A cold chain logistics warehousing intelligent management method and system
Through the use of prediction models and refrigeration estimates, the problem of inaccurate temperature adjustment in cold chain logistics warehousing is solved, energy efficiency and cargo quality are improved, and intelligent management of cold chain logistics warehousing is reflected.
Patent Information
- Application Number
- CN202410285359.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-13
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-03-13
AI Technical Summary
In cold chain logistics warehousing management, the existing technology cannot accurately predict and adjust the temperature in the logistics warehousing, resulting in the problem of waste of energy or deterioration of goods.
The information collection module obtains storage parameters, establishes a prediction model, generates a refrigeration estimate correction value and a refrigeration estimated time value, and simultaneously opens the refrigeration equipment of the next logistics bin to be used to ensure that the previous logistics bin is completed when the storage operation is completed, the next logistics bin is in progress. The cold chain environment has been reached.
It improves the accuracy of refrigeration management of logistics warehouses, avoids energy waste and cargo quality problems, and realizes intelligent management of cold chain logistics warehouses.
Smart Images

Figure CN117933850B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cold chain logistics, and in particular to a cold chain logistics warehousing intelligent management method and system. Background Art
[0002] Cold chain logistics refers to a special form of logistics that maintains temperature control during the logistics process. It is mainly used for the transportation, storage and distribution of temperature-sensitive products such as food, medicine, biological products, etc. The goal of cold chain logistics is to ensure that the goods are kept within a suitable temperature range throughout the supply chain to maintain their quality, safety and freshness. These goods usually need to be transported and stored under specific temperature conditions to prevent food corruption, drug failure or biological product deterioration. In the cold chain logistics process, various equipment and technologies are needed, such as temperature control equipment, such as refrigerated vehicles or cold storage, temperature sensors, data loggers, refrigeration units, insulation materials, monitoring and tracking systems, to ensure the temperature stability and traceability of goods during transportation, storage and distribution.
[0003] The technical solution pointed out in the document of the existing application publication number CN116468374A, entitled A Cold Chain Logistics Warehousing Intelligent Management System, includes: a main control module, an outbound management module, an inbound management module, an RFID recording module, a handheld terminal, a fresh-keeping control module, a warehouse database, a warehouse information storage module, and a transportation management module. The main control module is respectively connected to the outbound management module, the inbound management module, the RFID recording module, the handheld terminal, the fresh-keeping control module, the warehouse database, the warehouse information storage module, and the transportation management module. The handheld terminal is also respectively connected to the outbound management module and the inbound management module. The cold chain logistics warehousing intelligent management system provided by the present invention has the functions of inbound management, outbound management, in-warehouse refrigeration monitoring, inventory monitoring, and personnel monitoring, but it cannot accurately complete the advance adjustment of the temperature in the logistics warehouse;
[0004] There is also a patent with authorization announcement number CN112053119B, entitled A cold chain logistics warehousing intelligent management system based on big data, which points out the technical solution including: warehouse storage area division module, regional storage volume statistics module, incoming goods packaging shape parameter acquisition module, goods incoming classification module, regional remaining storage volume analysis and display module, temperature label marking collection module, temperature intelligent analysis module, early warning module and remote management module. The present invention divides the warehouse storage area and obtains the packaging shape parameters and commodity types of the incoming goods, thereby obtaining the storage area and shelf number of the incoming goods, and marks the RFID temperature tag on the surface of each commodity packaging to collect the temperature of the commodity during storage, and warns of commodities with abnormal temperature changes. It targets goods or commodities in cold chain transportation, but does not make accurate and effective adjustments to the cold chain logistics warehouse.
[0005] In combination with the above-mentioned patents and prior art, in the process of managing cold chain logistics warehousing, it is usually necessary to park the truck carrying the goods at the corresponding delivery port outside the logistics warehouse, and then move and store them manually or through transportation equipment. This part of the goods is usually packed in cartons with consistent specifications and weights, so as to facilitate storage and placement. In the process of storing the goods in the previous logistics warehouse, after the logistics warehouse is full, it is necessary to open the next logistics warehouse for cold chain storage. Since the transported goods require timely cold chain storage, if the refrigeration equipment of the next logistics warehouse is opened in advance, when the refrigeration environment in the next logistics warehouse meets the standards, the previous logistics warehouse is not full, then it is necessary to continue to maintain the operation of the refrigeration equipment of the previous logistics warehouse, thereby causing energy waste. If the refrigeration equipment of the next logistics warehouse is opened with a delay, the goods will be waiting to enter or the environment will not meet the standards after entering, and the process may cause the goods to deteriorate or be damaged. Summary of the invention
[0006] 1. Technical issues to be resolved
[0007] In view of the deficiencies in the prior art, the present invention provides a cold chain logistics warehousing intelligent management method and system. Under the premise of comprehensively considering the factors of the logistics warehouse itself and environmental factors, a refrigeration estimated correction value Re is obtained, and the preset standard time length Bs is corrected through the refrigeration estimated correction value Re to generate a logistics warehouse refrigeration estimated time length value Edo, and the required adjustment time value is obtained in combination with the predicted time. At the adjustment time, the refrigeration equipment in the next logistics warehouse to be used is synchronously started, so that at the same time when the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used completes the refrigeration treatment in the warehouse, which embodies the intelligent design of cold chain logistics warehouse management and solves the problems raised in the background technology.
[0008] (II) Technical solution
[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0010] A cold chain logistics warehousing intelligent management system, the system comprising:
[0011] The information collection module calculates and obtains storage parameters, including cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature;
[0012] The data analysis module extracts and calculates the storage time of the goods at the current moment based on the storage speed and storage distance of the goods in the storage parameters at the same moment, obtains the storage time of the goods at several moments in the historical data, and establishes a prediction model to generate a prediction curve chart that changes over time. According to the prediction curve chart, the prediction time corresponding to the estimated storage time of the goods is 0 is obtained;
[0013] The prediction and evaluation module extracts and pre-processes the cold air release rate, storage volume and ambient temperature of the logistics warehouse in the storage parameters, builds a logistics warehouse refrigeration estimation calculation model, generates a refrigeration estimation correction value Re, and obtains the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re;
[0014] The adjustment management module obtains the adjustment time value corresponding to the predicted time when the estimated refrigeration time value Edo of the logistics warehouse to be used next is reached according to the predicted time corresponding to the estimated storage time of the goods being 0. When the adjustment time value is reached, the adjustment strategy is started: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value.
[0015] Furthermore, each logistics warehouse is equipped with at least three columns of storage areas for cold chain goods, and a movable high-definition camera is installed above the material warehouse, and a virtual computing unit is installed in the high-definition camera.
[0016] Furthermore, the virtual computing unit performs edge detection and contour extraction based on the images taken by the high-definition camera using image processing technology to obtain the edge position of the goods, and performs target positioning based on the relevant feature matching method according to the shape and position characteristics of the goods, and determines the edge of the corresponding goods in the shelf facing the delivery port, and uses the line segment fitting method to generate a virtual line for the edge of the corresponding goods. Based on continuous image frames, the feature point matching method is used to calculate the moving speed of the virtual line, that is, the goods storage speed; the cut-off line position representing the delivery port is also pre-calibrated in the virtual computing unit, and the geometric distance calculation method is used to calculate the distance between the virtual line and the cut-off line. As the virtual line moves, the distance between the virtual line and the cut-off line is continuously updated, and this distance is the goods storage distance.
[0017] Furthermore, refrigeration equipment is installed in the corresponding logistics warehouse, and the refrigeration equipment is used to release cold air. The maximum speed of cold air release is the cold air release speed of the logistics warehouse; the length, width and height of the inner wall of the corresponding logistics warehouse are obtained, and the length is multiplied by the width and the height is multiplied to obtain the storage volume of the corresponding logistics warehouse; when the logistics warehouse is used for cold chain storage, the average meteorological temperature of the area where the logistics warehouse is located is the ambient temperature.
[0018] Furthermore, when calculating the cargo storage time at the current moment, cargo storage time = cargo storage distance ÷ cargo storage speed. Based on the cargo storage time at several moments in the historical data, a prediction model is established using the time series analysis method.
[0019] Furthermore, the process of preprocessing the cold air release rate, storage volume and ambient temperature of the logistics warehouse is: performing noise filtering and removing abnormal values on the cold air release rate, storage volume and ambient temperature of the logistics warehouse, and then performing dimensionless processing on the cold air release rate, storage volume and ambient temperature of the logistics warehouse.
[0020] Furthermore, the formula for generating the cooling estimate correction value Re is as follows:
[0021]
[0022] In the formula, Fs represents the cold air release rate of the logistics warehouse, Rj represents the storage volume, Hu represents the ambient temperature, f1, f2, and f3 are the preset proportional coefficients of the cold air release rate Fs of the logistics warehouse, the storage volume Rj, and the ambient temperature Hu, respectively, and f1>f2>f2>0, and G1 is the constant correction coefficient.
[0023] Furthermore, the formula for generating the estimated refrigeration duration value Edo of the logistics warehouse is as follows:
[0024] Edo=Re*Bs*G2
[0025] Wherein, Bs represents the preset standard duration, and G2 is the constant correction coefficient.
[0026] A cold chain logistics warehousing intelligent management method comprises the following steps:
[0027] S1. Calculate and obtain storage parameters, and the storage parameters include cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature;
[0028] S2. Calculate the storage time of the goods at the current moment based on the storage speed and storage distance of the goods in the storage parameters at the same moment, obtain the storage time of the goods at several moments in the historical data, establish a prediction model, generate a prediction curve chart that changes over time, and obtain the prediction time corresponding to the estimated storage time of the goods being 0 according to the prediction curve chart;
[0029] S3, extract and pre-process the cold air release speed, storage volume and ambient temperature of the logistics warehouse in the storage parameters, build a logistics warehouse refrigeration estimation calculation model, generate a refrigeration estimation correction value Re, and obtain the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re;
[0030] S4. According to the estimated refrigeration duration value Edo of the next logistics warehouse to be used, combined with the predicted time corresponding to the estimated storage time of the goods being 0, obtain the adjustment time value corresponding to the predicted time reached by the estimated refrigeration duration value Edo of the logistics warehouse. When the adjustment time value is reached, start the adjustment strategy: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value.
[0031] (III) Beneficial effects
[0032] The present invention provides a cold chain logistics warehousing intelligent management method and system, which has the following beneficial effects:
[0033] 1. Based on the virtual line formed by the edge of the goods on the shelf in the logistics warehouse toward the delivery port, combined with the design of a mobile high-definition camera and its internal virtual computing unit, by analyzing the movement process of the virtual line and the distance from the delivery port, the predicted time of completion of the current logistics warehouse storage under normal working conditions can be accurately obtained, which is convenient for managers to know the expected working time in advance, arrange subsequent work content, and facilitate management;
[0034] 2. Under the premise of comprehensively considering the factors of the logistics warehouse itself and the environmental factors, the estimated refrigeration correction value Re is obtained, and the preset standard time Bs is corrected by the estimated refrigeration correction value Re, which can further improve the accuracy of the generated logistics warehouse refrigeration estimated time value Edo, making it easier to cope with different logistics warehouses and environmental changes in management work;
[0035] 3. When the adjusted time value is reached, the refrigeration equipment in the next logistics warehouse to be used is turned on synchronously, so that the next logistics warehouse to be used can complete the refrigeration treatment in the warehouse at the same time as the previous logistics warehouse completes the storage operation, avoiding the energy waste caused by opening the next logistics warehouse in advance, and also eliminating the problem that the quality of some goods may be affected after delaying the opening of the next logistics warehouse, which reflects the intelligent design of cold chain logistics warehouse management. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 This is a schematic diagram of the modular structure of a cold chain logistics warehousing intelligent management system of the present invention;
[0037] Figure 2 It is a schematic diagram of the overall process of a cold chain logistics warehousing intelligent management method of the present invention;
[0038] Figure 3 This is a top view of the logistics warehouse structure used in the present invention. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0040] Example 1: Please refer to Figure 1 , this embodiment provides a cold chain logistics warehousing intelligent management system, the management system includes an information collection module, a data analysis module, a prediction and evaluation module and an adjustment management module, and the management system is applied to the continuous and uninterrupted cargo transportation and storage process, and the types of goods and the packaging boxes and weights of the corresponding goods are basically consistent, and the storage warehouse specifications and sizes actually used for cold chain storage of goods are consistent;
[0041] Information collection module, calculates and obtains storage parameters;
[0042] Among them, the storage parameters include cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature; each logistics warehouse is equipped with at least three rows of long storage areas for cold chain goods to be placed, and a high-definition camera that can be moved horizontally is installed above the material warehouse. At the same time, the moving trajectory of the high-definition camera enables the shooting surface of the high-definition camera to cover the entire storage area, which can be achieved by installing movable gantries on both sides of the logistics warehouse;
[0043] Cargo storage speed: The HD camera is equipped with a virtual computing unit. Based on the image captured by the HD camera, the virtual computing unit uses image processing technology to perform edge detection and contour extraction to obtain the edge position of the cargo. According to the shape and position characteristics of the cargo, the edge of the corresponding cargo in the shortest shelf facing the delivery port is determined. During this period, the image central axis transformation, gradient direction histogram or related feature matching methods can be used for target positioning. According to the edge of the cargo facing the delivery port, the corresponding virtual line is generated. The line segment fitting or polygon approximation method can be used to obtain the straight line segment to represent the virtual line. According to the continuous image frames, the moving speed of the virtual line is calculated. The optical flow method, feature point matching method or motion mode-based method can be used for calculation to obtain the real-time speed of the virtual line, that is, the required cargo storage speed, which indicates the storage progress of the cargo. The above steps are integrated and optimized to construct a complete operation mode, which can collect images, process images, generate virtual lines and calculate speed in real time, and provide corresponding data and results when needed;
[0044] It should be noted that forklifts, automatic stacking machines and some manual operations are used in the process of transportation, storage and stacking to ensure that the goods on the shelves in each storage area are stacked evenly and levelly;
[0045] Goods storage distance: In the virtual calculation unit, the position of the preset delivery port cut-off line can also be determined. The shape is a straight line segment and is distinguished from the virtual line. For example, the virtual line is a dotted line in the high-definition camera and is yellow, while the cut-off line is a solid line in the high-definition camera and is red. It can be obtained through pre-manual calibration or object detection-based methods. The distance between the virtual line and the cut-off line is calculated using a geometric distance calculation method. The geometric distance calculation methods used include Euclidean distance or Manhattan distance. As the virtual line moves, the distance between the virtual line and the cut-off line is continuously updated. This distance is the goods storage distance;
[0046] Cold air release speed of logistics warehouse: When cold chain storage is carried out for goods, refrigeration equipment will be installed in the corresponding logistics warehouse. The refrigeration equipment usually adopts large or high-power refrigerators as refrigeration equipment for cold chain storage logistics warehouses. The refrigeration equipment includes compressors, condensers, evaporators, pipes, valves and other components. When cold chain storage is actually carried out, the refrigeration equipment is used to release cold air. The maximum speed of cold air release is the cold air release speed of the logistics warehouse. At the same time, the specific value of the speed will be displayed on the refrigeration equipment. It is only necessary to use wireless communication technology to obtain the specific value on the refrigeration equipment. The wireless communication technology is 5G communication technology.
[0047] Storage volume: Indicates the storage capacity of each logistics warehouse. The length, width and height of the inner wall of any logistics warehouse are obtained by a laser rangefinder, and the required storage volume is obtained by multiplying the length by the width by the height. The storage volume also reflects the storage capacity of the corresponding logistics warehouse. The larger the storage volume, the greater the storage capacity.
[0048] Ambient temperature: When using a logistics warehouse for cold chain storage, the ambient temperature of the logistics warehouse and even the entire logistics warehouse is the required ambient temperature. The ambient temperature can be obtained in real time from the weather forecast, and the ambient temperature is the average meteorological temperature of the area. The lower the ambient temperature, the less electricity is required for cold chain storage of goods. The higher the ambient temperature, for example: when cold chain storage is carried out in summer, continuous refrigeration operations are required to prevent the temperature in the logistics warehouse from rising due to external influences, and continuous operations require more electricity.
[0049] The data analysis module extracts the cargo storage speed and cargo storage distance in the storage parameters, and calculates the cargo storage time at the current moment based on the cargo storage speed and cargo storage distance in the storage parameters at the same moment, obtains the cargo storage time at several moments in the historical data, and uses the regression analysis algorithm to establish a prediction model, generates a prediction curve chart that changes over time, and obtains the predicted time corresponding to the estimated cargo storage time of 0 according to the prediction curve chart;
[0050] Among them, when calculating the cargo storage time at the current moment, cargo storage time = cargo storage distance ÷ cargo storage speed. As time changes, the real-time cargo storage time also changes continuously, that is, the cargo storage time at several moments in the historical data. According to this part of the data, not only the regression analysis algorithm can be used, but also the time series analysis or machine learning method can be used to establish a prediction model to generate a prediction curve chart, which is convenient for subsequent prediction of the time through the existing data. In the obtained prediction curve chart, according to the change of the curvature of the curve, by analyzing the trend of the curve, the predicted time required when the cargo storage time is 0 can be estimated;
[0051] It should be noted that in actual application, factors such as the accuracy, robustness and real-time performance of the prediction model also need to be considered. The prediction model can be tuned and verified to improve the quality and reliability of the prediction results.
[0052] Specifically, based on the virtual line formed by the edge of the goods in the shortest shelf in the logistics warehouse toward the delivery port, and combined with the design of a mobile high-definition camera and its internal virtual computing unit, by analyzing the movement process of the virtual line and the distance from the delivery port, the predicted time when the current logistics warehouse storage is completed under normal working conditions can be accurately obtained, which is convenient for managers to know the expected working time in advance, arrange subsequent work content, and facilitate management.
[0053] The prediction and evaluation module extracts the cold air release rate, storage volume and ambient temperature of the logistics warehouse from the storage parameters, pre-processes the cold air release rate, storage volume and ambient temperature of the logistics warehouse, builds a logistics warehouse refrigeration estimation calculation model, generates a refrigeration estimation correction value Re, and obtains the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re;
[0054] Among them, the process of pre-processing the cold air release speed, storage volume and ambient temperature of the logistics warehouse is: filtering the noise and removing abnormal values of the cold air release speed, storage volume and ambient temperature of the logistics warehouse, and then performing dimensionless processing on the cold air release speed, storage volume and ambient temperature of the logistics warehouse;
[0055] The purpose of noise filtering and outlier removal is to remove interference items and abnormal data in the data to improve the quality and accuracy of the data. The moving average filtering method is used to smooth the data and reduce the impact of noise by calculating the average value of the data over a period of time. The median filtering method can also be used to use the median in the data window to replace the current data point, which can effectively remove noise. To remove outliers, the filter method can be used to use filters to identify and remove abnormal data. Commonly used filters include Kalman filters and spurious Kalman filters. The purpose of dimensionless processing is to eliminate the dimensional differences between data to facilitate subsequent calculation operations;
[0056] The formula for generating the estimated cooling correction value Re is as follows:
[0057]
[0058] In the formula, Fs represents the cold air release rate of the logistics warehouse, Rj represents the storage volume, Hu represents the ambient temperature, f1, f2, and f3 are the preset proportional coefficients of the cold air release rate Fs of the logistics warehouse, the storage volume Rj, and the ambient temperature Hu, respectively, and f1>f2>f2>0, G1 is a constant correction coefficient, the specific value of which can be adjusted and set by the user, or generated by the analysis function fitting, and the value range of G1 is 1 to 2;
[0059] It should be noted that the estimated refrigeration correction value Re affects the estimated refrigeration time of the subsequent logistics warehouse under normal circumstances, and the estimated refrigeration correction value Re is proportional to the estimated refrigeration time. When the cold air release speed Fs is higher, the logistics warehouse is fully covered by cold air or the environment in the logistics warehouse reaches the preset standard. The time is shorter, so the cold air release speed Fs is inversely proportional to the estimated refrigeration correction value Re; when the storage volume Rj is larger, the logistics warehouse is fully covered by cold air or the environment in the logistics warehouse reaches the preset standard. The longer it takes, the storage volume Rj is proportional to the estimated refrigeration correction value Re; when the ambient temperature Hu is higher, due to the lower temperature required for cold chain storage, the greater the temperature difference formed. To a certain extent, it takes more time to maintain and cool down, so the ambient temperature Hu is proportional to the estimated refrigeration correction value Re;
[0060] The size of the coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preset proportional coefficients initially set by technicians in this field for each set of sample data. It can also be said that it is preset according to actual conditions, as long as it does not affect the proportional relationship between the parameter and the quantized value. The preset proportional coefficients and constant correction coefficients described in other formulas also adopt the above description;
[0061] The formula for generating the estimated refrigeration duration value Edo for the logistics warehouse is as follows:
[0062] Edo=Re*Bs*G2
[0063] In the formula, Bs represents the preset standard duration, which is set according to historical experience. G2 is a constant correction coefficient, whose specific value can be adjusted and set by the user, or generated by analytical function fitting, and the value range of G2 is 0-1. After the standard duration Bs is corrected by the refrigeration estimated correction value Re, it is corrected twice by the constant correction coefficient G2 to obtain the final required logistics warehouse refrigeration estimated duration value Edo, which represents the time taken for the environment in the logistics warehouse to reach the preset standard after the refrigeration equipment is turned on. G1 and G2 in the above formula both play a correction role.
[0064] Specifically, under the premise of comprehensively considering the factors of the logistics warehouse itself and the environmental factors, the refrigeration estimated correction value Re is obtained, and the preset standard time Bs is corrected by the refrigeration estimated correction value Re, which can further improve the accuracy of the generated logistics warehouse refrigeration estimated time value Edo, making it easier to cope with different logistics warehouses and environmental changes in management work.
[0065] The adjustment management module obtains the adjustment time value corresponding to the predicted time when the estimated refrigeration time value Edo of the logistics warehouse to be used next is reached according to the predicted time corresponding to the estimated storage time of the goods in the prediction curve chart when the storage time is 0, and starts the adjustment strategy when the adjustment time value is reached;
[0066] Among them, the adjustment time value reaches the adjustment time value after the estimated refrigeration time value Edo of the logistics warehouse;
[0067] The adjustment strategy is: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value; when the adjustment time value is reached, the refrigeration equipment in the next logistics warehouse to be used is turned on synchronously, so that the next logistics warehouse to be used completes the refrigeration treatment in the warehouse at the same time as the previous logistics warehouse completes the storage operation, avoiding the energy waste caused by opening the next logistics warehouse in advance, and also eliminating the problem that the quality of some goods may be affected after delaying the opening of the next logistics warehouse, which reflects the intelligent design of cold chain logistics warehouse management.
[0068] Example 2: Please refer to Figure 2 and Figure 3 Based on Example 1, this embodiment also provides a cold chain logistics warehousing intelligent management method, including the following steps:
[0069] S1. Calculate and obtain storage parameters, and the storage parameters include cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature;
[0070] S2. Calculate the storage time of the goods at the current moment based on the storage speed and storage distance of the goods in the storage parameters at the same moment, obtain the storage time of the goods at several moments in the historical data, establish a prediction model, generate a prediction curve chart that changes over time, and obtain the prediction time corresponding to the estimated storage time of the goods being 0 according to the prediction curve chart;
[0071] S3, extract and pre-process the cold air release speed, storage volume and ambient temperature of the logistics warehouse in the storage parameters, build a logistics warehouse refrigeration estimation calculation model, generate a refrigeration estimation correction value Re, and obtain the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re;
[0072] S4. According to the estimated refrigeration duration value Edo of the next logistics warehouse to be used, combined with the predicted time corresponding to the estimated storage time of the goods being 0, obtain the adjustment time value corresponding to the predicted time reached by the estimated refrigeration duration value Edo of the logistics warehouse. When the adjustment time value is reached, start the adjustment strategy: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value.
[0073] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.
[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0075] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A cold chain logistics warehousing intelligent management system, characterized in that: The system includes: The information collection module calculates and obtains storage parameters, including cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature; The data analysis module extracts and calculates the storage time of the goods at the current moment based on the storage speed and storage distance of the goods in the storage parameters at the same moment, obtains the storage time of the goods at several moments in the historical data, and establishes a prediction model to generate a prediction curve chart that changes over time. According to the prediction curve chart, the prediction time corresponding to the estimated storage time of the goods is 0 is obtained; The prediction and evaluation module extracts and pre-processes the cold air release rate, storage volume and ambient temperature of the logistics warehouse in the storage parameters, builds a logistics warehouse refrigeration estimation calculation model, generates a refrigeration estimation correction value Re, and obtains the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re; The adjustment management module obtains the adjustment time value corresponding to the predicted time when the estimated refrigeration time value Edo of the logistics warehouse to be used next is reached according to the predicted time when the estimated storage time of the goods is 0. When the adjustment time value is reached, the adjustment strategy is started: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value; The virtual computing unit uses image processing technology to perform edge detection and contour extraction based on the images taken by the high-definition camera to obtain the edge position of the goods. According to the shape and position characteristics of the goods, the target is located based on the relevant feature matching method to determine the edge of the corresponding goods in the shelf facing the delivery port. The line segment fitting method is used to generate a virtual line for the edge of the corresponding goods. According to the continuous image frames, the feature point matching method is used to calculate the moving speed of the virtual line, that is, the goods storage speed; the virtual computing unit also pre-calibrates the position of the cut-off line representing the delivery port, and uses the geometric distance calculation method to calculate the distance between the virtual line and the cut-off line. As the virtual line moves, the distance between the virtual line and the cut-off line is continuously updated, and this distance is the goods storage distance; The formula for generating the estimated cooling correction value Re is as follows: In the formula, Fs represents the cold air release rate of the logistics warehouse, Rj represents the storage volume, Hu represents the ambient temperature, f1, f2, and f3 are the preset proportional coefficients of the cold air release rate Fs of the logistics warehouse, the storage volume Rj, and the ambient temperature Hu, respectively, and f1>f2>f2>0, and G1 is a constant correction coefficient; The formula for generating the estimated refrigeration duration value Edo for the logistics warehouse is as follows: Edo=Re*Bs*G2 Wherein, Bs represents the preset standard duration, and G2 is the constant correction coefficient.
2. The cold chain logistics warehousing intelligent management system according to claim 1 is characterized by: Each logistics warehouse is equipped with at least three rows of storage areas for cold chain goods. A movable high-definition camera is installed above the material warehouse, and a virtual computing unit is installed in the high-definition camera.
3. The cold chain logistics warehousing intelligent management system according to claim 2 is characterized by: Install refrigeration equipment in the corresponding logistics warehouse, and use the refrigeration equipment to release cold air. The maximum speed of cold air release is the cold air release speed of the logistics warehouse; obtain the length, width and height of the inner wall of the corresponding logistics warehouse, and multiply the length by the width by the height, which is the storage volume of the corresponding logistics warehouse; when using the logistics warehouse for cold chain storage, the average meteorological temperature of the area where the logistics warehouse is located is the ambient temperature.
4. The cold chain logistics warehousing intelligent management system according to claim 3 is characterized by: When calculating the cargo storage time at the current moment, cargo storage time = cargo storage distance ÷ cargo storage speed. Based on the cargo storage time at several moments in the historical data, a prediction model is established using the time series analysis method.
5. The cold chain logistics warehousing intelligent management system according to claim 4 is characterized by: The process of preprocessing the cold air release rate, storage volume and ambient temperature of the logistics warehouse is: filtering the noise and removing abnormal values of the cold air release rate, storage volume and ambient temperature of the logistics warehouse, and then performing dimensionless processing on the cold air release rate, storage volume and ambient temperature of the logistics warehouse.
6. A cold chain logistics warehousing intelligent management method, using any system described in claims 1 to 5, characterized in that: The steps include: S1. Calculate and obtain storage parameters, and the storage parameters include cargo storage speed, cargo storage distance, cold air release speed of the logistics warehouse, storage volume and ambient temperature; S2. Calculate the storage time of the goods at the current moment based on the storage speed and storage distance of the goods in the storage parameters at the same moment, obtain the storage time of the goods at several moments in the historical data, establish a prediction model, generate a prediction curve chart that changes over time, and obtain the prediction time corresponding to the estimated storage time of the goods being 0 according to the prediction curve chart; S3, extract and pre-process the cold air release speed, storage volume and ambient temperature of the logistics warehouse in the storage parameters, build a logistics warehouse refrigeration estimation calculation model, generate a refrigeration estimation correction value Re, and obtain the logistics warehouse refrigeration estimation duration value Edo based on the refrigeration estimation correction value Re; S4. According to the estimated refrigeration duration value Edo of the next logistics warehouse to be used, combined with the predicted time corresponding to the estimated storage time of the goods being 0, obtain the adjustment time value corresponding to the predicted time reached by the estimated refrigeration duration value Edo of the logistics warehouse. When the adjustment time value is reached, start the adjustment strategy: before the previous logistics warehouse completes the storage operation, the next logistics warehouse to be used starts the refrigeration work at the adjustment time value.
Citation Information
Patent Citations
A Big Data-Based Intelligent Management System for Cold Chain Logistics Warehousing
CN112053119B
Cold-chain logistics storage intelligent management system
CN116468374A
Sustainable cold-chain logistics system in chilled fresh meat industry
CN111932184A
Intelligent cold chain system based on block chain
CN113298461A
Intelligent warehouse management method and system in Internet of Things environment
CN116050154A
