A method and related apparatus for intelligent scheduling of medium-thick plate scribing and cutting dual interactive platforms
By acquiring the nesting characteristic parameters of medium and heavy plates, a whole-plate time prediction model is constructed, a production sequence is generated, and dual interactive worktables are controlled for processing. This solves the problem of separating the scribing and cutting processes of medium and heavy plate workpieces, and realizes the continuity and high efficiency of the production process.
Patent Information
- Application Number
- CN202611569112.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-10
- Publication Date
- 2026-11-10
AI Technical Summary
In existing technologies, the scribing and cutting processes for medium and thick plate workpieces are carried out separately, resulting in a discontinuous production process. This makes it impossible to reasonably match the processing cycle of the dual interactive worktables, thus limiting production efficiency.
By acquiring the nesting characteristic parameters of medium and heavy plates, a whole plate time prediction model is constructed to determine the scribing time of a single workpiece. Based on the relationship between the scribing time and the preset threshold interval, a production sequence is generated to control the dual interactive worktables to process the workpieces and dynamically adjust the timing of the interchange to achieve synchronous parallel operation of scribing and cutting.
It realizes closed-loop processing of scribing and cutting of medium and thick plates, which improves production efficiency, reduces station waiting and changeover time, and enhances equipment utilization.
Smart Images

Figure CN123060285A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent scheduling technology for steel structure plates, and in particular to an intelligent scheduling method and related device for a dual interactive platform for scribing and cutting of medium and thick plates. Background Technology
[0002] In the manufacturing of steel structures such as iron towers and heavy machinery, medium and thick plate workpieces typically require two processing steps: contour cutting and surface marking. Currently, laser cutting equipment with dual interactive worktables is widely used in the industry. However, in actual production, such equipment is usually only used to perform a single contour cutting process. The marking and cutting processes are often carried out separately, which requires the workpieces to be transferred between different equipment or workstations, resulting in a discontinuous production process.
[0003] Furthermore, current production scheduling relies primarily on manual experience to determine the order of material loading, lacking quantitative analysis of the processing time for the marking and cutting processes. Consequently, it is impossible to rationally match the processing cycle of the dual interactive worktables. This results in the marking and cutting stations waiting for each other, failing to fully utilize the interchangeability advantage of the dual interactive worktables, making it difficult for the production line to achieve uninterrupted cyclical processing, and thus restricting overall production efficiency.
[0004] Therefore, there is an urgent need for a method that can coordinate the production of both scribing and cutting processes for medium and heavy plates and achieve closed-loop processing with dual interactive worktables. Summary of the Invention
[0005] The purpose of this application is to provide an intelligent scheduling method and related device for a dual interactive platform for scribing and cutting of medium and heavy plates, which can solve the technical problems in the prior art such as process fragmentation, mismatch of workstation cycle time, and lack of quantitative data support for production scheduling.
[0006] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides an intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates, including: Obtain nesting feature parameters for multiple medium-thick plates to be processed; the nesting feature parameters include at least plate thickness, number of workpieces, total perimeter of cutting path and number of holes.
[0007] For any medium-thick plate to be processed, the corresponding whole-plate time prediction model is matched from multiple whole-plate time prediction models constructed according to plate thickness, based on the plate thickness of the medium-thick plate to be processed. The nesting feature parameters are then input into the matched whole-plate time prediction model to obtain the whole-plate predicted processing time of the medium-thick plate to be processed.
[0008] The scribing time of a single workpiece in the medium-thick plate to be processed is determined based on the overall plate predicted processing time, and the production scheduling category of the medium-thick plate to be processed is determined based on the relationship between the scribing time of a single workpiece and a preset threshold range. For multiple medium-thick plates to be processed in the production scheduling category of qualified plates, a production sequence is generated based on the difference in the scribing time of a single workpiece.
[0009] The dual interactive worktable is controlled to process according to the production sequence; the dual interactive worktable includes a first worktable and a second worktable, the first worktable is equipped with a mechanical scribing execution mechanism, the second worktable is equipped with a laser cutting mechanism, the first worktable and the second worktable can interchange positions, and the first worktable and the second worktable are configured such that: while the first worktable performs mechanical scribing on a medium-thick plate, the second worktable performs laser cutting on another medium-thick plate.
[0010] During the processing of the dual interactive worktable, the timing of the exchange between the first worktable and the second worktable is adjusted based on the deviation between the real-time working data of the dual interactive worktable and the predicted processing time of the whole plate, and / or the production sequence of the remaining medium and thick plates to be processed is updated.
[0011] Optionally, the whole-plate time prediction model for different plate thicknesses is constructed in the following way: Retrieve historical production log data.
[0012] The historical production log data is preprocessed to remove records with null or missing key fields, resulting in preprocessed historical production log data.
[0013] Based on preprocessed historical production log data, a global regression model was obtained by using the total perimeter of the cutting path and the number of holes as independent variables and the total measured working hours as the dependent variable.
[0014] Based on the mean and standard deviation of the residuals from the global regression model, outlier samples are removed from the preprocessed historical production log data.
[0015] The historical production log data, after removing abnormal samples, is split into multiple subsets based on plate thickness.
[0016] Multiple linear regression was performed on each subset of data to obtain the whole plate time prediction model for each plate thickness.
[0017] Optionally, based on the residual mean and residual standard deviation of the global regression model, outlier samples are removed from the preprocessed historical production log data, including: Calculate the residual for each sample in the preprocessed historical production log data.
[0018] Calculate the mean and standard deviation of the residuals for all valid samples.
[0019] When the absolute value of the deviation of the residual of any sample from the mean of the residuals is greater than the product of the anomaly determination factor and the standard deviation of the residuals, the sample is determined to be an anomaly.
[0020] Optionally, the preset threshold range includes a lower threshold and an upper threshold.
[0021] The single-workpiece scribing time of the medium-thick plate to be processed is determined based on the overall plate predicted processing time, including: The net processing time is determined by predicting the processing time of the entire plate and the preset clamping auxiliary time.
[0022] Divide the net processing time by the number of medium-thick plates to be processed to obtain the scribing time for a single workpiece.
[0023] Based on the relationship between the single workpiece scribing time and the preset threshold range, the production scheduling category of the medium-thick plate to be processed is determined, including: When the scribing time of a single workpiece is greater than or equal to the upper limit threshold, it is determined to be a qualified sheet material.
[0024] When the scratching time of a single workpiece is less than or equal to the lower threshold, it is determined to be a substandard material.
[0025] When the scribing time of a single workpiece is greater than the lower threshold and less than the upper threshold, it is determined to be a boundary plate and manual review information is output.
[0026] Optionally, a production sequence is generated based on the difference in scribing time for a single workpiece, including: Arrange multiple medium-thick plates of any thickness in descending order of their thickness.
[0027] Select the first medium-thick plate from the sorted list of plates to be processed as the first plate to be put into production.
[0028] Among the multiple medium-thick plates to be processed, the medium-thick plate with the smallest difference between the single workpiece scribing time and the single workpiece scribing time of the previous production plate is selected as the next production plate, until all medium-thick plates to be processed are scheduled for production.
[0029] Optionally, the dual interactive worktable further includes a transverse translation track, wherein the first worktable and the second worktable each have built-in upper and lower double-layer support surfaces, and are transversely translated as a whole along the transverse translation track to exchange positions.
[0030] Based on the deviation between the real-time operating data of the dual interactive worktables and the predicted processing time of the entire plate, the timing of the interchange between the first and second worktables is adjusted, and / or the production sequence of the remaining medium-thick plates to be processed is updated, including: When the real-time working time deviation of the dual interactive workbench exceeds a preset deviation threshold, a tiered control strategy is executed: If the deviation is a short-term, occasional deviation, the timing of the workstation swap will be postponed until the current process of the first workbench and the second workbench is completed simultaneously.
[0031] If the deviation is a long-term, cumulative deviation, then the remaining medium-thick plates to be processed are reordered, and the production sequence is updated.
[0032] Optionally, the method further includes: After completing the current batch of processing, the overall plate time prediction model for each plate thickness is updated based on the measured completion time data. Specifically, this includes: After completing the current batch of processing, the actual completed time data and the manual verification results of the boundary plates are sent back to the production database.
[0033] Based on the original data and the returned data in the production database, the regression coefficients of the whole-plate time prediction model corresponding to each plate thickness are iteratively updated.
[0034] Secondly, this application provides an intelligent scheduling device for a dual interactive platform of scribing and cutting on medium and heavy plates, used to implement the method described above. The device includes the following functional modules: The parameter acquisition module is used to acquire nesting feature parameters of multiple medium-thick plates to be processed; the nesting feature parameters include at least plate thickness, number of workpieces, total perimeter of cutting path and number of holes.
[0035] The time prediction module is used to match the corresponding whole plate time prediction model from multiple whole plate time prediction models constructed according to the plate thickness for any medium-thick plate to be processed, and input the nesting feature parameters into the matched whole plate time prediction model to obtain the whole plate predicted processing time of the medium-thick plate to be processed.
[0036] The production scheduling classification module is used to determine the single workpiece scribing time of the medium-thick plate to be processed based on the predicted processing time of the whole plate, and to determine the production scheduling category of the medium-thick plate to be processed based on the relationship between the single workpiece scribing time and the preset threshold range.
[0037] The sequence generation module is used to generate a production sequence for multiple medium-thick plates to be processed based on the difference in the scribing time of a single workpiece, given that the production scheduling category is qualified sheet material.
[0038] The dual interactive worktable includes a first worktable and a second worktable. The first worktable is equipped with a mechanical scribing actuator, and the second worktable is equipped with a laser cutting mechanism. The first worktable and the second worktable can be interchanged. The first worktable and the second worktable are configured such that while the first worktable performs mechanical scribing on a medium-thick plate, the second worktable performs laser cutting on another medium-thick plate.
[0039] The control module is used to control the dual interactive worktable to process according to the production sequence. During the processing of the dual interactive worktable, the module adjusts the timing of the exchange between the first worktable and the second worktable and / or updates the production sequence of the remaining medium-thick plates to be processed based on the deviation between the real-time working data of the dual interactive worktable and the predicted processing time of the whole plate.
[0040] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the intelligent scheduling method for the dual interactive platform of scribing and cutting of medium and heavy plates described above.
[0041] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intelligent scheduling method for the dual interactive platform of scribing and cutting of medium and heavy plates described above.
[0042] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides an intelligent scheduling method and related apparatus for a dual interactive platform for marking and cutting of medium-thick plates. The method first acquires nesting feature parameters of multiple medium-thick plates to be processed, including at least plate thickness, number of workpieces, total perimeter of the cutting path, and number of holes, providing a quantitative data foundation for subsequent prediction and scheduling. Then, for each medium-thick plate's nesting feature parameters, a corresponding prediction model is automatically matched based on the plate thickness to obtain the predicted processing time for the entire plate, thereby improving the adaptability of time prediction under different plate thickness conditions. Next, the marking time for a single workpiece is determined based on the predicted processing time for the entire plate, and the scheduling category is determined based on the relationship between the marking time for a single workpiece and a preset threshold range to automatically identify the cycle time matching status. For several plates that meet the standards, a production sequence is generated based on the differences in the marking time for a single workpiece. This balances the processing cycle time and reduces changeover and workstation waiting time. Finally, the dual interactive worktables are controlled to process according to the production sequence. The first worktable of the dual interactive worktable is equipped with a mechanical scribing actuator, and the second worktable is equipped with a laser cutting mechanism; the two can interchange positions. This allows the first worktable to mechanically scribble on one medium-thick plate while the second worktable performs laser cutting on another medium-thick plate, achieving synchronous parallel operation of scribing and cutting and improving equipment utilization. During processing, based on the deviation between the real-time operating data of the dual interactive worktables and the predicted processing time for the entire plate, the timing of the interchange between the first and second worktables is adjusted, and / or the production sequence of the remaining medium-thick plates to be processed is updated. This dynamically corrects on-site operating disturbances, ensuring the continuity and stability of production scheduling and processing. Attached Figure Description
[0043] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0044] Figure 1 The flowchart illustrates an intelligent scheduling method for a dual interactive platform of scribing and cutting on medium-thick plates, provided in one embodiment of this application.
[0045] Figure 2 This is a flowchart illustrating the construction of a whole-plate time prediction model for each plate thickness in an intelligent scheduling method for a dual interactive platform of scribing and cutting of medium-thick plates, provided in an embodiment of this application.
[0046] Figure 3 This is a schematic diagram illustrating the estimated single-workpiece scribing time distribution in an intelligent scheduling method for a dual interactive platform of scribing and cutting of medium-thick plates, provided in an embodiment of this application.
[0047] Figure 4This is a schematic diagram of the intelligent scheduling result in an intelligent scheduling method for a dual interactive platform of scribing and cutting of medium and thick plates, provided in an embodiment of this application.
[0048] Figure 5 This is a schematic diagram of a dual-interactive workbench integrating a double-layer bearing table in an intelligent scheduling method for a medium-thick plate scribing-cutting dual-interactive platform provided in an embodiment of this application.
[0049] Figure 6 This is a scatter plot of the prediction verification model of the whole plate time prediction model in an intelligent scheduling method for a dual interactive platform of scribing and cutting of medium and thick plates provided in an embodiment of this application.
[0050] Figure 7 This is a schematic diagram of the functional modules of an intelligent scheduling device for a medium-thick plate scribing-cutting dual interactive platform, provided in an embodiment of this application.
[0051] Figure 8 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation
[0052] 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, and 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.
[0053] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0054] This application provides an intelligent scheduling method for a dual interactive platform of scribing and cutting on medium-thick plates. In one exemplary embodiment, such as... Figure 1 As shown, the method includes the following steps: Step S100: Obtain the nesting feature parameters of multiple medium-thick plates to be processed.
[0055] Specifically, the system interfaces with the workshop MES (Manufacturing Execution System) to read the entire nesting drawing of a medium-thick plate, extracts the core feature parameters of multiple nesting plates in batches, and establishes parameter groups for multiple batches of plates to be processed. The nesting feature parameters include at least: the number of workpieces. Total perimeter of the cutting path Number of holes , plate thickness It can also include historical total working hours. Historical production data, etc.
[0056] In one specific implementation, the system reads basic board data through the MES data interface to construct a raw dataset containing physical processing parameters and historical production data. Preprocessing logic includes removing null values and missing invalid records from key fields such as the number of workpieces and board thickness, thus avoiding model solution anomalies caused by data misalignment.
[0057] In this embodiment, the system interfaces with the MES to read nesting drawings and feature parameters. In an optional extended implementation, data such as production scheduling results, actual working hours, and model update coefficients can also be transmitted back to the MES system in real time, enabling linkage with modules such as workshop production planning, material management, and equipment status monitoring. For example, when a sheet is determined to be substandard, the MES system can automatically trigger a layout optimization process or schedule it to a separate production line.
[0058] Step S200: For each medium-thick plate to be processed, automatically match the corresponding whole plate time prediction model according to its plate thickness to obtain the whole plate predicted processing time.
[0059] Among them, such as Figure 2 As shown, the construction process of the whole-plate time prediction model for different plate thicknesses is as follows: S210, Obtain historical production log data.
[0060] Real production logs of laser equipment in the workshop were collected as training samples. The sample dimensions include core effective features such as total processing time per sheet, number of workpieces per sheet, total processing edge length, and number of holes.
[0061] S220. Preprocess historical production log data.
[0062] Invalid records with null or missing values in key fields such as the number of workpieces and plate thickness are removed.
[0063] S230. Based on the preprocessed historical production log data, perform global regression to obtain a global regression model.
[0064] Select cutting length Number of holes As the independent variable, the measured total working hours As the dependent variable, a first-order multiple linear regression model is fitted using the least squares method, as shown in equation (1): In the formula, This represents the total measured working hours, in hours (h). This represents the constant term in the global regression model; Indicates cutting length The regression coefficients; Indicates the number of holes. The regression coefficients; This indicates the total perimeter of the cutting path, in millimeters (mm). This indicates the number of holes punched, expressed in individual holes.
[0065] S240. Based on the mean and standard deviation of the residuals of the global regression model, remove outlier samples.
[0066] Substituting historical samples into the model yields predicted working hours, and the residuals are calculated as shown in equation (2): In the formula, Indicates the first The residuals of each sample; Indicates the first The total measured working hours of each sample, in hours (h). Indicates the first The model predicts working hours for each sample, in hours (h).
[0067] Further calculate the mean of the residuals of all valid samples. Standard deviation .
[0068] If a sample satisfies the conditions shown in equation (3), it is determined to be an abnormal sample and marked for removal: In the formula, This represents the mean of the residuals of all valid samples; This represents the standard deviation of the residuals for all valid samples. This represents the anomaly detection factor, with a value ranging from 2.0 to 4.0, preferably 3.0.
[0069] S250. Split the historical production log data after removing abnormal samples into multiple subsets according to plate thickness.
[0070] A hierarchical independent modeling strategy is adopted to eliminate the interference of span features and extract all unique plate thickness sets in the filtered valid dataset. Based on plate thickness Split the dataset into The dataset consists of mutually exclusive subsets, each containing only a single thickness specification of sheet metal samples.
[0071] S260. Perform multiple linear regression on each subset of data to obtain the whole plate time prediction model for each plate thickness.
[0072] Regarding the first A thickness subset ( ), and independently construct a dedicated regression model, as shown in equation (4): In the formula, The time for the overall processing of the board material is expressed in hours (h). This represents the constant term in the thickness subset regression model; Represents the total perimeter of the cutting path The regression coefficients; Indicates the number of holes. The regression coefficients.
[0073] Using the effective samples within the subset, the coefficients are independently solved using the least squares method. , , .
[0074] In one specific implementation, the model training data is taken from the real production logs of laser processing equipment in industrial sites. A whole-board time prediction model is constructed using a multiple linear regression algorithm. The number of single-board workpieces, total processing edge length, and number of holes are used as input variables, and the total processing time of the board is used as the output variable. A quantitative mapping relationship between processing time and nesting parameters is established. The general formula is shown in equation (5): In the formula, This indicates the total processing time for the entire board, expressed in hours (h). Represents a constant term; This indicates the number of single-board components, expressed in pieces. This indicates the total processed side length, in millimeters (mm). This indicates the number of holes punched, expressed in individual holes. , , This represents 3 auxiliary features; Indicates the number of workpieces The regression coefficients; Indicates the total processing side length The regression coefficients; Indicates the number of holes. The regression coefficients; Indicate auxiliary features The regression coefficients; Indicate auxiliary features The regression coefficients; Indicate auxiliary features The regression coefficients.
[0075] The core coefficients of the model are calibrated by fitting and solving the data from on-site measurements. For example, the coefficients of the basic model (7 features) for an 8mm thick plate are: =1.1385, =0.338672, =0.132832, =0.088532, =0.055576, =-0.030197, =-0.092302; The coefficients of the complete model (7 features) with a plate thickness of 10mm are: =1.1305, =0.159445, =0.104279, =-0.003332, =0.027026, =0.012515, =-0.075698; The simplified model (5 features) coefficients for a 12mm thick plate are: =1.0655, =0.081330, =-0.028266, =0.045275, =0.117631.
[0076] The model features and parameter values obtained under different plate thicknesses exhibit significant differences, and the weight of each parameter on the scribing efficiency also varies considerably: the number of workpieces is the primary factor affecting processing time; the more workpieces, the higher the proportion of fixed time allocated. The number of holes is the second most important factor; increasing the number of holes directly lengthens the overall processing time of the plate. The total processing edge length has a relatively smaller impact on processing time. A complete 7-feature model is used for 8mm and 10mm plates, while a simplified 5-feature model is used for 12mm plates. This model reserves an iterative optimization mechanism; subsequent improvements can be made through refined modeling based on plate thickness, the introduction of nonlinear fitting algorithms, and the establishment of an online data iterative update mechanism to continuously improve the accuracy of time prediction and production scheduling adaptability under different working conditions.
[0077] For medium and heavy plates awaiting production scheduling According to its plate thickness Match the corresponding hierarchical regression model and calculate the total predicted working hours for the board material, as shown in Equation (6): In the formula, Indicates the first The total estimated man-hours for the production of Zhang's board materials are in hours (h). Indicates the first The constant term corresponding to each thickness subset; Indicates the first Regression coefficients of the total perimeter of the cutting path corresponding to each thickness subset; Indicates the first Regression coefficients for the number of holes corresponding to each thickness subset.
[0078] This embodiment uses a multiple linear regression model for work time prediction. In extended embodiments, other prediction models can also be used, such as support vector regression, random forest, gradient boosting tree, and neural networks. These models can be trained based on the same historical production log data and can be layered according to plate thickness or a unified model can be established. For work conditions with strong nonlinear relationships, using a nonlinear model may achieve higher prediction accuracy. When updating the model, the model parameters or structure can be updated synchronously.
[0079] Step S300: Determine the scribing time of a single workpiece based on the predicted processing time of the whole board, and determine the production scheduling category based on the scribing time of a single workpiece and the preset threshold range.
[0080] S310, Calculate the scribing time for a single workpiece.
[0081] Eliminate auxiliary time for fixing, clamping, and positioning the sheet metal. The conversion of the single workpiece scribing time, which can truly reflect the process efficiency, is shown in equation (7): In the formula, Indicates the first The scribing time for a single workpiece on a sheet metal plate, in seconds (s). Indicates the first The total estimated working hours for the sheet metal are in hours (h). This indicates the auxiliary time for fixing, clamping, and positioning the sheet metal, in hours (h). Indicates the first The total number of workpieces contained in a sheet of material, expressed in units of individual pieces.
[0082] S320. Determine the scribing time for the reference single workpiece.
[0083] Based on the hardware parameters of a single scribing machine: the standard scribing time for a single character at a constant speed in the workshop is 2~3 seconds / character, and the number of fixed marking characters on a single part of a medium-thick plate in the iron tower is 8~12. Taking the steady-state average of 10 characters as the benchmark, the benchmark scribing time for a single workpiece is shown in formula (8): In the formula, This indicates the scribing time for a single reference workpiece, in seconds (s). This indicates the number of characters used to identify a single workpiece, with a base value of 10. This represents the steady-state working time for a single character to be engraved, with a baseline value of 2.5 seconds per character.
[0084] Calculate the base working hours The processing time is calculated per second, taking into account factors such as edge and corner considerations, hole avoidance, equipment start-up and shutdown buffering, and positioning errors. A 28% process margin is reserved, and the final steady-state collaborative processing benchmark threshold is set at 30 seconds. An adaptive floating range of -20% to +30% (24s to 40s) is also set, allowing for adaptive fine-tuning based on different scribing equipment speeds, stroke rates, and material parameters of the sheet material.
[0085] S330. Make a judgment according to the three-level judgment and diversion rules.
[0086] High-confidence compliant components: This triggers an automatic production scheduling command; High-confidence substandard components: If the engraving cycle is too fast, it can easily cause imbalance between the two workstations, resulting in the separation and reorganization of the sheet material. Boundary area panels: It does not participate in automatic production scheduling. The system outputs a list for manual review. The review results confirmed by the process personnel are fed back into the dataset for subsequent model iterations.
[0087] in, This represents the lower limit of the adaptive floating range, with a value of 24 seconds. This represents the upper limit of the adaptive floating range, with a value of 40 seconds.
[0088] In one specific implementation, such as Figure 3 The diagram shows the distribution of estimated individual part marking times for each workpiece. The blue, red, and yellow dots correspond to sheet metal thicknesses of 8mm, 10mm, and 12mm, respectively. The green dashed lines indicate the lower limit (24s) and upper limit (40s) of the adaptive floating range. Points above the upper limit are considered compliant parts, points below the lower limit are considered non-compliant parts, and points between the upper and lower limits are considered boundary area parts.
[0089] In the above embodiments, a manual review list is output for the boundary area panels. In extended embodiments, an automatic review mechanism can be further introduced. For example, for boundary panels, a higher-precision prediction model or multi-model ensemble prediction can be used. If multiple models determine that the panel meets or fails to meet the standard, it is automatically categorized; if the determination results are inconsistent, a manual review is then output. The manual review results are fed back into the dataset and used to update the model and thresholds.
[0090] Step S400: For multiple medium-thick plates to be processed in the production scheduling category of qualified plates, a production sequence is generated based on the difference in the scribing time of a single workpiece.
[0091] Specifically, a two-level scheduling strategy is adopted to generate the final production sequence, balancing the processing cycle within each batch and reducing equipment waiting and idle time. First, for multiple medium-thick plates awaiting processing that meet the production standards, they are arranged in ascending or descending order of thickness, with the first plate selected as the first piece to be put into production. In subsequent steps, the single-workpiece scribing time is selected from the remaining plates. The board with the smallest difference from the previous board is selected as the next board to be processed, and this process is repeated until all boards in the group have been sorted. This algorithm achieves a more uniform processing pace, alleviates workstation congestion or standby issues caused by drastic fluctuations in working hours, and improves the overall utilization of the dual interactive workbench.
[0092] In one specific implementation, such as Figure 4 As shown, a schematic diagram of the intelligent production scheduling sequence is provided. The vertical axis represents the order in which the boards are put into production, and the horizontal axis represents the relative processing time for each board. Each blue rectangle represents the processing time for a single nested board. After optimization by the intelligent scheduling algorithm, the boards are put into production in an orderly manner according to the process load matching results, achieving a reasonable arrangement of boards with different processing loads. This effectively balances the production cycle of the scribing and cutting dual interactive workstations, reduces workstation waiting and idle time, and ensures the continuity of parallel cyclic production at both workstations.
[0093] Step S500: Control the dual interactive workbench to process according to the production sequence.
[0094] like Figure 5 As shown, the dual interactive worktable includes a left interactive worktable 1 and a right interactive worktable 2. The left interactive worktable 1 is equipped with a mechanical scribing actuator 4, which uses scribing technology to process the part number and specification characters on the entire medium-thick plate. The right interactive worktable 2 is equipped with a fiber laser cutting mechanism 5, which completes the contour edge finding, irregular shape cutting, and internal hole drilling of the medium-thick plate. The left and right interactive worktables 1 and 2 each have built-in upper and lower double-layer support surfaces, and are laterally moved along the transverse translation track 3 to interchange positions. The entire nested medium-thick plate 6 to be processed is placed on the interactive worktable, and after processing, it forms the finished workpiece 7.
[0095] By differentiating and fixing the division of labor, the marking and cutting processes can be carried out simultaneously and independently, providing a hardware execution basis for the balanced control of the intelligent production scheduling strategy.
[0096] According to the optimal production sequence, the hoisting, loading, and positioning of the boards to be processed are completed sequentially, and the two workstations carry out parallel operations synchronously according to the preset time sequence. The left interactive workstation performs sorting and unloading of finished products from the previous laser cutting and loading of new boards, as well as mechanical engraving of the entire board. The right interactive workstation simultaneously performs laser cutting on the boards that have already been engraved in the previous process.
[0097] In the above embodiments, the qualified boards are processed sequentially according to the production sequence. In an extended embodiment, a board buffer area can be set up near the dual interactive workbench to store boards that have been loaded but not yet started processing. When a workbench finishes ahead of schedule, the next board can be retrieved from the buffer area, reducing waiting time. The size of the buffer area and the scheduling strategy can be optimized according to the workshop space and production cycle.
[0098] Step S600: During the processing, acquire real-time working condition data of the dual interactive worktables, and adjust the switching timing and / or update the production sequence based on the deviation between the real-time working condition data and the predicted processing time of the whole board.
[0099] Specifically, it includes: (1) Real-time working condition data acquisition and deviation judgment: The processing progress, remaining processing time and equipment operating status of the dual-station are collected in real time through the equipment PLC system. The predicted working time of the hierarchical regression model is compared with the time, and the deviation of the processing time of the dual-station is calculated in real time to quantitatively identify the cycle mismatch problem caused by the disturbance of the working conditions on site.
[0100] (2) Two-level dynamic cycle time correction and control: When the real-time working time deviation of the two workstations is greater than the preset deviation threshold, the layered control strategy is executed: For short-term small deviations, the timing of workstation swapping is delayed, and the workstation swapping is executed after the current process of the two workstations is completed synchronously, so as to ensure the orderly flow of the process; For continuous accumulated processing deviations, the iterative optimization logic is restarted, the remaining unprocessed boards are reordered, the subsequent production sequence is updated, and the workstation processing deviation is compensated by the board cycle time adaptation to achieve dynamic correction of production rhythm.
[0101] In this tiered control strategy, short-term occasional deviations are "one-off small disturbances," while long-term cumulative deviations are "trend-based systematic deviations." For example: Short-term, occasional deviation: When processing a board at the left-side scribing station, an extra 6 seconds were spent due to corner avoidance, while the right-side cutting station had already completed and was waiting. When processing the next board, the left side returned to normal, and the two stations resynchronized. This deviation only affects the timing of one interchange and does not change subsequent production scheduling.
[0102] Long-term cumulative deviation: When multiple 10mm thick plates are awaiting processing, the overall plate processing time prediction model consistently predicts shorter times, causing each plate at the left-side scribing station to be 8-10 seconds slower than the right-side cutting station. The first plate had a wait of 8 seconds, the second a cumulative wait of 16 seconds, and the third a cumulative wait of 24 seconds, resulting in a continuous imbalance in the cycle time between the two stations. At this point, simply delaying and swapping the plates is no longer sufficient; it is necessary to reorder the remaining plates and even update the model coefficients corresponding to the 10mm plate thickness.
[0103] In terms of the judgment logic between the two, different sliding windows can be set to distinguish them. For example, if the deviation exceeds the limit in the last 1 to 2 periods but then falls back, it is judged as a short-term occasional occurrence; if the deviation exceeds the limit for more than 3 consecutive periods, or the moving average deviation is continuously greater than 5 seconds, or the cumulative deviation exceeds the set threshold (such as 15 seconds), it is judged as a long-term continuous cumulative deviation.
[0104] In this embodiment, the preset deviation threshold is set to 5 seconds. When the real-time time deviation exceeds 5 seconds, tiered control is implemented. In an extended embodiment, an emergency handling mechanism for abnormal working conditions can also be set. For example, when equipment malfunctions, the sheet metal clamping is abnormal, or the processing quality is unqualified, the system can automatically pause the current process, issue an alarm, mark the current sheet metal as abnormal, and reschedule subsequent sheet metal. Processing resumes after the fault is resolved.
[0105] In a further implementation, to further improve the robustness and adaptability of the whole-board time prediction model and the dual interactive workbench under complex disturbance conditions such as equipment status fluctuations, material batch differences, and temporary order insertions, the method can further include the following steps in addition to the real-time deviation control in step S600: Step S700: After completing the current batch processing, update the whole board processing time prediction model corresponding to each board thickness based on the measured completion time data.
[0106] Specifically, after a single batch of boards is processed, the actual measured completion time data and the manual verification results of the boundary boards are sent back to the production database. The coefficients of the layered regression model corresponding to each thickness specification are iteratively updated. In the actual production process, the optimization effect of the whole board time prediction model is judged based on the error value between the real-time prediction value of the model and the real-time working condition, and the updated regression coefficients are manually selected and adjusted to continuously reduce the whole board time prediction error and realize the production scheduling model adaptive optimization according to the production conditions.
[0107] After the two workstations are completed simultaneously, they automatically swap workstations laterally and switch processing steps. They continuously complete the entire process of feeding, scribing, cutting, and unloading of the board according to the dynamic optimal production sequence, forming a closed-loop intelligent cycle processing system that integrates time prediction, intelligent sorting, parallel processing, dynamic correction, and model iteration.
[0108] The system automatically generates multi-dimensional visualization charts based on the prediction results, including classification statistical histograms, thickness-single workpiece efficiency comparison charts, correlation curves between predicted and measured values, and error distribution histograms to support process engineers' decision-making. At the same time, the predicted working time, single workpiece scribing time, judgment results, and prediction error percentage are exported as Excel and TXT structured reports to achieve full-process data traceability in production scheduling.
[0109] In one specific embodiment, 73 pieces of 8mm, 10mm, and 12mm thick steel tower-specific medium-thick plates from the workshop were selected as test objects. Multiple sets of actual production condition samples with different nesting characteristics were collected, covering typical production scenarios such as the number of differentiated single-plate workpieces, total cutting edge length, and number of holes. Based on the aforementioned plate thickness-based multiple linear regression whole-plate time prediction model, the processing time of the sample plates was predicted, and the average scratching time per workpiece was calculated. Automatic plate classification was completed based on an adaptive floating threshold of 24s to 40s. The complete processing condition of a single sample corresponding to a single raw material whole-plate was analyzed, and the relative error between the model-predicted time and the actual measured time was statistically analyzed.
[0110] like Figure 6 As shown, a scatter plot of model error prediction verification is provided. The horizontal axis represents the actual processing time of the sheet metal, and the vertical axis represents the predicted processing time of the entire sheet metal by the model. The red dashed line is the ideal fitting line y=x. The statistical results of the model's error by sheet thickness are as follows: 8mm sheet metal, average error 6.94% (±8.12%); 10mm sheet metal, average error 13.87% (±8.83%); 12mm sheet metal, average error 8.61% (±4.04%); overall sample average error 10.04%. This accuracy can meet the basic production scheduling requirements of industry. With the continuous accumulation of subsequent production samples and the continuous expansion of the dataset, the model can iteratively optimize features and fitting coefficients, and the prediction error level will be further reduced.
[0111] The above embodiments use 8mm, 10mm, and 12mm medium-thick plates as examples, but this application is not limited to these. For other plate thicknesses, such as 6mm, 14mm, 16mm, 20mm, and 25mm, historical production logs can be collected using the same method, and corresponding multiple linear regression whole-plate time prediction models can be constructed according to plate thickness, with model coefficients calibrated. For plates with thicknesses exceeding the existing sample range, interpolation or extrapolation methods can be used for preliminary estimation, and the model can be iteratively updated using measured data during subsequent production processes.
[0112] The complete intelligent nesting and recycling process in this embodiment is as follows: Pre-production scheduling stage: The system connects with MES to read all the drawings of the whole sheet of material to be processed, calls the whole sheet time prediction model to automatically calculate the scribing time of a single workpiece, and distinguishes between qualified and non-qualified sheets in batches. The qualified boards are hoisted onto the double-layer support platform of the left-side interactive workbench in a balanced nesting production sequence. The left and right interactive worktables work in parallel: the left side completes the sorting of the previous batch of finished boards, the loading of new boards and mechanical marking, while the right side simultaneously performs laser cutting of the boards that have been marked in the previous step; After all processing at both workstations is completed, the workstations are horizontally interchanged, the processing functions are automatically switched, and the next closed-loop cycle begins. Substandard boards will undergo layout optimization or be processed separately and will not be included in the parallel production line with dual interactive workbenches.
[0113] The above embodiments are illustrated using a mechanical scribing actuator as an example, but this application is not limited thereto. For equipment employing other scribing methods such as laser scribing, plasma scribing, and pneumatic scribing, the steady-state working time for single-character scribing can be adjusted according to the actual operating parameters of the equipment. and the number of characters for single workpiece identification Re-verify the scribing time for the reference single workpiece. The baseline threshold for co-processing with steady-state conditions is adjusted, and the upper and lower limits of the adaptive floating range are adjusted accordingly. For example, when the laser scribing speed is high, the lower threshold can be appropriately lowered; when the scribing accuracy requirement is high, the upper threshold can be appropriately increased.
[0114] The above embodiments are illustrated using a dual-interactive worktable as an example, but this application is not limited thereto. For machining systems configured with three or more interactive worktables, the scribing and cutting processes can be further subdivided, or auxiliary processes (such as marking, inspection, cleaning, etc.) can be added. The same principles can be used to assign process tasks to each worktable, generate production sequences, and dynamically adjust the cycle time. The worktables can be interchanged via lateral translation tracks or rotation mechanisms.
[0115] Based on the same inventive concept, this application also provides an apparatus for implementing the intelligent scheduling method for a dual interactive platform of scribing and cutting of medium-thick plates as described above. The solution provided by this apparatus is similar to the solution described in the above method. In an exemplary embodiment, such as... Figure 7 As shown, a smart scheduling device for a dual-interactive platform of scribing and cutting on medium-thick plates is provided. This device includes: a parameter acquisition module, a time prediction module, a scheduling classification module, a sequence generation module, a dual-interactive workbench, a control module, and a model update module. This device is used to implement the steps in the above method embodiments, and its specific limitations can be found in the description of the method embodiments above, which will not be repeated here.
[0116] In one specific implementation, the time prediction module includes: The data preprocessing unit is used to acquire historical production log data, preprocess the historical production log data, and remove records with null values or missing key fields.
[0117] The global regression unit is used to perform global regression based on preprocessed historical production log data, with the total perimeter of the cutting path and the number of holes as independent variables and the total measured working hours as the dependent variable, to obtain a global regression model.
[0118] The anomaly removal unit is used to remove outlier samples from preprocessed historical production log data based on the mean and standard deviation of the residuals from the global regression model.
[0119] The hierarchical modeling unit is used to split the historical production log data after removing abnormal samples into multiple subsets according to the plate thickness, and perform multiple linear regression on each subset to obtain the whole plate working time prediction model corresponding to each plate thickness.
[0120] The production scheduling and classification module is specifically used for: The net processing time is determined based on the predicted processing time of the whole board and the preset clamping auxiliary time.
[0121] Divide the net processing time by the number of workpieces in the medium-thick plate to be processed, and convert it to seconds to obtain the scribing time for a single workpiece.
[0122] When the scribing time of a single workpiece is greater than or equal to the upper limit threshold, it is determined to be a qualified sheet material.
[0123] When the scribing time of a single workpiece is less than or equal to the lower threshold, it is determined to be a substandard material.
[0124] When the scribing time of a single workpiece is greater than the lower threshold but less than the upper threshold, it is identified as a boundary plate and manual verification information is output.
[0125] certainly, Figure 7 The architecture shown is merely exemplary; it can be omitted as needed when implementing different functionalities. Figure 7 One or at least two components of the system shown.
[0126] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 8As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores intelligent nesting and cyclic scheduling data for the dual interactive worktable for medium-thick plates (scribing and cutting). The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it can implement the intelligent scheduling method for the dual interactive platform for medium-thick plates (scribing and cutting) provided in the previous embodiment.
[0127] Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0128] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0129] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0130] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations and be authorized by the owner of the corresponding device.
[0132] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0133] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0134] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0135] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A smart scheduling method for a dual interactive platform of scribing and cutting on medium-thick plates, characterized in that, include: Obtain nesting characteristic parameters for multiple medium-thick plates to be processed; The nesting characteristic parameters include at least plate thickness, number of workpieces, total perimeter of the cutting path, and number of holes. For any medium-thick plate to be processed, the corresponding whole plate time prediction model is automatically matched according to the plate thickness of the medium-thick plate to be processed, and the nesting characteristic parameters are input into the matched whole plate time prediction model to obtain the whole plate predicted processing time of the medium-thick plate to be processed. The scribing time of a single workpiece in the medium-thick plate to be processed is determined based on the overall plate predicted processing time, and the production scheduling category of the medium-thick plate to be processed is determined based on the scribing time of a single workpiece and a preset threshold range. For multiple medium-thick plates to be processed in the production scheduling category of qualified plates, a production sequence is generated based on the difference in the scribing time of a single workpiece. The dual interactive worktable is controlled to process according to the production sequence; the dual interactive worktable includes a first worktable and a second worktable, the first worktable is equipped with a mechanical scribing execution mechanism, the second worktable is equipped with a laser cutting mechanism, the first worktable and the second worktable can interchange positions, and the first worktable and the second worktable are configured such that: while the first worktable performs mechanical scribing on a medium-thick plate, the second worktable performs laser cutting on another medium-thick plate; During the processing of the dual interactive worktable, the timing of the exchange between the first worktable and the second worktable is adjusted based on the deviation between the real-time working data of the dual interactive worktable and the predicted processing time of the whole plate, and / or the production sequence of the remaining medium and thick plates to be processed is updated.
2. The intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates according to claim 1, characterized in that, The whole-plate time prediction model for different plate thicknesses is constructed in the following way: Retrieve historical production log data; The historical production log data is preprocessed to remove records with null or missing key fields, resulting in preprocessed historical production log data. Based on the preprocessed historical production log data, a global regression model was obtained by using the total perimeter of the cutting path and the number of holes as independent variables and the total measured working hours as the dependent variable. Based on the mean and standard deviation of the residuals of the global regression model, outlier samples are removed from the preprocessed historical production log data. The historical production log data after removing abnormal samples is split into multiple subsets based on plate thickness; Multiple linear regression was performed on each subset of data to obtain the whole plate time prediction model for each plate thickness.
3. The intelligent scheduling method for medium-thick plate scribing-cutting dual interactive platform according to claim 2, characterized in that, Based on the residual mean and residual standard deviation of the global regression model, outlier samples are removed from the preprocessed historical production log data, including: Calculate the residual for each sample in the preprocessed historical production log data; Calculate the mean and standard deviation of the residuals for all valid samples; When the absolute value of the deviation of the residual of any sample from the mean of the residuals is greater than the product of the anomaly determination factor and the standard deviation of the residuals, the sample is determined to be an anomaly.
4. The intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates according to claim 1, characterized in that, The preset threshold range includes a lower threshold and an upper threshold; The single-workpiece scribing time of the medium-thick plate to be processed is determined based on the overall plate predicted processing time, including: The net processing time is determined based on the predicted processing time of the entire plate and the preset clamping auxiliary time. Divide the net processing time by the number of medium-thick plates to be processed to obtain the scribing time for a single workpiece; Based on the single workpiece scribing time and a preset threshold range, the production scheduling category of the medium-thick plate to be processed is determined, including: When the scribing time of a single workpiece is greater than or equal to the upper limit threshold, it is determined to be a qualified sheet material; When the scribing time of a single workpiece is less than or equal to the lower threshold, it is determined to be a substandard material. When the scribing time of a single workpiece is greater than the lower threshold and less than the upper threshold, it is determined to be a boundary plate and manual review information is output.
5. The intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates according to claim 1, characterized in that, A production sequence is generated based on the differences in scribing time for individual workpieces, including: For multiple medium-thick plates of any thickness to be processed, arrange them in descending order of thickness. Select the first medium-thick plate from the sorted medium-thick plates to be processed as the first plate to be put into production. Among the multiple medium-thick plates to be processed, the medium-thick plate with the smallest difference between the single workpiece scribing time and the single workpiece scribing time of the previous production plate is selected as the next production plate, until all medium-thick plates to be processed are scheduled for production.
6. The intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates according to claim 1, characterized in that, The dual interactive workbench also includes a transverse translation track. The first workbench and the second workbench each have built-in upper and lower double-layer support surfaces, and can be transversely translated as a whole along the transverse translation track to exchange positions. Based on the deviation between the real-time operating data of the dual interactive worktables and the predicted processing time of the entire plate, the timing of the interchange between the first and second worktables is adjusted, and / or the production sequence of the remaining medium-thick plates to be processed is updated, including: When the real-time working time deviation of the dual interactive workbench exceeds a preset deviation threshold, a tiered control strategy is executed: If the deviation is a short-term, occasional deviation, the timing of the workstation interchange will be postponed until the current process of the first workbench and the second workbench is completed simultaneously. If the deviation is a long-term, cumulative deviation, then the remaining medium-thick plates to be processed are reordered, and the production sequence is updated.
7. The intelligent scheduling method for a dual interactive platform of scribing and cutting in medium-thick plates according to claim 1, characterized in that, Also includes: After completing the current batch of processing, the overall plate time prediction model for each plate thickness is updated based on the measured completion time data. Specifically, this includes: After completing the current batch of processing, the actual completed working hours data and the manual verification results of the boundary plates are sent back to the production database. Based on the original data and the returned data in the production database, the regression coefficients of the whole-plate time prediction model corresponding to each plate thickness are iteratively updated.
8. A smart scheduling device for a dual interactive platform of scribing and cutting on medium-thick plates, characterized in that, The apparatus for implementing the method as described in any one of claims 1-7 comprises: The parameter acquisition module is used to acquire nesting feature parameters of multiple medium-thick plates to be processed; the nesting feature parameters include at least plate thickness, number of workpieces, total perimeter of cutting path and number of holes. The time prediction module is used to automatically match the corresponding whole plate time prediction model according to the thickness of any medium-thick plate to be processed, and input the nesting feature parameters into the matched whole plate time prediction model to obtain the whole plate predicted processing time of the medium-thick plate to be processed. The production scheduling classification module is used to determine the scribing time of a single workpiece in the medium-thick plate to be processed based on the predicted processing time of the whole plate, and to determine the production scheduling category of the medium-thick plate to be processed based on the scribing time of the single workpiece and a preset threshold range. The sequence generation module is used to generate a production sequence for multiple medium-thick plates to be processed based on the difference in the scribing time of a single workpiece for multiple plates whose production category is qualified plate material. The dual interactive worktable includes a first worktable and a second worktable. The first worktable is equipped with a mechanical scribing actuator, and the second worktable is equipped with a laser cutting mechanism. The first worktable and the second worktable can be interchanged. The first worktable and the second worktable are configured such that while the first worktable performs mechanical scribing on a medium-thick plate, the second worktable performs laser cutting on another medium-thick plate. The control module is used to control the dual interactive worktable to process according to the production sequence. During the processing of the dual interactive worktable, the module adjusts the timing of the exchange between the first worktable and the second worktable and / or updates the production sequence of the remaining medium-thick plates to be processed based on the deviation between the real-time working data of the dual interactive worktable and the predicted processing time of the whole plate.
9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the intelligent scheduling method for a dual interactive platform for scribing and cutting of medium-thick plates as described in any one of claims 1-7.
10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the intelligent scheduling method for the dual interactive platform of scribing and cutting of medium-thick plates as described in any one of claims 1-7.
