Pipeline Monitoring System Based on Fully Automatic Feeding Unmanned Logistics Vehicle

Abstract

The present invention belongs to the technical field of intelligent factories. It provides an assembly line monitoring system based on a fully automatic feeding unmanned logistics vehicle, which includes distributed monitoring cameras, a scheduling system, and a fully automatic feeding unmanned logistics vehicle. Among them, the distributed monitoring cameras capture high-definition image data related to each material storage node of the assembly line. The scheduling system determines the remaining amount of materials at each material storage node based on the high-definition image data. When the remaining amount of materials is lower than the preset value, it determines the fully automatic feeding unmanned logistics vehicle used to replenish the material storage node and sends a replenishment instruction to the corresponding fully automatic feeding unmanned logistics vehicle. The fully automatic feeding unmanned logistics vehicle delivers the materials corresponding to the material delivery volume to the material storage node corresponding to the identity information. The solution of the present invention makes full use of the existing distributed monitoring cameras in the assembly line production workshop and can realize the material distribution of the assembly line based on the fully automatic feeding unmanned vehicle at low cost.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent factories, and more particularly, to a pipeline monitoring system based on a fully automatic feeding unmanned logistics vehicle. Background Art

[0002] In order to improve production efficiency, more and more factories have begun to use fully automatic feeding unmanned vehicles to provide automatic distribution of production materials for the production line.

[0003] However, most of the existing scheduling systems dispatch the corresponding fully automatic feeding unmanned vehicles for material distribution based on manually triggered signals. When production workers find that the materials on the production line are insufficient, they press the scheduling button to send a material distribution request to the scheduling system, and then the scheduling system dispatches the corresponding fully automatic feeding unmanned vehicle for material distribution. This method relies too much on manpower and is difficult to further improve production efficiency. Moreover, it is also difficult to implement in a highly automated production line with little or no human participation.

[0004] Some factories set up material detection devices based on weighing sensors on the production line. When the materials are detected to be insufficient, a material distribution request is sent to the scheduling system, and then the scheduling system dispatches the corresponding fully automatic feeding unmanned vehicle for material distribution. This method requires the transformation of the material storage mechanism of the production line, and the implementation cost is relatively high.

[0005] Obviously, how to automatically analyze the demand for materials on the production line and dispatch the fully automatic feeding unmanned vehicle for feeding accordingly is a technical problem that needs to be solved at present. Summary of the Invention

[0006] In view of this, the present invention provides a pipeline monitoring method, system, electronic device, computer storage medium and computer program product based on a fully automatic feeding unmanned logistics vehicle to solve the above technical problems.

[0007] The present invention discloses a pipeline monitoring system based on a fully automatic feeding unmanned logistics vehicle, which includes distributed monitoring cameras, a scheduling system and a fully automatic feeding unmanned logistics vehicle; wherein,

[0008] The distributed monitoring cameras are used to capture high-definition image data related to each material storage node of the production line and send the high-definition image data to the scheduling system;

[0009] The scheduling system is used to determine the remaining material quantity of each material storage node based on the high-definition image data. When the remaining material quantity is lower than a preset value, it determines a fully automatic feeding unmanned logistics vehicle for feeding the material storage node and sends a feeding instruction to the corresponding fully automatic feeding unmanned logistics vehicle. The feeding instruction includes the identity information of the material storage node and the material delivery quantity.

[0010] The fully automatic feeding unmanned logistics vehicle is used to respond to the feeding instruction and deliver the material corresponding to the material delivery quantity to the material storage node corresponding to the identity information.

[0011] Preferably, the distributed monitoring camera is used to capture high-definition image data related to each material storage node on the production line, including:

[0012] The distributed monitoring camera captures the first high-definition image data of the production line, identifies the conveying equipment from the first high-definition image data, and extracts the moving direction of the product located on the conveying equipment. Each material storage node is determined by backtracking according to the corresponding moving direction of each conveying equipment.

[0013] The distributed monitoring camera then captures the second high-definition image data of each material storage node and the third high-definition image data of other equipment downstream of the material storage node, and uses the second high-definition image data and the third high-definition image data as the high-definition image data related to the material storage node.

[0014] In the embodiment of the present invention, the distributed monitoring camera of the present invention does not need to manually specify each material storage node on the production line, but can determine which devices are material storage nodes based on image recognition.

[0015] Preferably, the scheduling system is used to determine the remaining material quantity of each material storage node based on the high-definition image data, including:

[0016] The scheduling system performs a first processing on the second high-definition image data to obtain the vibration amplitude data of the material storage node, and predicts the first remaining material quantity in the material storage node according to the vibration amplitude data.

[0017] The scheduling system performs a second processing on the third high-definition image data to obtain the transfer interval of the product on the conveying equipment, and calculates the change trend of the transfer interval according to each transfer interval.

[0018] If the variation trend of the transfer interval indicates that the transfer interval is gradually increasing, set a first correction coefficient; otherwise, set a second correction coefficient. Among them, the first correction coefficient is less than 1, and the second correction coefficient is equal to 1;

[0019] Use the first correction coefficient or the second correction coefficient to correct the remaining amount of the first material to the remaining amount of the second material.

[0020] Preferably, the fully automatic replenishment unmanned logistics vehicle for replenishing the material storage node is determined and a replenishment instruction is sent to the corresponding fully automatic replenishment unmanned logistics vehicle, including:

[0021] Determine the material types of the material storage nodes by accessing the pipeline database, and determine the adapted fully automatic replenishment unmanned logistics vehicle according to the material types;

[0022] Generate the replenishment instruction according to the identity information of the material storage node and the material distribution volume, and send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle.

[0023] Preferably, the sending the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle includes:

[0024] Judge whether the current time period belongs to the target time period, and the target time period is the time period statistically obtained according to the historical operation stop data of the pipeline;

[0025] If the current time period does not belong to the target time period, send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle;

[0026] If the current time period belongs to the target time period, wait for a set duration, control the distributed monitoring camera to take the fourth high-definition image data of other devices downstream of the material storage node, and track the motion state of the products on each transfer device according to the fourth high-definition image data. If there is no static trend in the motion state within the set duration, send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, otherwise cancel or suspend the replenishment instruction.

[0027] Preferably, the set duration is determined in the following manner:

[0028] Calculate the distance between the fully automatic replenishment unmanned logistics vehicle and the corresponding material storage node, and predict the delivery duration according to the distance and the historical running speed of the fully automatic replenishment unmanned logistics vehicle;

[0029] The third correction coefficient is determined according to the number of the material storage nodes on the assembly line, and the set duration is obtained by multiplying the third correction coefficient by the distribution duration; wherein, the third correction coefficient is greater than 1.

[0030] The present invention also discloses a monitoring method for an assembly line based on a fully automatic material replenishment unmanned logistics vehicle. The method is based on the system described in any one of the preceding items and includes the following method steps:

[0031] The distributed monitoring cameras capture and obtain high-definition image data related to each material storage node on the assembly line, and send the high-definition image data to the scheduling system;

[0032] The scheduling system determines the remaining amount of materials at each material storage node based on the high-definition image data. When the remaining amount of materials is lower than a preset value, a fully automatic material replenishment unmanned logistics vehicle for replenishing the material storage node is determined, and a replenishment instruction is sent to the corresponding fully automatic material replenishment unmanned logistics vehicle; wherein, the replenishment instruction includes the identity information of the material storage node and the material distribution amount.

[0033] The fully automatic material replenishment unmanned logistics vehicle responds to the replenishment instruction and distributes the materials corresponding to the material distribution amount to the material storage node corresponding to the identity information.

[0034] The present invention also discloses an electronic device, which is characterized in that it is applied to the system described in any one of the preceding items and includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0035] The present invention also discloses a computer storage medium, which is characterized in that it is applied to the system described in any one of the preceding items, and the computer storage medium stores a computer program.

[0036] The present invention also discloses a computer program product, which is characterized in that it is applied to the system described in any one of the preceding items and includes a computer program stored on a non-transitory computer-readable medium.

[0037] The beneficial effects are as follows:

[0038] On the one hand, the solution of the present invention does not require manual generation of distribution requests, nor does it require weighing sensors to be set in the material storage nodes. Instead, it makes full use of the existing distributed monitoring cameras in the assembly line production workshop, and can realize the material distribution of the assembly line based on the fully automatic material replenishment unmanned vehicle at low cost. On the other hand, on the premise of low implementation cost, the solution of the present invention also realizes the automatic analysis of material distribution requirements, and supplemented by the fully automatic distribution of materials, can significantly improve the production efficiency of the assembly line. Description of the Drawings

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0040] Figure 1 is a schematic structural diagram of a pipeline monitoring system based on a fully automatic feeding unmanned logistics vehicle disclosed in an embodiment of the present invention;

[0041] Figure 2 is a schematic flow diagram of a pipeline monitoring method based on a fully automatic feeding unmanned logistics vehicle disclosed in an embodiment of the present invention;

[0042] Figure 3 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. Specific Embodiments

[0043] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present application.

[0044] In addition, the technical features involved in different implementation manners of the present application described below can be combined with each other as long as they do not conflict with each other.

[0045] Existing scheduling systems mostly dispatch corresponding fully automatic feeding unmanned vehicles to deliver materials based on manually triggered signals. When production workers find that the materials on the pipeline are insufficient, they press the scheduling button to send a material delivery request to the scheduling system, and then the scheduling system dispatches the corresponding fully automatic feeding unmanned vehicle to deliver materials. This method overly relies on manpower and is difficult to further improve production efficiency. Moreover, it is also difficult to implement in a highly automated pipeline with little or no human participation.

[0046] Some factories set up material detection devices such as weighing sensors on the pipeline. When it detects that the materials are insufficient, it sends a material delivery request to the scheduling system, and then the scheduling system dispatches the corresponding fully automatic feeding unmanned vehicle to deliver materials. This method requires the transformation of the material storage mechanism on the pipeline, and the implementation cost is relatively high.

[0047] It can be seen that both of the above two existing methods have many defects and it is difficult to achieve the pipeline material distribution based on the fully automatic feeding unmanned vehicle at low cost.

[0048] In view of the above technical problems, as Figure 1 shown, an embodiment of the present invention discloses a pipeline monitoring system based on a fully automatic feeding unmanned logistics vehicle. The system includes a distributed monitoring camera, a scheduling system and a fully automatic feeding unmanned logistics vehicle; wherein,

[0049] The distributed monitoring camera is configured to capture high-definition image data related to each material storage node of the pipeline and send the high-definition image data to the scheduling system;

[0050] The scheduling system is configured to determine the remaining amount of materials at each material storage node based on the high-definition image data. When the remaining amount of materials is lower than a preset value, determine a fully automatic feeding unmanned logistics vehicle for replenishing the material storage node, and send a replenishment instruction to the corresponding fully automatic feeding unmanned logistics vehicle; wherein, the replenishment instruction includes the identity information of the material storage node and the material distribution quantity;

[0051] The fully automatic feeding unmanned logistics vehicle is configured to respond to the replenishment instruction and deliver materials corresponding to the material distribution quantity to the material storage node corresponding to the identity information.

[0052] In the above solution of the present invention, the distributed monitoring cameras already arranged in the pipeline production workshop are used to capture the relevant high-definition image data of each material storage node of the corresponding pipeline. The scheduling system analyzes and processes the relevant high-definition image data to obtain the remaining amount of materials at each material storage node. When the remaining amount of materials is lower than the preset value, it is determined that the material storage node needs to be replenished with materials. At this time, the fully automatic feeding unmanned logistics vehicle is scheduled to carry an appropriate amount of materials to the material storage node, thereby realizing the fully automatic distribution of materials.

[0053] Therefore, on the one hand, the solution of the present invention does not require manual generation of distribution requests, nor does it require weighing sensors to be set in the material storage nodes. Instead, it makes full use of the existing distributed monitoring cameras in the pipeline production workshop, and can realize the pipeline material distribution based on the fully automatic feeding unmanned vehicle at low cost; on the other hand, under the premise of low implementation cost, the solution of the present invention also realizes the automatic analysis of material distribution requirements, and supplemented by the fully automatic distribution of materials, can significantly improve the production efficiency of the pipeline.

[0054] It should be noted that the pipeline production workshop in the present invention is, for example, a motorcycle assembly production line, and the corresponding materials include but are not limited to screws, nuts, powder coatings, lubricating powders, etc.

[0055] Preferably, the distributed monitoring camera is configured to capture high-definition image data related to each material storage node on the production line, including:

[0056] The distributed monitoring camera captures the first high-definition image data of the production line, identifies the conveying equipment from the first high-definition image data, and obtains the moving direction of the products located on the conveying equipment. Based on the moving directions corresponding to each conveying equipment, each material storage node is determined by reverse inference.

[0057] The distributed monitoring camera then captures the second high-definition image data of each material storage node and the third high-definition image data of other equipment downstream of the material storage node, and uses the second high-definition image data and the third high-definition image data as the high-definition image data related to the material storage node.

[0058] In the embodiment of the present invention, the distributed monitoring camera of the present invention does not need to manually specify each material storage node on the production line, but can automatically determine which equipment is the material storage node based on image recognition.

[0059] Specifically, the distributed monitoring camera first captures the first high-definition image data of the production line, identifies the conveying equipment from the first high-definition image data. The conveying equipment can be, for example, conveying rollers, conveyor belts, etc., and obtains the moving direction of the products located on these conveying equipment. Based on the moving directions of the products corresponding to each conveying equipment on this production line, each material storage node can be inferred in the reverse direction, that is, the "starting point" of the overall moving direction is determined as the material storage node. Then, the distributed monitoring camera captures the second high-definition image data of each material storage node and the third high-definition image data of other equipment downstream of the material storage node. The second high-definition image data and the third high-definition image data are the high-definition image data related to the material storage node.

[0060] Preferably, the scheduling system is configured to determine the remaining material quantity of each material storage node based on the high-definition image data, including:

[0061] The scheduling system performs a first processing on the second high-definition image data to obtain the vibration amplitude data of the material storage node, and predicts the first remaining material quantity in the material storage node according to the vibration amplitude data.

[0062] The scheduling system performs a second processing on the third high-definition image data to obtain the conveying interval of the products on the conveying equipment, and calculates the change trend of the conveying interval according to each conveying interval.

[0063] If the variation trend of the transfer interval indicates that the transfer interval is gradually increasing, set the first correction coefficient; otherwise, set the second correction coefficient. Among them, the first correction coefficient is less than 1, and the second correction coefficient is equal to 1;

[0064] Use the first correction coefficient or the second correction coefficient to correct the remaining amount of the first material to the remaining amount of the second material.

[0065] In the embodiments of the present invention, the material storage node is generally a barrel or a box directly connected to the production equipment on the production line. The material can be powdery materials (such as powder coatings, lubricating powders), granular materials (such as screws, nuts), etc. The lower opening of the barrel or the box is communicated with the production equipment, and the material falls into the production equipment through the lower opening. Stirring, scraping and other equipment can also be arranged in the barrel or the box to facilitate the smooth falling of the powdery materials and granular materials therein into the production equipment.

[0066] Therefore, when the stirring, scraping and other equipment are working, the barrel or the box will naturally vibrate to a certain extent, and this vibration is related to the remaining material amount in the barrel or the box. Generally speaking, when the remaining material amount in the barrel or the box is more, the stirring, scraping and other equipment need to overcome a greater mass, and the vibration energy of the stirring, scraping and other equipment will be dispersed and absorbed by more materials, and the vibration amplitude at this time will be reduced; on the contrary, when the remaining material amount in the barrel or the box is more, the vibration energy of the stirring, scraping and other equipment will be more transmitted to the barrel or the box, causing it to vibrate with a greater amplitude.

[0067] Based on the above actual situation, the present invention sets a scheduling system to obtain the vibration amplitude data of the material storage node from the second high-definition image data of the material storage node. Based on the above principle, the remaining amount of the first material in the material storage node is predicted according to the vibration amplitude data. Here, a comparison table can be preset for barrels or boxes of specific sizes and weights. The comparison table will contain multiple sets of correlations between the vibration amplitude and the remaining amount of the first material. By comparing this comparison table, the remaining amount of the first material corresponding to the measured vibration amplitude data can be obtained. Of course, a prediction model can also be built based on CNN, Transformer, etc. The prediction model comprehensively analyzes the vibration amplitude data of the material storage node and the self-attribute data (size, weight, etc.) of the material storage node to predict the above-mentioned remaining amount of the first material, which will not be elaborated here.

[0068] Meanwhile, the vibration amplitude of the barrel or box body is affected not only by the remaining amount of materials inside, but also by the transmission stability of equipment such as agitators and scrapers. For example, when equipment such as agitators and scrapers are severely aged, their own vibration amplitudes are higher, which will in turn cause the vibration amplitude of the barrel or box body to increase, resulting in the inaccuracy of the previously obtained first remaining amount of materials. To address this technical problem, the present invention sets up a scheduling system to analyze the operating status of other equipment downstream of the material storage node, so as to obtain a corresponding correction coefficient to assist in obtaining a more accurate remaining amount of materials. Specifically, the scheduling system identifies the spacing between each product on the conveying equipment, i.e., the above-mentioned conveying interval, from the third high-definition image data, and the change trend of the conveying interval can be calculated based on these continuous conveying intervals. When the materials in the material storage node are sufficient, the material storage node can continuously provide stable materials for the production equipment. At this time, the time taken for the production equipment to produce products will be very stable, and thus the conveying interval on the conveying equipment will be very stable, and the change trend of the conveying interval will not indicate that the conveying interval is gradually increasing. At this time, the correction coefficient is set to 1, that is, the previously mentioned first remaining amount of materials is not adjusted. When the materials in the material storage node start to be insufficient, the materials falling from the material storage node into the production equipment will no longer be uniform, that is, it cannot continuously provide stable materials for the production equipment. At this time, the production equipment needs to wait until the material supply is sufficient before producing products, and the time taken to produce products will gradually increase. As a result, the conveying interval on the conveying equipment will be unstable, and the change trend of the conveying interval will indicate that the conveying interval is gradually increasing. At this time, the correction coefficient is set to a value less than 1, that is, this correction coefficient is used to appropriately lower the previously mentioned first remaining amount of materials, so that the obtained second remaining amount of materials is more in line with the actual situation.

[0069] It should be noted that the first correction coefficient less than 1 in the present invention may not be a fixed value, but is negatively correlated with the rate at which the conveying interval indicated by the change trend of the conveying interval is gradually increasing. For example, mapping each conveying interval to a coordinate system, fitting to obtain a conveying interval change curve, and using the slope of the rear section (i.e., the curve section with the latest time) of the conveying interval change curve as the change trend of the conveying interval, and the above-mentioned first correction coefficient less than 1 is negatively correlated with this slope.

[0070] Preferably, determining the fully automatic replenishment unmanned logistics vehicle for replenishing the material storage node and sending a replenishment instruction to the corresponding fully automatic replenishment unmanned logistics vehicle includes:

[0071] Determining the material types of each of the material storage nodes by accessing the pipeline database, and determining the adapted fully automatic replenishment unmanned logistics vehicle according to the material types;

[0072] Generate the replenishment instruction based on the identity information of the material storage node and the material delivery volume, and send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle.

[0073] In the embodiment of the present invention, there may be multiple material storage nodes on the production line. Different types of materials are stored in different material storage nodes, and different types of materials require corresponding types of fully automatic replenishment unmanned logistics vehicles for distribution. For example, powder materials require type A fully automatic replenishment unmanned logistics vehicles for distribution, and granular materials require type B fully automatic replenishment unmanned logistics vehicles for distribution. To this end, access the production line database to determine the material types of each material storage node in the current production task, and then screen out the currently idle and adapted fully automatic replenishment unmanned logistics vehicles according to the determined material types. Then, package the identity information and material delivery volume of the material storage node that needs to perform material distribution into a replenishment instruction, and send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle. After receiving the replenishment instruction, the fully automatic replenishment unmanned logistics vehicle goes to the warehouse to automatically obtain the corresponding type of material that meets the material delivery volume and distributes it to the corresponding material storage node, thus completing the fully automatic distribution of materials.

[0074] Among them, the material delivery volume can be a fixed value and can be preset according to the capacity and material type of the material storage node, which will not be elaborated in the present invention.

[0075] Preferably, when sending the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, the method further includes:

[0076] Judge whether the current time period belongs to the target time period, and the target time period is the time period statistically obtained according to the historical operation stop data of the production line;

[0077] If the current time period does not belong to the target time period, send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle;

[0078] If the current time period belongs to the target time period, wait for a set duration, control the distributed monitoring camera to take the fourth high-definition image data of other devices downstream of the material storage node, and track the movement state of the products on each conveyor device according to the fourth high-definition image data; if there is no static trend in the movement state within the set duration, send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, otherwise cancel or suspend the replenishment instruction.

[0079] In the embodiment of the present invention, the factory assembly line does not run continuously, but there is an intermittent running phenomenon, which mainly depends on the number of production orders. In this regard, the above-mentioned target period obtained based on the statistical data of the historical running stops of the assembly line belongs to the period when the assembly line is likely to stop. If the current period belongs to the above-mentioned target period, it is not advisable to directly send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, because if a stop occurs, the materials replenished to the material storage node will be affected by moisture, deterioration, etc. due to long-term exposure. At this time, control the distributed monitoring camera to capture the fourth high-definition image data of other devices downstream of the material storage node, and track the movement state of the products on each conveying device according to the fourth high-definition image data; if there is no stationary trend in the movement state within the set duration, it indicates that the assembly line does not have a stop behavior at this time, and send the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, that is, perform the material distribution normally; otherwise, it is determined that the assembly line has a stop behavior at this time, cancel or suspend the replenishment instruction, and temporarily do not perform the material distribution. If the current period does not belong to the above-mentioned target period, there is no need to wait, but the replenishment instruction can be directly sent to the adapted fully automatic replenishment unmanned logistics vehicle.

[0080] Preferably, the set duration is determined in the following manner:

[0081] Calculate the distance between the fully automatic replenishment unmanned logistics vehicle and the corresponding material storage node, and predict the delivery duration according to the distance and the historical running speed of the fully automatic replenishment unmanned logistics vehicle;

[0082] Determine the third correction coefficient according to the number of material storage nodes on the assembly line, and multiply the delivery duration by the third correction coefficient to obtain the set duration; wherein, the third correction coefficient is greater than 1.

[0083] In an embodiment of the present invention, the set duration can be determined based on the delivery duration of the fully automatic feeding unmanned logistics vehicle to the material storage node to be delivered associated therewith, and the delivery duration is obtained by first calculating the distance between the fully automatic feeding unmanned logistics vehicle and the material storage node, and then dividing the distance by the historical running speed of the fully automatic feeding unmanned logistics vehicle. At the same time, the delivery duration of the fully automatic feeding unmanned logistics vehicle is also determined by the number of other fully automatic feeding unmanned logistics vehicles on the delivery route, and this number is obviously positively correlated with the number of material storage nodes on the production line. That is, when the number of material storage nodes on the production line is larger, the probability that there are more other logistics vehicles obstructing the operation of the logistics vehicle on the delivery route of the fully automatic feeding unmanned logistics vehicle is greater. In this regard, the present invention sets a third correction coefficient determined according to the number of material storage nodes on the production line, and then multiplies the previously obtained delivery duration by the third correction coefficient to obtain the final set duration. Among them, the third correction coefficient is positively correlated with the number of the material storage nodes on the production line, but the present invention does not limit the specific positive correlation representation formula.

[0084] As Figure 2 shown, an embodiment of the present invention also discloses a monitoring method for a production line based on a fully automatic feeding unmanned logistics vehicle. The method is based on the system described in any one of the previous items and includes the following method steps:

[0085] The distributed monitoring cameras capture and obtain high-definition image data related to each material storage node on the production line, and send the high-definition image data to the scheduling system;

[0086] The scheduling system determines the remaining amount of materials at each material storage node based on the high-definition image data. When the remaining amount of materials is lower than a preset value, it determines a fully automatic feeding unmanned logistics vehicle for replenishing the material storage node, and sends a replenishment instruction to the corresponding fully automatic feeding unmanned logistics vehicle; wherein, the replenishment instruction includes the identity information of the material storage node and the material delivery quantity;

[0087] The fully automatic feeding unmanned logistics vehicle responds to the replenishment instruction and delivers the materials corresponding to the material delivery quantity to the material storage node corresponding to the identity information.

[0088] As Figure 3 shown, an embodiment of the present invention also discloses an electronic device applied to the system described in any one of the previous items, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

[0089] An embodiment of the present invention also discloses a computer storage medium applied to the system described in any one of the previous items, and the computer storage medium stores a computer program.

[0090] An embodiment of the present invention also discloses a computer program product, which is applied to the system described in any one of the preceding items and includes a computer program stored on a non-transitory computer-readable medium.

[0091] The present invention is described with reference to the 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks.

[0094] As mentioned above, the above is only a preferred embodiment of the present invention and is not used to limit the protection scope of the present invention.

Claims

1. A pipeline monitoring system based on a fully automatic feeding unmanned logistics vehicle, characterized in that: The system includes distributed monitoring cameras, a scheduling system, and fully automated replenishment unmanned logistics vehicles; among them, the distributed monitoring cameras are used to capture high-definition image data related to each material storage node on the production line and send the high-definition image data to the scheduling system; the scheduling system is used to determine the remaining amount of materials at each material storage node based on the high-definition image data. When the remaining amount of materials is lower than a preset value, it determines a fully automated replenishment unmanned logistics vehicle for replenishing the material storage node and sends a replenishment instruction to the corresponding fully automated replenishment unmanned logistics vehicle; among them, the replenishment instruction includes the identity information of the material storage node and the material delivery volume; the fully automated replenishment unmanned logistics vehicle is used to respond to the replenishment instruction and deliver the material corresponding to the material delivery volume to the material storage node corresponding to the identity information; the distributed monitoring cameras are used to capture high-definition image data related to each material storage node on the production line, including: the distributed monitoring cameras capture the first high-definition image data of the production line, identify the conveying equipment from the first high-definition image data, and obtain the movement direction of the products located on the conveying equipment, and inversely deduce and determine each material storage node according to the movement direction corresponding to each conveying equipment; the distributed monitoring cameras then capture the second high-definition image data of each material storage node and the third high-definition image data of other equipment downstream of the material storage node, and use the second high-definition image data and the third high-definition image data as the high-definition image data related to the material storage node the scheduling system is used to determine the remaining amount of materials at each material storage node based on the high-definition image data, including: the scheduling system performs a first process on the second high-definition image data to obtain the vibration amplitude data of the material storage node, and predicts the first remaining amount of materials in the material storage node according to the vibration amplitude data; the scheduling system performs a second process on the third high-definition image data to obtain the conveying interval of the products on the conveying equipment, and calculates the change trend of the conveying interval according to each conveying interval; if the change trend of the conveying interval indicates that the conveying interval is gradually increasing, a first correction coefficient is set, otherwise a second correction coefficient is set; among them, the first correction coefficient is less than 1, and the second correction coefficient is equal to 1; the first remaining amount of materials is corrected to the second remaining amount of materials using the first correction coefficient or the second correction coefficient.

2. The pipeline monitoring system based on the fully automatic feeding unmanned logistics vehicle according to claim 1, wherein: Determining a fully automated replenishment unmanned logistics vehicle for replenishing the material storage node and sending a replenishment instruction to the corresponding fully automated replenishment unmanned logistics vehicle includes: determining the material type of each material storage node by accessing the production line database, and determining a suitable fully automated replenishment unmanned logistics vehicle according to the material type; generating the replenishment instruction according to the identity information of the material storage node and the material delivery volume, and sending the replenishment instruction to the suitable fully automated replenishment unmanned logistics vehicle.

3. The pipeline monitoring system based on the fully automatic feeding unmanned logistics vehicle according to claim 2, characterized in that: Sending the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle includes: Determining whether the current time period belongs to the target time period, where the target time period is a time period statistically obtained based on the historical operation stop data of the production line; If the current time period does not belong to the target time period, sending the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle; If the current time period belongs to the target time period, waiting for a set duration, controlling the distributed monitoring camera to capture the fourth high-definition image data of other devices downstream of the material storage node, and tracking the motion state of the products on each conveyor device according to the fourth high-definition image data; if there is no stationary trend in the motion state within the set duration, sending the replenishment instruction to the adapted fully automatic replenishment unmanned logistics vehicle, otherwise canceling or suspending the replenishment instruction.

4. The pipeline monitoring system based on the fully automatic feeding unmanned logistics vehicle according to claim 3, wherein: The set duration is determined in the following manner: Calculating the distance between the fully automatic replenishment unmanned logistics vehicle and the corresponding material storage node, and predicting the delivery duration based on the distance and the historical running speed of the fully automatic replenishment unmanned logistics vehicle; Determining a third correction coefficient according to the number of material storage nodes on the production line, and multiplying the delivery duration by the third correction coefficient to obtain the set duration; where the third correction coefficient is greater than 1.

5. A pipeline monitoring method based on a fully automatic feeding unmanned logistics vehicle, the method being based on the system according to any one of claims 1-4, characterized in that: It includes the following method steps: The distributed monitoring camera captures and obtains high-definition image data related to each material storage node of the production line, and sends the high-definition image data to the scheduling system; The scheduling system determines the remaining material quantity of each material storage node based on the high-definition image data. When the remaining material quantity is lower than the preset value, it determines the fully automatic replenishment unmanned logistics vehicle for replenishing the material storage node and sends a replenishment instruction to the corresponding fully automatic replenishment unmanned logistics vehicle; where the replenishment instruction includes the identity information of the material storage node and the material delivery quantity; The fully automatic replenishment unmanned logistics vehicle responds to the replenishment instruction and delivers the material corresponding to the material delivery quantity to the material storage node corresponding to the identity information.

6. An electronic device, characterized in that: Applied to the system according to any one of claims 1-4, it includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor.

7. A computer storage medium, characterized in that: Applied to the system according to any one of claims 1-4, the computer storage medium stores a computer program.

8. A computer program product, characterized in that: Applied to the system according to any one of claims 1-4, it includes a computer program stored on a non-transitory computer-readable medium.

Images