Multi-scale and multi-dimensional intelligent production scheduling method and system for chemical industry

Abstract

The invention provides a chemical industry-oriented multi-scale multi-dimensional intelligent production scheduling method and system, and the method comprises the steps: obtaining various production scheduling related data based on a factory model, a production management system, an inventory management system, a sales management system and an equipment management system which are established in advance; performing production scheduling according to the various production scheduling related data, a predetermined production quantity standard and gross profit data of different products, and determining a production plan of a target time granularity; and carrying out production according to the production plan, obtaining order insertion data and / or production abnormal information in real time, and updating the production plan. At least efficient, collaborative and benefit-maximized production scheduling can be realized, multi-objective optimization, dynamic order insertion, multi-system data integration and real-time collaboration are supported, and the actual demand of the fine chemical industry field for efficient production scheduling is met.

Description

Technical Field

[0001] This invention relates to the field of chemical production scheduling, and more specifically, to a multi-scale, multi-dimensional intelligent production scheduling method and system for the chemical industry. Background Technology

[0002] Currently, decision-making in chemical enterprises still relies primarily on the experience and process knowledge of management personnel. Human decision-making is inherently arbitrary and difficult to guarantee in a timely and accurate manner. Especially when market demand and production conditions change frequently, experience-based decisions often fail to respond effectively, easily leading to problems such as unstable product quality, high costs, and resource waste.

[0003] Although some chemical companies have introduced production scheduling systems, the existing systems still lack support for multi-objective optimization, dynamic order insertion, and real-time collaboration, and cannot meet the needs of the fine chemical industry for flexible production and maximum efficiency. Summary of the Invention

[0004] In view of this, the present invention discloses a multi-scale, multi-dimensional intelligent production scheduling method and system for the chemical industry, which realizes efficient, collaborative, and efficient production scheduling, supports multi-objective optimization, dynamic order insertion, multi-system data integration and real-time collaboration, and meets the actual needs of the fine chemical industry for efficient production scheduling.

[0005] Specifically, the present invention is achieved through the following technical solutions:

[0006] Firstly, this application proposes a multi-scale, multi-dimensional intelligent scheduling method for the chemical industry, the method comprising:

[0007] Based on pre-established factory models, production management systems, inventory management systems, sales management systems, and equipment management systems, various production scheduling-related data are obtained;

[0008] Based on the various production scheduling data, the pre-determined production volume standards, and the gross profit data of different products, production scheduling is carried out to determine the production plan at the target time granularity.

[0009] Production is carried out according to the production plan, and order insertion data and / or production anomaly information are obtained in real time to update the production plan.

[0010] Optionally, the various production scheduling related data include: factory model information, inventory information, tank capacity information, equipment inspection and maintenance information, sales plan information, production indicators, product gross profit information, and production line start-up and shutdown plan information.

[0011] Optionally, production scheduling is performed based on the various production scheduling-related data, predetermined production volume standards, and gross profit data for different products to determine a production plan with a target time granularity, including:

[0012] Based on inventory data and sales plan information, a preliminary production plan is prepared and the first production scheduling is carried out.

[0013] Based on the greedy algorithm, the production plan quantity of the first production scheduling is updated according to the product gross profit information to carry out the second production scheduling.

[0014] The second production scheduling result is decomposed to generate a production plan with the target time granularity.

[0015] Optionally, a preliminary production plan is prepared and the first production scheduling is carried out, including:

[0016] Based on inventory data and sales plan information, production is scheduled for the main product brand and intermediate brand brand. The intermediate brand brand is an intermediate product produced during the production of the main product brand. The main product brand is obtained from the sales plan information.

[0017] Group the main product brands or intermediate brand brands that compete for the same production line into a group of production needs;

[0018] Based on the integer optimization algorithm, the integer optimization solution is performed on each set of production requirements to obtain the production time required for each set of production requirements;

[0019] Based on a greedy algorithm, the main product brand and its intermediate brand are solved in descending order of product priority to obtain the number of production batches for each main product brand and its intermediate brand on each production line.

[0020] Alternatively, the solution can be optimized using the following formula with integers:

[0021] For any main product brand P ,and ;

[0022] For any P•M, ;

[0023] For any production line L, ;

[0024] Where Size represents the amount of material fed per batch on P•Li, PSale represents the planned sales volume of product P, Mcoeff represents the demand ratio of P for intermediate brand M, Period represents the feeding cycle of product Pi on production line L, and DurationL represents the total available time of production line L.

[0025] Optionally, the steps for re-compiling the production plan and scheduling a second production run include:

[0026] According to the pre-set planning cycle, the planning cycle is divided into multiple first-time phases;

[0027] Within each first time period, production is scheduled for each product and its intermediates, and the number of production batches on each production line within that first time period is determined, so as to schedule as many products and their intermediates as possible within the constraints of the total number of batches on each production line and the constraints of available tank capacity.

[0028] After completing the production schedule for one first time period, the product inventory is rolled over to the next first time period. Between the two first time periods, the product inventory is rolled over.

[0029] Optionally, the greedy algorithm includes decision variables, constraints, and an objective function.

[0030] The decision variables include:

[0031] Production batch number of product P on each production line: ,in ;

[0032] Production batch numbers of each intermediate product used in product P on each production line: ,in r is the number of intermediate products required for product P. Let be the number of production lines that can be used for the i-th intermediate product P. This is the i-th intermediate used in product P. The j-th production line used for the i-th intermediate product of product P.

[0033] Optionally, the constraints include intermediate product output constraints, tank capacity constraints, and production line constraints;

[0034] The intermediate product yield constraint is as follows: ,by ;

[0035] The tank capacity constraint is: ,in This indicates the volume of container Ti.

[0036] The production line time constraint is: the total production time shall not exceed the available production line time.

[0037] Optionally, the objective function includes maximizing the number of product batches and minimizing the number of intermediate batches.

[0038] Secondly, this invention discloses a multi-scale, multi-dimensional intelligent production scheduling system for the chemical industry, the system comprising:

[0039] The data acquisition module is used to acquire various production scheduling-related data based on pre-established factory models, production management systems, inventory management systems, sales management systems, and equipment management systems.

[0040] The production planning determination module is used to schedule production based on the various production scheduling-related data, pre-determined production volume standards, and gross profit data of different products, and to determine the production plan at the target time granularity.

[0041] The production plan update module is used to carry out production according to the production plan, and to obtain order insertion data and / or production anomaly information in real time to update the production plan.

[0042] The multi-scale, multi-dimensional intelligent production scheduling method and system proposed in this application for the chemical industry can achieve efficient, collaborative, and cost-effective production scheduling, support multi-objective optimization, dynamic order insertion, multi-system data integration and real-time collaboration, and meet the actual needs of the fine chemical industry for efficient production scheduling. Attached Figure Description

[0043] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0044] Figure 1 A flowchart illustrating a multi-scale, multi-dimensional intelligent scheduling method for the chemical industry, provided as an embodiment of this application;

[0045] Figure 2 The production planning flowchart provided for this application;

[0046] Figure 3 The algorithm flow for program decomposition provided in this application;

[0047] Figure 4 A schematic diagram of a multi-scale, multi-dimensional intelligent production scheduling system for the chemical industry provided in this application;

[0048] Figure 5 A schematic diagram of another multi-scale, multi-dimensional intelligent scheduling system for the chemical industry provided in this application. Detailed Implementation

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of systems and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0050] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0051] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0052] Please see Figure 1 This application discloses a flowchart illustrating a multi-scale, multi-dimensional intelligent scheduling method for the chemical industry. Specifically, the multi-scale, multi-dimensional intelligent scheduling method for the chemical industry proposed in this application includes:

[0053] S101. Based on the pre-established factory model, production management system, inventory management system, sales management system, and equipment management system, obtain various production scheduling-related data.

[0054] The various production scheduling related data include: factory model information, inventory information, tank capacity information, equipment inspection and maintenance information, sales plan information, production indicators, product gross profit information, and production line start-up and shutdown plan information.

[0055] It should be noted that the fine chemical industry is a typical intermittent production industry, meaning that the next batch of raw materials is processed immediately after the previous batch is completed. This application addresses the production scheduling problem in the fine chemical industry by using an intelligent scheduling algorithm to automatically complete production scheduling tasks based on sales targets. It also provides various auxiliary operations to improve the efficiency of production scheduling for users.

[0056] As an example, static manufacturing base data and dynamic order inventory data can be obtained from systems such as purchasing / sales / WMS; considering the overall goals and strategies of enterprise production scheduling (such as sales plans, continuous production of the same products, inventory, etc.), one-click automatic production scheduling and accurate material feeding plans can be carried out, and the results of the plan can be displayed in the form of various Gantt charts and reports.

[0057] Specifically, in the production scheduling preparation stage, it is necessary to synchronize the factory model information required for production scheduling from the master data system, such as the factory model module; synchronize the inventory and tank capacity information from the production management system; synchronize the equipment inspection and maintenance information from the equipment management module; and synchronize the sales plan information from the ERP module.

[0058] In some embodiments, during the production scheduling execution phase, the automatic scheduling of production plans with different time granularities, such as annual plans, monthly plans, and weekly plans, can be completed in multiple steps.

[0059] During the planning and tracking phase, completed plans are synchronized with external systems, such as ERP. The system supports dynamic adjustments to parts of the plan based on changes in market demand through an insert function.

[0060] As an example, a production line is the infrastructure used to process raw materials or oligomer semi-finished products to produce oligomer semi-finished products or finished products. Production line information can be synchronized from the factory model, and this invention also provides manual maintenance functionality to support units that do not have a factory model data source in preparing production line models.

[0061] As an example, the product model includes product definitions, oligomer semi-finished product definitions, and product BOM definitions, containing product type attributes such as regular / special products, and whether it participates in secondary decomposition. Production line information can be synchronized from the factory model. This invention also provides a manual maintenance function to support units without a factory model data source in preparing production line models.

[0062] As an example, this application also provides a product processing model to define the relationship between products / semi-finished products and production lines, and to specify information such as the feeding cycle, batch processing volume, and washing time of the product on the production line.

[0063] As an example, tank capacity information can be obtained through the tank model. Tank capacity information includes tank capacity attributes, storage relationship attributes between products and tanks, etc.

[0064] Specifically, tank capacity information can be synchronized from the production management system; inventory information can be synchronized from the inventory management system; sales plan information and product gross profit information can be synchronized from the sales management system; and production line start-up and shutdown plan information can be synchronized from the equipment management system.

[0065] In other words, the intelligent scheduling method of this invention includes a data integration layer for data preparation. The intelligent scheduling system also provides related functions to support collaborative management of materials and production lines, achieve precise matching of materials, production lines, and storage tanks, and support configuration of washing time, BOM information maintenance, and automatic calculation of raw material requirements.

[0066] S102. Based on the various production scheduling data, the pre-determined production volume standards, and the gross profit data of different products, production scheduling is carried out to determine the production plan at the target time granularity.

[0067] Specifically, production scheduling is conducted based on the aforementioned various production scheduling-related data, pre-determined production volume standards, and gross profit data for different products to determine the production plan at the target time granularity, including:

[0068] Based on inventory data and sales plan information, a preliminary production plan is prepared and the first production scheduling is carried out.

[0069] Based on the greedy algorithm, the production plan quantity of the first production scheduling is updated according to the product gross profit information to carry out the second production scheduling.

[0070] The second production scheduling result is decomposed to generate a production plan with the target time granularity.

[0071] This includes formulating a preliminary production plan and conducting the first production scheduling, which includes:

[0072] Based on inventory data and sales plan information, production is scheduled for the main product brand and intermediate brand brand. The intermediate brand brand is an intermediate product produced during the production of the main product brand. The main product brand is obtained from the sales plan information.

[0073] Group the main product brands or intermediate brand brands that compete for the same production line into a group of production needs;

[0074] Based on the integer optimization algorithm, the integer optimization solution is performed on each set of production requirements to obtain the production time required for each set of production requirements;

[0075] Based on a greedy algorithm, the main product brand and its intermediate brand are solved in descending order of product priority to obtain the number of production batches for each main product brand and its intermediate brand on each production line.

[0076] It's important to note that in the fine chemical industry, production is based on sales, and production scheduling begins with the sales plan. At this stage, the product grades to be produced are obtained from the sales plan. The sales plan's cycle corresponds to the production scheduling cycle (year, month, week). Specifically, the product grades to be produced can be determined based on the product grades in the sales plan, serving as the primary product grade.

[0077] In order to produce the main product, intermediate products must first be produced. Specifically, the grade and processing quantity requirements of the intermediate products can be determined based on the BOM definition in the product model constructed during the production scheduling preparation phase.

[0078] Furthermore, this application targets sales volume and schedules production for the main product brand and intermediate brand, that is, it clarifies the number of batches arranged for each product and intermediate product on each production line.

[0079] Specifically, since a product / intermediate can be produced on multiple production lines, and a single production line can also produce multiple products / intermediates, there is a problem of competing production lines for products / intermediates.

[0080] Since the number of batches is an integer, this is an integer programming optimization problem. To improve the efficiency of the optimization solution, this invention creatively proposes a grouping optimization solution.

[0081] Specifically, this application groups products or intermediates that compete on the same production line and products that use the same intermediates together.

[0082] For example, suppose there are products P1, P2, ..., Pn, intermediates M1, M2, ..., Mm, and production lines L1, L2, ..., Lq. Product Pi uses intermediate Mj and is denoted as Pi•Mj. Product Pi can be used in production line Lj and is denoted as Pi•Lj. Then products Pi and Pj are grouped together if and only if... .

[0083] In other words, if two products have the same intermediate products or the same production line, they should be grouped together.

[0084] In addition, if the intermediate products used by these two products are associated with overlapping production lines, then they should also be grouped together.

[0085] Among them, the integer optimization solution algorithm is used to perform integer optimization solution for each group.

[0086] The variable settings in the integer optimization algorithm include: setting a variable for each pair of Pi•Lj or Mi•Lj within the group. or , which represents the number of batches to be allocated to product Pi or Mi on production line Lj, ​​with the objective set to: maximize each variable.

[0087] Specifically, the following formula can be optimized for integer solutions:

[0088] For any main product brand P ,and ;

[0089] For any P•M, ;

[0090] For any production line L, ;

[0091] Where Size represents the amount of material fed per batch on P•Li, PSale represents the planned sales volume of product P, Mcoeff represents the demand ratio of P for intermediate brand M, Period represents the feeding cycle of product Pi on production line L, and DurationL represents the total available time of production line L.

[0092] The integer optimization algorithm requires a commercially available optimization solver. On a typical solver, if the number of variables exceeds 10 and the number of constraints exceeds 40, the solution efficiency becomes low. To address this, this application also proposes a greedy solution algorithm to suit situations where companies have not purchased commercial solvers.

[0093] Specifically, in the greedy algorithm, each product is solved in descending order of priority to obtain the production batch number of each product and its intermediate products on each production line.

[0094] In solving for each product and its intermediates, a binary search method is used to find the maximum number of processing batches for each production line to maximize the sales plan.

[0095] Here, after a production scheduling process, the number of production batches for each product and intermediate product on each production line within the planned cycle is obtained. The goal of this scheduling result is to meet the sales plan and takes into account the production capacity of the production line, including maintenance time, washing time, etc.

[0096] In addition to meeting predetermined sales targets, companies also hope to further tap into their production potential and produce more products with higher gross margins in order to achieve better economic benefits. This means increasing production beyond the planned sales volume.

[0097] The increase in production volume comes from two sources: one is the breakdown of reference quantities, and the other is the manual specification of production volumes.

[0098] Decomposition reference quantity refers to the decomposition result of a production plan at a coarser time granularity. For example, an annual plan can be decomposed into monthly production schedules. This decomposition result, for the monthly plan, is the decomposition reference quantity, which can be regarded as the production task of the monthly plan.

[0099] Users can also manually specify the production volume to be processed based on the current sales situation of the product.

[0100] It should be noted here that secondary production scheduling refers to production scheduling carried out based on the primary production scheduling, specifically for the increased production volume based on the sales plan.

[0101] In other words, the goal of the first production scheduling is to achieve the sales target. The second production scheduling, on the other hand, focuses on scheduling the production of high-margin products after meeting the sales target.

[0102] The algorithm for secondary production scheduling is basically the same as that for primary production scheduling, with the following two main differences:

[0103] The target processing volume of the first production scheduling is the sales plan volume, and the target of the second production scheduling is to complete the sales plan volume and increase the production volume of high-margin products.

[0104] In the first production scheduling, the product priority is based on the product's own attributes. In the second production scheduling, the production scheduling of the sales plan is based on the product's own priority attributes, while the additional production is scheduled based on the product's gross profit margin.

[0105] Specifically, similar to primary scheduling, secondary scheduling supports both integer optimization algorithms and greedy algorithms. This depends on whether the company has a commercial solver optimizer.

[0106] For example, please refer to Figure 2 When scheduling production, step S201 can be executed first to determine the main product brand.

[0107] Next, step S202 is executed to determine whether an intermediate brand number is included.

[0108] If so, proceed to step S203 to add an intermediate brand number.

[0109] Then proceed to step S204 for the first production scheduling.

[0110] If not, proceed directly to step S204.

[0111] Next, step S205 is executed to determine whether the production targets are met.

[0112] If so, proceed to step S207 to perform a second production scheduling.

[0113] If not, proceed to step S206 to increase positive production (gross profit). Then, perform a second production scheduling.

[0114] Next, proceed with step S208, decompose the plan.

[0115] Specifically, the steps for re-compiling the production plan and scheduling the second batch of production include:

[0116] According to the pre-set planning cycle, the planning cycle is divided into multiple first-time phases;

[0117] Within each first time period, production is scheduled for each product and its intermediates, and the number of production batches on each production line within that first time period is determined, so as to schedule as many products and their intermediates as possible within the constraints of the total number of batches on each production line and the constraints of available tank capacity.

[0118] After completing the production schedule for one first time period, the product inventory is rolled over to the next first time period. Between the two first time periods, the product inventory is rolled over.

[0119] The overall production schedule for the period was obtained through two rounds of scheduling.

[0120] As an example, for an annual plan, the production batches of each product and intermediate product on each production line within the year are obtained; for a monthly plan, the production batches of each product and intermediate product on each production line within the month are obtained; and for a weekly plan, the production batches of each product and intermediate product on each production line within the week are obtained.

[0121] Such production scheduling results are of significant reference value when considering the processing capacity of production lines. However, for actual production, further breakdown is needed before they can be used to guide production.

[0122] Specifically, for an annual plan, it is necessary to understand the arrangement of each product or intermediate product on each production line every month within the year; for a monthly plan, it is necessary to understand the arrangement of each product or intermediate product on each production line every week within the month. In particular, some products are special products and need to be directly broken down from the monthly plan to the daily plan; for a weekly plan, it is necessary to understand the arrangement of each product or intermediate product on each production line every day within the week.

[0123] The purpose of decomposing the plan here is to fulfill the above requirements, that is, to obtain the production schedule results at the lower time granularity based on the production schedule results at the higher time granularity.

[0124] During the production scheduling phase, the number of production batches for each product / intermediate product on each production line within the higher-level time granularity has been determined. Since the decomposition plan is to guide actual production, it should adopt a more pragmatic strategy: it should consider both the production line capacity and the inventory roll-off, as well as the availability of canned inventory.

[0125] In terms of algorithm selection, this invention adopts a hybrid algorithm that combines greedy algorithm and optimization solution.

[0126] The overall algorithm flow is a solution process that proceeds first vertically and then horizontally. Taking the decomposition of a monthly plan as an example, the solution process is as follows: Figure 3 As shown.

[0127] Please continue reading. Figure 3 In accordance with management requirements, the planning cycle is divided into several fine-grained time phases. For example, a month is divided into four weeks, and a week is divided into seven days.

[0128] Within each fine-grained time period, production scheduling is performed for each product and its intermediates to determine the number of batches to be produced on each production line within that fine-grained cycle. Within this fine-grained cycle, production line capacity and available tank capacity rotate between products. The scheduling principle is to schedule as many products as possible within the constraints of the total number of batches per product on each production line and the available tank capacity.

[0129] Specifically, after completing one fine-grained cycle of production scheduling, it rolls over to the next fine-grained cycle. Between fine-grained cycles, product inventory is rolled over.

[0130] As an example, in this overall greedy algorithm, the production scheduling of individual products within each stage uses an integer optimization algorithm.

[0131] For a given product P, with intermediate products M1, M2, …, Mn, the production lines that can process product P are L1, L2, …, Lp, and the containers that can store product P are T1, T2, …, Tq.

[0132] For any intermediate product Mi of P, the demand ratio of P for Mi is coeffi, and the production line that can be used to process Mi is: , ,…, The container can store the intermediate product Mi. , ,…, .

[0133] Because there may be competition between the production lines and cans of a product and its intermediates, and also between different intermediates, optimization methods are suitable for solving this problem. Furthermore, within the loop steps of the greedy algorithm, the number of intermediates, production lines, and cans involved in a product is significantly reduced. Using general optimization algorithms, the performance can be controlled in the millisecond range. Therefore, ordinary optimizers can be used for solving this problem, without resorting to commercial solvers.

[0134] The key information about the algorithm is explained below:

[0135] The model is an integer programming optimization solution.

[0136] The greedy algorithm includes decision variables, constraints, and an objective function.

[0137] The decision variables include:

[0138] Production batch number of product P on each production line: ,in ;

[0139] Production batch numbers of each intermediate product used in product P on each production line: ,in r is the number of intermediate products required for product P. Let be the number of production lines that can be used for the i-th intermediate product P. This is the i-th intermediate used in product P. The j-th production line used for the i-th intermediate product of product P.

[0140] The constraints include intermediate product output constraints, tank capacity constraints, and production line constraints.

[0141] The intermediate product yield constraint is as follows: ,by ;

[0142] The tank capacity constraint is: ,in This indicates the volume of container Ti.

[0143] The production line time constraint is: the total production time shall not exceed the available production line time.

[0144] The objective function includes maximizing the number of product batches and minimizing the number of intermediate batches.

[0145] In this way, by breaking it down, we can obtain the number of production batches for each production line at a fine-grained time scale, which can be used to guide production.

[0146] When breaking down the plan, it's necessary to distinguish between regular products and special products based on the company's actual needs. Special products are also known as customized products. The main difference between customized and regular products is that the monthly plan for customized products is directly broken down into daily plans; customized products support dynamic adjustments through order insertion.

[0147] S103. Produce according to the production plan, and obtain order insertion data and / or production anomaly information in real time, and update the production plan.

[0148] Here, after the production scheduling execution phase is completed, detailed production scheduling results are obtained. This invention supports publishing the production scheduling results as a production plan to relevant systems, such as ERP, production management systems, etc.

[0149] In addition, during the execution of the plan, it supports order insertion and production line monitoring and optimization.

[0150] Specifically, the order insertion mechanism includes: the system supports customized product order insertion, quickly responds to customer needs, dynamically adjusts the production schedule, and ensures delivery cycle.

[0151] Specifically, production line monitoring and optimization is used to compare planned and actual feeding / offline times in real time, analyze maintenance and washing times, and provide optimization suggestions.

[0152] In this way, this application can achieve one-click automatic production scheduling, improving scheduling efficiency and accuracy; support multi-objective collaborative optimization, balancing cost, delivery time, energy consumption and benefits; break down information silos and realize cross-system data linkage; have high flexibility, supporting order insertion and dynamic adjustment; improve resource utilization and reduce production costs and inventory waste.

[0153] Furthermore, this application enables fine chemical production enterprises to construct a multi-level planning management system; establish a planning management module covering three time dimensions: year, month, and week, realizing the functions of planning, decomposition, tracking, and viewing from macro to micro levels, supporting the systematic and hierarchical management of enterprise production plans; achieve intelligent production scheduling and resource optimization; by integrating key constraints such as sales plans, inventory data, maintenance plans, and product gross profit, and using scheduling models and algorithms, automatically generate optimal production plans and raw material demand plans to maximize benefits and improve scheduling efficiency and resource utilization. It also enables system integration and data collaboration; through data integration with sales systems, ERP, operational decision-making systems, equipment management, and other systems, it achieves data linkage and process collaboration between planning and business links such as sales, procurement, production, and equipment maintenance, improving overall operational efficiency; promotes the standardization and automation of business processes; clarifies the process specifications and system operation permissions for each link of planning, decomposition, release, and tracking, reducing manual intervention and improving the accuracy and execution efficiency of planning management, etc.

[0154] In an exemplary embodiment, taking a fine chemical production plant as an example, the specific implementation steps are as follows:

[0155] During the data preparation phase, data such as sales plans, inventory, BOM, and gross profit can be obtained by integrating with systems such as UBMP, WMS, and ERP. During the production scheduling execution phase, users input production scheduling targets, and the system automatically executes a three-stage production scheduling algorithm to generate plans and display them visually. During the plan release phase, the production scheduling results can be synchronized to the ERP system to generate production orders and guide actual production. During the dynamic adjustment phase, the system can reschedule production in real time based on order insertion requirements or production anomalies. During the monitoring and optimization phase, the production line monitoring module can be used to analyze execution deviations and continuously optimize the production scheduling strategy.

[0156] On the other hand, please see Figure 4 A schematic diagram of a multi-scale, multi-dimensional intelligent scheduling system for the chemical industry. The multi-scale, multi-dimensional intelligent scheduling system for the chemical industry includes:

[0157] The data acquisition module 100 is used to acquire various production scheduling-related data based on a pre-established factory model, production management system, inventory management system, sales management system, and equipment management system.

[0158] The production planning determination module 200 is used to schedule production based on the various production scheduling related data, the pre-determined production volume standards, and the gross profit data of different products, and to determine the production plan at the target time granularity.

[0159] The production plan update module 300 is used to carry out production according to the production plan, and to obtain order insertion data and / or production anomaly information in real time to update the production plan.

[0160] For example, please refer to Figure 5 , Figure 5 This application presents another multi-scale, multi-dimensional intelligent production scheduling system for the chemical industry. This system includes: an equipment management module 501, an inventory management module 502, a sales management module 503, an operations decision-making module 504, an ERP module 505, and a planning management module 506.

[0161] Among them, the equipment management module 501 is used to obtain maintenance plan data.

[0162] The inventory management module 502 is used to obtain inventory data, including inbound data and other inventory data.

[0163] The sales management module 503 is used to obtain sales data such as sales plan data and raw material procurement data.

[0164] The Operations Decision module 504 is used to obtain operational data such as product gross profit data.

[0165] ERP module 505 is used to obtain production plan data.

[0166] Specifically, the equipment management module 501, inventory management module 502, sales management module 503, operation decision module 504, and ERP module 505 interact with the planning management module 506.

[0167] The planning management module 506 is used to execute the steps described in the above-mentioned multi-scale and multi-dimensional intelligent scheduling method for the chemical industry.

[0168] This application proposes a multi-scale, multi-dimensional intelligent production scheduling method and system for the chemical industry, which can achieve efficient, collaborative, and cost-maximizing production scheduling. It supports multi-objective optimization, dynamic order insertion, multi-system data integration, and real-time collaboration, meeting the actual needs of the fine chemical industry for efficient production scheduling.

[0169] Specifically, by establishing a planning management module covering three time dimensions—year, month, and week—it enables the creation, decomposition, tracking, and viewing of plans from macro to micro levels, supporting the systematic and hierarchical management of enterprise production plans. By integrating key constraints such as sales plans, inventory data, maintenance plans, and product gross profit, and using scheduling models and algorithms, it automatically generates optimal production plans and raw material demand plans to maximize efficiency and improve scheduling efficiency and resource utilization. Through data integration with sales systems, ERP, operational decision-making systems, and equipment management systems, it achieves data linkage and process collaboration between planning and business processes such as sales, procurement, production, and equipment maintenance, improving overall operational efficiency. By clarifying the process specifications and system operation permissions for each stage of plan creation, decomposition, release, and tracking, it reduces manual intervention and improves the accuracy and execution efficiency of plan management.

[0170] For the above system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0171] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal disks or removable disks), magneto-optical disks, and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0172] Finally, it should be noted that although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily used to describe the features of specific embodiments of a particular invention. Certain features described in the various embodiments of this specification may also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation of a sub-combination.

[0173] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0174] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0175] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A multi-scale, multi-dimensional intelligent scheduling method for the chemical industry, characterized in that, The method includes: Based on pre-established factory models, production management systems, inventory management systems, sales management systems, and equipment management systems, various production scheduling-related data are obtained; Based on the various production scheduling data, the pre-determined production volume standards, and the gross profit data of different products, production scheduling is carried out to determine the production plan at the target time granularity. Production is carried out according to the production plan, and order insertion data and / or production anomaly information are obtained in real time to update the production plan.

2. The method according to claim 1, characterized in that, The various production scheduling related data include: factory model information, inventory information, tank capacity information, equipment inspection and maintenance information, sales plan information, production indicators, product gross profit information, and production line start-up and shutdown plan information.

3. The method according to claim 2, characterized in that, Based on the aforementioned production scheduling data, pre-determined production volume standards, and gross profit data for different products, production scheduling is performed to determine the production plan at the target time granularity, including: Based on inventory data and sales plan information, a preliminary production plan is prepared and the first production scheduling is carried out. Based on the greedy algorithm, the production plan quantity of the first production scheduling is updated according to the product gross profit information to carry out the second production scheduling. The second production scheduling result is decomposed to generate a production plan with the target time granularity.

4. The method according to claim 3, characterized in that, Develop a preliminary production plan and conduct the first production scheduling, including: Based on inventory data and sales plan information, production is scheduled for the main product brand and intermediate brand brand. The intermediate brand brand is an intermediate product produced during the production of the main product brand. The main product brand is obtained from the sales plan information. Group the main product brands or intermediate brand brands that compete for the same production line into a group of production needs; Based on the integer optimization algorithm, the integer optimization solution is performed on each set of production requirements to obtain the production time required for each set of production requirements; Based on a greedy algorithm, the main product brand and its intermediate brand are solved in descending order of product priority to obtain the number of production batches for each main product brand and its intermediate brand on each production line.

5. The method according to claim 4, characterized in that, The following formula can be optimized for integer solutions: For any main product brand P ,and ; For any P•M, ; For any production line L, ; Where Size represents the amount of material fed per batch on P•Li, P Sale M represents the planned sales volume of product P. coeff This indicates the demand ratio of P for intermediate brand M, Period indicates the feeding cycle of product Pi on production line L, and Duration indicates the production cycle of product Pi. L This represents the total available time of production line L.

6. The method according to claim 3, characterized in that, The steps for re-compiling the production plan and scheduling the second production run include: According to the pre-set planning cycle, the planning cycle is divided into multiple first-time phases; Within each first time period, production is scheduled for each product and its intermediates, and the number of production batches on each production line within that first time period is determined, so as to schedule as many products and their intermediates as possible within the constraints of the total number of batches on each production line and the constraints of available tank capacity. After completing the production schedule for one first time period, the product inventory is rolled over to the next first time period. Between the two first time periods, the product inventory is rolled over.

7. The method according to claim 6, characterized in that, The greedy algorithm includes decision variables, constraints, and an objective function. The decision variables include: The production batch number of product P on each production line is: ; in, ; The production batch numbers of each intermediate product used in product P on each production line are as follows: , in, r is the number of intermediate products required for product P. Let be the number of production lines that can be used for the i-th intermediate product P. This is the i-th intermediate used in product P. The j-th production line used for the i-th intermediate product of product P.

8. The method according to claim 6, characterized in that, The constraints include intermediate product output constraints, tank capacity constraints, and production line constraints. The intermediate product yield constraint is as follows: ,by ; The tank capacity constraint is: ,in This indicates the volume of container Ti. The production line time constraint is: the total production time shall not exceed the available production line time.

9. The method according to claim 6, characterized in that, The objective function includes maximizing the number of product batches and minimizing the number of intermediate batches.

10. A multi-scale, multi-dimensional intelligent scheduling system for the chemical industry, characterized in that, The system includes: The data acquisition module is used to acquire various production scheduling-related data based on pre-established factory models, production management systems, inventory management systems, sales management systems, and equipment management systems. The production planning determination module is used to schedule production based on the various production scheduling-related data, pre-determined production volume standards, and gross profit data of different products, and to determine the production plan at the target time granularity. The production plan update module is used to carry out production according to the production plan, and to obtain order insertion data and / or production anomaly information in real time to update the production plan.

Images