Intelligent scheduling method and system for factory production under multi-objective conditions

Abstract

The present invention discloses a method and system for intelligent scheduling of factory production under multi-objective conditions, and relates to the technical field of scheduling optimization, including: obtaining order information of product production, predicting the order addition in the current production cycle, and obtaining predicted order addition information; optimizing the order production schedule, and obtaining an optimized order production schedule set; performing secondary optimization of the optimized order production schedule within the optimized order production schedule set according to the predicted order addition information, and obtaining the optimal order production schedule, wherein the order addition allocation probability of multiple devices within the optimized order production schedule is obtained, and the order addition production quality analysis and order addition operation load analysis are performed in combination with the predicted order addition information, and secondary optimization is performed; and the optimal order production schedule is used for production. The present invention solves the technical problem that the prior art is difficult to effectively balance production quality and equipment load, and achieves the technical effects of improving production quality, reducing equipment load, and reasonably allocating order addition tasks.

Description

Technical Field

[0001] The present invention relates to the field of scheduling optimization technology, and in particular to a method and system for intelligent scheduling of factory production under multi-objective conditions. Background Art

[0002] In existing factory production management, production scheduling methods are usually guided by a single goal, such as maximizing production efficiency or minimizing production costs. However, this single-goal-oriented scheduling method often ignores the operating status and health of the equipment, causing the equipment to be in a state of high load or unbalanced load for a long time. This mode of operation not only reduces the service life of the equipment, but may also cause equipment failures, affecting production continuity and order delivery quality. At the same time, with the dynamic changes in market demand, the demand for additional orders is gradually increasing. The existing scheduling method lacks flexibility in handling additional order tasks, and it is difficult to adjust resource allocation in a timely manner, further exacerbating the imbalance between production quality and equipment load. Summary of the invention

[0003] The present application provides a method and system for intelligent scheduling of factory production under multi-objective conditions, which is used to solve the technical problem that the existing technology is difficult to effectively balance production quality and equipment load.

[0004] In view of the above problems, the present application provides a method and system for intelligent factory production scheduling under multi-objective conditions.

[0005] In a first aspect of the present application, a method for intelligent scheduling of factory production under multi-objective conditions is provided, the method comprising:

[0006] Obtain the order information of the products produced in the current production cycle of the factory, combine it with the production order information in the previous production cycle, make an order forecast for the current production cycle, and obtain the predicted order information; collect the equipment feature information of multiple equipment in the factory, combine it with the order information, optimize the order production schedule, and obtain an optimized order production schedule set, wherein the optimization is performed with the purpose of improving the order production quality and reducing the operating load of the multiple equipment; according to the predicted order information, perform secondary optimization of the optimized order production schedule in the optimized order production schedule set to obtain the optimal order production schedule, wherein the order allocation probability of the multiple equipment in the optimized order production schedule is obtained, and the order production quality analysis and order operation load analysis are performed in combination with the predicted order information, and secondary optimization is performed; adopt the optimal order production schedule to carry out production.

[0007] A second aspect of the present application provides a factory production intelligent scheduling system under multi-objective conditions, the system comprising:

[0008] An order addition prediction module, wherein the order addition prediction module obtains order information for product production in the current production cycle of the factory, and combines the production order information in the previous production cycle to perform order addition prediction for the current production cycle to obtain predicted order addition information; a production scheduling optimization module, wherein the production scheduling optimization module collects equipment feature information of multiple equipment in the factory, and combines the order information to optimize the order production schedule to obtain an optimized order production schedule set, wherein the optimization is performed with the purpose of improving the order production quality and reducing the operating load of the multiple equipment; a secondary optimization module, wherein the secondary optimization module performs secondary optimization of the optimized order production schedule within the optimized order production schedule set based on the predicted order addition information to obtain an optimal order production schedule, wherein the order addition allocation probability of the multiple equipment in the optimized order production schedule is obtained, and the order addition production quality analysis and order addition operating load analysis are performed in combination with the predicted order addition information, and secondary optimization is performed; a production module, wherein the production module adopts the optimal order production schedule to carry out production.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application obtains the order information of the product production in the current production cycle of the factory, combines the production order information in the previous production cycle, performs order prediction for the current production cycle, and obtains the predicted order information; collects the equipment feature information of multiple devices in the factory, combines the order information, optimizes the order production schedule, and obtains the optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of multiple devices; according to the predicted order information, performs secondary optimization of the optimized order production schedule in the optimized order production schedule set, and obtains the optimal order production schedule, wherein the order allocation probability of multiple devices in the optimized order production schedule is obtained, and the order production quality analysis and order operation load analysis are performed in combination with the predicted order information, and secondary optimization is performed; the optimal order production schedule is adopted for production. The present invention solves the technical problem that the prior art is difficult to effectively balance the production quality and equipment load, and realizes the formulation of the optimal order production schedule by predicting order information, collecting equipment feature information, combining the optimization algorithm for order scheduling and secondary optimization, and achieving the technical effect of improving production quality, reducing equipment load and reasonably allocating order tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a process flow of a factory production intelligent scheduling method under multi-objective conditions provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a factory production intelligent scheduling system under multi-objective conditions provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: order prediction module 11, production scheduling optimization module 12, secondary optimization module 13, production module 14. DETAILED DESCRIPTION

[0015] This application provides a method and system for intelligent factory production scheduling under multi-objective conditions to solve the technical problem that the existing technology is difficult to effectively balance production quality and equipment load. By predicting order information, collecting equipment feature information, and combining optimization algorithms for order scheduling and secondary optimization, the optimal order production schedule is formulated, achieving the technical effects of improving production quality, reducing equipment load and reasonably allocating order tasks.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a method for intelligent scheduling of factory production under multi-objective conditions, the method comprising:

[0019] Step S100: Obtain order information for product production in the factory's current production cycle, combine it with the production order information in the previous production cycle, make an order forecast for the current production cycle, and obtain forecast order information.

[0020] In the embodiment of the present application, firstly, the order information for product production in the current production cycle is obtained from the factory's production management system. This information refers to the detailed data of all orders that the factory needs to produce in the current production cycle, including production quantity, etc. Secondly, the production order information of the factory in the previous production cycle is obtained by querying the historical database, including product quantity, order information, etc.

[0021] Next, we combine the order information of the current production cycle with the production order information of the previous production cycle to make an order forecast. We collect sample data and train the order forecast model, input current and historical data, forecast future order demand, and obtain forecast order information.

[0022] Furthermore, in the method provided in the embodiment of the application, the order information of the product produced in the current production cycle of the factory is obtained, and the order increase prediction of the current production cycle is performed in combination with the production information in the previous production cycle to obtain the predicted order increase information, which also includes:

[0023] The number of products produced in the factory's current production cycle is obtained as order information; the number of products produced and added orders produced in the factory's previous production cycle is obtained as historical order information and historical added order information; combined with the order information, historical order information and historical added order information, an additional order forecast is made in the current production cycle to obtain the forecasted additional order information.

[0024] In an embodiment of the present application, first, the number of products produced in the current production cycle is obtained from the factory's production management system, and the number of products is used as order information. Next, the factory's historical database is queried to obtain the number of products produced and added to orders in the previous production cycle. Among them, the number of products produced in the previous production cycle is the number of products completed according to plan in the previous cycle, and the number of products produced by adding orders in the previous cycle is the amount of production tasks added due to changes in demand in the previous cycle, that is, the number of added orders. The number of products produced in the previous production cycle is used as historical order information, and the number of products produced by adding orders in the previous production cycle is used as historical order information.

[0025] Finally, the order information, historical order information and historical order addition information are input into a trained order addition prediction channel to perform order addition prediction within the current production cycle to obtain predicted order addition information.

[0026] Furthermore, in the method provided in the embodiment of the application, combining the order information, historical order information and historical order addition information, an order addition prediction within the current production cycle is performed to obtain predicted order addition information, and further includes:

[0027] According to the production data of the factory in the historical time, a sample order information set, a sample historical order information set and a sample historical add-order information set are collected, and different sample historical order information, sample historical add-order information and sample order information are collected as the sample predicted add-order information set; the sample order information set, the sample historical order information set, the sample historical add-order information set and the sample predicted add-order information set are used to train the add-order prediction channel; the order information, historical order information and historical add-order information are input into the add-order prediction channel, and the prediction output is used to obtain the predicted add-order information.

[0028] In an embodiment of the present application, firstly, based on the production data of the factory in the historical time, a sample order information set, a sample historical order information set and a sample historical order addition information set are collected. Specifically, the sample order information set, the sample historical order information set and the sample historical order addition information set are obtained by querying the factory's production management system. Among them, the sample order information set contains historical order information within a production cycle, which is the production quantity of all orders within the cycle; the sample historical order information set refers to the order quantity data in the previous production cycle corresponding to the sample order information set; the sample historical order addition information set corresponds to the order addition data in the previous production cycle of the sample order information set.

[0029] Next, by querying the factory's production management system, we obtain different sample historical order information, sample historical order addition information, and sample order addition information after the sample order information. The sample order addition information is order addition information corresponding to the sample order information set, and the collected sample order addition information set is used as the sample predicted order addition information set.

[0030] Then, the collected sample order information set, sample historical order information set, sample historical order addition information set, and the corresponding sample predicted order addition information set are used to train the order addition prediction channel through machine learning methods. Specifically, the long short-term memory network (LSTM) is used to learn the relationship between sample order information, historical order information, historical order addition information, and sample predicted order addition information, so as to establish a model that can predict future order addition demand and obtain the order addition prediction channel.

[0031] Finally, the order information, historical order information and historical order increase information of the factory's current production cycle are input into the trained order increase prediction channel. Through this prediction channel, the predicted order increase information is output based on the input historical data and the learned rules.

[0032] Step S200: Collect equipment feature information of multiple devices in the factory, combine it with the order information, optimize the order production schedule, and obtain an optimized order production schedule set, wherein the optimization is performed with the purpose of improving order production quality and reducing the operating load of the multiple devices.

[0033] In an embodiment of the present application, the device characteristic information of multiple devices in the factory, that is, the aging process coefficients of multiple devices, is first collected. Next, the maximum production quantity of each device within the production cycle is obtained as a constraint condition in the optimization process. Based on these device characteristic information and order information, the order information is first randomly assigned to each device to generate an initial order production schedule. Then, the order production schedule is optimized based on the aging process coefficient of the equipment and the production quantity of each device. The optimization effect of the production schedule is judged by calculating and analyzing the fitness of the initial order production schedule. The process continues to iterate until a convergence state is reached, and multiple order production schedules with the best fitness are output to obtain an optimized order production schedule set.

[0034] Furthermore, in the method provided in the embodiment of the application, the device feature information of multiple devices in the factory is collected, and the order production schedule is optimized in combination with the order information to obtain an optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of the multiple devices, and further includes:

[0035] Collect multiple aging process coefficients of multiple equipment in the factory as equipment feature information of the multiple equipment, wherein the aging process coefficient includes the ratio of the service life of the equipment to the maximum service life of the equipment; obtain the maximum production quantity of the multiple equipment within the production cycle as an optimization constraint; based on the optimization constraint, randomly distribute the order information to the multiple equipment to obtain a first order production schedule, wherein the first order production schedule includes multiple first production quantities of the multiple equipment; according to the multiple first production quantities and the multiple aging process coefficients, optimize with the purpose of improving the order production quality and reducing the operating load of the multiple equipment, calculate and analyze the first scheduling fitness of the first order production schedule; continue to optimize the order production schedule until convergence, output multiple order production schedules with the largest scheduling fitness, and obtain an optimized order production schedule set.

[0036] In the embodiment of the present application, the service life and maximum service life of multiple devices in the factory are first obtained from the factory's equipment management system. Then, the service life of each device is divided by the maximum service life of the device, and the calculated value is used as the aging process coefficient corresponding to each device, and the obtained multiple aging process coefficients are used as the device characteristic information of the device.

[0037] Subsequently, the maximum production quantity of multiple devices in the production cycle is obtained through the factory's equipment management system. The maximum production quantity is pre-set, and the maximum production quantity corresponding to each device is used as the optimization constraint. After the aging process coefficient and the maximum production quantity of the equipment are obtained, the order information is randomly assigned to each device according to the optimization constraint to obtain the preliminary order production schedule, that is, the first order production schedule. This schedule includes the first production quantity corresponding to each device.

[0038] Then, according to the first production quantity and aging process coefficient of each device, the first schedule fitness is calculated through the fitness function. Next, iterative optimization is performed. By using the genetic algorithm to continuously adjust the distribution of orders between devices, the fitness value of each schedule is calculated, and the schedule with the largest fitness value is selected as the optimal solution. When the fitness value reaches convergence, that is, there is no obvious improvement, the optimization process ends. Finally, the multiple order production schedules with the largest schedule fitness are output as the optimized order production schedule set.

[0039] Furthermore, in the method provided in the embodiment of the application, based on the multiple first production quantities and the multiple aging process coefficients, optimization is performed for the purpose of improving the order production quality and reducing the operating load of the multiple devices, and the first scheduling fitness of the first order production schedule is calculated and analyzed, and further includes:

[0040] The ratios of the plurality of first production quantities to the maximum production quantity are calculated to obtain a plurality of first production load coefficients; and the first scheduling fitness is calculated according to the plurality of first production load coefficients and a plurality of aging process coefficients, as shown in the following formula:

[0041] ;

[0042] Among them, SCA is the scheduling fitness, and is the quality weight and load weight, M is the number of multiple devices, is the production load factor of the i-th equipment, is the aging process coefficient of the i-th device.

[0043] In the embodiment of the present application, the first production load factor is first calculated based on the first production quantity of each device and the maximum production quantity of each device. Specifically, multiple first production load factors are obtained by dividing the first production quantity of each device by the corresponding maximum production quantity.

[0044] Next, the first scheduling fitness is calculated based on the multiple first production load coefficients and the multiple aging process coefficients. The calculation formula of the fitness function is: ; SCA is the scheduling fitness, and is the mass weight and load weight, which are preset by technical experts, M is the number of multiple devices, is the production load factor of the i-th equipment, is the aging process coefficient of the i-th device. Through the calculation of this function, the fitness of the first schedule is obtained, and its rationality is evaluated based on the preliminary order schedule. Then, using intelligent optimization algorithms such as genetic algorithms, multiple iterations are performed based on the fitness function to adjust the distribution of orders among devices. The fitness value is recalculated after each iteration, and the schedule with the highest fitness value is selected as the optimal solution. When the fitness value converges, that is, there is no obvious improvement, the optimization process ends.

[0045] Finally, multiple order production schedules with the highest fitness values ​​are output to form an optimized order production schedule set. For example, the top ten order production schedules with the highest fitness values ​​are selected to form an optimized order production schedule set.

[0046] Step S300: Based on the predicted order information, secondary optimization of the optimized order production schedule is performed within the optimized order production schedule set to obtain the optimal order production schedule, wherein the order allocation probability of the multiple devices in the optimized order production schedule is obtained, and the order production quality analysis and order operation load analysis are performed in combination with the predicted order information to perform secondary optimization.

[0047] In the embodiment of the present application, the production load coefficients in each schedule are first extracted from the set of optimized order production schedules to form multiple sets of optimized production load coefficients. Then, the set of optimized capacity redundancy coefficients is obtained by calculating the remaining capacity of each production load coefficient, that is, 1 minus the production load coefficient. In each set, the capacity redundancy ratio of each device is calculated to obtain the probability of adding orders, and the probability distribution of adding orders is constructed.

[0048] Then, according to the probability distribution of order allocation, the number of products in the predicted order information is allocated to the equipment with the highest order allocation probability, generating multiple sets of optimized production quantities for orders, thereby forming multiple optimized order production schedules. Based on these schedules, combined with the maximum production quantity of the equipment, the order production load coefficient of each equipment is calculated, and combined with the aging process coefficient, the order scheduling fitness is calculated.

[0049] Finally, the schedule with the highest fitness is output as the optimal order production schedule to complete the secondary optimization.

[0050] Furthermore, in the method provided in the embodiment of the application, according to the predicted order addition information, a secondary optimization of the optimized order production schedule is performed within the optimized order production schedule set to obtain the optimal order production schedule, and further includes:

[0051] Obtain production load coefficients of the multiple devices in multiple optimized order production schedules in the optimized order production schedule set to obtain multiple optimized production load coefficient sets; subtract the optimized production load coefficients in the multiple optimized production load coefficient sets from 1 to obtain multiple optimized capacity redundancy coefficient sets; in each optimized capacity redundancy coefficient set, calculate the ratio of each optimized capacity redundancy coefficient to the sum of multiple capacity redundancy coefficients to obtain multiple order allocation probabilities, and construct multiple order allocation probability distributions; according to the multiple order allocation probability distributions and based on the predicted order allocation information, perform secondary optimization on the multiple optimized order production schedules to obtain the optimal order production schedule.

[0052] In an embodiment of the present application, the production load coefficient of each device in each schedule is first extracted from the set of optimized order production schedules, and then the production load coefficients of the corresponding multiple devices in each optimized order production schedule are summarized to obtain multiple sets of optimized production load coefficients. Next, for each set of optimized production load coefficients, the load coefficient is subtracted from 1 to obtain a set of optimized capacity redundancy coefficients. The capacity redundancy coefficient represents the remaining capacity of the equipment, that is, the additional workload that the equipment can undertake without being overloaded, reflecting the equipment's potential ability to undertake additional orders.

[0053] After obtaining the set of optimized capacity redundancy coefficients, the probability of adding orders is further calculated. In each set of optimized capacity redundancy coefficients, the ratio of the capacity redundancy coefficient of each device to the sum of all capacity redundancy coefficients in the set is calculated to obtain the probability of adding orders for the device. These probability of adding orders constitute the probability distribution of adding orders, which indicates the probability of each device being selected to undertake the task when facing the demand for adding orders.

[0054] Then, based on the probability distribution of order addition and the predicted order addition information, secondary optimization is performed. According to the order addition probability, the number of order addition products in the predicted order addition information is allocated to the equipment with the largest order addition probability, thereby forming multiple order addition optimized production quantity sets, that is, the task allocation amount of each equipment under the order addition situation.

[0055] Finally, the order production load coefficient of each order optimization production quantity set is calculated, and the fitness of the order schedule is calculated through the fitness function based on the maximum production quantity and aging process coefficient of the equipment. Finally, the schedule with the highest order schedule fitness is selected as the optimal order production schedule.

[0056] Furthermore, in the method provided in the embodiment of the application, according to the multiple order allocation probability distributions and based on the predicted order information, the multiple optimized order production schedules are secondary optimized to obtain the optimal order production schedule, and further includes:

[0057] According to the multiple order allocation probability distributions, the order product quantity of the predicted order information is respectively allocated to the equipment with the largest order allocation probability in each order allocation probability distribution, and multiple order optimized production quantity sets are obtained as multiple order optimized order production schedules; based on the multiple order optimized production quantity sets, combined with the maximum production quantity, multiple order production load coefficient sets are calculated to obtain, and combined with the multiple aging process coefficients, multiple order scheduling fitness of the multiple order optimized order production schedules are calculated to obtain; output the optimized order production schedule corresponding to the order optimized order production schedule with the largest order scheduling fitness, and obtain the optimal order production schedule.

[0058] In the embodiment of the present application, firstly, according to the probability distribution of adding orders, the number of added orders of the predicted added order information is allocated to the equipment with the largest probability of adding orders in each probability distribution of adding orders, and multiple sets of optimized production quantities for adding orders are obtained, that is, the sets of production task quantities of each equipment under the condition of adding orders. Each set of optimized production quantities for adding orders is used as an optimized production schedule for adding orders, and multiple optimized production schedules for adding orders are obtained.

[0059] Next, based on multiple sets of optimized production quantities for additional orders, combined with the maximum production quantity of each device, the production quantity of each device is divided by the corresponding maximum production quantity through the same method as above, and multiple sets of additional order production load coefficients are calculated.

[0060] Subsequently, the fitness of each order optimization production schedule corresponding to each order optimization production schedule is obtained by calculating the fitness of each order optimization production schedule based on the calculated multiple order production load coefficient sets and the multiple aging process coefficients through the aforementioned fitness function.

[0061] Finally, the fitness values ​​of each order optimization production schedule are compared, and the optimized order production schedule corresponding to the order optimization production schedule with the largest order scheduling fitness is selected as the optimal order production schedule.

[0062] Step S400: adopt the optimal order production schedule to carry out production.

[0063] In the embodiment of the present application, the optimal order production schedule is adopted to allocate the order quantity to each device so that each device undertakes a reasonable amount of production tasks. According to the quantity allocated by the schedule, the device is started to perform production.

[0064] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0065] The present application obtains the order information of the product production in the current production cycle of the factory, combines the production order information in the previous production cycle, performs order prediction for the current production cycle, and obtains the predicted order information; collects the equipment feature information of multiple devices in the factory, combines the order information, optimizes the order production schedule, and obtains the optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of multiple devices; according to the predicted order information, performs secondary optimization of the optimized order production schedule in the optimized order production schedule set, and obtains the optimal order production schedule, wherein the order allocation probability of multiple devices in the optimized order production schedule is obtained, and the order production quality analysis and order operation load analysis are performed in combination with the predicted order information, and secondary optimization is performed; the optimal order production schedule is adopted for production. The present invention solves the technical problem that the prior art is difficult to effectively balance the production quality and equipment load, and realizes the formulation of the optimal order production schedule by predicting order information, collecting equipment feature information, combining the optimization algorithm for order scheduling and secondary optimization, and achieving the technical effect of improving production quality, reducing equipment load and reasonably allocating order tasks.

[0066] Embodiment 2 is based on the same inventive concept as the method for intelligent scheduling of factory production under multi-objective conditions in the previous embodiment. Figure 2 As shown, the present application provides a factory production intelligent scheduling system under multi-objective conditions, and the system and method embodiments in the present application are based on the same inventive concept. Among them, the system includes:

[0067] An order addition prediction module 11, the order addition prediction module 11 obtains the order information of the product production in the current production cycle of the factory, combines the production order information in the previous production cycle, performs order addition prediction in the current production cycle, and obtains the predicted order addition information; a production scheduling optimization module 12, the production scheduling optimization module 12 collects the equipment feature information of multiple equipment in the factory, combines the order information, optimizes the order production schedule, and obtains an optimized order production schedule set, wherein the optimization is performed with the purpose of improving the order production quality and reducing the operating load of the multiple equipment; a secondary optimization module 13, the secondary optimization module 13 performs secondary optimization of the optimized order production schedule in the optimized order production schedule set according to the predicted order addition information, and obtains the optimal order production schedule, wherein the order addition allocation probability of the multiple equipment in the optimized order production schedule is obtained, and the order addition production quality analysis and order addition operation load analysis are performed in combination with the predicted order addition information, and secondary optimization is performed; a production module 14, the production module 14 adopts the optimal order production schedule to carry out production.

[0068] Furthermore, the system is also used to implement the following functions:

[0069] The number of products produced in the factory's current production cycle is obtained as order information; the number of products produced and added orders produced in the factory's previous production cycle is obtained as historical order information and historical added order information; combined with the order information, historical order information and historical added order information, an additional order forecast is made in the current production cycle to obtain the forecasted additional order information.

[0070] Furthermore, the system is also used to implement the following functions:

[0071] According to the production data of the factory in the historical time, a sample order information set, a sample historical order information set and a sample historical add-order information set are collected, and different sample historical order information, sample historical add-order information and sample order information are collected as the sample predicted add-order information set; the sample order information set, the sample historical order information set, the sample historical add-order information set and the sample predicted add-order information set are used to train the add-order prediction channel; the order information, historical order information and historical add-order information are input into the add-order prediction channel, and the prediction output is used to obtain the predicted add-order information.

[0072] Furthermore, the system is also used to implement the following functions:

[0073] Collect multiple aging process coefficients of multiple equipment in the factory as equipment feature information of the multiple equipment, wherein the aging process coefficient includes the ratio of the service life of the equipment to the maximum service life of the equipment; obtain the maximum production quantity of the multiple equipment within the production cycle as an optimization constraint; based on the optimization constraint, randomly distribute the order information to the multiple equipment to obtain a first order production schedule, wherein the first order production schedule includes multiple first production quantities of the multiple equipment; according to the multiple first production quantities and the multiple aging process coefficients, optimize with the purpose of improving the order production quality and reducing the operating load of the multiple equipment, calculate and analyze the first scheduling fitness of the first order production schedule; continue to optimize the order production schedule until convergence, output multiple order production schedules with the largest scheduling fitness, and obtain an optimized order production schedule set.

[0074] Furthermore, the system is also used to implement the following functions:

[0075] The ratios of the plurality of first production quantities to the maximum production quantity are calculated to obtain a plurality of first production load coefficients; and the first scheduling fitness is calculated according to the plurality of first production load coefficients and a plurality of aging process coefficients, as shown in the following formula:

[0076] ;

[0077] Among them, SCA is the scheduling fitness, and is the quality weight and load weight, M is the number of multiple devices, is the production load factor of the i-th equipment, is the aging process coefficient of the i-th device.

[0078] Furthermore, the system is also used to implement the following functions:

[0079] Obtain production load coefficients of the multiple devices in multiple optimized order production schedules in the optimized order production schedule set to obtain multiple optimized production load coefficient sets; subtract the optimized production load coefficients in the multiple optimized production load coefficient sets from 1 to obtain multiple optimized capacity redundancy coefficient sets; in each optimized capacity redundancy coefficient set, calculate the ratio of each optimized capacity redundancy coefficient to the sum of multiple capacity redundancy coefficients to obtain multiple order allocation probabilities, and construct multiple order allocation probability distributions; according to the multiple order allocation probability distributions and based on the predicted order allocation information, perform secondary optimization on the multiple optimized order production schedules to obtain the optimal order production schedule.

[0080] Furthermore, the system is also used to implement the following functions:

[0081] According to the multiple order allocation probability distributions, the order product quantity of the predicted order information is respectively allocated to the equipment with the largest order allocation probability in each order allocation probability distribution, and multiple order optimized production quantity sets are obtained as multiple order optimized order production schedules; based on the multiple order optimized production quantity sets, combined with the maximum production quantity, multiple order production load coefficient sets are calculated to obtain, and combined with the multiple aging process coefficients, multiple order scheduling fitness of the multiple order optimized order production schedules are calculated to obtain; output the optimized order production schedule corresponding to the order optimized order production schedule with the largest order scheduling fitness, and obtain the optimal order production schedule.

[0082] 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. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0084] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The intelligent scheduling method for factory production under multi-objective conditions is characterized by: The method comprises: Obtain the order information of products produced in the factory's current production cycle, combine it with the production order information in the previous production cycle, make an order forecast for the current production cycle, and obtain the forecast order information; Collecting device feature information of multiple devices in the factory, combining the order information, optimizing the order production schedule, and obtaining an optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of the multiple devices; According to the predicted order addition information, a secondary optimization of the optimized order production schedule is performed within the optimized order production schedule set to obtain the optimal order production schedule, wherein the order addition allocation probability of the multiple devices in the optimized order production schedule is obtained, and the order addition production quality analysis and order addition operation load analysis are performed in combination with the predicted order addition information to perform secondary optimization; Using the optimal order production schedule to carry out production; Obtain the order information of the products produced in the factory's current production cycle, combine it with the production information in the previous production cycle, make an order forecast for the current production cycle, and obtain the forecast order information, including: Get the number of products produced in the factory's current production cycle as order information; Obtain the number of products produced and added to orders during the factory's previous production cycle as historical order information and historical added order information; Combine the order information, historical order information and historical order addition information to predict order additions within the current production cycle and obtain predicted order addition information; Collecting device feature information of multiple devices in the factory, combining the order information, optimizing the order production schedule, and obtaining an optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of the multiple devices, including: Collecting multiple aging process coefficients of multiple devices in the factory as device characteristic information of the multiple devices, wherein the aging process coefficient includes a ratio of the service life of the device to the maximum service life of the device; Obtaining the maximum production quantity of the plurality of devices within the production cycle as an optimization constraint; Based on the optimization constraint condition, the order information is randomly assigned to the multiple devices to obtain a first order production schedule, wherein the first order production schedule includes multiple first production quantities of the multiple devices; Optimizing, according to the plurality of first production quantities and the plurality of aging process coefficients, with the purpose of improving order production quality and reducing the operating load of the plurality of devices, calculating and analyzing the first scheduling fitness of the first order production schedule; Continue to optimize the order production schedule until convergence, output multiple order production schedules with the largest scheduling fitness, and obtain the optimized order production schedule set.

2. The method for intelligent factory production scheduling under multi-objective conditions according to claim 1 is characterized in that: Combine the order information, historical order information and historical order addition information to predict order additions in the current production cycle and obtain predicted order addition information, including: According to the production data of the factory in the historical time, a sample order information set, a sample historical order information set and a sample historical order addition information set are collected, and the sample order addition information after different sample historical order information, sample historical order addition information and sample order information is collected as a sample predicted order addition information set; The sample order information set, the sample historical order information set, the sample historical order addition information set and the sample predicted order addition information set are used to train an order addition prediction channel; The order information, historical order information and historical order addition information are input into the order addition prediction channel, and the prediction output obtains the predicted order addition information.

3. The method for intelligent factory production scheduling under multi-objective conditions according to claim 1 is characterized in that: According to the plurality of first production quantities and the plurality of aging process coefficients, optimization is performed for the purpose of improving order production quality and reducing the operation load of the plurality of devices, and a first scheduling fitness of the first order production schedule is calculated and analyzed, including: Calculating ratios of the plurality of first production quantities to the maximum production quantity to obtain a plurality of first production load coefficients; According to the plurality of first production load coefficients and the plurality of aging process coefficients, a first scheduling fitness is calculated and obtained as follows: ， Among them, SCA is the scheduling fitness, and is the quality weight and load weight, M is the number of multiple devices, is the production load factor of the i-th equipment, is the aging process coefficient of the i-th device.

4. The method for intelligent factory production scheduling under multi-objective conditions according to claim 3 is characterized in that: According to the predicted order addition information, a secondary optimization of the optimized order production schedule is performed within the optimized order production schedule set to obtain the optimal order production schedule, including: Acquire production load coefficients of the plurality of devices in the plurality of optimized order production schedules in the optimized order production schedule set, and obtain a plurality of optimized production load coefficient sets; Subtracting the optimized production load coefficients in the multiple optimized production load coefficient sets from 1 to obtain multiple optimized capacity redundancy coefficient sets; In each set of optimized capacity redundancy coefficients, the ratio of each optimized capacity redundancy coefficient to the sum of multiple capacity redundancy coefficients is calculated to obtain multiple order allocation probabilities, and to construct multiple order allocation probability distributions; According to the multiple order allocation probability distributions and based on the predicted order information, the multiple optimized order production schedules are secondary optimized to obtain the optimal order production schedule.

5. The method for intelligent factory production scheduling under multi-objective conditions according to claim 4 is characterized in that: According to the plurality of order addition allocation probability distributions and the predicted order addition information, the plurality of optimized order production schedules are secondary optimized to obtain an optimal order production schedule, including: According to the multiple order allocation probability distributions, the order product quantity of the predicted order information is respectively allocated to the equipment with the largest order allocation probability in each order allocation probability distribution, and multiple order optimization production quantity sets are obtained as multiple order optimization order production schedules; According to the multiple order optimization production quantity sets, combined with the maximum production quantity, multiple order production load coefficient sets are calculated, and combined with the multiple aging process coefficients, multiple order scheduling fitness of the multiple order optimization order production schedules are calculated; Output the optimized order production schedule corresponding to the optimized order production schedule with the largest order production schedule fitness, and obtain the optimal order production schedule.

6. The factory production intelligent scheduling system under multi-objective conditions is characterized by: The system is used to execute the method according to any one of claims 1 to 5, and the system comprises: An order addition prediction module, which obtains order information for product production in the factory's current production cycle, combines the production order information in the previous production cycle, predicts the order addition in the current production cycle, and obtains predicted order addition information; A production scheduling optimization module, wherein the production scheduling optimization module collects equipment feature information of multiple equipment in the factory, combines the order information, optimizes the order production schedule, and obtains an optimized order production schedule set, wherein the optimization is performed for the purpose of improving the order production quality and reducing the operating load of the multiple equipment; A secondary optimization module, wherein the secondary optimization module performs secondary optimization of the optimized order production schedule within the optimized order production schedule set according to the predicted order addition information to obtain the optimal order production schedule, wherein the order addition allocation probability of the multiple devices within the optimized order production schedule is obtained, and the order addition production quality analysis and order addition operation load analysis are performed in combination with the predicted order addition information to perform secondary optimization; A production module, wherein the production module adopts the optimal order production schedule to carry out production.

Images