A feeding speed control method and device for a special coconut delivery machine

Abstract

The present invention provides a feeding speed control method and device for a special coconut feeding machine, which relates to the technical field of automatic control. The present invention measures the average mass and average diameter of the coconuts to be conveyed to determine the reference feeding speed; before conveying, the mass, water content and image of each coconut are collected in real time, and the coconut diameter and surface roughness are obtained based on the coconut image; an adjustment buffer value is set. When the deviation between the real-time mass and diameter and the average value exceeds the adjustment conversion value, the reference feeding speed is adjusted for the first time to generate the first feeding speed, and then the first feeding speed is adjusted for the second time according to the water content and surface roughness and the water content threshold and the reference surface roughness to generate the final feeding speed, so as to achieve precise feeding speed control.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and specifically to a feeding speed control method and device for a special coconut green feeder. Background Art

[0002] With the advancement of agricultural modernization, the automatic processing and transportation of coconut greens have become important links in improving production efficiency and product quality. During the transportation of coconut greens, precise control of the feeding speed is crucial. Traditional feeding equipment often fails to consider the differences between different individual coconut greens, resulting in unstable feeding speeds, either too slow or too fast, which may cause damage and quality degradation of coconut greens during transportation. Moreover, existing technologies have deficiencies in real-time monitoring and dynamic control of speed, making it difficult to effectively meet the transportation requirements of coconut greens of different specifications and increasing the loss cost. Therefore, there is an urgent need for a device that can dynamically adjust the feeding speed according to actual data to improve the safety and efficiency of coconut green transportation.

[0003] The currently existing automatic coconut green feeding systems face many technical defects, mainly manifested in insufficient adaptability to changes in coconut green characteristics and unreasonable speed control methods. Usually, the feeding speed is set relying on a single parameter, making it impossible to effectively cope with the diversity of coconut greens in terms of volume and roughness. This single-dimensional control method makes it difficult to finely adjust the feeding speed, which may lead to problems such as product damage, low turnover efficiency, and resource waste.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a feeding speed control method and device for a special coconut green feeder to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A feeding speed control method for a special coconut green feeder, the specific steps including:

[0008] Step 1: Measure the average mass of a batch of coconuts to be transported that are about to enter the feeder, and randomly select 10% of the total number of coconuts in this batch as coconut samples to measure their diameters, generating the average diameter of the coconut samples, which is used to replace the average diameter of this batch of coconuts. Based on the average mass and average diameter of the coconuts, determine the reference feeding speed;

[0009] Step 2: Before each coconut enters the conveyor belt, it passes through an electronic weighing sensor, an optical sensor, and an infrared spectrometer respectively to collect the mass and water content of the coconut in real time, as well as the coconut image;

[0010] Step 3: Grayscale the coconut image to generate a first recognition image. Based on the canny algorithm, extract the edge pixel points of the first recognition image, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the coconut based on the variance of the LBP histogram;

[0011] Step 4: Set an adjustment buffer value. When the mass and diameter of a single coconut collected in real time do not exceed the adjustment buffer value relative to the average mass and average diameter of the coconuts, keep the first feeding speed equal to the reference feeding speed. When it exceeds the adjustment buffer value, generate a first adjustment amplitude to adjust the reference feeding speed and calculate the first feeding speed;

[0012] Step 5: Perform max-min normalization on the water content and surface roughness of the coconut. Set a water content threshold and a reference surface roughness. Based on the normalized water content and surface roughness and the water content threshold and reference surface roughness, generate a second adjustment amplitude to adjust the first feeding speed and generate the final feeding speed.

[0013] Further, the principle for generating the average mass and average diameter of the coconuts is as follows:

[0014] The formula for calculating the average mass is:

[0015] ;

[0016] Among them, represents the average mass of this batch of coconuts to be conveyed, represents the total mass of this batch of coconuts to be conveyed, represents the number of this batch of coconuts to be conveyed;

[0017] The formula for generating the average diameter of the coconuts is:

[0018] ;

[0019] Among them, represents the average diameter of the coconuts, represents the index of the coconut sample, represents the number of coconut samples, represents the th diameter of the coconut sample.

[0020] Further, the principle for extracting the edge pixel points of the first recognition image based on the canny algorithm is as follows:

[0021] For each pixel point in the first recognition image, the matrix formed by the pixel point and its neighboring pixel points is respectively convolved with the horizontal direction template and the vertical direction template of the Prewitt operator to generate the gray - level differences of the pixel point in the horizontal and vertical directions. The formulas are as follows:

[0022] ;

[0023] ;

[0024] ;

[0025] ;

[0026] Among them, represents the horizontal direction template of the Prewitt operator, represents the vertical direction template of the Prewitt operator, represents the horizontal direction difference of the pixel point, represents the vertical direction difference of the pixel point, represents the coordinates of the pixel point;

[0027] According to the gray - level differences in the horizontal and vertical directions, the gradient magnitude of each pixel point is generated. The formula is as follows:

[0028] ;

[0029] Among them, represents the gradient magnitude of the pixel point with coordinates , represents the horizontal direction difference of the pixel point, represents the vertical direction difference of the pixel point;

[0030] A preset edge threshold is set. When the gradient magnitude of the pixel point is higher than the edge threshold, the pixel point is retained as an edge pixel point; otherwise, the pixel point is discarded.

[0031] Furthermore, the principle for generating the surface roughness of the coconut is as follows:

[0032] For each pixel point in the first recognition image, taking it as the center, compare its gray value with that of the surrounding neighborhood pixel points. When the gray value of the neighborhood pixel point is greater than or equal to the center pixel point, mark it as 1, otherwise mark it as 0. Starting from the neighborhood pixel point in the upper left corner of the center pixel point, arrange all the marks in a clockwise direction into a binary number, and convert the binary number into a decimal number, which is used as the LBP value of the center pixel point. Statistically analyze the LBP values of all pixel points in the first recognition image to generate an LBP histogram reflecting the occurrence probability of different LBP values, and calculate the variance of the LBP histogram. The formula is as follows:

[0033] ;

[0034] ;

[0035] ;

[0036] Among them, represents the index of the LBP value, and , represents the th occurrence probability of the LBP value, represents the number of occurrences of the th LBP value, represents the mean value of the LBP histogram, represents the variance of the LBP histogram;

[0037] ;

[0038] Among them, represents the surface roughness of the coconut.

[0039] Furthermore, the principle for generating the first adjustment amplitude is as follows:

[0040] Set the adjustment buffer value to 10% of the average mass and average diameter of the coconut. When and , there is no need to adjust the reference feeding speed at this time;

[0041] Among them, represents the mass of a single coconut collected in real time, represents the diameter of a single coconut collected in real time;

[0042] Otherwise, generate the first adjustment amplitude to adjust the reference feeding speed. The formula is as follows:

[0043] ;

[0044] ;

[0045] ;

[0046] Among them, represents the quality adjustment range, represents the quality influence coefficient, represents the diameter adjustment range, represents the diameter influence coefficient, represents the first adjustment range;

[0047] The formula for calculating the first feeding speed is:

[0048] ;

[0049] Among them, represents the first feeding speed, represents the reference feeding speed.

[0050] Furthermore, the principle for generating the second adjustment range is:

[0051] ;

[0052] Among them, represents the second adjustment range, represents the water content after normalization, represents the water content threshold, represents the weight coefficient of the water content, represents the surface roughness after normalization, represents the reference surface roughness, represents the weight coefficient of the surface roughness, , and ;

[0053] The formula for generating the final feeding speed is:

[0054] ;

[0055] Among them, represents the final feeding speed.

[0056] The present invention also provides a feeding speed control device for a coconut special feeding machine, and the device is used to implement the feeding speed control method of the coconut special feeding machine as described above, and specifically includes:

[0057] A pretreatment module, which is used to measure the average quality of a batch of coconuts to be conveyed that are about to enter the feeding machine, and randomly select 10% of the total number of coconuts in this batch of coconut samples to measure the diameter, generate the average diameter of the coconut samples, and use it to replace the average diameter of this batch of coconuts, and determine the reference feeding speed based on the average quality and average diameter of the coconuts;

[0058] A data acquisition module, which is used to respectively pass each coconut through an electronic weighing sensor, an optical sensor and an infrared spectrometer before entering the conveyor belt, and collect the mass and water content of the coconut in real time, as well as the coconut image;

[0059] A data processing module, which is used to grayscale the coconut image to generate a first recognition image, extract the edge pixel points of the first recognition image based on the canny algorithm, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the coconut based on the variance of the LBP histogram;

[0060] A first control module, which is used to set an adjustment buffer value. When the mass and diameter of a single coconut collected in real time do not exceed the adjustment buffer value relative to the average mass and average diameter of the coconut, keep the first feeding speed equal to the reference feeding speed. When it exceeds the adjustment buffer value, generate a first adjustment amplitude to adjust the reference feeding speed, and calculate the first feeding speed;

[0061] A comprehensive control module, which is used to perform maximum-minimum normalization on the water content and surface roughness of the coconut, set a water content threshold and a reference surface roughness, and generate a second adjustment amplitude to adjust the first feeding speed based on the normalized water content and surface roughness and the water content threshold and the reference surface roughness, and generate a final feeding speed.

[0062] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0063] The present invention sets a corresponding reference feeding speed according to the average mass and average diameter of the coconut, effectively matching the characteristics of the coconut with the operation of the feeder, providing a standardized reference for the feeding speed in the whole feeding process, and helping to improve the accuracy of subsequent speed adjustment; before transporting the coconut, the mass, water content and image data of the coconut are collected in real time to ensure real-time feedback and reduce the loss caused by delayed feedback. The diameter and roughness of the coconut are obtained through the canny algorithm and the local binary pattern respectively, improving the accuracy of the data.

[0064] The present invention also determines whether the feeding speed needs to be adjusted by comparing the quality of the young coconuts collected in real time and the diameter of the young coconuts with the average quality and average diameter. By setting an adjustment buffer value, the device can flexibly adjust the feeding speed according to the actually collected quality and diameter data of the young coconuts, avoiding frequent speed adjustments caused by some minor changes and reducing resource consumption. When the speed needs to be adjusted, the quality and diameter of the young coconuts are considered simultaneously to make a primary adjustment to the reference feeding speed first, avoiding a decrease in efficiency due to speed mismatch. Then, the feeding speed is adjusted again according to the water content and surface roughness of the young coconuts, enabling fine control of the feeding speed, ensuring that each batch of young coconuts can be processed individually according to their characteristics, ensuring that the feeding speed matches the actual state of the young coconuts. Through two precise adjustments of the feeding speed, the first-round adjustment can quickly respond to characteristic changes, and the second-round adjustment further optimizes to ensure the stability and safety of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 is a schematic flowchart of the method according to an embodiment of the present invention;

[0066] Figure 2 is a schematic diagram of the device module according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0068] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meaning understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not denote any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or items appearing before this word cover the elements or items listed after this word and their equivalents, without excluding other elements or items. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0069] Embodiment:

[0070] Please refer to Figure 1 , the present invention provides a technical solution:

[0071] A method for controlling the feeding speed of a special feeding machine for young coconuts, the specific steps including:

[0072] Step 1: Measure the average mass of a batch of coconuts to be conveyed that are about to enter the feeder, and randomly select coconut samples accounting for 10% of the total number of coconuts in this batch to measure their diameters, generate the average diameter of the coconut samples, and use it to replace the average diameter of this batch of coconuts. Determine the reference feeding speed based on the average mass and average diameter of the coconuts.

[0073] In this embodiment, the principles for generating the average mass and average diameter of the coconuts are as follows:

[0074] The formula for calculating the average mass is:

[0075] ;

[0076] where, represents the average mass of this batch of coconuts to be conveyed, represents the total mass of this batch of coconuts to be conveyed, represents the number of this batch of coconuts to be conveyed;

[0077] The formula for generating the average diameter of the coconuts is:

[0078] ;

[0079] where, represents the average diameter of the coconuts, represents the index of the coconut samples, represents the number of the coconut samples, represents the diameter of the

[0080] Under the condition of knowing the average mass and average diameter, set the reference feeding speed based on expert decision. The reference feeding speed should meet the requirements of actual conveying efficiency, and considering the mass and diameter of the coconuts, avoid the situation of too fast or too slow feeding.

[0081] Step 2: Before each coconut enters the conveyor belt, it passes through an electronic weighing sensor, an optical sensor, and an infrared spectrometer respectively to collect the mass and water content of the coconut in real time, as well as the coconut image.

[0082] Step 3: Gray-scale process the coconut image to generate a first recognition image. Based on the canny algorithm, extract the edge pixel points of the first recognition image, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the coconut based on the variance of the LBP histogram.

[0083] In this embodiment, the principle for extracting the edge pixel points of the first recognition image based on the canny algorithm is:

[0084] For each pixel point in the first recognition image, the matrix formed by the pixel point and its neighboring pixel points is convolved with the horizontal direction template and the vertical direction template of the Prewitt operator respectively to generate the gray level difference of the pixel point in the horizontal direction and the vertical direction. The formula is as follows:

[0085] ;

[0086] ;

[0087] ;

[0088] ;

[0089] Among them, represents the horizontal direction template of the Prewitt operator, represents the vertical direction template of the Prewitt operator, represents the horizontal direction difference of the pixel point, represents the vertical direction difference of the pixel point, represents the coordinates of the pixel point;

[0090] According to the gray level differences in the horizontal direction and the vertical direction, the gradient magnitude of each pixel point is generated. The formula is as follows:

[0091] ;

[0092] Among them, represents the gradient magnitude of the pixel point with coordinates , represents the horizontal direction difference of the pixel point, represents the vertical direction difference of the pixel point;

[0093] A preset edge threshold is set. When the gradient magnitude of the pixel point is higher than the edge threshold, the pixel point is retained as an edge pixel point; otherwise, the pixel point is discarded.

[0094] The principle of the preset edge threshold is as follows: The histogram of the gradient magnitude is generated by combining the occurrence frequencies of the gradient magnitudes of all pixel points. The initial edge threshold is selected within the range of 70% - 90% in the histogram. A higher percentile helps to suppress noise and reduce false alarms, but may miss fine edges. A lower percentile can capture more details, but may cause too much noise to be recognized as edges. Therefore, after the initial edge threshold is selected, the edge pixel points of the first recognition image are extracted, and the domain experts judge the extraction effect of the edge pixel points and adjust the edge threshold according to the extraction effect of the edge pixel points until the edge extracted according to the edge threshold meets the requirements;

[0095] The principle for generating the surface roughness of the coconut is as follows:

[0096] For each pixel in the first recognition image, taking it as the center, compare its grayscale value with that of the surrounding neighborhood pixels. When the grayscale value of the neighborhood pixel is greater than or equal to the center pixel, mark it as 1, otherwise mark it as 0. Starting from the neighborhood pixel in the upper left corner of the center pixel, arrange all the marks in a clockwise direction into a binary number, and convert the binary number into a decimal number, which is used as the LBP value of the center pixel. Statistically analyze the LBP values of all pixels in the first recognition image to generate an LBP histogram reflecting the occurrence probability of different LBP values, and calculate the variance of the LBP histogram. The formula is as follows:

[0097] ;

[0098] ;

[0099] ;

[0100] where, represents the index of the LBP value, and , represents the probability of the th LBP value occurring, represents the number of times the th LBP value occurs, represents the mean value of the LBP histogram, represents the variance of the LBP histogram;

[0101] ;

[0102] where, represents the surface roughness of the coconut.

[0103] The larger the variance of the LBP histogram, the more complex the texture and the rougher the surface.

[0104] Step 4: Set an adjustment buffer value. When the quality and diameter of a single coconut collected in real time do not exceed the adjustment buffer value relative to the average quality and average diameter of the coconuts, keep the first feeding speed equal to the reference feeding speed. When it exceeds the adjustment buffer value, generate a first adjustment amplitude to adjust the reference feeding speed and calculate the first feeding speed;

[0105] In this embodiment, the principle for generating the first adjustment amplitude is as follows:

[0106] Set the adjustment buffer value to 10% of the average quality and average diameter of the coconuts. When and , there is no need to adjust the reference feeding speed at this time;

[0107] Adjusting the buffer value is an allowable deviation range. When the deviation of the mass and diameter of a single coconut from the reference value is within the buffer value range, the feeding speed remains unchanged, avoiding frequent adjustment of the feeding speed due to small changes in mass and diameter;

[0108] Among them, represents the mass of a single coconut collected in real time, represents the diameter of a single coconut collected in real time;

[0109] Otherwise, generate the first adjustment amplitude to adjust the reference feeding speed, and the formula is:

[0110] ;

[0111] ;

[0112] ;

[0113] Among them, represents the mass adjustment amplitude, represents the mass influence coefficient, represents the diameter adjustment amplitude, represents the diameter influence coefficient, represents the first adjustment amplitude, , , and ;

[0114] According to and size relationship, there may be four situations: both mass and diameter are lower than the average mass and average diameter, both mass and diameter are higher than the average mass and average diameter, mass is higher than the average mass and diameter is lower than the average diameter, mass is lower than the average mass and diameter is higher than the average diameter. When the mass of a single coconut exceeds the adjustment buffer value, the larger the mass, the slower the conveying speed. To avoid the conveying speed being too slow, it is necessary to increase the feeding speed for regulation: when the diameter of a single coconut exceeds the adjustment buffer value, the larger the diameter, the larger the coconut, the slower the conveying speed, and it is necessary to increase the feeding speed for regulation. When takes a negative value, it means it has a slowing effect on the reference feeding speed. The mass adjustment amplitude is proportional to the difference between the mass of a single coconut collected in real time and the average mass, and the diameter adjustment amplitude is proportional to the difference between the diameter of a single coconut collected in real time and the average diameter. Calculate the adjustment amplitudes of mass and diameter on the reference feeding speed respectively, and add them up to get the final adjustment amplitude of the reference speed. The mass directly determines the inertia of the coconut and the load of the conveyor belt. Therefore, the mass influence coefficient is larger, mainly affects the arrangement of coconuts. Therefore, the diameter influence coefficient takes a smaller value, take , 。

[0115] The formula for calculating the first feeding speed is:

[0116] ;

[0117] Wherein, represents the first feeding speed, represents the reference feeding speed.

[0118] Step 5: Perform maximum-minimum normalization on the water content and surface roughness of the coconut, set the water content threshold and the reference surface roughness, and generate a second adjustment amplitude based on the normalized water content and surface roughness and the water content threshold and the reference surface roughness to adjust the first feeding speed and generate the final feeding speed.

[0119] In this embodiment, the principle for generating the second adjustment amplitude is:

[0120] ;

[0121] Wherein, represents the second adjustment amplitude, represents the normalized water content, represents the water content threshold, represents the weight coefficient of the water content, represents the normalized surface roughness, represents the reference surface roughness, represents the weight coefficient of the surface roughness, , and ;

[0122] The water content threshold represents the dividing line at which the water content has two effects on the feeding speed, namely accelerating and decelerating. The reference surface roughness represents the value when the surface roughness just does not affect the feeding speed of the coconut. The water content threshold and the reference surface roughness are respectively subjected to maximum-minimum normalization with the water content and the surface roughness under the same conditions, and are determined based on expert evaluation. When the water content is less than or equal to the water content threshold, as the water content of the coconut increases, the surface of the coconut will gradually become wet and sticky, increasing the friction with the conveyor belt of the feeder. If not adjusted, the feeding speed will decrease. At this time, it is necessary to increase the feeding speed to balance this effect. When the water content is greater than the water content threshold, there is too much water between the coconut and the conveyor belt, resulting in the surface of the coconut becoming slippery and reducing the friction. At this time, as the water content of the coconut increases, if not adjusted, the conveying speed will increase, and it is necessary to reduce the feeding speed to balance this effect. When the surface roughness is higher than the reference surface roughness, the friction between the coconut and the conveyor belt of the feeder is too large. If not adjusted, the feeding speed will decrease, and it is necessary to increase the feeding speed to balance this effect. When the surface roughness is lower than or equal to the reference surface roughness, the coconut is too smooth and the friction with the feeder is too small. If not adjusted, the feeding speed will increase. Therefore, it is necessary to reduce the feeding speed to balance this effect. The water content of the coconut is easily affected by factors such as storage conditions and transportation time, resulting in fluctuations, while the surface roughness is relatively more stable. Take , .

[0123] The formula for generating the final feeding speed is:

[0124] ;

[0125] Among them, represents the final feeding speed.

[0126] Please refer to Figure 2 The present invention also provides a feeding speed control device for a coconut-specific feeder. The device is used to implement the feeding speed control method of the coconut-specific feeder, and specifically includes:

[0127] A preprocessing module, which is used to measure the average mass of a batch of coconuts to be conveyed that are about to enter the feeder, and randomly select 10% of the total number of coconuts in this batch as coconut samples to measure the diameter, generate the average diameter of the coconut samples, and use it to replace the average diameter of this batch of coconuts, and determine the reference feeding speed based on the average mass and average diameter of the coconuts;

[0128] A data acquisition module, which is used to respectively pass through an electronic weighing sensor, an optical sensor and an infrared spectrometer for each coconut before it enters the conveyor belt, and real-time collect the mass and water content of the coconut, as well as the coconut image;

[0129] A data processing module is used to grayscale the coconut image to generate a first recognition image, extract the edge pixel points of the first recognition image based on the canny algorithm, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the coconut based on the variance of the LBP histogram.

[0130] A first control module is used to set an adjustment buffer value. When the mass of a single coconut and the coconut diameter collected in real time do not exceed the adjustment buffer value relative to the average mass and average diameter of the coconuts, keep the first feeding speed equal to the reference feeding speed. When exceeding the adjustment buffer value, generate a first adjustment amplitude to adjust the reference feeding speed and calculate the first feeding speed.

[0131] A comprehensive control module is used to perform maximum-minimum normalization on the water content and surface roughness of the coconut, set a water content threshold and a reference surface roughness, and generate a second adjustment amplitude to adjust the first feeding speed based on the normalized water content and surface roughness and the water content threshold and reference surface roughness, and generate a final feeding speed.

[0132] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0133] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0134] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application.

Claims

1. A method for controlling the feeding speed of a special feeding machine for young coconuts, characterized in that, The specific steps include: Step 1: Measure the average mass of a batch of coconuts to be conveyed that are about to enter the feeder, and randomly select coconut samples accounting for 10% of the total number of coconuts in this batch to measure their diameters, generate the average diameter of the coconut samples, and use it to replace the average diameter of this batch of coconuts. Determine the reference feeding speed based on the average mass and average diameter of the coconuts. Step 2: Before each coconut enters the conveyor belt, it passes through an electronic weighing sensor, an optical sensor, and an infrared spectrometer respectively to collect the mass and water content of the coconut in real time, as well as the coconut image. Step 3: Grayscale the coconut image to generate a first recognition image. Extract the edge pixel points of the first recognition image based on the canny algorithm, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the coconut based on the variance of the LBP histogram. Step 4: Set an adjustment buffer value. When the mass and diameter of a single coconut collected in real time do not exceed the adjustment buffer value relative to the average mass and average diameter of the coconuts, keep the first feeding speed equal to the reference feeding speed. When it exceeds the adjustment buffer value, generate a first adjustment amplitude to adjust the reference feeding speed and calculate the first feeding speed. Step 5: Perform maximum-minimum normalization on the water content and surface roughness of the coconut, set a water content threshold and a reference surface roughness. Based on the normalized water content and surface roughness and the water content threshold and reference surface roughness, generate a second adjustment amplitude to adjust the first feeding speed and generate the final feeding speed.

2. The feeding speed control method of a special coconut delivery machine according to claim 1, characterized in that: The principles for generating the average mass and average diameter of coconuts in Step 1 are as follows: The formula for calculating the average mass is: Among them, represents the average quality of this batch of young coconuts to be transmitted, M total represents the total quality of this batch of young coconuts to be transmitted, and N represents the quantity of this batch of young coconuts to be transmitted; The formula for generating the average diameter of coconuts is: Among them, represents the average diameter of the young coconuts, i represents the index of the young coconut samples, 0.1N represents the number of young coconut samples, and D i represents the diameter of the i-th young coconut sample.

3. The feeding speed control method of a special coconut delivery machine according to claim 1, characterized in that: The principle for extracting the edge pixel points of the first recognition image based on the canny algorithm in Step 3 is as follows: For each pixel point in the first recognition image, convolve the matrix composed of the pixel point and its neighborhood pixel points with the horizontal direction template and vertical direction template of the Prewitt operator respectively to generate the gray difference of the pixel point in the horizontal and vertical directions. The formula is: Among them, P X represents the horizontal direction template of the Prewitt operator, P Y represents the vertical direction template of the Prewitt operator, G x represents the horizontal direction difference of the pixel point, G y represents the vertical direction difference of the pixel point, and (x, y) represents the coordinates of the pixel point; According to the gray differences in the horizontal and vertical directions, generate the gradient amplitude of each pixel point. The formula is: Among them, G(x, y) represents the gradient magnitude of the pixel point with coordinates (x, y), and G x represents the horizontal direction difference of the pixel point, and G y represents the vertical direction difference of the pixel point; Preset an edge threshold. When the gradient amplitude of a pixel point is higher than the edge threshold, retain the pixel point as an edge pixel point, otherwise discard the pixel point.

4. The feeding speed control method of a special coconut delivery machine according to claim 1, characterized in that: The principle for generating the surface roughness of the coconut in Step 3 is as follows: For each pixel point in the first recognition image, with it as the center, compare the gray value of it with that of the surrounding neighborhood pixel points. When the gray value of the neighborhood pixel point is greater than or equal to the center pixel point, mark it as 1, otherwise mark it as 0. Starting from the neighborhood pixel point in the upper left corner of the center pixel point, arrange all the marks in a clockwise direction into a binary number, and convert the binary number into a decimal number as the LBP value of the center pixel point. Statistically analyze the LBP values of all pixel points in the first recognition image to generate an LBP histogram reflecting the occurrence probability of different LBP values, and calculate the variance of the LBP histogram. The formula is: where \(j\) represents the index of the LBP value, and \(j\in\{0,255\}\), \(p(j)\) represents the probability of the \(j\)-th LBP value occurring, \(h\) j represents the number of occurrences of the \(j\)-th LBP value, \(\mu\) represents the mean of the LBP histogram, \(\sigma\) 2 represents the variance of the LBP histogram; R = σ 2 Among them, R represents the surface roughness of the young coconut.

5. The feeding speed control method of a special coconut delivery machine according to claim 2, characterized in that: The principle for generating the first adjustment amplitude in step 4 is as follows: Set the adjustment buffer value to 10% of the average mass and average diameter of the coconut, when and at this time, there is no need to adjust the reference feeding speed; Among them, M represents the mass of a single young coconut collected in real time, and d represents the diameter of a single young coconut collected in real time; Otherwise, generate the first adjustment amplitude to adjust the reference feeding speed, and the formula is: Among them, k1 represents the mass adjustment amplitude, α represents the mass influence coefficient, k2 represents the diameter adjustment amplitude, β represents the diameter influence coefficient, and A1 represents the first adjustment amplitude; The formula for calculating the first feeding speed is: V1 = V0 + A1·V0 Among them, V1 represents the first feeding speed, and V0 represents the reference feeding speed.

6. The feeding speed control method of a special coconut delivery machine according to claim 5, characterized in that: The principle for generating the second adjustment amplitude in step 5 is as follows: Among them, A2 represents the second adjustment amplitude, W0 represents the water content after normalization, W threshold represents the water content threshold, w1 represents the weight coefficient of the water content, R0 represents the surface roughness after normalization, R base represents the reference surface roughness, w2 represents the weight coefficient of the surface roughness, w1 + w2 = 1, and w1 < w2; The formula for generating the final feeding speed is: V2 = V1 + A2·V1 Among them, V2 represents the final feeding speed.

7. A feeding speed control device for a special coconut delivery machine, characterized in that: The device is used to implement the feeding speed control method of the special feeding machine for young coconuts described in any one of claims 1-6, and specifically includes: A preprocessing module, which is used to measure the average mass of a batch of young coconuts to be conveyed that are about to enter the feeding machine, randomly select 10% of the total number of young coconuts in this batch as coconut samples to measure the diameter, generate the average diameter of the coconut samples, and use it to replace the average diameter of this batch of young coconuts, and determine the reference feeding speed based on the average mass and average diameter of the young coconuts; A data acquisition module, which is used for each young coconut to pass through an electronic weighing sensor, an optical sensor and an infrared spectrometer respectively before entering the conveyor belt, and collect the mass, water content and coconut image of the young coconut in real time; A data processing module, which is used to grayscale the coconut image to generate a first recognition image, extract the edge pixel points of the first recognition image based on the canny algorithm, measure the distance between the two farthest edge pixel points as the coconut diameter, generate an LBP histogram based on the local binary pattern, and generate the surface roughness of the young coconut based on the variance of the LBP histogram; A first control module, which is used to set an adjustment buffer value. When the mass and diameter of a single young coconut collected in real time do not exceed the adjustment buffer value relative to the average mass and average diameter of the young coconuts, keep the first feeding speed equal to the reference feeding speed. When it exceeds the adjustment buffer value, generate the first adjustment amplitude to adjust the reference feeding speed, and calculate the first feeding speed; A comprehensive control module, which is used to perform maximum-minimum normalization on the water content and surface roughness of the young coconut, set a water content threshold and a reference surface roughness, and generate a second adjustment amplitude to adjust the first feeding speed based on the normalized water content and surface roughness and the water content threshold and reference surface roughness, and generate the final feeding speed.

Images