Intelligent cargo inspection method, system and device for aviation departure and storage medium

Abstract

The invention discloses an intelligent cargo inspection method, system and device for aviation departure, and a storage medium. The method comprises the following steps: receiving cargo information acquired from a preorder link of an aviation departure service, flight information corresponding to cargos and container information acquired from a departure link; according to the cargo information and the container information corresponding to each flight, obtaining an optimal cargo stacking scheme corresponding to each flight by using a hybrid heuristic algorithm; the optimal stacking scheme is loaded to stacking and film winding equipment, a mechanical arm of the stacking and film winding equipment is guided to accurately stack goods, and the film winding procedure is automatically completed; a grating and profiling door dual verification mechanism is adopted to detect the container which completes the film winding process and is loaded with goods, net covering processing is conducted on the container which completes the film winding process and is loaded with the goods after detection is correct, and meanwhile data of a departure service background database are updated. The automatic level of aviation departure cargo detection can be improved, the requirement for manual intervention is reduced, and the working efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of cargo handling in air departure business, and specifically to an intelligent cargo inspection method, system, device and storage medium for air departure. Background Art

[0002] Traditional air logistics operations are highly dependent on manual intervention. Although they can meet basic needs, problems such as low efficiency and prone to errors and omissions are gradually emerging. With the popularization of emerging technologies such as the Internet of Things and artificial intelligence, air logistics has gradually entered the automation stage, which has not only greatly improved the speed and accuracy of cargo handling, but also injected new vitality and development potential into the industry. In this context, smart cargo inspection for air departures often covers multiple core links, including cargo transportation, cargo assembly and stacking, cargo film wrapping, and cargo netting and outbound delivery. The coordinated optimization of each link is crucial to improving overall efficiency.

[0003] At present, in actual operation, in order to optimize the whole process of air cargo inspection, the industry has widely adopted a series of basic means. For example, barcode scanners are used to check information during cargo transportation, or basic sensors are used to detect the status of the whole process of cargo departure. Some scenarios also try to combine electronic billboards to display key progress information to assist on-site staff in arranging the work sequence reasonably.

[0004] However, the existing automation solutions mainly focus on the optimization of a single link detection, lack of optimization and improvement of multiple links in the whole chain of cargo inspection, especially the inspection preparation link, and lack of intelligent decision-making support, and the overall automation level is low. Therefore, how to comprehensively improve the automation level of cargo inspection and reduce excessive reliance on manual labor has become an important direction for promoting the advancement of intelligent cargo inspection technology for air departures. Summary of the invention

[0005] In order to improve the level of automation of outbound air cargo inspection, reduce the need for manual intervention, and improve work efficiency, the present application provides an intelligent outbound air cargo inspection method, system, device, and storage medium.

[0006] In a first aspect, the present application provides a smart cargo inspection method for air departure, comprising: Receive cargo information and cargo corresponding flight information collected from the previous link of the air departure business; the previous link includes cargo collection, security inspection, classification and warehousing; receive container information collected from the departure link of the air departure business; According to the cargo information and container information corresponding to each flight, a hybrid heuristic algorithm is used to obtain the optimal stacking scheme for the cargo corresponding to each flight; the hybrid heuristic algorithm includes: using a greedy packing algorithm to generate an initial stacking scheme, using a genetic algorithm to perform global optimization on the generated initial stacking scheme, and using a simulated annealing algorithm to perform local optimization on the generated initial stacking scheme; Load the optimal stacking solution to the palletizing and wrapping equipment to guide the robotic arm of the palletizing and wrapping equipment to stack the goods and automatically complete the wrapping process; A dual verification mechanism of grating and contour door is used to check the shape and integrity of the container that has completed the wrapping process and is loaded with goods. After the inspection is correct, the container that has completed the wrapping process and is loaded with goods is covered with a net, and the data of the goods and containers to be loaded in the outbound business background database are updated at the same time.

[0007] By adopting the above scheme, cargo information in the pre-departure link and container information in the departure link are collected, and the hybrid heuristic algorithm is used to generate the optimal stacking plan to guide the stacking and wrapping equipment robot arm to accurately perform the stacking task and automatically complete the stacking and wrapping, which provides a basis for the subsequent rapid detection of containers using the grating and contour door dual verification mechanism and directly covers the container after the inspection meets the requirements, thereby achieving high automation of multiple links of cargo departure inspection, greatly shortening the cargo turnover time and reducing labor costs.

[0008] Preferably, it also includes: Receive flight change information, and adaptively adjust the cargo priority of the changed flights based on the flight change information, so that the cargo corresponding to the flight with a closer departure time has a higher priority; Adjust the main and secondary objectives of cargo stacking according to the cargo priority corresponding to each flight, so that the main objective of cargo stacking with a priority higher than the preset priority is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score, and the secondary objective is to maximize the space utilization rate of the container; the main objective of cargo stacking with a priority lower than the preset priority is to maximize the space utilization rate of the container and maximize the cargo stacking stability score, and the secondary objective is to minimize the total stacking time of cargo stacking; the main objective of cargo stacking with a priority equal to the preset priority is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the space utilization rate of the container, and there is no secondary objective; According to the main and secondary objectives of the adjusted cargo stacking, the fitness function in the genetic algorithm is designed accordingly, so that the first fitness function whose main objective is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score corresponding to the design stacking time parameter weight and the cargo stacking stability score parameter weight is greater than the space utilization parameter weight; the second fitness function whose main objective is to maximize the container space utilization and maximize the cargo stacking stability score corresponding to the design space utilization parameter weight and the cargo stacking stability parameter weight is greater than the stacking time parameter weight; the third fitness function whose main objective is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization corresponding to the design space utilization parameter weight, the cargo stacking stability score parameter weight, and the stacking time parameter weight is the same.

[0009] By adopting the above solution, we can respond to flight change information in real time, adjust the priority of flight cargo at the departure time, adapt the stacking optimization algorithm to adjust the cargo stacking strategy, and realize intelligent decision support for the cargo assembly and stacking link of outbound cargo, so as to facilitate the subsequent timely and rapid container inspection and improve the efficiency of cargo outbound inspection.

[0010] Preferably, the automatic film wrapping process further comprises: Calculate the center of gravity offset of the container under the optimal stacking solution; Input the container information and the calculated center of gravity offset into the wrapping process acquisition network to obtain the wrapping tension, material and wrapping method in the wrapping process so that the center of gravity offset of the container is reduced to a preset threshold after wrapping; the wrapping process acquisition network uses a convolutional neural network, which is trained and generated using historical container information, the center of gravity offset of the container, and the wrapping tension, material and wrapping method in the wrapping process; The container is wrapped according to the obtained wrapping tension, material and wrapping method in the wrapping process.

[0011] By adopting the above scheme, the specific parameters of the wrapping process are intelligently selected according to the center of gravity offset under the optimal stacking scheme, so as to ensure that the stacked goods are wrapped stably, facilitate the subsequent rapid completion of the cargo wrapping inspection, and improve the efficiency of outbound cargo inspection.

[0012] Preferably, it also includes: Integrate a wrapping tension sensor array and a machine vision device on the pallet wrapping equipment, and use the integrated wrapping tension sensor array and machine vision device to monitor the wrapping tension of the container at all angles and the image of the container wrapped with film in real time during the wrapping process; The analysis detects in real time the shape of the container wrapped by the film in the wrapping process, compares the shape of the container wrapped by the film with the shape of the target container wrapped by the film in the wrapping process, or compares the wrapping tension at each angle of the container with the target wrapping tension in the wrapping process. If the comparison result shows that the error is greater than the preset error value, the wrapping self-correction program is triggered and the wrapping is performed again.

[0013] By adopting the above solution, sensors and machine vision are used to detect the film wrapping process from multiple angles, and the film wrapping is corrected in time according to the detection results to ensure the accuracy of the film wrapping and improve the degree of automation of outbound cargo inspection.

[0014] Preferably, it also includes: Add multiple verification devices at key positions of the conveyor belts used to transport goods during the outbound process. The multiple verification devices include smart camera arrays and RFID readers. Multiple verification devices are used to detect cargo and perform image analysis to determine whether the current cargo information is consistent with the recorded information and whether the transportation route conforms to the preset cargo transportation route of the corresponding flight. Once it is determined that the cargo information is inconsistent with the recorded information and does not conform to any of the preset cargo transportation routes of the corresponding flight, an alarm is triggered and the current cargo is tracked in real time to be displayed on the display device.

[0015] By adopting the above solution, multiple verification methods such as smart camera arrays and RFID readers are used to ensure the accuracy and completeness of outbound cargo during the transmission stage, thereby improving the degree of automation in outbound cargo inspection.

[0016] Preferably, it also includes: Obtaining first feedback data of users on outbound cargo and second feedback data of airline staff on outbound cargo, wherein the first feedback data includes: cargo damage rate; and the second feedback data includes: usage cost of the container; Once the cargo damage rate of outbound cargo reaches the preset damage rate or the proportion of the container usage cost in the preset time period is greater than the preset cost, the optimized hybrid heuristic algorithm is selected.

[0017] By adopting the above solution, a feedback mechanism is used to optimize the stacking algorithm of outbound cargo, further ensuring that the outbound cargo is correctly stacked, facilitating subsequent rapid passing of stacking inspections.

[0018] Preferably, it also includes: Determine the loading position requirement of each cargo according to the cargo information, wherein the loading position requirement includes: the loading positions of the associated cargoes are adjacent and the loading positions of the cargoes with high extraction priority are close to the entrance position of the container; Whether the goods in the stacking scheme meet the loading position requirements is taken as a penalty parameter and incorporated into the fitness function of the genetic algorithm.

[0019] By adopting the above scheme, the specific loading location requirements of each cargo are determined according to the cargo information, and these requirements are converted into penalty item parameters in the genetic algorithm. While optimizing the rationality of the spatial layout of cargo stacking, the user experience is enhanced, user satisfaction is improved, the time consumption of the optimization algorithm is reduced, and the correct stacking of outbound cargo is ensured, which facilitates the subsequent rapid passing of the stacking detection.

[0020] In a second aspect, the present application provides a smart cargo inspection system for air departure, including: The outbound cargo data collection module is used to receive cargo information and cargo corresponding flight information collected from the previous link of the outbound aviation business; the previous link includes cargo collection, security inspection, classification and warehousing; and receive container information collected from the outbound link of the outbound aviation business; The outbound cargo stacking scheme acquisition module is used to obtain the optimal stacking scheme for the cargo corresponding to each flight by using a hybrid heuristic algorithm according to the cargo information and container information corresponding to each flight; the hybrid heuristic algorithm includes: using a greedy packing algorithm to generate an initial stacking scheme, using a genetic algorithm to perform global optimization on the generated initial stacking scheme, and using a simulated annealing algorithm to perform local optimization on the generated initial stacking scheme; The outbound cargo wrapping execution module is used to load the optimal stacking plan into the palletizing and wrapping equipment to guide the robotic arm of the palletizing and wrapping equipment to stack the cargo and automatically complete the wrapping process; The outbound cargo verification and data update module is used to use the dual verification mechanism of grating and contour door to perform shape and integrity detection on the container that has completed the wrapping process and is loaded with cargo. After the detection is correct, the container that has completed the wrapping process and is loaded with cargo is covered with a net, and the data of cargo and container to be loaded in the outbound business background database are updated at the same time.

[0021] By adopting the above solution, we receive goods and related information from multiple links, use a variety of algorithms to generate the optimal stacking plan, guide the robotic arm of the stacking and wrapping equipment to accurately stack the goods and complete the wrapping process, and use a double verification mechanism to ensure the quality of cargo loading and data consistency, directly or indirectly promote efficient and accurate cargo departure inspection, and realize a highly automated air departure smart cargo inspection system.

[0022] In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method as described above.

[0023] In a fourth aspect, the present application provides a computer device, comprising a memory, a processor, and a program stored and executable on the memory, wherein the program implements the steps of the above method when executed by the processor.

[0024] In summary, this application has the following beneficial effects: 1. By adopting a hybrid heuristic algorithm to generate the optimal stacking plan, the cargo stacking efficiency and the space utilization rate of the container are improved, which indirectly ensures that the cargo stacking link passes the inspection quickly; the dual verification mechanism of grating and contour door is introduced to ensure the accuracy of cargo stacking link inspection and improve the automation level of outbound cargo stacking link inspection; 2. Combined with the dynamic flight change information, adjust the cargo priority and then match the appropriate stacking optimization algorithm to respond to the emergency of outbound cargo, improve the stacking efficiency of outbound cargo, and indirectly ensure the rapid passing of cargo stacking inspection; 3. Introduce an adaptive cargo wrapping mechanism to complete adaptive and stable cargo wrapping so that cargo can quickly pass the cargo wrapping stage inspection; combine a variety of wrapping detection technical means to timely query the wrong wrapping of outbound cargo and self-correct it, so as to improve the accuracy and automation of the outbound cargo wrapping link inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of the intelligent cargo inspection method for air departure described in a specific embodiment; Figure 2 It is a full process diagram of the pre-order link of the departure business and the departure link of the departure business described in the smart cargo inspection method for departure by air described in the specific embodiment; Figure 3 It is a diagram of all links of the departure business described in the smart cargo inspection method for departure by air described in the specific embodiment; Figure 4 It is a schematic diagram of the structure of the intelligent cargo inspection system for air departure described in a specific embodiment. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] Smart cargo inspection for air departure covers the entire process of cargo departure, including cargo extraction from warehouse, cargo transportation, cargo stacking, cargo wrapping, cargo netting, and cargo departure (i.e. cargo departure). Considering that the existing departure cargo inspection technology has a low degree of automation and is difficult to support intelligent decision-making, the efficiency of smart cargo inspection for air departure is low and prone to errors, and the labor cost is high. In order to improve the automation level of smart cargo inspection for air departure, reduce the need for manual intervention, and improve work efficiency; Figure 1 As shown, the embodiment of the present application discloses a smart cargo inspection method for air departure, and the specific steps include: S1. Receive cargo information collected from the previous stage of air departure business, cargo corresponding flight information and container information collected from the departure stage.

[0028] Specifically, Figure 2 As shown, the preceding link refers to the preceding link of the air departure business, including: cargo collection and transportation, cargo security inspection, cargo classification and cargo warehousing, etc. The information of the subsequent cargo to be departed is collected and obtained through various information collection devices in the preceding link, including: the size, type, packaging type, fragility, handling priority and flight number to be loaded, etc., as well as the corresponding flight information of the subsequent cargo to be departed, including: flight number, flight operation, postponement or cancellation status, and the above collected information is stored in the departure business background database.

[0029] In order to complete the departure of goods, the goods to be departed need to be uniformly packaged and loaded into containers according to the corresponding flight numbers. Therefore, the information of used and unused containers in the cargo departure business is generally monitored in real time and stored in the departure business background database. Correspondingly, the container information collected from the departure link of the aviation departure business is received, including: the size, maximum load-bearing capacity, available quantity and current loading status of the container (such as: PMC, PAG board).

[0030] S2. According to the cargo information and container information corresponding to each flight, a hybrid heuristic algorithm is used to obtain the optimal stacking solution for the cargo corresponding to each flight.

[0031] like Figure 3 As shown, in order to improve the automation level of intelligent cargo inspection for air departure, it is not only necessary to optimize the cargo inspection itself in each link, but also to optimize the basis of cargo inspection in advance to facilitate the subsequent rapid passing of inspection. From this perspective, by optimizing the stacking scheme in the outbound cargo stacking link, it can not only improve the efficiency of cargo stacking and quickly enter the inspection stage, but also ensure the correctness of cargo stacking and quickly pass the stacking inspection, avoiding repeated stuck in the stacking inspection stage due to cargo stacking problems.

[0032] Specifically, according to the cargo information and container information corresponding to each flight, a hybrid heuristic algorithm is used to obtain the optimal stacking solution for the cargo corresponding to each flight; wherein the hybrid heuristic algorithm includes: First, the greedy packing algorithm is used to generate the initial stacking plan. The specific steps include: Arrange all cargo to be loaded on the same flight in descending order by volume; Determine the flight priority order according to the flight operation time, and select the container that best matches the cargo in the current remaining space for each cargo corresponding to the highest priority flight according to the priority order, wherein the matching rule is determined by comparing the size of the cargo and the remaining space of the container; Try to place the cargo in the selected ULD and check whether all physical and weight constraints are met. If so, update the state of the ULD; if not, try the next best matching ULD; Repeat the above steps of matching containers and placing cargo until all cargo is placed or the current container cannot hold more cargo, and obtain the initial stacking plan for all cargo to be loaded on the same flight.

[0033] Secondly, the generated initial stacking scheme is globally optimized using a genetic algorithm. The specific steps include: Encode the loading order and placement of all cargoes to be loaded on the same flight into chromosomes, such as using integer encoding, where each integer represents the code of a cargo, and the order of the chromosomes represents the loading order of the cargoes; Based on the initial stacking scheme, multiple initial solutions are randomly generated as the initial population, each of which represents a possible cargo loading method; Design a comprehensive fitness function to evaluate the quality of each solution; since the cargo stacking solution is a multi-objective optimization problem, the comprehensive fitness function balances the conflicts between cargo loading, and the cargo stacking objectives include: maximizing the space utilization of the container, maximizing the cargo stacking stability score, and minimizing the total stacking time of cargo stacking; and the target calculation is often based on some constraints, such as the stability of cargo stacking, which can be determined based on factors such as whether the compressive strength of each cargo in the corresponding stacking layer exceeds the preset compressive strength of the corresponding cargo, and the center of gravity position of the overall cargo. Then, the fitness function parameters are designed to include: space utilization, handling time, stability score, and weighted calculation to finally obtain a comprehensive fitness function; According to the fitness function, excellent individuals are selected for reproduction, and new solutions are generated through crossover operations (such as exchanging some genes of two chromosomes) and mutation operations (such as changing the position or rotation direction of a certain cargo); The selection, crossover and mutation operations are repeated until the termination condition is met, such as reaching the maximum number of iterations or the fitness improvement is less than a certain threshold, and the global optimization solution is obtained accordingly.

[0034] Finally, the generated initial stacking scheme is locally optimized using the simulated annealing algorithm, including: Based on the global optimization of the initial stacking plan to obtain the global optimization solution, the global optimization solution is disturbed, such as: exchanging the positions of two goods, or adjusting the rotation direction or position of the goods; If the perturbed solution is better than the global optimal solution (i.e., has higher fitness), then the solution is accepted as the new current solution; otherwise, the inferior solution is accepted with a certain preset probability to avoid falling into the local optimum; Repeat the perturbation and acceptance operations until the termination condition is met (such as reaching the maximum number of iterations) to obtain the optimal solution, that is, the optimal stacking solution.

[0035] S3. Load the optimal stacking solution into the palletizing and wrapping equipment, so as to use the optimal stacking solution to guide the robot arm to accurately stack the goods and automatically complete the wrapping process.

[0036] Specifically, in order to improve the degree of automation in the entire process of outbound cargo inspection, the optimal stacking solution is loaded into the stacking and wrapping equipment to guide the robotic arm of the stacking and wrapping equipment to accurately stack the cargo.

[0037] For better transportation, it is often necessary to further wrap and shape the container where the goods are stacked. After the goods are accurately stacked, the wrapping process is completed using the robotic arm of the palletizing and wrapping equipment. While completing the wrapping process, the monitoring equipment installed on the palletizing and wrapping equipment is used to monitor the wrapping process in real time to prevent errors in the wrapping operation that may lead to subsequent verification failures.

[0038] S4 uses a dual verification mechanism of light barriers and contour doors to inspect the shape and integrity of containers that have completed the wrapping process and are loaded with goods.

[0039] Specifically, in addition to stacking optimization during the outbound cargo stacking stage to speed up the stacking process, inspections are carried out on the carrying containers to prevent deformation of the containers after stacking and wrapping and before leaving the warehouse, which may lead to failure to leave the warehouse normally. In order to ensure the accuracy of the inspection and improve the degree of automation, a dual verification mechanism of gratings and contour doors is selected to perform shape and integrity inspections on the containers that have completed the wrapping process and are loaded with goods. Among them, the grating is used in advance to perform preliminary inspections on the shape and size of the containers that have completed the wrapping process and are loaded with goods. After the inspection is passed, the contour door is used to continue the verification. Once it passes smoothly, it indicates that the verification is successful.

[0040] S5. After the inspection is correct, the container that has completed the film wrapping process and is loaded with goods is covered with a net, and the data of the goods and containers to be loaded in the outbound business background database are updated at the same time.

[0041] Specifically, when the container that has completed the film wrapping process and is loaded with goods is detected to be correct, the container is pushed to the area to be shipped out and the container that has completed the film wrapping process and is loaded with goods is automatically covered with a net cover by a covering device, and the data of the goods to be loaded and the container in the outbound business background database are updated at the same time, such as deleting the loaded goods and the used containers when updating the outbound business background database.

[0042] In addition, when a container that has completed the wrapping process and is loaded with goods fails to be inspected, the container is pushed to the manual review area so that the user can choose to push it to the palletizing wrapping area or the grating and contour door double verification area to re-perform palletizing wrapping or verification.

[0043] By adopting the above methods, the degree of automation of the entire process of cargo outbound inspection can be comprehensively improved, reducing manual intervention and improving work efficiency.

[0044] In a specific embodiment, considering that the actual cargo departure process often leads to an advance or delay in the departure time of cargo due to changes in flights, in order to respond to the changes in a timely manner, it is necessary to dynamically adjust the stacking strategy to ensure efficient operation under complex circumstances; the method also includes: Receive flight change information, including flight delay and delay time, flight advance and advance time, flight cancellation and adjustment information.

[0045] Adaptively adjust the cargo priority of the changed flight based on the flight change information, so that the cargo priority of the flight closer to the departure time is higher; specifically, determine the flight operation time after the change according to the flight information and the flight change information, and set the corresponding cargo priority to the first priority according to whether the current time period is the first time period, the second priority according to whether the current time period is the second time period, and the third priority according to whether the current time period is the third time period, wherein the duration of the first time period, the second time period and the third time period are gradually extended; the priority levels of the first priority, the second priority and the third priority are gradually reduced.

[0046] Considering that the cargo stacking corresponding to flights with closer operating times focuses more on efficiency, space utilization can be sacrificed as much as possible. On the contrary, the cargo stacking corresponding to flights with farther operating times focuses more on space utilization to save costs. The overall cargo stacking stability needs to be met as much as possible under any circumstances; therefore, the main goal and secondary goal of cargo stacking are adjusted according to the cargo priority corresponding to each flight, so that the main goal of cargo stacking with a priority higher than the preset priority is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score, and the secondary goal is to maximize the container space utilization; the main goal of cargo stacking with a priority lower than the preset priority is to maximize the container space utilization and maximize the cargo stacking stability score, and the secondary goal is to minimize the total stacking time of cargo stacking; the main goal of cargo stacking with a priority equal to the preset priority is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization, and there is no secondary goal; in this embodiment, the preset priority is the second priority.

[0047] According to the main and secondary objectives of the adjusted cargo stacking, the fitness function in the genetic algorithm is designed accordingly, so that the first fitness function whose main objectives are to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score corresponding to the design stacking time parameter weight and the cargo stacking stability score parameter weight are greater than the space utilization parameter weight, such as: the weight ratio of stacking time parameter: cargo stacking stability score parameter: space utilization parameter is 4:4:2; the second fitness function whose main objectives are to maximize the container space utilization and maximize the cargo stacking stability score corresponding to the design space utilization parameter weight and the cargo stacking stability parameter weight are greater than the stacking time parameter weight, such as: the weight ratio of stacking time parameter: cargo stacking stability score parameter: space utilization parameter is 2:4:4; the third fitness function whose main objectives are to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization corresponding to the design space utilization parameter weight, the cargo stacking stability score parameter weight, and the stacking time parameter weight, which is the same as or less than the difference of the preset weight.

[0048] In a specific embodiment, in order to further improve the automation level of the whole process of outbound cargo inspection, the wrapping process with good wrapping effect is adaptively selected to complete the wrapping, so as to quickly enter the next link and successfully complete the wrapping inspection. The method of automatically completing the wrapping process also includes: Calculate the center of gravity offset of the container under the optimal stacking solution; The container information and the calculated center of gravity offset are input into the wrapping process acquisition network to obtain the wrapping tension, material and winding method in the wrapping process; wherein the wrapping process can be divided into the early, middle and late stages, and the winding method includes: the number of wrapping layers, the wrapping shape (each part of the container). The wrapping process acquisition network uses a convolutional neural network, which is trained and generated using historical container information, the center of gravity offset of the container, and the wrapping tension, material and wrapping method in the wrapping process; wherein the wrapping tension, material and wrapping method in the historical wrapping process can be determined based on the suggestions of experienced wrapping experts so that the center of gravity offset is reduced to a preset threshold after the wrapping process is executed.

[0049] Finally, the container is wrapped according to the obtained wrapping tension, material and winding method in the wrapping process, so that the center of gravity offset of the container is reduced to a preset threshold after wrapping.

[0050] In addition, in addition to performing adaptive wrapping at the wrapping stage of outbound cargo to select a wrapping process with good wrapping effect, multi-level inspection and timely correction can be performed on the wrapping to ensure good wrapping effect, smoothly pass subsequent inspections, and improve inspection efficiency. The method also includes: A wrapping tension sensor array and a machine vision device are integrated on the pallet wrapping equipment, and the wrapping tension at various angles of the container and the image of the container wrapped with film are monitored in real time during the wrapping process. Among them, various angles can be set according to the size of the container, such as: facing the front, back, left, right and other angles of the container.

[0051] The analysis detects in real time the shape of the container wrapped by the film in the wrapping process, compares the shape of the container wrapped by the film with the shape of the target container wrapped by the film in the wrapping process, or compares the wrapping tension of the container at various angles with the target wrapping tension in the wrapping process. If the comparison result shows that the error between the two is greater than the preset error value, the wrapping self-correction program is triggered and the wrapping is performed again.

[0052] Specifically, if the wrapping self-correction program is triggered at any stage of the specific early, middle and late stages of the wrapping process, the wrapping is reversely released and the process returns to the starting point of the stage and wrapping is performed again.

[0053] In a specific embodiment, in order to further improve the automation level of the whole stage of outbound cargo inspection, multiple inspection devices are integrated to complete automatic inspection during the outbound cargo transportation stage, and the method further includes: Add multiple verification devices at key positions of the conveyor belts used to transport goods during the outbound process. The multiple verification devices include smart camera arrays and RFID readers. Multiple verification devices are used to detect the cargo and perform image analysis to determine whether the current cargo is consistent with the recorded information (such as size, weight, etc.) and whether the transportation path conforms to the preset cargo transportation path of the corresponding flight (such as the preset transportation path of the cargo corresponding to flight A is the f-segment conveyor belt path). Once it is determined that the cargo information is inconsistent with the recorded information and does not conform to any of the preset cargo transportation paths of the corresponding flight, an alarm is triggered and the current cargo is tracked in real time to be displayed on the display device.

[0054] In a specific embodiment, considering using a feedback mechanism to continuously optimize the stacking layout, thereby improving the stacking efficiency or increasing the probability of sequentially passing the inspection, the method further includes: From the perspectives of the owner (user) of the outbound cargo or the handler (airline employee) of the outbound cargo, the first feedback data of the user on the outbound cargo and the second feedback data of the airline employee on the outbound cargo are obtained accordingly. The first feedback data includes: cargo damage rate, satisfaction with cargo collection; the second feedback data includes: the cost of using the container, and the time taken for the outbound cargo to be shipped out of the warehouse.

[0055] Once the data in the first feedback data of the outbound cargo reaches the preset value of the data, such as: If the cargo damage rate reaches the preset damage rate or there is data in the second feedback data that reaches a preset value ratio greater than the preset ratio within a preset time period, such as: the proportion of the container's use cost greater than the preset cost within the preset time period is greater than the preset ratio, it indicates that the entire process of port inspection needs to be further improved to further improve efficiency and user satisfaction, so the optimized hybrid heuristic algorithm is selected.

[0056] In addition, in order to further improve satisfaction and avoid extra time consumption caused by optimizing the stacking algorithm, the method further includes: Determine the loading position requirement for each cargo based on the cargo information, wherein the loading position requirement includes: the loading positions of related cargoes are adjacent, the loading positions of cargoes with high extraction priority are close to the container entrance position, etc.; wherein the cargo extraction priority can be set manually.

[0057] Whether the goods in the stacking scheme meet the loading position requirements is taken as a penalty parameter and incorporated into the fitness function of the genetic algorithm. That is, the penalty score corresponding to the proportion of goods in the stacking scheme that does not meet the loading position requirements is calculated and added as a penalty parameter into the calculation of the comprehensive fitness function.

[0058] like Figure 4 As shown, the embodiment of the present application provides a smart cargo inspection system for air departure, including: The outbound cargo data collection module 101 is used to receive cargo information and cargo corresponding flight information collected from the previous link of the outbound aviation business; the previous link includes cargo collection, security inspection, classification and warehousing; and receive container information collected from the outbound link of the outbound aviation business; The outbound cargo stacking scheme acquisition module 102 is used to obtain the optimal stacking scheme for the cargo corresponding to each flight by using a hybrid heuristic algorithm according to the cargo information and container information corresponding to each flight; the hybrid heuristic algorithm includes: using a greedy packing algorithm to generate an initial stacking scheme, using a genetic algorithm to perform global optimization on the generated initial stacking scheme, and using a simulated annealing algorithm to perform local optimization on the generated initial stacking scheme; The outbound cargo wrapping execution module 103 is used to load the optimal stacking plan to the stacking and wrapping equipment to guide the mechanical arm of the stacking and wrapping equipment to stack the cargo and automatically complete the wrapping process; The outbound cargo verification and data update module 104 is used to use a dual verification mechanism of grating and contour door to perform shape and integrity detection on the container that has completed the film wrapping process and is loaded with cargo, and after the detection is correct, the container that has completed the film wrapping process and is loaded with cargo is covered with a net, and at the same time, the cargo and container data to be loaded in the outbound business background database are updated.

[0059] A specific embodiment further includes: The outbound cargo stacking plan optimization module 105 is used to receive flight change information, and adaptively adjust the cargo priority corresponding to the changed flight based on the flight change information, so that the cargo corresponding to the flight with a closer departure time has a higher priority; adjust the main goal and secondary goal of cargo stacking according to the cargo priority corresponding to each flight, so that the main goal of cargo stacking with a priority higher than the preset priority is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score, and the secondary goal is to maximize the container space utilization rate, the main goal of cargo stacking with a priority lower than the preset priority is to maximize the container space utilization rate and maximize the cargo stacking stability score, and the secondary goal is to minimize the total stacking time of cargo stacking, and the main goal of cargo stacking with a priority equal to the preset priority is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization rate. space utilization, no secondary objectives; according to the adjusted main objectives and secondary objectives of cargo stacking, the fitness function in the genetic algorithm is designed accordingly, so that the first fitness function whose main objectives are to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score corresponding to the design stacking time parameter weight and the cargo stacking stability score parameter weight are greater than the space utilization parameter weight; the second fitness function whose main objectives are to maximize the container space utilization and maximize the cargo stacking stability score corresponding to the design space utilization parameter weight and the cargo stacking stability parameter weight are greater than the stacking time parameter weight; the third fitness function whose main objectives are to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization corresponding to the design space utilization parameter weight, the cargo stacking stability score parameter weight, and the stacking time parameter weight are the same.

[0060] The outbound cargo stacking scheme optimization module 105 is also used to determine the loading position requirement of each cargo according to the cargo information, wherein the loading position requirement includes: the loading positions of associated cargoes are adjacent, the loading positions of cargoes with high priority are extracted close to the entrance position of the container; and whether the cargoes in the stacking scheme meet the loading position requirement is included in the fitness function of the genetic algorithm as a penalty parameter.

[0061] A specific embodiment further includes: The outbound cargo wrapping execution optimization module 106 is used to calculate the center of gravity offset of the container under the optimal stacking solution; input the container information and the calculated center of gravity offset into the wrapping process acquisition network to obtain the wrapping tension, material and wrapping method in the wrapping process link; the wrapping process acquisition network uses a convolutional neural network, which is trained and generated using historical container information, the center of gravity offset of the container, and the wrapping tension, material and wrapping method in the wrapping process link; wrap the container according to the obtained wrapping tension, material and wrapping method in the wrapping process link; and is also used to integrate wrapping on the stacking wrapping equipment. The film tension sensor array and the machine vision device utilize the integrated film tension sensor array and the machine vision device to monitor the film tension at various angles of the container and the image of the wrapped container in the wrapping process in real time; the shape of the container wrapped in the wrapping process is detected in real time, and the shape of the wrapped container is compared with the shape of the target wrapped container in the wrapping process, or the film tension at various angles of the container is compared with the target wrapping tension in the wrapping process. If the comparison result shows that the error is greater than the preset error value, the wrapping self-correction program is triggered and the wrapping is performed again.

[0062] A specific embodiment also includes: The outbound cargo transportation detection module 107 is used to add multiple verification devices at key positions of the conveyor belt for transporting cargo in the outbound link, and the multiple verification devices include a smart camera array and an RFID reader; Multiple verification devices are used to detect cargo and perform image analysis to determine whether the current cargo information is consistent with the recorded information and whether the transportation route conforms to the preset cargo transportation route of the corresponding flight. Once it is determined that the cargo information is inconsistent with the recorded information and does not conform to any of the preset cargo transportation routes of the corresponding flight, an alarm is triggered and the current cargo is tracked in real time to be displayed on the display device.

[0063] A specific embodiment further includes: The outbound cargo data feedback module 108 is used to obtain the first feedback data of the user on the outbound cargo and the second feedback data of the airline staff on the outbound cargo, wherein the first feedback data includes: the cargo damage rate; the second feedback data includes: the use cost of the container; once the cargo damage rate of the outbound cargo reaches a preset damage rate or the use cost of the container within a preset time period is greater than the preset cost by a ratio greater than a preset ratio, the optimized hybrid heuristic algorithm is selected.

[0064] The embodiment of the present application also discloses a computer-readable storage medium.

[0065] Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned smart cargo inspection method for air departure. The computer-readable storage medium includes, for example: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0066] The embodiment of the present application also discloses a computer device.

[0067] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute the above-mentioned smart cargo inspection method for air departure.

[0068] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. A smart cargo inspection method for air departure, characterized in that: include: Receive cargo information and cargo corresponding flight information collected from the previous stages of the air departure business; the previous stages include cargo collection, security inspection, classification and warehousing; Receive container information collected from the departure phase of aviation departure business; According to the cargo information and container information corresponding to each flight, a hybrid heuristic algorithm is used to obtain the optimal stacking scheme for the cargo corresponding to each flight; the hybrid heuristic algorithm includes: using a greedy packing algorithm to generate an initial stacking scheme, using a genetic algorithm to perform global optimization on the generated initial stacking scheme, and using a simulated annealing algorithm to perform local optimization on the generated initial stacking scheme; Load the optimal stacking solution to the palletizing and wrapping equipment to guide the robotic arm of the palletizing and wrapping equipment to stack the goods and automatically complete the wrapping process; A dual verification mechanism of grating and contour door is used to check the shape and integrity of the container that has completed the wrapping process and is loaded with goods. After the inspection is correct, the container that has completed the wrapping process and is loaded with goods is covered with a net, and the data of the goods and containers to be loaded in the outbound business background database are updated at the same time.

2. The intelligent cargo inspection method for air departure according to claim 1, characterized in that: Also includes: Receive flight change information, and adaptively adjust the cargo priority of the changed flights based on the flight change information, so that the cargo corresponding to the flight with a closer departure time has a higher priority; Adjust the main and secondary objectives of cargo stacking according to the cargo priority corresponding to each flight, so that the main objective of cargo stacking with a priority higher than the preset priority is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score, and the secondary objective is to maximize the space utilization rate of the container; the main objective of cargo stacking with a priority lower than the preset priority is to maximize the space utilization rate of the container and maximize the cargo stacking stability score, and the secondary objective is to minimize the total stacking time of cargo stacking; the main objective of cargo stacking with a priority equal to the preset priority is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the space utilization rate of the container, and there is no secondary objective; According to the main and secondary objectives of the adjusted cargo stacking, the fitness function in the genetic algorithm is designed accordingly, so that the first fitness function whose main objective is to minimize the total stacking time of cargo stacking and maximize the cargo stacking stability score corresponding to the design stacking time parameter weight and the cargo stacking stability score parameter weight is greater than the space utilization parameter weight; the second fitness function whose main objective is to maximize the container space utilization and maximize the cargo stacking stability score corresponding to the design space utilization parameter weight and the cargo stacking stability parameter weight is greater than the stacking time parameter weight; the third fitness function whose main objective is to minimize the total stacking time of cargo stacking, maximize the cargo stacking stability score and maximize the container space utilization corresponding to the design space utilization parameter weight, the cargo stacking stability score parameter weight, and the stacking time parameter weight is the same.

3. The intelligent cargo inspection method for air departure according to claim 1, characterized in that: The automatic wrapping process also includes: Calculate the center of gravity offset of the container under the optimal stacking solution; Input the container information and the calculated center of gravity offset into the wrapping process acquisition network to obtain the wrapping tension, material and wrapping method in the wrapping process so that the center of gravity offset of the container is reduced to a preset threshold after wrapping; the wrapping process acquisition network uses a convolutional neural network, which is trained and generated using historical container information, the center of gravity offset of the container, and the wrapping tension, material and wrapping method in the wrapping process; The container is wrapped according to the obtained wrapping tension, material and wrapping method in the wrapping process.

4. The intelligent cargo inspection method for air departure according to claim 3, characterized in that: Also includes: Integrate a wrapping tension sensor array and a machine vision device on the pallet wrapping equipment, and use the integrated wrapping tension sensor array and machine vision device to monitor the wrapping tension of the container at all angles and the image of the container wrapped with film in real time during the wrapping process; The analysis detects in real time the shape of the container wrapped by the film in the wrapping process, compares the shape of the container wrapped by the film with the shape of the target container wrapped by the film in the wrapping process, or compares the wrapping tension at each angle of the container with the target wrapping tension in the wrapping process. If the comparison result shows that the error is greater than the preset error value, the wrapping self-correction program is triggered and the wrapping is performed again.

5. The intelligent cargo inspection method for air departure according to claim 1, characterized in that: Also includes: Add multiple verification devices at key positions of the conveyor belts used to transport goods during the outbound process. The multiple verification devices include smart camera arrays and RFID readers. Multiple verification devices are used to detect cargo and perform image analysis to determine whether the current cargo information is consistent with the recorded information and whether the transportation route conforms to the preset cargo transportation route of the corresponding flight. Once it is determined that the cargo information is inconsistent with the recorded information and does not conform to any of the preset cargo transportation routes of the corresponding flight, an alarm is triggered and the current cargo is tracked in real time to be displayed on the display device.

6. The intelligent cargo inspection method for air departure according to claim 1, characterized in that: Also includes: Obtaining first feedback data of users on outbound cargo and second feedback data of airline staff on outbound cargo, wherein the first feedback data includes: cargo damage rate; and the second feedback data includes: usage cost of the container; Once the cargo damage rate of outbound cargo reaches the preset damage rate or the proportion of the container usage cost in the preset time period is greater than the preset cost, the optimized hybrid heuristic algorithm is selected.

7. The intelligent cargo inspection method for air departure according to claim 6, characterized in that: Also includes: Determine the loading position requirement of each cargo according to the cargo information, wherein the loading position requirement includes: the loading positions of the associated cargoes are adjacent and the loading positions of the cargoes with high extraction priority are close to the entrance position of the container; Whether the goods in the stacking scheme meet the loading position requirements is taken as a penalty parameter and incorporated into the fitness function of the genetic algorithm.

8. An intelligent cargo inspection system for air departure, characterized in that: include: The outbound cargo data collection module is used to receive cargo information and cargo corresponding flight information collected from the previous link of the outbound aviation business; the previous link includes cargo collection, security inspection, classification and warehousing; and receive container information collected from the outbound link of the outbound aviation business; The outbound cargo stacking scheme acquisition module is used to obtain the optimal stacking scheme for the cargo corresponding to each flight by using a hybrid heuristic algorithm according to the cargo information and container information corresponding to each flight; the hybrid heuristic algorithm includes: using a greedy packing algorithm to generate an initial stacking scheme, using a genetic algorithm to perform global optimization on the generated initial stacking scheme, and using a simulated annealing algorithm to perform local optimization on the generated initial stacking scheme; The outbound cargo wrapping execution module is used to load the optimal stacking plan into the palletizing and wrapping equipment to guide the robotic arm of the palletizing and wrapping equipment to stack the cargo and automatically complete the wrapping process; The outbound cargo verification and data update module is used to use the dual verification mechanism of grating and contour door to perform shape and integrity detection on the container that has completed the wrapping process and is loaded with cargo. After the detection is correct, the container that has completed the wrapping process and is loaded with cargo is covered with a net, and the data of cargo and container to be loaded in the outbound business background database are updated at the same time.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer device, characterized in that: The computer device comprises a memory, a processor and a program stored and executable on the memory, and the program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images