Dynamic storage intelligent sorting method, system and equipment based on production takt and medium

Abstract

The invention provides a dynamic storage intelligent sorting method, system and equipment based on production takt, and a medium, which can improve the adaptability of the sorting system to the production takt, optimize the inventory circulation efficiency, reduce the risk of production interruption caused by material mismatching or supply delay, and improve the production efficiency. The method comprises the following steps: collecting real-time parameters of production takt of each key station on a production line, and obtaining demand information of target materials to be sorted; based on the real-time parameters of the production takt and the demand information, the production takt prediction parameters and the material demand prediction quantity of each key station in a future period of time are predicted, and in combination with the current inventory state, the equipment availability and the preset optimization parameters, a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for a production line are generated and are used as the basis; and the flexible dispatching mechanism is dispatched to dynamically adjust the physical positions of the corresponding materials, then the sorting mechanism is called to sort out the target materials with the specified number from the dynamically adjusted storage locations, and then the target materials are sorted to the corresponding target stations.

Description

Technical Field

[0001] The present application relates to the field of warehouse management technology, and in particular to a dynamic warehouse intelligent sorting method, system, equipment and medium based on production rhythm. Background Art

[0002] The existing warehousing and sorting system mainly includes the following three categories: (1) Fixed-path AGV sorting system: This system is commonly used in large e-commerce / distribution centers. It uses automated guided vehicles (AGVs) to transport and sort items along a preset path to solve the problem of automated processing of large-scale, standardized orders. However, when faced with frequent adjustments to production plans or drastic fluctuations in production rhythm, this system has difficulty in re-planning the path and is slow to respond, making it difficult to achieve timely and accurate supply of materials.

[0003] (2) Static location management system based on WMS preset instructions: This system uses the warehouse management system (WMS) to issue inbound and outbound instructions to materials, so as to achieve relatively fixed storage locations or only perform periodic optimization, solving the basic tracking and inventory management problems of materials. However, this system cannot dynamically adjust the inventory layout based on the real-time material consumption rate and demand priority of the production line, which may result in long pickup routes for popular materials or unpopular materials occupying high-quality storage locations.

[0004] (3) Sorting system based on modular design: This system adopts modular design to obtain partially flexible modular sorting units. The sorting units can be expanded to a certain extent according to demand, but their scheduling logic is mostly based on historical data or fixed thresholds. In addition, the linkage with the Manufacturing Execution System (MES) is insufficient, and most of the instructions are received in a one-way manner. There is a lack of real-time perception of production rhythm data and predictive scheduling based on this data. This leads to a time difference or quantity mismatch between material supply and production demand, which easily leads to waiting or backlogs. In other words, the sorting system based on modular design has limited ability to respond to real-time dynamic changes in the production line.

[0005] In summary, existing warehousing and sorting systems suffer from insufficient efficiency and flexibility, weak intelligence and adaptability, and poor system integration and coordination. These issues make it difficult for existing warehousing and sorting systems to adapt to dynamic changes in production rhythms, lead to low material flow efficiency, suboptimal utilization of storage space, and insufficient precision in matching sorting operations with actual production needs.

[0006] Therefore, there is an urgent need for a comprehensive solution that can effectively combine the real-time beat data of the production line and dynamically adjust the warehousing strategy and sorting task priority to achieve accurate, efficient and adaptive sorting of materials. Summary of the Invention

[0007] The present application provides a method, system, device, and medium for dynamic warehousing intelligent sorting based on production rhythm to solve the problems existing in related technologies. The technical solution is as follows: In a first aspect, an embodiment of the present application provides a dynamic warehousing intelligent sorting method based on production rhythm, comprising: Collect real-time production rhythm parameters of key workstations on the production line and obtain demand information of target materials to be sorted; Based on the real-time production rhythm parameters and the demand information, calling the production forecast model to predict the production rhythm forecast parameters and material demand forecast amount of each key workstation in the future period; Based on the production cycle forecast parameters, the material demand forecast, and in combination with the current inventory status, equipment availability, and preset optimization parameters, a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for the production line are generated, wherein the dynamic storage location adjustment plan includes the corresponding materials of the target materials that need to have their physical locations adjusted, and the optimal sorting task sequence includes the target workstations corresponding to the target materials; Based on the dynamic storage location adjustment plan, a flexible scheduling mechanism in the scheduling production environment dynamically adjusts the physical location of the corresponding material; Based on the optimal sorting task sequence, the sorting mechanism in the production environment is called to pick out a specified number of the target materials from the dynamically adjusted storage locations, and then sort them to the corresponding target workstations.

[0008] In one embodiment, collecting real-time production rhythm parameters of key workstations on the production line and obtaining demand information of target materials to be sorted includes: Calling the photoelectric sensors and industrial cameras on each of the key workstations to monitor the product throughput rate and buffer material inventory level of each of the key workstations in real time; Calling the PLC controllers on each of the key workstations to read the equipment status and real-time production data of each of the key workstations; The information identification channel at the warehouse entrance is called to automatically scan the unique identification code label on the incoming material or the unique identification code on the incoming material box to obtain detailed information about the incoming material; Call the ERP system to obtain the production plan for the next period of time; Obtaining the real-time parameters of the production rhythm based on the product throughput rate, the material inventory level in the buffer zone, the equipment status, and the real-time output data; Based on the detailed information of the incoming materials and the production plan, the demand for the target material is determined to obtain the demand information.

[0009] In one embodiment, based on the real-time production rhythm parameters and the demand information, calling a production forecast model to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period includes: Performing data cleaning and feature extraction on the real-time parameters of the production rhythm and the demand information to obtain corresponding feature data; Using a specified time series forecasting model as the production forecasting model; Based on the corresponding characteristic data, the specified time series prediction model is called to predict the production rhythm prediction parameters and material demand prediction quantity of each key workstation in a future period of time.

[0010] In one embodiment, based on the production cycle forecast parameters, the material demand forecast, and in combination with the current inventory status, equipment availability, and preset optimization parameters, generating a dynamic inventory adjustment plan and an optimal sorting task sequence currently suitable for the production line includes: Taking the preset optimization parameters as the optimization target, calling the specified multi-objective optimization algorithm based on the production cycle prediction parameters, the material demand forecast, the current inventory status and the equipment availability, to generate the dynamic storage location adjustment plan and the optimal sorting task sequence.

[0011] In one embodiment, based on the dynamic inventory location adjustment plan, the flexible scheduling mechanism in the scheduling production environment dynamically adjusts the physical location of the corresponding material, including: sending the dynamic storage location adjustment plan to the WCS, and invoking the WCS to determine the current storage location, target storage location, and storage location adjustment time of the corresponding material based on the dynamic storage location adjustment plan, wherein the WCS refers to a warehouse control system; Send a location adjustment instruction to the WCS, instructing the WCS to dispatch the flexible dispatching mechanism to transfer the corresponding material from the current location to the target location within the location adjustment time, so as to complete the dynamic adjustment of the geographical location of the corresponding material.

[0012] In one embodiment, the optimal sorting task sequence includes an optimal sorting operation sequence and an optimal path planning for transporting the target material. Based on the optimal sorting task sequence, calling a sorting mechanism in the production environment to pick a specified quantity of the target material from the dynamically adjusted storage location and then sorting the target material to the corresponding target workstation includes: sending sorting instructions to the sorting mechanism in sequence according to the optimal sorting operation sequence of the optimal sorting task sequence, so as to instruct the sorting mechanism to grab a specified quantity of the target materials from the dynamically adjusted storage location according to the received sorting instructions, and then sequentially sort the grabbed target materials to the designated locations of the corresponding target workstations; According to the optimal path planning of the optimal sorting task sequence, the sorting mechanism is called to deliver the sorted target materials from the designated location to the corresponding target workstation.

[0013] In one embodiment, the method further comprises: Real-time monitoring of the actual flow of the target material and the actual production rhythm changes of the production line to obtain real-time monitoring results; When it is determined based on the real-time monitoring results that a production abnormality occurs, an alarm is triggered, and the execution is returned to call the production forecast model based on the real-time parameters of the production rhythm and the demand information to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period.

[0014] In a second aspect, the embodiments of the present application further provide a dynamic warehousing intelligent sorting system based on production rhythm, comprising: The production rhythm perception module is used to collect the real-time production rhythm parameters of each key workstation on the production line and obtain the demand information of the target materials to be sorted; The data fusion and decision processing module is used to call the production forecast model to predict the production rhythm forecast parameters and material demand forecast quantity of each key workstation in the future period based on the real-time production rhythm parameters and the demand information; based on the production rhythm forecast parameters and the material demand forecast quantity, combined with the current inventory status, equipment availability and preset optimization parameters, generate a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for the production line, wherein the dynamic storage location adjustment plan includes the corresponding materials of the target materials whose physical positions need to be adjusted, and the optimal sorting task sequence includes the target workstations corresponding to the target materials; A dynamic adaptive warehousing module is used to schedule a flexible scheduling mechanism in a production environment to dynamically adjust the physical location of the corresponding materials based on the dynamic storage location adjustment plan; The intelligent sorting execution module is used to call the sorting mechanism in the production environment to pick out a specified number of the target materials from the dynamically adjusted storage locations based on the optimal sorting task sequence, and then sort them to the corresponding target workstations.

[0015] In one embodiment, the production rhythm perception module is used to collect real-time production rhythm parameters of key workstations on the production line and obtain demand information of target materials to be sorted, specifically for: Calling the photoelectric sensors and industrial cameras on each of the key workstations to monitor the product throughput rate and buffer material inventory level of each of the key workstations in real time; Calling the PLC controllers on each of the key workstations to read the equipment status and real-time production data of each of the key workstations; The information identification channel at the warehouse entrance is called to automatically scan the unique identification code label on the incoming material or the unique identification code on the incoming material box to obtain detailed information about the incoming material; Call the ERP system to obtain the production plan for the next period of time; Obtaining the real-time parameters of the production rhythm based on the product throughput rate, the material inventory level in the buffer zone, the equipment status, and the real-time output data; Based on the detailed information of the incoming materials and the production plan, the demand for the target material is determined to obtain the demand information.

[0016] In one embodiment, when the data fusion and decision processing module is used to call the production forecast model to predict the production tact forecast parameters and material demand forecast of each key workstation in the future period based on the real-time production tact parameters and the demand information, it is specifically used to: Performing data cleaning and feature extraction on the real-time parameters of the production rhythm and the demand information to obtain corresponding feature data; Using a specified time series forecasting model as the production forecasting model; Based on the corresponding characteristic data, the specified time series prediction model is called to predict the production rhythm prediction parameters and material demand prediction quantity of each key workstation in a future period of time.

[0017] In one embodiment, the data fusion and decision processing module, when used to generate a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for the production line based on the production cycle forecast parameters, the material demand forecast, and in combination with the current inventory status, equipment availability, and preset optimization parameters, is specifically used to: Taking the preset optimization parameters as the optimization target, calling the specified multi-objective optimization algorithm based on the production cycle prediction parameters, the material demand forecast, the current inventory status and the equipment availability, to generate the dynamic storage location adjustment plan and the optimal sorting task sequence.

[0018] In one embodiment, when the dynamic adaptive warehousing module is used to schedule a flexible scheduling mechanism in a production environment to dynamically adjust the physical location of the corresponding material based on the dynamic storage location adjustment plan, it is specifically used to: sending the dynamic storage location adjustment plan to the WCS, and invoking the WCS to determine the current storage location, target storage location, and storage location adjustment time of the corresponding material based on the dynamic storage location adjustment plan, wherein the WCS refers to a warehouse control system; Send a location adjustment instruction to the WCS, instructing the WCS to dispatch the flexible dispatching mechanism to transfer the corresponding material from the current location to the target location within the location adjustment time, so as to complete the dynamic adjustment of the geographical location of the corresponding material.

[0019] In one embodiment, the optimal sorting task sequence includes an optimal sorting operation sequence and an optimal path planning for transporting the target material. When the intelligent sorting execution module is used to call a sorting mechanism in a production environment to pick a specified quantity of the target material from a dynamically adjusted storage location based on the optimal sorting task sequence, and then sort it to the corresponding target workstation, it is specifically used to: sending sorting instructions to the sorting mechanism in sequence according to the optimal sorting operation sequence of the optimal sorting task sequence, so as to instruct the sorting mechanism to grab a specified quantity of the target materials from the dynamically adjusted storage location according to the received sorting instructions, and then sequentially sort the grabbed target materials to the designated locations of the corresponding target workstations; According to the optimal path planning of the optimal sorting task sequence, the sorting mechanism is called to deliver the sorted target materials from the designated location to the corresponding target workstation.

[0020] In one embodiment, the system further comprises a central coordination and monitoring module, wherein the central coordination and monitoring module is configured to: Real-time monitoring of the actual flow of the target material and the actual production rhythm changes of the production line to obtain real-time monitoring results; When it is determined based on the real-time monitoring results that an abnormal production situation occurs, an alarm is triggered, and the data fusion and decision processing module is returned to execute based on the real-time parameters of the production rhythm and the demand information, and the production forecast model is called to predict the production rhythm forecast parameters and material demand forecast of each key workstation in the future period of time.

[0021] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a memory and a processor, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement a method in any one of the above-mentioned embodiments, wherein the memory and the processor communicate with each other through an internal connection path.

[0022] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is implemented.

[0023] Compared with existing technologies, this application achieves at least the following beneficial effects by sensing and predicting production rhythm in real time, dynamically adjusting warehouse layout to adapt to changes in material demand, and accurately matching and coordinating sorting tasks with production needs: (1) Improved adaptability to production rhythm: The system can quickly respond to changes in production rhythm caused by factors such as changes in production plans and fluctuations in equipment efficiency, dynamically adjusting material supply strategies. This significantly reduces waiting times and backlogs caused by mismatches between material supply and production demand, improving the overall fluidity and flexibility of the production line. Preliminary simulation analysis shows that average material waiting time can be reduced by 15%-30%.

[0024] (2) Optimized storage space utilization and operational efficiency: Through dynamic location management driven by real-time data and the intelligent formation of hotspot areas, the access paths of high-frequency materials are effectively shortened, while storage space is more reasonably allocated. It is expected that the overall storage space utilization rate can be increased by 10%-20%, and the average transportation distance per unit material can be reduced.

[0025] (3) Improved sorting accuracy and material turnover: The intelligent sorting execution module combines precise path planning with advanced recognition technology to significantly reduce the probability of missorting and missed sorting. Furthermore, close integration with the production rhythm accelerates overall material turnover and reduces work-in-progress inventory backlogs.

[0026] (IV) Achieved deep integration of warehousing and sorting with production processes: This application no longer regards warehousing and sorting as an isolated link, but as an organic part of the intelligent manufacturing system. It achieves real-time collaboration with production planning and execution through data-driven, which helps to improve overall production and operation efficiency, reduce operating costs, and provide strong support for on-demand production and lean manufacturing.

[0027] In summary, this application can improve the sorting system's adaptability to the production rhythm, optimize inventory turnover efficiency, and reduce the risk of production interruptions due to material mismatches or supply delays. It can thus provide a comprehensive solution that can effectively combine the real-time rhythm data of the production line and dynamically adjust the warehousing strategy and sorting task priority to achieve accurate, efficient, and adaptive sorting of materials.

[0028] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0030] Figure 1 This is a flowchart illustrating a dynamic warehousing intelligent sorting method based on production rhythm provided in an embodiment of the present application; Figure 2 This is a flowchart illustrating another method for dynamic warehousing and intelligent sorting based on production rhythm provided in an embodiment of the present application; Figure 3 A structural block diagram of a dynamic warehousing intelligent sorting system based on production rhythm provided in an embodiment of the present application; Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and description are to be regarded as illustrative in nature and not restrictive.

[0032] Figure 1 FIG. 1 is a flow chart showing a dynamic warehousing intelligent sorting method based on production rhythm according to an embodiment of the present application. Figure 1 As shown, the method may include the following steps: S110. Collect the real-time production rhythm parameters of each key workstation on the production line and obtain detailed information of the target materials to be sorted.

[0033] In one embodiment, step S110 may be performed at a preset frequency (e.g., a frequency in seconds or a frequency in minutes, such as 1 minute). The key workstations on the production line may include, but are not limited to, stamping workstations, welding workstations, painting workstations, and the entrance and exit workstations of the final assembly line.

[0034] In one embodiment, the implementation process of step S110 may include the following steps: S111. Use the photoelectric sensors and industrial cameras at each key workstation to monitor the product throughput rate and buffer material inventory level at each key workstation in real time.

[0035] In practice, photoelectric sensors and industrial cameras can be deployed at key workstations to monitor the throughput rate of products at each key workstation and the inventory level of materials in the buffer zone in real time. That is, during step S111, the photoelectric sensors and industrial cameras at each key workstation can be used to monitor the throughput rate of products at each key workstation and the inventory level of materials in the buffer zone in real time.

[0036] Among them, the product throughput rate can be understood as the core data that reflects the production rhythm in terms of the number of products. The buffer material inventory level can be understood as the core data that reflects the production rhythm in terms of the equipment operating status.

[0037] S112: Call the PLC controller on each key station to read the equipment status and real-time production data of each key station.

[0038] In specific implementations, the system can be connected to the PLC controllers at each key workstation via industrial Ethernet. When executing step S112, the PLC controllers at each key workstation are called to read the equipment status and real-time production data at each key workstation. This real-time production data may include real-time production rate.

[0039] S113. Call the information identification channel at the warehouse entrance to automatically scan the unique identification code on the incoming material or the unique identification code on the incoming material box to obtain detailed information on the incoming material.

[0040] During specific implementation, an information identification channel can be set up in advance at the warehouse entry point to serve as an automatic material information identification channel.

[0041] As an example, the unique identification code may be a QR code (i.e., a two-dimensional code) or an RFID tag. The type of the information identification channel may be determined based on the unique identification code on the material and the box.

[0042] For example, if the unique identification code is an RFID tag, then the information identification channel can be an RFID read-write channel, wherein the RFID read-write channel can be composed of an RFID reader array.

[0043] In specific implementation, the detailed information of the incoming material may include but is not limited to: material ID, batch, material type, quantity, incoming time, supplier information and initial storage location.

[0044] It should be understood that by executing steps S111 to S113, the real-time online product quantity and offline beat data of each key workstation can be collected.

[0045] S114. Call the ERP system to obtain the production plan for the next period of time.

[0046] In practice, an ERP system refers to an Enterprise Resource Planning (ERP) system, which can be used to create production plans for a specific period of time (e.g., the next 8 hours).

[0047] As an example, the production plan may include vehicle model, configuration, planned output, as well as the target workstation for each material, priority (which may be determined by the urgency of demand), expected delivery time window, etc.

[0048] In steps S111 to S114, the corresponding data can be transmitted in real time via the MQTT protocol. For example, in step S111, the product throughput rate and buffer material inventory levels of each key workstation are transmitted in real time via the MQTT protocol. In step S112, the equipment status and real-time production data of each key workstation are transmitted in real time via the MQTT protocol. In step S113, detailed information on incoming materials is transmitted in real time via the MQTT protocol. In step S114, the production plan for the future period is transmitted in real time via the MQTT protocol.

[0049] S115. Obtain the real-time parameters of the production rhythm based on the product throughput rate, the material inventory level in the buffer zone, the equipment status, and the real-time output data.

[0050] In specific implementations, the Overall Equipment Effectiveness (OEE) can be calculated based on the product throughput rate, the real-time production data, and the production time (i.e., the duration corresponding to the future period in step S114). The OEE, real-time production rate, and buffer material inventory level are then used as real-time parameters of the production cycle. It can be understood that the real-time parameters of the production cycle include the OEE, real-time production rate, and buffer material inventory level.

[0051] S116. Based on the detailed information of the incoming material and the production plan, the demand for the target material is determined to obtain the demand information.

[0052] During specific implementation, the demand for the target material can be determined based on the detailed information of the incoming material and the production plan, and according to the relevant requirements that need to be processed for the target material, the demand information can be obtained.

[0053] As an example, the demand information may include but is not limited to: material ID, required quantity (which may be determined by the quantity in the incoming material details / planned output in the production plan), target workstation, expected delivery time window and priority.

[0054] The target workstation may be a key workstation or any other workstation on the production line except the key workstations, which is not limited in the embodiment of the present application.

[0055] In specific implementation, step S116 and step S115 can be executed simultaneously or in a corresponding order, which is not limited in the embodiment of the present application.

[0056] In the embodiment of the present application, by executing step S110, the production rhythm and material requirements on the production line can be perceived in real time.

[0057] S120: Based on the real-time production rhythm parameters and the demand information, call the production forecast model to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future.

[0058] In one embodiment, the implementation process of step S120 may include the following steps: S121. Perform data cleaning and feature extraction on the real-time parameters of the production rhythm and the demand information to obtain corresponding feature data.

[0059] In specific implementation, the method of data cleaning and feature extraction of the real-time parameters of the production rhythm and the demand information is the same as or similar to the method of data cleaning and feature extraction in existing machine learning, and will not be repeated here.

[0060] S122. Use a specified time series forecasting model as the production forecasting model.

[0061] During specific implementation, multiple time series prediction models can be built in, and all of these time series prediction models can be used as production prediction models. Subsequently, the corresponding time series prediction model can be selected as the production prediction model according to actual needs.

[0062] As an example, multiple time series prediction models may include: a time series model based on an LSTM (Long Short-Term Memory Network) and an Autoregressive Integrated Moving Average (ARIMA) model. The ARIMA model is also called a summed autoregressive moving average model.

[0063] In this example, the specified time series prediction model may be an LSTM-based time series model or an ARIMA model.

[0064] S123. Based on the corresponding characteristic data, the specified time series prediction model is called to predict the production rhythm prediction parameters and material demand prediction quantity of each key workstation in the future period.

[0065] In specific implementation, the specified time series prediction model can adopt the existing one, that is, in the embodiment of the present application, only the input parameters of the specified time series prediction model are modified to obtain the corresponding output parameters, and no modification is made to its internal processing logic. Therefore, the prediction processing process of the specified time series prediction model will not be described in detail.

[0066] During specific implementation, the future period of time in step S123 can be set according to actual needs, for example, it can be the next 1-4 hours.

[0067] In an embodiment of the present application, by executing steps S121 to S123, time series analysis and machine learning prediction models (such as LSTM) can be used to make short-term predictions on the production rhythm, thereby predicting the production rhythm trend and material consumption rate in the future.

[0068] That is, in an embodiment of the present application, by executing step S120, the production rhythm data and ERP planning data of each key workstation on the production line are integrated to predict the production rhythm trend and material consumption rate in the future period, such as predicting the average production rhythm T predicted and material demand M_predicted (item, workstation, qty) of each key workstation in the next hour, where item is used to represent the material, workstation is used to represent the workstation number, and qty is used to represent the demand quantity.

[0069] S130: Based on the production rhythm prediction parameters, the material demand prediction quantity, and in combination with the current inventory status, equipment availability, and preset optimization parameters, a dynamic storage location adjustment plan and an optimal sorting task sequence suitable for the current production line are generated.

[0070] In one embodiment, the preset optimization parameters may include but are not limited to: minimizing total material waiting time, maximizing storage space turnover, minimizing total material handling distance, maximizing on-time delivery rate, minimizing inventory holding costs, minimizing average order delivery delay and maximizing equipment utilization. At least two parameters.

[0071] In one embodiment, the dynamic storage location adjustment plan may include corresponding materials of the target materials whose physical locations need to be adjusted, and the optimal sorting task sequence may include target workstations corresponding to the target materials.

[0072] In one embodiment, the preset optimization parameters can be used as the optimization target, and the specified multi-objective optimization algorithm can be called to generate the dynamic storage location adjustment plan (i.e., which materials should be moved to which storage location) and the optimal sorting task sequence based on the production cycle prediction parameters, the material demand forecast, the current inventory status and equipment availability.

[0073] As an example, the specified multi-objective optimization algorithm may be, but is not limited to, a genetic algorithm (GA) or a simulated annealing algorithm (SA). For example, in practical applications, the specified multi-objective optimization algorithm may also be a particle swarm optimization algorithm or a reinforcement learning algorithm.

[0074] As an example, if the preset optimization parameters include minimizing the average order delivery delay and maximizing the equipment utilization, and the specified multi-objective optimization algorithm is the simulated annealing algorithm, the simulated annealing algorithm can be used to solve the problem with minimizing the average order delivery delay and maximizing the equipment utilization as the optimization objectives: The algorithm inputs include: production cycle prediction parameter T predicted, material demand forecast M_ predicted, current real-time inventory S_current (item, location), and robot / shuttle status R_status; Algorithm output: the next hour's storage location adjustment plan L_adjust (item, from_loc, to_loc, priority) and the picking task sequence P_task (item, qty, from _loc, to_workstation, sequence_no, due_time).

[0075] In this example, the current real-time inventory S_current (item, location) represents the current inventory status, and the robot / shuttle status R_status represents equipment availability. The one-hour location adjustment plan L_adjust (item, from_loc, to_loc, priority) represents the dynamic location adjustment plan, and the sorting task sequence P_task (item, qty, from_loc, to_workstation, sequence_no, due_time) represents the optimal sorting task sequence. Here, item represents the material, from_loc represents the source location (i.e., the current location), to_loc represents the target location, priority represents the task priority, qyt represents the required quantity, to_workstation represents the sorting location, sequence_no represents the sorting task sequence number, and due_time represents the expected time.

[0076] As another example, taking the preset optimization parameters including minimizing the total material waiting time and maximizing the storage space turnover rate, and the specified multi-objective optimization algorithm being a genetic algorithm as an example, the optimization goals can be minimizing the total material waiting time and maximizing the storage space turnover rate, and comprehensively considering the production rhythm prediction parameters, material demand forecast, the actual storage location of each material in the current warehouse (which can be obtained through interaction with the warehouse control system (Warehouse Control System, WCS)), the ABC classification of the material, the availability of the flexible scheduling mechanism in the production environment and the movement cost, and calculating and generating a dynamic storage location adjustment plan and the optimal sorting task sequence every certain period of time (such as 15 minutes).

[0077] That is, in this example, the actual location of each material in the current warehouse is used to represent the current inventory status, and the availability and movement cost of the flexible scheduling mechanism in the production environment are used to represent the equipment availability.

[0078] In the embodiment of the present application, by executing step S130, the current and predicted production demand, inventory status, and equipment availability are comprehensively evaluated, thereby dynamically generating a dynamic storage location adjustment plan and an optimal sorting task sequence.

[0079] S140. Based on the dynamic storage location adjustment plan, the flexible scheduling mechanism in the scheduling production environment dynamically adjusts the physical location of the corresponding material.

[0080] In one embodiment, the flexible dispatching mechanism may include, but is not limited to, multiple shuttles and multiple elevators capable of four-way shuttle operation. The specific number of shuttles and elevators can be set according to actual needs and is not limited in this embodiment of the present application.

[0081] In one embodiment, the implementation process of step S140 may include the following steps: S141. Send the dynamic storage location adjustment plan to the WCS, and call the WCS to determine the current storage location, target storage location, and storage location adjustment time of the corresponding material based on the dynamic storage location adjustment plan.

[0082] In practice, the priority of the corresponding materials can be determined based on the demand information in step S110. Dynamic location adjustment plans for the high-priority materials are then sent to the WCS first. Upon receiving the dynamic location adjustment plans, the WCS determines the current location, target location, and location adjustment time for the corresponding materials based on the dynamic location adjustment plans.

[0083] For example, after receiving a dynamic location adjustment plan, the WCS identifies that Class A material X (such as a high-value or critical component) is currently located in cold zone C-03-05, but the production cycle forecast parameters of its corresponding target workstation W01 will increase significantly. In this case, the WCS can determine that Class A material X's current location is cold zone C-03-05, the target location is a fast cache area (such as hot cache area H-01-01), and the location adjustment time is 30 seconds (determined by the increase in the production cycle forecast parameters of the target critical workstation W01).

[0084] S142. Send a location adjustment instruction to the WCS, instructing the WCS flexible scheduling mechanism to transfer the corresponding material from the current location to the target location within the location adjustment time, so as to complete the dynamic adjustment of the geographical location of the corresponding material.

[0085] During implementation, the WCS can provide feedback on the current location, target location, and location adjustment time of the corresponding material determined based on the dynamic location adjustment plan. After receiving the feedback from the WCS, the location adjustment instruction can be sent to the WCS.

[0086] As an example, after receiving the location adjustment instruction, the WCS dispatches a flexible scheduling mechanism to move Class A material X from cold zone C-03-05 to hot cache H-01-01 within 30 seconds. This flexible scheduling mechanism can be the one closest to cold zone C-03-05 in the production environment. For example, the shuttle and elevator closest to cold zone C-03-05 can be dispatched to work together to move Class A material X from cold zone C-03-05 to hot cache H-01-01 within 30 seconds, rapidly completing the automatic relocation of Class A material X.

[0087] In an embodiment of the present application, by executing step S140, materials with high frequency demand can be moved from the backup storage area to a fast picking area or a hot spot cache area near the corresponding production station (both the fast picking area and the hot spot cache area belong to the fast cache area). Conversely, materials with low frequency demand in the short term can be moved to a slow cache area (such as a slow picking area or a cold area), thereby realizing dynamic caching of materials, pre-allocation of hot spot materials to high frequency access areas, centralized storage of unpopular materials, etc., thereby forming a warehouse layout that dynamically matches the production rhythm, can optimize the utilization of storage space and improve material picking efficiency. That is, step S140 is used to realize flexible storage and dynamic allocation of materials.

[0088] S150: Based on the optimal sorting task sequence, call the sorting mechanism in the production environment to pick out a specified number of target materials from the dynamically adjusted storage locations, and then sort them to corresponding target workstations.

[0089] In one embodiment, the sorting mechanism may include, but is not limited to, a high-speed sorting device (such as a cross-belt sorter, a swing wheel sorter, or a robotic sorting arm) or a robotic system (including multiple robots, including AGVs (automated guided vehicles)). It should be understood that the sorting mechanism is equipped with a 3D vision guidance system and an intelligent path guidance system (both of which are currently available) to achieve material identification and precise positioning.

[0090] In one embodiment, the optimal sorting task sequence may include, but is not limited to: an optimal sorting operation sequence and optimal path planning for target material transportation.

[0091] In one embodiment, the implementation process of step S150 may include the following steps: S151. Sorting instructions are sent to the sorting mechanism in sequence according to the optimal sorting operation sequence of the optimal sorting task sequence, so as to instruct the sorting mechanism to grab a specified number of target materials from the dynamically adjusted storage location according to the received sorting instructions, and then sort the grabbed target materials in sequence and sort them to the designated locations of the corresponding target workstations.

[0092] During specific implementation, the designated location may be a sorting slide or AGV corresponding to the target workstation, so that the target material can be delivered.

[0093] S152: According to the optimal path planning of the optimal sorting task sequence, the sorting mechanism is called to deliver the sorted target materials from the designated location to the corresponding target workstation.

[0094] During specific implementation, the optimal path planning of the optimal sorting task sequence can be followed, and the sorting mechanism can be called to deliver the sorted target materials from the designated area to the sorting buffer of the target key workstation, such as a designated buffer zone, a specific JIS (Just-In-Sequence) sorting grid, a line-side warehouse, or an outbound assembly point (such as a direct outbound port).

[0095] For example, consider a sorting instruction to pick three pieces of material A (the target material) from storage location H-01-01 and deliver them to the sorting buffer lane of workstation Z03 on the final assembly line (the target workstation). In this case, the WCS has already dispatched a flexible dispatching mechanism (such as a four-way shuttle) to move the bin containing material A to storage location H-01-01. Upon receiving this sorting instruction, the sorting mechanism activates the robotic sorting arm R01 to retrieve the three pieces of material A from storage location H-01-01 and sort these three pieces to the sorting chute or AGV corresponding to workstation Z03 on the final assembly line. Visual recognition is then used to confirm that the three pieces of material A are indeed material A. Once this is confirmed, the sorting mechanism (such as an AGV) is activated to deliver these three pieces of material A to the sorting buffer lane of workstation Z03 on the final assembly line according to the optimal path planned for the optimal sorting task sequence.

[0096] In step S152, when it is confirmed that the target material has been sorted, the sorting completion time can be recorded and the material inventory status can be updated.

[0097] In the embodiment of the present application, by executing step S150, the target materials can be sorted, sorted (if JIS supply is required) and delivered to the sorting buffer lane matching the target key station in sequence and accurately in strict accordance with the production rhythm requirements of each key station.

[0098] In an applicable scenario provided in the embodiment of the present application, combined with Figure 1 and Figure 2 As shown, the dynamic warehousing intelligent sorting method based on production rhythm provided in the embodiment of the present application may also include the following steps: S160: Monitor the actual flow of target materials and the actual production rhythm changes of the production line in real time to obtain real-time monitoring results.

[0099] In one implementation, the core functions of a warehouse management system (WMS) and WCS can be built-in, with bidirectional data interaction with the manufacturing execution system (MES) via a unified API interface to facilitate command issuance and status aggregation. In this scenario, a system status visualization interface (such as a web-based digital twin dashboard) can be provided to display real-time data such as material flow, equipment status, inventory heat maps, and key performance indicators (KPIs) such as production cycle matching across the entire storage and sorting area. By monitoring this data, the actual flow of target materials and actual production cycle changes of the production line can be monitored in real time.

[0100] Among them, the production rhythm matching degree can be represented by the deviation between the real-time production rhythm parameters and the production rhythm prediction parameters. The smaller the deviation, the higher the production rhythm matching degree, and the larger the deviation, the smaller the production rhythm matching degree.

[0101] S170. When it is determined based on the real-time monitoring result that a production abnormality occurs, an alarm is triggered and the process returns to step S120.

[0102] As a first example, when it is determined based on the real-time monitoring results that the production rhythm has significantly deviated from the prediction (perhaps due to a sudden equipment failure causing a line stoppage or an urgent order change causing a drastic change in the production rhythm), it can be determined that a production anomaly has occurred. For example, when the real-time monitoring results include a monitoring result that the deviation (|T_actual-T_predicted| / T_predicted) between the real-time parameter T_actual of the production rhythm and the predicted parameter T_predicted is greater than a preset threshold (for example, 15%) and the duration exceeds a preset duration (such as 5 minutes), it is determined that the production rhythm has significantly deviated from the prediction and a production anomaly has occurred. Among them, the preset threshold and the preset duration can be set according to actual needs, and the embodiments of the present application are not limited to this.

[0103] As a second example, when an abnormality occurs during the sorting process based on the real-time monitoring results, it can be determined that a production abnormality has occurred. For example, when the real-time monitoring results include relevant monitoring results such as material identification errors, path obstruction, etc., it is determined that a production abnormality has occurred.

[0104] As a third example, if the real-time monitoring results indicate that a critical piece of equipment (e.g., a shuttle vehicle) has stopped due to a fault for longer than a specified period (e.g., 3 minutes), a production anomaly may be determined. This specified period can be set based on actual needs and is not limited in this embodiment.

[0105] In one embodiment, combining the above three examples and possible application scenarios on the production line, it can be concluded that when the real-time monitoring results include the following monitoring conditions, it is determined that a production abnormality has occurred: (1) Sudden change in production rhythm: The deviation between the actual value of production rhythm and the predicted value exceeds the preset threshold.

[0106] (2) Abnormal material status: such as material shortage, quality problems or wrong location.

[0107] (3) Equipment status changes: such as AGV failure, charging requirements, or channel blockage.

[0108] (4) Execution abnormality: The sorting task fails or is severely delayed.

[0109] (5) Regular optimization: reaching the specified optimization duration (in this case, routine optimization is performed at preset time intervals).

[0110] The above five monitoring conditions can be used as closed-loop adaptive adjustment trigger conditions to trigger alarms.

[0111] In one embodiment, when a production anomaly is determined based on the real-time monitoring results, an alarm is triggered, and the anomaly information and current system snapshot data are fed back, and then the process returns to step S120. In this way, an emergency re-planning can be forced to be triggered (i.e., returning to step S120), so as to adapt to the new system status and production constraints.

[0112] In another embodiment, when it is determined based on the real-time monitoring result that a production abnormality occurs, an alarm is triggered, the abnormality is processed, and the process returns to step S120.

[0113] For example, if, in S150 above, robot sorting arm R01 is grabbing item Y from location C-03-05 and the vision system reports that the item's posture is abnormal and cannot be grasped, it will attempt to adjust the grasping posture several times (e.g., twice). If it still fails, it will report the exception information (e.g., item ID, location, and exception type) for feedback. In this case, the real-time monitoring results may include the following: Material Y (item ID) in location C-03-05 failed to be grasped due to an abnormal material posture (exception type).

[0114] Based on the monitoring situation, the following exception handling can be performed: 1) Suspend other tasks involving this material; 2) Instruct another backup robot or manual intervention; 3) If the material has a substitute and production is urgent, consider using the substitute when returning to execute S120 to make a new decision.

[0115] In an embodiment of the present application, by executing steps S160 and S170, the decision optimization process can be dynamically adjusted or re-executed when production abnormalities occur, thereby achieving closed-loop adaptive adjustment of warehousing and sorting, ensuring continuous adaptation to changes in the production environment.

[0116] For ease of understanding, the closed-loop adaptive adjustment process in the dynamic warehousing intelligent sorting method based on production rhythm provided in the embodiment of the present application will be further explained below in conjunction with an automobile chassis assembly production line.

[0117] Consider a chassis assembly line that originally planned to produce Model A chassis at a rate of 200 units per hour. Material sorting strategies had previously been optimized based on this production rate. However, during production, a temporary quality issue in an upstream process reduced the actual production rate to 120 units per hour. Simultaneously, Model B chassis production (80 units per hour) was urgently added. In this case, closed-loop adaptive adjustments for the chassis assembly line could include the following steps: Step 1: Change Detection and Anomaly Identification In step 1, the real-time monitoring data may be as shown in Table 1 below.

[0118] Table 1

[0119] At this point, photoelectric sensors installed at key workstations on the production line can monitor significant changes in actual production rates in real time, and the MES system pushes work order changes. By comparing the actual production rate with the predicted rate, if the deviation exceeds the preset 15% threshold, a closed-loop adjustment mechanism is automatically triggered.

[0120] Step 2: Snapshot Saving and Status Evaluation In step 2, the relevant content of the system status snapshot may be as shown in Table 2 below.

[0121] Table 2

[0122] When the closed-loop adjustment mechanism is automatically triggered, a complete snapshot of the current operating status can be immediately captured, including all ongoing and pending sorting tasks, AGV location and status, inventory status, etc. At the same time, the interruption cost of the currently executing task and the impact of continuing execution can be evaluated.

[0123] Step 3: Re-execute the decision optimization process in step S120 The input parameters for re-execution of the decision in step S120 may be as shown in Table 3 below.

[0124] Table 3

[0125] The execution process of re-execution of the decision in step S120 may include real-time recalculation of the time series prediction model and re-optimization of the dynamic sorting strategy engine.

[0126] The relevant process of real-time recalculation of the time series forecasting model is as follows: Input the changed production data; Update the beat bias matrix B = 0.5·F_workorder' + 0.3·F_equipment' + 0.2·F_production'; Re-forecast the material demand time series distribution for the next 2 hours.

[0127] The relevant process of re-optimization of the dynamic sorting strategy engine is as follows: Recalculate the priority scores of all materials to be sorted; Type A material priority is reduced: Score_A = 0.6·60 + 0.3·40 + 0.1·70 = 56.0; Type B material priority increased: Score_B = 0.6·85 + 0.3·50 + 0.1·30 = 70.5; Generate a new sorting task queue and execution plan.

[0128] That is, in step 3, the decision optimization process in step S120 can be rerun based on the newly detected production tact time and work order changes. The time series forecasting model receives the updated data and recalculates the material demand forecast for chassis B, taking this into account. Simultaneously, the dynamic sorting strategy engine reassesses the priorities of all pending tasks, giving chassis B a higher priority due to the urgent insertion of the order.

[0129] Step 4: Dynamic adjustment of storage location In step 4, the relevant content of the storage location dynamic adjustment instruction can be shown in Table 4 below.

[0130] Table 4

[0131] In step 4, the calculation result of the hotspot area reallocation may be shown in Table 5 below.

[0132] Table 5

[0133] That is, in step 4, dynamic inventory adjustment instructions can be generated based on the new material demand forecast and priority score. Specialized parts for Type B chassis originally stored in a remote warehouse can be urgently dispatched to a high-frequency area close to the production line, while some Type A parts can be moved from a high-frequency area to a medium-frequency area, achieving dynamic optimization of inventory resources.

[0134] Step 5: Task queue rescheduling and resource reallocation In step 5, the task queue reordering result may be as shown in Table 6 below.

[0135] Table 6

[0136] In step 5, the resource reallocation result may be as shown in Table 7 below.

[0137] Table 7

[0138] In step 5, all pending and newly added sorting tasks can be reordered based on the new priority scores. For tasks that have already begun, they can be allowed to continue unless the interruption cost is extremely low. At the same time, AGV resources can be reallocated, with some AGVs being dispatched to the new, high-priority B-type chassis material sorting tasks, and previously standby AGVs activated to increase processing capacity.

[0139] Step 6: Exception handling and manual collaboration In step 6, if the replanning process reveals insufficient inventory of key parts required for the Type B chassis, potentially leading to production disruption, the material shortage exception handling process can be automatically triggered, generating a collaborative task. The AR-assisted system immediately provides task guidance to the warehouse operator, helping them quickly locate and pick the scarce materials in the backup warehouse.

[0140] Illustratively, in step 6, the exception handling strategy may be as shown in Table 8 below.

[0141] Table 8

[0142] Step 7: Conduct monitoring and evaluate results In step 7, the execution monitoring data may be as shown in Table 9 below.

[0143] Table 9

[0144] In step 7, the effectiveness of the closed-loop adaptive adjustments can be continuously monitored, and key performance indicators can be collected in real time. Data shows that timely adjustments successfully addressed the challenges of changing production cycles, maintained a high on-time material delivery rate, and effectively reduced the AGV idle rate. Furthermore, emerging issues, such as low AGV battery levels, can be continuously monitored and corresponding solutions generated.

[0145] Step 8: Parameter self-learning update (optional) In step 8, based on the actual results of closed-loop adaptive adjustments, decision parameters can be updated through reinforcement learning. Rewards are calculated based on factors such as successfully responding to production changes and maintaining high on-time delivery rates. Priority scoring weights and anomaly detection thresholds are then fine-tuned accordingly. Simultaneously, model performance metrics are recorded and evaluated to provide data support for subsequent algorithm optimization.

[0146] Exemplarily, in step 8, the relevant parameters updated by reinforcement learning may be as shown in Table 10 below.

[0147] Table 10

[0148] In summary, by dynamically adjusting or re-executing the decision optimization process, closed-loop adaptive adjustment of warehousing and sorting can be achieved to ensure continuous adaptation to changes in the production environment.

[0149] As can be seen from the above description, compared with the prior art, the dynamic warehousing intelligent sorting method based on production rhythm provided by the embodiments of the present application achieves the following beneficial effects by sensing and predicting the production rhythm in real time, dynamically adjusting the warehouse layout to adapt to changes in material demand, and accurately matching and coordinating sorting tasks with production demand: (1) Improved adaptability to production rhythm: The system can quickly respond to changes in production rhythm caused by factors such as changes in production plans and fluctuations in equipment efficiency, dynamically adjusting material supply strategies. This significantly reduces waiting times and backlogs caused by mismatches between material supply and production demand, improving the overall fluidity and flexibility of the production line. Preliminary simulation analysis shows that average material waiting time can be reduced by 15%-30%.

[0150] (2) Optimized storage space utilization and operational efficiency: Through dynamic location management driven by real-time data and the intelligent formation of hotspot areas, the access paths of high-frequency materials are effectively shortened, while storage space is more reasonably allocated. It is expected that the overall storage space utilization rate can be increased by 10%-20%, and the average transportation distance per unit material can be reduced.

[0151] (3) Improved sorting accuracy and material turnover: The intelligent sorting execution module combines precise path planning with advanced recognition technology to significantly reduce the probability of missorting and missed sorting. Furthermore, close integration with the production rhythm accelerates overall material turnover and reduces work-in-progress inventory backlogs.

[0152] (IV) Achieved deep integration of warehousing and sorting with production processes: This application no longer regards warehousing and sorting as an isolated link, but as an organic part of the intelligent manufacturing system. It achieves real-time collaboration with production planning and execution through data-driven, which helps to improve overall production and operation efficiency, reduce operating costs, and provide strong support for on-demand production and lean manufacturing.

[0153] In summary, the dynamic warehousing intelligent sorting method based on production rhythm provided in the embodiments of the present application can improve the adaptability of the sorting system to the production rhythm, optimize inventory turnover efficiency, and reduce the risk of production interruption due to material mismatch or supply delays, thereby providing a comprehensive solution that can effectively combine the real-time rhythm data of the production line and achieve accurate, efficient and adaptive sorting of materials by dynamically adjusting the warehousing strategy and sorting task priority.

[0154] Figure 3 The structural block diagram of the dynamic warehousing intelligent sorting system based on production rhythm according to an embodiment of the present application is shown. Figure 3 As shown, the system may include: The production rhythm sensing module 10 is used to collect the real-time production rhythm parameters of each key workstation on the production line and obtain the demand information of the target materials to be sorted; The data fusion and decision processing module 20 is used to call the production forecast model to predict the production cycle forecast parameters and material demand forecast for each key workstation in the future period based on the real-time production cycle parameters and demand information; based on the production cycle forecast parameters and material demand forecast, combined with the current inventory status, equipment availability and preset optimization parameters, a dynamic storage location adjustment plan and an optimal sorting task sequence suitable for the current production line are generated, wherein the dynamic storage location adjustment plan includes the corresponding materials whose physical locations need to be adjusted among the target materials, and the optimal sorting task sequence includes the target workstations corresponding to the target materials; Dynamic adaptive warehousing module 30, used to dynamically adjust the physical location of corresponding materials based on the dynamic storage location adjustment plan and the flexible scheduling mechanism in the scheduling production environment; The intelligent sorting execution module 40 is used to call the sorting mechanism in the production environment to pick out a specified number of target materials from the dynamically adjusted storage locations based on the optimal sorting task sequence, and then sort them to the corresponding target workstations.

[0155] In one embodiment, when the production rhythm perception module 10 is used to collect the real-time parameters of the production rhythm of each key station on the production line and obtain the demand information of the target material to be sorted, it is specifically used to: call the photoelectric sensors and industrial cameras on each key station to monitor the product throughput rate and buffer material inventory level of each key station in real time; call the PLC controller on each key station to read the equipment status and real-time production data of each key station; call the information recognition channel at the warehouse entrance to automatically scan the unique identification code label on the incoming material or the unique identification code on the incoming material box to obtain detailed information of the incoming material; call the ERP system to obtain the production plan for a period of time in the future; obtain the real-time parameters of the production rhythm based on the product throughput rate, buffer material inventory level, equipment status and real-time production data; determine the demand for the target material based on the detailed information of the incoming material and the production plan, and obtain demand information.

[0156] As an example, Figure 3 As shown, the production rhythm perception module 10 can serve as the perception layer of a dynamic warehousing intelligent sorting system based on production rhythm. It can include a production line real-time data acquisition interface 11 and a material information automatic identification unit 12. The production line real-time data acquisition interface 11 is used to communicate with the photoelectric sensors, industrial cameras, and PLCs at each key workstation to monitor the product throughput rate and buffer material inventory levels at each key workstation in real time, read the equipment status and real-time output data of each key workstation, and obtain production plans for the future period. It is also used to communicate with the ERP system. The material information automatic identification unit 12 is used to communicate with the information identification channel at the warehouse entrance to automatically scan the unique identification code labels on incoming materials or the unique identification codes on incoming material boxes to obtain detailed information about the incoming materials.

[0157] That is, the production rhythm sensing module 10 can be integrated with, for example, an RFID reader array, a machine vision sensor, a PLC data interface, and a communication interface with an MES / ERP system.

[0158] In one embodiment, when the data fusion and decision processing module 20 is used to call the production forecast model to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period based on the real-time parameters and demand information of the production rhythm, it is specifically used to: perform data cleaning and feature extraction on the real-time parameters and demand information of the production rhythm to obtain corresponding feature data; adopt a specified time series forecast model as the production forecast model; based on the corresponding feature data, call the specified time series forecast model to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period.

[0159] In one embodiment, the data fusion and decision processing module 20 is used to generate a dynamic warehouse adjustment plan and an optimal sorting task sequence currently suitable for the production line based on production cycle prediction parameters, material demand prediction, current inventory status, equipment availability and preset optimization parameters. Specifically, it is used to: use the preset optimization parameters as the optimization target, call the specified multi-objective optimization algorithm based on production cycle prediction parameters, material demand prediction, current inventory status and equipment availability, and generate a dynamic warehouse adjustment plan and an optimal sorting task sequence.

[0160] As an example, Figure 3 As shown, the data fusion and decision processing module 20 can serve as the decision-making layer of the dynamic warehousing intelligent sorting system based on production takt time. It can include a production takt time prediction unit 21 and a dynamic scheduling optimization algorithm engine 22. Specifically, the production takt time prediction unit 21 is used to call the production prediction model to predict the production takt time prediction parameters and material demand forecast for each key workstation over a period of time in the future based on real-time production takt time parameters and demand information. The dynamic scheduling optimization algorithm engine 22 is used to generate a dynamic storage location adjustment plan and an optimal sorting task sequence suitable for the current production line based on the production takt time prediction parameters and material demand forecast, combined with the current inventory status, equipment availability, and preset optimization parameters.

[0161] In one embodiment, when the dynamic adaptive warehousing module 30 is used to schedule the flexible scheduling mechanism in the production environment to dynamically adjust the physical location of corresponding materials based on the dynamic location adjustment plan, it is specifically used to: send the dynamic location adjustment plan to the WCS, call the WCS to determine the current location, target location and location adjustment time of the corresponding material based on the dynamic location adjustment plan, where WCS refers to the warehouse control system; send a location adjustment instruction to the WCS, instructing the WCS to schedule the flexible scheduling mechanism to transfer the corresponding material from the current location to the target location within the location adjustment time to complete the dynamic adjustment of the geographical location of the corresponding material.

[0162] In one embodiment, the optimal sorting task sequence includes an optimal sorting operation sequence and an optimal path planning for the handling of target materials; when the intelligent sorting execution module 40 is used to call the sorting mechanism in the production environment to pick out a specified number of target materials from the dynamically adjusted storage location based on the optimal sorting task sequence, and then sort them to the corresponding target workstations, it is specifically used to: send sorting instructions to the sorting mechanism in sequence according to the optimal sorting operation sequence of the optimal sorting task sequence, so as to instruct the sorting mechanism to grab the specified number of target materials from the dynamically adjusted storage location according to the received sorting instructions, and then sort the grabbed target materials in sequence and sort them to the designated positions of the corresponding target workstations; call the sorting mechanism to deliver the sorted target materials from the designated position to the corresponding target workstation according to the optimal path planning of the optimal sorting task sequence.

[0163] As an example, Figure 3 As shown, the dynamic adaptive warehousing module 30 and the intelligent sorting execution module 40 can serve as the execution layer of a dynamic warehousing and intelligent sorting system based on production rhythm. Specifically, the dynamic adaptive warehousing module 30 can include a reconfigurable modular storage unit 31 and a flexible scheduling execution mechanism 32. The intelligent sorting execution module 40 can include a high-speed automatic sorting device 41 and a path guidance and material tracking system 42.

[0164] Exemplarily, the reconfigurable modular storage units 31 may include, but are not limited to, modular racking, height-adjustable shelves, and a four-way shuttle racking system. The flexible dispatching mechanism 32 is responsible for accurately and efficiently sorting materials according to instructions. It may include multiple shuttles and elevators, as well as collaborative mobile robots (AMRs). The high-speed automatic sorting device 41 may include a cross-belt sorter, a swing wheel sorter, a robotic sorting arm, etc. The path guidance and material tracking system 42 may include a robotic system consisting of several robots (including AGVs).

[0165] In one embodiment, the dynamic warehousing intelligent sorting system based on production rhythm also includes a central coordination and monitoring module 50, which is used to: monitor the actual flow of target materials and the actual production rhythm changes of the production line in real time to obtain real-time monitoring results; when it is determined that a production abnormality occurs based on the real-time monitoring results, an alarm is triggered, and the data fusion and decision processing module 20 is returned to execute based on the real-time parameters and demand information of the production rhythm, and the production prediction model is called to predict the production rhythm prediction parameters and material demand prediction quantities of each key workstation in the future period of time.

[0166] It should be understood that in the dynamic warehousing intelligent sorting system based on production rhythm, the data of the production rhythm perception module 10 is the input of the data fusion and decision processing module 20; the instructions of the data fusion and decision processing module 20 drive the dynamic adaptive warehousing module 30 and the intelligent sorting execution module 40; the execution status of the dynamic adaptive warehousing module 30 and the intelligent sorting execution module 40 is fed back to the central coordination and monitoring module 50, and may be further fed back to the data fusion and decision processing module 20 to form a closed-loop control.

[0167] As an example, the central coordination and monitoring module 50 can be developed based on a microservice architecture to include the core functions of WMS and WCS, and conduct two-way data interaction with MES through a unified API interface. It is responsible for completing material sorting accurately and efficiently according to instructions, and is responsible for coordinating the synchronous and efficient collaboration of the above-mentioned production rhythm perception module 10, data fusion and decision processing module 20, dynamic adaptive warehousing module 30 and intelligent sorting execution module 40. It also ensures that the system can continuously adapt to changes in the production environment by monitoring the system operation status in real time, detecting abnormal situations, and dynamically adjusting or re-executing the decision optimization process through the data fusion and decision processing module 20 based on feedback data. This closed-loop adaptive adjustment mechanism can allow the entire dynamic warehousing and intelligent sorting system based on production rhythm to form a complete PDCA cycle (Plan-Do-Check-Act), thereby realizing intelligent self-optimization.

[0168] For example, Figure 3 As shown, the central coordination and monitoring module 50 serves as the monitoring layer for a dynamic, production-paced intelligent warehousing and sorting system. It includes a system status visualization interface 51 and a collaborative control and bus system 52. Specifically, the system status visualization interface 51 displays key performance indicators (KPIs) such as material flow, equipment status, inventory heat maps, and production-paced matching across the entire warehousing and sorting area in real time. The collaborative control and bus system 52 facilitates bidirectional data exchange with other modules. Through the system status visualization interface 51 and the collaborative control and bus system 52, the central coordination and monitoring module 50 also provides the necessary human-computer interaction interface, supporting manual intervention and system parameter adjustment.

[0169] For example, assume that the production cycle of a paint painting station (P01) for a certain model on a production line is expected to increase by 20% within the next hour due to order adjustments, resulting in a significant increase in demand for a specific color of paint (material X). In this case, the modules in the dynamic warehousing and intelligent sorting system based on production cycle can execute the following processing logic: 1. The production rhythm perception module 10 obtains the plan adjustment information through the MES interface, and monitors through its own sensors that the pass rate of the work-in-progress at the P01 station has an upward trend.

[0170] 2. The production rhythm prediction unit 21 of the data fusion and decision processing module 20 confirms the rhythm change trend, and the dynamic scheduling optimization algorithm engine 22 determines that the material X currently stored in the reserve area is insufficient to meet the predicted demand, and the picking path to its current storage location is long.

[0171] 3. Data fusion and decision processing module 20 generates the following instructions: a) dynamically move the latest batch of material X (partially or entirely) from the more distant D-10-05 storage location to the fast cache F-02 near the exit of station P01; b) increase the sorting task priority of material X for station P01 within the next hour.

[0172] 4. The central coordination and monitoring module 50 dispatches the shuttle vehicle of the dynamic adaptive storage module 30 to move material X. Simultaneously, the intelligent sorting execution module 40 prioritizes sorting requests for material X destined for workstation P01, ensuring sufficient material reserves in the lineside buffer near workstation P01 before the actual peak in production demand arrives.

[0173] The functions of each module in the dynamic warehousing intelligent sorting system based on production rhythm in the embodiment of the present application can be referred to the corresponding description in the above method, and will not be repeated here.

[0174] Figure 4 FIG. 1 shows a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device includes: a memory 310 and a processor 320. The memory 310 stores instructions, which are loaded and executed by the processor 320 to implement the dynamic warehousing intelligent sorting method based on production rhythm in the above embodiment. The number of memory 310 and processor 320 can be one or more.

[0175] The electronic device also includes: The communication interface 330 is used to communicate with external devices and perform data exchange transmission.

[0176] If the memory 310, processor 320, and communication interface 330 are implemented independently, the memory 310, processor 320, and communication interface 330 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0177] Optionally, in a specific implementation, if the memory 310, the processor 320 and the communication interface 330 are integrated on a chip, the memory 310, the processor 320 and the communication interface 330 can communicate with each other through an internal interface.

[0178] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs on a computer, the method provided in the embodiment of the present application is implemented.

[0179] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in a memory, so that a communication device equipped with the chip executes the method provided in the embodiment of the present application.

[0180] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory. The input interface, the output interface, the processor and the memory are connected through an internal connection path. The processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0181] It should be understood that the processor described above may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor. It is worth noting that the processor may be a processor that supports the Advanced RISC Machines (ARM) architecture.

[0182] Furthermore, optionally, the above-mentioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory may include random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0183] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0184] In the description of this specification, the reference terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0185] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0186] Any process or method description in a flow chart or otherwise described herein can be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process. The scope of the preferred embodiments of the present application includes additional implementations in which the functions may be performed in a different order than shown or discussed, including in a substantially simultaneous manner or in a reverse order depending on the functions involved.

[0187] The logic and / or steps represented in the flowchart or otherwise described herein may be considered, for example, as a sequenced list of executable instructions for implementing the logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device).

[0188] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0189] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the aforementioned integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc.

[0190] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A dynamic warehousing intelligent sorting method based on production rhythm, characterized in that: include: Collect real-time production rhythm parameters of key workstations on the production line and obtain demand information of target materials to be sorted; Based on the real-time production rhythm parameters and the demand information, calling the production forecast model to predict the production rhythm forecast parameters and material demand forecast amount of each key workstation in the future period; Based on the production cycle forecast parameters, the material demand forecast, and in combination with the current inventory status, equipment availability, and preset optimization parameters, a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for the production line are generated, wherein the dynamic storage location adjustment plan includes the corresponding materials of the target materials that need to have their physical locations adjusted, and the optimal sorting task sequence includes the target workstations corresponding to the target materials; Based on the dynamic storage location adjustment plan, a flexible scheduling mechanism in the scheduling production environment dynamically adjusts the physical location of the corresponding material; Based on the optimal sorting task sequence, the sorting mechanism in the production environment is called to pick out a specified number of the target materials from the dynamically adjusted storage locations, and then sort them to the corresponding target workstations.

2. The method according to claim 1, characterized in that Collect the real-time production rhythm parameters of each key workstation on the production line and obtain the demand information of the target materials to be sorted, including: Calling the photoelectric sensors and industrial cameras on each of the key workstations to monitor the product throughput rate and buffer material inventory level of each of the key workstations in real time; Calling the PLC controllers on each of the key workstations to read the equipment status and real-time production data of each of the key workstations; The information identification channel at the warehouse entrance is called to automatically scan the unique identification code label on the incoming material or the unique identification code on the incoming material box to obtain detailed information about the incoming material; Call the ERP system to obtain the production plan for the next period of time; Obtaining the real-time parameters of the production rhythm based on the product throughput rate, the material inventory level in the buffer zone, the equipment status, and the real-time output data; Based on the detailed information of the incoming materials and the production plan, the demand for the target material is determined to obtain the demand information.

3. The method according to claim 1, characterized in that Based on the real-time production rhythm parameters and the demand information, the production forecast model is called to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period, including: Performing data cleaning and feature extraction on the real-time parameters of the production rhythm and the demand information to obtain corresponding feature data; Using a specified time series forecasting model as the production forecasting model; Based on the corresponding characteristic data, the specified time series prediction model is called to predict the production rhythm prediction parameters and material demand prediction quantity of each key workstation in a future period of time.

4. The method according to claim 1, wherein Based on the production cycle forecast parameters, the material demand forecast, and in combination with the current inventory status, equipment availability, and preset optimization parameters, a dynamic inventory adjustment plan and an optimal sorting task sequence currently suitable for the production line are generated, including: Taking the preset optimization parameters as the optimization target, calling the specified multi-objective optimization algorithm based on the production cycle prediction parameters, the material demand forecast, the current inventory status and the equipment availability, to generate the dynamic storage location adjustment plan and the optimal sorting task sequence.

5. The method according to claim 1, wherein Based on the dynamic inventory adjustment plan, the flexible scheduling mechanism in the scheduling production environment dynamically adjusts the physical location of the corresponding material, including: sending the dynamic storage location adjustment plan to the WCS, and invoking the WCS to determine the current storage location, target storage location, and storage location adjustment time of the corresponding material based on the dynamic storage location adjustment plan, wherein the WCS refers to a warehouse control system; Send a location adjustment instruction to the WCS, instructing the WCS to dispatch the flexible dispatching mechanism to transfer the corresponding material from the current location to the target location within the location adjustment time, so as to complete the dynamic adjustment of the geographical location of the corresponding material.

6. The method according to claim 1, characterized in that The optimal sorting task sequence includes an optimal sorting operation sequence and an optimal path planning for transporting the target material. Based on the optimal sorting task sequence, calling a sorting mechanism in the production environment to pick a specified quantity of the target material from the dynamically adjusted storage location and then sorting the target material to the corresponding target workstation includes: sending sorting instructions to the sorting mechanism in sequence according to the optimal sorting operation sequence of the optimal sorting task sequence, so as to instruct the sorting mechanism to grab a specified quantity of the target materials from the dynamically adjusted storage location according to the received sorting instructions, and then sequentially sort the grabbed target materials to the designated locations of the corresponding target workstations; According to the optimal path planning of the optimal sorting task sequence, the sorting mechanism is called to deliver the sorted target materials from the designated location to the corresponding target workstation.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Real-time monitoring of the actual flow of the target material and the actual production rhythm changes of the production line to obtain real-time monitoring results; When it is determined based on the real-time monitoring results that a production abnormality occurs, an alarm is triggered, and the execution is returned to call the production forecast model based on the real-time parameters of the production rhythm and the demand information to predict the production rhythm forecast parameters and material demand forecast quantities of each key workstation in the future period of time.

8. A dynamic warehousing intelligent sorting system based on production rhythm, characterized by: include: The production rhythm perception module is used to collect the real-time production rhythm parameters of each key workstation on the production line and obtain the demand information of the target materials to be sorted; The data fusion and decision processing module is used to call the production forecast model to predict the production rhythm forecast parameters and material demand forecast quantity of each key workstation in the future period based on the real-time production rhythm parameters and the demand information; based on the production rhythm forecast parameters and the material demand forecast quantity, combined with the current inventory status, equipment availability and preset optimization parameters, generate a dynamic storage location adjustment plan and an optimal sorting task sequence currently suitable for the production line, wherein the dynamic storage location adjustment plan includes the corresponding materials of the target materials whose physical positions need to be adjusted, and the optimal sorting task sequence includes the target workstations corresponding to the target materials; A dynamic adaptive warehousing module is used to schedule a flexible scheduling mechanism in a production environment to dynamically adjust the physical location of the corresponding materials based on the dynamic storage location adjustment plan; The intelligent sorting execution module is used to call the sorting mechanism in the production environment to pick out a specified number of the target materials from the dynamically adjusted storage locations based on the optimal sorting task sequence, and then sort them to the corresponding target workstations.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a computer, the method according to any one of claims 1 to 7 is implemented.

Images