Cutter predictability control method and system applied to automatic cutting bed and electronic equipment
Through dynamic model and long-term memory network, the cutting control scheme of the automatic cutting bed is optimized, which solves the problem of decreasing the cutting accuracy caused by the influencing factors of the cutting posture, and avoids experimental cutting time and rework , improves cutting efficiency.
Patent Information
- Application Number
- CN202410987270.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
During the automatic cutting process, the actual posture of the cutting tool is affected by a variety of factors, resulting in a decrease in the cutting accuracy. The existing control methods require experimental cutting to optimize the cutting tool posture, which takes up time and may lead to rework or cutting of the cutting.
The dynamic model and long-term memory network algorithm are used to construct a cutting tool attitude change trend prediction model to predict the cutting tool's attitude change trend in the cutting task, and optimize the cutting tool control scheme based on the prediction results to avoid experimental cutting.
Directly predict the cutting posture change trend based on the model, optimize the cutting control plan, improve the cutting accuracy, reduce rework and time occupation, and improve the cutting operation progress.
Smart Images

Figure CN118940435A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of cutting blade control of a cutting table, and more specifically, relates to a cutting blade predictive control method, system and electronic equipment applied to an automatic cutting table. Background Art
[0002] The automatic cutting machine is an automated device that controls the cutting knife to cut the fabric and obtain the cut pieces. Specifically, in the process of cutting, the automatic cutting machine controls the cutting knife in the time dimension according to the predetermined cutting knife control scheme, so that the cutting knife cuts the fabric according to the predetermined cutting path and cutting direction, thereby obtaining the cut pieces for subsequent garment production.
[0003] However, in the actual cutting process, the actual posture of the cutter will be affected by many factors, such as the cutting speed of the cutter, the wear of the cutter edge, and the thickness distribution, hardness and toughness of the fabric. Under the influence of these factors, the actual posture of the cutter may differ from the expected posture of the cutter. When the difference between the actual posture of the cutter and the expected posture reaches a certain level, it will affect the accuracy of the cut pieces, resulting in a decrease in the yield of the cut pieces, or even waste due to excessive errors.
[0004] Based on the above, it can be seen that it is very necessary to control the deviation of the cutting knife posture during the cutting task. The existing methods of controlling the deviation of the cutting knife posture during the cutting process are mainly:
[0005] Before formally executing the cutting task, the current cutter control scheme is used to experimentally cut a bed of cloth, the contours of the cut pieces are extracted, and the extracted cut piece contours are compared with the benchmark cut piece contours to determine the accuracy of the cut pieces. If the cut piece accuracy meets the requirements, it means that the current cutter control scheme can be used for formal cutting operations. If the cut piece accuracy does not meet the requirements, the current cutter control scheme is optimized based on the difference between the extracted cut piece contour and the benchmark cut piece contour, so that the contours of the cut pieces obtained by subsequent cutting are close to the benchmark cut piece contour, that is, the optimized cutter control scheme is used to compensate for the deviation of the cutter posture caused by factors affecting the cutter posture.
[0006] However, although the above-mentioned method of controlling the deviation of the cutter posture during the cutting process can reduce the influence of the factors affecting the cutter posture on the actual cutter posture to a certain extent, so as to improve the cutting accuracy, it requires experimental cutting of a bed of cloth. If the accuracy of the cut pieces obtained by the experimental cutting does not meet the requirements, the cut pieces will need to be reworked or the cut pieces will be discarded because they cannot be repaired. In addition, the experimental cutting will take a certain amount of time, which will inevitably affect the overall progress of the cloth cutting operation. Summary of the invention
[0007] In view of this, the present invention provides a cutter predictive control method, system and electronic equipment applied to an automatic cutting table.
[0008] According to a first aspect of the present invention, there is provided a method for predictive control of a cutting blade applied to an automatic cutting machine, the method comprising the following steps:
[0009] According to the first data set and based on the dynamics model, an algorithm is constructed to obtain a first cutting knife posture change trend prediction model;
[0010] According to the second data set and based on the long short-term memory network algorithm, a second cutting knife posture change trend prediction model is obtained;
[0011] Before executing the cutting task, the first cutting knife posture change trend prediction model is used to predict the first posture change trend of the cutting knife during the cutting task execution process; if the first posture change trend is inconsistent with the expected posture change trend of the cutting knife, the second cutting knife posture change trend prediction model is used to predict the second posture change trend of the cutting knife during the cutting task execution process; and based on the deviation between the second posture change trend and the expected posture change trend, the predetermined cutting knife control scheme is optimized;
[0012] In the process of executing the cutting task, the cutting knife is controlled by adopting an optimized cutting knife control scheme.
[0013] Optionally, the first data set includes cutting knife posture characterization data and cutting knife posture influence data;
[0014] The cutting knife posture characterization data includes the cutting knife position and the cutting knife angle;
[0015] The cutter posture influencing data include the cutter cutting speed, the quantitative value of the cutter edge wear, the temperature and humidity of the working environment, the dynamic load fluctuation of the cutter, and the hardness, thickness distribution and toughness of the cut material.
[0016] Optionally, the method for determining whether the first posture change trend is consistent with the expected posture change trend includes:
[0017] Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing the first posture change trend;
[0018] Uniformly selecting a plurality of discrete reference trend points on an expected trend line representing the expected posture change trend;
[0019] If the number of inconsistent trend points among the plurality of trend points to be determined reaches a set value, it is determined that the first posture change trend is inconsistent with the expected posture change trend,
[0020] The inconsistent trend point is a trend point to be determined that is inconsistent with the cutting knife position represented by the corresponding reference trend point or inconsistent with the cutting knife angle represented by the corresponding reference trend point.
[0021] Optionally, the second data set includes a plurality of data combinations with timestamps;
[0022] The data combination includes the cutting knife posture characterization data and the cutting knife posture influence data.
[0023] Optionally, the optimizing the predetermined cutting knife control scheme based on the deviation between the second posture change trend and the expected posture change trend includes:
[0024] Splitting a second trend line representing the change trend of the second posture into a cutting knife position change trend line and a cutting knife angle change trend line;
[0025] Splitting the expected trend line representing the expected posture change trend into an expected cutting knife position change trend line and an expected cutting knife angle change trend line;
[0026] Acquire a set of cutter position adjustment vectors for making the cutter position variation trend line approach the expected cutter position variation trend line;
[0027] Acquire a set of cutting angle adjustment vectors for making the cutting angle variation trend line approach the expected cutting angle variation trend line;
[0028] Optimizing the cutter position control vector set in the cutter control scheme according to the cutter position adjustment vector set;
[0029] The cutting knife angle control vector set in the cutting knife control scheme is optimized according to the cutting knife angle adjustment vector set.
[0030] Optionally, the number of trend points to be determined is positively correlated with the cutting accuracy required for the cut material.
[0031] According to a second aspect of the present invention, there is provided a predictive control system for a cutting knife applied to an automatic cutting machine, the system comprising the following functional modules:
[0032] A first prediction model acquisition module, used to construct an algorithm based on the first data set and the dynamics model to acquire a first cutting knife posture change trend prediction model;
[0033] A second prediction model acquisition module, used for acquiring a second cutting knife posture change trend prediction model according to the second data set and based on a long short-term memory network algorithm;
[0034] a cutter control scheme optimization module, used for, before executing a cutting task, using the first cutter posture change trend prediction model to predict a first posture change trend of the cutter during the execution of the cutting task; if the first posture change trend is inconsistent with an expected posture change trend of the cutter, using the second cutter posture change trend prediction model to predict a second posture change trend of the cutter during the execution of the cutting task; and optimizing a predetermined cutter control scheme based on a deviation between the second posture change trend and the expected posture change trend;
[0035] The cutting knife optimization control module is used to control the cutting knife by adopting an optimized cutting knife control scheme during the execution of the cutting task.
[0036] Preferably, the method for determining whether the first posture change trend is consistent with the expected posture change trend includes:
[0037] Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing the first posture change trend;
[0038] Uniformly selecting a plurality of discrete reference trend points on an expected trend line representing the expected posture change trend;
[0039] If the number of inconsistent trend points among the plurality of trend points to be determined reaches a set value, it is determined that the first posture change trend is inconsistent with the expected posture change trend,
[0040] The inconsistent trend point is a trend point to be determined that is inconsistent with the cutting knife position represented by the corresponding reference trend point or inconsistent with the cutting knife angle represented by the corresponding reference trend point.
[0041] Preferably, the step of optimizing the predetermined cutting knife control scheme based on the deviation between the second posture change trend and the expected posture change trend comprises:
[0042] Splitting a second trend line representing the change trend of the second posture into a cutting knife position change trend line and a cutting knife angle change trend line;
[0043] Splitting the expected trend line representing the expected posture change trend into an expected cutting knife position change trend line and an expected cutting knife angle change trend line;
[0044] Acquire a set of cutter position adjustment vectors for making the cutter position variation trend line approach the expected cutter position variation trend line;
[0045] Acquire a set of cutting angle adjustment vectors for making the cutting angle variation trend line approach the expected cutting angle variation trend line;
[0046] Optimizing the cutter position control vector set in the cutter control scheme according to the cutter position adjustment vector set;
[0047] The cutting knife angle control vector set in the cutting knife control scheme is optimized according to the cutting knife angle adjustment vector set.
[0048] According to a third aspect of the present invention, there is provided an electronic device comprising a processor and a memory, wherein the processor implements any one of the above-mentioned predictive control methods for cutting blades applied to an automatic cutting table when executing a computer program stored in the memory.
[0049] The beneficial effects of the present invention are:
[0050] The present invention applies to the predictive control method of the cutter of an automatic cutting bed. Before executing the cutting task, a first cutter posture change trend prediction model is used to predict the first posture change trend of the cutter during the execution of the cutting task. If the first posture change trend is inconsistent with the expected posture change trend of the cutter, a second cutter posture change trend prediction model is used to predict the second posture change trend of the cutter during the execution of the cutting task. Based on the deviation between the second posture change trend and the expected posture change trend, a predetermined cutter control scheme is optimized. Then, during the execution of the cutting task, the optimized cutter control scheme is used to control the cutter.
[0051] Compared with the existing method of controlling the deviation of the cutter posture in the cutting process, which is to first experimentally cut a bed of cloth, and then determine the deviation of the cutter contour relative to the reference cutter contour based on the cut pieces obtained by the experimental cutting, the cutter predictive control method applied to the automatic cutting table of the present invention does not involve the link of experimental cutting, but directly predicts the trend of the cutter posture change based on the model, and optimizes the current cutter control scheme when the cutter posture change trend is inconsistent with the expected posture change trend. It can be seen that since it does not involve the link of experimental cutting, in the process of implementing the cutter predictive control method applied to the automatic cutting table of the present invention, it does not involve the problem that the existing method of controlling the deviation of the cutter posture in the cutting process may cause the need to rework the cut pieces obtained by experimental cutting and affect the overall progress of the cloth cutting operation.
[0052] The predictive cutter control system and electronic device applied to an automatic cutting table of the present invention belong to a general inventive concept with the above-mentioned predictive cutter control method applied to an automatic cutting table, and have at least the same beneficial effects as the above-mentioned predictive cutter control method applied to an automatic cutting table, and its beneficial effects will not be repeated here.
[0053] Other features and advantages of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] The present invention may be better understood by referring to the following description taken in conjunction with the accompanying drawings, in which the same or similar reference numerals are used throughout the drawings to represent the same or similar components.
[0055] Figure 1 A flowchart of a method for predictive control of a cutting blade applied to an automatic cutting table according to an embodiment of the present invention is shown;
[0056] Figure 2 A structural block diagram of a predictive control system for cutting blades applied to an automatic cutting machine according to an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0057] In order to enable those skilled in the art to more fully understand the technical solution of the present invention, the exemplary embodiments of the present invention will be described in more comprehensive and detailed in conjunction with the accompanying drawings below. Obviously, the one or more embodiments of the present invention described below are only one or more of the specific ways in which the technical solution of the present invention can be implemented, and are not exhaustive. It should be understood that other ways belonging to a general inventive concept can be used to implement the technical solution of the present invention, and should not be limited by the exemplary embodiments described. Based on one or more embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.
[0058] Example: Figure 1 The flowchart of the implementation of the predictive control method of the cutting blade applied to the automatic cutting machine according to the embodiment of the present invention is shown. Figure 1 The predictive control method for cutting blades applied to an automatic cutting machine according to an embodiment of the present invention comprises the following steps:
[0059] Step S100, constructing an algorithm based on the first data set and the dynamics model to obtain a first cutting knife posture change trend prediction model;
[0060] Step S200, obtaining a second cutting knife posture change trend prediction model according to the second data set and based on a long short-term memory network algorithm;
[0061] Step S300: before executing the cutting task, using a first cutting knife posture change trend prediction model to predict a first posture change trend of the cutting knife during the cutting task execution process; if the first posture change trend is inconsistent with an expected posture change trend of the cutting knife, using a second cutting knife posture change trend prediction model to predict a second posture change trend of the cutting knife during the cutting task execution process; and optimizing a predetermined cutting knife control scheme based on a deviation between the second posture change trend and the expected posture change trend;
[0062] Step S400: During the execution of the cutting task, the cutting knife is controlled by using an optimized cutting knife control scheme.
[0063] Specifically, in the embodiment of the present invention, when facing the task of predicting the trend of the cutting knife posture change, the dynamic model construction algorithm is difficult to accurately capture all dynamic changes due to model simplification and assumption restrictions, and its prediction accuracy is lower than that of the neural network algorithm, that is, the prediction accuracy of the first cutting knife posture change trend prediction model is lower than that of the second cutting knife posture change trend prediction model. Since the deviation of the cutting knife that is sufficient to affect the accuracy of the cutting piece during the cutting process is a low-probability event, in order to reduce the overall time cost of the prediction of the cutting knife posture change trend, the embodiment of the present invention adopts the first cutting knife posture change trend prediction model with a relatively fast prediction speed to predict the cutting knife posture change trend, and then realizes the qualitative judgment of whether the cutting knife posture change trend is consistent with the expected posture change trend; if it is judged that the cutting knife posture change trend is inconsistent with the expected posture change trend, then the cutting knife posture change trend is predicted more accurately based on the second cutting knife posture change trend prediction model, and then the cutting knife control scheme is optimized.
[0064] Further, in step S100 of the embodiment of the present invention, the first data set includes cutting knife posture characterization data and cutting knife posture influence data;
[0065] The cutting knife posture characterization data includes the cutting knife position and the cutting knife angle;
[0066] The data affecting the cutter posture include the cutting speed of the cutter, the quantitative value of the cutter edge wear, the temperature and humidity of the working environment, the dynamic load fluctuation of the cutter, and the hardness, thickness distribution and toughness of the cutter material.
[0067] Furthermore, in step S300 of the embodiment of the present invention, the method for determining whether the first posture change trend is consistent with the expected posture change trend includes:
[0068] Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing a first posture change trend;
[0069] Uniformly selecting multiple discrete reference trend points on an expected trend line representing an expected posture change trend;
[0070] If the number of inconsistent trend points among the plurality of trend points to be determined reaches a set value, it is determined that the first posture change trend is inconsistent with the expected posture change trend.
[0071] The inconsistent trend point is a trend point to be determined that is inconsistent with the cutting knife position represented by the corresponding reference trend point or is inconsistent with the cutting knife angle represented by the corresponding reference trend point.
[0072] Specifically, in an embodiment of the present invention, an optimized method for determining whether a first posture change trend is consistent with an expected posture change trend includes:
[0073] Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing a first posture change trend, and uniformly selecting a plurality of discrete reference trend points on an expected trend line representing an expected posture change trend;
[0074] Determine whether the number of inconsistent trend points among multiple trend points to be judged reaches a set value. If not, continue to determine whether each inconsistent trend point among the multiple trend points to be judged contains N consecutive trend points to be judged. If so, determine that the first posture change trend is inconsistent with the expected posture change trend.
[0075] Furthermore, in step S200 of the embodiment of the present invention, the second data set includes a plurality of data combinations with time stamps, and the data combinations include cutting knife posture representation data and cutting knife posture influence data.
[0076] Furthermore, in step S300 of the embodiment of the present invention, optimizing the predetermined cutting knife control scheme based on the deviation between the second posture change trend and the expected posture change trend includes:
[0077] Splitting the second trend line representing the change trend of the second posture into a cutting knife position change trend line and a cutting knife angle change trend line;
[0078] Splitting the expected trend line representing the expected posture change trend into an expected cutting knife position change trend line and an expected cutting knife angle change trend line;
[0079] Obtain a set of cutter position adjustment vectors for making the cutter position variation trend line approach the expected cutter position variation trend line;
[0080] Obtain a set of cutter angle adjustment vectors for making the cutter angle variation trend line approach the expected cutter angle variation trend line;
[0081] Optimizing the cutter position control vector set in the cutter control scheme according to the cutter position adjustment vector set;
[0082] The cutter angle control vector set in the cutter control scheme is optimized according to the cutter angle adjustment vector set.
[0083] Furthermore, in an embodiment of the present invention, in the process of judging whether the first posture change trend is consistent with the expected posture change trend, the number of trend points to be judged selected on the first trend line representing the first posture change trend is positively correlated with the cutting accuracy required by the cut material, that is, the higher the cutting accuracy required by the cut material, the more trend points to be judged are selected.
[0084] Accordingly, based on the predictive control method for a cutting knife applied to an automatic cutting table in an embodiment of the present invention, the embodiment of the present invention further proposes a predictive control system for a cutting knife applied to an automatic cutting table.
[0085] Figure 2 The structure block diagram of the predictive control system for cutting blades applied to automatic cutting machines according to an embodiment of the present invention is shown. Figure 2 The predictive control system for cutting blades applied to automatic cutting machines according to an embodiment of the present invention includes the following functional modules:
[0086] A first prediction model acquisition module, used to construct an algorithm based on the first data set and the dynamics model to acquire a first cutting knife posture change trend prediction model;
[0087] A second prediction model acquisition module, used for acquiring a second cutting knife posture change trend prediction model according to the second data set and based on a long short-term memory network algorithm;
[0088] A cutter control scheme optimization module is used to, before executing a cutting task, use a first cutter posture change trend prediction model to predict a first posture change trend of the cutter during the cutting task execution process; if the first posture change trend is inconsistent with an expected posture change trend of the cutter, use a second cutter posture change trend prediction model to predict a second posture change trend of the cutter during the cutting task execution process; and optimize a predetermined cutter control scheme based on a deviation between the second posture change trend and the expected posture change trend;
[0089] The cutter optimization control module is used to control the cutter using an optimized cutter control scheme during the execution of the cutting task.
[0090] Accordingly, based on the predictive control method for cutting blades applied to an automatic cutting table in an embodiment of the present invention, an embodiment of the present invention further proposes an electronic device, which includes a processor and a memory. When the processor executes a computer program stored in the memory, the predictive control method for cutting blades applied to an automatic cutting table in an embodiment of the present invention is implemented.
[0091] Although one or more embodiments of the present invention are described above, it should be known to those skilled in the art that the present invention can be implemented in any other form without departing from its subject matter and scope. Therefore, the embodiments described above are illustrative rather than restrictive, and many modifications and substitutions are obvious to those skilled in the art without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims
1. A predictive control method for cutting blades applied to an automatic cutting machine, characterized in that: include: According to the first data set and based on the dynamics model, an algorithm is constructed to obtain a first cutting knife posture change trend prediction model; According to the second data set and based on the long short-term memory network algorithm, a second cutting knife posture change trend prediction model is obtained; Before executing the cutting task, the first cutting knife posture change trend prediction model is used to predict the first posture change trend of the cutting knife during the cutting task execution process; if the first posture change trend is inconsistent with the expected posture change trend of the cutting knife, the second cutting knife posture change trend prediction model is used to predict the second posture change trend of the cutting knife during the cutting task execution process; and based on the deviation between the second posture change trend and the expected posture change trend, the predetermined cutting knife control scheme is optimized; In the process of executing the cutting task, the cutting knife is controlled by adopting an optimized cutting knife control scheme.
2. The method for predictive control of cutting blades applied to automatic cutting machines according to claim 1, characterized in that: The first data set includes cutting knife posture characterization data and cutting knife posture influence data; The cutting knife posture characterization data includes the cutting knife position and the cutting knife angle; The cutter posture influencing data include the cutter cutting speed, the quantitative value of the cutter edge wear, the temperature and humidity of the working environment, the dynamic load fluctuation of the cutter, and the hardness, thickness distribution and toughness of the cut material.
3. The method for predictive control of cutting blades applied to automatic cutting machines according to claim 2, characterized in that: The method for determining whether the first posture change trend is consistent with the expected posture change trend includes: Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing the first posture change trend; Uniformly selecting a plurality of discrete reference trend points on an expected trend line representing the expected posture change trend; If the number of inconsistent trend points among the plurality of trend points to be determined reaches a set value, it is determined that the first posture change trend is inconsistent with the expected posture change trend, The inconsistent trend point is a trend point to be determined that is inconsistent with the cutting knife position represented by the corresponding reference trend point or inconsistent with the cutting knife angle represented by the corresponding reference trend point.
4. The method for predictive control of cutting blades applied to automatic cutting machines according to claim 3, characterized in that: The second data set includes a plurality of data combinations with time stamps; The data combination includes the cutting knife posture characterization data and the cutting knife posture influence data.
5. The method for predictive control of cutting blades applied to automatic cutting machines according to claim 4, characterized in that: The optimizing of the predetermined cutting knife control scheme based on the deviation between the second posture change trend and the expected posture change trend comprises: Splitting a second trend line representing the change trend of the second posture into a cutting knife position change trend line and a cutting knife angle change trend line; Splitting the expected trend line representing the expected posture change trend into an expected cutting knife position change trend line and an expected cutting knife angle change trend line; Acquire a set of cutter position adjustment vectors for making the cutter position variation trend line approach the expected cutter position variation trend line; Acquire a set of cutting angle adjustment vectors for making the cutting angle variation trend line approach the expected cutting angle variation trend line; Optimizing the cutter position control vector set in the cutter control scheme according to the cutter position adjustment vector set; The cutting knife angle control vector set in the cutting knife control scheme is optimized according to the cutting knife angle adjustment vector set.
6. The method for predictive control of cutting blades applied to automatic cutting machines according to claim 5, characterized in that: The number of trend points to be determined is positively correlated with the cutting accuracy required for the cut material.
7. A predictive control system for cutting blades applied to automatic cutting machines, characterized in that: include: A first prediction model acquisition module, used to construct an algorithm based on the first data set and the dynamics model to acquire a first cutting knife posture change trend prediction model; A second prediction model acquisition module, used for acquiring a second cutting knife posture change trend prediction model according to the second data set and based on a long short-term memory network algorithm; a cutter control scheme optimization module, used for, before executing a cutting task, using the first cutter posture change trend prediction model to predict a first posture change trend of the cutter during the execution of the cutting task; if the first posture change trend is inconsistent with an expected posture change trend of the cutter, using the second cutter posture change trend prediction model to predict a second posture change trend of the cutter during the execution of the cutting task; and optimizing a predetermined cutter control scheme based on a deviation between the second posture change trend and the expected posture change trend; The cutting knife optimization control module is used to control the cutting knife by adopting an optimized cutting knife control scheme during the execution of the cutting task.
8. The predictive control system for cutting blades applied to automatic cutting machines according to claim 7, characterized in that: The method for determining whether the first posture change trend is consistent with the expected posture change trend includes: Uniformly selecting a plurality of discrete trend points to be determined on a first trend line representing the first posture change trend; Uniformly selecting a plurality of discrete reference trend points on an expected trend line representing the expected posture change trend; If the number of inconsistent trend points among the plurality of trend points to be determined reaches a set value, it is determined that the first posture change trend is inconsistent with the expected posture change trend, The inconsistent trend point is a trend point to be determined that is inconsistent with the cutting knife position represented by the corresponding reference trend point or inconsistent with the cutting knife angle represented by the corresponding reference trend point.
9. The predictive control system for cutting blades applied to automatic cutting machines according to claim 8, characterized in that: The optimizing of the predetermined cutting knife control scheme based on the deviation between the second posture change trend and the expected posture change trend comprises: Splitting a second trend line representing the change trend of the second posture into a cutting knife position change trend line and a cutting knife angle change trend line; Splitting the expected trend line representing the expected posture change trend into an expected cutting knife position change trend line and an expected cutting knife angle change trend line; Acquire a set of cutter position adjustment vectors for making the cutter position variation trend line approach the expected cutter position variation trend line; Acquire a set of cutting angle adjustment vectors for making the cutting angle variation trend line approach the expected cutting angle variation trend line; Optimizing the cutter position control vector set in the cutter control scheme according to the cutter position adjustment vector set; The cutting knife angle control vector set in the cutting knife control scheme is optimized according to the cutting knife angle adjustment vector set.
10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the processor implements the predictive control method for cutting blades applied to an automatic cutting table as described in any one of claims 1 to 6 when executing a computer program stored in the memory.
