Digital storage and logistics management system based on AI intelligent scheduling technology
By adopting AI intelligent scheduling technology in the digital warehousing and logistics management system, and using machine learning models to optimize material location and early warning modules, the problem of resource waste and efficiency reduction caused by unreasonable material stacking is solved, and more efficient logistics management and energy are achieved Consume utilization.
Patent Information
- Application Number
- CN202411437479.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-10-15
AI Technical Summary
The unreasonable material stacking location in the existing digital warehousing and logistics management systems leads to waste of resources, increasing transport distance, path complexity and energy consumption, and reducing logistics efficiency.
Using a digital warehousing and logistics management system based on AI intelligent scheduling technology, through warehousing and logistics data acquisition, status analysis, location analysis and optimization modules, machine learning models are used to build theoretical energy consumption and efficiency prediction models, optimize material position, and realize material position adaptation. Maximize the degree and monitor and adjust it in real time through the early warning module.
It improves the efficiency and energy consumption utilization rate of warehousing and logistics, provides scientific basis for optimization, timely warnings and measures are taken to avoid potential problems, and ensure the smooth operation of warehousing and logistics.
Smart Images

Figure CN118966976A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of digital warehouse management technology, and more specifically, to a digital warehouse and logistics management system based on AI intelligent scheduling technology. Background Art
[0002] The digital warehousing and logistics management system based on AI intelligent scheduling technology is of great significance in improving supply chain competitiveness, reducing enterprise costs, enhancing flexibility and optimizing resource utilization. With the continuous advancement of technology and the expansion of application scenarios, the system will play an important role in more fields and promote the intelligent upgrading and transformation of the logistics industry.
[0003] However, it still has many shortcomings in actual use. For example, in the prior art, there is the problem of unreasonable material stacking position leading to waste of resources. Specifically, in digital warehousing, the location layout of materials has a direct impact on logistics efficiency and energy consumption. Unreasonable layout will lead to increased transportation distance, complicated transportation path, uneconomical transportation height and other problems, thereby increasing energy consumption and reducing efficiency. Summary of the invention
[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a digital warehousing and logistics management system based on AI intelligent scheduling technology to solve the problems raised in the above-mentioned background technology.
[0005] To achieve the above objectives, the present invention provides the following technical solutions: a digital warehousing and logistics management system based on AI intelligent scheduling technology, comprising: The warehousing logistics data collection module is used to collect material information and logistics execution information in digital warehousing. The material information at least includes the current location coordinates of the material; the logistics execution information at least includes the logistics execution instructions and the corresponding actual logistics efficiency and actual material energy consumption; The warehouse logistics status analysis module is used to obtain the theoretical efficiency and theoretical energy consumption under ideal scenarios; build a theoretical energy consumption prediction model and a theoretical efficiency prediction model based on machine learning, input logistics execution instructions into the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, and output the theoretical efficiency and theoretical energy consumption; The storage location analysis module is used to obtain the maximum value and current value of the material location fitness, build the material location fitness function according to the material's theoretical efficiency and theoretical energy consumption, take the highest material location fitness as the goal, output the updated location coordinates of each material type through the optimization algorithm, and obtain the maximum value of the material location fitness when all materials are in the updated location coordinates; The storage location optimization module optimizes the material location based on the updated location coordinates.
[0006] Preferably, the actual logistics efficiency refers to the amount of work completed per unit time in the actual warehousing and logistics process, and the actual material energy consumption refers to the actual energy consumed in the actual warehousing and logistics process; the theoretical efficiency refers to the amount of work completed per unit time under the ideal operating scenario; the theoretical energy consumption refers to the theoretical energy consumed under the ideal operating scenario.
[0007] Preferably, the process of obtaining the theoretical efficiency and theoretical energy consumption includes the following steps: Step S11: Collect historical operation data under an ideal operation scenario, where the historical operation data includes historical energy consumption, efficiency data, and logistics execution instructions; the logistics execution instructions include at least: transport distance, transport path, transport weight, transport height, and speed; Step S12: Mark the target variables in the historical operation data, where the target variables are the target energy consumption and the target efficiency, and divide the historical operation data into a training set and a validation set according to the preset; Step S13: Select a machine learning model to predict energy consumption and efficiency, input logistics execution instructions into the machine learning model, output prediction variables, and the prediction variables include predicted energy consumption and predicted efficiency; initialize machine learning model parameters, and define loss functions and optimization algorithms; Step S14, training and verification: Use the training set data to train the machine learning model, and in each iteration, adjust the parameters according to the value of the loss function; monitor the change of the loss value during the training process to prevent overfitting or underfitting; use the verification set data to evaluate the performance of the model, and adjust the model structure and parameters according to the verification results until satisfactory performance is achieved; Step S15, obtain the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, deploy and apply the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, input the logistics execution instructions into the theoretical energy consumption prediction model and theoretical efficiency prediction model respectively, and output the theoretical energy consumption and theoretical efficiency.
[0008] Preferably, the theoretical energy consumption prediction model includes: Based on the current position coordinates of each material type, the horizontal distance and handling height difference corresponding to transporting the material to the destination are obtained; Obtain the cumulative transport weight w after completing the execution instruction, the cumulative transport distance d of the material on the horizontal plane, and the cumulative transport height difference h of the material in the vertical direction, and calculate the theoretical energy consumption E through the following formula:
[0009] Among them, α1 and α2 are the energy consumption coefficients corresponding to horizontal and vertical transportation, respectively, which are obtained through experiments or historical data fitting; α3 represents the fixed energy consumption item, which indicates other fixed energy consumption that may be generated during the transportation process in addition to distance and height.
[0010] Preferably, the effective time period is obtained by flexibly adjusting the length and division method of the effective time period according to the production plan and order situation. If the warehouse mainly serves the production of a single order, the time required for a single order from order placement to completion is used as the effective time period; if the warehouse is closely related to the production line, the time required for the production line to complete a complete production cycle (such as from raw material input to finished product output) is used as the effective time period.
[0011] Preferably, the maximum value of the material position adaptability is obtained by: Assume that there are n material types in the digital warehouse, and i represents the sequential number of the material type; Collect or predict the logistics execution instructions of each material within the effective time period, input them into the theoretical energy consumption prediction model and the theoretical efficiency prediction model, output the theoretical efficiency and theoretical energy consumption of each material within the effective time period, and record the theoretical efficiency and theoretical energy consumption of the i-th material as Xi and Ei respectively; The material position fitness function is constructed according to the theoretical efficiency and theoretical energy consumption of the material. The highest material position fitness is taken as the goal. Through the optimization algorithm, the updated position coordinates of each material type are obtained to maximize the value of the material position fitness and output the maximum value of the material position fitness.
[0012] Preferably, the material position fitness function is obtained as follows: The workload of the i-th material per unit time is recorded as the theoretical efficiency and recorded as Xi; the theoretical energy consumed by the i-th material per unit workload is recorded as Ei; the cumulative transportation distance of the i-th material is recorded as di; the transportation time of the i-th material from the current position to the target position is recorded as ti, and a material position fitness function Fs is constructed to satisfy the following formula:
[0013] Among them, β1 and β2 are weight coefficients, which are used to adjust the influence of transportation distance and transportation time on fitness.
[0014] Preferably, the digital warehousing and logistics management system also includes a warehousing logistics early warning module, which is used to obtain the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate, and monitor them in real time; when the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate exceed the corresponding thresholds, a warning is issued and measures are taken.
[0015] Preferably, the warehousing logistics early warning module includes a logistics efficiency abnormality early warning unit, a logistics energy consumption abnormality early warning unit and a material location abnormality early warning unit. The logistics efficiency abnormal warning unit is calculated by formula The logistics efficiency loss rate Sa is calculated, where X0 represents the actual logistics efficiency; The abnormal early warning unit for logistics energy consumption is implemented by the formula The logistics energy consumption loss rate Sb is calculated, where E0 represents the actual material energy consumption; The material position abnormality warning unit is provided by formula The material position fitness loss rate Sc is calculated, where Max_Fs represents the maximum value of the material position fitness and Fs_A represents the current value of the material position fitness; When the logistics efficiency loss rate, logistics energy consumption loss rate, and material location adaptability loss rate exceed the corresponding thresholds, an early warning is issued and measures are taken, including: When the logistics efficiency loss rate exceeds the corresponding threshold TH A , indicating that there are logistics bottlenecks or equipment failures, which require timely attention and processing, and measures should be taken to improve logistics efficiency; When the logistics energy loss rate exceeds the corresponding threshold TH B , analyze the causes of abnormal energy consumption and take measures to reduce logistics energy consumption; When the material position fitness loss rate exceeds the corresponding threshold TH C , prompting that the material placement is unreasonable, and making adjustments based on the updated position coordinates of each material type.
[0016] Preferably, the digital warehousing and logistics management system also includes: The warehouse logistics improvement demand assessment module is used to assess the improvement demand of digital warehouse logistics, and jointly analyze the logistics efficiency loss rate, logistics energy consumption loss rate and material location adaptability loss rate to obtain the warehouse logistics improvement demand coefficient; By formula The improved demand factor Gx is calculated, where TH A , TH B , TH C They represent the corresponding thresholds of logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate respectively; Divide the warehouse logistics into several areas according to the functional areas; prioritize the warehouse logistics improvement needs in different areas according to the improvement demand coefficient; Areas with higher improvement demand coefficients should be given priority in management resources for improvement.
[0017] Technical effects and advantages of the present invention: The digital warehousing and logistics management system based on AI intelligent scheduling technology provided by the present invention utilizes machine learning models to construct theoretical energy consumption prediction models and theoretical efficiency prediction models, and can accurately predict the theoretical efficiency and theoretical energy consumption in ideal scenarios based on historical data, providing a scientific basis for the optimization of warehousing and logistics; at the same time, the updated position coordinates of each material type are output through the optimization algorithm to achieve the optimized layout of material locations, further improving the efficiency of warehousing and logistics; a warehousing and logistics early warning module is provided to monitor the logistics efficiency, logistics energy consumption and material location fitness function in real time. When these indicators exceed the preset thresholds, an early warning is issued in time and corresponding treatment measures are prompted, effectively avoiding the occurrence of potential problems, ensuring the smooth operation of warehousing and logistics, and solving the problem of lack of supervision and early warning of the efficiency and energy consumption of warehousing and logistics in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a structural block diagram of the digital warehousing and logistics management system of the present invention.
[0019] Figure 2 It is a schematic diagram of the structural block diagram of the warehousing logistics early warning module of the present invention. DETAILED DESCRIPTION
[0020] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein; on the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0021] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.
[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.
[0023] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.
[0024] Example 1, see Figure 1 The digital warehousing and logistics management system structure diagram is provided in the embodiment of the present invention. A digital warehousing and logistics management system based on AI intelligent scheduling technology includes: The warehousing logistics data collection module is used to collect material information and logistics execution information in digital warehousing. The material information at least includes the current location coordinates of the material; the logistics execution information at least includes the logistics execution instructions and the corresponding actual logistics efficiency and actual material energy consumption; The warehouse logistics status analysis module is used to obtain the theoretical efficiency and theoretical energy consumption under ideal scenarios; build a theoretical energy consumption prediction model and a theoretical efficiency prediction model based on machine learning, input logistics execution instructions into the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, and output the theoretical efficiency and theoretical energy consumption; The storage location analysis module is used to obtain the maximum value and current value of the material location fitness, build the material location fitness function according to the material's theoretical efficiency and theoretical energy consumption, take the highest material location fitness as the goal, output the updated location coordinates of each material type through the optimization algorithm, and obtain the maximum value of the material location fitness when all materials are in the updated location coordinates; The storage location optimization module optimizes the material location based on the updated location coordinates.
[0025] What needs to be further explained in the embodiments of the present invention is that the actual logistics efficiency refers to the amount of work completed per unit time in the actual warehousing and logistics process, and the actual material energy consumption refers to the actual energy consumed in the actual warehousing and logistics process; the theoretical efficiency refers to the amount of work completed per unit time under the ideal operating scenario; the theoretical energy consumption refers to the theoretical energy consumed under the ideal operating scenario, and the workload refers to the total amount of all operations required to complete the logistics execution instructions in the warehousing and logistics process, such as the tonnage of materials transported and the number of deliveries. In the embodiments of the present invention, the actual logistics efficiency refers to the weighted sum of the delivery distance completed per unit time and the delivery weight per unit time in the actual warehousing and logistics process.
[0026] It needs to be further explained in the embodiment of the present invention that the process of obtaining the theoretical efficiency and the theoretical energy consumption includes the following steps: Step S11: Collect historical operation data of material handling of sufficient quantity and quality under an ideal operation scenario, where the historical operation data includes historical energy consumption, efficiency data, and logistics execution instructions; the logistics execution instructions at least include: handling distance, handling path, handling weight, handling height, and speed; Step S12: Mark the target variables in the historical operation data, where the target variables are the target energy consumption and the target efficiency, and divide the historical operation data into a training set and a validation set according to the preset; Explanation: Historical energy consumption and efficiency data are close to or represent theoretical optimal values in some way; in the embodiment of the present invention, historical energy consumption and efficiency data under an ideal operation scenario are recorded as target energy consumption and target efficiency; Step S13: Select a machine learning model to predict energy consumption and efficiency, input logistics execution instructions into the machine learning model, output prediction variables, and the prediction variables include predicted energy consumption and predicted efficiency; initialize machine learning model parameters, and define loss functions and optimization algorithms; The machine learning model is any one of linear regression, random forest regression, and gradient boosting tree; In one possible embodiment, the loss function is the mean square error of the target variable and the prediction variable; the optimization algorithm is gradient descent; Step S14, training and verification: Use the training set data to train the machine learning model, and in each iteration, adjust the parameters according to the value of the loss function; monitor the change of the loss value during the training process to prevent overfitting or underfitting; use the verification set data to evaluate the performance of the model, such as calculating the prediction error and root mean square error indicators, and adjust the model structure and parameters according to the verification results until satisfactory performance is achieved; Step S15, obtain the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, deploy and apply the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, input the logistics execution instructions into the theoretical energy consumption prediction model and theoretical efficiency prediction model respectively, and output the theoretical energy consumption and theoretical efficiency.
[0027] It needs to be further explained in the embodiment of the present invention that the specific method for obtaining the theoretical energy consumption and the theoretical efficiency is not limited in the embodiment of the present invention. In a possible embodiment, the theoretical energy consumption prediction model includes: Based on the current position coordinates of each material type, the horizontal distance and handling height difference corresponding to transporting the material to the destination are obtained; Obtain the cumulative transport weight w after completing the execution instruction, the cumulative transport distance d of the material on the horizontal plane, and the cumulative transport height difference h of the material in the vertical direction, and calculate the theoretical energy consumption E through the following formula: Among them, α1 and α2 are the energy consumption coefficients corresponding to horizontal and vertical transportation, respectively, which are obtained through experiments or historical data fitting; α3 represents the fixed energy consumption item, which indicates other fixed energy consumption that may be generated during the transportation process in addition to distance and height, such as starting and stopping.
[0028] It needs to be further explained in the embodiment of the present invention that the maximum value of the material position adaptability is obtained in the following manner: Assume that there are n material types in the digital warehouse, and i represents the sequential number of the material type; each material type is placed in a non-repeated position coordinate; Collect or predict the logistics execution instructions of each material within the effective time period, input them into the theoretical energy consumption prediction model and the theoretical efficiency prediction model, output the theoretical efficiency and theoretical energy consumption of each material within the effective time period, and record the theoretical efficiency and theoretical energy consumption of the i-th material as Xi and Ei respectively; The material position fitness function is constructed according to the theoretical efficiency and theoretical energy consumption of the material. The highest material position fitness is taken as the goal. Through the optimization algorithm, the updated position coordinates of each material type are obtained to maximize the value of the material position fitness and output the maximum value of the material position fitness.
[0029] It needs to be further explained in the embodiment of the present invention that the embodiment of the present invention obtains the updated position coordinates of each material type through an optimization algorithm, and the optimization algorithm is any one of an ant colony algorithm, a genetic algorithm, and a particle swarm optimization algorithm. The present invention does not specifically limit this. For ease of understanding, the algorithm steps for obtaining the updated position coordinates of each material type using the ant colony algorithm are listed as follows: Step S21, algorithm initialization: setting ant colony parameters, such as the number of ants, pheromone evaporation rate, and pheromone intensity, and randomly generating the initial ant position, that is, the initial position coordinates of the material; Step S22, constructing a solution: each ant selects the next position, i.e., the new position coordinates of the material, according to the current position and surrounding environment, such as pheromone intensity and distance from the entrance and exit, until all ants complete a round of movement; Explanation: Based on the pheromone intensity at the current location, the distance to the entrance and exit, and other possible heuristic information, such as avoiding obstacles and considering the convenience of material handling, the decision-making process of ants may involve probabilistic selection, that is, calculating the selection probability of each optional path according to the pheromone concentration and other factors, and then randomly selecting a path to move; Step S23, calculating fitness: constructing corresponding logistics execution instructions according to the newly generated material position coordinates; inputting the logistics execution instructions into the theoretical energy consumption prediction model and the theoretical efficiency prediction model respectively, and outputting the theoretical energy consumption and theoretical efficiency; inputting the theoretical energy consumption and theoretical efficiency into the material position fitness function, and outputting the corresponding material position fitness; Step S24, updating pheromones: updating the pheromone intensity on the path according to the quality of the solution constructed by the ants, that is, the material position fitness; Step S25, iteration: repeat steps S2-S4 until the preset number of iterations is reached or the fitness function value no longer changes significantly, and select the solution with the highest material position fitness as the optimal solution, that is, the optimal position coordinates of the material.
[0030] Explanation: The algorithm searches in the solution space in an iterative manner. Each iteration calculates the corresponding fitness value based on the current position coordinates and adjusts the position coordinates based on the fitness value. After multiple iterations, the algorithm converges to a solution whose corresponding fitness value is the highest among all possible solutions (or is close enough to the highest value to meet certain stopping criteria). The fitness function is used to evaluate the quality of the solution (i.e., the material position coordinates). The fitness function aims to achieve a balance between logistics resource consumption and efficiency.
[0031] Explanation: The embodiment of the present invention does not limit the specific form of the material position fitness function Fs, and it only needs to reflect the ratio or trade-off relationship between theoretical efficiency and theoretical energy consumption; For example, by the formula The material position adaptability is calculated; For example, the workload of the i-th material per unit time is recorded as the theoretical efficiency and recorded as Xi; the theoretical energy consumed by the i-th material per unit workload is recorded as Ei; the cumulative transportation distance of the i-th material is recorded as di; the transportation time of the i-th material from the current position to the target position is recorded as ti, and a material position fitness function Fs is constructed to satisfy the following formula: Among them, β1 and β2 are weight coefficients, which are used to adjust the influence of transportation distance and transportation time on fitness. The square of transportation distance is used to emphasize the quadratic effect of distance on energy consumption and efficiency (that is, when the distance increases, the effect is more significant); the exponential function of transportation time is used to simulate the situation where efficiency decreases rapidly when transportation time increases.
[0032] Explanation: Updating the material location coordinates will cause changes in the transport distance, transport path, and transport height in the logistics execution instructions. By adjusting the material location coordinates, the output value of the location fitness function will change.
[0033] What needs to be further explained in the embodiments of the present invention is that the method for obtaining the effective time period is to flexibly adjust the length and division method of the effective time period according to the production plan and order situation, and flexibly adjust the length of the effective time period; if the warehouse mainly serves the production of a single order, the time required for a single order from order placement to completion is used as the effective time period; if the warehouse is closely related to the production line, the time required for the production line to complete a complete production cycle (such as from raw material input to finished product output) is used as the effective time period; select a fixed time period (such as one day, one week or one month) as the effective time period.
[0034] In summary, the digital warehousing and logistics management system based on AI intelligent scheduling technology provided by the embodiment of the present invention can automatically collect, analyze and process warehousing and logistics data by integrating AI intelligent scheduling technology, realize intelligent and automated management of material handling, and greatly improve the efficiency and energy utilization rate of warehousing and logistics, specifically including the following aspects: The theoretical energy consumption prediction model and theoretical efficiency prediction model are constructed using machine learning models. Based on historical data, the theoretical efficiency and theoretical energy consumption in ideal scenarios can be accurately predicted, providing a scientific basis for the optimization of warehousing and logistics. At the same time, the updated position coordinates of each material type are output through the optimization algorithm to achieve the optimal layout of material locations, further improving the efficiency of warehousing and logistics. Example 2, see Figure 2 The structural block diagram of the warehousing and logistics early warning module of the embodiment of the present invention is different from the embodiment 1 in that a digital warehousing and logistics management system based on AI intelligent scheduling technology is provided, which also includes: The warehousing logistics early warning module is used to obtain the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate, and monitor them in real time; when the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate exceed the corresponding threshold, an early warning is issued and measures are taken; the warehousing logistics early warning module includes a logistics efficiency abnormality early warning unit, a logistics energy consumption abnormality early warning unit and a material location abnormality early warning unit. The logistics efficiency abnormal warning unit is calculated by formula The logistics efficiency loss rate Sa is calculated, where X0 represents the actual logistics efficiency; The abnormal early warning unit for logistics energy consumption is implemented by the formula The logistics energy consumption loss rate Sb is calculated, where E0 represents the actual material energy consumption; The material position abnormality warning unit is provided by formula The material position fitness loss rate Sc is calculated, where Max_Fs represents the maximum value of the material position fitness and Fs_A represents the current value of the material position fitness; When the logistics efficiency loss rate, logistics energy consumption loss rate, and material location adaptability loss rate exceed the corresponding thresholds, an early warning is issued and measures are taken, including: When the logistics efficiency loss rate exceeds the corresponding threshold TH A , indicating that there is a logistics bottleneck or equipment failure, which requires timely attention and processing, and taking measures such as checking equipment status, adjusting personnel allocation, optimizing route planning, etc. to improve logistics efficiency; When the logistics energy loss rate exceeds the corresponding threshold TH B , analyze the causes of abnormal energy consumption and take measures, such as replacing high-efficiency equipment, optimizing transportation routes, and strengthening energy management, to reduce logistics energy consumption; When the material position fitness loss rate exceeds the corresponding threshold TH C , prompting that the material placement is unreasonable, and making adjustments based on the updated position coordinates of each material type.
[0035] In a possible embodiment, the digital warehousing and logistics management system based on AI intelligent scheduling technology also includes: The warehouse logistics improvement demand assessment module is used to assess the improvement demand of digital warehouse logistics, and jointly analyze the logistics efficiency loss rate, logistics energy consumption loss rate and material location adaptability loss rate to obtain the warehouse logistics improvement demand coefficient; By formula The improved demand factor Gx is calculated, where TH A , TH B , TH C They represent the corresponding thresholds of logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate respectively; Divide the warehouse logistics into several areas according to the functional areas; prioritize the warehouse logistics improvement needs in different areas according to the improvement demand coefficient; Areas with higher improvement demand coefficients should be given priority in management resources for improvement.
[0036] The embodiment of the present invention does not specifically limit the type of management resources. The management resources may be any one or a combination of equipment maintenance resources, path planning and adjustment resources, and monitoring resources.
[0037] In summary, the warehousing logistics early warning module can monitor logistics efficiency, logistics energy consumption and material location fitness function in real time. When these indicators exceed the preset thresholds, it will issue early warnings in time and prompt corresponding treatment measures to effectively avoid the occurrence of potential problems and ensure the smooth operation of warehousing logistics. The management resource allocation strategy based on the improved demand coefficient can dynamically adjust the allocation strategy to adapt to new demands and environmental changes, reduce the waste and idleness of management resources, and maintain the efficient operation of the system.
[0038] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A digital warehousing and logistics management system based on AI intelligent scheduling technology, characterized by: include: The warehousing logistics data collection module is used to collect material information and logistics execution information in digital warehousing. The material information at least includes the current location coordinates of the material; the logistics execution information at least includes the logistics execution instructions and the corresponding actual logistics efficiency and actual material energy consumption; Warehousing logistics status analysis module, used to obtain theoretical efficiency and theoretical energy consumption under ideal scenarios; Build a theoretical energy consumption prediction model and a theoretical efficiency prediction model based on machine learning, input the logistics execution instructions into the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, and output the theoretical efficiency and theoretical energy consumption; The storage location analysis module is used to obtain the maximum value and current value of the material location fitness, build the material location fitness function according to the material's theoretical efficiency and theoretical energy consumption, take the highest material location fitness as the goal, output the updated location coordinates of each material type through the optimization algorithm, and obtain the maximum value of the material location fitness when all materials are in the updated location coordinates; The storage location optimization module optimizes the material location based on the updated location coordinates.
2. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 1 is characterized in that: The actual logistics efficiency refers to the amount of work completed per unit time in the actual warehousing and logistics process, and the actual material energy consumption refers to the actual energy consumed in the actual warehousing and logistics process; the theoretical efficiency refers to the amount of work completed per unit time under the ideal operating scenario; the theoretical energy consumption refers to the theoretical energy consumed under the ideal operating scenario.
3. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 2 is characterized in that: The process of obtaining the theoretical efficiency and theoretical energy consumption includes the following steps: Step S11: Collect historical operation data under an ideal operation scenario, where the historical operation data includes historical energy consumption, efficiency data, and logistics execution instructions; The logistics execution instructions at least include: transport distance, transport path, transport weight, transport height, and speed; Step S12: Mark the target variables in the historical operation data, where the target variables are the target energy consumption and the target efficiency, and divide the historical operation data into a training set and a validation set according to the preset; Step S13: Select a machine learning model to predict energy consumption and efficiency, input logistics execution instructions into the machine learning model, output prediction variables, and the prediction variables include predicted energy consumption and predicted efficiency; initialize machine learning model parameters, and define loss functions and optimization algorithms; Step S14, training and verification: Use the training set data to train the machine learning model, and in each iteration, adjust the parameters according to the value of the loss function; monitor the change of the loss value during the training process to prevent overfitting or underfitting; use the verification set data to evaluate the performance of the model, and adjust the model structure and parameters according to the verification results; Step S15, obtain the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, deploy and apply the trained theoretical energy consumption prediction model and theoretical efficiency prediction model, input the logistics execution instructions into the theoretical energy consumption prediction model and theoretical efficiency prediction model respectively, and output the theoretical energy consumption and theoretical efficiency.
4. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 3 is characterized in that: The theoretical energy consumption prediction model is: Based on the current position coordinates of each material type, the horizontal distance and handling height difference corresponding to transporting the material to the destination are obtained; Obtain the cumulative transport weight w after completing the execution instruction, the cumulative transport distance d of the material on the horizontal plane, and the cumulative transport height difference h of the material in the vertical direction, and calculate the theoretical energy consumption E through the following formula: Among them, α1 and α2 are the energy consumption coefficients corresponding to horizontal and vertical transportation, respectively, which are obtained through experiments or historical data fitting; α3 represents the fixed energy consumption item, which indicates other fixed energy consumption that may be generated during the transportation process in addition to distance and height.
5. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 1 is characterized in that: The method for obtaining the maximum value of the material position fitness is as follows: Assume that there are n material types in the digital warehouse, and i represents the sequential number of the material type; Collect or predict the logistics execution instructions of each material within the effective time period, input them into the theoretical energy consumption prediction model and the theoretical efficiency prediction model, output the theoretical efficiency and theoretical energy consumption of each material within the effective time period, and record the theoretical efficiency and theoretical energy consumption of the i-th material as Xi and Ei respectively; The material position fitness function is constructed according to the theoretical efficiency and theoretical energy consumption of the material. The highest material position fitness is taken as the goal. Through the optimization algorithm, the updated position coordinates of each material type are obtained to maximize the value of the material position fitness and output the maximum value of the material position fitness.
6. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 5 is characterized in that: The method for obtaining the effective time period is to flexibly adjust the length and division method of the effective time period according to the production plan and order situation. If the warehouse mainly serves the production of a single order, the time required for a single order from order placement to completion is used as the effective time period; if the warehouse is closely related to the production line, the time required for the production line to complete a complete production cycle is used as the effective time period.
7. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 1 is characterized in that: The material position fitness function is obtained as follows: The workload of the i-th material per unit time is recorded as the theoretical efficiency and recorded as Xi; the theoretical energy consumed by the i-th material per unit workload is recorded as Ei; the cumulative transportation distance of the i-th material is recorded as di; the transportation time of the i-th material from the current position to the target position is recorded as ti, and a material position fitness function Fs is constructed to satisfy the following formula: Among them, β1 and β2 are weight coefficients, which are used to adjust the influence of transportation distance and transportation time on fitness.
8. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 1 is characterized in that: The digital warehousing and logistics management system also includes a warehousing logistics early warning module, which is used to obtain the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate, and monitor them in real time; when the logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate exceed the corresponding thresholds, a warning is issued and measures are taken.
9. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 8 is characterized in that: The storage logistics early warning module includes a logistics efficiency abnormality early warning unit, a logistics energy consumption abnormality early warning unit and a material location abnormality early warning unit. The logistics efficiency abnormal warning unit is calculated by formula The logistics efficiency loss rate Sa is calculated, where X0 represents the actual logistics efficiency; The abnormal early warning unit for logistics energy consumption is implemented by the formula The logistics energy consumption loss rate Sb is calculated, where E0 represents the actual material energy consumption; The material position abnormality warning unit is provided by formula The material position fitness loss rate Sc is calculated, where Max_Fs represents the maximum value of the material position fitness and Fs_A represents the current value of the material position fitness; When the logistics efficiency loss rate, logistics energy consumption loss rate, and material location adaptability loss rate exceed the corresponding thresholds, an early warning is issued and measures are taken, including: When the logistics efficiency loss rate exceeds the corresponding threshold TH A , indicating that there are logistics bottlenecks or equipment failures, which require timely attention and processing, and measures should be taken to improve logistics efficiency; When the logistics energy loss rate exceeds the corresponding threshold TH B , analyze the causes of abnormal energy consumption and take measures to reduce logistics energy consumption; When the material position fitness loss rate exceeds the corresponding threshold TH C , prompting that the material placement is unreasonable, and making adjustments based on the updated position coordinates of each material type.
10. The digital warehousing and logistics management system based on AI intelligent scheduling technology according to claim 8 is characterized in that: The digital warehousing and logistics management system also includes: The warehouse logistics improvement demand assessment module is used to assess the improvement demand of digital warehouse logistics, and jointly analyze the logistics efficiency loss rate, logistics energy consumption loss rate and material location adaptability loss rate to obtain the warehouse logistics improvement demand coefficient; By formula The improved demand factor Gx is calculated, where TH A , TH B , TH C They represent the corresponding thresholds of logistics efficiency loss rate, logistics energy consumption loss rate and material location fitness loss rate respectively; Divide the warehouse logistics into several areas according to the functional areas; prioritize the warehouse logistics improvement needs in different areas according to the improvement demand coefficient; Areas with higher improvement demand coefficients should be given priority in management resources for improvement.
Citation Information
Patent Citations
Intelligent storage layout method based on intelligent data analysis and algorithm optimization
CN116934220A
Intelligent management and control method and system for material transportation of hydraulic power plant
CN117217642A
KR20240137406A
Cited By
Logistics and warehousing system optimization method based on multi-agent system
CN119273122A
MES system-based intelligent storage area management and control method and system
CN120181748A
A manufacturing warehouse inventory and logistics transportation intelligent linkage management method and system
CN122759931A
