Multi-station storage, picking and stacking conveyor and stacking method

Abstract

The present invention discloses a multi-station storage, picking and stacking conveyor and a stacking method, which relate to the field of transportation and solve the problem of poor stacking effect of the existing multi-station storage, picking and stacking conveyor. The present invention comprises a data acquisition module: which divides multiple goods to be stacked on the conveyor belt into a first type of goods to be stacked and a second type of goods to be stacked, and obtains initial classification data of the types of goods to be stacked; a data analysis module: which is used to perform goods stacking index analysis on the second type of goods to be stacked according to the initial classification data of the types of goods to be stacked, and obtain goods stacking index analysis data; a goods stacking module: which is used to automatically stack the first type of goods to be stacked and the second type of goods to be stacked according to the initial classification data of the types of goods to be stacked and the goods stacking index analysis data. The present invention can improve the safety and scientificity of the goods stacking process.

Description

Technical Field

[0001] The invention belongs to the field of transportation and relates to stacking technology, in particular to a multi-station storage, picking and stacking conveyor and a stacking method. Background Art

[0002] The existing multi-station storage, picking and stacking conveyor has the following specific defects when sorting and stacking goods:

[0003] 1. When sorting and stacking goods, the existing picking and stacking conveyor does not re-screen and classify flammable and explosive goods on the stacking conveyor belt. This can easily cause flammable and explosive goods to be mixed with regular goods, resulting in certain safety hazards in the stacking process.

[0004] 2. When sorting and stacking goods, the existing picking and stacking conveyor does not perform center of gravity analysis and geometric shape analysis on the conventional stacked goods on the stacking conveyor belt to determine the basic stacking height of the goods, which results in the lack of pertinence and scientificity in the determination of the stacking height.

[0005] To this end, we propose a multi-station storage, picking and stacking conveyor and a stacking method. Summary of the Invention

[0006] In view of the deficiencies in the prior art, the present invention aims to provide a multi-station storage, picking and stacking conveyor. The present invention is based on real-time marking of goods on a conveyor belt to obtain a plurality of goods to be stacked, and respectively obtains a goods label image corresponding to each of the goods to be stacked, creates a goods label type recognition model to recognize the goods label image corresponding to each of the goods to be stacked, divides the plurality of goods to be stacked into a first type of goods to be stacked and a second type of goods to be stacked, obtains initial classification data of the types of goods to be stacked, performs a goods stacking index analysis on the second type of goods to be stacked based on the initial classification data of the types of goods to be stacked, and respectively obtains a stacking center of gravity deviation and a geometric shape deviation coefficient corresponding to each of the goods to be stacked to obtain goods stacking index analysis data, and automatically stacks the first type of goods to be stacked and the second type of goods to be stacked based on the initial classification data of the types of goods to be stacked and the goods stacking index analysis data;

[0007] In order to achieve the above objectives, the present invention adopts the following technical solution: a multi-station storage, picking and stacking conveyor, the specific working process of each module is as follows:

[0008] Data acquisition module: used to mark the goods on the conveyor belt in real time, obtain multiple goods to be stacked, and respectively obtain the cargo label image corresponding to each cargo to be stacked, create a cargo label type recognition model to recognize the cargo label image corresponding to each cargo to be stacked, and classify the multiple cargo to be stacked into the first type of cargo to be stacked and the second type of cargo to be stacked, thereby obtaining the initial classification data of the cargo to be stacked;

[0009] Data analysis module: used to perform cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtain the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, to obtain cargo stacking index analysis data;

[0010] Cargo stacking module: used to automatically stack the first type of cargo to be stacked and the second type of cargo to be stacked according to the initial classification data of the cargo types to be stacked and the cargo stacking index analysis data.

[0011] Furthermore, the data acquisition module acquires data on the initial classification of the types of goods to be stacked, specifically as follows:

[0012] During the operation of the stacking conveyor, the goods to be stacked in the conveyor belt of the stacking conveyor are marked in real time to obtain multiple goods to be stacked, and one of the multiple goods to be stacked marked in real time is randomly selected as the target goods to be stacked;

[0013] Perform label recognition on the target goods to be stacked to obtain the goods label image corresponding to the target goods to be stacked;

[0014] Perform label recognition on each of the goods to be stacked except the target goods to be stacked, and obtain multiple goods label images;

[0015] Create a cargo label type recognition model;

[0016] Use the cargo label type recognition model to identify the cargo label images corresponding to the target cargo to be stacked, and perform preliminary classification of the target cargo to be stacked based on the recognition results;

[0017] The details are as follows:

[0018] Use the cargo label type recognition model to perform preliminary classification of cargo label images corresponding to the target cargo to be stacked;

[0019] If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a first type of stacking label image, the target cargo to be stacked is marked as the first type of cargo to be stacked;

[0020] If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a second type of stacking label image, the target cargo to be stacked is marked as the second type of cargo to be stacked;

[0021] Using a cargo label type recognition model, the cargo label image corresponding to each cargo to be stacked except the target cargo to be stacked is classified into types to obtain a plurality of first-type cargo to be stacked and second-type cargo to be stacked;

[0022] The first type of goods to be stacked and the second type of goods to be stacked are defined as data for initial classification of types of goods to be stacked.

[0023] Furthermore, the data acquisition module acquires the cargo label image corresponding to the target cargo to be stacked, as follows:

[0024] Obtain the cargo label corresponding to the target cargo to be stacked to obtain the target cargo label to be stacked;

[0025] If the target cargo label to be stacked is an image label, the label content corresponding to the image label is acquired by the first data acquisition device to obtain a cargo label image corresponding to the target cargo to be stacked;

[0026] If the target cargo label to be stacked is an RFID tag, the second data acquisition device reads the tag content corresponding to the RFID tag, and captures the displayed text corresponding to the tag content to obtain a cargo label image corresponding to the target cargo to be stacked.

[0027] Furthermore, the data acquisition module creates a cargo label type recognition model as follows:

[0028] Using big data crawler technology, multiple dry stacked cargo label images are obtained using stacked cargo label images as keywords;

[0029] Each stacked cargo label image is marked as a first type stacking label image and a second type stacking label image by manual marking to obtain stacking label image marking data;

[0030] The stacked labeled image labeled data is divided into a labeled image training set and a labeled image test set according to the image training and testing ratio;

[0031] Create an image recognition model using the existing artificial intelligence platform and train it using the labeled image training set until the image recognition model is trained once for each labeled image of stacked goods in the labeled image training set;

[0032] The image recognition model is tested using the labeled image test set, and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed, and the cargo label type recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the image recognition model is trained using the labeled image training set until the recognition accuracy is greater than or equal to the target recognition accuracy.

[0033] Furthermore, the data analysis module acquires cargo stacking index analysis data as follows:

[0034] Obtaining data on the initial classification of the types of goods to be stacked, obtaining data on each second type of goods to be stacked based on the data on the initial classification of the types of goods to be stacked, obtaining a plurality of second types of goods to be stacked, and randomly selecting one of the plurality of second types of goods to be stacked as a characteristic goods to be stacked;

[0035] Performing a center of gravity analysis on characteristic goods to be stacked to obtain a center of gravity deviation corresponding to the characteristic goods to be stacked;

[0036] Obtaining the stacking center of gravity deviation corresponding to each second type of goods to be stacked, respectively, to obtain multiple stacking center of gravity deviations;

[0037] Analyze the geometric shape of characteristic goods to be stacked to obtain the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked;

[0038] Obtaining a geometric shape deviation coefficient corresponding to each second type of goods to be stacked, to obtain a plurality of geometric shape deviation coefficients;

[0039] A plurality of geometric shape deviation coefficients and a plurality of stacking center of gravity deviations are defined as cargo stacking index analysis data.

[0040] Furthermore, the data analysis module obtains the stacking center of gravity deviation corresponding to the characteristic goods to be stacked, as follows:

[0041] Acquire a characteristic three-dimensional modeling image of the goods to be stacked, and obtain a characteristic three-dimensional modeling image;

[0042] In the characteristic 3D modeling image, mark the geometric center of the characteristic goods to be stacked as the coordinate origin. Draw a horizontal line in any direction through the coordinate origin to obtain the coordinate X-axis. In the horizontal plane, draw a line perpendicular to the coordinate X-axis through the coordinate origin to obtain the coordinate Y-axis. Draw a line perpendicular to the horizontal plane through the coordinate origin to obtain the coordinate Z-axis.

[0043] The three-dimensional coordinate system composed of the coordinate X axis, coordinate Y axis, coordinate Z axis and coordinate origin is marked as the center of gravity monitoring coordinate system;

[0044] Mark a number of characteristic points inside the characteristic goods to be stacked, and name the marked characteristic points as the first characteristic point to the jth characteristic point respectively;

[0045] Acquire the feature point density of the first feature point to the jth feature point inside the characteristic goods to be stacked, and obtain the first feature density to the jth feature density;

[0046] In the center of gravity monitoring coordinate system, the three-dimensional coordinates corresponding to the first feature point to the j-th feature point are respectively acquired to obtain the first three-dimensional coordinates to the j-th three-dimensional coordinates;

[0047] The first three-dimensional coordinate to the j-th three-dimensional coordinate and the first characteristic density to the j-th characteristic density are calculated to obtain the center of gravity coordinate corresponding to the characteristic goods to be stacked;

[0048] Calculate the center of gravity coordinates corresponding to the characteristic goods to be stacked, as follows: ;

[0049] Where Zx (X, Y, Z) is the coordinate of the center of gravity corresponding to the characteristic goods to be stacked, (x1, y1, z1) to (xj, yj, zj) are the first three-dimensional coordinates to the jth three-dimensional coordinates, m1 to mj are the first characteristic density to the jth characteristic density, and j is the quantity value corresponding to the characteristic point;

[0050] Obtain the X-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a first coordinate deviation; obtain the Y-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a second coordinate deviation; obtain the Z-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a third coordinate deviation;

[0051] The first coordinate deviation, the second coordinate deviation, and the third coordinate deviation are averaged to obtain the stacking center of gravity deviation corresponding to the characteristic goods to be stacked.

[0052] Furthermore, the data analysis module obtains the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked, as follows:

[0053] Obtaining a characteristic floor area value of the cargo to be stacked on the stacking conveyor belt to obtain a characteristic floor area value, obtaining a cargo weight corresponding to the characteristic cargo to be stacked to obtain a characteristic cargo weight value, calculating a ratio of the characteristic cargo weight value to the characteristic floor area value to obtain a characteristic cargo stacking pressure;

[0054] Obtaining a height value of the characteristic cargo to be stacked on the stacking conveyor belt to obtain a characteristic cargo height value, obtaining a cargo width value corresponding to the characteristic cargo to be stacked to obtain a characteristic width value, and calculating a ratio of the characteristic width value to the characteristic cargo height value to obtain a characteristic cargo stacking width-to-height ratio;

[0055] Obtaining the reference stacking pressure and reference stacking width-to-height ratio corresponding to the characteristic goods to be stacked respectively;

[0056] The characteristic cargo stacking pressure, the characteristic cargo stacking width-to-height ratio, the reference stacking pressure and the reference stacking width-to-height ratio are calculated to obtain the geometric shape deviation coefficient corresponding to the characteristic cargo to be stacked;

[0057] Calculate the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked. The specific formula is as follows: ;

[0058] Among them, Jhp is the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked, Ptz is the characteristic goods stacking pressure, Pjz is the reference stacking pressure, Btz is the characteristic goods stacking width-to-height ratio, and Bjz is the reference stacking width-to-height ratio.

[0059] Furthermore, the cargo stacking module automatically stacks the first type of cargo to be stacked and the second type of cargo to be stacked, respectively, as follows:

[0060] Acquire data on the initial classification of types of goods to be stacked, and acquire a plurality of first-type goods to be stacked and a plurality of second-type goods to be stacked according to the data on the initial classification of types of goods to be stacked;

[0061] Automatically stack each first type of goods to be stacked according to the calibrated stacking height for flammable and explosive goods;

[0062] Each second type of goods to be stacked is automatically stacked according to the corresponding goods reference stacking height.

[0063] Furthermore, the cargo stacking module obtains the cargo reference stacking height as follows:

[0064] Obtain cargo stacking index analysis data, and obtain a geometric shape deviation coefficient and a stacking center of gravity deviation corresponding to each second type of cargo to be stacked according to the cargo stacking index analysis data;

[0065] Get the maximum stacking height of the goods that can be stacked by the current stacker and get the maximum stacking height of the goods;

[0066] The geometric shape deviation coefficient, stacking center of gravity deviation and maximum stacking height of the goods corresponding to the same goods are calculated to obtain the reference stacking height of the goods;

[0067] Calculate the base stacking height of goods. The specific formula is as follows: ;

[0068] Among them, Ddj is the reference stacking height of the goods, Gjx is the maximum stacking height of the goods, Jhp is the geometric shape deviation coefficient, Zxp is the stacking center of gravity deviation, and s1 is the set proportional coefficient.

[0069] A multi-station storage, picking, stacking and conveying method includes the following specific steps:

[0070] Step S1: Marking goods on a conveyor belt in real time to obtain a plurality of goods to be stacked, and obtaining a cargo label image corresponding to each of the goods to be stacked, creating a cargo label type recognition model to recognize the cargo label image corresponding to each of the goods to be stacked, and classifying the plurality of goods to be stacked into a first type of goods to be stacked and a second type of goods to be stacked, thereby obtaining initial classification data of the types of goods to be stacked;

[0071] Step S2: performing cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtaining the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, to obtain cargo stacking index analysis data;

[0072] Step S3: Automatically stacking the first type of goods to be stacked and the second type of goods to be stacked according to the initial classification data of the types of goods to be stacked and the goods stacking index analysis data.

[0073] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0074] 1. The present invention re-screens and classifies flammable and explosive goods in the cargo on the stacking conveyor belt, thereby preventing flammable and explosive goods from being mixed with conventional goods in stacking, thereby reducing safety hazards in the stacking process;

[0075] 2. The present invention determines the standard stacking height of goods by performing a center of gravity analysis and a geometric shape analysis on conventional stacked goods on a stacking conveyor belt, thereby ensuring the scientific nature of the stacking height of goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0077] Figure 1 is a block diagram of the overall system of the present invention;

[0078] Figure 2 It is a diagram of the implementation steps of the present invention;

[0079] Figure 3 This is the characteristic three-dimensional modeling image in the present invention. DETAILED DESCRIPTION

[0080] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. Example

[0081] See also Figure 1 The present invention provides a technical solution: a multi-station storage, picking and stacking conveyor, the stacker comprising a data acquisition module, a data analysis module, a cargo stacking module and a server, the data acquisition module, the data analysis module and the cargo stacking module being respectively connected to the server, and the server controlling the data acquisition module, the acquisition and sorting module and the cargo stacking module respectively;

[0082] The data acquisition module marks the goods on the conveyor belt in real time to obtain multiple goods to be stacked, and obtains the cargo label image corresponding to each of the goods to be stacked. A cargo label type recognition model is created to recognize the cargo label image corresponding to each of the goods to be stacked, and the multiple goods to be stacked are classified into the first type of goods to be stacked and the second type of goods to be stacked, thereby obtaining the initial classification data of the types of goods to be stacked;

[0083] The details are as follows:

[0084] During the operation of the stacking conveyor, the goods to be stacked in the conveyor belt of the stacking conveyor are marked in real time to obtain multiple goods to be stacked, and one of the multiple goods to be stacked marked in real time is randomly selected as the target goods to be stacked;

[0085] It should be noted here that:

[0086] In this application, the goods to be stacked referred to herein are specifically box-packed goods in the conveyor belt of the stacking conveyor;

[0087] Perform label recognition on the target goods to be stacked to obtain the goods label image corresponding to the target goods to be stacked;

[0088] The details are as follows:

[0089] Obtain the cargo label corresponding to the target cargo to be stacked to obtain the target cargo label to be stacked;

[0090] If the target cargo label to be stacked is an image label, the label content corresponding to the image label is acquired by the first data acquisition device to obtain a cargo label image corresponding to the target cargo to be stacked;

[0091] If the target cargo label to be stacked is an RFID tag, the second data acquisition device reads the label content corresponding to the RFID tag, and captures the displayed text corresponding to the label content to obtain a cargo label image corresponding to the target cargo label;

[0092] Perform label recognition on each of the goods to be stacked except the target goods to be stacked, and obtain multiple goods label images;

[0093] It should be noted here that:

[0094] In this application, the first data acquisition device involved here is a camera, and the second data acquisition device involved here is an RFID reader and a display device matched therewith;

[0095] Create a cargo label type recognition model;

[0096] The details are as follows:

[0097] Using big data crawler technology, multiple dry stacked cargo label images are obtained using stacked cargo label images as keywords;

[0098] Each stacked cargo label image is marked as a first type stacking label image and a second type stacking label image by manual marking to obtain stacking label image marking data;

[0099] It should be noted here that:

[0100] In this application, the first type of stacking label image involved here is specifically the cargo label image corresponding to flammable and explosive goods, and the second type of stacking label image involved here is specifically the cargo label image corresponding to non-flammable and explosive goods;

[0101] In this application, the specific cargo corresponding to the first type of stacking label image involved herein includes but is not limited to metal powder, chemicals and gas cargo;

[0102] The stacked labeled image labeled data is divided into a labeled image training set and a labeled image test set according to the image training and testing ratio;

[0103] It should be noted here that:

[0104] In this application, the image training-test ratio is specifically set to 7:3, that is, the ratio of the number of labeled images of stacked goods in the labeled image training set and the labeled image test set is 7:3;

[0105] Create an image recognition model using the existing artificial intelligence platform and train it using the labeled image training set until the image recognition model is trained once for each labeled image of stacked goods in the labeled image training set;

[0106] Use the labeled image test set to test the image recognition model and obtain the recognition accuracy. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed and the cargo label type recognition model is obtained. If the recognition accuracy is less than the target recognition accuracy, continue to use the labeled image training set to train the image recognition model until the recognition accuracy is greater than or equal to the target recognition accuracy.

[0107] It should be noted here that:

[0108] The target recognition accuracy involved here is specifically set to 95% in this application;

[0109] Use the cargo label type recognition model to identify the cargo label images corresponding to the target cargo to be stacked, and perform preliminary classification of the target cargo to be stacked based on the recognition results;

[0110] The details are as follows:

[0111] Use the cargo label type recognition model to perform preliminary classification of cargo label images corresponding to the target cargo to be stacked;

[0112] If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a first type of stacking label image, the target cargo to be stacked is marked as the first type of cargo to be stacked;

[0113] If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a second type of stacking label image, the target cargo to be stacked is marked as the second type of cargo to be stacked;

[0114] Using a cargo label type recognition model, the cargo label image corresponding to each cargo to be stacked except the target cargo to be stacked is classified into types to obtain a plurality of first-type cargo to be stacked and second-type cargo to be stacked;

[0115] The first type of goods to be stacked and the second type of goods to be stacked are defined as initial classification data of goods to be stacked;

[0116] The data analysis module performs cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtains the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, thereby obtaining cargo stacking index analysis data;

[0117] Obtaining data on the initial classification of the types of goods to be stacked, obtaining data on each second type of goods to be stacked based on the data on the initial classification of the types of goods to be stacked, obtaining a plurality of second types of goods to be stacked, and randomly selecting one of the plurality of second types of goods to be stacked as a characteristic goods to be stacked;

[0118] Performing a center of gravity analysis on characteristic goods to be stacked to obtain the center of gravity deviation corresponding to the characteristic goods to be stacked;

[0119] The details are as follows:

[0120] Acquire a characteristic three-dimensional modeling image of the goods to be stacked, and obtain a characteristic three-dimensional modeling image;

[0121] In the characteristic 3D modeling image, mark the geometric center of the characteristic goods to be stacked as the coordinate origin. Draw a horizontal line in any direction through the coordinate origin to obtain the coordinate X-axis. In the horizontal plane, draw a line perpendicular to the coordinate X-axis through the coordinate origin to obtain the coordinate Y-axis. Draw a line perpendicular to the horizontal plane through the coordinate origin to obtain the coordinate Z-axis.

[0122] The three-dimensional coordinate system composed of the coordinate X axis, coordinate Y axis, coordinate Z axis and coordinate origin is marked as the center of gravity monitoring coordinate system;

[0123] Mark a number of characteristic points inside the characteristic goods to be stacked, and name the marked characteristic points as the first characteristic point to the jth characteristic point respectively;

[0124] It should be noted here that:

[0125] In this application, j is an integer greater than 0.

[0126] Acquire the feature point density of the first feature point to the jth feature point inside the characteristic goods to be stacked, and obtain the first feature density to the jth feature density;

[0127] In the center of gravity monitoring coordinate system, the three-dimensional coordinates corresponding to the first feature point to the j-th feature point are respectively acquired to obtain the first three-dimensional coordinates to the j-th three-dimensional coordinates;

[0128] The first three-dimensional coordinate to the j-th three-dimensional coordinate and the first characteristic density to the j-th characteristic density are calculated to obtain the center of gravity coordinate corresponding to the characteristic goods to be stacked;

[0129] Calculate the center of gravity coordinates corresponding to the characteristic goods to be stacked, as follows: ;

[0130] Where Zx (X, Y, Z) is the coordinate of the center of gravity corresponding to the characteristic goods to be stacked, (x1, y1, z1) to (xj, yj, zj) are the first three-dimensional coordinates to the jth three-dimensional coordinates, m1 to mj are the first characteristic density to the jth characteristic density, and j is the quantity value corresponding to the characteristic point;

[0131] Obtain the X-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a first coordinate deviation; obtain the Y-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a second coordinate deviation; obtain the Z-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a third coordinate deviation;

[0132] Calculate the average of the first coordinate deviation, the second coordinate deviation, and the third coordinate deviation to obtain the stacking center of gravity deviation corresponding to the characteristic goods to be stacked;

[0133] Obtaining the stacking center of gravity deviation corresponding to each second type of goods to be stacked, respectively, to obtain multiple stacking center of gravity deviations;

[0134] Analyze the geometric shape of characteristic goods to be stacked to obtain the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked;

[0135] The details are as follows:

[0136] Obtaining a characteristic floor area value of the cargo to be stacked on the stacking conveyor belt to obtain a characteristic floor area value, obtaining a cargo weight corresponding to the characteristic cargo to be stacked to obtain a characteristic cargo weight value, calculating a ratio of the characteristic cargo weight value to the characteristic floor area value to obtain a characteristic cargo stacking pressure;

[0137] Obtaining a height value of the characteristic cargo to be stacked on the stacking conveyor belt to obtain a characteristic cargo height value, obtaining a cargo width value corresponding to the characteristic cargo to be stacked to obtain a characteristic width value, and calculating a ratio of the characteristic width value to the characteristic cargo height value to obtain a characteristic cargo stacking width-to-height ratio;

[0138] Obtaining the reference stacking pressure and reference stacking width-to-height ratio corresponding to the characteristic goods to be stacked respectively;

[0139] The characteristic cargo stacking pressure, the characteristic cargo stacking width-to-height ratio, the reference stacking pressure and the reference stacking width-to-height ratio are calculated to obtain the geometric shape deviation coefficient corresponding to the characteristic cargo to be stacked;

[0140] Calculate the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked. The specific formula is as follows: ;

[0141] Among them, Jhp is the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked, Ptz is the characteristic goods stacking pressure, Pjz is the reference stacking pressure, Btz is the characteristic goods stacking width-to-height ratio, and Bjz is the reference stacking width-to-height ratio;

[0142] Obtaining a geometric shape deviation coefficient corresponding to each second type of goods to be stacked, to obtain a plurality of geometric shape deviation coefficients;

[0143] A plurality of geometric shape deviation coefficients and a plurality of stacking center of gravity deviations are defined as cargo stacking index analysis data;

[0144] The cargo stacking module automatically stacks the first type of cargo to be stacked and the second type of cargo to be stacked according to the initial classification data of the cargo types to be stacked and the cargo stacking index analysis data;

[0145] Acquire data on the initial classification of types of goods to be stacked, and acquire a plurality of first-type goods to be stacked and a plurality of second-type goods to be stacked according to the data on the initial classification of types of goods to be stacked;

[0146] Automatically stack each first type of goods to be stacked according to the calibrated stacking height for flammable and explosive goods;

[0147] It should be noted here that:

[0148] The rated stacking height of flammable and explosive goods involved here is determined by the local fire department;

[0149] Automatically stacking each second type of goods to be stacked according to the corresponding goods reference stacking height;

[0150] Obtain the benchmark stacking height of the goods, as follows:

[0151] Obtain cargo stacking index analysis data, and obtain a geometric shape deviation coefficient and a stacking center of gravity deviation corresponding to each second type of cargo to be stacked according to the cargo stacking index analysis data;

[0152] Get the maximum stacking height of the goods that can be stacked by the current stacker and get the maximum stacking height of the goods;

[0153] The geometric shape deviation coefficient, stacking center of gravity deviation and maximum stacking height of the goods corresponding to the same goods are calculated to obtain the reference stacking height of the goods;

[0154] Calculate the base stacking height of goods. The specific formula is as follows: ;

[0155] Among them, Ddj is the reference stacking height of the goods, Gjx is the maximum stacking height of the goods, Jhp is the geometric shape deviation coefficient, Zxp is the stacking center of gravity deviation, and s1 is the set proportional coefficient.

[0156] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable. Example

[0157] See also Figure 2 Based on another concept of the same invention, a multi-station storage, picking and stacking conveyor and a stacking method are proposed, including the following specific steps:

[0158] Step S1: Marking goods on a conveyor belt in real time to obtain a plurality of goods to be stacked, and obtaining a cargo label image corresponding to each of the goods to be stacked, creating a cargo label type recognition model to recognize the cargo label image corresponding to each of the goods to be stacked, and classifying the plurality of goods to be stacked into a first type of goods to be stacked and a second type of goods to be stacked, thereby obtaining initial classification data of the types of goods to be stacked;

[0159] Step S11: During the operation of the stacking conveyor, the goods to be stacked on the conveyor belt of the stacking conveyor are marked in real time to obtain a plurality of goods to be stacked, and one of the goods to be stacked marked in real time is randomly selected as the target goods to be stacked;

[0160] Step S12: performing label recognition on the target goods to be stacked to obtain a goods label image corresponding to the target goods to be stacked;

[0161] The details are as follows:

[0162] Step S121: Acquire the cargo label corresponding to the target cargo to be stacked to obtain the target cargo label;

[0163] Step S122: If the target cargo label to be stacked is an image label, the label content corresponding to the image label is acquired by a first data acquisition device to obtain a cargo label image corresponding to the target cargo to be stacked;

[0164] Step S123: If the target cargo label to be stacked is an RFID tag, the tag content corresponding to the RFID tag is read by a second data acquisition device, and the displayed text corresponding to the tag content is captured on the screen to obtain a cargo label image corresponding to the target cargo label;

[0165] Step S13: performing label recognition on each of the goods to be stacked except the target goods to be stacked, and obtaining a plurality of goods label images;

[0166] Step S14: creating a cargo label type recognition model;

[0167] The details are as follows:

[0168] Step S141: using big data crawler technology to obtain multiple dry stacked cargo label images using stacked cargo label images as keywords;

[0169] Step S142: manually marking each stacked goods label image as a first type stacking label image and a second type stacking label image to obtain stacking label image marking data;

[0170] Step S143: dividing the stacked labeled image labeled data into a labeled image training set and a labeled image test set according to the image training and testing ratio;

[0171] Step S144: Create an image recognition model using an existing artificial intelligence platform, and train the image recognition model using the labeled image training set until the image recognition model is trained once for each labeled image of stacked goods in the labeled image training set;

[0172] Step S145: The image recognition model is tested using the labeled image test set and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed, and a cargo label type recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the image recognition model is continuously trained using the labeled image training set until the recognition accuracy is greater than or equal to the target recognition accuracy.

[0173] Step S15: using a cargo label type recognition model to identify the cargo label image corresponding to the target cargo to be stacked, and performing a preliminary classification of the target cargo to be stacked based on the recognition result;

[0174] The details are as follows:

[0175] Step S151: using a cargo label type recognition model to perform preliminary classification of cargo label images corresponding to target cargo to be stacked;

[0176] Step S152: If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a first type of stacking label image, the target cargo to be stacked is marked as the first type of cargo to be stacked;

[0177] Step S153: If the cargo label type recognition model classifies the cargo label image corresponding to the target cargo to be stacked as a second type of stacking label image, the target cargo to be stacked is marked as the second type of cargo to be stacked;

[0178] Step S16: using a cargo label type recognition model to classify the cargo label image corresponding to each cargo to be stacked except the target cargo to be stacked into a type, to obtain a plurality of first-type cargo to be stacked and second-type cargo to be stacked;

[0179] Step S17: defining the first type of goods to be stacked and the second type of goods to be stacked as initial classification data of goods to be stacked;

[0180] Step S2: performing cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtaining the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, to obtain cargo stacking index analysis data;

[0181] Step S21: obtaining data on the initial classification of the types of goods to be stacked, obtaining data on each second type of goods to be stacked based on the data on the initial classification of the types of goods to be stacked, obtaining a plurality of second types of goods to be stacked, and randomly selecting one of the plurality of second types of goods to be stacked as a characteristic goods to be stacked;

[0182] Step S22: analyzing the center of gravity of the characteristic goods to be stacked to obtain the center of gravity deviation corresponding to the characteristic goods to be stacked;

[0183] The details are as follows:

[0184] Step S221: Acquire a characteristic 3D modeling image of the goods to be stacked to obtain a characteristic 3D modeling image;

[0185] Step S222: Please refer to Figure 3 In the characteristic 3D modeling image, the geometric center corresponding to the characteristic goods to be stacked is marked as the coordinate origin. A horizontal straight line is drawn in any direction through the coordinate origin to obtain the coordinate X-axis. In the horizontal plane, a straight line perpendicular to the coordinate X-axis is drawn through the coordinate origin to obtain the coordinate Y-axis. A straight line perpendicular to the horizontal plane is drawn through the coordinate origin to obtain the coordinate Z-axis.

[0186] Step S223: The three-dimensional coordinate system consisting of the coordinate X axis, the coordinate Y axis, the coordinate Z axis and the coordinate origin is marked as the center of gravity monitoring coordinate system;

[0187] Step S224: Marking a plurality of characteristic points inside the characteristic goods to be stacked, and naming the marked characteristic points as the first characteristic point to the jth characteristic point respectively;

[0188] Step S225: acquiring characteristic point densities of the first characteristic point to the jth characteristic point inside the characteristic goods to be stacked, respectively, to obtain first characteristic density to jth characteristic density;

[0189] Step S226: in the center of gravity monitoring coordinate system, respectively obtain the three-dimensional coordinates corresponding to the first feature point to the j-th feature point to obtain the first three-dimensional coordinates to the j-th three-dimensional coordinates;

[0190] Step S227: Calculating the first three-dimensional coordinate to the j-th three-dimensional coordinate and the first characteristic density to the j-th characteristic density to obtain the center of gravity coordinate corresponding to the characteristic goods to be stacked;

[0191] Calculate the center of gravity coordinates corresponding to the characteristic goods to be stacked, as follows: ;

[0192] Where Zx (X, Y, Z) is the coordinate of the center of gravity corresponding to the characteristic goods to be stacked, (x1, y1, z1) to (xj, yj, zj) are the first three-dimensional coordinates to the jth three-dimensional coordinates, m1 to mj are the first characteristic density to the jth characteristic density, and j is the quantity value corresponding to the characteristic point;

[0193] Step S228: Obtain the X-axis coordinate deviation between the center-of-gravity coordinates of the characteristic goods to be stacked and the coordinate origin to obtain a first coordinate deviation; obtain the Y-axis coordinate deviation between the center-of-gravity coordinates of the characteristic goods to be stacked and the coordinate origin to obtain a second coordinate deviation; obtain the Z-axis coordinate deviation between the center-of-gravity coordinates of the characteristic goods to be stacked and the coordinate origin to obtain a third coordinate deviation;

[0194] Step S229: Calculate the average of the first coordinate deviation, the second coordinate deviation, and the third coordinate deviation to obtain the stacking center of gravity deviation corresponding to the characteristic goods to be stacked;

[0195] Step S23: Obtaining the stacking center of gravity deviation corresponding to each second type of goods to be stacked, to obtain multiple stacking center of gravity deviations;

[0196] Step S24: Analyzing the geometric shape of the characteristic goods to be stacked to obtain a geometric shape deviation coefficient corresponding to the characteristic goods to be stacked;

[0197] The details are as follows:

[0198] Step S241: obtaining the floor space value of the characteristic cargo to be stacked on the stacking conveyor belt to obtain the characteristic floor space value, obtaining the cargo weight corresponding to the characteristic cargo to be stacked to obtain the characteristic cargo weight value, calculating the ratio of the characteristic cargo weight value to the characteristic floor space value to obtain the characteristic cargo stacking pressure;

[0199] Step S242: obtaining a height value of the characteristic cargo to be stacked on the stacking conveyor belt to obtain a characteristic cargo height value, obtaining a cargo width value corresponding to the characteristic cargo to be stacked to obtain a characteristic width value, and calculating a ratio of the characteristic width value to the characteristic cargo height value to obtain a characteristic cargo stacking width-to-height ratio;

[0200] Step S243: respectively obtaining a reference stacking pressure and a reference stacking aspect ratio corresponding to the characteristic goods to be stacked;

[0201] Step S244: Calculating the characteristic cargo stacking pressure, the characteristic cargo stacking width-to-height ratio, the reference stacking pressure, and the reference stacking width-to-height ratio to obtain a geometric shape deviation coefficient corresponding to the characteristic cargo to be stacked;

[0202] Calculate the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked. The specific formula is as follows: ;

[0203] Among them, Jhp is the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked, Ptz is the characteristic goods stacking pressure, Pjz is the reference stacking pressure, Btz is the characteristic goods stacking width-to-height ratio, and Bjz is the reference stacking width-to-height ratio;

[0204] Step S25: acquiring the geometric shape deviation coefficient corresponding to each second type of goods to be stacked, to obtain a plurality of geometric shape deviation coefficients;

[0205] Step S26: defining a plurality of geometric shape deviation coefficients and a plurality of stacking center of gravity deviations as cargo stacking index analysis data;

[0206] Step S3: Automatically stacking the first type of goods to be stacked and the second type of goods to be stacked according to the initial classification data of the goods to be stacked and the goods stacking index analysis data;

[0207] Step S31: obtaining data on the initial classification of the types of goods to be stacked, and obtaining a plurality of first-type goods to be stacked and a plurality of second-type goods to be stacked according to the data on the initial classification of the types of goods to be stacked;

[0208] Step S32: Automatically stack each first type of goods to be stacked according to the calibrated stacking height for flammable and explosive goods;

[0209] Step S33: Automatically stacking each second type of goods to be stacked according to the corresponding goods reference stacking height;

[0210] Obtain the benchmark stacking height of goods;

[0211] The details are as follows:

[0212] Step S331: Obtain cargo stacking index analysis data, and obtain the geometric shape deviation coefficient and stacking center of gravity deviation corresponding to each second type of cargo to be stacked according to the cargo stacking index analysis data;

[0213] Step S332: Obtain the maximum stacking height of the goods that can be stacked by the current stacker to obtain the maximum stacking height of the goods;

[0214] Step S333: Calculating the geometric shape deviation coefficient, stacking center of gravity deviation, and maximum stacking height of the goods corresponding to the same goods to obtain a reference stacking height of the goods;

[0215] Calculate the base stacking height of goods. The specific formula is as follows: Among them, Ddj is the reference stacking height of the goods, Gjx is the maximum stacking height of the goods, Jhp is the geometric shape deviation coefficient, Zxp is the stacking center of gravity deviation, and s1 is the set proportional coefficient.

[0216] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-station storage, picking and stacking conveyor, characterized in that: Including the following modules: Data acquisition module: used to mark the goods on the conveyor belt in real time, obtain multiple goods to be stacked, and respectively obtain the cargo label image corresponding to each cargo to be stacked, create a cargo label type recognition model to recognize the cargo label image corresponding to each cargo to be stacked, and classify the multiple cargo to be stacked into the first type of cargo to be stacked and the second type of cargo to be stacked, thereby obtaining the initial classification data of the cargo to be stacked; Data analysis module: used to perform cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtain the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, to obtain cargo stacking index analysis data; Cargo stacking module: used for automatically stacking the first type of cargo to be stacked and the second type of cargo to be stacked according to the initial classification data of the cargo types to be stacked and the cargo stacking index analysis data; The data analysis module acquires cargo stacking index analysis data as follows: Obtaining data on the initial classification of the types of goods to be stacked, obtaining data on each second type of goods to be stacked based on the data on the initial classification of the types of goods to be stacked, obtaining a plurality of second types of goods to be stacked, and randomly selecting one of the plurality of second types of goods to be stacked as a characteristic goods to be stacked; Performing a center of gravity analysis on characteristic goods to be stacked to obtain the center of gravity deviation corresponding to the characteristic goods to be stacked; Obtaining the stacking center of gravity deviation corresponding to each second type of goods to be stacked, respectively, to obtain multiple stacking center of gravity deviations; Analyze the geometric shape of characteristic goods to be stacked to obtain the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked; Obtaining a geometric shape deviation coefficient corresponding to each second type of goods to be stacked, to obtain a plurality of geometric shape deviation coefficients; A plurality of geometric shape deviation coefficients and a plurality of stacking center of gravity deviations are defined as cargo stacking index analysis data; The data analysis module obtains the geometric shape deviation coefficient corresponding to the characteristic goods to be stacked, as follows: Obtaining a characteristic floor area value of the cargo to be stacked on the stacking conveyor belt to obtain a characteristic floor area value, obtaining a cargo weight corresponding to the characteristic cargo to be stacked to obtain a characteristic cargo weight value, calculating a ratio of the characteristic cargo weight value to the characteristic floor area value to obtain a characteristic cargo stacking pressure; Obtaining a height value of the characteristic cargo to be stacked on the stacking conveyor belt to obtain a characteristic cargo height value, obtaining a cargo width value corresponding to the characteristic cargo to be stacked to obtain a characteristic width value, and calculating a ratio of the characteristic width value to the characteristic cargo height value to obtain a characteristic cargo stacking width-to-height ratio; Obtaining the reference stacking pressure and reference stacking width-to-height ratio corresponding to the characteristic goods to be stacked respectively; The characteristic cargo stacking pressure, the characteristic cargo stacking width-to-height ratio, the reference stacking pressure and the reference stacking width-to-height ratio are calculated to obtain the geometric shape deviation coefficient corresponding to the characteristic cargo to be stacked.

2. The multi-station storage, picking and stacking conveyor according to claim 1, characterized in that: The data acquisition module acquires data on the initial classification of the types of goods to be stacked, specifically as follows: During the operation of the stacking conveyor, the goods to be stacked in the conveyor belt of the stacking conveyor are marked in real time to obtain multiple goods to be stacked, and one of the multiple goods to be stacked marked in real time is randomly selected as the target goods to be stacked; Perform label recognition on the target goods to be stacked to obtain the goods label image corresponding to the target goods to be stacked; Perform label recognition on each of the goods to be stacked except the target goods to be stacked, and obtain multiple goods label images; Create a cargo label type recognition model; Use the cargo label type recognition model to identify the cargo label images corresponding to the target cargo to be stacked, and perform preliminary classification of the target cargo to be stacked based on the recognition results; The details are as follows: Use the cargo label type recognition model to perform preliminary classification of cargo label images corresponding to the target cargo to be stacked; If the cargo label type recognition model classifies the cargo label image as a first type of stacking label image, the target cargo to be stacked is marked as the first type of cargo to be stacked; If the cargo label type recognition model classifies the cargo label image as a second type of stacking label image, the target cargo to be stacked is marked as the second type of cargo to be stacked; Using a cargo label type recognition model, classify the cargo label images corresponding to each cargo to be stacked except the target cargo to be stacked into different types, thereby obtaining a plurality of first-type cargo to be stacked and a plurality of second-type cargo to be stacked; The first type of goods to be stacked and the second type of goods to be stacked are defined as data for initial classification of types of goods to be stacked.

3. The multi-station storage, picking and stacking conveyor according to claim 2, characterized in that: The data acquisition module acquires the cargo label image corresponding to the target cargo to be stacked, specifically as follows: Obtain the cargo label corresponding to the target cargo to be stacked to obtain the target cargo label to be stacked; If the target cargo label to be stacked is an image label, the label content corresponding to the image label is acquired by the first data acquisition device to obtain a cargo label image corresponding to the target cargo to be stacked; If the target cargo label to be stacked is an RFID tag, the second data acquisition device reads the tag content corresponding to the RFID tag, and captures the displayed text corresponding to the tag content to obtain a cargo label image corresponding to the target cargo to be stacked.

4. The multi-station storage, picking and stacking conveyor according to claim 2, characterized in that: The data acquisition module creates a cargo label type recognition model as follows: Using big data crawler technology, multiple dry stacked cargo label images are obtained using stacked cargo label images as keywords; Each stacked cargo label image is marked as a first type stacking label image and a second type stacking label image by manual marking to obtain stacking label image marking data; The stacked labeled image labeled data is divided into a labeled image training set and a labeled image test set according to the image training and testing ratio; Create an image recognition model using the existing artificial intelligence platform and train it using the labeled image training set until the image recognition model is trained once for each labeled image of stacked goods in the labeled image training set; The image recognition model is tested using the labeled image test set, and the recognition accuracy is obtained. When the recognition accuracy is greater than or equal to the target recognition accuracy, the image recognition model training is completed, and the cargo label type recognition model is obtained. When the recognition accuracy is less than the target recognition accuracy, the image recognition model is trained using the labeled image training set until the recognition accuracy is greater than or equal to the target recognition accuracy.

5. The multi-station storage, picking and stacking conveyor according to claim 1, characterized in that: The data analysis module obtains the stacking center of gravity deviation corresponding to the characteristic goods to be stacked, specifically as follows: Acquire a characteristic three-dimensional modeling image of the goods to be stacked, and obtain a characteristic three-dimensional modeling image; In the characteristic 3D modeling image, mark the geometric center of the characteristic goods to be stacked as the coordinate origin. Draw a horizontal line in any direction through the coordinate origin to obtain the coordinate X-axis. In the horizontal plane, draw a line perpendicular to the coordinate X-axis through the coordinate origin to obtain the coordinate Y-axis. Draw a line perpendicular to the horizontal plane through the coordinate origin to obtain the coordinate Z-axis. The three-dimensional coordinate system composed of the coordinate X axis, coordinate Y axis, coordinate Z axis and coordinate origin is marked as the center of gravity monitoring coordinate system; Mark a number of characteristic points inside the characteristic goods to be stacked, and name the marked characteristic points as the first characteristic point to the jth characteristic point respectively; Acquire the characteristic point density of the first characteristic point to the j-th characteristic point inside the characteristic goods to be stacked, and obtain the first characteristic density to the j-th characteristic density; In the center of gravity monitoring coordinate system, the three-dimensional coordinates corresponding to the first feature point to the j-th feature point are respectively acquired to obtain the first three-dimensional coordinates to the j-th three-dimensional coordinates; The first three-dimensional coordinate to the j-th three-dimensional coordinate and the first characteristic density to the j-th characteristic density are calculated to obtain the center of gravity coordinate corresponding to the characteristic goods to be stacked; Calculate the center of gravity coordinates corresponding to the characteristic goods to be stacked, as follows: Where Zx (X, Y, Z) is the coordinate of the center of gravity corresponding to the characteristic goods to be stacked, (x1, y1, z1) to (xj, yj, zj) are the first three-dimensional coordinates to the jth three-dimensional coordinates, m1 to mj are the first characteristic density to the jth characteristic density, and j is the quantity value corresponding to the characteristic point; Obtain the X-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a first coordinate deviation; obtain the Y-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a second coordinate deviation; obtain the Z-axis coordinate deviation of the center of gravity coordinate corresponding to the characteristic goods to be stacked and the coordinate origin to obtain a third coordinate deviation; The first coordinate deviation, the second coordinate deviation, and the third coordinate deviation are averaged to obtain the stacking center of gravity deviation corresponding to the characteristic goods to be stacked.

6. The multi-station storage, picking and stacking conveyor according to claim 1, characterized in that: The cargo stacking module automatically stacks the first type of cargo to be stacked and the second type of cargo to be stacked, respectively, as follows: Acquire data on the initial classification of types of goods to be stacked, and acquire a plurality of first-type goods to be stacked and a plurality of second-type goods to be stacked according to the data on the initial classification of types of goods to be stacked; Automatically stack each first type of goods to be stacked according to the calibrated stacking height for flammable and explosive goods; Each second type of goods to be stacked is automatically stacked according to the corresponding goods reference stacking height.

7. The multi-station storage, picking and stacking conveyor according to claim 6, characterized in that: The cargo stacking module obtains the cargo reference stacking height as follows: Obtain cargo stacking index analysis data, and obtain a geometric shape deviation coefficient and a stacking center of gravity deviation corresponding to each second type of cargo to be stacked according to the cargo stacking index analysis data; Get the maximum stacking height of the goods that can be stacked by the current stacker and get the maximum stacking height of the goods; The geometric shape deviation coefficient, stacking center of gravity deviation and maximum stacking height of the goods corresponding to the same goods are calculated to obtain the reference stacking height of the goods; Calculate the base stacking height of goods. The specific formula is as follows: Ddj=Gjx-Gjx×[1-(Jhp+Zxp)×s1]; Among them, Ddj is the reference stacking height of the goods, Gjx is the maximum stacking height of the goods, Jhp is the geometric shape deviation coefficient, Zxp is the stacking center of gravity deviation, and s1 is the set proportional coefficient.

8. A multi-station storage, picking, stacking and conveying method, applicable to a multi-station storage, picking, stacking and conveying machine according to any one of claims 1 to 7, characterized in that: The stacking and conveying method comprises the following specific steps: Step S1: Marking goods on a conveyor belt in real time to obtain a plurality of goods to be stacked, and obtaining a cargo label image corresponding to each of the goods to be stacked, creating a cargo label type recognition model to recognize the cargo label image corresponding to each of the goods to be stacked, and classifying the plurality of goods to be stacked into a first type of goods to be stacked and a second type of goods to be stacked, thereby obtaining initial classification data of the types of goods to be stacked; Step S2: performing cargo stacking index analysis on the second type of cargo to be stacked based on the initial classification data of the cargo types to be stacked, and obtaining the stacking center of gravity deviation and geometric shape deviation coefficient corresponding to each cargo to be stacked, to obtain cargo stacking index analysis data; Step S3: Automatically stacking the first type of goods to be stacked and the second type of goods to be stacked according to the initial classification data of the types of goods to be stacked and the goods stacking index analysis data.

Images