A multi-factory collaborative scheduling optimization method and system considering resource constraints

Abstract

The application relates to the technical field of factory scheduling, in particular to a multi-factory collaborative scheduling optimization method and system considering resource constraints. The method comprises the following steps: analyzing historical order delivery information of each factory, determining order delivery capacity values of each factory, and distributing orders of the multiple factories according to the order delivery capacity values to determine initial distribution order values of each factory; analyzing collaborative scheduling information of each factory to obtain supplementary scheduling order values and cancellation scheduling order values of each factory to other factories, wherein the collaborative scheduling information is used for representing idle order values and new order values of each factory in a current scheduling period; and based on the supplementary scheduling order values of each factory to other factories, the cancellation scheduling order values of each factory to other factories and the initial distribution order values of each factory, target distribution order values of each factory are determined. The application can improve the utilization effect of production resources of a production cluster composed of multiple factories.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of factory scheduling, in particular to a multi-factory collaborative scheduling optimization method and system considering resource constraints. BACKGROUND

[0002] Different factories producing the same product often face different resource constraints, such as differences in equipment, materials, personnel, and time dimensions. In this context, multi-factory coordinated scheduling based on resource constraints can effectively improve overall production efficiency, maximize resource utilization, and reduce waste in complex production environments. Through coordinated scheduling, the allocation of resources between factories can be reasonably balanced, avoiding situations where some factories have excess resources while others lack resources, thereby avoiding production bottlenecks or resource waste and ensuring efficient, flexible, and sustainable production.

[0003] Generally speaking, multi-factory collaborative scheduling optimization based on existing fixed orders and resource constraints first acquires key information such as resource status, order priority, and delivery period of each factory through real-time monitoring and data collection. Then, combining this information, an optimization algorithm such as genetic algorithm is used to iteratively, cross, and mutate to allocate production tasks reasonably, thereby avoiding resource waste and imbalance. Finally, through intelligent scheduling and resource constraint management, the system can significantly improve production flexibility, reduce overall operating costs, and ensure timely delivery of customer orders.

[0004] However, in real-world environments, the total order value faced by a production cluster composed of multiple factories is often changing, and existing optimization algorithms are mostly based on static predicted total order values for multi-factory production resource scheduling management, making it difficult to effectively respond to disturbances caused by order fluctuations. When faced with the addition of urgent orders, only temporary increases in production resources can be made (which requires higher costs), and when faced with the cancellation of temporary orders, only the idle production resources can be used (which will result in the sinking of the costs already invested), that is, the existing technology has poor utilization of production resources for production clusters. SUMMARY

[0005] The present application aims to provide a multi-factory collaborative scheduling optimization method and system considering resource constraints, to solve the technical problem of poor utilization of production resources for production clusters in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a multi-factory collaborative scheduling optimization method considering resource constraints, comprising:

[0007] In a plurality of factories, analyze historical order delivery information of each factory to determine the order delivery capacity value of each factory;

[0008] performing order optimization distribution on the plurality of factories based on the order delivery capability value of each factory, to determine an initial distribution order value of each factory;

[0009] analyzing collaborative scheduling information of each factory to obtain a supplementary scheduling order value and a canceling scheduling order value of each factory to other factories, wherein the collaborative scheduling information is used to represent an idle order value and a new order value of each factory in a current scheduling period;

[0010] determining a target distribution order value of each factory based on the supplementary scheduling order value of each factory to other factories, the canceling scheduling order value of each factory to other factories, and the initial distribution order value of each factory.

[0011] In an embodiment, the analyzing, in the plurality of factories, historical order delivery information of each factory to determine an order delivery capability value of each factory comprises:

[0012] In the plurality of factories, based on the historical order delivery information of each factory, obtaining an order delivery time consumption, an order delivery quantity, and an order delivery overtime value of each historical order of each factory, wherein the order delivery overtime value is a difference between an actual delivery time and a latest delivery time of the corresponding historical order;

[0013] In the plurality of factories, analyzing the order delivery time consumption, the order delivery quantity, and the order delivery overtime value of each historical order of each factory to determine the order delivery capability value of each factory.

[0014] In an embodiment, the analyzing, in the plurality of factories, the order delivery time consumption, the order delivery quantity, and the order delivery overtime value of each historical order of each factory to determine the order delivery capability value of each factory comprises:

[0015] In the plurality of factories, calculating a ratio of the order delivery time consumption and the order delivery quantity of each historical order of each factory to obtain a plurality of historical production efficiency values of each factory, wherein the plurality of historical production efficiency values of each factory correspond to a plurality of historical orders of the factory in one-to-one correspondence;

[0016] respectively performing standardization processing on the plurality of historical production efficiency values of each factory to obtain a plurality of production indexes of each factory;

[0017] respectively performing standardization processing on the plurality of order delivery overtime values of each factory to obtain a plurality of delivery indexes of each factory;

[0018] determining a plurality of energy efficiency values of each factory according to the plurality of production indexes and the plurality of delivery indexes of each factory;

[0019] In the plurality of factories, based on an order weight corresponding to each historical order of each factory, the plurality of energy efficiency values of the factory are weighted and calculated to obtain an order delivery capacity value of each factory, wherein the order weight is negatively correlated with an order time difference of the corresponding historical order, and the order time difference is a time difference between an order start time of the corresponding historical order and a current time.

[0020] In one embodiment, the order delivery timeout value is negatively correlated with the corresponding delivery index.

[0021] In one embodiment, the initial allocation order value of each factory is obtained based on a preset genetic algorithm, and the plurality of order delivery capacity values of the plurality of factories are used to calculate fitness of a population generated in an optimization solving process of the genetic algorithm.

[0022] In one embodiment, the analysis of the cooperative scheduling information of each factory obtains a supplementary scheduling order value and a cancel scheduling order value of each factory to other factories, including:

[0023] According to the cooperative scheduling information of each factory, a distance between each factory and other factories, an idle order value of each factory, and a new order value of each factory are obtained, wherein the idle order value is a difference between a maximum cancel order value and a minimum emergency order value predicted in a current scheduling period of the corresponding factory, and the new order value is a difference between a maximum emergency order value and a minimum cancel order value predicted in the current scheduling period of the corresponding factory;

[0024] According to the distance between each factory and other factories and the idle order value of each factory, a supplementary scheduling index of each factory to other factories is determined;

[0025] According to the supplementary scheduling index of each factory to other factories and the new order value of each factory, a supplementary scheduling order value of each factory to other factories is calculated;

[0026] According to the distance between each factory and other factories and the new order value of each factory, a cancel scheduling index of each factory to other factories is determined;

[0027] According to the cancel scheduling index of each factory to other factories and the idle order value of each factory, a cancel scheduling order value of each factory to other factories is calculated.

[0028] In one embodiment, the distance between the first factory and the second factory is negatively correlated with a complementary scheduling index of the first factory to the second factory, the idle order value of the first factory is positively correlated with the complementary scheduling index of the first factory to the second factory, and the complementary scheduling index of the first factory to the second factory is positively correlated with a complementary scheduling order value of the first factory to the second factory.

[0029] The distance between the first factory and the second factory is negatively correlated with a cancellation scheduling index of the first factory to the second factory, the new order value of the first factory is positively correlated with the cancellation scheduling index of the first factory to the second factory, and the cancellation scheduling index of the first factory to the second factory is positively correlated with a cancellation scheduling order value of the first factory to the second factory.

[0030] The first factory and the second factory are any two different factories in the plurality of factories.

[0031] In one embodiment, the target allocation order value of each factory is the sum of the complementary scheduling order value of the factory to other factories, the cancellation scheduling order value of the factory to other factories, and the initial allocation order value of the factory.

[0032] In a second aspect, another embodiment of the present application provides a multi-factory collaborative scheduling optimization system considering resource constraints, which comprises:

[0033] A first analysis module is configured to analyze historical order delivery information of each factory in the plurality of factories to determine an order delivery capability value of each factory.

[0034] An optimization allocation module is configured to perform order optimization allocation on the plurality of factories based on the order delivery capability value of each factory to determine an initial allocation order value of each factory.

[0035] A second analysis module is configured to analyze collaborative scheduling information of each factory to obtain a complementary scheduling order value and a cancellation scheduling order value of each factory to other factories, wherein the collaborative scheduling information is used to represent an idle order value and a new order value of each factory in a current scheduling period.

[0036] An output module is configured to determine a target allocation order value of each factory based on the complementary scheduling order value of each factory to other factories, the cancellation scheduling order value of each factory to other factories, and the initial allocation order value of each factory.

[0037] In one embodiment, the target allocation order value of each factory is the sum of the complementary scheduling order value of the factory to other factories, the cancellation scheduling order value of the factory to other factories, and the initial allocation order value of the factory.

[0038] In a third aspect, a further embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method of the first aspect.

[0039] In a fourth aspect, a further embodiment of the present application provides a computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the method of the first aspect.

[0040] The present application has the following advantages:

[0041] The present application first analyzes historical order delivery information of each factory to determine order delivery capability of each factory in historical order delivery process, and then optimizes order distribution of the multiple factories according to the order delivery capability to determine an initial distribution order value of each factory under static order demand; then further analyzes idle order value and new order value of each factory in a current scheduling period to determine a supplementary scheduling order value and a cancel scheduling order value of each factory to other factories, that is, to determine cooperative processing capability of each factory in the production cluster to fluctuating orders in actual production environment, and to calculate a target distribution order value of each factory considering inherent orders and fluctuating orders in combination with the determined initial distribution order value, so as to schedule production resources of each factory, thereby inhibiting temporary increase or idling of production resources, improving utilization effect of production resources of the production cluster composed of the multiple factories, helping the production cluster to meet actual order demand, and reducing cost overhead of the production cluster. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, a brief introduction will be given to the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0043] Figure 1 is a flowchart of a multi-factory cooperative scheduling optimization method considering resource constraints provided by an embodiment of the present application;

[0044] Figure 2 is a structural diagram of a multi-factory cooperative scheduling optimization system provided by an embodiment of the present application;

[0045] Figure 3 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the specific implementation, structure, features and effects of a resource-constrained multi-factory collaborative scheduling optimization method and system according to the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0048] The specific scheme of a resource-constrained multi-factory collaborative scheduling optimization method and system provided by the present application is described in detail below in combination with the accompanying drawings.

[0049] The present application proposes a resource-constrained multi-factory collaborative scheduling optimization method, please refer to Figure 1 which shows a schematic flowchart of a resource-constrained multi-factory collaborative scheduling optimization method provided by one embodiment of the present application, which includes the following steps:

[0050] Step S1, in a plurality of factories, analyze the historical order delivery information of each factory to determine the order delivery capacity value of each factory.

[0051] In the present application, the plurality of factories are used to produce the same product, for example: engineering parts (such as screws), daily necessities (such as towels, toothbrushes), etc.

[0052] The historical order delivery information is used to represent the relevant information of each historical order that has been delivered by the corresponding factory, such as: the start time of the corresponding historical order, the end time of the corresponding historical order, the latest delivery time of the corresponding historical order, the delivery product quantity of the corresponding historical order, etc.

[0053] The order delivery capacity value is used to represent the product production capacity of the corresponding factory. The higher the order delivery capacity value, the stronger the product production capacity of the corresponding factory (i.e. the more product quantity produced per unit time).

[0054] Specifically, the step of analyzing the historical order delivery information of each factory in a plurality of factories to determine the order delivery capacity value of each factory includes:

[0055] In the plurality of factories, based on historical order delivery information of each factory, an order delivery time consumption, an order delivery quantity and an order delivery overtime value of each historical order of each factory are obtained, wherein the order delivery overtime value is a difference between an actual delivery time and a latest delivery time of the corresponding historical order;

[0056] In the plurality of factories, the order delivery time consumption, the order delivery quantity and the order delivery overtime value of each historical order of each factory are analyzed to determine an order delivery capability value of each factory.

[0057] The order delivery time consumption is a difference between an end time of the corresponding historical order and a start time of the corresponding historical order. The order delivery quantity is a delivery product quantity of the corresponding historical order. The actual delivery time of the historical order is the end time of the corresponding historical order.

[0058] It should be understood that the order delivery overtime value can be any integer. When the order delivery overtime value is negative, it means that the actual delivery time of the corresponding historical order is earlier than the latest delivery time (which can be determined by an order contract corresponding to the historical order). Conversely, when the order delivery overtime value is positive, it means that the actual delivery time of the corresponding historical order is later than the latest delivery time (when the order delivery overtime value is 0, it means that the actual delivery time of the corresponding historical order is the latest delivery time).

[0059] In the above setting, by analyzing the order delivery time consumption and the order delivery quantity of each historical order of each factory, the production capability of each factory in each historical order is determined. It should be understood that the shorter the total time consumption of the factory in completing the historical order and the more the product quantity delivered, the stronger the production capability of the factory in the corresponding historical order. Correspondingly, the smaller the order delivery overtime value of the factory in completing the historical order, the stronger the delivery deadline management capability of the factory in the corresponding historical order.

[0060] Based on the above setting, the order delivery capability of the factory is comprehensively judged from the product production efficiency and the deadline management of the historical order. Starting from the actual completion of the completed historical order, statistical interference caused by differences in production resource allocation of different factories can be excluded as much as possible (that is, from the dimensions of the number of devices, the number of personnel, the area of the factory building, etc. to evaluate the production capability of the factory, it is difficult to avoid the omission of related factors affecting the production capability, and starting from the order completion, the production capability of the factory is inversely inferred from the order completion result, which can avoid the above omission problem as much as possible and ensure the accurate evaluation of the production capability of the factory). The actual order delivery capability of each factory is quickly and accurately quantified.

[0061] Further, the order delivery capability value of each factory is determined by analyzing the order delivery time consumption, order delivery quantity and order delivery overtime value of each historical order of each factory in the plurality of factories, comprising:

[0062] The ratio of the order delivery time consumption and the order delivery quantity of each historical order of each factory is calculated to obtain a plurality of historical production efficiency values of each factory, wherein the plurality of historical production efficiency values of each factory correspond to the plurality of historical orders of the factory one by one.

[0063] The plurality of historical production efficiency values of each factory are respectively standardized to obtain a plurality of production indexes of each factory.

[0064] The plurality of order delivery overtime values of each factory are respectively standardized to obtain a plurality of delivery indexes of each factory.

[0065] The plurality of energy efficiency values of each factory are determined according to the plurality of production indexes and the plurality of delivery indexes of each factory.

[0066] The plurality of energy efficiency values of each factory are weighted calculated based on the order weight corresponding to each historical order of each factory to obtain the order delivery capability value of each factory, wherein the order weight is negatively correlated with the order time difference of the corresponding historical order, and the order time difference is the time difference between the order start time of the corresponding historical order and the current time.

[0067] The historical production efficiency value can be understood as the number of products that can be produced by the corresponding factory per unit time during the completion of the corresponding historical order.

[0068] The concept of order weight is introduced to adapt to the changing production resource allocation of the factory, that is, the historical order closer to the current time reflects the production capacity of the factory.

[0069] In an example, the plurality of historical orders of each factory can be arranged in order of order start time, and the first historical order is the historical order with the earliest order start time in the plurality of historical orders of the corresponding factory (the earlier the order start time, the smaller the corresponding serial number). Then the ratio of the serial number corresponding to each historical order to the total number of serial numbers is determined as the order weight of each historical order, and the total number of serial numbers is the sum of the serial numbers of the plurality of historical orders of the corresponding factory.

[0070] In some embodiments, the order delivery overtime value is negatively correlated with the corresponding delivery index.

[0071] For example, the jth delivery index in the plurality of delivery indexes of the A th factory in the plurality of factories may be expressed as:

[0072]

[0073] wherein exp represents an exponential function with the natural constant e as the base, the max function is used to output the larger function input of the two function inputs, represents the order delivery overtime value of the historical order corresponding to the jth delivery index of the A th factory, is an adjustment coefficient (used to adjust the calculation proportion of the delivery index when the order delivery overtime value is greater than 0), and the value of k can be set to 2 based on experience.

[0074] Exemplarily, the ith production index of the A th factory in the plurality of factories may be expressed as:

[0075]

[0076] wherein, represents the end time of the ith historical order of the A th factory, represents the start time of the ith historical order of the A th factory, represents the order delivery amount of the ith historical order of the A th factory, represents the standard production efficiency value corresponding to the A th factory, wherein the standard production efficiency corresponding to the A th factory is the average of the plurality of historical production efficiency values of the plurality of historical orders of the A th factory.

[0077] In one example, the order delivery capacity value of the A th factory in the plurality of factories may be expressed as:

[0078]

[0079] wherein, represents the total number of historical orders included in the A th factory, represents the order weight corresponding to the ith historical order, and it is to be noted that the smaller the value of i, the earlier the order start time of the corresponding historical order.

[0080] Step S2, based on the order delivery capacity value of each factory, the plurality of factories are optimally distributed, and the initial distribution order value of each factory is determined.

[0081] wherein the initial distribution order value of each factory is obtained based on a preset genetic algorithm, and the plurality of order delivery capacity values of the plurality of factories are used to calculate the fitness of the population generated in the optimization solving process of the genetic algorithm.

[0082] In the present application, the genetic algorithm will iterate the population, in this process, each population represents a factory order distribution strategy, the fitness of each population is calculated by summing a plurality of sub-fitnesses (corresponding to a plurality of factories) which are modified by the order delivery capacity value of the corresponding factory, and the sub-fitness is calculated based on the order value of the corresponding factory under the corresponding population.

[0083] Specifically, the fitness of the Qth population in the population iteration process Can be expressed as:

[0084]

[0085] Wherein, Indicates the total number of factories, Indicates the sub-fitness of the A th factory in the Q th population.

[0086] Exemplarily, the process of the above population iteration can be:

[0087] Randomly generate u (u can be set to 30 based on experience) factory order distribution strategies as initial populations, and calculate the fitness of each initial population according to the above fitness calculation method, then select the top 10% of the initial populations with higher fitness as the "parents", and randomly mutate the selected "parents" through single-point crossover, and repeat the above fitness calculation, parent selection and random mutation process until the fitness of the population increases by less than or equal to 1%, then determine the population with the highest fitness from the remaining populations as the target population, and determine the initial allocation order value of each factory (i.e. the number of products to be produced by each factory in the current scheduling period) according to the factory order distribution strategy indicated by the target population.

[0088] It should be noted that in the above population iteration, the total order value corresponding to the factory order distribution strategy indicated by each population always remains the same, which can be understood as the sum of the amount of products to be produced by each factory in the current scheduling period (determined according to the order contract signed by the factory).

[0089] In application, the length of the scheduling period can be adaptively adjusted based on actual needs, for example, set to 7 days or 15 days.

[0090] Step S3, analyze the collaborative scheduling information of each factory to obtain the complementary scheduling order value and the cancellation scheduling order value of each factory to other factories.

[0091] Wherein, the collaborative scheduling information is used to represent the idle order value and the new order value of each factory in the current scheduling period.

[0092] The above supplementary scheduling order value can be understood as follows: when the newly added product quantity indicated by the emergency order of other factories increases sharply (for example, when the product is in high demand), each factory can share the product quantity of other factories.

[0093] The above cancel scheduling order value can be understood as follows: when the newly added product quantity indicated by the emergency order of the factory itself increases sharply, each factory needs to share the product quantity of other factories.

[0094] Specifically, the analysis of the cooperative scheduling information of each factory obtains the supplementary scheduling order value and the cancel scheduling order value of each factory to other factories, including:

[0095] According to the cooperative scheduling information of each factory, the distance between each factory and other factories, the idle order value of each factory, and the newly added order value of each factory are obtained, wherein the idle order value is the difference between the predicted maximum cancel order value and the predicted minimum emergency order value of the corresponding factory in the current scheduling period, and the newly added order value is the difference between the predicted maximum emergency order value and the predicted minimum cancel order value of the corresponding factory in the current scheduling period.

[0096] According to the distance between each factory and other factories and the idle order value of each factory, the supplementary scheduling index of each factory to other factories is determined.

[0097] According to the supplementary scheduling index of each factory to other factories and the newly added order value of each factory, the supplementary scheduling order value of each factory to other factories is calculated.

[0098] According to the distance between each factory and other factories and the newly added order value of each factory, the cancel scheduling index of each factory to other factories is determined.

[0099] According to the cancel scheduling index of each factory to other factories and the idle order value of each factory, the cancel scheduling order value of each factory to other factories is calculated.

[0100] It should be noted that the above maximum emergency order value is the maximum value of the temporarily newly added product quantity predicted for the corresponding factory in the current scheduling period, and similarly, the minimum emergency order value is the minimum value of the temporarily newly added product quantity predicted for the corresponding factory in the current scheduling period.

[0101] Correspondingly, the above maximum cancel order value is the maximum value of the product quantity predicted for the corresponding factory to cancel production in the current scheduling period, and similarly, the minimum emergency order value is the minimum value of the product quantity predicted for the corresponding factory to cancel production in the current scheduling period.

[0102] In one example, a number of historical cancellation order values (amount of products cancelled in the corresponding historical scheduling period) and a number of historical emergency order values (amount of products temporarily added in the corresponding historical scheduling period) of each factory in a number of historical scheduling periods (such as the previous 100 scheduling periods) before the current scheduling period can be collected, and then the average of the top 10% of order values (order values arranged in descending order) in the number of historical cancellation order values is determined as the maximum cancellation order value of the corresponding factory in the current scheduling period, the average of the bottom 10% of order values is determined as the minimum cancellation order value of the corresponding factory in the current scheduling period, the average of the top 10% of order values (order values arranged in descending order) in the number of historical emergency order values is determined as the maximum emergency order value of the corresponding factory in the current scheduling period, and the average of the bottom 10% of order values is determined as the minimum emergency order value of the corresponding factory in the current scheduling period.

[0103] In the above setting, through the calculation of the supplementary scheduling order value and the cancellation scheduling order value, the change of the order value of each factory due to the fluctuation of product demand in the actual production environment can be quantitatively represented, and the real production demand of each factory can be more effectively met in cooperation with the aforementioned determined initial allocation order value, so that the production resources of each factory can be fully used.

[0104] The distance between the first factory and the second factory is negatively correlated with the supplementary scheduling index of the first factory to the second factory, the idle order value of the first factory is positively correlated with the supplementary scheduling index of the first factory to the second factory, and the supplementary scheduling index of the first factory to the second factory is positively correlated with the supplementary scheduling order value of the first factory to the second factory.

[0105] The distance between the first factory and the second factory is negatively correlated with the cancellation scheduling index of the first factory to the second factory, the new order value of the first factory is positively correlated with the cancellation scheduling index of the first factory to the second factory, and the cancellation scheduling index of the first factory to the second factory is positively correlated with the cancellation scheduling order value of the first factory to the second factory.

[0106] The first factory and the second factory are any two different factories in the plurality of factories.

[0107] As described above, the closer the distance between different factories, the stronger the ability of different factories to coordinate with each other to better bear the fluctuation of product demand (such as temporarily adding products to be produced or cancelling product production), and the greater the idle order value of the factory, the stronger the ability of the factory to help other factories share the temporarily added products to be produced, and the greater the new order value of the factory, the stronger the need for other factories to help the factory share the temporarily added products to be produced.

[0108] In the present application, the maximum cancelled order value of each factory is greater than the minimum emergency order value of the factory, and the maximum cancelled emergency value of each factory is greater than the minimum cancelled order value of the factory.

[0109] Exemplarily, the supplementary scheduling index of the Bth factory in the plurality of factories to the Ath factory in the scheduling process may be expressed as:

[0110]

[0111] wherein, represents the maximum cancelled order value predicted by the Bth factory in the current scheduling period, represents the minimum emergency order value predicted by the Bth factory in the current scheduling period, and f represents a maximum-minimum value normalization function, represents the distance between the Bth factory and the Ath factory.

[0112] The cancelled scheduling index of the Bth factory in the plurality of factories to the Ath factory in the scheduling process may be expressed as:

[0113]

[0114] wherein, represents the minimum cancelled order value predicted by the Bth factory in the current scheduling period, represents the maximum emergency order value predicted by the Bth factory in the current scheduling period.

[0115] The supplementary scheduling order value of the Bth factory in the plurality of factories to the Ath factory in the scheduling process may be expressed as:

[0116]

[0117] wherein, represents the minimum cancelled order value predicted by the Ath factory in the current scheduling period, represents the maximum emergency order value predicted by the Ath factory in the current scheduling period.

[0118] The cancelled scheduling order value of the Bth factory in the plurality of factories to the Ath factory in the scheduling process may be expressed as:

[0119]

[0120] wherein, represents the maximum cancelled order value predicted by the Ath factory in the current scheduling period, represents the minimum emergency order value predicted by the A th factory in the current scheduling period.

[0121] Step S4, based on the supplementary scheduling order value of each factory to other factories, the cancel scheduling order value of each factory to other factories and the initial allocation order value of each factory, determines the target allocation order value of each factory.

[0122] Specifically, the target allocation order value of each factory is the sum of the supplementary scheduling order value of the factory to other factories, the cancel scheduling order value of the factory to other factories and the initial allocation order value of the factory.

[0123] Exemplarily, the target allocation order value of the B th factory in the plurality of factories may be represented as:

[0124]

[0125] wherein, represents the supplementary scheduling order value of the B th factory.

[0126] It should be noted that after determining the target allocation order value of each factory based on the above process, each factory performs scheduling of production resources (such as starting of production equipment, personnel scheduling, etc.) in the current scheduling period according to the determined target allocation order value, and in the current scheduling period, if an emergency order or a cancel order occurs, the existing production resources of the plurality of factories are preferentially coordinated, and after there is no production resource in the plurality of factories that can be coordinated, new production resources are started to reduce the management burden and additional cost overhead caused by temporary starting of production resources as much as possible.

[0127] In general, the present application first analyzes the historical order delivery information of each factory to determine the order delivery capability of each factory in the historical order delivery process, and then optimizes the order allocation of the plurality of factories according to the same to determine the initial allocation order value of each factory under static order demand; further analyze the idle order value and the new order value of each factory in the current scheduling period to determine the supplementary scheduling order value and the cancel scheduling order value of each factory to other factories, i.e. to determine the cooperative processing capability of each factory in the production cluster in the face of fluctuating orders in the actual production environment, and calculate the target allocation order value of each factory considering inherent orders and fluctuating orders in combination with the determined initial allocation order value, and perform production resource scheduling of each factory according to the same, which can inhibit the temporary increase or idling of production resources, improve the utilization effect of production resources of the production cluster composed of the plurality of factories, help the production cluster to meet the actual order demand while reducing the cost overhead of the production cluster.

[0128] The application provides a multi-factory collaborative scheduling optimization system considering resource constraints Figure 2 which shows a structure diagram of a multi-factory collaborative scheduling optimization system 200 considering resource constraints provided by an embodiment of the application, and the system comprises:

[0129] a first analysis module 201, configured to analyze historical order delivery information of each factory in a plurality of factories, and determine an order delivery capability value of each factory;

[0130] an optimization distribution module 202, configured to perform order optimization distribution on the plurality of factories based on the order delivery capability value of each factory, and determine an initial distribution order value of each factory;

[0131] a second analysis module 203, configured to analyze collaborative scheduling information of each factory, and obtain a supplementary scheduling order value of each factory to other factories and a cancel scheduling order value of each factory to other factories, wherein the collaborative scheduling information is used to represent an idle order value and a new order value of each factory in a current scheduling period;

[0132] an output module 204, configured to determine a target distribution order value of each factory based on the supplementary scheduling order value of each factory to other factories, the cancel scheduling order value of each factory to other factories and the initial distribution order value of each factory.

[0133] In an embodiment, the target distribution order value of each factory is a sum of the supplementary scheduling order value of the factory to other factories, the cancel scheduling order value of the factory to other factories and the initial distribution order value of the factory.

[0134] It should be noted that the system provided in the above embodiment is only used as an example for the division of the above functional modules, and in actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the above described functions. In addition, the multi-factory collaborative scheduling optimization system considering resource constraints and the multi-factory collaborative scheduling optimization method provided in the above embodiment belong to the same concept, and the specific implementation process is described in detail in the method embodiment, which will not be repeated here.

[0135] The embodiment of the application further provides an electronic device. Please refer to Figure 3 The electronic device can include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and executable on the processor 301.

[0136] When the program 3021 is executed by the processor 301, it can implement Figure 1 any step in the corresponding method embodiment and achieve the same beneficial effects, which will not be repeated here.

[0137] Those skilled in the art can understand that all or part of the steps of the method of the above-mentioned embodiments can be completed by program instructions related to hardware, and the programs can be stored in a readable medium.

[0138] The embodiment of the present application further provides a readable storage medium, which stores a computer program, and the computer program can realize any step in the method embodiment of the present application and achieve the same technical effects when executed by a processor. Figure 1 The embodiment of the present application further provides a readable storage medium, which stores a computer program, and the computer program can realize any step in the method embodiment of the present application and achieve the same technical effects when executed by a processor.

[0139] The computer readable storage medium of the embodiment of the present application can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0140] The computer readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, in which a computer readable program code is borne. Such a propagated data signal can take on multiple forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a storage medium and that can transmit, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device.

[0141] The program code contained in the storage medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0142] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0143] The embodiments of the present application further provide a computer program product, which, when running on a computer, enables the computer to perform the above related steps to realize the method for collaborative scheduling optimization of multiple plants considering resource constraints provided by the above embodiments.

[0144] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0145] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

Claims

1. A method for multi-plant collaborative scheduling optimization considering resource constraints, characterized in that, The method comprises: In a plurality of factories, analyzing historical order delivery information of each factory to determine an order delivery capability value of each factory; Based on the order delivery capability value of each factory, order optimization distribution is performed on the plurality of factories to determine an initial allocation order value of each factory; Analyzing collaborative scheduling information of each factory to obtain a supplementary scheduling order value and a cancel scheduling order value of each factory to other factories, wherein the collaborative scheduling information is used to represent an idle order value and a new order value of each factory in a current scheduling period; Based on the supplementary scheduling order value of each factory to other factories, the cancel scheduling order value of each factory to other factories, and the initial allocation order value of each factory, a target allocation order value of each factory is determined; The analysis of the collaborative scheduling information of each factory to obtain the supplementary scheduling order value and the cancel scheduling order value of each factory to other factories comprises: According to the collaborative scheduling information of each factory, the distance between each factory and other factories, the idle order value of each factory, and the new order value of each factory are obtained, wherein the idle order value is the difference between the predicted maximum cancel order value and the predicted minimum urgent order value of the corresponding factory in the current scheduling period, and the new order value is the difference between the predicted maximum urgent order value and the predicted minimum cancel order value of the corresponding factory in the current scheduling period; According to the distance between each factory and other factories and the idle order value of each factory, a supplementary scheduling index of each factory to other factories is determined; According to the supplementary scheduling index of each factory to other factories and the new order value of each factory, a supplementary scheduling order value of each factory to other factories is calculated; According to the distance between each factory and other factories and the new order value of each factory, a cancel scheduling index of each factory to other factories is determined; According to the cancel scheduling index of each factory to other factories and the idle order value of each factory, a cancel scheduling order value of each factory to other factories is calculated.

2. The method of claim 1, wherein, The analysis of the historical order delivery information of each factory in a plurality of factories to determine the order delivery capability value of each factory comprises: In a plurality of factories, based on the historical order delivery information of each factory, the order delivery time, order delivery quantity, and order delivery overtime value of each historical order of each factory are obtained, wherein the order delivery overtime value is the difference between the actual delivery time and the latest delivery time of the corresponding historical order; In a plurality of factories, the order delivery time, order delivery quantity, and order delivery overtime value of each historical order of each factory are analyzed to determine the order delivery capability value of each factory. 3.The method of claim 2, wherein, The analysis of the historical order delivery information of each factory in a plurality of factories to determine the order delivery capability value of each factory comprises: In the plurality of factories, a ratio of an order delivery time consumption to an order delivery amount of each historical order of each factory is calculated to obtain a plurality of historical production efficiency values of each factory, wherein the plurality of historical production efficiency values of each factory correspond to a plurality of historical orders of the factory in one-to-one manner; The plurality of historical production efficiency values of each factory are respectively standardized to obtain a plurality of production indexes of each factory; The plurality of order delivery overtime values of each factory are respectively standardized to obtain a plurality of delivery indexes of each factory; Based on the plurality of production indexes and the plurality of delivery indexes of each factory, a plurality of energy efficiency values of each factory are determined; In the plurality of factories, based on an order weight corresponding to each historical order of each factory, the plurality of energy efficiency values of the factory are weighted to obtain an order delivery capacity value of each factory, wherein the order weight is negatively correlated with an order time difference of the corresponding historical order, and the order time difference is a time difference between an order start time of the corresponding historical order and a current time.

4. The method of claim 3, wherein, The order delivery overtime value is negatively correlated with the corresponding delivery index.

5. The method of claim 1, wherein, The initial allocation order value of each factory is obtained based on a preset genetic algorithm, and the plurality of order delivery capacity values of the plurality of factories are used to calculate fitness of a population generated in an optimization solving process of the genetic algorithm.

6. The method of claim 1, wherein, A distance between the first factory and the second factory is negatively correlated with a supplementary scheduling index of the first factory to the second factory, an idle order value of the first factory is positively correlated with the supplementary scheduling index of the first factory to the second factory, and the supplementary scheduling index of the first factory to the second factory is positively correlated with a supplementary scheduling order value of the first factory to the second factory. A distance between the first factory and the second factory is negatively correlated with a cancellation scheduling index of the first factory to the second factory, an added order value of the first factory is positively correlated with the cancellation scheduling index of the first factory to the second factory, and the cancellation scheduling index of the first factory to the second factory is positively correlated with a cancellation scheduling order value of the first factory to the second factory. The first factory and the second factory are any two different factories in the plurality of factories.

7. The method of claim 1, wherein, The target allocation order value of each factory is a sum of the supplementary scheduling order value of the factory to other factories, the cancellation scheduling order value of the factory to other factories, and the initial allocation order value of the factory.

8. A multi-plant collaborative scheduling optimization system considering resource constraints, characterized in that, The system comprises: A first analysis module is configured to analyze historical order delivery information of each factory in the plurality of factories to determine an order delivery capacity value of each factory; An optimization allocation module is configured to perform order optimization allocation on the plurality of factories based on the order delivery capacity value of each factory to determine an initial allocation order value of each factory; A second analysis module is configured to analyze cooperative scheduling information of each factory to obtain a supplementary scheduling order value and a cancellation scheduling order value of each factory to other factories, wherein the cooperative scheduling information is used to represent an idle order value and an added order value of each factory in a current scheduling period. The output module is configured to determine a target allocation order value of each factory based on a supplement scheduling order value of each factory to other factories, a cancel scheduling order value of each factory to other factories, and an initial allocation order value of each factory. The step of analyzing the collaborative scheduling information of each factory to obtain the supplement scheduling order value and the cancel scheduling order value of each factory to other factories comprises: According to the collaborative scheduling information of each factory, the distance between each factory and other factories, the idle order value of each factory, and the new order value of each factory are obtained, wherein the idle order value is the difference between the predicted maximum cancel order value and the predicted minimum urgent order value of the corresponding factory in the current scheduling period, and the new order value is the difference between the predicted maximum urgent order value and the predicted minimum cancel order value of the corresponding factory in the current scheduling period; According to the distance between each factory and other factories and the idle order value of each factory, a supplement scheduling index of each factory to other factories is determined; According to the supplement scheduling index of each factory to other factories and the new order value of each factory, a supplement scheduling order value of each factory to other factories is calculated; According to the distance between each factory and other factories and the new order value of each factory, a cancel scheduling index of each factory to other factories is determined; According to the cancel scheduling index of each factory to other factories and the idle order value of each factory, a cancel scheduling order value of each factory to other factories is calculated. 9.The system of claim 8, wherein, The target allocation order value of each factory is the sum of the supplement scheduling order value of the factory to other factories, the cancel scheduling order value of the factory to other factories, and the initial allocation order value of the factory.

Images