Production sequencing method and equipment for drilling machining

Abstract

The embodiment of the invention provides a production sorting method and equipment for drilling machining. The method comprises the steps of obtaining multi-source data of drilling processing equipment, obtaining a plurality of to-be-sorted drilling processing orders, determining an initial production scheduling result according to the multi-source data and the plurality of orders, and obtaining a plurality of to-be-sorted drilling processing orders based on a digital twinborn model and a preset objective function, wherein the multi-source data is used for indicating the current processing state of the drilling processing equipment; the initial production scheduling result is iteratively optimized, a final production scheduling result is obtained, the preset target function comprises a completion time length constraint term, an energy consumption constraint term and a quality constraint term related to tool abrasion, and the final production scheduling result is sent to drilling machining equipment so that the drilling machining equipment can execute drilling machining according to the final production scheduling result. According to the method provided by the embodiment of the invention, the defect of low intelligent level of traditional static production scheduling is overcome, the processing and manufacturing efficiency is improved, and the energy consumption is reduced.

Description

Production sequencing method and equipment for drilling operations Technical Field

[0001] This application relates to the field of drilling technology, and in particular to a production sequencing method and equipment for drilling. Background Technology

[0002] As production orders become more complex and customer demands become more diverse, the requirements for sequencing the production of multiple orders are also increasing.

[0003] In related technologies, production is typically sorted based on static priority rules such as delivery deadlines.

[0004] However, in the process of realizing this application, the inventors discovered that the relevant technology has at least the following problems: the existing production scheduling method has a low level of intelligence, which easily leads to problems such as low processing and manufacturing efficiency and high energy consumption. Summary of the Invention

[0005] This application provides a production sequencing method and equipment for drilling processes, which improves the intelligence level of production sequencing, thereby increasing processing and manufacturing efficiency and reducing energy consumption.

[0006] In a first aspect, embodiments of this application provide a production sequencing method for drilling operations, including:

[0007] Multi-source data is collected from the drilling equipment; the multi-source data is used to indicate the current processing status of the drilling equipment.

[0008] Retrieve multiple drilling orders that need to be sorted;

[0009] Based on the multi-source data and the multiple orders, the initial production scheduling results are determined;

[0010] Based on the digital twin model and the preset objective function, the initial production scheduling result is iteratively optimized to obtain the final production scheduling result; the preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear.

[0011] The final production schedule result is sent to the drilling equipment so that the drilling equipment can perform drilling based on the final production schedule result.

[0012] In one possible design, each order includes delivery deadlines, sheet material data, and process data; determining the initial production scheduling result based on the multi-source data and multiple orders includes:

[0013] The multi-source data and the sheet material data and process data of multiple orders are input into the association model to obtain the predicted sheet material hardness and predicted energy efficiency matching degree for each order; the association model is trained based on historical multi-source data;

[0014] Determine the urgency and quality requirements for each order;

[0015] The priority of each order is determined based on the predicted hardness of the sheet metal, the predicted energy efficiency matching degree, the urgency of delivery time, and the quality requirement level.

[0016] The initial production schedule is determined based on the priority of each order.

[0017] In one possible design, acquiring multi-source data from the drilling equipment includes:

[0018] Acquire sensor data; the sensor data includes spindle power data, spindle vibration data, image data of the material to be processed, moisture content of the material, density of the material, spindle current value, motion data of each axis, adsorption vacuum degree, tool temperature, and ambient temperature and humidity;

[0019] The sensor data is preprocessed to obtain multi-source data from the device.

[0020] In one possible design, the preprocessing of the sensing data to obtain multi-source data from the device includes:

[0021] The spindle vibration data is subjected to wavelet transform for noise reduction to obtain the target vibration data;

[0022] The spindle power data and the spindle current value are filtered by moving average to obtain smoothed power values ​​and smoothed current values.

[0023] The amplitude of a preset frequency band is extracted from the spectrum of the target vibration data and used as the plate knot data;

[0024] The image data is processed to obtain the plate texture direction angle and knot location coordinates;

[0025] The moisture content of the board is corrected according to the ambient temperature and humidity to obtain the corrected moisture content, and the initial value of the board hardness is determined according to the corrected moisture content and the density of the board.

[0026] Based on the timestamp of the motion data, the sensor data is synchronized to obtain multi-source data from the device.

[0027] In one possible design, the iterative optimization of the initial production scheduling result based on the digital twin model and a preset objective function to obtain the final production scheduling result includes:

[0028] The initial production scheduling results are input into the digital twin model to obtain verification results; the verification results include total processing time, total energy consumption, total tool wear, and abnormal results.

[0029] Based on the preset objective function, the corresponding target value is determined according to the verification results;

[0030] If the target value does not meet the iteration termination condition, the initial production scheduling result is optimized based on the preset optimization strategy to obtain a new production scheduling result. The new production scheduling result is input into the digital twin model to obtain a new verification result. Based on the preset objective function, a new target value is determined according to the new verification result. This process continues until the new target value meets the iteration termination condition or reaches the preset number of iterations, at which point the final production scheduling result is obtained.

[0031] In one possible design, inputting the initial production scheduling results into the digital twin model to obtain verification results includes:

[0032] The initial production scheduling results are input into the correlation model to obtain the prediction results; the prediction results include total processing time, total energy consumption, and total tool wear.

[0033] The prediction results are input into the digital twin model, and drilling is performed in a virtual environment based on the initial production schedule. The prediction results are then visualized to obtain verification results.

[0034] In one possible design, the preset objective function further includes a power consumption constraint term; the step of determining the corresponding target value based on the verification result according to the preset objective function includes:

[0035] Obtain time-of-use electricity price data;

[0036] Based on the preset objective function, the corresponding target value is determined according to the time-of-use electricity price data and the verification results.

[0037] In one possible design, the preset optimization strategy includes at least one of the following: sorting strategy, path strategy, energy efficiency strategy, and tool switching strategy;

[0038] The sorting strategy includes one order having a board hardness greater than a first preset hardness, and another order having a board hardness less than a second preset hardness; the first preset hardness is greater than or equal to the second preset hardness;

[0039] The path strategy includes determining the processing path of the order based on a smooth path algorithm if the hardness of the board material in the order is greater than the first preset hardness; and determining the processing path of the order based on a shortest idle path algorithm if the hardness of the board material in the order is less than the second preset hardness.

[0040] The energy efficiency strategy includes executing orders with predicted energy consumption higher than the preset energy consumption during target periods when the time-of-use electricity price is greater than the preset electricity price;

[0041] The tool changing strategy includes inserting a new tool changing command after the first order in the subsequent order whose plate hardness is less than the second preset hardness if the total tool wear of multiple orders after inserting the tool changing command is greater than the preset wear.

[0042] In one possible design, the method further includes:

[0043] Receive detection data from the drilling equipment during the drilling process; the detection data includes actual energy consumption and actual tool wear;

[0044] If the detection data indicates that there is an anomaly in the currently processed order, a new production schedule is generated based on the remaining orders in the final production schedule result.

[0045] Secondly, embodiments of this application provide a production sequencing device for drilling operations, comprising:

[0046] The acquisition module is used to acquire multi-source data from the drilling equipment; the multi-source data is used to indicate the current processing status of the drilling equipment.

[0047] The acquisition module is also used to acquire multiple drilling orders that need to be sorted.

[0048] The determination module is used to determine the initial production scheduling result based on the multi-source data and the multiple orders;

[0049] The iteration module is used to iteratively optimize the initial production scheduling result based on the digital twin model and the preset objective function to obtain the final production scheduling result; the preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear.

[0050] The sending module is used to send the final production schedule result to the drilling equipment so that the drilling equipment can perform drilling according to the final production schedule result.

[0051] Thirdly, embodiments of this application provide a production sequencing device for drilling processes, comprising: at least one processor and a memory;

[0052] The memory stores computer-executed instructions;

[0053] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the method described in the first aspect above and various possible designs of the first aspect.

[0054] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method described in the first aspect and various possible designs of the first aspect.

[0055] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect and various possible designs of the first aspect.

[0056] This embodiment provides a production scheduling method and equipment for drilling operations. The method includes acquiring multi-source data from the drilling equipment, which indicates the current processing status of the equipment; acquiring multiple drilling orders to be scheduled; determining an initial scheduling result based on the multi-source data and the orders; iteratively optimizing the initial scheduling result based on a digital twin model and a preset objective function to obtain a final scheduling result. The preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear. The final scheduling result is then sent to the drilling equipment so that it can perform drilling operations according to the final scheduling result. The method provided in this embodiment, by integrating real-time multi-source data from the drilling equipment with order information, provides a data foundation that accurately reflects the characteristics of the processing object and the equipment status for scheduling decisions. Based on this, the digital twin model is used to perform multi-objective iterative optimization of the initial scheduling result, effectively achieving a synergistic improvement in processing efficiency, production energy consumption, and processing quality related to tool wear. It overcomes the shortcomings of traditional static scheduling with low intelligence levels, improves processing and manufacturing efficiency, reduces energy consumption, and significantly enhances the adaptability and overall economic benefits of the production system. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 is a schematic diagram of an application scenario for the production sequencing method for drilling provided in an embodiment of this application;

[0059] Figure 2 is a schematic flowchart of a production sequencing method for drilling provided in an embodiment of this application;

[0060] Figure 3 is a schematic flowchart of the production sequencing method for drilling provided in an embodiment of this application.

[0061] Figure 4 is a schematic diagram of the structure of the production sequencing equipment for drilling provided in an embodiment of this application;

[0062] Figure 5 is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application.

[0063] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] It should be noted that the production sequencing method and equipment for drilling provided in this application can be used in the field of drilling technology, or in any field other than drilling technology. The application field of the production sequencing method and equipment for drilling provided in this application is not limited.

[0066] This application specifically relates to dynamic scheduling technology for computer numerical control (CNC) woodworking drilling, primarily applied in industrial fields such as furniture manufacturing, architectural decoration, and custom wood products. In these scenarios, CNC equipment is widely used for high-precision, high-efficiency wood drilling. With the increasing complexity of production orders and the diversification of customer needs, the level of intelligence in scheduling multiple production orders directly impacts the efficiency and quality of processing and manufacturing.

[0067] In related technologies, orders are typically prioritized based on static priority rules such as processing time and delivery deadlines. However, this method has a low level of intelligence, leading to problems such as low processing and manufacturing efficiency and high energy consumption.

[0068] To address the aforementioned technical problems, the inventors of this application have discovered that by collecting multi-source data from drilling equipment and integrating the physical properties of the processed wood and the dynamic state of the equipment, a more accurate data foundation regarding equipment status can be provided for production scheduling decisions. Furthermore, based on this foundation, iterative optimization can be performed based on multiple objectives such as efficiency and energy efficiency to obtain the optimal production scheduling result. This improves the intelligence level of production sequencing, increases processing efficiency, and reduces energy consumption. Based on this, embodiments of this application provide a production sequencing method for drilling processing.

[0069] Figure 1 is a schematic diagram of an application scenario for the production sequencing method for drilling provided in an embodiment of this application. As shown in Figure 1, the terminal device 101 is communicatively connected to the drilling equipment 102.

[0070] In the specific implementation process, the drilling equipment 102 sends multi-source data collected through sensors and motion control cards during the current processing to the terminal equipment 101. The terminal equipment 101 determines the initial production schedule based on the multi-source data and the multiple orders to be processed. Based on a digital twin model and a preset objective function, it iteratively optimizes the initial production schedule to obtain the final production schedule. The preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear. The final production schedule is then sent to the drilling equipment so that it can perform drilling operations according to the final production schedule. The method provided in this application embodiment, by integrating real-time multi-source data from the drilling equipment with order information, can provide a data foundation that accurately reflects the characteristics of the processing object and the equipment status for production scheduling decisions. Based on this, the digital twin model is used to perform multi-objective iterative optimization of the initial production schedule, effectively achieving a synergistic improvement in processing efficiency, production energy consumption, and processing quality related to tool wear. This overcomes the shortcomings of low intelligence levels in traditional static production scheduling, significantly enhancing the adaptability and overall economic benefits of the production system.

[0071] It should be noted that the scenario diagram shown in Figure 1 is merely an example. The production sequencing method and scenario for drilling processing described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of the system and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0072] The technical solutions of this application will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0073] Figure 2 is a flowchart illustrating a production sequencing method for drilling provided in an embodiment of this application. As shown in Figure 2, the method includes:

[0074] 201. Obtain multi-source data from the drilling equipment. Multi-source data is used to indicate the current processing status of the drilling equipment.

[0075] The execution subject in this embodiment can be a terminal device or a server.

[0076] Specifically, before scheduling production, it is necessary to observe the current processing site in real time to understand the state of the equipment in response to the physical characteristics of the processed object (e.g., wood-based panels) during the processing. This provides an accurate data foundation for subsequent production scheduling, accurately demonstrating the current capabilities of the equipment and improving the effectiveness of scheduling.

[0077] In some embodiments, acquiring multi-source data of the drilling equipment may include: acquiring sensor data; the sensor data includes spindle power data, spindle vibration data, image data of the material to be processed, moisture content of the material, density of the material, spindle current value, motion data of each axis, adsorption vacuum degree, tool temperature, and ambient temperature and humidity; preprocessing the sensor data to obtain multi-source data of the equipment.

[0078] Specifically, by collecting multi-source data, a comprehensive digital perception of the current processing can be established. This multi-dimensional raw data can be continuously collected through various sensors and motion control cards integrated into the equipment.

[0079] The spindle power and vibration data in the sensor data reflect the load changes and internal knot defects in the wood during the cutting process in real time; image data can be acquired through industrial cameras for visual analysis to determine the texture and knot location of the wood; the moisture content and density of the board are the basic physical properties of wood; the spindle current value and the motion data of each axis (such as position, speed, and acceleration) characterize the operating status and dynamic load of the equipment; the adsorption vacuum degree reflects the stability of the fixture; the tool temperature is a direct indicator of wear and thermal load; and the ambient temperature and humidity affect the deformation of the wood and the accuracy of the equipment.

[0080] In this embodiment, by collecting the above-mentioned multi-source data, the status of the processing object (wood), drilling equipment and external environment can be digitized in a unified manner, providing high-dimensional information input for subsequent intelligent decision-making that far exceeds traditional single data sources (such as time).

[0081] In some embodiments, preprocessing the sensing data to obtain multi-source data of the device may include: performing wavelet transform noise reduction on the spindle vibration data to obtain target vibration data; performing moving average filtering on the spindle power data and spindle current value to obtain smoothed power value and smoothed current value; extracting the amplitude of a preset frequency band from the spectrum of the target vibration data as the board knot data; performing recognition processing on the image data to obtain the board texture direction angle and knot location coordinates; correcting the board moisture content according to the ambient temperature and humidity to obtain the corrected moisture content; determining the initial value of the board hardness based on the corrected moisture content and board density; and synchronizing the sensing data with the timestamp of the motion data as a reference to obtain multi-source data of the device.

[0082] Specifically, after obtaining multi-source data, the key preprocessing steps of cleaning, feature extraction, and fusion of the multi-source data can be performed first.

[0083] Among them, wavelet transform denoising is a signal processing technique that can effectively separate noise in vibration signals from impact characteristics caused by defects such as knots.

[0084] Moving average filtering smooths out random fluctuations in power and current signals by averaging adjacent data points, highlighting their stable trend.

[0085] Extracting the amplitude of a preset frequency band from the spectrum refers to performing frequency domain analysis on the noise-reduced vibration signal to quantify the vibration energy within a specific frequency range (such as 100-300Hz), which is strongly correlated with the presence and intensity of knots.

[0086] Image recognition processing refers to using computer vision algorithms to analyze images of the board surface and automatically identify the direction of wood fibers (texture direction angle) and the precise pixel position of knots.

[0087] Correcting the moisture content based on ambient temperature and humidity can be achieved by using a known temperature and humidity compensation model to calibrate the original moisture content value measured by the sensor, thereby eliminating environmental interference and obtaining a more accurate corrected moisture content. Furthermore, this corrected value can be combined with the measured density of the board material to calculate an initial hardness value that more accurately reflects the processing difficulty using empirical formulas (such as weighted summation formulas).

[0088] Synchronization processing based on the timestamp of motion data refers to aligning all data from different sensors with different acquisition times to a high-precision device motion time sequence, forming a time-space synchronized fusion data packet.

[0089] It should be noted that this fused data packet can be used as a representation of device status to input into the association model for computation, and can also be used as training data to incrementally train the association model in order to improve the accuracy of the association model.

[0090] Through the preprocessing process of the above system, raw, heterogeneous, and noisy sensor data can be transformed into a clean, high-quality information set with key feature labels and consistent in time and space, providing reliable data input for accurate prediction and intelligent decision-making of subsequent correlation models.

[0091] 202. Obtain multiple drilling orders to be sorted.

[0092] Specifically, multiple drilling orders constitute a set of tasks that the production scheduling system needs to process. These drilling orders can originate from the enterprise's upper-level management systems, such as Manufacturing Execution System (MES) or Enterprise Resource Planning (ERP). Each order, as an independent production task unit, contains the basic information necessary for execution, including the order's unique identifier, the material and specifications of the sheet metal to be processed, the number of holes to be drilled, and the customer's required delivery time.

[0093] 203. Determine the initial production schedule based on multi-source data and multiple orders.

[0094] Specifically, after obtaining multi-source data representing the current equipment status and multiple pending orders, a preliminary and reasonable production sequence can be generated based on these two data sets as the starting point for subsequent optimization.

[0095] For example, a comprehensive decision can be made based on real-time, multi-source data and static information from pending orders. Multi-source data provides the current health status of the equipment (and, in cases where ambient temperature and humidity are included, real-time processing environment conditions can also be reflected). Order information provides the basic constraints and objectives of the tasks. Through a specific decision-making algorithm, these two types of information are fused to calculate an initial processing sequence. This initial scheduling result is not directly used as the final scheduling result, but its quality directly affects the efficiency and effectiveness of subsequent optimization processes.

[0096] In some embodiments, each order includes delivery deadlines, sheet material data, and process data. Determining the initial production scheduling result based on multi-source data and multiple orders may include: inputting multi-source data and sheet material data and process data of multiple orders into an association model to obtain the predicted sheet material hardness and predicted energy efficiency matching degree corresponding to each order; the association model is trained based on historical multi-source data; determining the delivery urgency and quality requirement level of each order; determining the priority of each order based on the predicted sheet material hardness, predicted energy efficiency matching degree, delivery urgency, and quality requirement level of each order; and determining the initial production scheduling result based on the priority of each order.

[0097] Specifically, the matching degree between board hardness and energy efficiency can be predicted based on the prediction model.

[0098] The correlation model is a machine learning model (such as a neural network) trained on a large amount of historical multi-source data. Its function is to learn the complex mapping relationship between processing parameters, material properties, and processing outputs (such as energy consumption and tool wear). Predicting board hardness is a quantitative assessment of the overall processing difficulty of an order, based on the model's comprehensive data on the board material (such as density and moisture content) and the current equipment status. It depends not only on the density and moisture content of the wood itself but also on the process (e.g., deep hole processing may mean a higher load in the model). Predicting energy efficiency matching degree is a prediction of the energy utilization efficiency score when executing an order, combining the current equipment status (such as spindle efficiency and background energy consumption) with the order's process data. It can also incorporate data such as ambient temperature and humidity. For example, at the current workshop temperature, processing high-precision orders requires additional energy consumption to maintain stability, resulting in a low energy efficiency matching degree.

[0099] In the specific implementation process, the association model can first be incrementally trained based on multi-source data to obtain the latest association model. Then, real-time multi-source data, along with the sheet material and process data of each order, can be input into this latest association model to obtain the predicted sheet material hardness and predicted energy efficiency matching degree specific to each order. Simultaneously, the urgency of delivery (e.g., based on the reciprocal of remaining time) and quality requirement level (based on process complexity such as hole diameter and hole depth) of each order can be calculated in parallel. Furthermore, a multi-criteria decision-making method (such as weighted scoring) can be used to assign weights to the four dimensions of each order and calculate a comprehensive priority score. Finally, the orders are sorted according to their scores, and this sorting result is determined as the initial production scheduling result.

[0100] In this embodiment, by using an association model to make forward-looking predictions on the processing difficulty and energy efficiency of orders, and by coordinating these predictions with delivery deadlines and quality requirements, a leap from static sorting to dynamic optimization can be achieved, enabling the initial production sequence to achieve a better starting balance in terms of efficiency, energy efficiency, and processing stability.

[0101] In some embodiments, priority can be determined based on timber availability; for example, if timber for an order is not delivered on time, the priority of that order can be lowered. Identification information such as QR codes or electronic tags can be attached to the timber to track its logistics and delivery.

[0102] 204. Based on the digital twin model and the preset objective function, the initial production scheduling results are iteratively optimized to obtain the final production scheduling results. The preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear.

[0103] Specifically, after the initial production schedule is determined, a digital twin model can be used to iteratively optimize the initial production schedule based on a preset objective function to obtain a better final production schedule and build an automated decision-making closed loop.

[0104] In some embodiments, the initial production scheduling result is iteratively optimized based on a digital twin model and a preset objective function to obtain a final production scheduling result. This may include: inputting the initial production scheduling result into the digital twin model to obtain verification results; the verification results include total processing time, total energy consumption, total tool wear, and abnormal results; determining the corresponding target value based on the verification results according to the preset objective function; if the target value does not meet the iteration termination condition, optimizing the initial production scheduling result based on a preset optimization strategy to obtain a new production scheduling result; inputting the new production scheduling result into the digital twin model to obtain a new verification result; determining the corresponding new target value based on the new verification result according to the preset objective function; and so on, until the new target value meets the iteration termination condition or reaches a preset number of iterations, at which point the final production scheduling result is obtained.

[0105] The preset objective function unifies three key, often conflicting, indicators—completion time, energy consumption, and machining quality related to tool wear—into a quantifiable evaluation system. The digital twin model serves as a high-fidelity virtual testing platform. By simulating the initial production scheduling results within the digital twin model, a comprehensive performance verification report is obtained, and scores are assigned based on the objective function. If the score is lower than a preset value, an optimization algorithm is triggered to adjust the production scheduling plan according to preset rules, and simulation verification is performed again. This process iterates until a final production scheduling result that achieves an optimal balance across multiple indicators, making the target value less than the preset target value, or until the maximum number of iterations is reached, at which point the optimal solution is taken as the final production scheduling result.

[0106] In this embodiment, by constructing an automated iterative closed loop of generation-verification-optimization, the global optimal solution can be efficiently screened and approximated in the virtual space, ensuring that the final solution is significantly better than the traditional static scheduling results in terms of efficiency, energy efficiency and quality.

[0107] In some embodiments, inputting the initial production scheduling results into a digital twin model to obtain verification results may include: inputting the initial production scheduling results into an association model to obtain prediction results; the prediction results include total processing time, total energy consumption, and total tool wear. The prediction results are then input into the digital twin model, and drilling is performed in a virtual environment based on the initial production scheduling results. The prediction results are then visualized to obtain verification results.

[0108] Specifically, a digital twin model can embed an associated model, or the digital twin model and the associated model can be used as two independent models in a collaborative working mechanism during the verification process.

[0109] The correlation model, acting as a rapid prediction engine, directly outputs predicted values ​​of key performance indicators (KPIs) based on the initial production scheduling results, such as total processing time, total energy consumption, and total tool wear. The digital twin model, building upon this, dynamically simulates the entire processing flow in a 3D virtual environment. It not only receives and intuitively displays these prediction results but also simulates physical interactions, detecting dynamic anomalies that are difficult for algorithmic models to cover, such as equipment motion interference and fixture collisions.

[0110] For example, digital twin models can be used to identify process risks and diagnose bottlenecks. For instance, peak equipment load can be determined to indicate the risk of continuous spindle current exceeding limits during a given period. Tool life warnings can be provided to predict whether any tools will reach their lifespan limit during machining, leading to unplanned downtime. Thermal management bottlenecks can be identified to determine whether tool temperatures will exceed safe thresholds during continuous hardwood machining. Logistics connection points can be identified to assess the risk of equipment waiting for materials based on material arrival times. Visual bottlenecks can also be identified, highlighting machining path conflicts, equipment interference, and waiting periods in the 3D model.

[0111] In practical applications, while the data fusion package corresponding to the multi-source data in step 201 is input into the association model for incremental training, it is also input into the digital twin model so that the location and status of the virtual device corresponding to the digital twin model are completely synchronized with the physical world.

[0112] In this embodiment, by adopting a dual verification mechanism that combines model prediction and simulation, we can ensure the computational efficiency of the optimization loop and ensure the physical feasibility and safety of the production scheduling plan through high-fidelity simulation, thereby comprehensively reducing the actual execution risk.

[0113] In some embodiments, the preset objective function further includes an electricity consumption constraint term; determining the corresponding target value based on the preset objective function and the verification results may include: acquiring time-of-use electricity price data; and determining the corresponding target value based on the preset objective function, the time-of-use electricity price data, and the verification results.

[0114] Specifically, electricity consumption constraints can be constructed for a predefined objective function, elevating the optimization objective from simple physical energy consumption management to production cost optimization. For example, time-of-use (TOU) electricity price data from the power grid can be obtained, defining the electricity cost for different time periods. When calculating the objective function value based on the verification results, total energy consumption can be converted into total electricity cost according to the time period in which it occurs, and this total electricity cost can be used as a key optimization indicator. This ensures that the optimization process focuses not only on how many kilowatt-hours of electricity are saved, but also on how much electricity cost is saved.

[0115] In this embodiment, by incorporating time-of-use electricity pricing into the optimization objective, high-energy-consuming operations can be intelligently guided to avoid peak electricity price periods, thereby significantly reducing energy costs and directly improving the economic efficiency of production and operation while completing the same production tasks.

[0116] In some embodiments, the preset optimization strategy includes at least one of the following: sorting strategy, path strategy, energy efficiency strategy, and tool changing strategy; wherein, the sorting strategy includes that the hardness of the sheet metal in one order of adjacent orders is greater than a first preset hardness, and the hardness of the sheet metal in another order is less than a second preset hardness; the first preset hardness is greater than or equal to the second preset hardness.

[0117] The path strategy includes determining the processing path of an order based on a smooth path algorithm if the hardness of the board material in the order is greater than a first preset hardness, and determining the processing path of an order based on a shortest idle path algorithm if the hardness of the board material in the order is less than a second preset hardness.

[0118] The energy efficiency strategy includes executing orders with predicted energy consumption exceeding the preset energy consumption during target periods when the time-of-use electricity price is greater than the preset electricity price.

[0119] The tool changing strategy includes inserting a new tool changing command after the first order in the subsequent order whose plate hardness is less than the second preset hardness if the total tool wear of multiple orders after inserting the tool changing command is greater than the preset wear.

[0120] In this embodiment, the first preset hardness can be 0.7 g / cm³, and the second preset hardness can be 0.5 g / cm³.

[0121] Specifically, in iterative optimization, new solutions can be generated based on preset optimization strategies.

[0122] The sorting strategy, by alternating high-hardness orders with low-hardness orders, provides an intermittent recovery window for the tool, which helps dissipate heat and reduce continuous heavy-load wear.

[0123] The path strategy employs differentiated planning: a smooth path algorithm is used for high-hardness plates to protect the tool and ensure hole quality through smooth acceleration and deceleration; while a shortest idle path algorithm is used for low-hardness plates to maximize efficiency by utilizing their ease of machining.

[0124] Energy efficiency strategies directly respond to electricity price signals, proactively avoiding high-energy-consuming orders during peak hours to achieve cost savings.

[0125] The tool change strategy is based on the predicted cumulative tool wear. It intelligently inserts a preventative tool change command at the time when the impact on the tool is minimal, such as after machining softwood, to avoid catastrophic tool failure when machining hardwood.

[0126] In this embodiment, by adopting refined strategies targeting different optimization dimensions, the scheme can be systematically adjusted during the iteration process, effectively resolving the inherent contradictions between efficiency, cost, and quality, thereby synergistically improving the overall performance of the production scheduling scheme.

[0127] 205. Send the final production schedule to the drilling equipment so that the drilling equipment can perform drilling based on the final production schedule.

[0128] Specifically, after obtaining the final production schedule, the drilling equipment can be controlled to perform drilling operations according to the final production schedule.

[0129] For example, the final production scheduling result is a fully validated and optimized detailed work plan that can directly guide production. This result can be reliably and stably transmitted from the optimized terminal device or server to the CNC system of the drilling equipment via industrial network communication protocols. After receiving and parsing the instruction, the CNC system can drive the equipment to automatically execute the drilling task according to the optimal sequence and parameters.

[0130] In this embodiment, by automatically sending out the final production scheduling results and driving the equipment to execute them, it is possible to achieve a tight integration of production scheduling decisions and production control, ensuring that the optimal solution in the virtual space can be transformed into efficient and high-quality production activities in the physical world without loss.

[0131] The production scheduling method for drilling provided in this embodiment integrates real-time multi-source data from drilling equipment with order information, providing a data foundation that accurately reflects the characteristics of the workpiece and the equipment status for scheduling decisions. Based on this, a digital twin model is used to perform multi-objective iterative optimization of the initial scheduling results, effectively achieving a synergistic improvement in processing efficiency, production energy consumption, and processing quality related to tool wear. This overcomes the shortcomings of traditional static scheduling's low level of intelligence, significantly enhancing the adaptability of the production system and overall economic benefits.

[0132] Figure 3 is a schematic flowchart (II) of the production sequencing method for drilling provided in an embodiment of this application. As shown in Figure 3, the method includes:

[0133] 301. Obtain multi-source data from the drilling equipment; multi-source data is used to indicate the current processing status of the drilling equipment.

[0134] 302. Obtain multiple drilling orders to be sorted;

[0135] 303. Determine the initial production schedule based on multi-source data and multiple orders;

[0136] 304. Based on the digital twin model and the preset objective function, the initial production scheduling results are iteratively optimized to obtain the final production scheduling results; the preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear.

[0137] 305. Send the final production schedule to the drilling equipment so that the drilling equipment can perform drilling based on the final production schedule.

[0138] Steps 301 to 305 in this embodiment are similar to steps 201 to 205 in the above embodiment, and will not be described again here.

[0139] 306. Receive the detection data of the drilling equipment during the processing; the detection data includes actual energy consumption and actual tool wear;

[0140] 307. Determine if the detection data indicates an anomaly in the currently processed order. If yes, return to steps 301 to 304 and generate a new production schedule based on the remaining orders. If no, proceed to step 308.

[0141] 308. Record the processing data and perform incremental training on the correlation model.

[0142] If the detection data indicates that there is an anomaly in the currently processed order, a new production schedule will be generated based on the remaining orders in the final production schedule.

[0143] Specifically, after the final production schedule is sent to the drilling equipment and execution begins, the system can continuously receive monitoring data from the equipment, including key indicators such as actual energy consumption and actual tool wear calculated from sensor data. Anomaly detection and dynamic response can then be based on this monitoring data.

[0144] For example, real-time detection data can be compared with expected indicators. If the data indicates a serious anomaly in the current processing order (such as a sudden change in equipment status or a processing quality deviation exceeding a threshold), a global rescheduling mechanism is immediately triggered. The process returns to step 301, where an optimized production schedule is regenerated using the remaining unfinished orders and the latest equipment status as input. This enables rapid response and dynamic adjustment to production interruptions. If no anomaly is detected, or the anomaly is minor (such as a sudden change in equipment status or a processing quality deviation not exceeding a threshold), the actual processing data is recorded, and this new data is used to incrementally train the correlation model. This allows the model to continuously adapt to changes in the processing environment and material characteristics, gradually improving prediction accuracy and scheduling quality.

[0145] By introducing an anomaly detection and rescheduling mechanism based on real-time detection data, it is possible to effectively deal with unexpected situations in the production process, upgrade the traditional open-loop scheduling to adaptive closed-loop control, and significantly enhance the robustness of the production system in the face of uncertainty and the continuity of intelligent decision-making.

[0146] The production scheduling method for drilling provided in this embodiment achieves the adaptive and self-learning capabilities of the production scheduling system at both the macro-scheduling and micro-optimization levels by constructing a two-layer cyclic optimization architecture.

[0147] First, through the inner loop of step 304, the initial production scheduling plan can be rapidly iterated and optimized in the virtual space based on the digital twin model. This process, through the generation-verification-optimization closed loop of step 304, finds a refined solution that achieves the best balance between processing efficiency, energy consumption, and tool wear for a fixed set of orders, thereby ensuring that the production plan issued to the physical equipment is itself a fully verified near-optimal solution.

[0148] Secondly, the outer loop from steps 307 to 301 enables the production line to dynamically respond to unforeseen circumstances. When a serious anomaly is detected in real-time by step 307, a rescheduling process starting from step 301 is immediately triggered. Based on the latest equipment status and remaining orders, a new global production schedule is generated. This allows the production system to quickly recover from planned disruptions, effectively reducing downtime and resource waste caused by anomalies.

[0149] Ultimately, the combination of these two loops with the incremental learning mechanism in step 308 significantly improves the intelligence level of production sequencing. This upgrades the traditional static, open-loop production planning model into a dynamic, closed-loop, adaptive intelligent production control system, significantly enhancing production resilience, resource utilization, and overall economic efficiency.

[0150] Figure 4 is a schematic diagram of the structure of a production sequencing device for drilling provided in an embodiment of this application. As shown in Figure 4, the production sequencing device 40 for drilling includes: an acquisition module 401, a determination module 402, an iteration module 403, and a sending module 404.

[0151] The acquisition module 401 is used to acquire multi-source data from the drilling equipment. The multi-source data is used to indicate the current processing status of the drilling equipment.

[0152] The acquisition module 401 is also used to acquire multiple drilling orders that need to be sorted.

[0153] The determination module 402 is used to determine the initial production scheduling results based on multi-source data and multiple orders.

[0154] The iteration module 403 is used to iteratively optimize the initial production scheduling results based on the digital twin model and a preset objective function to obtain the final production scheduling results. The preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear.

[0155] The sending module 404 is used to send the final production schedule result to the drilling equipment so that the drilling equipment can perform drilling according to the final production schedule result.

[0156] The production scheduling equipment for drilling operations provided in this application integrates real-time multi-source data from the drilling equipment with order information, providing a data foundation that accurately reflects the characteristics of the workpiece and the equipment status for scheduling decisions. Based on this, a digital twin model is used to perform multi-objective iterative optimization of the initial scheduling results, effectively achieving a synergistic improvement in processing efficiency, production energy consumption, and processing quality related to tool wear. This overcomes the shortcomings of traditional static scheduling's low level of intelligence, significantly enhancing the adaptability of the production system and overall economic benefits.

[0157] In some embodiments, each order includes delivery deadlines, sheet material data, and process data. The determining module 402 is specifically used to: input multi-source data and sheet material data and process data from multiple orders into the association model to obtain the predicted sheet material hardness and predicted energy efficiency matching degree corresponding to each order. The association model is trained based on historical multi-source data. The urgency of delivery and the quality requirement level of each order are determined. The priority of each order is determined based on its predicted sheet material hardness, predicted energy efficiency matching degree, urgency of delivery, and quality requirement level. The initial production scheduling result is determined based on the priority of each order.

[0158] In some embodiments, the acquisition module 401 is specifically used to: acquire sensor data. The sensor data includes spindle power data, spindle vibration data, image data of the material to be processed, moisture content of the material, density of the material, spindle current value, motion data of each axis, adsorption vacuum degree, tool temperature, and ambient temperature and humidity. The sensor data is preprocessed to obtain multi-source data of the equipment.

[0159] In some embodiments, the acquisition module 401 is specifically used for: performing wavelet transform noise reduction on the spindle vibration data to obtain target vibration data; performing moving average filtering on the spindle power data and spindle current value to obtain smoothed power and current values; extracting the amplitude of a preset frequency band from the spectrum of the target vibration data as the board knot data; performing recognition processing on the image data to obtain the board texture direction angle and knot location coordinates; correcting the board moisture content according to the ambient temperature and humidity to obtain the corrected moisture content; determining the initial value of the board hardness based on the corrected moisture content and board density; and synchronizing the sensor data using the timestamp of the motion data as a reference to obtain multi-source data from the device.

[0160] In some embodiments, the iteration module 403 is specifically used to: input the initial production scheduling result into the digital twin model to obtain verification results. The verification results include total processing time, total energy consumption, total tool wear, and abnormal results. Based on a preset objective function, the corresponding target value is determined according to the verification results. If the target value does not meet the iteration termination condition, the initial production scheduling result is optimized based on a preset optimization strategy to obtain a new production scheduling result. The new production scheduling result is input into the digital twin model to obtain a new verification result. Based on the preset objective function, the corresponding new target value is determined according to the new verification result. This process continues until the new target value meets the iteration termination condition or reaches a preset number of iterations, at which point the final production scheduling result is obtained.

[0161] In some embodiments, the iteration module 403 is specifically used to: input the initial scheduling results into the correlation model to obtain prediction results. The prediction results include total processing time, total energy consumption, and total tool wear. The prediction results are then input into a digital twin model to perform drilling operations in a virtual environment based on the initial scheduling results, and the prediction results are visualized to obtain verification results.

[0162] In some embodiments, the preset objective function further includes an electricity consumption constraint term. The iteration module 403 is specifically used to: acquire time-of-use electricity price data; and determine the corresponding target value based on the preset objective function, the time-of-use electricity price data, and the verification results.

[0163] In some embodiments, the preset optimization strategy includes at least one of the following: sorting strategy, path strategy, energy efficiency strategy, and tool switching strategy.

[0164] The sorting strategy includes orders where the board hardness of one order is greater than a first preset hardness, and the board hardness of the other order is less than a second preset hardness. The first preset hardness is greater than or equal to the second preset hardness.

[0165] The path strategy includes determining the processing path of an order based on a smooth path algorithm if the hardness of the board material is greater than a first preset hardness, and determining the processing path of an order based on a shortest idle path algorithm if the hardness of the board material is less than a second preset hardness.

[0166] The energy efficiency strategy includes executing orders with predicted energy consumption exceeding the preset energy consumption during target periods when the time-of-use electricity price is greater than the preset electricity price.

[0167] The tool changing strategy includes inserting a new tool changing command after the first order in the subsequent order whose plate hardness is less than the second preset hardness if the total tool wear of multiple orders after inserting the tool changing command is greater than the preset wear.

[0168] In some embodiments, the iteration module 403 is further configured to: receive detection data from the drilling equipment during the drilling process. The detection data includes actual energy consumption and actual tool wear.

[0169] If the detection data indicates that there is an anomaly in the currently processed order, a new production schedule will be generated based on the remaining orders in the final production schedule.

[0170] The production sequencing equipment for drilling provided in this application embodiment can be used to execute the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be repeated here.

[0171] Figure 5 is a schematic diagram of the structure of the electronic device provided in this application. As shown in Figure 5, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, the memory 502, and the communication component 503 are connected via a bus.

[0172] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0173] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0174] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0175] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0176] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0177] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0178] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0179] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0180] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0181] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0182] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0184] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0185] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0186] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A production sequencing method for drilling operations, characterized in that, include: Acquire multi-source data from the drilling equipment; the multi-source data is used to indicate the current processing status of the drilling equipment. Retrieve multiple drilling orders that need to be sorted; Based on the multi-source data and the multiple orders, the initial production scheduling results are determined; Based on the digital twin model and the preset objective function, the initial production scheduling result is iteratively optimized to obtain the final production scheduling result; the preset objective function includes completion time constraints, energy consumption constraints, and quality constraints related to tool wear. The final production schedule result is sent to the drilling equipment so that the drilling equipment can perform drilling based on the final production schedule result.

2. The method according to claim 1, characterized in that, Each order includes delivery deadline, sheet material data, and process data. Determining the initial production schedule based on the multi-source data and multiple orders includes: inputting the multi-source data and the sheet material data and process data of the multiple orders into a correlation model to obtain the predicted sheet material hardness and predicted energy efficiency matching degree corresponding to each order; the correlation model is trained based on historical multi-source data; determining the delivery urgency and quality requirement level of each order; determining the priority of each order based on the predicted sheet material hardness, predicted energy efficiency matching degree, delivery urgency, and quality requirement level; and determining the initial production schedule based on the priority of each order.

3. The method according to claim 1, characterized in that, The acquisition of multi-source data from the drilling equipment includes: acquiring sensor data; the sensor data includes spindle power data, spindle vibration data, image data of the material to be processed, moisture content of the material, density of the material, spindle current value, motion data of each axis, adsorption vacuum degree, tool temperature, and ambient temperature and humidity; and preprocessing the sensor data to obtain the multi-source data of the equipment.

4. The method according to claim 3, characterized in that, The preprocessing of the sensing data to obtain multi-source data of the device includes: performing wavelet transform noise reduction on the spindle vibration data to obtain target vibration data; performing moving average filtering on the spindle power data and spindle current value to obtain smoothed power value and smoothed current value; extracting the amplitude of a preset frequency band from the spectrum of the target vibration data as board knot data; performing recognition processing on the image data to obtain board texture direction angle and knot position coordinates; correcting the board moisture content according to the ambient temperature and humidity to obtain the corrected moisture content; determining the initial value of board hardness based on the corrected moisture content and board density; and synchronizing the sensing data with the timestamp of the motion data as a reference to obtain multi-source data of the device.

5. The method according to claim 1, characterized in that, The step of iteratively optimizing the initial production scheduling result based on a digital twin model and a preset objective function to obtain a final production scheduling result includes: inputting the initial production scheduling result into the digital twin model to obtain verification results; the verification results include total processing time, total energy consumption, total tool wear, and abnormal results; determining a corresponding target value based on the verification results according to the preset objective function; if the target value does not meet the iteration termination condition, optimizing the initial production scheduling result based on a preset optimization strategy to obtain a new production scheduling result; inputting the new production scheduling result into the digital twin model to obtain a new verification result; determining a corresponding new target value based on the new verification result according to the preset objective function; and so on, until the new target value meets the iteration termination condition or reaches a preset number of iterations, thus obtaining the final production scheduling result.

6. The method according to claim 5, characterized in that, The step of inputting the initial production scheduling result into the digital twin model to obtain the verification result includes: inputting the initial production scheduling result into the association model to obtain the prediction result; the prediction result includes the total processing time, total energy consumption, and total tool wear; inputting the prediction result into the digital twin model, performing drilling processing in a virtual environment according to the initial production scheduling result, visualizing the prediction result, and obtaining the verification result.

7. The method according to claim 5, characterized in that, The preset objective function further includes an electricity consumption constraint term; the step of determining the corresponding target value based on the preset objective function and the verification result includes: acquiring time-of-use electricity price data; and determining the corresponding target value based on the preset objective function, the time-of-use electricity price data, and the verification result.

8. The method according to claim 5, characterized in that, The preset optimization strategy includes at least one of the following: sorting strategy, path strategy, energy efficiency strategy, and tool changing strategy; the sorting strategy includes that in adjacent orders, the sheet hardness of one order is greater than a first preset hardness, and the sheet hardness of another order is less than a second preset hardness; the first preset hardness is greater than or equal to the second preset hardness; the path strategy includes that if the sheet hardness of the order is greater than the first preset hardness, the processing path of the order is determined based on a smooth path algorithm; if the sheet hardness of the order is less than the second preset hardness, the processing path of the order is determined based on a shortest idle path algorithm; the energy efficiency strategy includes that during target periods when the time-of-use electricity price is greater than a preset electricity price, orders with predicted energy consumption higher than preset energy consumption are executed; the tool changing strategy includes that if the total tool wear of multiple orders after inserting a tool changing instruction is greater than a preset wear amount, a new tool changing instruction is inserted after the first order in the subsequent orders whose sheet hardness is less than the second preset hardness.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: receiving detection data from the drilling equipment during the processing; the detection data includes actual energy consumption and actual tool wear; if the detection data indicates that there is an anomaly in the currently processed order, a new production schedule is generated based on the remaining orders in the final production schedule result.

10. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, causing the at least one processor to perform the production sequencing method for drilling as described in any one of claims 1 to 9.

Images