Intelligent warehousing air freight container storage control method and system

Abstract

The invention provides an air freight container storage control method and system for intelligent storage, and relates to the technical field of intelligent logistics and air freight, and the method comprises the steps: collecting the real-time container information of a target container based on a sensor network, and obtaining the model data and cargo hold region data from a storage database; a container storage control model is constructed, and a container storage strategy is generated according to the real-time container information, the model data and the cargo hold area data; based on the container storage strategy, the air freight robot is controlled to carry the target container; real-time freight data of the target container are collected, abnormity monitoring is carried out on the real-time freight data, and abnormal freight data are fed back to the central controller; and recording the current storage data of the target container and sending the current storage data to the intelligent warehouse management interface, so that intelligent and precise management of the container can be realized, the warehousing efficiency and safety are improved, and the operation risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent logistics and air cargo transportation, and particularly to a storage control method and system for air cargo unit load devices in intelligent warehousing. Background Art

[0002] Traditional air cargo warehousing management mainly relies on manual records and monitoring. However, manual operation is inefficient, and errors are prone to occur during the recording of cargo information and the scheduling of unit load devices, resulting in chaotic cargo management. At the same time, it is difficult to track the status of goods in real time, and information such as the location of unit load devices and the loading situation of goods cannot be grasped in a timely manner.

[0003] Currently, through technologies such as radio frequency identification tags and barcode scanning, unit load devices can be identified and tracked. However, these technologies are greatly affected by equipment accuracy, and the operation is complex, prone to identification errors. Moreover, the existing technologies cannot accurately control the load distribution of unit load devices under different aircraft types and cabin conditions, resulting in low space utilization rate of the aircraft cargo hold.

[0004] For non-standard size or overweight goods, the existing technologies lack effective management strategies, increasing the safety hazards of cargo transportation. In addition, traditional unit load device management methods are difficult to adapt to rapidly changing flight schedules and fluctuations in cargo volume, prone to causing operation delays, and thus increasing operating costs.

[0005] Therefore, it is necessary to provide a storage control method and system for air cargo unit load devices in intelligent warehousing to solve the above technical problems. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a storage control method and system for air cargo unit load devices in intelligent warehousing, which are used to solve the problems that the existing technologies cannot manage unit load devices in an intelligent and precise manner, resulting in low space utilization rate; and it is difficult to adapt to rapidly changing flight schedules and fluctuations in cargo volume, resulting in significant increases in operation delays and costs; at the same time, effective classification and scheduling of special goods cannot be achieved, and the operation risk is relatively high.

[0007] A storage control method for air cargo unit load devices in intelligent warehousing provided by the present invention includes: Collecting real-time unit load device information of a target unit load device based on a sensor network, and obtaining aircraft type data and cargo hold area data from a warehousing database; Constructing a unit load device storage control model, and generating a unit load device storage strategy according to the real-time unit load device information, the aircraft type data, and the cargo hold area data; Controlling an air cargo robot to carry the target unit load device based on the unit load device storage strategy; Collect the real-time freight data of the target container, monitor the real-time freight data for anomalies and feed the abnormal freight data back to the central controller; Record the current storage data of the target container and send it to the intelligent warehousing management interface.

[0008] Preferably, the real-time container information of the target container is collected based on the sensor network, specifically including: The sensor network includes a weight sensor, a laser ranging sensor, and a positioning sensor; Collect the weight information of the target container based on the weight sensor; Collect the size information of the target container based on the laser ranging sensor; Collect the position information of the target container based on the positioning sensor; Summarize the weight information, the size information, and the position information to generate the real-time container information.

[0009] Preferably, the container storage control model is constructed, and the container storage strategy is generated according to the real-time container information, the aircraft type data, and the cargo hold area data, specifically including: Perform preprocessing operations on the real-time container information, the aircraft type data, and the cargo hold area data; Construct the container storage control model, and input the preprocessed real-time container information, the aircraft type data, and the cargo hold area data into the container storage control model to generate the container storage strategy, and the container storage strategy includes the container storage location and the container storage order; Determine the load balance degree and space utilization rate of the cargo hold based on the container storage strategy, and adjust and optimize the container storage control model according to the load balance degree and the space utilization rate.

[0010] Preferably, inputting the preprocessed real-time container information, the aircraft type data, and the cargo hold area data into the container storage control model to generate the container storage strategy specifically includes: Based on the preprocessed real-time container information, the aircraft type data, and the cargo hold area data, construct an input vector X, and the number of elements of the input vector X is 3; Input the input vector X into the input layer of the container storage control model, and the number of neurons in the input layer is the same as the number of elements of the input vector X, and the activation output of the j-th neuron in the first hidden layer of the container storage control model is obtained as follows: In the formula, Denotes the weighted input of the j-th neuron in the first hidden layer; Denotes the weight from the i-th neuron in the input layer to the j-th neuron in the first hidden layer; Denotes the i-th element of the input vector X, ; Denotes the bias of the j-th neuron in the first hidden layer; Denotes the activation output of the j-th neuron in the first hidden layer; Denotes the activation function; If the number of hidden layers of the container storage control model is L, the activation output of the j-th neuron in the L-th hidden layer is as follows: In the formula, Denotes the weighted input of the j-th neuron in the L-th hidden layer; Denotes the number of neurons in the (L - 1)-th hidden layer; Denotes the weight from the i-th neuron in the (L - 1)-th hidden layer to the j-th neuron in the L-th hidden layer; Denotes the activation output of the i-th neuron in the (L - 1)-th hidden layer; Denotes the bias of the j-th neuron in the L-th hidden layer; Denotes the activation output of the j-th neuron in the L-th hidden layer.

[0011] Preferably, the output of the output layer of the container storage control model Is the container storage strategy, where Denotes the coordinates of the container storage location; Denotes the container storage order; The number of neurons in the output layer is the number of elements of the output Y. Calculate the output value of the k-th neuron in the output layer as follows: In the formula, Denotes the weighted input of the k-th neuron in the output layer; Denotes the number of neurons in the L-th hidden layer; Denotes the weight from the i-th hidden layer in the L-th hidden layer to the k-th neuron in the output layer; Denotes the activation output of the i-th neuron in the L-th hidden layer; Denotes the bias of the k-th neuron in the output layer; Denotes the output value of the k-th neuron in the output layer, that is, the k-th element of the output Y, and .

[0012] Preferably, based on the container storage strategy, controlling the air cargo robot to carry the target container specifically includes: Generate a handling instruction based on the container storage strategy and send the handling instruction to the air cargo robot through a wireless communication network; After receiving the handling instruction, the air cargo robot handles the target container according to a preset planned path and a preset handling method; Among them, the preset planned path includes a first planned path and a second planned path.

[0013] Preferably, the first planned path is the shortest path between the starting position of the air cargo robot and the current position of the target container; the second planned path is the shortest path between the current position of the target container and the storage position of the target container; The determination process of the first planned path is as follows: Calculate the comprehensive evaluation value of the cargo hold node n as follows: In the formula, represents the comprehensive evaluation value of the cargo hold node n; represents the actual cost from the starting position of the air cargo robot to the cargo hold node n; represents the cost of the m-th step from the starting position of the air cargo robot to the cargo hold node n; M represents the total number of steps from the starting position of the air cargo robot to the cargo hold node n; represents the estimated cost from the cargo hold node n to the current position of the target container; represents the current position coordinates of the target container; represents the position coordinates of the cargo hold node n; If the comprehensive evaluation value of the cargo hold node n meets the first planned path condition, it is determined that the cargo hold node n is the first path node corresponding to the first planned path; Repeat the judgment process of the first path node until the first planned path is determined; The determination process of the second planned path is the same as that of the first planned path.

[0014] Preferably, collect the real-time freight data of the target container and perform anomaly monitoring on the real-time freight data; When it is detected that the air cargo robot deviates from the preset planned path, the target container tilts, or there are obstacles on the preset planned path, trigger an anomaly alarm mechanism and feedback the detected abnormal freight data to the central controller.

[0015] Preferably, recording the current storage data of the target container and sending it to the intelligent warehousing management interface specifically includes: Record the current storage data of the target container; Update the storage record of the target container in the warehousing database based on the current stored data; Perform visualization processing on the current stored data and send it to the intelligent warehousing management interface.

[0016] An air cargo container storage control system for intelligent warehousing, the system includes: An acquisition module, configured to acquire real-time container information of a target container based on a sensor network, and obtain aircraft type data and cargo hold area data from a warehousing database; A policy generation module, configured to construct a container storage control model, and generate a container storage policy according to the real-time container information, the aircraft type data, and the cargo hold area data; A handling control module, configured to control an air cargo robot to handle the target container based on the container storage policy; An anomaly monitoring module, configured to collect real-time freight data of the target container, perform anomaly monitoring on the real-time freight data, and feed back the abnormal freight data to a central controller; A record sending module, configured to record the current stored data of the target container and send it to the intelligent warehousing management interface.

[0017] Compared with related technologies, an air cargo container storage control method and system for intelligent warehousing provided by the present invention has the following beneficial effects: The present invention can acquire real-time container information of a target container based on a sensor network, and obtain aircraft type data and cargo hold area data from a warehousing database; construct a container storage control model, and generate a container storage policy according to the real-time container information, the aircraft type data, and the cargo hold area data; control an air cargo robot to handle the target container based on the container storage policy; collect real-time freight data of the target container, perform anomaly monitoring on the real-time freight data, and feed back the abnormal freight data to a central controller; record the current stored data of the target container and send it to the intelligent warehousing management interface, so as to realize the intelligent and precise management of the container, improve the warehousing efficiency and safety, and reduce the operation risk.

[0018] The present invention adopts an intelligent and refined container storage control method, which can control the handling of containers by air cargo robots through container storage strategies, and accurately control the load distribution of containers according to the limiting conditions of different aircraft models and cabin positions, effectively improving the space utilization rate of the aircraft cargo hold, reducing the waste of space resources, and improving the management efficiency of large and overweight goods and reducing the operation risk; through an abnormal monitoring mechanism, the present invention can enhance the adaptability to rapidly changing flight schedules and cargo volume fluctuations, reduce operation delays, and reduce operating costs; the present invention can record the real-time storage situation of containers and visualize it, and then send it to the intelligent warehousing management interface, improving the convenience and accuracy of warehousing management, reducing manual intervention, and reducing the error rate. Brief Description of the Drawings

[0019] Figure 1 is a flowchart of an air cargo container storage control method for intelligent warehousing according to the present invention; Figure 2 is a schematic diagram of the generation of real-time container information according to the present invention; Figure 3 is a schematic diagram of the sending of handling instructions according to the present invention; Figure 4 is a system block diagram of an air cargo container storage control system for intelligent warehousing according to the present invention. Detailed Embodiments

[0020] The present invention will be further described below in conjunction with the drawings and embodiments.

[0021] Embodiment 1

[0022] As Figure 1 shown, an air cargo container storage control method for intelligent warehousing, the method includes: S1, collecting real-time container information of the target container based on a sensor network, and obtaining aircraft model data and cargo hold area data from a warehousing database; Among them, the sensor network refers to a sensor network used to collect and transmit real-time information of containers, which can perform all-round and real-time monitoring of containers. The target container refers to the container that needs to be stored. The warehousing database refers to a database used to store and manage air cargo-related data. The aircraft model data includes information such as the model, structural characteristics, load limit, and cabin layout of the aircraft. The cargo hold area data includes information such as the volume, load-bearing weight limit, space shape, and connection relationship of different areas of the cargo hold.

[0023] In practical applications, through a sensor network and using sensing technology, real-time data collection can be carried out on the target container in all directions. These sensors can accurately obtain real-time container information such as the weight, size, location, and internal cargo status of the target container.

[0024] Meanwhile, through an efficient data interaction interface, aircraft type data and cargo hold area data can be quickly retrieved from the warehouse database. Among them, the warehouse database stores detailed parameters of various aircraft, such as aircraft type data like the load limits and cabin layouts of different aircraft types, as well as cargo hold area data such as the volume, load-bearing weight limits, and space shapes of each area of the cargo hold.

[0025] S2. Construct a container storage control model, and generate a container storage strategy based on the real-time container information, the aircraft type data, and the cargo hold area data; It can be understood that the container storage control model refers to a model used to analyze container information, aircraft type data, and cargo hold area data and generate a container storage strategy. The container storage strategy refers to a strategy used to synthesize container information, aircraft type data, and cargo hold area data and determine the placement position and loading order of the container in the cargo hold.

[0026] Furthermore, a container storage control model can be constructed to deeply analyze real-time container information, aircraft type data, and cargo hold area data, and generate a container storage strategy, which includes information such as the storage position and loading order of the container in the cargo hold.

[0027] S3. Based on the container storage strategy, control an air cargo robot to carry the target container; Among them, the air cargo robot refers to an intelligent device with automated handling and navigation functions, used to carry air cargo containers.

[0028] In practical applications, based on the container storage strategy, precise instructions can be issued to the air cargo robot. The air cargo robot is equipped with advanced navigation and handling equipment and can accurately carry out handling operations on the target container according to the instructions, thereby ensuring that the container is accurately placed at the designated position.

[0029] S4. Collect real-time freight data of the target container, monitor the real-time freight data for anomalies, and feed back the abnormal freight data to the central controller; It can be understood that the real-time freight data refers to the real-time collected container handling status data. The abnormal freight data refers to freight data that does not conform to the normal standard and may affect freight safety and efficiency. The central controller is the core control unit, used to complete data processing, instruction issuing, and task coordination work.

[0030] During the transportation process, real-time freight data of the target container can be continuously collected, and these real-time freight data can be analyzed in real time using anomaly monitoring algorithms. Once an anomaly is detected, abnormal freight data will be immediately generated and fed back to the central controller.

[0031] S5, record the current storage data of the target container and send it to the intelligent warehousing management interface.

[0032] It should be noted that the current storage data refers to the container storage status data recorded in real time. The intelligent warehousing management interface refers to a platform for realizing visual display of warehousing information and human-computer interaction operations, which is convenient for managers to monitor and manage warehousing activities.

[0033] Finally, the current storage data of the target container, such as storage location, storage time, cargo status, etc., can be automatically recorded, and with the help of network communication technology, these data can be transmitted to the intelligent warehousing management interface in real time. This interface presents the warehousing status in an intuitive visual form, which is convenient for managers to conduct real-time monitoring and decision-making.

[0034] In the specific implementation process, as Figure 2 shown, the acquisition of real-time container information of the target container based on the sensor network specifically includes: The sensor network includes a weight sensor, a laser range finder sensor, and a positioning sensor; Based on the weight sensor, collect the weight information of the target container; Based on the laser range finder sensor, collect the size information of the target container; Based on the positioning sensor, collect the position information of the target container; Summarize the weight information, the size information, and the position information to generate the real-time container information.

[0035] It should be noted that this sensor network is composed of a variety of sensors with different functions working together, specifically including a weight sensor, a laser range finder sensor, and a positioning sensor.

[0036] Specifically, the weight sensor adopts high-precision pressure sensing technology. By measuring the pressure generated by the target container on it, the weight information of the target container can be accurately collected, providing key data for subsequent load distribution and safety assessment.

[0037] The laser range finder sensor can use the principle of laser reflection to emit a laser beam to the target container and receive the reflected light, calculate the distance between the sensor and each surface of the container, and then the length, width, and height size information of the target container can be obtained, which helps to reasonably plan the storage space in the cargo hold.

[0038] The positioning sensor can, by means of satellite positioning or indoor positioning technology, track the location information of the target container in the warehousing environment in real time, and thus can accurately locate the target container.

[0039] Finally, the weight information collected by the weight sensor, the dimension information obtained by the laser range finder sensor, and the location information tracked by the positioning sensor can be efficiently summarized. Through data fusion algorithms, these different types of data are integrated into unified real-time container information, providing comprehensive and accurate data support for subsequent warehousing management decisions.

[0040] Constructing the container storage control model and generating a container storage strategy based on the real-time container information, the aircraft type data, and the cargo hold area data specifically includes: Performing preprocessing operations on the real-time container information, the aircraft type data, and the cargo hold area data; Constructing the container storage control model, inputting the preprocessed real-time container information, the aircraft type data, and the cargo hold area data into the container storage control model, generating the container storage strategy, and the container storage strategy includes the container storage location and the container storage order; Based on the container storage strategy, determining the load balance degree and space utilization rate of the cargo hold, and adjusting and optimizing the container storage control model according to the load balance degree and the space utilization rate.

[0041] Among them, preprocessing can be performed on the real-time container information, the aircraft type data, and the cargo hold area data. Specifically, data cleaning techniques can be used to remove noise, outliers, and duplicate records in the data to ensure the accuracy and integrity of the data. Then, through data standardization means, data of different magnitudes and units can be unified into a specific range to enhance the comparability of the data.

[0042] Immediately afterwards, a container storage control model can be constructed, and the preprocessed real-time container information, the aircraft type data, and the cargo hold area data are input into this model to generate a container storage strategy. This strategy includes the container storage location and the storage order.

[0043] Furthermore, based on the container storage strategy, the load balance degree and space utilization rate of the cargo hold can be accurately calculated. Among them, the load balance degree can be determined by analyzing the load weight distribution in each area. The space utilization rate is determined based on the ratio of the space occupied by the container to the total volume of the cargo hold.

[0044] Finally, the container storage control model can be adjusted and optimized based on the load balancing degree and space utilization rate. For example, if it is found that a certain area is overloaded or the space utilization is poor, targeted adjustments can be made to the parameters or algorithm logic of the container storage control model, thereby continuously improving the scientificity and effectiveness of the container storage strategy.

[0045] Inputting the preprocessed real-time container information, the aircraft type data, and the cargo hold area data into the container storage control model to generate the container storage strategy specifically includes: Based on the preprocessed real-time container information, the aircraft type data, and the cargo hold area data, construct an input vector X, and the number of elements of the input vector X is 3; Input the input vector X into the input layer of the container storage control model. The number of neurons in the input layer is the same as the number of elements of the input vector X, and the activation output of the j-th neuron in the first hidden layer of the container storage control model is obtained as follows: In the formula, represents the weighted input of the j-th neuron in the first hidden layer; represents the weight from the i-th neuron in the input layer to the j-th neuron in the first hidden layer; represents the i-th element of the input vector X, ; represents the bias of the j-th neuron in the first hidden layer; represents the activation output of the j-th neuron in the first hidden layer; represents the activation function; If the number of hidden layers of the container storage control model is L, the activation output of the j-th neuron in the L-th hidden layer is as follows: In the formula, represents the weighted input of the j-th neuron in the L-th hidden layer; represents the number of neurons in the L-1-th hidden layer; represents the weight from the i-th neuron in the L-1-th hidden layer to the j-th neuron in the L-th hidden layer; represents the activation output of the i-th neuron in the L-1-th hidden layer; represents the bias of the j-th neuron in the L-th hidden layer; represents the activation output of the j-th neuron in the L-th hidden layer.

[0046] The output of the output layer of the container storage control model is the container storage strategy, where, Represent the coordinates of the storage location of the container; Represent the storage order of the container; The number of neurons in the output layer is the number of elements of the output Y. Calculate the output value of the k-th neuron in the output layer as follows: In the formula, Represents the weighted input of the k-th neuron in the output layer; Represents the number of neurons in the L-th hidden layer; Represents the weight from the i-th neuron in the L-th hidden layer to the k-th neuron in the output layer; Represents the activation output of the i-th neuron in the L-th hidden layer; Represents the bias of the k-th neuron in the output layer; Represents the output value of the k-th neuron in the output layer, that is, the k-th element of the output Y, and .

[0047] It can be understood that first, an input vector can be constructed based on the preprocessed real-time container information, aircraft type data, and cargo hold area data. The input vector includes three elements, corresponding to the above three types of data respectively.

[0048] Then, the input vector can be input into the input layer of the container storage control model. The number of neurons in the input layer is the same as the number of elements of the input vector. After receiving the data, the input layer passes the data to the first hidden layer through a series of calculations. In the first hidden layer, each neuron performs a weighted calculation on the input data and adds a bias value, and then processes it through an activation function to obtain the activation output of the j-th neuron in the first hidden layer.

[0049] If the container storage control model includes multiple hidden layers, assuming the number of hidden layers is L, then starting from the second hidden layer, the neurons in each layer will receive the activation output of the neurons in the previous layer as input, and after processing, obtain the activation output of the j-th neuron in the L-th hidden layer.

[0050] Finally, the output layer of the container storage control model can receive the output result of the last hidden layer, and obtain the final output through calculation, that is, the container storage strategy. This strategy includes the storage location coordinates and storage order of the container. The number of neurons in the output layer is consistent with the number of elements of the output result.

[0051] Based on the container storage strategy, controlling the air cargo robot to carry the target container specifically includes: Generating a handling instruction based on the container storage strategy and sending the handling instruction to the air cargo robot through a wireless communication network; After receiving the handling instruction, the air cargo robot handles the target container according to the preset planned path and preset handling method; Among them, the preset planned path includes a first planned path and a second planned path.

[0052] Specifically, the central controller can parse and generate a handling instruction containing detailed handling information according to the container storage strategy. Then, as Figure 3 shown, these handling instructions can be stably and accurately sent to the air cargo robot through an efficient wireless communication network.

[0053] After receiving the handling instruction, the air cargo robot can execute the handling task according to the preset planned path and preset handling method through its built-in intelligent control system. And the preset planned path includes a first planned path and a second planned path.

[0054] The first planned path is the shortest path between the starting position of the air cargo robot and the current position of the target container; the second planned path is the shortest path between the current position of the target container and the storage position of the target container; The determination process of the first planned path is as follows: Calculate the comprehensive evaluation value of the cargo hold node n as follows: In the formula, represents the comprehensive evaluation value of the cargo hold node n; represents the actual cost from the starting position of the air cargo robot to the cargo hold node n; represents the cost of the mth step from the starting position of the air cargo robot to the cargo hold node n; M represents the total number of steps from the starting position of the air cargo robot to the cargo hold node n; represents the estimated cost from the cargo hold node n to the current position of the target container; represents the current position coordinates of the target container; represents the position coordinates of the cargo hold node n; If the comprehensive evaluation value of the cargo hold node n meets the first planned path condition, it is determined that the cargo hold node n is the first path node corresponding to the first planned path; Repeat the judgment process of the first path node until the first planned path is determined; The determination process of the second planned path is the same as that of the first planned path.

[0055] It can be understood that the first planned path refers to the shortest path for the air cargo robot to go from the starting position to the current position of the target container, while the second planned path refers to the shortest path for the target container to reach its storage position from the current position.

[0056] For the first planned path, first, the comprehensive evaluation value of each node in the cargo hold can be calculated. This comprehensive evaluation value is jointly determined by the actual cost from the starting position of the air cargo robot to the cargo hold node and the estimated cost from this cargo hold node to the current position of the target container. And the actual cost is the sum of the moving costs for each step.

[0057] The condition for the first planned path is that the comprehensive evaluation value exceeds the first planned path threshold. Here, the first planned path threshold refers to a pre-set threshold used to determine whether a cargo hold node is a first path node.

[0058] When the comprehensive evaluation value of a certain cargo hold node meets the condition of the first planned path, it can be determined that this cargo hold node is the first path node corresponding to the first planned path. Repeat the above judgment process until the complete first planned path is determined.

[0059] It should be noted that the determination process of the second planned path is exactly the same as that of the first planned path, which can thus ensure that the optimal path corresponds to different handling stages.

[0060] Collect the real-time freight data of the target container and perform anomaly monitoring on the real-time freight data; When it is monitored that the air cargo robot deviates from the preset planned path, the target container tilts, or there are obstacles on the preset planned path, trigger the anomaly alarm mechanism and feedback the monitored abnormal freight data to the central controller.

[0061] It should be noted that the real-time freight data of the target container can be continuously collected. Then, an anomaly monitoring algorithm can be used to perform all-round and real-time analysis on the collected real-time freight data.

[0062] Once it is monitored that the air cargo robot deviates from the pre-set planned path, the target container tilts, or there are obstacles on the preset planned path, the anomaly alarm mechanism can be immediately triggered.

[0063] This mechanism can quickly feedback the monitored abnormal freight data, such as key information like the deviation direction and distance, tilt angle, and obstacle position, to the central controller through an efficient data transmission link, so that the central controller can make timely response decisions to ensure the safety of freight operations.

[0064] Embodiment 2 As Figure 4 shown, an air cargo container storage control system for an intelligent warehouse, the system includes: The acquisition module is used to collect the real-time container information of the target container based on the sensor network, and obtain the aircraft type data and cargo hold area data from the warehousing database; The strategy generation module is used to construct a container storage control model, and generate a container storage strategy according to the real-time container information, the aircraft type data and the cargo hold area data; The handling control module is used to control the air cargo robot to handle the target container based on the container storage strategy; The anomaly monitoring module is used to collect the real-time freight data of the target container, monitor the anomaly of the real-time freight data and feedback the abnormal freight data to the central controller; The recording and sending module is used to record the current storage data of the target container and send it to the intelligent warehousing management interface.

[0065] Through the introduction of the above embodiments, the air cargo container storage control method and system of the present invention can collect the real-time container information of the target container based on the sensor network, and obtain the aircraft type data and cargo hold area data from the warehousing database; construct a container storage control model, and generate a container storage strategy according to the real-time container information, the aircraft type data and the cargo hold area data; control the air cargo robot to handle the target container based on the container storage strategy; collect the real-time freight data of the target container, monitor the anomaly of the real-time freight data and feedback the abnormal freight data to the central controller; record the current storage data of the target container and send it to the intelligent warehousing management interface, so as to realize the intelligent and precise management of the container, improve the warehousing efficiency and safety, and reduce the operation risk.

[0066] The present invention adopts an intelligent and refined container storage control method, which can control the air cargo robot to handle the container through the container storage strategy, and accurately control the load distribution of the container according to the limiting conditions of different aircraft types and cabin positions, effectively improving the space utilization rate of the aircraft cargo hold, reducing the waste of space resources, and improving the management efficiency of large and overweight goods and reducing the operation risk; through the anomaly monitoring mechanism, the present invention can enhance the adaptability to the rapidly changing flight schedule and cargo volume fluctuations, reduce operation delays and lower operating costs; the present invention can record the real-time storage situation of the container and perform visual processing on it, and then send it to the intelligent warehousing management interface, improving the convenience and accuracy of warehousing management, reducing manual intervention and lowering the error rate.

[0067] Taking the B777F aircraft type as an example, the specific implementation process of the present invention is described in detail as follows: Before the start of the cargo storage operation, it is necessary to ensure that all components of the air cargo container storage control system are operating normally. That is, the sensor network has completed self-check and entered the working state, and it can monitor the storage environment in real time; the relevant parameters of the cargo hold of the B777F model have been stored in the database, including the dimensions, volumes, weight limits, etc. of different cargo holds, as well as the standard parameters of various containers; the central controller is loaded with preset management rules and algorithms; the user interface has been started and displays the initial state of the storage.

[0068] When a new batch of containers is ready to be stored in the warehouse, the sensor network quickly collects the real-time data of each container, such as weight, dimensions, etc., and transmits this data to the central controller. At the same time, the system receives basic information such as the model of the incoming containers.

[0069] Based on the received container information and combined with the specific restrictions of the cargo hold of the B777F model, such as the weight and dimension requirements of different areas in the main cargo hold and the lower cargo hold, the central controller analyzes the characteristics of this batch of containers through deep learning algorithms, considering asymmetric factors such as the center of gravity restrictions in different areas of the cargo hold, and calculates the optimal storage plan. For example, for the M-type container, according to its weight and dimensions, determine the specific loading position in the main cargo hold, that is, the side position in the A-P area, the central loading area, or the transverse loading position in the R area.

[0070] The central controller sends instructions to the handling robot according to the calculated storage plan. The handling robot accurately transports the container to the designated location for storage according to the instructions. During the handling process, if an unexpected situation occurs, such as the handling path is blocked, the sensor network timely feedbacks the abnormal information to the central controller, and the central controller readjusts the handling strategy to ensure the smooth completion of the handling task.

[0071] After the containers are stored, the system automatically updates the database, records the latest location, status, etc. of the containers, and real-time feedbacks the updated information to the user interface. Then, the management personnel can intuitively view the storage situation of the containers through the user interface.

[0072] In addition, if an oversize or overweight container is encountered, the adaptive adjustment mechanism is activated. The system flexibly adjusts the usage mode of adjacent spaces according to the actual situation, such as adjusting the storage positions of some small containers to reserve enough space for the oversize container. At the same time, the advanced prediction model predicts possible similar situations in the future based on historical data and current cargo trends, and plans the storage plan in advance to improve the response efficiency.

[0073] When the flight schedule changes, the emergency plan system and the intelligent scheduling engine work together. If the flight is advanced or postponed, the intelligent scheduling engine combines real-time flight data and warehouse load status to quickly adjust the loading sequence and storage location of the goods to ensure that the goods can be loaded on time. In case of major abnormal situations such as flight cancellations, the system immediately activates the corresponding emergency plan to rearrange the stored goods and reduce losses.

[0074] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows 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, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes or multiple processes and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0075] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is readable by a computer.

[0076] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

Claims

1. A method for controlling storage of air cargo containers in smart warehousing, characterized in that: The method comprises: Collect real-time ULD information of the target ULD based on the sensor network, and obtain aircraft model data and cargo hold area data from the warehouse database; Constructing a container storage control model, and generating a container storage strategy according to the real-time container information, the aircraft model data and the cargo hold area data; Based on the container storage strategy, controlling the air cargo robot to carry the target container; Collecting real-time freight data of the target container, monitoring the real-time freight data for abnormalities and feeding back the abnormal freight data to a central controller; The current storage data of the target container is recorded and sent to the smart warehouse management interface.

2. The method for controlling storage of air cargo containers in smart warehousing according to claim 1, characterized in that: The real-time container information of the target container is collected based on the sensor network, specifically including: The sensor network includes a weight sensor, a laser ranging sensor and a positioning sensor; Collecting weight information of the target container based on the weight sensor; Collecting size information of the target container based on the laser ranging sensor; Collecting the position information of the target container based on the positioning sensor; The weight information, the size information, and the location information are aggregated to generate the real-time container information.

3. The method for controlling storage of air cargo containers in smart warehousing according to claim 1, characterized in that: The constructing of the container storage control model and generating the container storage strategy according to the real-time container information, the aircraft model data and the cargo hold area data specifically includes: Preprocessing the real-time container information, the aircraft model data, and the cargo hold area data; Constructing the container storage control model, and inputting the preprocessed real-time container information, the aircraft model data and the cargo hold area data into the container storage control model to generate the container storage strategy, wherein the container storage strategy includes a container storage position and a container storage order; The load balance and space utilization of the cargo hold are determined based on the container storage strategy, and the container storage control model is adjusted and optimized according to the load balance and the space utilization.

4. The method for controlling storage of air cargo containers in smart warehousing according to claim 3, characterized in that: The pre-processed real-time container information, the aircraft model data and the cargo hold area data are input into the container storage control model to generate the container storage strategy, specifically including: Based on the preprocessed real-time container information, the aircraft model data and the cargo hold area data, an input vector X is constructed, and the number of elements of the input vector X is 3; The input vector X is input to the input layer of the container storage control model, and the number of neurons in the input layer is the number of elements of the input vector X. The activation output of the jth neuron in the first hidden layer of the container storage control model is obtained as follows: In the formula, represents the weighted input of the jth neuron in the first hidden layer; Represents the weight from the i-th neuron in the input layer to the j-th neuron in the first hidden layer; represents the i-th element of the input vector X, ; represents the bias of the jth neuron in the first hidden layer; represents the activation output of the jth neuron in the first hidden layer; represents the activation function; The number of hidden layers of the container storage control model is L, and the activation output of the jth neuron in the Lth hidden layer is as follows: In the formula, represents the weighted input of the jth neuron in the Lth hidden layer; represents the number of neurons in the L-1th hidden layer; represents the weight from the i-th neuron in the L-1th hidden layer to the j-th neuron in the Lth hidden layer; represents the activation output of the i-th neuron in the L-1-th hidden layer; represents the bias of the jth neuron in the Lth hidden layer; represents the activation output of the jth neuron in the Lth hidden layer.

5. The method for controlling storage of air cargo containers in smart warehousing according to claim 4, characterized in that: The container stores the output of the output layer of the control model That is the container storage strategy, where: The coordinates representing the storage location of the container; Indicates the storage order of the containers; The number of neurons in the output layer is the number of elements in the output Y. The output value of the kth neuron in the output layer is calculated as follows: In the formula, represents the weighted input of the kth neuron in the output layer; represents the number of neurons in the Lth hidden layer; represents the weight of the neuron from the i-th hidden layer to the k-th output layer in the L-th hidden layer; represents the activation output of the i-th neuron in the L-th hidden layer; represents the bias of the kth neuron in the output layer; represents the output value of the kth neuron in the output layer, that is, the kth element of output Y, and .

6. The method for controlling storage of air cargo containers in smart warehousing according to claim 1, characterized in that: The controlling the air cargo robot to carry the target container based on the container storage strategy specifically includes: Generate a handling instruction based on the container storage strategy, and send the handling instruction to the air cargo robot via a wireless communication network; After receiving the transport instruction, the air cargo robot transports the target container according to a preset planned path and a preset transport method; The preset planned path includes a first planned path and a second planned path.

7. The method for controlling storage of air cargo containers in smart warehousing according to claim 6, characterized in that: The first planned path is the shortest path between the starting position of the air cargo robot and the current position of the target container; the second planned path is the shortest path between the current position of the target container and the storage position of the target container; The process of determining the first planned path is as follows: The comprehensive evaluation value of cargo hold node n is calculated as follows: In the formula, represents the comprehensive evaluation value of cargo hold node n; represents the actual cost from the starting position of the air cargo robot to the cargo hold node n; represents the m-th moving cost from the starting position of the air cargo robot to the cargo hold node n; M represents the total number of steps from the starting position of the air cargo robot to the cargo hold node n; represents the estimated cost from cargo hold node n to the current position of the target container; Indicates the current position coordinates of the target container; Represents the position coordinates of cargo hold node n; If the comprehensive evaluation value of the cargo hold node n meets the first planned path condition, then the cargo hold node n is determined to be the first path node corresponding to the first planned path; Repeat the first path node determination process until the first planned path is determined; The process of determining the second planned path is the same as that of determining the first planned path.

8. The method for controlling storage of air cargo containers in smart warehousing according to claim 7, characterized in that: Collecting real-time freight data of the target container and performing abnormal monitoring on the real-time freight data; When it is monitored that the air cargo robot deviates from the preset planned path, the target container is tilted, or there is an obstacle on the preset planned path, an abnormal alarm mechanism is triggered and the monitored abnormal cargo data is fed back to the central controller.

9. The method for controlling storage of air cargo containers in smart warehousing according to claim 1, characterized in that: The recording of the current storage data of the target container and sending it to the smart warehouse management interface specifically includes: Recording current storage data of the target container; Based on the current storage data, updating the storage record of the target container in the storage database; The currently stored data is visualized and sent to the smart warehouse management interface.

10. A smart warehousing air cargo container storage control system, applied to a smart warehousing air cargo container storage control method as claimed in any one of claims 1 to 9, characterized in that: The system comprises: The acquisition module is used to collect the real-time container information of the target container based on the sensor network, and obtain the aircraft model data and cargo hold area data from the warehouse database; A strategy generation module, used to construct a container storage control model and generate a container storage strategy according to the real-time container information, the aircraft model data and the cargo hold area data; A handling control module, used for controlling the air cargo robot to handle the target container based on the container storage strategy; An abnormality monitoring module, used for collecting real-time freight data of the target container, performing abnormality monitoring on the real-time freight data and feeding back the abnormal freight data to the central controller; The record sending module is used to record the current storage data of the target container and send it to the smart warehouse management interface.

Images