Dish quality detection system

Abstract

The invention relates to the technical field of dish detection, in particular to a dish quality detection system which comprises a conveying module, a clamping module, a detection module, a raw material dividing module, a display module and an analysis module. The clamping module determines the freshness condition of the raw materials through the action of lifting the raw materials, and the analysis module determines whether the raw materials of a single batch meet the preset standard or not according to the grade proportion of all the raw materials and determines that the operation speed of the mechanical arm is adjusted to a corresponding value based on the judgment result, or the maximum retention early warning duration for the raw materials of the single batch is adjusted in a targeted mode. And the detection efficiency of the raw materials is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of food detection, and in particular to a food quality detection system. Background Art

[0002] With the rapid development of the catering industry and the increasing demand of consumers for food safety and quality, traditional raw material quality detection methods can no longer meet the needs of modern catering management. These methods often have problems such as low detection efficiency. Therefore, it is particularly important to develop an efficient and accurate dish detection system.

[0003] Chinese Patent Publication No.: CN116148231 B, discloses an online detection system and method for frozen preservation of pre-prepared dishes, including an online display module, a detection point arrangement module and a probe detection module, wherein the online display module is used to store the freezing status of dishes on the network, the detection point arrangement module is used to arrange detection points for dishes in the detection screen, the probe detection module is used to detect the freshness of dishes in the detection screen, the detection point arrangement module is electrically connected to the probe detection module, the detection point arrangement module and the probe detection module are both electrically connected to the online display module, the online display module includes a dish archiving module, a data conversion module and an information transmission module, the dish archiving module is used to store the property data of dish raw materials corresponding to different dishes in the cloud, and the data conversion module is electrically connected to the dish archiving module; it can be seen that the above technical solution has the following problems: it does not take into account the classification of the grades of the raw materials, and does not take into account the automatic adjustment of the detection parameters according to the proportion of the raw materials of each grade, which affects the accuracy of the detection results and thus affects the detection efficiency. Summary of the invention

[0004] To this end, the present invention provides a dish quality detection system to overcome the problem that the prior art does not consider the grade of each raw material, and does not consider automatically adjusting the detection parameters according to the proportion of each grade of raw materials, which affects the accuracy of the detection results and further affects the detection efficiency.

[0005] To achieve the above object, the present invention provides a food quality detection system, comprising:

[0006] A conveying module, comprising a conveyor belt for conveying raw materials to be processed;

[0007] a gripping module, comprising a mechanical arm disposed above the conveyor belt for lifting the raw material at a predetermined gripping point;

[0008] A detection module, comprising a first visual detector arranged above the conveyor belt for obtaining image information of the raw material and a second visual detector arranged at one side of the conveyor belt for obtaining side image information;

[0009] A raw material classification module, which is connected to the detection module, is used to determine the doping degree of the color block based on the raw material image information obtained by the visual detector, and classify each raw material grade in combination with the change in raw material curvature;

[0010] A display module, which is used to output the maximum retention warning time of each batch of raw materials;

[0011] The analysis module is respectively connected to the clamping module, the raw material classification module and the display module, and is used to determine whether a single batch of raw materials meets the preset standards based on the grade proportion of each raw material, and to adjust the operating speed of the robot arm to a corresponding value or adjust the maximum retention warning time for a single batch of raw materials to a corresponding value based on the judgment result.

[0012] Furthermore, the raw material classification module is used to determine the doping degree of the color block based on the raw material image information, including:

[0013] Used to identify and select each grayscale area based on the grayscale value of the raw material image information;

[0014] It is used to calculate the ratio of the average area of ​​each grayscale area to the total raw material area in the raw material image information to obtain the color block doping degree.

[0015] Furthermore, the raw material classification module is used to classify the grade of a single raw material based on the doping degree of the color block, including:

[0016] If the color block impurity is greater than the second preset color block impurity, the raw material is classified as a primary raw material;

[0017] If the color block impurity is less than or equal to the second preset color block impurity and greater than the first preset color block impurity, the grade of the single raw material is divided based on the change in curvature of the raw material;

[0018] If the color block impurity is less than or equal to the first preset color block impurity, the raw material is classified into three levels of raw materials.

[0019] Furthermore, the raw material classification module is used to determine the curvature change of the raw material based on the side image information, including:

[0020] The robot arm is used to lift the raw material under the condition that the raw material classification module determines to classify the single raw material based on the curvature change of the raw material, and the second visual detector obtains the side image information after lifting;

[0021] The raw material segmentation module is used to obtain the raw material contour in the side image information;

[0022] The raw material division module is used to obtain the height distance between the height of the lowest point in the raw material contour and the height of the end of the robot arm, and solve the ratio of the height distance to the length of the raw material contour to obtain the curvature change of the raw material;

[0023] The raw material classification module is used to classify the grade of a single raw material based on the change in raw material curvature, including:

[0024] If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material, the raw material is classified as a first-level raw material;

[0025] If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material and greater than the second preset curvature change of the raw material, the raw material is classified as a secondary raw material;

[0026] If the change in curvature of the raw material is greater than the second preset change in curvature of the raw material, the raw material is classified as secondary or tertiary raw material.

[0027] Furthermore, the analysis module is used to determine whether the operating parameters of the clamping module meet the preset standards based on the proportion of the quantity of the secondary and tertiary raw materials to the total quantity of raw materials detected in a single detection cycle, including:

[0028] If the proportion of the second-level third-level is less than or equal to the preset proportion of the second-level third-level, the quality of the single batch of raw materials is determined based on the proportion of the second-level;

[0029] If the secondary tertiary proportion is greater than the preset secondary tertiary proportion, the operating speed of the robot arm will be adjusted to the corresponding value based on the corresponding reference weight of the single batch of raw materials, and based on the secondary tertiary proportion within the detection cycle re-acquired after adjustment, it will be determined whether the preset secondary proportion will be adjusted to the corresponding value, and based on the secondary proportion, it will be determined whether the quality of the single batch of raw materials is qualified.

[0030] Further, the analysis module is used to adjust the running speed of the robot arm to a corresponding value based on the corresponding reference weight of a single batch of raw materials, wherein:

[0031] The reduction in the operating speed of the robot arm determined based on the corresponding reference weight of a single batch of raw materials is negatively correlated with the corresponding reference weight.

[0032] Further, the analysis module is used to determine whether to adjust the preset secondary proportion to a corresponding value based on the secondary and tertiary proportions in the re-acquired detection cycle under the condition that the operation speed adjustment of the robot arm is completed, including:

[0033] Calculate the ratio of the re-acquired secondary third-level proportion to the secondary third-level proportion acquired in the previous detection cycle, and determine the ratio as an adjustment parameter;

[0034] If the adjustment parameter is less than or equal to the preset adjustment parameter, the preset secondary proportion is adjusted to the corresponding value, and whether the quality of the single batch of raw materials is qualified is determined based on the secondary proportion;

[0035] If the adjustment parameter is greater than the preset adjustment parameter, the quality of the single batch of raw materials is judged to be unqualified.

[0036] Furthermore, the analysis module is used to adjust the preset secondary proportion to a corresponding value based on the preset adjustment parameter and the parameter difference of the adjustment parameter, wherein:

[0037] The increase in the preset secondary proportion determined based on the parameter difference is positively correlated with the parameter difference.

[0038] Furthermore, the analysis module is used to determine whether the quality of a single batch of raw materials is qualified based on the secondary proportion, including:

[0039] If the secondary proportion is less than or equal to the preset secondary proportion, the quality of the single batch of raw materials is determined to be qualified;

[0040] If the secondary proportion is greater than the preset secondary proportion, the quality of the single batch of raw materials is judged to be unqualified.

[0041] Further, the analysis module is used to adjust the maximum retention warning time to a corresponding value based on the secondary proportion when determining that the quality of a single batch of raw materials is unqualified, wherein:

[0042] The reduction in the maximum retention warning time determined based on the secondary proportion is positively correlated with the secondary proportion.

[0043] Compared with the prior art, the beneficial effects of the present invention lie in that the data of each raw material obtained is processed through the raw material classification module, and the grades of each module are divided; the clamping module determines the freshness of the raw materials by lifting the raw materials; the analysis module determines whether a single batch of raw materials meets the preset standards based on the grade proportion of each raw material, and based on the judgment result, determines whether the operating speed of the robot arm is adjusted to the corresponding value, or specifically adjusts the maximum retention warning time for a single batch of raw materials, thereby improving the detection efficiency of raw materials.

[0044] Furthermore, the grade of each raw material is divided according to the color block impurity. The color block impurity characterizes the decay of the raw material. When the raw material is decayed, there will be a decayed area with a gray value significantly lower than the surrounding gray value in some areas of the raw material. The more gray areas selected by the raw material division module, the more decayed areas there are, resulting in a decrease in the average area of ​​each gray area, that is, the color block impurity is inversely proportional to the decay of the raw material; when the color block impurity is less than or equal to the second preset color block impurity and greater than the first preset color block impurity, in order to ensure the accuracy of data processing and the precision of raw material division, in this case, combined The change in raw material curvature is used to divide the grade of individual raw materials; the change in raw material curvature represents the freshness of the raw materials. After the robot arm completes lifting the raw materials, the bending degree of the raw materials is negatively correlated with the freshness, and the change in raw material curvature is negatively correlated with the freshness of the raw materials. The proportion of the second-third level in a single detection cycle is obtained. When the proportion of the second-third level is greater than the preset proportion of the second-third level, the raw materials may be damaged due to the excessive lifting speed of the robot arm. At this time, the operating parameters of the robot arm are adjusted in a targeted manner to ensure the integrity of the raw material detection process. While improving the accuracy of the detection results, the detection efficiency is thereby improved.

[0045] Furthermore, under the condition of completing the adjustment of the running speed of the robot arm, an adjustment parameter is obtained, and the adjustment parameter characterizes the influence of the adjustment of the running speed of the robot arm on the detection results of the raw materials. When the adjustment parameter is greater than the preset adjustment parameter, the running speed of the robot arm has little influence on the detection of the raw materials, and there are a large number of secondary and tertiary raw materials in the raw materials. In this case, the quality of a single batch of raw materials is judged to be unqualified; when the adjustment parameter is less than or equal to the preset adjustment parameter, the running speed of the robot arm has an influence on the detection results of the raw materials. Such raw materials are easier to bend, and bending will cause the cell structure of the vegetables to be damaged, causing the cell contents to leak out, and the damaged parts provide a convenient channel for the invasion and reproduction of microorganisms, causing this type of vegetables to rot easily. In this case, the preset secondary proportion for judging whether the quality of a single batch of raw materials is qualified is adjusted to automatically adjust the data processing standard according to the actual situation and characteristics of the raw materials, thereby effectively improving the detection efficiency of the quality of the dishes. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a module block diagram of a food quality detection system according to an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of a food quality detection system according to an embodiment of the present invention;

[0048] Figure 3 A logic decision diagram of a raw material classification module according to an embodiment of the present invention for classifying the grade of a single raw material based on the doping degree of a color block;

[0049] Figure 4This is a logic decision diagram of the raw material classification module of the embodiment of the present invention for classifying the grade of a single raw material based on the change amount of the raw material curvature;

[0050] In the figure: 1, conveyor belt; 2, robotic arm; 31, first visual detector; 32, second visual detector. DETAILED DESCRIPTION

[0051] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0053] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0054] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0055] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively a module block diagram, a structural schematic diagram, a logic decision diagram of a raw material classification module for classifying a single raw material based on the doping degree of a color block, and a logic decision diagram of a raw material classification module for classifying a single raw material based on the curvature variation of the raw material; a dish quality detection system according to an embodiment of the present invention comprises:

[0056] A conveying module, comprising a conveyor belt 1 for conveying raw materials to be processed;

[0057] A gripping module, comprising a mechanical arm 2 arranged above the conveyor belt 1 for lifting the raw material at a predetermined gripping point;

[0058] A detection module, which includes a first visual detector 31 arranged above the conveyor belt 1 to obtain raw material image information and a second visual detector 32 arranged at one side of the conveyor belt 1 to obtain side image information;

[0059] A raw material classification module (not shown in the figure), which is connected to the detection module, is used to determine the doping degree of the color block based on the raw material image information obtained by the visual detector, and classify each raw material grade in combination with the change in raw material curvature;

[0060] A display module (not shown) is used to output the maximum retention warning time of each batch of raw materials;

[0061] An analysis module (not shown) is respectively connected to the clamping module, the raw material classification module and the display module, and is used to determine whether a single batch of raw materials meets the preset standards based on the grade proportion of each raw material, and to adjust the operating speed of the robot 2 to a corresponding value or adjust the maximum retention warning time for a single batch of raw materials to a corresponding value based on the judgment result.

[0062] Specifically, there is no limitation on the predetermined clamping point, and it may be the center point of the raw material obtained by the visual detector, or it may be the tail of the raw material, which will not be elaborated here.

[0063] Specifically, for the tertiary raw materials, the clamping module can sort them into a waste box (not shown in the figure) arranged on one side of the transmission module, which will not be described in detail.

[0064] Specifically, there is no limit on the initial maximum retention warning time for each batch of raw materials determined by the display module. It can be determined based on historical data, and the corresponding retention time in the test results of a single variety of raw materials in which the proportion of third-level raw materials is greater than 5% is determined as the initial maximum retention warning time corresponding to this type of raw materials. This will not be repeated here.

[0065] Specifically, the data of each raw material obtained is processed through the raw material classification module, and the grades of each module are divided. The clamping module determines the freshness of the raw materials by lifting the raw materials. The analysis module determines whether a single batch of raw materials meets the preset standards based on the grade ratio of each raw material, and adjusts the operating speed of the robot 2 to the corresponding value based on the judgment result, or adjusts the maximum retention warning time for a single batch of raw materials in a targeted manner, thereby improving the detection efficiency of raw materials.

[0066] Specifically, the raw material division module is used to determine the doping degree of the color block based on the raw material image information, including:

[0067] Used to identify and select each grayscale area based on the grayscale value of the raw material image information;

[0068] It is used to calculate the ratio of the average area of ​​each grayscale area to the total raw material area in the raw material image information to obtain the color block doping degree.

[0069] Specifically, there is no limitation on the specific process of identifying the grayscale values ​​based on the raw image information and selecting each grayscale area. A seed point can be selected through the region growing method, and adjacent pixels can be gradually merged according to the grayscale similarity criterion to form a region. The grayscale image can also be segmented through deep learning models such as U-Net and FCN to select different grayscale areas. This is a prior art and will not be described in detail.

[0070] Specifically, the raw material classification module is used to classify the grade of a single raw material based on the doping degree of the color block, including:

[0071] If the color block impurity is greater than the second preset color block impurity, the raw material is classified as a primary raw material;

[0072] If the color block impurity is less than or equal to the second preset color block impurity and greater than the first preset color block impurity, the grade of the single raw material is divided based on the change in curvature of the raw material;

[0073] If the color block impurity is less than or equal to the first preset color block impurity, the raw material is classified into three levels of raw materials.

[0074] Specifically, the first preset color block impurity C1 is selected in the interval [0.61D0, 0.67D0]; the second preset color block impurity C2 is selected in the interval [0.73D0, 0.82D0], and D0 is the average impurity of each raw material color block obtained for each type of warehoused raw material in the historical detection data;

[0075] Specifically, the incoming raw materials are the fresh raw materials initially received in order to determine the fresh raw material data parameters. It can be understood that in order to divide the specific circumstances of the raw materials, the number of selected incoming raw materials should be no less than 1,800, which will not be repeated here.

[0076] Specifically, the raw material classification module is used to determine the curvature change of the raw material based on the side image information, including:

[0077] The robot arm 2 is used to lift the raw material under the condition that the raw material classification module determines to classify the single raw material based on the curvature change of the raw material, and the second visual detector 32 obtains the side image information after lifting;

[0078] The raw material segmentation module is used to obtain the raw material contour in the side image information;

[0079] The raw material division module is used to obtain the height distance between the height of the lowest point in the raw material contour and the height of the end of the robot arm 2, and solve the ratio of the height distance to the length of the raw material contour to obtain the curvature change of the raw material;

[0080] Specifically, the raw material classification module is used to classify the grade of a single raw material based on the change in raw material curvature, including:

[0081] If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material, the raw material is classified as a first-level raw material;

[0082] If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material and greater than the second preset curvature change of the raw material, the raw material is classified as a secondary raw material;

[0083] If the change in curvature of the raw material is greater than the second preset change in curvature of the raw material, the raw material is classified as secondary or tertiary raw material.

[0084] Specifically, there is no limitation on the specific method of obtaining the outline of the raw material in the side image information. Image processing algorithms and edge detection algorithms, such as Canny edge detection and Sobel operator, can be used to detect areas where the pixel values ​​in the side image change dramatically, thereby determining the edge outline of the vegetables. It can be understood that the outline of the raw material in the image information can be selected. This is a prior art and will not be elaborated on.

[0085] Specifically, the first preset raw material curvature change B1 is selected within the interval [1.27H0, 1.67H0]; the second preset raw material curvature change B2 is selected within the interval [3.61H0, 4.62H0], and H0 is the average value of the curvature changes of each raw material obtained for each type of incoming raw materials in the historical detection data.

[0086] Specifically, the analysis module is used to determine whether the operating parameters of the clamping module meet the preset standards based on the proportion of the amount of the secondary and tertiary raw materials to the total amount of raw materials detected in a single detection cycle, including:

[0087] If the proportion of the second-level third-level is less than or equal to the preset proportion of the second-level third-level, the quality of the single batch of raw materials is determined based on the proportion of the second-level;

[0088] If the secondary tertiary proportion is greater than the preset secondary tertiary proportion, the operating speed of the robot arm 2 is adjusted to the corresponding value based on the corresponding reference weight of the single batch of raw materials, and based on the secondary tertiary proportion within the detection cycle re-acquired after adjustment, it is determined whether the preset secondary proportion is adjusted to the corresponding value, and based on the secondary proportion, it is determined whether the quality of the single batch of raw materials is qualified.

[0089] Specifically, the preset secondary and tertiary proportion Z0 is selected within the interval [0.68, 0.81].

[0090] Specifically, there is no limitation on the method for determining the corresponding reference weight of a single type of raw material. It can be the average value of each weight obtained for each single type of incoming raw material in the historical detection data, which will not be elaborated here.

[0091] Specifically, a single detection cycle is the duration of the grade division for a single raw material determined by the raw material classification module based on the change in the curvature of the raw material.

[0092] Specifically, the grade of each raw material is divided according to the color block impurity. The color block impurity characterizes the decay of the raw material. When the raw material is rotten, there will be rotten areas with grayscale values ​​significantly lower than the surrounding grayscale values ​​in some areas of the raw material. The more grayscale areas selected by the raw material division module, the more rotten areas there are, resulting in a decrease in the average area of ​​each grayscale area, that is, the color block impurity is inversely proportional to the decay of the raw material; when the color block impurity is less than or equal to the second preset color block impurity and greater than the first preset color block impurity, in order to ensure the accuracy of data processing and the accuracy of raw material division, in this case, combined with the raw material The curvature change is used to divide the grade of a single raw material; the curvature change of the raw material represents the freshness of the raw material. After the robot arm 2 completes the lifting of the raw material, the bending degree of the raw material is negatively correlated with the freshness, and the curvature change of the raw material is negatively correlated with the freshness of the raw material. The proportion of the second-third level in a single detection cycle is obtained. When the proportion of the second-third level is greater than the preset proportion of the second-third level, the raw material may be damaged due to the excessive lifting speed of the robot arm 2. At this time, the operating parameters of the robot arm 2 are adjusted in a targeted manner to ensure the integrity of the raw material detection process. While improving the accuracy of the detection results, the detection efficiency is thereby improved.

[0093] Specifically, the analysis module is used to adjust the running speed of the robot arm 2 to a corresponding value based on the corresponding reference weight of a single batch of raw materials, wherein:

[0094] The reduction range of the running speed of the robot arm 2 determined based on the corresponding reference weight of a single batch of raw materials is negatively correlated with the corresponding reference weight.

[0095] In this embodiment, optionally:

[0096] comparing the corresponding reference weight of the single batch of raw materials with the first preset reference weight and the second preset reference weight;

[0097] If the corresponding reference weight is less than or equal to the first preset reference weight, the operating speed of the robot arm 2 is determined to be the first operating speed, and the first operating speed is 0.72 times the initial operating speed;

[0098] If the corresponding reference weight is less than or equal to the second preset reference weight and greater than the first preset reference weight, the operating speed of the robot arm 2 is determined as the second operating speed, and the second operating speed is 0.84 times the initial operating speed;

[0099] If the corresponding reference weight is greater than the second preset reference weight, the operating speed of the robot arm 2 is determined to be the third operating speed, which is 0.93 times the initial operating speed;

[0100] The first preset reference weight G1 is selected within the interval [110, 130], and the second preset reference weight G2 is selected within the interval [480, 500].

[0101] Specifically, the analysis module is used to determine whether to adjust the preset secondary proportion to a corresponding value based on the secondary and tertiary proportions in the re-acquired detection cycle under the condition that the operation speed adjustment of the robot arm 2 is completed, including:

[0102] Calculate the ratio of the re-acquired secondary third-level proportion to the secondary third-level proportion acquired in the previous detection cycle, and determine the ratio as an adjustment parameter;

[0103] If the adjustment parameter is less than or equal to the preset adjustment parameter, the preset secondary proportion is adjusted to the corresponding value, and whether the quality of the single batch of raw materials is qualified is determined based on the secondary proportion;

[0104] If the adjustment parameter is greater than the preset adjustment parameter, the quality of the single batch of raw materials is judged to be unqualified.

[0105] Specifically, the preset adjustment parameter T0 is selected within the interval [0.63, 0.71].

[0106] Specifically, the adjustment parameter is obtained under the condition of completing the adjustment of the running speed of the robot 2, and the adjustment parameter represents the influence of the adjustment of the running speed of the robot 2 on the detection results of the raw materials. When the adjustment parameter is greater than the preset adjustment parameter, the running speed of the robot 2 has little effect on the detection of the raw materials, and there are a large number of secondary and tertiary raw materials in the raw materials. In this case, the quality of a single batch of raw materials is judged to be unqualified; when the adjustment parameter is less than or equal to the preset adjustment parameter, the running speed of the robot 2 has an impact on the detection results of the raw materials. Such raw materials are easier to bend, and bending will cause the cell structure of the vegetables to be damaged, causing the cell contents to leak out, and the damaged parts provide a convenient channel for the invasion and reproduction of microorganisms, causing this type of vegetables to rot easily. In this case, the preset secondary proportion for judging whether the quality of a single batch of raw materials is qualified is adjusted to automatically adjust the data processing standard according to the actual situation and characteristics of the raw materials, thereby effectively improving the detection efficiency of the quality of the dishes.

[0107] Specifically, the analysis module is used to adjust the preset secondary proportion to a corresponding value based on the preset adjustment parameter and the parameter difference of the adjustment parameter, wherein:

[0108] The increase in the preset secondary proportion determined based on the parameter difference is positively correlated with the parameter difference.

[0109] In this embodiment, optionally:

[0110] Comparing the parameter difference with a first preset parameter difference and a second preset parameter difference;

[0111] If the parameter difference is less than or equal to the first preset parameter difference, the preset secondary proportion is adjusted to the corresponding value using the first preset proportion adjustment coefficient, and the preset secondary proportion adjusted using the first preset proportion adjustment coefficient is 1.12 times the initial preset secondary proportion.

[0112] If the parameter difference is less than or equal to the second preset parameter difference and greater than the first preset parameter difference, the preset secondary proportion is adjusted to the corresponding value using the second preset proportion adjustment coefficient. The preset secondary proportion adjusted using the second preset proportion adjustment coefficient is 1.22 times the initial preset secondary proportion.

[0113] If the parameter difference is greater than the second preset parameter difference, the preset secondary proportion is adjusted to the corresponding value using the third preset proportion adjustment coefficient, and the preset secondary proportion adjusted using the third preset proportion adjustment coefficient is 1.32 times the initial preset secondary proportion;

[0114] The first preset parameter difference is 0.2T0, and the second preset parameter difference is 0.8T0.

[0115] Specifically, the analysis module is used to determine whether the quality of a single batch of raw materials is qualified based on the secondary proportion, including:

[0116] If the secondary proportion is less than or equal to the preset secondary proportion, the quality of the single batch of raw materials is determined to be qualified;

[0117] If the secondary proportion is greater than the preset secondary proportion, the quality of the single batch of raw materials is judged to be unqualified.

[0118] The preset secondary proportion R0 is selected in the interval [0.23, 0.33].

[0119] Specifically, the analysis module is used to adjust the maximum retention warning time to a corresponding value based on the secondary proportion when determining that the quality of a single batch of raw materials is unqualified, wherein:

[0120] The reduction in the maximum retention warning time determined based on the secondary proportion is positively correlated with the secondary proportion.

[0121] In this embodiment, optionally:

[0122] Compare the secondary proportion with the first preset proportion proofreading threshold and the second preset proportion proofreading threshold;

[0123] If the secondary proportion is less than or equal to the first preset proportion proofreading threshold, the maximum retention warning duration is determined as the first maximum retention warning duration, and the first maximum retention warning duration is 0.82 times the initial maximum retention warning duration;

[0124] If the secondary proportion is less than or equal to the second preset proportion proofreading threshold and greater than the first preset proportion proofreading threshold, the maximum retention warning duration is determined as the second maximum retention warning duration, and the second maximum retention warning duration is 0.62 times the initial maximum retention warning duration;

[0125] If the secondary proportion is greater than the second preset proportion proofreading threshold, the maximum retention warning duration is determined as the third maximum retention warning duration, and the third maximum retention warning duration is 0.41 times the initial maximum retention warning duration;

[0126] The first preset ratio correction threshold is 1.4R0, and the second preset ratio correction threshold is 2.2R0.

[0127] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0128] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A food quality detection system, characterized in that: include: A conveying module, comprising a conveyor belt for conveying raw materials to be processed; a gripping module, comprising a mechanical arm disposed above the conveyor belt for lifting the raw material at a predetermined gripping point; A detection module, comprising a first visual detector arranged above the conveyor belt for obtaining image information of the raw material and a second visual detector arranged at one side of the conveyor belt for obtaining side image information; A raw material classification module, which is connected to the detection module, is used to determine the doping degree of the color block based on the raw material image information obtained by the visual detector, and classify each raw material grade in combination with the change in raw material curvature; A display module, which is used to output the maximum retention warning time of each batch of raw materials; The analysis module is respectively connected to the clamping module, the raw material classification module and the display module, and is used to determine whether a single batch of raw materials meets the preset standards based on the grade proportion of each raw material, and to adjust the operating speed of the robot arm to a corresponding value or adjust the maximum retention warning time for a single batch of raw materials to a corresponding value based on the judgment result.

2. The food quality detection system according to claim 1, characterized in that: The raw material classification module is used to determine the doping degree of the color block based on the raw material image information, including: Used to identify and select each grayscale area based on the grayscale value of the raw material image information; It is used to calculate the ratio of the average area of ​​each grayscale area to the total raw material area in the raw material image information to obtain the color block doping degree.

3. The food quality detection system according to claim 2, characterized in that: The raw material classification module is used to classify the grade of a single raw material based on the doping degree of the color block, including: If the color block impurity is greater than the second preset color block impurity, the raw material is classified as a primary raw material; If the color block impurity is less than or equal to the second preset color block impurity and greater than the first preset color block impurity, the grade of the single raw material is divided based on the change in curvature of the raw material; If the color block impurity is less than or equal to the first preset color block impurity, the raw material is classified into three levels of raw materials.

4. The food quality detection system according to claim 3, characterized in that: The raw material classification module is used to determine the curvature change of the raw material based on the side image information, including: The robot arm is used to lift the raw material under the condition that the raw material classification module determines to classify the single raw material based on the curvature change of the raw material, and the second visual detector obtains the side image information after lifting; The raw material segmentation module is used to obtain the raw material contour in the side image information; The raw material division module is used to obtain the height distance between the height of the lowest point in the raw material contour and the height of the end of the robot arm, and solve the ratio of the height distance to the length of the raw material contour to obtain the curvature change of the raw material; The raw material classification module is used to classify the grade of a single raw material based on the change in raw material curvature, including: If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material, the raw material is classified as a first-level raw material; If the curvature change of the raw material is less than or equal to the first preset curvature change of the raw material and greater than the second preset curvature change of the raw material, the raw material is classified as a secondary raw material; If the change in curvature of the raw material is greater than the second preset change in curvature of the raw material, the raw material is classified as secondary or tertiary raw material.

5. The food quality detection system according to claim 4, characterized in that: The analysis module is used to determine whether the operating parameters of the clamping module meet the preset standards based on the proportion of the quantity of the secondary and tertiary raw materials to the total quantity of the raw materials detected in a single detection cycle, including: If the proportion of the second-level third-level is less than or equal to the preset proportion of the second-level third-level, the quality of the single batch of raw materials is determined based on the proportion of the second-level; If the secondary tertiary proportion is greater than the preset secondary tertiary proportion, the operating speed of the robot arm will be adjusted to the corresponding value based on the corresponding reference weight of the single batch of raw materials, and based on the secondary tertiary proportion within the detection cycle re-acquired after adjustment, it will be determined whether the preset secondary proportion will be adjusted to the corresponding value, and based on the secondary proportion, it will be determined whether the quality of the single batch of raw materials is qualified.

6. The food quality detection system according to claim 5, characterized in that: The analysis module is used to adjust the running speed of the robot arm to a corresponding value based on the corresponding reference weight of a single batch of raw materials, wherein: The reduction in the operating speed of the robot arm determined based on the corresponding reference weight of a single batch of raw materials is negatively correlated with the corresponding reference weight.

7. The food quality detection system according to claim 6, characterized in that: The analysis module is used to determine whether to adjust the preset secondary proportion to a corresponding value based on the secondary and tertiary proportions in the re-acquired detection cycle under the condition that the operation speed adjustment of the robot arm is completed, including: Calculate the ratio of the re-acquired secondary third-level proportion to the secondary third-level proportion acquired in the previous detection cycle, and determine the ratio as an adjustment parameter; If the adjustment parameter is less than or equal to the preset adjustment parameter, the preset secondary proportion is adjusted to the corresponding value, and whether the quality of the single batch of raw materials is qualified is determined based on the secondary proportion; If the adjustment parameter is greater than the preset adjustment parameter, the quality of the single batch of raw materials is judged to be unqualified.

8. The food quality detection system according to claim 7, characterized in that: The analysis module is used to adjust the preset secondary proportion to a corresponding value based on the preset adjustment parameter and the parameter difference of the adjustment parameter, wherein: The increase in the preset secondary proportion determined based on the parameter difference is positively correlated with the parameter difference.

9. The food quality detection system according to claim 8, characterized in that: The analysis module is used to determine whether the quality of a single batch of raw materials is qualified based on the secondary proportion, including: If the secondary proportion is less than or equal to the preset secondary proportion, the quality of the single batch of raw materials is determined to be qualified; If the secondary proportion is greater than the preset secondary proportion, the quality of the single batch of raw materials is judged to be unqualified.

10. The food quality detection system according to claim 9, characterized in that: The analysis module is used to adjust the maximum retention warning time to a corresponding value based on the secondary proportion when determining that the quality of a single batch of raw materials is unqualified, wherein: The reduction in the maximum retention warning time determined based on the secondary proportion is positively correlated with the secondary proportion.

Images