Product production device control method and apparatus, electronic device, and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for controlling product manufacturing equipment, relating to the field of industrial production. The method includes: determining the expected finished goods inventory of at least one product at at least one desired time point within a target time period based on a production task; determining the expected process inventory of at least one process corresponding to each product at the corresponding desired time point based on the process flow corresponding to each product; determining at least one segment and parameter constraints for each segment based on each product, the corresponding process, and the production equipment; determining production constraints corresponding to each segment based on the expected finished goods inventory and expected process inventory of each product at the corresponding desired time point; and determining the parameter values ​​for each segment. Embodiments of this invention can reduce resource waste in industrial production.

Description

Technical Field

[0001] This invention relates to the field of industrial production, and in particular to a method, apparatus, electronic device, and storage medium for controlling product manufacturing equipment. Background Technology

[0002] Most existing production scheduling models treat orders as the sole driver of machine production, meaning that each production cycle must be associated with a specific order. Once there are no orders to fulfill or the current order's demand has been met, production immediately stops and production of other orders begins.

[0003] Order delivery time has a significant impact on the solver's scheduling of machine production time, especially when the demand order includes small batch orders, resulting in fragmented production tasks. This not only puts enormous pressure on the solver but also forces the machine to frequently switch products, leading to numerous changeover operations. Changeovers typically consume significant time and labor costs, ultimately wasting machine capacity. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for controlling product manufacturing equipment, which can reduce resource waste in industrial production.

[0005] According to one aspect of the present invention, a method for controlling product manufacturing equipment is provided, comprising:

[0006] Based on the production task, determine the expected finished goods inventory of at least one product at at least one expected time point within the target time period;

[0007] Based on the process flow corresponding to each product, determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point;

[0008] Based on each product, the corresponding process and production equipment, at least one segment is determined, along with parameter constraints for each segment.

[0009] Based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point, determine the production constraints corresponding to each segment;

[0010] Using the production constraints and parameter constraints corresponding to each segment as constraints, and taking the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period as targets, the parameter values ​​of each segment are determined. The parameters of each segment include: activation parameters, production parameters, and duration parameters.

[0011] According to another aspect of the present invention, a product manufacturing equipment control device is provided, comprising:

[0012] The first expectation determination module is used to determine the expected finished goods inventory of at least one product at at least one expected time point in the target time period based on the production task.

[0013] The second expectation determination module is used to determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point, based on the process flow corresponding to each product.

[0014] The parameter constraint determination module is used to determine at least one segment and the parameter constraints of each segment based on each product, the corresponding process and production equipment of each product.

[0015] The production constraint determination module is used to determine the production constraints corresponding to each segment based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point.

[0016] The production parameter determination module is used to determine the parameter values ​​of each segment based on the production constraints and parameter constraints corresponding to each segment, and based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period. The parameters of each segment include: activation parameters, output parameters, and duration parameters.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the product manufacturing equipment control method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the product manufacturing equipment control method according to any embodiment of the present invention.

[0022] The technical solution of this invention sets desired finished product inventory and desired process inventory as production targets. This allows equipment to continue production in segments until the inventory reaches the target level, rather than immediately switching after completing an order. This significantly reduces frequent changeover operations caused by order switching, lowers changeover time and labor costs, and increases effective equipment production time. Each segment is independent of the batch size of a specific order, using inventory constraints as boundary conditions for continuous production. Small-batch orders only affect the rate of inventory consumption, without directly driving equipment start-up, shutdown, or switching, thus effectively suppressing production task fragmentation. Through joint optimization of segment parameters (activation parameters, output parameters, and duration parameters), upstream processes can begin production in advance based on process inventory constraints, eliminating the need for downstream processes to wait due to material shortages. Simultaneously, it avoids equipment idling or downtime due to a lack of orders, achieving continuous connection between production stages and significantly improving overall equipment utilization.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a product manufacturing equipment control method according to an embodiment of the present invention;

[0026] Figure 2 This is a flowchart of a product manufacturing equipment control method according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the structure of a product manufacturing equipment control device according to an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the product manufacturing equipment control method of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Figure 1 This is a flowchart illustrating a product manufacturing equipment control method provided in an embodiment of the present invention. This embodiment is applicable to production scheduling scenarios, enabling the automatic generation of optimal or near-optimal production plans that meet order delivery deadlines in a manufacturing environment with multiple products, processes, and machines operating in parallel. This method can be executed by a product manufacturing equipment control device, which can be implemented in hardware and / or software. The product manufacturing equipment control device can be configured in an electronic device with certain data processing capabilities, such as a server.

[0032] See Figure 1 The product manufacturing equipment control method shown includes:

[0033] S101. Based on the production task, determine the expected finished goods inventory of at least one product at at least one expected time point within the target time period.

[0034] Here, a production task refers to the task of producing products within a target time period. Products can refer to finished industrially manufactured goods. A production task includes: order information for at least one product, including order identifier, product identifier, required quantity, and delivery date. Order information can be sourced structured data. The expected time point can refer to the delivery date. The expected finished goods inventory can refer to the inventory of finished goods to be delivered.

[0035] In some embodiments, order information in a production task can be aggregated and demand analyzed. All order information is grouped and merged by product identifier. For each product, the required quantity of all related orders is summarized and sorted by delivery date from earliest to latest. Simultaneously, the cumulative expected value at each delivery time point is calculated, i.e., the total number of products required by all due orders up to the expected delivery time point, which is used as the expected finished goods inventory at that expected time point.

[0036] In addition, production capacity and inventory levels for each product can be determined based on the industrial production line system. Furthermore, the production process flow for each product can be determined accordingly. Production capacity can include output and yield. Output can be measured as production rate.

[0037] In a specific example, the production task includes order information for 6 orders. As shown in Table 1, these 6 orders need to be scheduled within 14 days (336 hours):

[0038]

[0039] The target time period lasts for 14 days, or 336 hours. The product manufacturing process (process sequence) is as follows: Product A: Process 1 (thermal processing) and Process 2 (machining); Product B: Process 1 (thermal processing) and Process 2 (machining); and Product C: Process 1 (thermal processing). Available production machines and their production capacity are as follows:

[0040]

[0041] Mold changeover time: Switching between different products on the same thermal processing equipment takes 4 hours (14,400 seconds). Work-in-process (WIP) inventory in the industrial production line system prior to the target time period:

[0042] The order aggregation and demand analysis process is as follows: All order information is grouped by product identifier, and all orders for the same product are merged into a single product demand record. The aggregation process for Product A involves aggregating three original orders: ORD-001 (800 units, day 4), ORD-002 (1200 units, day 8), and ORD-003 (600 units, day 12). The aggregation result is: the expected finished goods inventory at the end of the target time period is 800 + 1200 + 600 = 2600 units. The cumulative demand timeline (sorted by delivery date) for the expected finished goods inventory at the expected time point is shown below:

[0043]

[0044] The aggregation result for Product B is: Expected finished goods inventory at the end of the target time period: 1000 + 500 = 1500 units. Cumulative demand timeline:

[0045]

[0046] Aggregation results for Product C: Expected finished goods inventory at the end of the target time period: 400 units. Cumulative demand schedule: Cumulative demand of 400 units on day 7 (168h).

[0047] After aggregation, the original six independent orders are transformed into three product demand curves. Subsequent solver modeling uses products as the basic unit—instead of creating a separate task for each order, a production variable that can be shared across multiple machines is created for each product. This reduces the scale of decision variables from the order level (6) to the product level (3), a reduction of 50%. In large-scale scenarios (such as 500 orders and 50 products), the reduction can reach 90%.

[0048] S102. Based on the process flow corresponding to each product, determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point.

[0049] In this context, "process flow" refers to at least one sequentially executed process required to transform a product from raw materials into a finished product. These processes may have an execution order or a dependency order. For example, processes may include heat treatment or machining. A process can be an independent step or stage, representing a specific sequential processing, handling, or assembly. Each process corresponds to a result, which can be a finished product or a semi-finished product. For example, in plastic parts production: Process 1: Injection molding, producing injection molded parts (semi-finished products). Process 2: Spray painting, producing painted parts (semi-finished products). Process 3: Assembly, producing finished products. "Expected process inventory" refers to the expected inventory quantity of a process's output, where the expected process inventory can be finished products or semi-finished products.

[0050] In one example, such as Figure 2As shown, processes 1, 2, and so on, are executed sequentially. Each process can be performed by at least one production device. For example, production devices 1 and 2 perform process 1, production devices 3 and 4 perform process 2, and production devices 5 and 6 perform the final process. Items from each process are placed into the corresponding semi-finished product warehouse. For example, items produced in process 1 are placed into the process 1 semi-finished product warehouse. Subsequent processes extract semi-finished products from the adjacent preceding process's semi-finished product warehouse. Subsequent processes then process or produce these extracted semi-finished products and place them into the corresponding semi-finished product warehouse. This process continues until the final process's semi-finished product warehouse, which is also the finished product warehouse, thus completing the production process for one product.

[0051] In addition, if there are some products in stock in the industrial production line system, the expected finished goods inventory and expected process inventory can be updated based on the initial inventory (work-in-process inventory).

[0052] For each product, work-in-process inventory is deducted progressively from the last process forward to calculate the actual production demand for each process.

[0053] For product A (two processes: thermal processing and machining): The demand for the final process (machining) is: Machining demand = Total order demand - Finished goods inventory = 2600 - 100 = 2500 units. The demand for the preceding process (thermal processing) is: Thermal processing demand = Machining demand - Thermally processed finished goods inventory = 2500 - 200 = 2300 units.

[0054] For product B (two processes: thermal processing and machining): Machining process requirement = 1500 - 0 = 1500 units. Thermal processing process requirement = 1500 - 0 = 1500 units.

[0055] For product C (single process: thermal): thermal process requirement = 400 - 50 = 350 units.

[0056] Accordingly, the expected updated stock is:

[0057]

[0058] S103. Based on each product, the corresponding process and production equipment, determine at least one segment and parameter constraints for each segment.

[0059] In this context, "production equipment" refers to the physical resources that perform production activities, used to produce products or process materials. "Segmentation" refers to a combination of time segments, products, processes, and production equipment, where a time segment is a time interval divided from the target time period. "Parameter constraints" refers to the restrictions imposed on the parameters of each segment. Segment parameter constraints are typically determined by the attribute information of processes, products, and production equipment. Typically, segment parameters can include activation parameters, output parameters, and duration parameters. For example, parameter constraints could be sequential constraints between processes, or production equipment could only execute in one segment at a time.

[0060] In actual production, determining how many times the same product needs to be produced on the same machine is a dynamic decision problem. Theoretically, the number of times can be any positive integer, leading to an uncontrollable number of decision variables. This invention simplifies this problem by introducing the concept of segmentation: each product and machine combination is presumably allowed to have a maximum of several segments. Instead of determining an unbounded number of times the product needs to be produced, it is only necessary to decide which segments to activate and the output and time for each segment. This fixed-uppercase modeling method effectively constrains the size of variables while preserving scheduling flexibility (allowing interruptions and recovery), thus accelerating the solution process.

[0061] For each product, process, and production equipment combination, create up to 3 segments. Each segment contains 3 parameters, which can be refined into 5 parameters.

[0062] For example, the thermal processing of product A, and the production equipment M1 (capacity 60 units / h, yield 0.95) and M2 (capacity 55 units / h, yield 0.90):

[0063]

[0064] Similarly, parameters are created for all combinations of products, processes, and production equipment. This allows for the construction of an inventory timeline for each product, i.e., an inventory level curve that changes over time. Key characteristics of this curve are: Initial level: equal to the initial inventory of the product (including work-in-process inventory); Level change during production: as a production machine produces the product within a certain time period, the inventory level rises at a constant rate according to the production rate (hourly output) of that machine, rather than increasing all at once at the end of production; Non-production periods: the inventory level remains constant (horizontal segment); Overall shape: the inventory timeline is a "step-up" curve composed of multiple straight lines, sloping upwards during production periods and horizontal during non-production periods.

[0065] In an optional embodiment, the parameter constraints of each segment include: the activation parameter and the production parameter of each segment have the same value type; the numerical relationship between the production parameter of each segment and the duration of the duration segment is determined according to the production capacity yield of each segment; the activation parameter of each segment and the duration segment parameter have the same value type; and the dependency relationship between the activation parameter of each segment and the segment corresponds.

[0066] The consistent value type can mean that all values ​​are positive or zero. The activation parameter ranges from 0 to 1. If the activation parameter is 0, the output parameter is 0, the duration parameter is 0, and all three have a value type of 0. If the activation parameter is 1, the output parameter is positive, the duration parameter is 1, and all three have a positive value type. The numerical relationship includes the product of the ratio between the output parameter and the duration and the production yield. When the production equipment for a segment is determined, the production yield is also determined; that is, the product of the production yields of the segments is a constant. There are dependencies between segments; only after the activation parameter of the segment executed first is 1 can the activation parameter of the subsequent segment be 1.

[0067] Specifically, for potential parameters, the following associated constraints are applied to each parameter group (taking A-thermal-M1-segment 0 as an example):

[0068] Activation-output linkage: when x=1, q>0; when x=0, q=0.

[0069] In other words, the machine's production task is either activated (and must produce a positive quantity) or completely shut down.

[0070] Production-Time Relationship: Duration d = Production q ÷ (Capacity × Yield)

[0071] The effective production capacity (production rate) of product A processed by M1 = 60 units / h × 0.95 = 57 units / h

[0072] Time per item = 1 / 57 ≈ 0.01754 hours / item ≈ 63.16 seconds / item, rounded up to 64 seconds / item

[0073] d = q × 64 seconds

[0074] Time window: t end =t start +d

[0075] Inactive and zeroed out: When x=0, t start =t end =d=0

[0076] Segmentation order: Segment 1 can only be activated when segment 0 is activated; segment 2 can only be activated when segment 1 is activated. Between adjacent segments on the same machine, the start time of the segment executed later must be later than the end time of the segment executed earlier.

[0077] In addition, the parameter constraints include: for each segment, the sum of the start times of the duration segments of that segment equals the end time. For each segment, the product of the duration of that segment, the production rate, and the yield rate equals the output.

[0078] It is evident that by configuring parameter constraints for each segment, and by determining the corresponding parameter constraints for each segment, differentiated and precise constraints can be achieved for different products and equipment. This ensures that the production plan conforms to the natural production patterns of the equipment, improves production feasibility, and allows for continuous adjustments within a time frame, thereby enhancing flexibility.

[0079] S104. Based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point, determine the production constraints corresponding to each segment.

[0080] Production constraints refer to the restrictions on the expected production results of a segment. They link the expected inventory target to the production activities of a segment, ensuring that the production behavior of that segment enables the actual inventory to reach or approach the expected value at the expected time point. Production constraints are typically determined based on the production task, specifically the expected time point, expected finished goods inventory, and expected process inventory extracted from the production task. Expected process inventory can be understood as a semi-finished goods inventory constraint. Expected process inventory is used to control the material balance between upstream and downstream processes, prevent excessively rapid production in one process leading to downstream stockpiling, and prevent excessively slow production in one process leading to downstream material shortages.

[0081] S105. Using the production constraints and parameter constraints corresponding to each segment as constraints, and taking the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period as targets, determine the parameter values ​​of each segment. The parameters of each segment include: activation parameters, production parameters, and duration parameters.

[0082] In this optimization problem, the production constraints and parameter constraints corresponding to each segment are used as the limiting conditions. The expected finished goods inventory and expected process inventory at the expected time point are used as the optimization direction, i.e., tending to approach or reach the expected finished goods inventory and expected process inventory at the expected time point. The parameters of each segment are solved. The parameter values ​​of each segment are used to determine the executable production plan, specifically which production equipment executes which process of which product at what time. The activation parameter is used to determine whether a segment is activated, i.e., whether a production equipment executes the segment, specifically whether a production equipment executes the process of the product within the corresponding time period. The output parameter can refer to the quantity produced. The duration parameter can refer to the time period between the start time point and the end time point of the segment. The duration parameter can include: start time point, end time point, and duration.

[0083] The technical solution of this invention sets desired finished product inventory and desired process inventory as production targets. This allows equipment to continue production in segments until the inventory reaches the target level, rather than immediately switching after completing an order. This significantly reduces frequent changeover operations caused by order switching, lowers changeover time and labor costs, and increases effective equipment production time. Each segment is independent of the batch size of a specific order, using inventory constraints as boundary conditions for continuous production. Small-batch orders only affect the rate of inventory consumption, without directly driving equipment start-up, shutdown, or switching, thus effectively suppressing production task fragmentation. Through joint optimization of segment parameters (activation parameters, output parameters, and duration parameters), upstream processes can begin production in advance based on process inventory constraints, eliminating the need for downstream processes to wait due to material shortages. Simultaneously, it avoids equipment idling or downtime due to a lack of orders, achieving continuous connection between production stages and significantly improving overall equipment utilization.

[0084] In an optional embodiment, determining the production constraints corresponding to each segment based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point includes: determining the production demand constraints between the production parameters and expected inventory of each segment to which each product belongs, based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point; determining the minimum batch size constraint of each segment based on the minimum production time, the products corresponding to each segment, and the capacity yield corresponding to each segment; determining the non-overlapping equipment time constraint based on the production equipment and duration of each segment; determining the mold change time period constraint based on the production equipment, duration, and mold change time of each segment; and determining the process demand constraint based on the difference between the output of the subsequent process and the output of the preceding process in the adjacent process of each segment and each product.

[0085] In this context, production demand constraints refer to constraints ensuring that predicted production is greater than or equal to expected production. Production parameters refer to the quantity of items produced in segments, which are actually predicted values. Expected inventory refers to the expected finished goods inventory and expected process inventory of all segments of a product at each expected time point. At each order delivery time, i.e., at each expected time point, the predicted production (inventory level) of the product must be greater than or equal to the expected production (cumulative order demand) up to that expected time point. For example, if product A has three orders, with 100 units delivered on day 3, 200 units on day 5, and 150 units on day 7, then the requirements are: on day 3, the predicted production of product A ≥ 100 (satisfying the first order); on day 5, the predicted production of product A ≥ 300 (satisfying the sum of the first two orders); and on day 7, the predicted production of product A ≥ 450 (satisfying the sum of all three orders). If an expected time point cannot be met, the order is marked as delayed, and the earliest fulfillment time point is calculated, i.e., the time point when the inventory level curve first reaches the required height.

[0086] In one example, for each product and process combination, the sum of the projected outputs for all segments of all production equipment must not be less than the expected inventory. Specifically:

[0087] Product A - Thermal constraints:

[0088] q(A, thermal, M1, segment 0)+q(A, thermal, M1, segment 1)+q(A, thermal, M1, segment 2)+q(A, thermal, M2, segment 0)+q(A, thermal, M2, segment 1)+q(A, thermal, M2, segment 2)≥2300.

[0089] Constraints satisfied by product A - machining:

[0090] q(A, machined, M3, segment 0) + q(A, machined, M3, segment 1) + q(A, machined, M3, segment 2) ≥ 2500.

[0091] Product B-thermal constraint: q(B, thermal, M1, segment 0) + ... + q(B, thermal, M2, segment 2) ≥ 1500.

[0092] Constraints to be satisfied by product B-machining:

[0093] q(B, machined, M4, segment 0) + q(B, machined, M4, segment 1) + q(B, machined, M4, segment 2) ≥ 1500.

[0094] The product C-thermal constraint is: q(C, thermal, M1, segment 0) + ... + q(C, thermal, M2, segment 2) ≥ 350.

[0095] The minimum batch size constraint is used to constrain the minimum production quantity for each active segment. In practice, each production start cannot be lower than the minimum production batch size to avoid overly fragmented production sub-plans. The production rate of one item per piece for the production equipment corresponding to the segment can be calculated based on its capacity and yield. The minimum number of items to be produced, i.e., the minimum production quantity, is then calculated based on the minimum duration and production rate. The output parameter value for the segment should be greater than or equal to this minimum production quantity.

[0096] In one example, once each production machine is activated (x=1), the total output of that product on that machine must not be less than the minimum production output. M1 processes product A at a rate of 57 units / h. M2 processes product A at a rate of 49.5 units / h. M1 processes product B at a rate of 47.5 units / h.

[0097] Minimum production time = max(12 hours, mold change time 4 hours) = 12 hours = 43200 seconds

[0098] Minimum production capacity of product A processed by M1 = 57 pieces / h × 12h = 684 pieces

[0099] The minimum production capacity of product A processed by M2 is 49.5 pieces / hour × 12 hours = 594 pieces.

[0100] The minimum production capacity of product B processed by M1 is 47.5 pieces / hour × 12 hours = 570 pieces.

[0101] The equipment time non-overlap constraint is used to ensure that only one production task (segment) can be executed by the same production equipment at any given time. For example, taking machine M1 as an example, the possible active tasks on M1 include: A - 3 segments of thermal operation, B - 3 segments of thermal operation, and C - 3 segments of thermal operation, for a total of 9 selectable intervals. The equipment time non-overlap constraint is that any two activated intervals must not overlap in time.

[0102] The mold changeover time constraint is used to restrict the time required for switching from product A to product B on the same production equipment, during which the equipment cannot produce. In some embodiments, when M1 switches from product A to product B (or vice versa), a 4-hour mold changeover time is required. An ordering variable β∈{0,1} is introduced:

[0103]

[0104]

[0105] Process requirement constraints are used in scenarios where product manufacturing involves multiple processes (such as stamping, welding, and painting), ensuring that subsequent processes can only begin after the preceding processes have produced sufficient material. Output requirement constraints are essentially finished product level constraints, while process requirement constraints are essentially semi-finished product level constraints. At any given time, the predicted output (subsequent level) of the subsequent process must be greater than or equal to the predicted output (previous level) of the preceding process up to that time.

[0106] In one example, the production demand constraint for product A is as follows:

[0107] At each expected time point for product A, the predicted output of finished goods must meet the expected finished goods inventory (cumulative finished goods inventory) up to that expected time point.

[0108] Calculate the cumulative finished goods inventory at each desired time point. Specifically, for each activated segment of the machining process, calculate how many units have been produced in that segment before the delivery date (continuous warehousing model):

[0109] For ORD-001 (delivery required in the 96th hour, cumulative demand 800 units):

[0110]

[0111] The cumulative output of all segments of the machining process up to hour 96:

[0112]

[0113]

[0114] For ORD-002 (delivery required in the 192nd hour, cumulative demand 2000 units):

[0115]

[0116]

[0117] For ORD-003 (delivery required in the 288th hour, cumulative demand 2600 units):

[0118]

[0119]

[0120] If inventory is insufficient at any point in time (sum of output < demand), the order is marked as delayed (Boolean variable isLate = 1), and the delay time (the time difference between the delivery date and the actual fulfillment of demand) is calculated. These delay metrics are fed into the objective function.

[0121] The process requirement constraints for product A (semi-finished product), also known as the semi-finished product inventory level constraints (inter-process material balance constraints):

[0122] The aforementioned production demand constraints ensure that there are sufficient finished goods in the warehouse for delivery. However, in multi-process production, there is another key issue: the output of the preceding process is the raw material for the following process. If the following process starts too early and its consumption rate exceeds the supply rate of the preceding process, a raw material shortage will occur, meaning that the following process wants to process, but the preceding process has not yet produced enough semi-finished products.

[0123] The core idea of ​​inventory level-driven inventory management is extended from the finished product level to the semi-finished product level between processes, establishing a reservoir constraint for intermediate materials between each pair of adjacent processes.

[0124] Intermediate material constraints for Product A (thermal and machined):

[0125] Intermediate materials: Processing steps for thermally finished product A, initial level: 200 units (initial WIP inventory): Continuous production or consumption rate for each stage:

[0126]

[0127] Water level timeline of the pool (Continuous model):

[0128]

[0129]

[0130]

[0131]

[0132] Throughout the process The fact that the number of semi-finished products remained constant (with a minimum of 57 units at 43.9 hours) indicates that the supply of semi-finished products under the production plan was sufficient and the constraints were met.

[0133] The machining process's consumption rate (78.4 units / hour) exceeds the output rate of a single thermal production unit (57 units / hour). Even with an initial inventory of 200 units of work-in-progress (WIP) buffer, it can only sustain the process for approximately 9.35 hours. After that, the water level will turn negative, meaning that the machining process is attempting to consume material that has not yet been thermally produced—which is physically impossible.

[0134] Once the solver detects that the constraint has been violated, it will automatically adjust the solution:

[0135] Increase the number of parallel production equipment for the thermal processing (such as simultaneously activating M2) so that the total injection rate (106.5 pieces / h) exceeds the consumption rate (78.4 pieces / h), and the net rate is always positive; or postpone the start time of the machining process to allow the water tank to accumulate sufficient buffer; or perform machining in segments, pausing before the initial inventory of WIP is exhausted, and waiting for the thermal processing to replenish before continuing.

[0136] Intermediate material constraints for Product B (thermal and machined):

[0137] Intermediate materials: Thermal finished product process for product B, initial water level: 0 units (no initial WIP inventory):

[0138]

[0139] This represents the total output of the thermal processing steps. This represents the total output of the machining process. Since the initial inventory (WIP) is 0, the cumulative consumption of the machining process must be zero before the thermal processing process begins production—that is, machining cannot begin before thermal processing. Even if thermal processing has already started production, machining must wait until the cumulative output of thermal processing is sufficient in time to continuously cover its own cumulative consumption; otherwise, the water level will still drop below zero at some point.

[0140] Product C (only one process): Product C only has one thermal process, and there is no material transfer between processes, so there is no need for semi-finished product water level constraints.

[0141] A unified perspective on semi-finished product constraints and finished product constraints:

[0142] Thus, the inventory level-driven mechanism constitutes a complete two-layer system, with both layers employing the same continuous piecewise linear model (Ψ function):

[0143]

[0144] This represents the total output of the preceding process. This represents the total output of the subsequent processes. This represents the total output of the final process. The first layer ensures that the material flow between processes remains continuously balanced over time—the cumulative consumption of the subsequent process at any given time does not exceed the cumulative output of the preceding process plus the initial work-in-process (WIP) inventory. The second layer ensures that the finished goods inventory is sufficient to deliver orders on time. Together, these two layers constitute a complete inventory level-driven constraint system.

[0145] It is evident that by establishing specific details of segmented production constraints based on production tasks, the decoupling of objectives and behaviors is achieved, so that production plans are no longer directly tied to specific orders, thereby reducing sensitivity to order fluctuations. Linkage constraints between finished and semi-finished products are established to achieve material balance throughout the entire process, avoiding excessive backlog upstream or production stoppages due to material shortages downstream. Existing targets act as a buffer to absorb short-term demand fluctuations, ensuring continuous and stable segmented production, significantly reducing frequent model changes caused by small-batch orders, and enhancing the robustness and adaptability of the system.

[0146] In an optional embodiment, determining the parameter values ​​of each segment, using the production constraints and parameter constraints corresponding to each segment as constraints and the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period as objectives, includes: determining the parameter values ​​of each segment and using them as the current parameter value group; determining the target penalty score of the objective function of the production task based on the current parameter value group, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period; adjusting the current parameter value group based on the production constraints, parameter constraints, and target penalty score corresponding to each segment to obtain a target parameter value group that satisfies the production constraints and parameter constraints corresponding to each segment and minimizes the target penalty score; and determining the parameter values ​​of each segment based on the target parameter value group.

[0147] The process involves solving for the parameters of each segment, using the production constraints and parameter constraints corresponding to each segment as constraints, and the expected finished goods inventory and expected process inventory of each product at the corresponding expected time point within the target time period as objectives. Initial values ​​for the parameters of each segment can be tentatively determined to form the current parameter value set. By combining the production constraints, parameter constraints, and the expected finished goods inventory and expected process inventory at the expected time point, the parameter values ​​of each parameter in the current parameter value set are adjusted to obtain the target parameter value set that satisfies the constraints and minimizes the target penalty score. The target penalty score measures the degree of deviation between the predicted output and the expected inventory. The smaller the target penalty score, the lower the deviation; the larger the target penalty score, the higher the deviation. The target parameter value set can be the parameter values ​​of each segment after adjustment.

[0148] It is evident that by using the production constraints and parameter constraints corresponding to each segment as constraints, and taking the expected finished goods inventory and expected process inventory of each product at the corresponding expected time point in the target time period as objectives, it is possible to combine mandatory constraints and expected objectives to determine the parameters of the production plan. This ensures the engineering feasibility of the parameters of the production plan obtained, as well as the validity of the parameter values. It also allows for balancing multiple objectives and obtaining the optimal solution of the production plan in the effective direction, thereby improving the efficiency and accuracy of parameter value calculation.

[0149] In an optional embodiment, determining the target penalty score of the objective function of the production task based on the current parameter value set, the expected finished goods inventory and the expected process inventory of each product at the corresponding expected time point within the target time period includes: determining the predicted inventory of each product at the corresponding expected time point based on the current parameter value set, the expected finished goods inventory and the expected process inventory of each product at the corresponding expected time point within the target time period; the predicted inventory includes the predicted finished goods inventory and the predicted process inventory; calculating the number of delayed orders, the delay duration, and the overproduction quantity based on the predicted inventory, expected finished goods inventory, and expected process inventory of each product at the corresponding expected time point; and based on the current parameter value set, the expected finished goods inventory, and the expected process inventory of each product at the corresponding expected time point. The parameter value group is used to count the number of mold changes for each of the production devices within the target time period. Based on the current parameter value group, the duration of each segment is determined, and segments shorter than a preset duration threshold are selected. The extremely short duration difference between the duration of the selected segments and the duration threshold is calculated. Based on the current parameter value group, the number of interruptions and activations for each of the production devices are counted. Based on the current parameter value group, the total time consumption of the production task is determined. The number of delayed orders, the delay duration, the overproduction quantity, the number of mold changes, the extremely short duration difference, the number of interruptions, the number of activations, and the total time consumption are weighted and summed to obtain the target penalty score of the objective function of the production task.

[0150] The objective function can be an expression for calculating the target penalty score, used to evaluate the quality of the current parameter value set. The number of delayed orders can be the number of delayed orders, which can be orders where the predicted inventory based on the current parameter value set is less than the expected inventory at the expected time point. The delay duration can be the difference between the time point when the predicted inventory reaches the expected inventory based on the current parameter value set and the expected time point, where the delayed arrival time point is after the expected time point. The overproduction quantity can be the difference between the predicted inventory and the expected inventory based on the current parameter value set. The number of mold changes can be the number of times production equipment switches to produce different products. The extremely short duration difference can be the difference between the duration of the duration less than the duration threshold and the duration threshold. The number of interruptions can be the number of times the task is interrupted. The number of activations can be the number of production equipment segments with an activation parameter of 1. The total time consumption can be the difference between the end time of the last segment and the start time of the target time period. For example, the objective function is... :

[0151]

[0152] in, Priority for order o It is a Boolean expression indicating whether an order is delayed (1 = delayed, 0 = on time). This refers to the number of delayed orders. The delay time (in seconds) for order o is 0 if there is no delay. It is the delay duration (a statistical value of the delay duration of all delayed orders). Penalty for extremely short tasks. It is the number of mold changes (a statistical value of the number of mold changes for all production equipment). It represents the total number of preemptions (task interruptions), i.e., the number of interruptions. This is the total number of activated machines, i.e., the number of activations. It is the amount of overproduction. This is the total completion time (the end time of the last task). The priority and weight of the number of delayed orders, delay duration, extremely short duration difference, number of mold changes, number of interruptions, number of activations, number of overproductions, and total time consumption correspond. The higher the priority, the greater the weight; the lower the priority, the smaller the weight. w1, w2, w3, w4, w5, w6, w7, and w8 are the weights of the number of delayed orders, delay duration, extremely short duration difference, number of mold changes, number of interruptions, number of activations, number of overproductions, and total time consumption, respectively. For example, the values ​​of w1, w2, w3, w4, w5, w6, w7, and w8 are 1010, 107, 5×10⁶, 106, 105, 105, 1, and 10, respectively.

[0153] Based on the current parameter value set, determine the predicted finished goods inventory and predicted process inventory corresponding to each expected time point. Then, based on the expected finished goods inventory and expected process inventory, identify delayed orders where the expected finished goods inventory is greater than the predicted finished goods inventory and / or the expected process inventory is greater than the predicted process inventory. Count the number of delayed orders. Furthermore, for each delayed order, determine the predicted completion time point for the expected finished goods inventory and expected process inventory, and use this as the delayed time point. Calculate the difference duration between the delayed time point and the expected time point, and count the difference duration for all delayed orders to obtain the delayed duration.

[0154] Based on the predicted process inventory and the expected process inventory corresponding to the end time point, determine the difference between the predicted process inventory that is greater than the expected finished product inventory and the expected process inventory, and obtain the overproduction quantity.

[0155] Based on the current parameter value set, determine the number of times the same production equipment switches products, and use this number as the mold change count.

[0156] Based on the current parameter values, the segments are grouped according to the production equipment. If, within the same production equipment, the start time of a later segment coincides with the end time of a previous segment, the later segment has a higher priority than the previous segment, and a task interruption is determined. The total number of task interruptions across all production equipment is counted to obtain the interruption count.

[0157] Based on the current parameter value group, determine the segments with an activation parameter of 1, and count the number of production equipment involved in these segments to obtain the activation quantity.

[0158] Extremely short duration difference: For each activated segment, if its duration is shorter than the minimum duration (duration threshold). (12 hours) then a penalty will be applied based on the difference. The difference for extremely short durations is:

[0159]

[0160] in, This refers to the s-th segment of process j on machine m for product p. Let s be the duration of the s-th segment of process j on machine m for product p.

[0161] For each product-process, if the total output exceeds the demand, a penalty is imposed for the excess quantity. Overproduction quantity:

[0162]

[0163] in, Let p be the total output of process j across all machines and all sections. The actual production demand for product p is calculated through reverse propagation for process j.

[0164] By using weights, high-priority metrics, such as the number of delayed orders, are prioritized for fulfillment. For ORD-001 (priority 5) and ORD-003 (priority 1), on-time delivery of ORD-001 will be prioritized. The weight of delays for the lowest priority orders is far greater than the weight of mold changeovers. Therefore, the production plan will not sacrifice the delivery of any order to reduce mold changeovers.

[0165] As can be seen, by calculating multiple intermediate data points using the current parameter value set, the expected finished product inventory and the expected process inventory at the expected time point, and then weighting and summing them to obtain the target penalty score of the objective function, it is possible to flexibly express the differences under different production scenarios. At the same time, it preserves the compensability between the intermediate data. For example, a slight deterioration in one intermediate data point can be exchanged for a significant improvement in another intermediate data point. This trade-off mechanism avoids extreme cases under hard constraints, significantly expands the feasible solution space, improves the success rate of the solution, supports horizontal comparison and sensitivity analysis between different parameter sets, and provides a clear quantitative basis for production planning. Under the premise of ensuring production feasibility, it achieves an effective trade-off of multiple objectives, flexibility in scenario adaptation, and transparency of solution results.

[0166] In an optional embodiment, adjusting the current parameter value set according to the production constraints, parameter constraints, and target penalty score corresponding to each segment to obtain a target parameter value set that satisfies the production constraints and parameter constraints corresponding to each segment and minimizes the target penalty score includes: determining whether the current parameter value set satisfies the production constraints and parameter constraints corresponding to each segment; when it is determined that the current parameter value set does not satisfy the production constraints or parameter constraints corresponding to each segment, adjusting the current parameter value set, updating the current parameter value set, and re-determining whether the current parameter value set satisfies the production constraints and parameter constraints corresponding to each segment; when it is determined that the current parameter value set satisfies the production constraints or parameter constraints corresponding to each segment, calculating the target penalty score of the current parameter value set. Penalty score; when it is determined that the current parameter value group does not meet the iteration completion condition, the current parameter value group is adjusted to obtain a new parameter value group; calculate the target penalty score of the new parameter value group that satisfies the production constraints or parameter constraints corresponding to each segment; when the target penalty score of the new parameter value group is less than that of the current parameter value group, update the current parameter value group according to the new parameter value group, and readjust the current parameter value group, and update the target penalty score of the new parameter value group; when the target penalty score of the new parameter value group is greater than or equal to that of the current parameter value group, readjust the current parameter value group, and update the target penalty score of the new parameter value group; when it is determined that the current parameter value group meets the iteration completion condition, the current parameter value group is determined as the target parameter value group.

[0167] Here, constraints are mandatory limitations, and the objective is the optimization direction. A set of current parameter values ​​that satisfy the constraints can be chosen as the initial values, and these values ​​are continuously adjusted to continuously reduce the target penalty score. The iteration completion condition is used to determine whether the current parameter value set has been adjusted completely. The iteration completion condition can be whether the target penalty score has converged, or whether the number of adjustments is greater than or equal to a preset threshold, etc.

[0168] An example of constraints taking effect: In a certain production plan, only M1 is used for thermal processing (rate 57 pieces / h), while the machining of M3 starts simultaneously with M1 from hour 0 (rate 78.4 pieces / h):

[0169]

[0170]

[0171] If the water level drops to zero, violating the constraints, return to readjust or redetermine the current parameter value group.

[0172] A CP-SAT (Constraint Programming–Satisfiability) hybrid solver can be used to solve for the current set of parameter values. The core workflow of the solver is as follows:

[0173] 1. Initial value determination

[0174] First, for all activation parameters x (Boolean variables, domain {0,1}), there's a tendency to initially try deactivating x=0. For the output parameter q, a strategy of "selecting the variable with the smallest domain" is used, first determining the output with the most constraints. Time parameter... , The duration d is calculated by constraint propagation.

[0175] Once the solver generates an initial, tentative value (e.g., x(A, thermal, M1, segment 0) = 1, q = 1200), it automatically infers its impact. For example:

[0176] x(A, Thermal Engineering, M1, Section 0) = 1, q(A, Thermal Engineering, M1, Section 0) = 1200

[0177] Propagation chain: d = 1200 × 64 seconds = 76800 seconds = 21.3 hours = + 21.3h, machine M1 is in [ , [+21.3h] is occupied, and the start time of other tasks using M1 is postponed. If the postponement results in insufficient inventory for an order at the delivery date, a conflict is detected, backtracking is performed, and the process is recorded to learn how to avoid this combination.

[0178] 2. Large Neighborhood Search (LNS)

[0179] After finding an initial feasible solution, i.e., the current set of parameter values, the solver selects a subset of variables to "release" (restore to an undecided state) and solves for them again. For example:

[0180] Iteration 1: Release all tasks on M1 and re-optimize the production schedule of M1; it is found that producing product A simultaneously on M1 and M2 can meet the ORD-001 delivery date faster; the target value is improved.

[0181] Iteration 2: Release all segments of product A and re-optimize the multi-machine allocation of product A; it was found that splitting product A into M1 (1400 units) and M2 (900 units) can balance the load; the target value was further improved.

[0182] 3. Parallel Search

[0183] CP-SAT runs different search strategies simultaneously on multiple threads. For example: Thread 1: Default search (CDCL + constraint propagation); Thread 2: Randomly restarted search; Thread 3: LNS (fix 50% of variables, release 50%); Thread 4: LNS (fix 80% of variables, release 20%); Thread 5: Linear relaxation-guided search; Thread 6: Goal-oriented search. Once any thread finds a better solution, it broadcasts it to all threads as the new current parameter value set.

[0184] When the iteration completion condition is met, output the current parameter value set and use it as the target parameter value set.

[0185] It is evident that by first determining feasible solutions that satisfy the constraints, and then iteratively adjusting within the neighborhood, accepting new solutions only when the penalty score decreases, the algorithm moves from a feasible solution as the starting point and remains within the feasible region. This avoids the large amount of constraint verification and backtracking calculations caused by the frequent generation of infeasible solutions, significantly improving search efficiency. Secondly, the unidirectional movement criterion of only accepting better solutions ensures that the penalty score monotonically decreases during iteration, giving the algorithm a clear convergence direction and stable termination conditions, avoiding oscillations and divergences that may be caused by non-monotonic search. Thirdly, this strategy only adjusts the local neighborhood of the current solution in each round, rather than resolving the global model each time, greatly reducing the computational cost of a single iteration and enabling it to efficiently handle large-scale, multi-variable production scheduling problems. When external disturbances cause the current solution to fail, the adjustment process can be quickly restarted while retaining existing optimization results, enhancing the robustness and practicality of the algorithm in real-world production environments.

[0186] In an optional embodiment, after determining the parameter values ​​of each segment, the method further includes: according to the parameter values ​​of each segment, controlling the corresponding production equipment to execute the process steps of the corresponding product at the start time point of the duration segment corresponding to each segment; and controlling the corresponding production equipment to stop executing the process steps of the corresponding product at the end time point of the duration segment corresponding to each segment.

[0187] Specifically, the activation parameter determines whether to send an execution command to the production equipment. The duration parameter determines the timing of sending the execution command to the production equipment and the timing of sending the stop command.

[0188] As can be seen, by solving the segmented parameters and converting them into actual control commands for the physical equipment, determining whether to activate the production equipment corresponding to the segment based on the activation parameters, and determining the time period for running the production equipment corresponding to the segment based on the duration parameters, precise synchronization between the production plan time point and the start-up of the production equipment is achieved. This avoids manual estimation or delays, precise timed shutdowns, and avoids overproduction or underproduction. It transforms the production process from a passive and responsive approach to a proactive and planned approach, reducing uncertainty at the execution level and improving execution reliability.

[0189] Figure 3 This is a schematic diagram of a product manufacturing equipment control device provided in an embodiment of the present invention. This device can execute a product manufacturing equipment control method. The device can be implemented in hardware and / or software, and can be configured in an electronic device that carries a certain data processing capability.

[0190] See Figure 3 The product manufacturing equipment control device shown includes:

[0191] The first expectation determination module 301 is used to determine the expected finished goods inventory of at least one product at at least one expected time point in the target time period based on the production task.

[0192] The second expectation determination module 302 is used to determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point based on the process flow corresponding to each product.

[0193] The parameter constraint determination module 303 is used to determine at least one segment and the parameter constraints of each segment based on each product, the corresponding process and production equipment of each product.

[0194] The production constraint determination module 304 is used to determine the production constraints corresponding to each segment based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point.

[0195] The production parameter determination module 305 is used to determine the parameter values ​​of each segment based on the production constraints and parameter constraints corresponding to each segment, and based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period. The parameters of each segment include: activation parameters, production parameters, and duration parameters.

[0196] The technical solution of this invention sets desired finished product inventory and desired process inventory as production targets. This allows equipment to continue production in segments until the inventory reaches the target level, rather than immediately switching after completing an order. This significantly reduces frequent changeover operations caused by order switching, lowers changeover time and labor costs, and increases effective equipment production time. Each segment is independent of the batch size of a specific order, using inventory constraints as boundary conditions for continuous production. Small-batch orders only affect the rate of inventory consumption, without directly driving equipment start-up, shutdown, or switching, thus effectively suppressing production task fragmentation. Through joint optimization of segment parameters (activation parameters, output parameters, and duration parameters), upstream processes can begin production in advance based on process inventory constraints, eliminating the need for downstream processes to wait due to material shortages. Simultaneously, it avoids equipment idling or downtime due to a lack of orders, achieving continuous connection between production stages and significantly improving overall equipment utilization.

[0197] Optionally, the parameter constraints of each segment include: the activation parameter and the production parameter of each segment have the same value type; the numerical relationship between the production parameter of each segment and the duration of the duration segment is determined according to the production capacity yield of each segment; the activation parameter of each segment and the duration segment parameter have the same value type; and the dependency relationship between the activation parameter of each segment and the segment corresponds.

[0198] Optionally, the production constraint determination module 304 is specifically used for:

[0199] Based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point, determine the production demand constraints between the production parameters and expected inventory of each segment of each product.

[0200] The minimum batch size constraint for each segment is determined based on the minimum production time, the products corresponding to each segment, and the capacity yield corresponding to each segment.

[0201] Based on the production equipment and duration of each segment, determine the constraint that equipment time does not overlap;

[0202] The mold change time constraints are determined based on the production equipment, duration, and mold change time of each segment.

[0203] The process requirement constraints are determined based on the difference between the output of the next process and the output of the previous process in each of the segments and products.

[0204] Optional, the production parameter determination module 305 is specifically used for:

[0205] Determine the parameter values ​​for each segment and use them as the current parameter value group;

[0206] Based on the current parameter value set, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period, the target penalty score of the objective function of the production task is determined;

[0207] Based on the production constraints, parameter constraints, and target penalty scores corresponding to each segment, the current parameter value set is adjusted to obtain a target parameter value set that satisfies the production constraints and parameter constraints corresponding to each segment and minimizes the target penalty score.

[0208] Based on the target parameter value group, determine the parameter values ​​for each segment.

[0209] Optional, the production parameter determination module 305 is specifically used for:

[0210] Based on the current parameter value set, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period, the predicted inventory of each product at the corresponding expected time point is determined; the predicted inventory includes the predicted finished product inventory and the predicted process inventory.

[0211] Based on the predicted inventory, expected finished goods inventory, and expected process inventory of each product at the corresponding expected time point, calculate the number of delayed orders, the duration of delay, and the amount of overproduction.

[0212] Based on the current parameter value set, count the number of mold changes for each of the production equipment within the target time period;

[0213] Based on the current parameter value group, determine the duration of each segment, and filter out segments with a duration less than a preset threshold.

[0214] Calculate the extremely short duration difference between the duration of the selected segment and the duration threshold;

[0215] Based on the current parameter value group, count the number of interruptions and activations of each of the production devices;

[0216] Based on the current parameter value set, determine the total time consumed by the production task;

[0217] The target penalty score of the objective function of the production task is obtained by weighted summing of the number of delayed orders, the delay duration, the overproduction quantity, the number of mold changes, the difference in extremely short duration, the number of interruptions, the number of activations, and the total time consumption.

[0218] Optional, the production parameter determination module 305 is specifically used for:

[0219] Determine whether the current parameter value group satisfies the production constraints and parameter constraints corresponding to each segment;

[0220] When it is determined that the current parameter value group does not meet the production constraints or parameter constraints corresponding to each segment, the current parameter value group is adjusted and updated, and the current parameter value group is re-evaluated to determine whether the current parameter value group meets the production constraints and parameter constraints corresponding to each segment.

[0221] When it is determined that the current parameter value group satisfies the production constraints or parameter constraints corresponding to each segment, the target penalty score of the current parameter value group is calculated.

[0222] When it is determined that the current parameter value group does not meet the iteration completion condition, the current parameter value group is adjusted to obtain a new parameter value group;

[0223] Calculate the target penalty score for the new parameter value set that satisfies the production constraints or parameter constraints corresponding to each segment;

[0224] When the target penalty score of the new parameter value group is less than that of the current parameter value group, the current parameter value group is updated according to the new parameter value group, the current parameter value group is readjusted, and the target penalty score of the new parameter value group is updated.

[0225] When the target penalty score of the new parameter value group is greater than or equal to that of the current parameter value group, the current parameter value group is readjusted and the target penalty score of the new parameter value group is updated.

[0226] When it is determined that the current parameter value group meets the iteration completion condition, the current parameter value group is determined as the target parameter value group.

[0227] Optional, the product manufacturing equipment control device also includes:

[0228] The production control module is used to, after determining the parameter values ​​of each segment, control the corresponding production equipment to execute the process steps of the corresponding product at the start time point of the duration segment corresponding to each segment, based on the parameter values ​​of each segment.

[0229] At the end of the duration segment corresponding to each segment, the corresponding production equipment is controlled to stop executing the process steps of the corresponding product.

[0230] The product manufacturing equipment control device provided in the embodiments of the present invention can execute the product manufacturing equipment control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the product manufacturing equipment control method.

[0231] The data acquisition and other aspects involved in the technical solutions of this invention comply with relevant laws and regulations and do not violate public order and good morals.

[0232] Figure 4 A schematic diagram of an electronic device 400 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0233] like Figure 4 As shown, the electronic device 400 includes at least one processor 401 and a memory, such as a read-only memory (ROM) 402 or a random access memory (RAM) 403, communicatively connected to the at least one processor 401. The memory stores computer programs executable by the at least one processor. The processor 401 can perform various appropriate actions and processes based on the computer program stored in the ROM 402 or loaded into the RAM 403 from storage unit 408. The RAM 403 may also store various programs and data required for the operation of the electronic device 400. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0234] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0235] Processor 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 401 performs the various methods and processes described above, such as product manufacturing equipment control methods.

[0236] In some embodiments, the product manufacturing equipment control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the product manufacturing equipment control method described above may be performed. Alternatively, in other embodiments, processor 401 may be configured to perform the product manufacturing equipment control method by any other suitable means (e.g., by means of firmware).

[0237] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0238] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0239] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0240] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0241] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0242] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0243] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0244] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling product manufacturing equipment, characterized in that, The method includes: Based on the production task, determine the expected finished goods inventory of at least one product at at least one expected time point within the target time period; Based on the process flow corresponding to each product, determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point; Based on each product, the corresponding process and production equipment, at least one segment is determined, along with parameter constraints for each segment. Based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point, determine the production constraints corresponding to each segment; Using the production constraints and parameter constraints corresponding to each segment as constraints, and taking the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period as targets, the parameter values ​​of each segment are determined. The parameters of each segment include: activation parameters, production parameters, and duration parameters.

2. The method according to claim 1, characterized in that, The parameter constraints for each segment include: the activation parameter and the production parameter of each segment have the same value type; the numerical relationship between the production parameter of each segment and the duration of the duration segment is determined according to the production yield of each segment; the activation parameter of each segment and the duration segment parameter have the same value type; and the dependency relationship between the activation parameter of each segment and the segment corresponds.

3. The method according to claim 1, characterized in that, The step of determining the production constraints corresponding to each segment based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point includes: Based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point, determine the production demand constraints between the production parameters and expected inventory of each segment of each product. The minimum batch size constraint for each segment is determined based on the minimum production time, the products corresponding to each segment, and the capacity yield corresponding to each segment. Based on the production equipment and duration of each segment, determine the constraint that equipment time does not overlap; The mold change time constraints are determined based on the production equipment, duration, and mold change time of each segment. The process requirement constraints are determined based on the difference between the output of the next process and the output of the previous process in each of the segments and products.

4. The method according to claim 1, characterized in that, The step of determining the parameter values ​​for each segment, using the production constraints and parameter constraints corresponding to each segment as constraints and the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period as targets, includes: Determine the parameter values ​​for each segment and use them as the current parameter value group; Based on the current parameter value set, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period, the target penalty score of the objective function of the production task is determined; Based on the production constraints, parameter constraints, and target penalty scores corresponding to each segment, the current parameter value set is adjusted to obtain a target parameter value set that satisfies the production constraints and parameter constraints corresponding to each segment and minimizes the target penalty score. Based on the target parameter value group, determine the parameter values ​​for each segment.

5. The method according to claim 4, characterized in that, The step of determining the target penalty score of the objective function of the production task based on the current parameter value group, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period, includes: Based on the current parameter value set, the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period, the predicted inventory of each product at the corresponding expected time point is determined; the predicted inventory includes the predicted finished product inventory and the predicted process inventory. Based on the predicted inventory, expected finished goods inventory, and expected process inventory of each product at the corresponding expected time point, calculate the number of delayed orders, the duration of delay, and the amount of overproduction. Based on the current parameter value set, count the number of mold changes for each of the production equipment within the target time period; Based on the current parameter value group, determine the duration of each segment, and filter out segments with a duration less than a preset threshold. Calculate the extremely short duration difference between the duration of the selected segment and the duration threshold; Based on the current parameter value group, count the number of interruptions and activations of each of the production devices; Based on the current parameter value set, determine the total time consumed by the production task; The target penalty score of the objective function of the production task is obtained by weighted summing of the number of delayed orders, the delay duration, the overproduction quantity, the number of mold changes, the difference in extremely short duration, the number of interruptions, the number of activations, and the total time consumption.

6. The method according to claim 4, characterized in that, The step of adjusting the current parameter value set according to the production constraints, parameter constraints, and target penalty score corresponding to each segment to obtain a target parameter value set that satisfies the production constraints and parameter constraints corresponding to each segment and minimizes the target penalty score includes: Determine whether the current parameter value group satisfies the production constraints and parameter constraints corresponding to each segment; When it is determined that the current parameter value group does not meet the production constraints or parameter constraints corresponding to each segment, the current parameter value group is adjusted and updated, and the current parameter value group is re-evaluated to determine whether the current parameter value group meets the production constraints and parameter constraints corresponding to each segment. When it is determined that the current parameter value group satisfies the production constraints or parameter constraints corresponding to each segment, the target penalty score of the current parameter value group is calculated. When it is determined that the current parameter value group does not meet the iteration completion condition, the current parameter value group is adjusted to obtain a new parameter value group; Calculate the target penalty score for the new parameter value set that satisfies the production constraints or parameter constraints corresponding to each segment; When the target penalty score of the new parameter value group is less than that of the current parameter value group, the current parameter value group is updated according to the new parameter value group, the current parameter value group is readjusted, and the target penalty score of the new parameter value group is updated. When the target penalty score of the new parameter value group is greater than or equal to that of the current parameter value group, the current parameter value group is readjusted and the target penalty score of the new parameter value group is updated. When it is determined that the current parameter value group meets the iteration completion condition, the current parameter value group is determined as the target parameter value group.

7. The method according to claim 1, characterized in that, After determining the parameter values ​​for each segment, the process also includes: Based on the parameter values ​​of each segment, at the start time of the duration segment corresponding to each segment, the corresponding production equipment is controlled to execute the process steps of the corresponding product. At the end of the duration segment corresponding to each segment, the corresponding production equipment is controlled to stop executing the process steps of the corresponding product.

8. A product manufacturing equipment control device, characterized in that, include: The first expectation determination module is used to determine the expected finished goods inventory of at least one product at at least one expected time point in the target time period based on the production task. The second expectation determination module is used to determine the expected process inventory of at least one process corresponding to each product at the corresponding expected time point, based on the process flow corresponding to each product. The parameter constraint determination module is used to determine at least one segment and the parameter constraints of each segment based on each product, the corresponding process and production equipment of each product. The production constraint determination module is used to determine the production constraints corresponding to each segment based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point. The production parameter determination module is used to determine the parameter values ​​of each segment based on the production constraints and parameter constraints corresponding to each segment, and based on the expected finished product inventory and expected process inventory of each product at the corresponding expected time point in the target time period. The parameters of each segment include: activation parameters, output parameters, and duration parameters.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the product manufacturing equipment control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the product manufacturing equipment control method according to any one of claims 1-7.

Images