Meat product processing control system and method based on data analysis

Abstract

The present invention discloses a meat product processing process control system and method based on data analysis, and belongs to the technical field of general control or regulation systems. The present invention collects pictures of raw meat to be minced and pictures of processing equipment blades to obtain raw meat data and processing equipment blade data; imports the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing the raw meat; imports the processing equipment blade data into a processing equipment wear degree evaluation model to evaluate the degree of wear of the processing equipment blades; obtains the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimates the mincing time for the raw meat to reach a target state according to a mincing time estimation strategy. The present invention combines the raw meat data with the processing equipment blade data to comprehensively analyze the impact on mincing meat, thereby predicting the optimal mincing time and ensuring the product quality of the mincing process during meat product processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of general control or regulation systems, and specifically relates to a meat product processing process control system and method based on data analysis. Background Art

[0002] In meat processing, minced meat processes the whole piece of meat raw material into uniform meat filling or meat particles, providing a basis for subsequent mixing, molding and other processing steps, making the meat filling texture more delicate and uniform, and the taste richer. The minced meat filling is easier to carry out subsequent molding, filling and other processing steps, which is convenient for the production of various meat products such as sausages, meatballs, meat patties, etc.

[0003] The existing meat mincing process control part is to judge the degree of meat mincing by the motor speed, and mince the meat filling with the degree of mincing required by the user, but it lacks the comprehensive analysis of the influence of raw meat data and processing equipment blade data on mincing, so it is impossible to predict the optimal mincing time, resulting in low mincing efficiency and poor mincing effect;

[0004] In order to solve the above problems, the present invention designs a meat product processing process control system and method based on data analysis. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes a meat processing process control system and method based on data analysis. The present invention collects pictures of raw meat to be minced and pictures of processing equipment blades to obtain raw meat data and processing equipment blade data; imports the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing the raw meat; imports the processing equipment blade data into a processing equipment wear degree evaluation model to evaluate the degree of wear of the processing equipment blades; obtains the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimates the mincing time for the raw meat to reach a target state according to a mincing time estimation strategy. The present invention combines the raw meat data with the processing equipment blade data to comprehensively analyze the impact on mincing meat, thereby predicting the optimal mincing time and ensuring the product quality of the mincing process in the meat processing process.

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

[0007] The meat product processing process control method based on data analysis includes the following specific steps:

[0008] S1. Collect pictures of raw meat to be minced and pictures of blades of processing equipment to obtain data of raw meat and blades of processing equipment;

[0009] S2, importing the raw meat data into the raw meat evaluation model to evaluate the difficulty of mincing the raw meat;

[0010] S3, importing the processing equipment blade data into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade;

[0011] S4. Obtain the difficulty of mincing the raw meat and the degree of wear of the blades of the processing equipment, and estimate the mincing time for the raw meat to reach a target state according to the mincing time estimation strategy.

[0012] Preferably, S1 comprises the following specific steps:

[0013] S11, collecting a picture of raw meat to be minced, segmenting the raw meat picture into fat area, lean meat area and fascia area through an image processing module, obtaining the area, height and hardness of the fat area, lean meat area and fascia area, and collecting the temperature and volume of the raw meat;

[0014] S12, collecting images of processing equipment blades, and obtaining the number of cracks, crack depth, and crack distance of the processing equipment blades through the image processing module.

[0015] Preferably, S2 comprises the following specific steps:

[0016] The raw meat data is imported into a raw meat evaluation model to evaluate the difficulty of mincing the raw meat. The raw meat evaluation model includes a raw meat mincing difficulty index calculation formula, and the raw meat mincing difficulty index calculation formula is:

[0017] ;

[0018] In the formula, is the raw meat temperature collected, The standard temperature of raw meat. is the area of ​​raw meat fat area, is the height of the fat area of ​​raw meat, is the volume of raw meat, The hardness of the fat area of ​​raw meat, The standard hardness of the fat area of ​​raw meat. is the area of ​​raw lean meat area, is the height of the raw meat lean area, The hardness of the lean area of ​​raw meat. The standard hardness of the lean area of ​​raw meat. is the area of ​​the raw meat fascia, is the height of the raw meat fascia area, The hardness of the raw meat fascia area, It is the standard hardness of the raw meat fascia area.

[0019] Preferably, the standard temperature of raw meat material , Standard hardness of raw meat fat area , Standard hardness of raw meat lean area And the standard hardness of the raw meat fascia area The value is obtained by selecting 500 raw meat samples, measuring the temperature of the samples, the hardness of the fat area, the hardness of the lean meat area and the hardness of the fascia area, and then taking the average value of the measured data as the standard temperature of the raw meat material , Standard hardness of raw meat fat area , Standard hardness of raw meat lean area And the standard hardness of the raw meat fascia area The value of .

[0020] Preferably, S3 comprises the following specific steps:

[0021] The processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade. The processing equipment wear degree evaluation model includes a processing equipment wear degree calculation formula, and the processing equipment wear degree calculation formula is:

[0022] ;

[0023] In the formula, is the depth of the nth crack of the ith blade, is the safety threshold of blade crack depth, is the number of blades in the processing equipment, The number of cracks for each blade, is the distance between the nth crack of the ith blade and its closest crack, is the safety distance threshold between the two closest cracks. hour, The value is 0.

[0024] Preferably, S4 comprises the following specific steps:

[0025] The difficulty of mincing raw meat and the degree of wear of the blades of the processing equipment are obtained, and the mincing time for the raw meat to reach the target state is estimated according to the mincing time estimation strategy. The mincing time estimation strategy includes an optimal mincing time calculation formula, and the optimal mincing time calculation formula is:

[0026] ;

[0027] In the formula, For standard mincing time, is the coefficient of the impact of raw meat mincing difficulty index on mincing time, is the coefficient of the influence of the wear degree of processing equipment on the mincing time, , are positive numbers and .

[0028] Preferably, the standard mincing time is determined by selecting 500 portions of raw meat samples of the same weight, putting them into a brand new processing equipment for mincing, recording the mincing time for the raw meat samples to reach the target state, and taking the average value of the measured data as the standard mincing time;

[0029] Preferably, the safe threshold of blade crack depth is , the safety distance threshold between the two closest cracks , the coefficient of the impact of raw meat mincing difficulty index on mincing time The influence of wear degree of processing equipment on the mincing time The value of is obtained as follows: 500 raw meat samples and 10 processing equipment are selected to obtain raw meat sample data and processing equipment data, the raw meat data is imported into the raw meat evaluation model to evaluate the difficulty of mincing raw meat, the processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blades, and the raw meat mincing difficulty and the wear degree of the processing equipment blades are imported into the mincing time estimation strategy to estimate the mincing time for raw meat to reach the target state; a meat processing factory is selected to use the processing equipment to mince raw meat samples, and the mincing time for the raw meat samples to reach the optimal state is recorded, and the calculated mincing time and the recorded mincing time are imported into the fitting software one by one to obtain a set of safety thresholds for the blade crack depth with the highest similarity. , the safety distance threshold between the two closest cracks , the coefficient of the impact of raw meat mincing difficulty index on mincing time The influence of wear degree of processing equipment on the mincing time The value of .

[0030] A meat product processing control system based on data analysis, which is implemented based on the above-mentioned meat product processing control method based on data analysis, includes a control module, an image acquisition module, an image processing module, a data acquisition module, a raw meat evaluation module, a processing equipment evaluation module and a meat mincing time estimation module;

[0031] Preferably, the control module is used to control the operation of the image acquisition module, the image processing module, the data acquisition module, the raw meat evaluation module, the processing equipment evaluation module and the minced meat time estimation module;

[0032] Preferably, the image acquisition module is used to acquire images of raw meat to be minced and images of processing equipment blades, the image processing module is used to process the acquired images of raw meat to be minced and images of processing equipment blades, the data acquisition module is used to obtain raw meat data and processing equipment blade data, the raw meat evaluation module is used to import the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing raw meat, the processing equipment evaluation module is used to import the processing equipment blade data into a processing equipment wear evaluation model to evaluate the degree of wear of the processing equipment blades, the meat mincing time estimation module is used to acquire the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimate the mincing time for the raw meat to reach the target state according to the meat mincing time estimation strategy.

[0033] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned meat product processing process control method based on data analysis by calling the computer program stored in the memory.

[0034] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the meat product processing control method based on data analysis.

[0035] The beneficial effects of the present invention are as follows: the present invention collects pictures of raw meat to be minced and pictures of processing equipment blades to obtain raw meat data and processing equipment blade data; imports the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing raw meat; imports the processing equipment blade data into a processing equipment wear degree evaluation model to evaluate the degree of wear of the processing equipment blades; obtains the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimates the mincing time for the raw meat to reach a target state according to a mincing time estimation strategy. The present invention combines the raw meat data with the processing equipment blade data to comprehensively analyze the impact on mincing meat, thereby predicting the optimal mincing time and ensuring the product quality of the mincing process during meat processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a flow chart of a meat product processing control method based on data analysis of the present invention;

[0037] Figure 2 It is a schematic diagram of the flow of S1 in the meat product processing control method based on data analysis of the present invention;

[0038] Figure 3 It is a schematic diagram of the overall framework of the meat product processing control system based on data analysis of the present invention. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0040] Example 1

[0041] See also Figure 1 The present invention provides an embodiment: a meat product processing control method based on data analysis, which comprises the following specific steps:

[0042] S1. Collect pictures of raw meat to be minced and pictures of blades of processing equipment to obtain data of raw meat and blades of processing equipment;

[0043] See also Figure 2 In this embodiment, S1 includes the following specific steps:

[0044] S11, collecting a picture of raw meat to be minced, segmenting the raw meat picture into fat area, lean meat area and fascia area through an image processing module, obtaining the area, height and hardness of the fat area, lean meat area and fascia area, and collecting the temperature and volume of the raw meat;

[0045] It should be further explained in this embodiment that the steps of collecting raw meat pictures are: fixing the camera to collect front and side pictures of the raw meat, ensuring that the texture and details of the raw meat can be clearly captured, distinguishing the fat area, lean meat area and fascia area of ​​the raw meat, marking the raw meat pictures, recording the shooting date, type of raw meat, shooting environment and other information, and storing the pictures in the picture storage module.

[0046] It should be further explained in this embodiment that the steps of separating lean meat, fat meat and fascia in the raw meat image by the image processing module through the local binary pattern (LBP) are as follows:

[0047] Image acquisition: Use a camera or scanner to obtain high-quality images of raw meat;

[0048] Image preprocessing: converting the image to grayscale format and applying filters (such as Gaussian filtering) to reduce image noise;

[0049] Calculate LBP features: For each pixel in the image, define a central pixel and its surrounding neighborhood pixels (usually the number of neighborhood pixels is fixed, such as 8 points); use the grayscale value of the central pixel as the threshold, compare the grayscale value of the central pixel with the grayscale value of each pixel in its neighborhood, if the value of the neighborhood pixel is greater than or equal to the value of the central pixel, then encode the point as 1; otherwise, encode it as 0, and form a binary code for the comparison result; repeat the above steps for each pixel in the image, so as to generate LBP features for the entire image;

[0050] LBP feature normalization: Normalize the LBP features to reduce the impact of illumination changes and image contrast;

[0051] Feature statistics: count the frequency of occurrence of different LBP modes in the entire image;

[0052] Construct feature vector: Take the LBP histogram (i.e. the frequency of occurrence of each pattern) as a feature vector;

[0053] Train the classifier: Use labeled training data (i.e., image regions known to be lean meat, fat meat, or fascia) to train a classifier, which can be a support vector machine, random forest, or neural network.

[0054] Image segmentation: Use the trained classifier to segment the entire image. According to the color and texture features, set different thresholds to segment the image into fat, lean meat and fascia areas.

[0055] It should be further explained in this embodiment that the steps of obtaining the area, height and hardness of the fat area, lean area and fascia area are as follows:

[0056] Area: Use edge detection and other methods to further determine the boundaries of the segmented raw meat images. Based on seed point expansion, similar pixels are grouped into one region. The number of pixels in the fat region, lean region, and fascia region is counted. The number of pixels is converted into actual area based on the resolution and actual size ratio of the image.

[0057] Height: Find the boundaries of the fat area, lean meat area, and fascia area based on the raw meat side image. Calculate the height of each area by calculating the pixel difference between the upper and lower boundaries. Convert the pixel difference into actual height units (such as millimeters or centimeters) based on the actual size ratio of the image. If the height of the area is not uniform, collect multiple heights and take the average value as the height of the area.

[0058] Hardness: Hardness acquisition can be done by penetration testing or ultrasonic hardness assessment;

[0059] Use a specialized penetration device (such as a penetration hardness tester) to measure the force required for the probe to penetrate the meat sample, select a penetration needle of appropriate length, penetrate the meat sample at a set speed and angle, record the force required during the penetration process, perform multiple measurements for each area, and calculate the average value;

[0060] The hardness is assessed by the propagation speed of ultrasound (the higher the hardness, the faster the propagation speed of ultrasound). The meat sample is scanned using an ultrasonic instrument and probe, the propagation speed of ultrasound in different areas is analyzed, and the hardness value is calculated based on the propagation speed.

[0061] The steps for collecting the temperature of raw meat are: gently insert the probe of the thermocouple into the center of the meat, avoiding the probe from touching the bone or fascia, connect it to the digital display unit, wait for the temperature to stabilize, read the displayed temperature value, and record the temperature reading;

[0062] The steps for collecting the volume of raw meat are: use an edge detection algorithm (such as Canny edge detection) to identify the outline of the raw meat, use a contour fitting algorithm (such as least squares method, polygonal approximation, etc.) to fit the detected edges to form a closed contour, and calculate the volume of the raw meat based on the number of pixels in the fitted contour (for example, the shape of the raw meat is approximated as a rectangular parallelepiped, and the volume of the raw meat is length*width*height).

[0063] S12, collecting images of processing equipment blades, and obtaining the number of cracks, crack depth, and crack distance of the processing equipment blades through the image processing module.

[0064] It should be further explained in this embodiment that the steps of obtaining the number of cracks, crack depth and crack distance of the blade of the processing equipment are:

[0065] Number of cracks: Mark the connected regions of the binary image and count the number of cracks based on the results of the connected region marking;

[0066] The steps of the connected component labeling algorithm are:

[0067] Initialize a label array of the same size as the raw meat image, with all values ​​set to 0; traverse each pixel in the binary image, and if the pixel value is 1 (foreground pixel), check the labels of the pixels above and to the left of the pixel. If the labels of the pixels above and to the left are both undefined (values ​​are 0), assign a new label and assign it to the current pixel and the pixels above and to the left; if one of the labels of the pixels above and to the left is defined, set the label of the current pixel to the defined label; if the labels of the pixels above and to the left are both defined and different, store the smaller label at the current pixel position, and record label conflicts (larger label, smaller label) in an auxiliary array; traverse the auxiliary array to resolve label conflicts; traverse the label array and optimize all labels to consecutive integers starting from 0; output the label array, in which each different integer represents a connected area.

[0068] Crack depth: Measure the deepest pixel of the crack and determine the crack depth by calculating the shortest distance from the crack edge to the deepest pixel of the crack;

[0069] Crack distance: Measures the distance between cracks, which can be obtained by calculating the edge distance between connected areas.

[0070] S2, importing the raw meat data into the raw meat evaluation model to evaluate the difficulty of mincing the raw meat;

[0071] In this embodiment, S2 includes the following specific steps:

[0072] The raw meat data is imported into the raw meat evaluation model to evaluate the difficulty of raw meat mincing. The raw meat evaluation model includes a raw meat mincing difficulty index calculation formula, which is:

[0073] ;

[0074] In the formula, is the raw meat temperature collected, The standard temperature of raw meat. is the area of ​​raw meat fat area, is the height of the fat area of ​​raw meat, is the volume of raw meat, The hardness of the fat area of ​​raw meat, The standard hardness of the fat area of ​​raw meat. is the area of ​​raw lean meat area, is the height of the raw meat lean area, The hardness of the lean area of ​​raw meat. The standard hardness of the lean area of ​​raw meat. is the area of ​​the raw meat fascia, is the height of the raw meat fascia area, The hardness of the raw meat fascia area, It is the standard hardness of the raw meat fascia area.

[0075] It should be further explained in this embodiment that the standard temperature of the raw meat material is , Standard hardness of raw meat fat area , Standard hardness of raw meat lean area And the standard hardness of the raw meat fascia area The value is obtained by selecting 500 raw meat samples, measuring the temperature of the samples, the hardness of the fat area, the hardness of the lean meat area and the hardness of the fascia area, and then taking the average value of the measured data as the standard temperature of the raw meat material , Standard hardness of raw meat fat area , Standard hardness of raw meat lean area And the standard hardness of the raw meat fascia area The value of .

[0076] S3, importing the processing equipment blade data into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade;

[0077] In this embodiment, S3 includes the following specific steps:

[0078] The processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade. The processing equipment wear degree evaluation model includes a processing equipment wear degree calculation formula. The processing equipment wear degree calculation formula is:

[0079] ;

[0080] In the formula, is the depth of the nth crack of the ith blade, is the safety threshold of blade crack depth, is the number of blades in the processing equipment, The number of cracks for each blade, is the distance between the nth crack of the ith blade and its closest crack, is the safety distance threshold between the two closest cracks. hour, The value is 0.

[0081] S4. Obtain the difficulty of mincing the raw meat and the degree of wear of the blades of the processing equipment, and estimate the mincing time for the raw meat to reach the target state according to the mincing time estimation strategy.

[0082] In this embodiment, S4 includes the following specific steps:

[0083] The difficulty of mincing raw meat and the degree of wear of the blades of the processing equipment are obtained, and the mincing time for raw meat to reach the target state is estimated according to the mincing time estimation strategy. The mincing time estimation strategy includes the optimal mincing time calculation formula, which is:

[0084] ;

[0085] In the formula, For standard mincing time, is the coefficient of the impact of raw meat mincing difficulty index on mincing time, is the coefficient of the influence of the wear degree of processing equipment on the mincing time, , are positive numbers and .

[0086] It should be further explained in this embodiment that the standard mincing time is determined by selecting 500 raw meat samples of the same weight, putting them into a brand-new processing equipment for mincing, recording the mincing time for the raw meat samples to reach the target state, and taking the average value of the measured data as the standard mincing time, wherein the target state is that the raw meat presents uniform meat quality, has no obvious meat pieces or meat particles, has a natural color, and has a suitable temperature. The specific target state needs to be set according to the target meat product standard;

[0087] It should be further explained in this embodiment that the safety threshold of the blade crack depth is , the safety distance threshold between the two closest cracks , the coefficient of the impact of raw meat mincing difficulty index on mincing time The influence of wear degree of processing equipment on the mincing time The value of is obtained as follows: 500 raw meat samples and 10 processing equipment are selected to obtain raw meat sample data and processing equipment data, the raw meat data is imported into the raw meat evaluation model to evaluate the difficulty of mincing raw meat, the processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blades, and the raw meat mincing difficulty and the wear degree of the processing equipment blades are imported into the mincing time estimation strategy to estimate the mincing time for raw meat to reach the target state; a meat processing factory is selected to use the processing equipment to mince raw meat samples, and the mincing time for the raw meat samples to reach the optimal state is recorded, and the calculated mincing time and the recorded mincing time are imported into the fitting software one by one to obtain a set of safety thresholds for the blade crack depth with the highest similarity. , the safety distance threshold between the two closest cracks , the coefficient of the impact of raw meat mincing difficulty index on mincing time The influence of wear degree of processing equipment on the mincing time The value of .

[0088] Example 2

[0089] An embodiment provided by the present invention is a meat product processing process control method based on data analysis, which comprises the following specific steps:

[0090] S1. Collect pictures of raw meat to be minced and pictures of blades of processing equipment to obtain data of raw meat and blades of processing equipment;

[0091] In this embodiment, S1 includes the following specific steps:

[0092] S11, collecting a picture of raw meat to be minced, segmenting the raw meat picture into fat area, lean meat area and fascia area through an image processing module, obtaining the area, height and hardness of the fat area, lean meat area and fascia area, and collecting the temperature and volume of the raw meat;

[0093] S12, collecting images of processing equipment blades, and obtaining the number of cracks, crack depth, and crack distance of the processing equipment blades through the image processing module.

[0094] S2, importing the raw meat data into the raw meat evaluation model to evaluate the difficulty of mincing the raw meat;

[0095] In this embodiment, S2 includes the following specific steps:

[0096] The raw meat data is imported into the raw meat evaluation model to evaluate the difficulty of raw meat mincing. The raw meat evaluation model includes a raw meat mincing difficulty index calculation formula, which is:

[0097] ;

[0098] In the formula, is the raw meat temperature collected, The standard temperature of raw meat. is the area of ​​raw meat fat area, is the height of the fat area of ​​raw meat, is the volume of raw meat, The hardness of the fat area of ​​raw meat, The standard hardness of the fat area of ​​raw meat. is the area of ​​raw lean meat area, is the height of the raw meat lean area, The hardness of the lean area of ​​raw meat. The standard hardness of the lean area of ​​raw meat. is the area of ​​the raw meat fascia, is the height of the raw meat fascia area, The hardness of the raw meat fascia area, It is the standard hardness of the raw meat fascia area.

[0099] S3, importing the processing equipment blade data into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade;

[0100] In this embodiment, S3 includes the following specific steps:

[0101] The processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade. The processing equipment wear degree evaluation model includes a processing equipment wear degree calculation formula. The processing equipment wear degree calculation formula is:

[0102] ;

[0103] In the formula, is the depth of the nth crack of the ith blade, is the safety threshold of blade crack depth, is the number of blades in the processing equipment, The number of cracks for each blade, is the distance between the nth crack of the ith blade and its closest crack, is the safety distance threshold between the two closest cracks. hour, The value is 0.

[0104] S4. Obtain the difficulty of mincing the raw meat and the degree of wear of the blades of the processing equipment, and estimate the mincing time for the raw meat to reach a target state according to the mincing time estimation strategy.

[0105] In this embodiment, S4 includes the following specific steps:

[0106] The difficulty of mincing raw meat and the degree of wear of the blades of the processing equipment are obtained, and the mincing time for raw meat to reach the target state is estimated according to the mincing time estimation strategy. The mincing time estimation strategy includes the optimal mincing time calculation formula, which is:

[0107] ;

[0108] In the formula, is the standard processing equipment speed, is the coefficient of the impact of raw meat mincing difficulty index on mincing time, is the coefficient of the influence of the wear degree of processing equipment on the mincing time, , are positive numbers and , is the power of e, The standard value of the difficulty of mincing raw meat. It is the standard value of the wear degree of processing equipment.

[0109] In this embodiment, the standard value of difficulty of raw meat mincing is And the standard value of the degree of wear of processing equipment The value of is obtained as follows: 500 sets of calculated raw meat grinding difficulty values ​​and processing equipment blade wear degree values ​​are obtained, and the average values ​​are taken respectively.

[0110] Example 3

[0111] See also Figure 3 , a meat product processing control system based on data analysis, which is implemented based on the above-mentioned meat product processing control method based on data analysis, including a control module, an image acquisition module, an image processing module, a data acquisition module, a raw meat evaluation module, a processing equipment evaluation module and a minced meat time estimation module;

[0112] In this embodiment, the image acquisition module is used to collect images of raw meat to be minced and images of processing equipment blades, the image processing module is used to process the collected images of raw meat to be minced and images of processing equipment blades, the data acquisition module is used to obtain raw meat data and processing equipment blade data, the raw meat evaluation module is used to import the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing raw meat, the processing equipment evaluation module is used to import the processing equipment blade data into a processing equipment wear evaluation model to evaluate the degree of wear of the processing equipment blades, and the meat mincing time estimation module is used to obtain the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimate the mincing time for the raw meat to reach the target state according to the meat mincing time estimation strategy.

[0113] In this embodiment, the control module is used to control the operation of the image acquisition module, the image processing module, the data acquisition module, the raw meat evaluation module, the processing equipment evaluation module and the minced meat time estimation module.

[0114] Example 4

[0115] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned meat processing process control method based on data analysis by calling the computer program stored in the memory.

[0116] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the meat product processing control method based on data analysis provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0117] Example 5

[0118] This embodiment provides a computer-readable storage medium storing instructions, which, when a computer program is executed on a computer device, enables the computer device to execute the above-mentioned meat product processing control method based on data analysis.

[0119] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0120] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0121] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only one way. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0122] In the description of this specification, the descriptions with reference to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example, and the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0123] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can well understand and use the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A meat product processing control method based on data analysis, characterized in that: The specific steps include: S1. Collect pictures of raw meat to be minced and pictures of blades of processing equipment to obtain data of raw meat and blades of processing equipment; S2, importing the raw meat data into the raw meat evaluation model to evaluate the difficulty of mincing the raw meat; S3, importing the processing equipment blade data into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade; S4, obtaining the difficulty of mincing the raw meat and the degree of wear of the blades of the processing equipment, and estimating the mincing time for the raw meat to reach the target state according to the mincing time estimation strategy; The S2 comprises the following specific steps: The raw meat data is imported into a raw meat evaluation model to evaluate the difficulty of mincing the raw meat. The raw meat evaluation model includes a raw meat mincing difficulty index calculation formula, and the raw meat mincing difficulty index calculation formula is: ； In the formula, is the raw meat temperature collected, The standard temperature of raw meat. is the area of ​​raw meat fat area, is the height of the fat area of ​​raw meat, is the volume of raw meat, The hardness of the fat area of ​​raw meat. The standard hardness of the fat area of ​​raw meat. is the area of ​​raw lean meat area, is the height of the raw meat lean area, The hardness of the lean area of ​​raw meat. The standard hardness of the lean area of ​​raw meat. is the area of ​​the raw meat fascia, is the height of the raw meat fascia area, The hardness of the raw meat fascia area, It is the standard hardness of the raw meat fascia area; The S3 comprises the following specific steps: The processing equipment blade data is imported into the processing equipment wear degree evaluation model to evaluate the wear degree of the processing equipment blade. The processing equipment wear degree evaluation model includes a processing equipment wear degree calculation formula, and the processing equipment wear degree calculation formula is: ； In the formula, is the depth of the nth crack of the ith blade, is the safety threshold of blade crack depth, is the number of blades in the processing equipment, The number of cracks for each blade, is the distance between the nth crack of the ith blade and its closest crack, is the safety distance threshold between the two closest cracks. hour, The value is 0.

2. The meat product processing control method based on data analysis according to claim 1, characterized in that: The S4 comprises the following specific steps: The difficulty of mincing raw meat and the degree of wear of the blades of the processing equipment are obtained, and the mincing time for the raw meat to reach the target state is estimated according to the mincing time estimation strategy. The mincing time estimation strategy includes an optimal mincing time calculation formula, and the optimal mincing time calculation formula is: ； In the formula, For standard mincing time, is the coefficient of the impact of raw meat mincing difficulty index on mincing time, is the coefficient of the influence of the wear degree of processing equipment on the mincing time, , are positive numbers and .

3. The meat product processing control method based on data analysis according to claim 2, characterized in that: The S1 comprises the following specific steps: S11, collecting a picture of raw meat to be minced, segmenting the raw meat picture into fat area, lean meat area and fascia area through an image processing module, obtaining the area, height and hardness of the fat area, lean meat area and fascia area, and collecting the temperature and volume of the raw meat; S12, collecting images of processing equipment blades, and obtaining the number of cracks, crack depth, and crack distance of the processing equipment blades through the image processing module.

4. A meat product processing control system based on data analysis, implemented based on the meat product processing control method based on data analysis according to any one of claims 1 to 3, characterized in that: It includes a control module, an image acquisition module, an image processing module, a data acquisition module, a raw meat evaluation module, a processing equipment evaluation module and a minced meat time estimation module. The control module is used to control the operation of the image acquisition module, the image processing module, the data acquisition module, the raw meat evaluation module, the processing equipment evaluation module and the minced meat time estimation module.

5. The meat product processing control system based on data analysis as claimed in claim 4, characterized in that: The image acquisition module is used to acquire images of raw meat to be minced and images of processing equipment blades; the image processing module is used to process the acquired images of raw meat to be minced and images of processing equipment blades; the data acquisition module is used to obtain raw meat data and processing equipment blade data; the raw meat evaluation module is used to import the raw meat data into a raw meat evaluation model to evaluate the difficulty of mincing raw meat; the processing equipment evaluation module is used to import the processing equipment blade data into a processing equipment wear evaluation model to evaluate the degree of wear of the processing equipment blades; the meat mincing time estimation module is used to acquire the difficulty of mincing raw meat and the degree of wear of the processing equipment blades, and estimate the mincing time for the raw meat to reach a target state according to a meat mincing time estimation strategy.

6. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the meat product processing control method based on data analysis as described in any one of claims 1 to 3 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the meat product processing control method based on data analysis as described in any one of claims 1 to 3.

Images