Metal coil carrying and stacking method and system based on AGV

Abstract

The invention belongs to the technical field of smart factories. The invention provides a metal coil carrying and stacking method and system based on an AGV. The method comprises the following steps: acquiring a high-definition image of a target metal roll, extracting safety feature data according to the high-definition image, and processing the safety feature data by using a safety risk assessment model to obtain a carrying risk value; when the carrying risk value is higher than a risk threshold value, the placement posture of the target metal roll is determined, and a target AGV is obtained through screening according to the placement posture and the carrying risk value; and the target metal coil is placed on a bearing component of the target AGV according to the placing posture, and the target AGV is controlled to automatically carry the target metal coil to a stacking point position of the stacking area. According to the scheme, the proper placement posture of the target metal roll on the AGV and the proper AGV are determined according to the risk factors of the target metal roll, and therefore the safety risk of the AGV in the carrying process is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of smart factories, and in particular to an AGV-based metal coil handling and stacking method and system. Background Art

[0002] Metal coils are metal materials with certain size, shape and performance produced through a rolling process. Metal parts are widely used in automobile manufacturing, home appliance manufacturing, aerospace and other fields.

[0003] Metal coils are stacked in the production workshop and then transported to the production equipment when they are used. At present, many production workshops have begun to use AGV to automatically transport metal coils, which has significantly improved the efficiency of metal coil transportation. However, the existing AGV-based metal coil transportation and stacking methods mainly focus on the planning of the AGV's transportation route and the precise stacking at the stacking point, but lack consideration of the safety of the AGV during the transportation process, which makes transportation accidents prone to occur. This technical problem has not yet been effectively solved. Summary of the invention

[0004] In this regard, the present invention provides a metal coil handling and stacking method, system, electronic equipment, computer storage medium and computer program product based on AGV to solve the above technical problems.

[0005] The present invention discloses a metal coil handling and stacking method based on AGV, which comprises the following steps: obtaining a high-definition image of a target metal coil, extracting safety feature data according to the high-definition image, processing the safety feature data using a safety risk assessment model, and obtaining a handling risk value; when the handling risk value is higher than a risk threshold, determining the placement posture of the target metal coil, and obtaining a target AGV according to the placement posture and the handling risk value; placing the target metal coil on a bearing component of a target AGV according to the placement posture, and controlling the target AGV to automatically transport the target metal coil to a stacking point in a stacking area.

[0006] In some embodiments, the obtaining of a high-definition image of the target metal coil and extracting safety feature data based on the high-definition image include: capturing a panoramic image of the initial stacking area of ​​the metal coils through a high-definition camera, identifying the target metal coil from the panoramic image based on the current production task information, and capturing a high-definition image of the target metal coil; using image processing technology to identify and extract the safety feature data of the target metal coil in the high-definition image, the safety feature data including at least the number of binding straps, the uniformity of distribution of the binding straps, the tightness of the binding straps, and whether the metal coil is covered with protective materials; wherein the binding straps are steel straps or plastic straps.

[0007] In some embodiments, the use of a security risk assessment model to process the security feature data to obtain a handling risk value includes: using a convolutional network to extract features of the number of the binding straps, the distribution uniformity of the binding straps, the tightness of the binding straps, and whether the metal roll is covered with protective materials, respectively, to obtain quantity features, distribution uniformity features, tightness features, and protective material features, and integrating the quantity features, the distribution uniformity features, the tightness features, and the protective material features into risk features; inputting the risk features into the security risk assessment model to obtain the handling risk value predicted and output by the security risk assessment model.

[0008] In some embodiments, the inputting the risk feature into the safety risk assessment model to obtain the handling risk value predicted and output by the safety risk assessment model includes: inputting the risk feature into the safety risk assessment model to obtain a first handling risk value predicted and output by the safety risk assessment model; identifying a target binding strap adjacent to the end of a target metal coil based on the high-definition image, and calculating the interval distance between the target binding strap and the end of the target metal coil; wherein the target binding strap refers to a binding strap adjacent to the end of the target metal coil and located on the outermost metal plate of the target metal coil; determining a risk adjustment coefficient based on the interval distance, and multiplying the risk adjustment coefficient by the first handling risk value to obtain a second handling risk value, wherein the second handling risk value is the final handling risk value.

[0009] In some embodiments, determining the risk adjustment coefficient based on the spacing distance includes: obtaining the metal type and the number of winding layers of the target metal coil, and predicting the standard spacing distance based on the metal type and the number of winding layers; calculating the difference between the spacing distance and the standard spacing distance, and deriving the risk adjustment coefficient based on matching the difference with a preset first positive correlation.

[0010] In some embodiments, when the handling risk value is higher than a risk threshold, the placement posture of the target metal coil is determined, and a target AGV is obtained by screening according to the placement posture and the handling risk value, including: when the handling risk value is higher than the risk threshold, determining the placement posture of the target metal coil so that the end of the target metal coil is located at the bottom; determining a length range of the load-bearing clamping device according to the handling risk value and a preset second positive correlation, and obtaining the target AGV by screening according to the length range.

[0011] The present invention also discloses a metal coil handling and stacking system based on AGV, the system comprising a risk analysis module, a screening module and a scheduling module; the risk analysis module is used to obtain a high-definition image of a target metal coil, extract safety feature data based on the high-definition image, process the safety feature data using a safety risk assessment model, and obtain a handling risk value; the screening module is used to determine the placement posture of the target metal coil when the handling risk value is higher than a risk threshold, and obtain a target AGV based on the placement posture and the handling risk value; the scheduling module is used to place the target metal coil on the bearing component of the target AGV according to the placement posture, and control the target AGV to automatically transport the target metal coil to the stacking point in the stacking area.

[0012] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0013] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0015] Compared with the prior art which only focuses on planning the AGV's transport route and precise stacking at stacking points, the solution of the present invention focuses on the safety of the AGV during the transport process, and determines the appropriate placement posture of the target metal roll on the AGV and the appropriate AGV based on the extracted risk factors of the target metal roll, thereby reducing the probability of safety risks occurring during the transport of the AGV, and even if an accident occurs during the transport, the risk of injury to people and property can be minimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a method for transporting and stacking metal coils based on AGV disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a corresponding schematic diagram of the target metal coil and the load-bearing clamping device disclosed in the embodiment of the present invention.

[0019] Figure 3 It is a structural schematic diagram of a metal roll handling and stacking system based on AGV disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0021] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0022] Metal coils are stacked in the production workshop and then transported to the production equipment when they are used. At present, many production workshops have begun to use AGV (Automated Guided Vehicle) to automatically transport metal coils, which has significantly improved the efficiency of metal coil transportation. However, the existing AGV-based metal coil transportation and stacking methods mainly focus on the planning of AGV transportation routes and precise stacking at stacking points, but lack consideration of the safety of AGV during the transportation process, which makes transportation accidents prone to occur. This technical problem has not yet been effectively solved.

[0023] In view of the above technical problems existing in the prior art, Figure 1 As shown, an embodiment of the present invention discloses a metal coil handling and stacking method based on an AGV (Automated Guided Vehicle), the method comprising the following steps: acquiring a high-definition image of a target metal coil, extracting safety feature data based on the high-definition image, processing the safety feature data using a safety risk assessment model, and obtaining a handling risk value; when the handling risk value is higher than a risk threshold, determining a placement posture of the target metal coil, and obtaining a target AGV based on the placement posture and the handling risk value; placing the target metal coil on a bearing component of the target AGV according to the placement posture, and controlling the target AGV to automatically transport the target metal coil to a stacking point in a stacking area.

[0024] In the above scheme of the present invention, a high-definition camera is arranged in the production workshop. When the metal coil needs to be transported, the high-definition camera is controlled to first capture a high-definition image of the target metal coil to be transported, and the safety feature data of the target metal coil is extracted from the high-definition image. Then, the extracted safety feature data is processed using a pre-built safety risk assessment model to obtain a transportation risk value. The transportation risk value characterizes the size of the potential risk of the target metal coil due to its own factors during the transportation process. When the transportation risk value is higher than the risk threshold, a special transportation method is required, and when the transportation risk value is lower than the risk threshold, no special transportation method is required.

[0025] Then, for the target metal coils with a handling risk value higher than the risk threshold, a safe placement posture is determined, which can ensure that the target metal coils can minimize the risk of injury to people and objects even if a safety incident occurs. Then, the target AGV is screened based on the placement posture and handling risk value, that is, the most suitable target AGV is screened. It should be noted that there are many types of AGVs deployed in the production workshop, and these AGVs differ in many aspects such as rated load, length of the load-bearing clamping device, etc.

[0026] Finally, the target metal roll is placed on the bearing component of the target AGV according to the determined safest placement posture, and the target AGV is controlled to automatically transport the target metal roll to the stacking point in the stacking area. At this point, the automatic stacking of the target metal roll is completed.

[0027] It can be seen that compared with the prior art which only focuses on the planning of the AGV's transportation route and the precise stacking at the stacking points, the solution of the present invention focuses on the safety of the AGV during the transportation process, and determines the appropriate placement posture of the target metal roll on the AGV and the appropriate AGV based on the extracted risk factors of the target metal roll, thereby reducing the probability of safety risks of the AGV during transportation, and even if an accident occurs during transportation, the risk of injury to people and property can be minimized.

[0028] In some embodiments, the obtaining of a high-definition image of the target metal coil and extracting safety feature data based on the high-definition image include: capturing a panoramic image of the initial stacking area of ​​the metal coils through a high-definition camera, identifying the target metal coil from the panoramic image based on the current production task information, and capturing a high-definition image of the target metal coil; using image processing technology to identify and extract the safety feature data of the target metal coil in the high-definition image, the safety feature data including at least the number of binding straps, the uniformity of distribution of the binding straps, the tightness of the binding straps, and whether the metal coil is covered with protective materials; wherein the binding straps are steel straps or plastic straps.

[0029] In the embodiment of the present invention, after receiving new production task information, the production task information is parsed to determine the type of metal coil required for production, i.e., the target metal coil. There are multiple types of metal coils stacked in the initial stacking area. First, a panoramic image of the initial stacking area of ​​the metal coils is captured. Based on the stacking partitions of these metal coils and the special marks attached to the metal coils, the type of metal coil required for this production, i.e., the target metal coil, can be determined. The target metal coil can be the metal coil of the corresponding type located at the top. Then, the high-definition camera is controlled to capture the panoramic image of the target metal coil.

[0030] Next, the image processing technology is used to at least identify and extract the number of binding straps on the target metal roll in the image, the distribution uniformity of the binding straps, the tightness of the binding straps, and whether the metal roll is covered with protective materials. This information constitutes the safety feature data of the target metal roll. The binding strap refers to a plurality of steel straps or plastic straps used to bind and constrain the metal roll. Among them, the distribution uniformity of the binding straps refers to, for example, the variance of the spacing between two adjacent binding straps in each group. The larger the variance, the lower the distribution uniformity of the binding straps, and vice versa. The tightness of the binding straps refers to the degree of close contact between the binding straps and the metal roll. When the binding straps are completely close to the metal roll, the corresponding tightness of the binding straps is higher, and vice versa. In addition, the number of binding straps and whether the metal roll is covered with protective materials will also affect the safety of the target metal roll during transportation, mainly the probability of collapse during transportation. Obviously, the fewer the number of binding straps, the lower the distribution uniformity of the binding straps, the lower the tightness of the binding straps, and when the metal roll is not covered with protective materials, the higher the probability of collapse, and vice versa. Subsequently, the handling risk value of the target metal coil can be obtained based on the above safety feature data analysis.

[0031] It should be noted that after some metal rolls are rolled up, they will be covered with a layer of protective material and then bound and reinforced with multiple binding straps, so not all metal rolls are covered with protective material.

[0032] In some embodiments, the use of a security risk assessment model to process the security feature data to obtain a handling risk value includes: using a convolutional network to extract features of the number of the binding straps, the distribution uniformity of the binding straps, the tightness of the binding straps, and whether the metal roll is covered with protective materials, respectively, to obtain quantity features, distribution uniformity features, tightness features, and protective material features, and integrating the quantity features, the distribution uniformity features, the tightness features, and the protective material features into risk features; inputting the risk features into the security risk assessment model to obtain the handling risk value predicted and output by the security risk assessment model.

[0033] In the embodiment of the present invention, since the AGV will inevitably shake during the handling process, the shaking amplitude of some non-good sections may be very large, and the target metal roll is similar to a spring, and the accumulated stress drives the end of the metal roll to no longer fit the metal roll body. When the binding belt and protective materials that restrain this trend break or loosen, it will collapse, which will cause personal injury and property damage. Moreover, as mentioned above, the above-mentioned safety feature data will affect the self-stability of the target metal roll, that is, the probability of collapse.

[0034] In this regard, the present invention is designed to use a convolutional network to first extract features from the security feature data, such as the number of binding straps, the uniformity of their distribution, the tightness of their tightness, and whether the metal roll is covered with protective materials. The extracted features are then integrated to obtain risk features that can be used to analyze the probability of the target metal roll breaking. The pre-constructed safety risk assessment model performs an in-depth analysis of the features to obtain the handling risk value.

[0035] It should be noted that the above security risk assessment model is a model based on a deep learning algorithm, which mainly includes an input layer, a convolution layer, an activation function layer, a pooling layer, a fully connected layer, and an output layer. The specific functions of each structure are introduced as follows: Input layer: used to receive the above risk features.

[0036] Convolution layer: The input risk features are convolved through multiple convolution kernels (also called filters) to extract local features in the risk features. Each convolution kernel generates a feature map, which contains the feature information of the risk features at different scales and directions.

[0037] Activation function layer: Activation functions such as ReLU, Sigmoid, or Tanh can perform nonlinear transformations on the output of the convolutional layer, allowing the model to learn more complex feature representations.

[0038] Pooling layer: Downsamples the feature map output by the convolutional layer to reduce the dimension of the data and the amount of computation. Commonly used pooling methods include Max Pooling and Average Pooling. The pooling layer can retain the key information in the feature map while reducing redundancy and noise.

[0039] Fully connected layer: One or two layers of fully connected layers can integrate feature information and perform classification or regression tasks. Each neuron in the fully connected layer is connected to all neurons in the previous layer, and linear transformation and nonlinear activation are performed through weights and bias parameters.

[0040] Output layer: The output layer uses a regression layer. The regression layer maps the output of the fully connected layer to the range of risk values ​​through linear transformation and activation functions (such as sigmoid or tanh), that is, obtains the corresponding transportation risk value.

[0041] In some embodiments, the inputting the risk feature into the safety risk assessment model to obtain the handling risk value predicted and output by the safety risk assessment model includes: inputting the risk feature into the safety risk assessment model to obtain a first handling risk value predicted and output by the safety risk assessment model; identifying a target binding strap adjacent to the end of a target metal coil based on the high-definition image, and calculating the interval distance between the target binding strap and the end of the target metal coil; wherein the target binding strap refers to a binding strap adjacent to the end of the target metal coil and located on the outermost metal plate of the target metal coil; determining a risk adjustment coefficient based on the interval distance, and multiplying the risk adjustment coefficient by the first handling risk value to obtain a second handling risk value, wherein the second handling risk value is the final handling risk value.

[0042] In an embodiment of the present invention, the present invention first uses a safety risk assessment model to analyze the risk characteristics obtained above to obtain an initial first handling risk value. Then, based on the high-definition image, the target binding belt adjacent to the end of the target metal roll is identified. The target binding belt is the binding belt adjacent to the end of the target metal roll and located on the outermost metal plate of the target metal roll. For example, the target metal roll is rolled up 10 layers (the innermost is the 1st layer and the outermost is the 10th layer). The binding belt adjacent to the end of the target metal roll includes the binding belt located on the 10th layer and the binding belt located on the 9th layer, and the binding belt located on the 10th layer is the target binding belt. Next, the interval distance between the target binding belt and the end of the target metal roll is calculated. The interval distance will affect the binding restriction ability of the target binding belt to the end of the target metal roll. Generally speaking, the larger the interval distance, the worse the binding restriction ability of the target binding belt to the end of the target metal roll, that is, the easier it is to collapse. On the contrary, the stronger the interval distance, the less likely it is to collapse. On this basis, the present invention is configured to determine a risk adjustment coefficient according to the interval distance, and then use the risk adjustment coefficient to multiply the first transportation risk value to obtain a second transportation risk value, and the second transportation risk value is the final transportation risk value.

[0043] In some embodiments, determining the risk adjustment coefficient based on the spacing distance includes: obtaining the metal type and the number of winding layers of the target metal coil, and predicting the standard spacing distance based on the metal type and the number of winding layers; calculating the difference between the spacing distance and the standard spacing distance, and deriving the risk adjustment coefficient based on matching the difference with a preset first positive correlation.

[0044] In an embodiment of the present invention, after determining the target metal roll, the metal type (material, thickness and other parameters related to elastic force) and the number of winding layers of the target metal roll can be retrieved from the background system. After different types of metals are wound in different numbers of layers, the stress magnitudes at the ends of the metal rolls are different. Therefore, the present invention is set to predict the standard spacing distance based on the obtained metal type and winding number of layers. The standard spacing distance refers to the distance between the binding position of the target binding belt and the end of the target metal roll, that is, binding the target binding belt at this position can make the probability of the end of the target metal roll being broken and bounced up the lowest (the binding position is generally not the end of the target metal roll, because it is easy to slip, which increases the probability of the end of the target metal roll being broken and bounced up). If the target binding belt is tied away from the binding position (that is, the spacing distance is larger), the probability of the end of the target metal roll being broken and bounced up gradually increases as the spacing distance increases. The prediction of the standard spacing distance in this embodiment can be implemented based on a preset model, for example, it can also be constructed based on the above-mentioned deep learning algorithm, and the specific details will not be repeated.

[0045] Then, the difference between the interval distance and the standard interval distance is calculated, and the risk adjustment coefficient is obtained by matching the difference with the preset first positive correlation. The preset first positive correlation can be expressed in the form of a comparison table.

[0046] In some embodiments, when the handling risk value is higher than a risk threshold, the placement posture of the target metal coil is determined, and a target AGV is obtained by screening according to the placement posture and the handling risk value, including: when the handling risk value is higher than the risk threshold, determining the placement posture of the target metal coil so that the end of the target metal coil is located at the bottom; determining a length range of the load-bearing clamping device according to the handling risk value and a preset second positive correlation, and obtaining the target AGV by screening according to the length range.

[0047] In the embodiment of the present invention, when the handling risk value is higher than the risk threshold, it indicates that there is a probability that the end of the target metal roll will break apart during the handling process. At this time, it can be determined that the placement posture of the target metal roll is that the end of the target metal roll is located at the bottom. Since the end of the target metal roll is located between the two clamping devices of the load-bearing part, it will not bounce outward even if it breaks apart, and will not cause damage to the surrounding personnel and objects. At the same time, it is also set to determine the length interval of the load-bearing part clamping device according to the size of the handling risk value, and then screen the target AGV according to this length interval. Figure 2As shown in the figure, for example, if the length interval of the load-bearing clamping device is determined to be 20-30cm according to the size of the handling risk value, then the A-type AGV with a load-bearing clamping device length (i.e., the inclined length of the gray area in the figure) of 25cm is selected as the target AGV. Obviously, the larger the handling risk value, the more AGVs with larger load-bearing clamping device lengths are selected (i.e., the larger the length interval of the load-bearing clamping device).

[0048] like Figure 3 As shown, an embodiment of the present invention further discloses a metal coil handling and stacking system based on AGV (Automated Guided Vehicle), the system comprising a risk analysis module, a screening module, and a scheduling module; the risk analysis module is used to obtain a high-definition image of a target metal coil, extract safety feature data based on the high-definition image, and process the safety feature data using a safety risk assessment model to obtain a handling risk value; the screening module is used to determine the placement posture of the target metal coil when the handling risk value is higher than a risk threshold, and obtain a target AGV based on the placement posture and the handling risk value; the scheduling module is used to place the target metal coil on the bearing component of the target AGV according to the placement posture, and control the target AGV to automatically transport the target metal coil to the stacking point in the stacking area.

[0049] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0050] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0051] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A metal coil handling and stacking method based on AGV, characterized in that: The method comprises the following steps: obtaining a high-definition image of a target metal coil, extracting safety feature data according to the high-definition image, and processing the safety feature data using a safety risk assessment model to obtain a handling risk value; When the handling risk value is higher than the risk threshold, determining the placement posture of the target metal coil, and selecting and obtaining the target AGV according to the placement posture and the handling risk value; The target metal roll is placed on the bearing component of the target AGV according to the placement posture, and the target AGV is controlled to automatically transport the target metal roll to the stacking point in the stacking area.

2. The AGV-based metal coil handling and stacking method according to claim 1, characterized in that: A high-definition image of a target metal coil is obtained, and safety feature data is extracted based on the high-definition image, including: capturing a panoramic image of an initial stacking area of ​​the metal coils by a high-definition camera, identifying the target metal coil from the panoramic image based on the current production task information, and capturing a high-definition image of the target metal coil; using image processing technology to identify and extract the safety feature data of the target metal coil in the high-definition image, wherein the safety feature data includes at least the number of binding straps, the uniformity of distribution of the binding straps, the tightness of the binding straps, and whether the metal coil is covered with protective materials; wherein the binding straps are steel straps or plastic straps.

3. The method for transporting and stacking metal coils based on AGV according to claim 2, characterized in that: The safety feature data is processed using a safety risk assessment model to obtain a handling risk value, including: using a convolutional network to extract features of the number of the binding straps, the distribution uniformity of the binding straps, the tightness of the binding straps, and whether the metal roll is covered with protective materials, respectively, to obtain quantity features, distribution uniformity features, tightness features, and protective material features, and integrating the quantity features, the distribution uniformity features, the tightness features, and the protective material features into risk features; inputting the risk features into the safety risk assessment model to obtain the handling risk value predicted and output by the safety risk assessment model.

4. The method for transporting and stacking metal coils based on AGV according to claim 3, characterized in that: The risk feature is input into the safety risk assessment model to obtain the handling risk value predicted by the safety risk assessment model, including: inputting the risk feature into the safety risk assessment model to obtain the first handling risk value predicted by the safety risk assessment model; identifying the target binding belt adjacent to the end of the target metal coil based on the high-definition image, and calculating the interval distance between the target binding belt and the end of the target metal coil; wherein the target binding belt refers to the binding belt adjacent to the end of the target metal coil and located on the outermost metal plate of the target metal coil; determining a risk adjustment coefficient based on the interval distance, and multiplying the first handling risk value by the risk adjustment coefficient to obtain a second handling risk value, and the second handling risk value is the final handling risk value.

5. The method for transporting and stacking metal coils based on AGV according to claim 4, characterized in that: Determining a risk adjustment coefficient based on the spacing distance includes: obtaining the metal type and the number of winding layers of the target metal coil, and predicting a standard spacing distance based on the metal type and the number of winding layers; calculating the difference between the spacing distance and the standard spacing distance, and obtaining the risk adjustment coefficient based on matching the difference with a preset first positive correlation relationship.

6. The method for transporting and stacking metal coils based on AGV according to claim 5, characterized in that: When the handling risk value is higher than the risk threshold, the placement posture of the target metal coil is determined, and the target AGV is obtained by screening according to the placement posture and the handling risk value, including: when the handling risk value is higher than the risk threshold, the placement posture of the target metal coil is determined to be that the end of the target metal coil is located at the bottom; according to the handling risk value and a preset second positive correlation, a length range of the load-bearing clamping device is determined, and the target AGV is obtained by screening according to the length range.

7. A metal coil handling and stacking system based on AGV, the system comprising a risk analysis module, a screening module, and a scheduling module; characterized in that: The risk analysis module is used to obtain a high-definition image of the target metal coil, extract safety feature data based on the high-definition image, and process the safety feature data using a safety risk assessment model to obtain a handling risk value; The screening module is used to determine the placement posture of the target metal coil when the handling risk value is higher than the risk threshold, and to screen and obtain the target AGV according to the placement posture and the handling risk value; The scheduling module is used to place the target metal roll on the bearing component of the target AGV according to the placement posture, and control the target AGV to automatically transport the target metal roll to the stacking point in the stacking area.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images