the inclination direction such as left and right inclination, which are determined by the slope of the conveying line mark and the preset direction definition rule, such as the slope being positive corresponding to the inclination to the right and up. By matching the conveying direction data, the system can clearly determine the advancing path direction of the batching frame, providing spatial orientation reference for the division of subsequent controlled parts.

[0089] Taking the conveying direction as horizontal right as an example, along the conveying direction, the left edge region of the batching frame is defined as the first controlled part, and the right edge region is defined as the second controlled part; if the conveying direction is inclined upward, the perpendicular line of the conveying direction is taken as the reference, and the corresponding regions of the two sides of the batching frame are set as two controlled parts. The specific range of the controlled part is determined by the preset proportion parameter (such as 1 / 3 of the width of the batching frame), which ensures that it can accurately reflect the stress state of the two sides of the batching frame.

[0090] The posture deviation data is calculated by a posture comparison algorithm according to the real-time posture data and the posture reference data. The posture comparison algorithm includes: extracting the center offset and the angle deviation value in the real-time posture data, and extracting the reference offset and the reference angle value in the posture reference data; calculating the difference between the two, to obtain the actual offset deviation and the actual angle deviation; the actual offset deviation is the difference between the real-time center offset and the reference offset; the actual angle deviation is the difference between the real-time long-side angle and the reference angle; the two deviation values are comprehensively calculated by a preset weighting calculation model to obtain quantized posture deviation data, and the size of the data directly reflects the severity of the posture skew of the batching frame. The weighting calculation model is, for example, offset deviation weight 0.4 and angle deviation weight 0.6.

[0091] The first force control data is calculated by a deviation control algorithm according to the posture deviation data, and the force of the conveying line on the first controlled part is adjusted according to the first force control data; and / or, the second force control data is calculated by a posture force algorithm according to the posture deviation data, and the force of the conveying line on the second controlled part is adjusted according to the second force control data. The control trend of the first force control data is opposite to that of the second force control data. The deviation control algorithm and the posture force algorithm are both based on a preset control model, such as a PID control model, wherein the first force control data has a positive correlation with the posture deviation data; that is, the greater the deviation, the greater the control data. The second force control data has a negative correlation with the posture deviation data; that is, the greater the deviation, the smaller the control data; or vice versa. For example, when the posture deviation data shows that the batching frame is skewed to the left, the first force control data drives the conveying line to increase the driving force on the first controlled part (the left side), and the second force control data drives the conveying line to reduce the driving force on the second controlled part (the right side), so that a correction torque is generated by the difference in force on the two sides, and the batching frame gradually returns to the standard posture. When the batching frame is skewed to the left, no matter whether the initial friction forces on the two sides are balanced or not, as long as the force on the left side is greater than that on the right side or the force on the right side is smaller than that on the left side, a rightward correction torque can be formed; the increase in the force on the left side can push the left side to move faster, and the decrease in the force on the right side can slow down the movement of the right side, so that the batching frame rotates around the center of gravity and gradually returns to the normal position.

[0092] Through the above steps, the posture change of the batching frame can be monitored in real time, the skew deviation can be accurately identified, and automatic correction can be achieved by differentiating the force on the two sides, so that the posture instability problem caused by the wear of the conveying roller body, installation errors and the like can be effectively solved, and the stability of the traditional Chinese medicine dry material in the conveying process can be ensured.

[0093] In this embodiment, the image recognition algorithm includes two implementation manners:

[0094] Referring to Figure 2 , the first image recognition algorithm:

[0095] Extract the contour line of the part of the conveying target close to the conveying line; for the conveying target area segmented in the image, i.e. the area of the ingredient frame, the Canny edge detection algorithm is used to extract the contour of the bottom edge, i.e. the part in contact with the conveying line, to obtain a continuous edge pixel point set. In order to ensure the integrity of the contour line, the extracted edge pixel points are fitted and completed to eliminate the contour break caused by image noise or local occlusion, and finally a closed contour line is formed which can accurately reflect the shape of the bottom of the conveying target.

[0096] Calculate the intersection center and intersection angle according to the contour line, and the intersection center and intersection angle correspond to each other; the bottom contour line of the conveying target is usually rectangular, corresponding to the bottom border of the ingredient frame, and the contact area with the conveying line will form four corner points, i.e. the turning points of the contour line. The four corner points are identified by an angle point detection algorithm such as Harris corner point detection, and the line segment between each two adjacent corner points is defined as a contour edge, and the intersection of the two adjacent contour edges is the corner point, i.e. the intersection. For each intersection, calculate its pixel coordinates in the image coordinate system as the intersection center, and calculate the intersection angle of the intersection by the slope difference of the two adjacent contour edges, for example, the intersection angle of the rectangular border is theoretically 90°, and the actual deviation may be caused by the attitude skew.

[0097] Extract the conveying edge line of the conveying line; fit the conveying line mark according to the conveying edge line; for the conveying line area segmented in the image, identify the edge contour on both sides, i.e. the two boundary lines formed by the conveying roller arrangement, and fit the pixel points of the edge contour on both sides by a straight line fitting algorithm such as the least squares method to obtain two parallel or approximately parallel straight lines, i.e. the conveying edge line. Select one of the conveying edge lines, usually the one close to the center of the conveying target as the reference, or perform midline fitting on the two conveying edge lines to obtain a reference straight line that can represent the overall extension direction of the conveying line, i.e. the conveying line mark.

[0098] Select the pair of intersection center and intersection angle closest to the conveying edge line; calculate the perpendicular distance from all intersection centers to the conveying edge line, and select the intersection center with the smallest distance, and take the center coordinates of the intersection center and the corresponding intersection angle as the key analysis object to focus on the direct contact area between the conveying target and the conveying line and improve the pertinence of the attitude detection.

[0099] Calculate the offset distance between the conveying edge line and the intersection center; based on the selected intersection center, calculate the perpendicular distance from the intersection center to the conveying edge line by the distance formula from a point to a straight line, in pixels; then convert it to the actual physical distance by a preset pixel-physical size conversion coefficient (such as 1 pixel = 0.3 mm), in mm, i.e. the offset distance. This distance directly reflects the degree of positional offset of the conveying target in the direction perpendicular to the conveying direction.

[0100] According to the offset distance and the preset reference distance, offset data is calculated; the preset reference distance is the theoretical distance from the above intersection center to the conveying edge line when the conveying target is in the standard posture, such as 30 mm, and the offset data is the difference between the actual offset distance and the reference distance, offset data = actual offset distance - reference distance. If the offset data is positive, it indicates that the conveying target is offset away from the conveying line center; if it is negative, it indicates that it is offset towards the conveying line center, and the absolute value size reflects the offset degree.

[0101] The posture included angle between the conveying edge line and the bisector of the intersection angle is calculated; for the selected intersection angle, the direction vector of the bisector, i.e. the direction vector of the bisector, is calculated, the direction vector is synthesized by the direction vectors of the two intersecting contour edges, and then the included angle between the bisector and the conveying edge line is calculated by using the vector included angle formula, i.e. the posture included angle. For example, the bisector of the corner of the batching frame in the standard posture should be perpendicular to the conveying edge line, and the theoretical value of the posture included angle is 90°, and the angle will deviate when the posture is skewed.

[0102] According to the posture included angle and the preset first reference included angle, the included angle difference value is calculated; the preset first reference included angle is the theoretical value of the posture included angle in the standard posture, and the theoretical value is usually 90°; the included angle difference value is the difference between the actual posture included angle and the first reference included angle, included angle difference = actual posture included angle - first reference included angle. If the difference value is positive, it indicates that the conveying target is deflected in a certain direction; if it is negative, it indicates that it is deflected in the opposite direction, and the absolute value reflects the severity of the angle skew.

[0103] According to the included angle difference value and the offset data, real-time posture data is composed, and the real-time posture data is output. The included angle difference value (unit: degree) and the offset data (unit: mm) are integrated into real-time posture data and output, which fully reflects the posture characteristics of the conveying target in terms of angle and position.

[0104] The first image recognition algorithm accurately extracts the position offset and angle deviation characteristics by focusing on the key contact points between the conveying target and the conveying line, effectively improving the pertinence and accuracy of posture recognition.

[0105] Referring to Figure 3 , the second image recognition algorithm:

[0106] The conveying edge line of the conveying line is extracted; for the conveying line region segmented in the image, an edge detection and straight line fitting method is used to identify the boundary contour on both sides of the conveying line, i.e. two parallel edge lines formed by a plurality of roller bodies, i.e. the conveying edge line. By performing least squares fitting on the edge pixel points, two accurate straight line parameters such as slope and intercept are obtained, which ensures that the horizontal boundary range of the conveying line can be accurately reflected.

[0107] According to the conveying edge line, a conveying center line is extracted; based on the two conveying edge lines, a geometric center line is calculated as the conveying center line; by solving the perpendicular distance between the two edge lines, a midpoint trajectory is taken to form a straight line parallel to the edge line, and the straight line is the conveying center line, and the parameter is expressed in the form of a straight line equation in the image coordinate system. The conveying center line serves as the reference line of the conveying direction, and can accurately reflect the extension direction and center position of the conveying line.

[0108] A target contour of the conveying target on the conveying line is extracted; for the recognized conveying target region in the image, a contour extraction algorithm is used, such as a contour tree-based extraction method, to obtain the complete outer contour boundary, including the top, bottom and two side edges. Through morphological processing, noise points and redundant line segments in the contour are removed, so that the target contour can accurately and clearly reflect the overall shape of the batching frame, providing a basis for subsequent volume calculation and center line extraction.

[0109] A projection line of the conveying center line on the target contour surface is fitted according to the relative position of the conveying center line and the target contour; the conveying center line is projected along the direction perpendicular to itself to the plane where the target contour is located, and the projection range covers the entire longitudinal length of the target contour, i.e. the length in the conveying direction. By calculating the intersection points of the conveying center line and the target contour edge, a straight line parallel to the conveying center line and located on the target contour surface is fitted, which is the projection line. The projection line serves as the reference for dividing the two side regions of the target contour, and the relative position of the projection line and the conveying center line can reflect the overall deviation trend of the conveying target.

[0110] The volumes of the target contour on both sides of the projection line are calculated as a first volume and a second volume; based on the two-dimensional image features of the target contour, and in combination with a preset conveying target height parameter, such as the standard height of the batching frame, a stereographic conversion algorithm is used to calculate the volumes of the regions on both sides of the projection line: the two-dimensional areas of the target contour on both sides of the projection line are multiplied by the height parameter to obtain the first volume and the second volume; the first volume is the volume on one side of the projection line, and the second volume is the volume on the other side of the projection line. During the volume calculation process, the pixel-physical size conversion coefficient (such as 1 pixel corresponding to 0.5 mm) is used to convert the image area to the actual area (unit: mm²), so as to ensure the physical meaning of the volume parameter.

[0111] The volume difference between the first volume and the second volume is calculated; the volume difference is the difference between the first volume and the second volume, and the volume difference = first volume-second volume, and the positive and negative values reflect the deviation direction of the center of gravity of the conveying target relative to the projection line: a positive value indicates that the center of gravity deviates to one side of the projection line, a negative value indicates that the center of gravity deviates to the other side, and the absolute value size reflects the degree of deviation of the center of gravity.

[0112] According to the volume difference and the preset volume reference value, offset data is calculated; the preset volume reference value is a theoretical difference value of the volumes on both sides of the projection line when the conveying target is in a standard posture, and the theoretical difference value is usually 0, that is, the volumes on both sides are equal; the offset data is a ratio of the actual volume difference to the volume reference value, offset data = volume difference / volume reference value, the volume difference is converted into a quantitative index that can be directly used for posture analysis through normalization processing, and the numerical size directly reflects the position deviation degree of the conveying target caused by the gravity center offset.

[0113] The profile center line of the target profile is extracted. By calculating the geometric center trajectory of the target profile perpendicular to the conveying direction, a straight line passing through the target profile is fitted, that is, the profile center line. When the conveying target is in a standard posture, the profile center line is parallel to the conveying center line, and the two are coincident or maintain a fixed distance in the horizontal direction.

[0114] The posture included angle between the conveying center line and the profile center line is calculated; the included angle between the conveying center line and the profile center line is calculated by the vector included angle formula through the slope parameters of the two straight lines, that is, the posture included angle. The angle directly reflects the overall deflection degree of the conveying target: the included angle is 0° in the standard posture, and the included angle increases when the posture is skewed, and the maximum value is not more than 90°.

[0115] According to the posture included angle and the preset second reference included angle, an included angle difference value is calculated; the preset second reference included angle is a theoretical included angle of the two center lines in the standard posture, and the theoretical included angle is usually 0°, and the included angle difference value is the difference between the actual posture included angle and the second reference included angle, included angle difference = actual posture included angle-second reference included angle, and the numerical size is positively correlated with the angle deviation degree of the conveying target.

[0116] Real-time posture data is composed according to the included angle difference value and the offset data, and the real-time posture data is output. The included angle difference value (unit: degree) and the offset data (dimensionless normalized value) are integrated into real-time posture data and output. The data set reflects the posture characteristics of the conveying target from two dimensions of gravity distribution (offset data derived from volume difference) and overall deflection (included angle difference value derived from posture included angle), and provides multi-dimensional quantitative basis for subsequent posture adjustment.

[0117] The second image recognition algorithm realizes posture quantization by analyzing the overall shape and gravity distribution of the conveying target in combination with the center line angle relationship, can effectively capture the posture deviation caused by uneven loading or force imbalance, significantly improves the comprehensiveness and accuracy of posture recognition, and provides reliable support for posture adjustment under complex working conditions.

[0118] The posture comparison algorithm includes:

[0119] The angle difference and the offset data are extracted from the real-time posture data. The real-time posture data includes two core parameters output by the image recognition algorithm: the angle difference and the offset data. The angle difference reflects the angular deviation of the conveying target relative to the standard posture, and the unit is degree. The offset data reflects the position offset of the conveying target, and the unit is millimeter or normalized value. The algorithm separates the two parameters through the data analysis module as quantitative indicators of real-time posture characteristics. The positive and negative of the angle difference identify the deviation direction, and the positive and negative of the offset data identify the offset direction.

[0120] The angle reference difference and the offset reference data are extracted from the posture reference data. The posture reference data is the pre-stored standard posture parameter. The angle reference difference is the maximum angle deviation threshold allowed when the conveying target is in the ideal posture, such as ±1°. If the angle exceeds this range, it is determined to be an angle anomaly. The offset reference data is the maximum position offset threshold allowed in the ideal posture, such as ±5mm. If the position exceeds this range, it is determined to be a position anomaly. The two reference parameters are pre-set according to the accuracy requirements of the conveying line and the size characteristics of the batching frame, and are stored in the posture database. The algorithm calls the corresponding reference data by matching the current conveying line label.

[0121] The first deviation data is calculated according to the angle difference and the angle reference difference. The calculation formula is: first deviation data = angle difference ÷ angle reference difference. This calculation converts the angle deviation into a proportional value relative to the allowed threshold. For example, when the real-time angle difference is 2° and the angle reference difference is 1°, the first deviation data is 2.0, indicating that the angle deviation has exceeded the allowed threshold by 2 times. If the angle difference is -0.5°, the first deviation data is -0.5, indicating that the angle deviation is within the allowed range and deviates to the negative direction. Through division operation, the first deviation data realizes the normalization of the angle deviation, which is convenient for horizontal comparison of different orders of magnitude.

[0122] The second deviation data is calculated according to the offset data and the offset reference data. The calculation formula is: second deviation data = offset data ÷ offset reference data. The logic of angle deviation calculation is consistent. This formula converts the position offset into a proportional value relative to the allowed threshold. For example, when the offset data is 8mm and the offset reference data is 5mm, the second deviation data is 1.6, indicating that the position offset exceeds the allowed threshold by 60%. If the offset data is -3mm, the second deviation data is -0.6, indicating that the position offset is within the allowed range and deviates to the negative direction. Division operation also realizes the normalization of the position deviation, making the angle and position deviation have a unified quantitative scale.

[0123] The posture deviation data is calculated according to the first deviation value and the second deviation value. The specific steps are as follows: first, the first deviation value and the second deviation value are assigned a preset weight, such as an angle deviation weight of 0.5, a position deviation weight of 0.5, or the weight is adjusted according to the influence degree of the two on the stability of the posture, for example, an angle deviation weight of 0.6 and a position deviation weight of 0.4; then the first deviation value is multiplied by the corresponding weight, the second deviation value is multiplied by the corresponding weight, and the two product results are summed to obtain the final posture deviation data, posture deviation data = first deviation value x weight 1 + second deviation value x weight 2. In the weighted average process, the positive and negative signs of the deviation values are retained to reflect the deviation direction, for example, a positive deviation value indicates that the conveying target deviates or shifts to one side, and a negative deviation value indicates deviation to the opposite direction.

[0124] Through the above process, the posture comparison algorithm first normalizes the angle and position deviations to a proportion relative to the allowed threshold through division operation, eliminating the influence of different physical dimensions, and then realizes comprehensive evaluation of multi-dimensional deviations through weighted average. This way not only retains the direction characteristics and relative severity of each deviation, but also reflects the difference in the influence of different deviations on the overall posture through weight distribution.

[0125] The deviation control algorithm includes:

[0126] The difference between the posture deviation data and the preset deviation control data is calculated as the control difference value; the posture deviation data is the comprehensive deviation index output by the posture comparison algorithm; the comprehensive deviation index contains positive and negative signs, reflecting the deviation direction; the preset deviation control data is the maximum deviation threshold allowed by the system, which is usually set to 0, i.e. no deviation in ideal state. The calculation formula of the control difference value is: control difference value = posture deviation data - deviation control data. For example, when the posture deviation data is 1.2 (positive deviation), the control difference value is 1.2-0=1.2; when the posture deviation data is -0.8 (negative deviation), the control difference value is -0.8-0=-0.8. This difference directly reflects the degree and direction of the current posture deviation from the ideal state, providing an original error signal for subsequent control.

[0127] The preset filtering algorithm is used to obtain a control average value based on a plurality of control difference values; in order to eliminate instantaneous deviation interference caused by image noise, equipment vibration and other factors, the algorithm filters a plurality of control difference values that are continuously collected, such as control difference values in the last 5-10 sampling periods. The preset filtering algorithm can adopt a sliding average filtering or a weighted moving average filtering; the sliding average filtering obtains the control average value by calculating an arithmetic average value of the plurality of control difference values, and is suitable for a scenario with a low interference frequency; the weighted moving average filtering gives a higher weight to a recent control difference value and a lower weight to a long-term value, and can better reflect a dynamic change trend of the deviation. For example, when a 5-point sliding average is adopted, the control average value = (the n th control difference value + the (n-1) th +... + the (n-4) th) ÷ 5. Through the filtering processing, the control average value can effectively smooth instantaneous fluctuations and avoid misoperation of the actuator due to high-frequency interference.

[0128] The control data is calculated according to the control average value and a preset correction reference value; the preset correction reference value is a regulation amount coefficient corresponding to a unit deviation of the system, such as 1.5 N / unit deviation, that is, 1.5 N of correction force needs to be applied for each unit deviation, and the value is pre-calibrated according to the weight, friction coefficient and other physical characteristics of the conveying target. The calculation formula of the control data is: control data = control average value × correction reference value. For example, when the control average value is 1.2 and the correction reference value is 2 N / unit, the control data = 1.2 × 2 = 2.4 N, indicating that 2.4 N of correction force needs to be applied; if the control average value is -0.8, the control data = -0.8 × 2 = -1.6 N, and the negative sign indicates that the direction of the correction force is opposite to the positive direction. This step converts the normalized deviation signal into a force control parameter with physical meaning.

[0129] If the control data is less than a preset first reference data and the control data is used to adjust the first force receiving part, the control data is taken as the first force control data. If the control data is greater than a preset second reference data and the control data is used to adjust the second force receiving part, the control data is taken as the second force control data. The second reference data is greater than the first reference data.

[0130] The first force control data and the second force control data are determined by threshold judgment. The preset first reference data and the second reference data are thresholds for distinguishing the adjustment objects, and the second reference data is greater than the first reference data, for example, the first reference data is -0.5N, and the second reference data is 0.5N, and the values are set according to the minimum correction force requirement of the conveying target. The specific judgment logic is as follows: when the control data is less than the first reference data, for example, -0.6N<-0.5N, and the control data is used to adjust the first controlled part (for example, the left side of the batching frame), the control data is directly used as the first force control data, and the driving mechanism is driven to apply a corresponding adjustment force to the first controlled part, for example, to increase the left driving force; when the control data is greater than the second reference data, for example, 0.7N>0.5N, and the control data is used to adjust the second controlled part (for example, the right side of the batching frame), the control data is directly used as the second force control data, and the driving mechanism is driven to apply a corresponding adjustment force to the second controlled part, for example, to increase the right driving force. If the control data is between the first reference data and the second reference data, for example, -0.3N, it is determined that the deviation is within the allowable range, and the control data is not output temporarily, so as to avoid posture shaking caused by frequent adjustment.

[0131] Through the above process, the deviation control algorithm first obtains the original error signal through control difference calculation, obtains the smoothed control average value after filtering processing, and then converts it into quantized control data in combination with the correction reference value. Finally, the accurate adjustment of different controlled parts is realized through the differential threshold judgment. This design can not only effectively filter interference and ensure the stability of the control process, but also realize targeted adjustment through direction differentiation and threshold setting, and ensure the accuracy and efficiency of posture correction.

[0132] In the embodiment, the adjustment of the force size of the conveying line on the first controlled part and / or the second controlled part includes the following two implementation methods:

[0133] The first adjustment method: a first control conveying roller is arranged at a preset position on the conveying line, and the first control conveying roller includes two groups of driving small rollers, which are independently arranged and respectively connected with driving assemblies capable of independently controlling the rotating speed. The two groups of driving small rollers are arranged in parallel along the transverse direction of the conveying line, the axis of each group of small rollers is perpendicular to the conveying direction, and a preset distance is maintained between the two groups of small rollers, such as the width of the batching frame, to ensure that they can act on the bottom of the two sides of the batching frame respectively. Each group of driving small rollers is independently connected with a driving assembly, such as a servo motor and a speed reduction gear set, which can receive a control signal and independently adjust the rotating speed of the corresponding small roller. The two groups of driving assemblies are not mechanically connected, ensuring the independence of the rotating speed adjustment.

[0134] The rotation speeds of the two groups of active small rollers are initialized as the preset conveying rotation speed of the conveying line; the initial rotation speeds of the two groups of small rollers are set as the preset conveying rotation speed of the conveying line, such as 100 r / min, which is consistent with the rotation speed of other ordinary conveying rollers on the conveying line, so as to ensure that the conveying target can be conveyed at a uniform speed along the preset path when there is no posture deviation.

[0135] When the force of the conveying line on the first controlled part is adjusted according to the first force control data, the rotation speed increment of the active small roller corresponding to the first controlled part is adjusted according to the positive correlation of the first force control data, so as to adjust the driving force on the first controlled part. When the system outputs the first force control data for adjusting the first controlled part, the rotation speed increment of the active small roller corresponding to the first controlled part is adjusted according to the positive correlation of the first force control data. Specifically, the numerical value of the first force control data is in a positive proportional relationship with the rotation speed increment; if the first force control data is positive and the absolute value increases, it indicates that the driving force on the first controlled part needs to be increased, at this time the driving assembly corresponding to the active small roller increases the rotation speed, and the rotation speed increment increases with the increase of the force control data, such as the rotation speed increment increases by 5 r / min for each increase of 1 N of the force control data; if the first force control data is negative, it indicates that the driving force on the first controlled part needs to be reduced, at this time the driving assembly reduces the rotation speed of the corresponding small roller, and the rotation speed increment is negative and the absolute value increases with the increase of the absolute value of the force control data. The friction (driving force) between the active small roller and the bottom of the conveying target is changed by changing the rotation speed, so as to realize the accurate adjustment of the force on the first controlled part.

[0136] When the force of the conveying line on the second controlled part is adjusted according to the second force control data, the rotation speed increment of the active small roller corresponding to the second controlled part is adjusted according to the positive correlation of the second force control data, so as to adjust the driving force on the second controlled part. When the system outputs the second force control data for adjusting the second controlled part, the rotation speed increment of the active small roller corresponding to the second controlled part is adjusted according to the positive correlation of the second force control data. The adjustment logic is consistent with that of the first controlled part, that is, the numerical value of the second force control data is in a positive proportional relationship with the rotation speed increment of the corresponding small roller, and the driving force on the second controlled part is changed by changing the rotation speed.

[0137] The speed regulation trend of the active small roller corresponding to the first controlled part is opposite to that of the active small roller corresponding to the second controlled part. For example, when the conveying target is skewed to the left and needs to be corrected to the right, the first force control data is positive, the driving force on the left needs to be increased, the speed of the first controlled part corresponding to the active small roller is increased, for example, from 100 r / min to 110 r / min, and the second force control data is negative, the driving force on the right needs to be reduced, the speed of the second controlled part corresponding to the active small roller is reduced, for example, from 100 r / min to 90 r / min; conversely, when the conveying target is skewed to the right, the speed of the left small roller is reduced and the speed of the right small roller is increased. The speed difference between the two groups of small rollers forms a directional correction torque, which pushes the conveying target to gradually restore to the standard posture.

[0138] Through the above process, the first adjustment method uses two groups of independently controlled speed active small rollers, and the difference between the driving forces on the two sides is controlled by the positive correlation between the force control data and the speed increment, and the adjustment trend is opposite. This design can not only realize real-time correction through the rapid response of the speed, but also ensure the accuracy of the posture adjustment through the precise control of the speed difference, effectively solving the problem of uneven force caused by the deviation of the roller body synchronization, and ensuring the stable posture of the conveying target during the entire conveying process.

[0139] The second adjustment method: a second control conveying roller is arranged at a set position on the conveying line, the second control conveying roller includes two groups of driven small rollers, and the two groups of driven small rollers are independently arranged and respectively connected with an adjustment assembly that can be independently controlled to rise and fall. The two groups correspond to the first controlled part and the second controlled part of the conveying target respectively. The two groups of driven small rollers are arranged transversely and parallel along the conveying line, the axis is perpendicular to the conveying direction, the distance is matched with the width of the conveying target (such as a batching frame), and it is ensured that the two groups of driven small rollers can act on the bottom of the target on the two sides respectively. Each group of driven small rollers is independently connected with an adjustment assembly, such as an electric push rod or a lifting mechanism driven by a pneumatic cylinder, which can receive a control signal and independently adjust the lifting height and time of the corresponding small roller, and the two groups of adjustment assemblies are not mechanically linked, which ensures the independence of the lifting control.

[0140] The initial height of the two groups of driven small rollers is lower than the height of other conveying rollers on the conveying line; the initial height of the two groups of small rollers is set to be lower than the height of other ordinary conveying rollers on the conveying line, for example, 5-10 mm lower. At this time, the driven small rollers do not contact the bottom of the conveying target, avoiding additional friction interference to the conveying process when there is no posture deviation, and ensuring that the conveying target is only supported by other conveying rollers and keeps uniform motion.

[0141] When the first force control data is used to adjust the force of the first controlled part, the raising time of the driven small roller under the first controlled part is adjusted according to the first force control data. The raising time of the driven small roller under the first controlled part is adjusted according to the first force control data. The setting height is the height of the top surface of the other conveying roller, which ensures that the small roller can contact the bottom of the conveying target and generate friction. The raising time refers to the duration of the small roller from the initial low position to the set height and the duration of the contact. The specific adjustment logic is that the numerical value of the first force control data is positively proportional to the raising time. If the first force control data is positive and the absolute value increases, it indicates that the friction force acting on the first controlled part needs to be increased. At this time, the corresponding adjustment component is controlled to prolong the raising time. For example, if the force control data increases by 1 N, the raising time increases by 0.5 seconds. If the first force control data is negative, it indicates that the friction force needs to be reduced. At this time, the raising time is shortened, and the raising time can be zero, that is, the small roller remains in a low position without contact. By changing the contact time of the driven small roller with the conveying target, the cumulative effect of the friction force is adjusted, and the flexible adjustment of the force of the first controlled part is realized.

[0142] When the second force control data is used to adjust the force of the second controlled part, the raising time of the driven small roller under the second controlled part is adjusted according to the second force control data. The raising time of the driven small roller under the second controlled part is adjusted according to the second force control data. The adjustment logic is consistent with that of the first controlled part, that is, the numerical value of the second force control data is positively proportional to the raising time of the corresponding driven small roller. The cumulative effect of the friction force on the second controlled part is changed by changing the contact time.

[0143] The raising time adjustment trend of the driven small roller corresponding to the first controlled part and the driven small roller corresponding to the second controlled part is opposite. For example, when the conveying target is skewed to the left and needs to be corrected to the right, the first force control data is positive, the left friction needs to be enhanced, and the driven small roller corresponding to the first controlled part needs to be prolonged, for example, from 0.3 seconds to 0.8 seconds. At the same time, the second force control data is negative, the right friction needs to be reduced, and the driven small roller corresponding to the second controlled part needs to be shortened, for example, from 0.3 seconds to 0 seconds. Conversely, when the conveying target is skewed to the right, the left small roller shortens the raising time and the right small roller prolongs the raising time. Through the difference in contact time of the two groups of small rollers, the unbalanced effect of the friction forces on both sides is formed, and a smooth correction torque is generated to push the conveying target to gradually correct.

[0144] Through the above process, the second adjustment method utilizes two groups of independently lifted driven small rollers to realize the differentiated control of the friction force acting time on both sides through the positive correlation adjustment of force control data and lifting time based on the initial low position, and the adjustment trends are opposite. This design can not only avoid interference when there is no adjustment requirement through the non-contact initial state, but also realize flexible correction through the precise control of contact time, effectively reducing the target shaking or material spilling caused by rigid adjustment during conveying, and is especially suitable for the conveying posture adjustment scene of fragile materials such as traditional Chinese medicine raw materials, which improves the stability of the conveying process while ensuring the adjustment accuracy.

[0145] The embodiment of the present application also discloses a conveying posture automatic adjustment system of a raw material batching device, which comprises a processor, and the processor executes the steps of the conveying posture automatic adjustment method of the raw material batching device according to any one of the above.

[0146] The embodiment of the present application also discloses a storage medium, which stores a program, and the program is executed by a processor to realize the steps of the conveying posture automatic adjustment method of the raw material batching device according to any one of the above.

[0147] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for automatically adjusting the conveying posture of a raw material batching device, characterized in that: The steps include: Based on the raw material batching instructions, obtain real-time images of the conveyor line; Extract the conveying target and conveying line from the real-time image; Calculate the real-time posture data of the conveying target and the conveying line mark of the conveying line through the image recognition algorithm; Match the posture reference data from the preset posture database according to the conveyor line mark; Match the conveying direction data from the preset conveying database according to the conveying line mark; Setting the two sides of the transport target along the transport direction as a first controlled part and a second controlled part according to the transport direction data; Calculate the posture deviation data through the posture comparison algorithm based on the real-time posture data and the posture reference data; The first force control data is calculated based on the posture deviation data through the deviation control algorithm, and the force applied by the conveyor line to the first controlled part is adjusted based on the first force control data; and / or, the second force control data is calculated based on the posture deviation data through the posture force algorithm, and the force applied by the conveyor line to the second controlled part is adjusted based on the second force control data, and the control trend of the first force control data is opposite to the control trend of the second force control data.

2. The method for automatically adjusting the conveying posture of the raw material batching device according to claim 1, characterized in that: Image recognition algorithms include: Extract the contour line of the part of the conveying target close to the conveying line; The intersection center and intersection angle are calculated based on the contour line, and the intersection center and intersection angle correspond one to one; Extract the conveying edge line of the conveying line; fit the conveying line mark according to the conveying edge line; Select a pair of intersection centers and intersection angles that are closest to the conveying edge line; Calculate the offset distance between the conveying edge line and the center of the intersection; Calculate the offset data based on the offset distance and the preset reference distance; Calculate the posture angle between the conveying edge line and the median line of the intersection angle; Calculating an angle difference based on the posture angle and a preset first reference angle; The real-time attitude data is formed based on the angle difference and offset data and output.

3. The method for automatically adjusting the conveying posture of a raw material batching device according to claim 1, characterized in that: Image recognition algorithms include: Extract the conveying edge line of the conveying line; Extract the conveying center line according to the conveying edge line; Extract the target contour of the conveying target on the conveying line; According to the relative position of the conveying center line and the target contour, the projection line of the conveying center line on the target contour surface is fitted; Calculating the volumes of the target contour on both sides of the projection line as the first volume and the second volume; calculating a volume difference between the first volume and the second volume; Calculating offset data based on the volume difference and a preset volume reference value; Extract the center line of the target contour, which is parallel to the conveying center line when the conveying target is in a standard posture; Calculate the posture angle between the conveying center line and the contour center line; Calculating an angle difference based on the posture angle and a preset second reference angle; The real-time attitude data is formed based on the angle difference and offset data and output.

4. The method for automatically adjusting the conveying posture of a raw material batching device according to claim 2 or 3, characterized in that: The pose comparison algorithm includes: Extract angle difference and offset data from real-time posture data; Extracting angle reference difference and offset reference data from attitude reference data; Calculating first deviation data according to the angle difference and the angle reference difference; Calculating second deviation data based on the offset data and the offset reference data; The posture deviation data is calculated according to the first deviation value and the second deviation value.

5. The method for automatically adjusting the conveying posture of the raw material batching device according to claim 4, characterized in that: Deviation control algorithms include: The difference between the calculated attitude deviation data and the preset deviation control data is the control difference; A control average value is obtained based on multiple control differences using a preset filtering algorithm; The control data is calculated based on the control average value and the preset correction reference value; If the control data is less than the preset first reference data, and the control data is used to adjust the first force-bearing part, the control data is used as the first force control data; If the control data is greater than the preset second reference data, and the control data is used to adjust the second force-bearing part, the control data is used as the second force control data; The second reference data is greater than the first reference data.

6. The method for automatically adjusting the conveying posture of a raw material batching device according to claim 5, characterized in that: Adjusting the force exerted by the conveyor line on the first controlled part and / or the second controlled part includes the following steps: A first controlled conveying roller is provided at a set position on the conveying line. The first controlled conveying roller includes two sets of active small rollers. The two sets of active small rollers are independently provided and are respectively connected to a driving assembly with independently controllable rotational speed. Initialize the speed of the two sets of active small rollers to the preset conveying speed of the conveyor line; When the force exerted by the conveyor line on the first controlled part is adjusted according to the first force control data, the rotation speed increment of the active small roller corresponding to the first controlled part is adjusted in a positive correlation with the first force control data to adjust the driving force exerted on the first controlled part; When the force exerted by the conveyor line on the second controlled part is adjusted according to the second force control data, the rotation speed increment of the active small roller corresponding to the second controlled part is adjusted in a positive correlation with the second force control data to adjust the driving force exerted on the second controlled part; The rotation speed adjustment trends of the active small roller corresponding to the first controlled part and the active small roller corresponding to the second controlled part are opposite.

7. The method for automatically adjusting the conveying posture of a raw material batching device according to claim 5, characterized in that: Adjusting the force exerted by the conveyor line on the first controlled part and / or the second controlled part includes the following steps: A second control conveying roller is provided at a set position on the conveying line. The second control conveying roller includes two sets of driven small rollers. The two sets of driven small rollers are independently provided and are respectively connected to an adjustment component that can be independently controlled to rise and fall. Initialize the height of the two sets of driven small rollers to be lower than the height of other conveyor rollers on the conveyor line; When the force exerted by the conveyor line on the first controlled part is adjusted according to the first force control data, the time for the driven small roller corresponding to the first controlled part to be raised to the set height is adjusted in a positive correlation with the first force control data to adjust the friction time on the first controlled part; When the force exerted by the conveyor line on the second controlled part is adjusted according to the second force control data, the time for the driven small roller corresponding to the second controlled part to be raised to the set height is adjusted in a positive correlation with the second force control data to adjust the friction time on the second controlled part; The rising time adjustment trends of the driven small roller corresponding to the first controlled portion and the driven small roller corresponding to the second controlled portion are opposite.

8. A conveying posture automatic adjustment system for a raw material batching device, characterized in that: The method comprises a processor, wherein the processor executes the steps of the method for automatically adjusting the conveying posture of the raw material batching device according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium stores a program, and when the program is executed by the processor, the steps of the method for automatically adjusting the conveying posture of the raw material batching device according to any one of claims 1 to 7 are implemented.

Images