Saw chain blade limiting angle automatic optimization method and system

Abstract

The invention discloses a saw chain blade limiting angle automatic optimization method and system, and relates to the technical field of saw chain blade angle optimization, and the method comprises the steps: carrying out the real-time collection of a saw chain blade, and obtaining a blade state data set; constructing a blade limiting angle fuzzy list; performing deep correlation learning to obtain a state-angle correlation network; mapping the sawing task to a state-angle association network for matching; simulating and executing a saw cutting task on the saw chain blade according to the first blade limiting angle information, and performing cutting test analysis on a cutting simulation result to generate cutting feedback information; and dynamic optimization response is carried out, and second blade limiting angle information is generated. The technical problems that in the prior art, saw chain blade angle adjustment is not intelligent, optimization cannot be conducted according to different cutting tasks and environment changes, and consequently the cutting efficiency and the cutting quality are low are solved, and the technical effects that the cutting efficiency and the cutting quality of the actual cutting task are improved, and the service life of the blade is prolonged are achieved.

Description

Technical Field

[0001] This application relates to the technical field related to the angle optimization of saw chain blades, and specifically relates to an automatic optimization method and system for the limiting angle of saw chain blades. Background Art

[0002] Saw chain blades are widely used in the cutting operations of wood, metal and other materials. In order to improve the cutting efficiency and accuracy, the angle adjustment of saw chain blades is crucial. At present, the angle adjustment of saw chain blades mostly relies on manual experience or preset fixed angles, which is prone to situations that are not suitable for different cutting tasks, thus affecting the cutting effect. For example, it often relies on fixed angle settings to perform cutting tasks and cannot be adjusted in real time according to different materials, cutting methods or the actual state of the saw chain blade, which may lead to low cutting efficiency, and even cause increased blade wear and reduced service life. In addition, the adjustment of the limiting angle lacks deep association and adaptability with various factors such as blade state and cutting environment, resulting in the failure to fully utilize the blade performance in actual applications, without considering environmental changes, wear and loss of saw chain blades, and affecting cutting quality and efficiency.

[0003] Therefore, in the current related technologies, there are technical problems that the angle adjustment of saw chain blades lacks intelligence and cannot be optimized according to different cutting tasks and environmental changes, resulting in low cutting efficiency and cutting quality. Thus, this application proposes an automatic optimization method and system for the limiting angle of saw chain blades. Summary of the Invention

[0004] By providing an automatic optimization method and system for the limiting angle of saw chain blades, this application solves the technical problems in the prior art that the angle adjustment of saw chain blades lacks intelligence and cannot be optimized according to different cutting tasks and environmental changes, resulting in low cutting efficiency and cutting quality, and achieves the technical effects of improving the cutting efficiency, cutting quality and blade service life of actual cutting tasks.

[0005] The present application provides a method for automatically optimizing the limiting angle of a saw chain blade. The method includes: collecting the saw chain blade in real time according to a sawing task through a sensing device to obtain a blade state data set; performing fuzzy inference based on the blade state data set to construct a fuzzy list of blade limiting angles; performing deep correlation learning on the blade state data set and the fuzzy list of blade limiting angles to obtain a state-angle correlation network; mapping the sawing task to the state-angle correlation network for matching, and extracting first blade limiting angle information; simulating the execution of the sawing task on the saw chain blade according to the first blade limiting angle information to obtain a cutting simulation result, and performing cutting test analysis on the cutting simulation result to generate cutting feedback information; synchronizing the cutting feedback information to the sawing task to perform a dynamic optimization response on the first blade limiting angle information, and generating second blade limiting angle information.

[0006] In a possible implementation manner, when performing deep correlation learning on the blade state data set and the fuzzy list of blade limiting angles to obtain a state-angle correlation network, the following processing is further performed: traversing the fuzzy list of blade limiting angles for defuzzification processing to generate multiple blade limiting angle information; using a deep neural network to synchronize the blade state data set and the multiple blade limiting angle information to the deep neural network through an input layer for matching, and performing correlation capture according to the matching result to determine multiple state-angle pairs; performing repair cross-validation based on the multiple state-angle pairs, and performing cross-backtracking according to the verification result to construct the state-angle correlation network.

[0007] In a possible implementation manner, when traversing the fuzzy list of blade limiting angles for defuzzification processing to generate multiple blade limiting angle information, the following processing is further performed: introducing multiple sawing scenario information, traversing the fuzzy list of blade limiting angles and combining the multiple sawing scenario information for membership calculation to generate a fuzzy membership degree, where the fuzzy membership degree includes membership area information and membership distribution information; performing weighted calculation on the fuzzy list of blade limiting angles based on the membership area information and the membership distribution information to generate multiple weight coefficients; performing centroid calculation on the fuzzy list of blade limiting angles according to the multiple weight coefficients to determine multiple blade limiting angle information, and there is a corresponding relationship between the multiple blade limiting angle information and the multiple sawing scenario information.

[0008] In a possible implementation, cross-validation is performed based on the multiple state-angle pairs, cross-backtracking is performed according to the verification result, and the state-angle correlation network is constructed. The following processing is further performed: multiple angle constraint conditions are set according to the multiple blade limit angle information in combination with the blade state data set; random extraction is performed based on the multiple state-angle pairs to obtain a first state-angle pair and a second state-angle pair; cross-validation is performed according to the first state-angle pair and the second state-angle pair to generate the verification result, and it is determined whether the verification result meets the multiple angle constraint conditions; if the verification result does not meet any one of the multiple angle constraint conditions, the first state-angle pair and the second state-angle pair are cross-backtracked according to the verification result to generate a backtracking result; the backtracking result is mapped to the multiple state-angles, and the first state-angle pair and the second state-angle pair are updated and iterated until the multiple angle constraint conditions are met, and the state-angle correlation network is constructed.

[0009] In a possible implementation, the sawing task is simulatedly executed on the saw chain blade according to the first blade limit angle information to obtain a cutting simulation result. The following processing is further performed: the multiple sawing scenario information is matched according to the sawing task to determine the simulated sawing environment information; according to the simulated sawing environment information, in combination with the first blade limit angle information, the sawing task is simulatedly executed for multi-dimensional analysis to generate multi-dimensional cutting analysis data, where the multi-dimensional cutting analysis data includes cutting performance data, cutting wear data, and cutting stability data; performance calculation is performed based on the cutting performance data in combination with the sawing task to obtain a cutting efficiency parameter; wear calculation is performed based on the cutting wear data in combination with the sawing task to obtain a blade life parameter; stability calculation is performed based on the cutting stability data in combination with the sawing task to obtain a blade amplitude parameter; the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter are added to the cutting simulation result.

[0010] In a possible implementation, the cutting simulation results are subjected to cutting test analysis to generate cutting feedback information, and the following processing is also performed: the sawing task is segmented based on the cutting simulation results to determine multiple cutting stages; cutting tests are performed in accordance with the multiple cutting stages in combination with the cutting efficiency parameter to obtain first blade cutting behavior test data; cutting tests are performed in accordance with the multiple cutting stages in combination with the blade life parameter to obtain second blade cutting behavior test data; cutting tests are performed in accordance with the multiple cutting stages in combination with the blade amplitude parameter to obtain third blade cutting behavior test data; the first blade cutting behavior test data, the second blade cutting behavior test data, and the third blade cutting behavior test data are used to perform sawing behavior analysis on the saw chain blade according to the first blade limit angle information to generate the cutting feedback information.

[0011] In a possible implementation, the cutting feedback information is synchronized to the sawing task to perform a dynamic optimization response to the first blade limit angle information, generating second blade limit angle information, and the following processing is also performed: the first blade cutting behavior test data is synchronized to the sawing task to perform a fitness evaluation of the first blade limit angle information, generating a first fitness score; the second blade cutting behavior test data is synchronized to the sawing task to perform a fitness evaluation of the first blade limit angle information, generating a second fitness score; the third blade cutting behavior test data is synchronized to the sawing task to perform a fitness evaluation of the first blade limit angle information, generating a third fitness score; sawing analysis is performed based on the first fitness score, the second fitness score, the third fitness score in combination with the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to obtain a first sawing effect, and the first sawing effect has a corresponding relationship with the first blade limit angle information; comprehensive analysis is performed in accordance with the multiple cutting stages in combination with the first fitness score, the second fitness score, and the third fitness score to generate a dynamic parameter to be optimized, and the first sawing effect is optimized in response to the dynamic parameter to be optimized to generate the second blade limit angle information.

[0012] The present application also provides an automatic optimization system for the limiting angle of a saw chain blade, including: a blade state data set acquisition module, configured to obtain a blade state data set by collecting the saw chain blade in real time according to a sawing task through a sensing device; a fuzzy inference module, configured to perform fuzzy inference based on the blade state data set to construct a fuzzy list of the limiting angle of the blade; a deep correlation learning module, configured to perform deep correlation learning on the blade state data set and the fuzzy list of the limiting angle of the blade to obtain a state-angle correlation network; a first limiting angle information extraction module of the blade, configured to map the sawing task to the state-angle correlation network for matching and extract first limiting angle information of the blade; a cutting feedback information generation module, configured to simulate the execution of the sawing task on the saw chain blade according to the first limiting angle information of the blade to obtain a cutting simulation result, perform cutting test analysis on the cutting simulation result, and generate cutting feedback information; and a dynamic optimization response module, configured to synchronize the cutting feedback information to the sawing task to perform dynamic optimization response on the first limiting angle information of the blade and generate second limiting angle information of the blade.

[0013] It is intended to collect the saw chain blade in real time through an automatic optimization method and system for the limiting angle of a saw chain blade proposed in the present application to obtain a blade state data set; construct a fuzzy list of the limiting angle of the blade; perform deep correlation learning to obtain a state-angle correlation network; map the sawing task to the state-angle correlation network for matching; simulate the execution of the sawing task on the saw chain blade according to the first limiting angle information of the blade, perform cutting test analysis on the cutting simulation result, and generate cutting feedback information; and perform dynamic optimization response to generate second limiting angle information of the blade. This solves the technical problem in the prior art that the angle adjustment of the saw chain blade lacks intelligence and cannot be optimized according to different cutting tasks and environmental changes, resulting in low cutting efficiency and cutting quality, and achieves the technical effects of improving the cutting efficiency, cutting quality, and service life of the blade in actual cutting tasks. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0015] Figure 1 It is a schematic flowchart of an automatic optimization method for the limiting angle of a saw chain blade provided by an embodiment of the present application.

[0016] Figure 2Schematic structural diagram of an automatic optimization system for the limiting angle of a saw chain blade provided by an embodiment of the present application.

[0017] Explanation of reference numerals in the drawings: Blade state data set acquisition module 10, fuzzy inference module 20, deep correlation learning module 30, first blade limiting angle information extraction module 40, cutting feedback information generation module 50, dynamic optimization response module 60. Detailed implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first" and "second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] An embodiment of the present application provides an automatic optimization method for the limiting angle of a saw chain blade, as Figure 1 shown. The method includes: Step S100, performing real-time acquisition on the saw chain blade according to the sawing task through a sensing device to obtain a blade state data set.

[0022] Preferably, a sensing device (multiple different sensors) is used to collect the blade status data of the saw chain blade during the cutting task, including load data, temperature data, vibration data, wear data, etc., to form a blade status data set. Specifically, the load data refers to the magnitude of the force borne by the saw chain blade during the cutting process, including cutting force, axial force, etc. during the cutting process. The load data can reflect the working load of the blade in actual use, thus helping to determine whether the blade is in a normal working state, whether it is overloaded or there is an abnormality; the temperature data refers to the temperature change generated by the saw chain blade during the cutting process. Friction during the cutting process will cause the surface temperature of the blade to rise. Excessive temperature may accelerate the wear of the blade, or even cause deformation of the material or a decrease in cutting quality. The temperature data helps to monitor the working temperature of the blade and promptly detect overheating or abnormal temperature rise to avoid blade damage; the vibration data refers to the vibration generated by the saw chain blade during the cutting process. The vibration condition of the saw chain blade is closely related to its working state. Excessive vibration may indicate imbalance, damage or instability during the cutting process of the blade. The vibration data helps to detect the stability of the blade and the smoothness of the cutting process; the wear data refers to the degree of wear generated by the contact friction between the blade and the material during long-term use. The wear data reflects the service life and wear condition of the blade. An overly worn blade may cause a decrease in cutting effect or blade damage. The wear data can provide real-time feedback on the blade status and help with timely maintenance or angle adjustment.

[0023] Step S200, based on the blade status data set, perform fuzzy inference to construct a fuzzy list of blade limit angles.

[0024] Preferably, the fuzzy logic method is used to analyze the working state data of the blade, infer multiple possible suitable blade limiting angle ranges, and construct a blade limiting angle fuzzy list. Among them, fuzzy inference is a method for dealing with uncertainty and ambiguity, usually by converting precise values into fuzzy sets for inference. Fuzzy inference mainly determines the working angle range of the blade based on multiple data in the blade state dataset (such as load, temperature, vibration, wear, etc.). Specifically, the blade state data (such as load data, temperature data, vibration data, wear data, etc.) collected from the sensing device is fuzzified, that is, converted into fuzzy values according to predetermined fuzzy rules. For example, the load data can be fuzzified into categories such as low load, medium load, and high load; the temperature data can be fuzzified into categories such as low temperature, normal temperature, and high temperature; the vibration data can be fuzzified into categories such as light vibration, medium vibration, and strong vibration; the wear data can be fuzzified into categories such as slight wear, medium wear, and severe wear. Among them, by defining a rule base, the relationship between the input fuzzy state data and the blade angle is mapped. For example, assuming that the blade has a heavy load, a high temperature, and severe wear, the corresponding inference rule will result in a smaller limiting angle to avoid excessive wear or overheating; finally, through the inference of different state combinations, multiple possible angle ranges are obtained and a blade limiting angle fuzzy list is constructed, indicating the angle range that the blade should adopt under specific working conditions. Through this method of fuzzification and inference, the system can dynamically adjust the blade angle according to different working conditions, thereby improving the cutting effect, extending the blade life, and achieving a more efficient cutting process.

[0025] Step S300, deeply associate and learn the blade state dataset with the blade limiting angle fuzzy list to obtain a state-angle correlation network.

[0026] Preferably, deep learning (such as algorithms like deep neural networks) is used to deeply analyze and learn the blade status data collected from sensors and the fuzzy list of blade limit angles obtained according to fuzzy inference, and an accurate correlation model between the blade status and the limit angle, that is, the state-angle correlation network, is established, which can help the system automatically predict and adjust the most suitable blade limit angle according to different blade working states. Specifically, through deep learning algorithms (such as deep neural networks), the complex relationship between the blade status data set and the fuzzy angle list is trained and learned, including using the blade status data (load, temperature, vibration, wear, etc.) as input data, and at the same time using the angle values in the fuzzy angle list as the target output data. These data are used as training samples and input into the deep neural network. Through deep learning models (such as convolutional neural network CNN, recurrent neural network RNN or multi-layer perceptron MLP, etc.), the relationship between the blade status data and the fuzzy angle values is trained. By iteratively optimizing the parameters multiple times, the mapping relationship between the blade status and the limit angle is learned. Finally, through the deep learning network, the optimal mapping relationship between the blade status data and the fuzzy angle list is found, and the state-angle correlation network is constructed, which can automatically predict the most suitable blade limit angle or angle range according to the real-time collected blade status data; it can also recommend the most suitable blade angle for different working states (such as different loads, different temperatures, different wear conditions, etc.), so that the cutting task can always maintain the best cutting effect under different conditions, reduce blade loss, and improve cutting accuracy and efficiency.

[0027] Further, step S300 further includes step S310 of traversing the fuzzy list of blade limit angles for defuzzification processing to generate multiple blade limit angle information; step S320 of using a deep neural network to synchronize the blade status data set and the multiple blade limit angle information to the deep neural network through the input layer for matching, and performing correlation capture according to the matching result to determine multiple state-angle pairs; step S330 of performing repair cross-validation based on the multiple state-angle pairs, and performing cross-backtracking according to the verification result to construct the state-angle correlation network.

[0028] Preferably, traversing the fuzzy list of blade limit angles for defuzzification means converting the fuzzy angle values obtained in the fuzzy inference process into specific and definite numerical values, so as to determine multiple blade limit angle information. Among them, defuzzification refers to defuzzifying the fuzzy angle values through a certain algorithm (such as the maximum membership degree method, weighted average method, etc.), converting the fuzzy angle interval into a single angle or a specific angle range. The determined multiple blade limit angle information represents the optimal angle value or angle range to be adopted under different blade working states; using a deep neural network (DNN) to match and associate the blade state data with the blade limit angle information. Specifically, the previously collected blade state data set (for example, load, temperature, vibration, wear, etc.) and multiple defuzzified blade limit angle information are input into the input layer of the deep neural network and are converted into the input feature vectors of the network. By training the deep neural network, the network will learn and capture the matching pattern between the blade state and the angle according to the relationship between the input blade state data (such as load, temperature, etc.) and the limit angle information. The network automatically identifies and associates the most suitable angle information with the current blade state, and then performs associated capture according to the matching result to determine multiple state-angle pairs. Each state-angle pair includes a specific blade working state (such as load, temperature, vibration, etc.) and the corresponding optimal blade limit angle.

[0029] Preferably, perform repair cross-validation according to multiple state-angle pairs, that is, optimize and validate the generated state-angle pairs to ensure the accuracy and reliability of the state-angle relationship network. Specifically, through the cross-validation method (such as K-fold cross-validation), train and test the performance of the neural network on different data subsets. If it is found during the cross-validation process that the matching results of some state-angle pairs are inaccurate, repair is performed (including adjusting network parameters, retraining the network, or adjusting input data features, etc.), that is, adjust and optimize these state-angle pairs until better matching and optimization results are obtained; then perform cross-backtracking according to the verification results, that is, backtrack and check whether the state-angle pairs generated by the model conform to the actual situation, and perform further optimization based on the verification results. For example, through backtracking analysis, find the state-angle pairs with inaccurate matching or poor performance, and perform analysis and adjustment. Finally, through backtracking and repair, the deep neural network will continuously optimize itself and generate a more accurate state-angle relationship network, which represents the accurate relationship between different blade working states (such as load, temperature, vibration, etc.) and the corresponding blade limit angles, and can automatically predict and select the most suitable limit angle according to the real-time blade working state data; and ensure the best selection of the blade angle in each cutting task, improving the cutting efficiency and quality.

[0030] Further, step S310 further includes step S311, introducing multiple sawing scenario information, traversing the blade limit angle fuzzy list and performing membership calculation in combination with the multiple sawing scenario information to generate fuzzy membership degrees, where the fuzzy membership degrees include membership area information and membership distribution information; step S312, performing weighted calculation on the blade limit angle fuzzy list based on the membership area information and the membership distribution information to generate multiple weight coefficients; step S313, performing centroid calculation on the blade limit angle fuzzy list according to the multiple weight coefficients to determine multiple blade limit angle information, and there is a corresponding relationship between the multiple blade limit angle information and the multiple sawing scenario information.

[0031] Preferably, by performing fuzzy calculation, weighting, and optimization on the relationship between different sawing scenarios and blade angle fuzzy values, the blade angle most suitable for different sawing scenarios is further accurately determined. Specifically, multiple sawing scenario information is introduced, that is, various working conditions and environmental factors in the cutting task are introduced. For example, different material types such as wood, metal, and plastic, different cutting methods such as straight cutting, curve cutting, and depth cutting, different cutting speeds, and different environmental temperatures and humidities. These sawing scenario information are closely related to the blade state (load, temperature, vibration, wear, etc.).

[0032] Preferably, traversing the blade limit angle fuzzy list and performing membership calculation in combination with multiple sawing scenario information, that is, combining the blade limit angle and the sawing scenario information to calculate the fuzzy membership degree, which measures the adaptation degree between the blade angle and the sawing scenario information, that is, the membership degree of this angle under a specific sawing scenario. The value of the membership degree is usually between 0 and 1, where 0 means completely inapplicable and 1 means completely applicable. The fuzzy membership degree includes membership area information and membership distribution information. The membership area represents the size of the adaptation area of the angle value under the sawing scenario. A larger membership area indicates a wider applicable range of this angle under this scenario; the membership distribution represents the distribution of the membership degree within the fuzzy angle value range. The membership distribution describes how the membership degree of each angle value is distributed within the entire angle range, reflecting the relative importance of different angles in different scenarios. For example, if the membership degree of a certain angle value under a specific sawing scenario is 0.8 and 0.5 under another scenario, then this angle value has stronger adaptability and a larger membership area in the first scenario.

[0033] Preferably, weights are assigned according to the information of membership area and membership distribution, and the fuzzy list of blade limiting angles is weighted and calculated to generate multiple weight coefficients. The angle values with higher weight coefficients are more applicable in specific scenarios, while the angles with lower weight coefficients are less suitable for use in such scenarios. Then, the most suitable blade limiting angle for each sawing scenario is determined by the centroid method. The centroid method is a commonly used fuzzy defuzzification method for determining the centroid or center point of a set. Specifically, according to the weighted list of blade limiting angles, the centroid of each scenario is calculated. For example, the weighted average is calculated based on the product of the membership degree of each angle and the weight coefficient to determine an optimal angle value, which represents the optimal angle considering multiple factors (such as membership area, distribution, weight coefficient). Furthermore, multiple blade limiting angle information is determined, and the corresponding relationship between the multiple blade limiting angle information and the multiple sawing scenario information is established, that is, each sawing scenario has an optimal blade limiting angle or angle range, enabling the system to automatically adjust the blade angle according to different cutting tasks and environmental conditions to achieve an efficient and accurate cutting process.

[0034] Further, step S330 further includes step S331 of setting multiple angle constraint conditions according to the multiple blade limiting angle information in combination with the blade state data set; step S332 of randomly extracting based on the multiple state-angle pairs to obtain a first state-angle pair and a second state-angle pair; step S333 of performing cross-validation according to the first state-angle pair and the second state-angle pair to generate the verification result and determining whether the verification result meets the multiple angle constraint conditions; step S334 of, if the verification result does not meet any one of the multiple angle constraint conditions, performing cross-backtracking on the first state-angle pair and the second state-angle pair according to the verification result to generate a backtracking result; step S335 of mapping the backtracking result to the multiple state-angles, and updating and iterating the first state-angle pair and the second state-angle pair until the multiple angle constraint conditions are met to construct the state-angle association network.

[0035] Preferably, multiple angle constraint conditions are set based on multiple blade limit angle information in combination with the blade state data set to define a reasonable range or limit for the blade angle under specific working conditions. For example, the blade angle cannot exceed a certain maximum or minimum value to avoid excessive cutting or overly severe wear; the blade angle should adapt to a specific workload, such as using a smaller cutting angle under high load and a larger angle under low load; the blade angle is related to the ambient temperature, and the blade angle should be reduced when the temperature is too high to avoid overheating of the blade; the change in the blade angle should follow certain rate and amplitude limits to avoid the impact of sudden changes on the cutting performance. Then, two pairs are randomly extracted from multiple state-angle pairs as the first state-angle pair and the second state-angle pair respectively, and the first state-angle pair and the second state-angle pair can be adjacent or non-adjacent.

[0036] Preferably, the first state-angle pair and the second state-angle pair are verified to check whether they meet all the angle constraint conditions. If a certain state-angle pair does not meet the angle constraint conditions, it means that this pair is not applicable in the current situation and needs to be optimized or adjusted. For example, if the angle value is not within the allowed range, or the angle does not match the working conditions such as load and temperature, the cross-verification will mark this non-conforming situation and determine whether the verification result meets multiple angle constraint conditions. If the verification result finds that a certain state-angle pair does not meet the constraint conditions, it is necessary to correct it through cross-backtracking to obtain the backtracking result, that is, adjust the non-conforming state-angle pair according to the verification result to ensure that they meet the predetermined angle constraint conditions. For example, if the angle of a certain state-angle pair exceeds the maximum value, the angle can be modified through backtracking to ensure that it meets the predetermined range.

[0037] Preferably, the backtracking result is mapped to multiple state-angles, and the first state-angle pair and the second state-angle pair are updated iteratively until they meet multiple angle constraint conditions, that is, the state-angle pairs are updated according to the corrected backtracking result and remapped into multiple state-angle pairs. Specifically, see where the problem is in the backtracking result, eliminate and replace the problematic ones, and then randomly extract based on multiple state-angle pairs for cross-verification again until all state-angle pairs meet the angle constraint conditions, and finally generate a complete state-angle correlation network, which represents the relationship between different blade states (such as load, temperature, vibration, etc.) and the optimal limit angle. The state-angle correlation network can accurately describe the relationship between the blade state and the limit angle, ensuring the best blade angle selection in various sawing scenarios and improving the cutting efficiency and accuracy.

[0038] Step S400, map the sawing task to the state-angle correlation network for matching, and extract the first blade limit angle information.

[0039] Preferably, mapping the sawing task to the state-angle correlation network for matching means that according to the current sawing task, the state-angle correlation network is used to select and extract the most suitable blade limiting angle, so as to achieve the optimal cutting effect. Specifically, the current sawing task parameters (such as load, temperature, cutting method, etc.) are converted into blade states, and then the blade angle that best matches this state is found in the state-angle correlation network. For example, if the current sawing task is carried out in an environment of "high load" and "high temperature", this task is mapped to the two states of "high load" and "high temperature", and the corresponding optimal angle in the state-angle correlation network is searched, that is, the first blade limiting angle information is extracted, ensuring that the optimal blade limiting angle can be automatically selected and adjusted in each sawing task, thereby optimizing the cutting effect, improving the cutting efficiency, reducing blade wear, and extending the service life of the blade.

[0040] Step S500, the sawing task is simulatedly executed on the saw chain blade according to the first blade limiting angle information, a cutting simulation result is obtained, and the cutting simulation result is subjected to cutting test analysis to generate cutting feedback information.

[0041] Preferably, the selected blade limiting angle information is applied to the simulation of the sawing task, the cutting effect is predicted by simulating the cutting process, and then the simulation result is verified through actual cutting tests, and feedback information is generated to further optimize the blade angle. Specifically, the first blade limiting angle information is used through computer simulation or simulation technology to simulate how the blade behaves in the actual cutting process to evaluate the cutting effect of the blade in the sawing task at a specific limiting angle. For example, the simulation may include calculating factors such as the contact force between the blade and the material, the movement trajectory of the blade, the cutting speed, and the cutting depth, and then obtaining the cutting simulation result, including the detailed performance of the blade executing the cutting task at the selected angle, such as whether the simulated cutting can meet the expected accuracy requirements, the speed of the blade executing the cutting task at a specific angle, the vibration, temperature change, etc. during the cutting process, as well as the friction force between the blade and the material, the load change during cutting, etc.; then the obtained cutting simulation result is subjected to cutting test analysis, that is, the simulated cutting result is compared with the actual physical cutting process, or the simulation result is verified through actual cutting experiments, and then cutting feedback information is generated, that is, the feedback data obtained from the cutting test analysis, which is used to evaluate the effect of the cutting task execution, and may include whether the cutting accuracy meets the expectation, whether the cutting speed is appropriate, whether the blade is excessively worn, whether it overheats, whether it operates stably, etc., whether there are abnormalities such as excessive vibration, noise, and increased cutting resistance, so as to help optimize the blade angle or cutting conditions and further improve the cutting performance and efficiency.

[0042] Further, step S500 further includes step S510 of matching the multiple sawing scenario information based on the sawing task to determine simulated sawing environment information; step S520 of performing multi-dimensional analysis by simulating the execution of the sawing task according to the simulated sawing environment information in combination with the first blade limit angle information to generate multi-dimensional cutting analysis data, where the multi-dimensional cutting analysis data includes cutting performance data, cutting wear data, and cutting stability data; step S530 of performing performance calculation based on the cutting performance data in combination with the sawing task to obtain a cutting efficiency parameter; step S540 of performing wear calculation based on the cutting wear data in combination with the sawing task to obtain a blade life parameter; step S550 of performing stability calculation based on the cutting stability data in combination with the sawing task to obtain a blade amplitude parameter; and step S560 of adding the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to the cutting simulation result.

[0043] Preferably, a comprehensive evaluation of the sawing task and the cutting performance of the blade in the simulated environment is carried out through multi-dimensional data analysis. By combining parameters such as cutting efficiency, wear, and stability, the cutting task is deeply analyzed and optimized. Specifically, matching the multiple sawing scenario information based on the sawing task means that according to the requirements of the sawing task (for example, the task of cutting wood, metal, or plastic), the sawing scenario information related to this task is selected and matched. For example, when cutting metal, a higher load and a smaller angle are required, while when cutting wood, a larger angle and a lower load may be needed, so as to determine the simulated sawing environment information, including factors such as temperature, load, friction, and cutting speed during the cutting process; combining the simulated sawing environment information and the first blade limit angle information, simulating the execution of the sawing task and performing multi-dimensional analysis, that is, when simulating the execution of the sawing task in the simulated environment, not only the cutting effect of the blade is analyzed, but also the cutting process is analyzed from multiple angles to generate multi-dimensional cutting analysis data, including cutting performance data (cutting efficiency, cutting speed, cutting accuracy, etc.), cutting wear data (the wear situation of the blade during the cutting process, including the wear speed, wear position, and wear degree of the blade), and cutting stability data (whether the blade can maintain a stable working state during the cutting process, including vibration, temperature change, and whether there is an unstable or out-of-control situation of the blade during the cutting process).

[0044] Preferably, performance calculation is performed according to the cutting performance data in combination with the sawing task, that is, cutting efficiency parameters are calculated based on the cutting speed, cutting depth, cutting accuracy, etc. Cutting efficiency usually refers to the amount of cutting tasks completed per unit time; wear calculation is performed according to the cutting wear data in combination with the sawing task to predict the service life of the blade (blade life parameter), which reflects the durability and replaceable cycle of the blade under specific sawing tasks and environmental conditions. For example, the wear speed of the blade during cutting under high load is faster than that under low load, so its life parameter will be relatively shorter; stability calculation is performed according to the cutting stability data in combination with the sawing task to calculate the blade amplitude parameter. The blade amplitude parameter reflects the intensity and amplitude of the blade vibration during cutting. Excessive vibration will affect the cutting accuracy and accelerate the blade wear; finally, the cutting efficiency parameter, blade life parameter, and blade amplitude parameter are integrated into the cutting simulation result, providing data support for subsequent optimization decisions and blade performance adjustment to ensure the efficient execution of each cutting task and the optimal use of the blade.

[0045] Further, step S500 further includes step S570 of dividing the sawing task into data according to the cutting simulation result to determine multiple cutting stages; step S580 of performing cutting tests according to the multiple cutting stages in combination with the cutting efficiency parameter to obtain the first blade cutting behavior test data; step S590 of performing cutting tests according to the multiple cutting stages in combination with the blade life parameter to obtain the second blade cutting behavior test data; step S5100 of performing cutting tests according to the multiple cutting stages in combination with the blade amplitude parameter to obtain the third blade cutting behavior test data; step S5200 of analyzing the sawing behavior of the saw chain blade according to the first blade cutting behavior test data, the second blade cutting behavior test data, and the third blade cutting behavior test data according to the first blade limit angle information to generate the cutting feedback information.

[0046] Preferably, by analyzing the cutting task in stages, combining multiple cutting performance parameters (such as cutting efficiency, blade life, blade amplitude, etc.), and conducting tests to generate the behavior data of the blade at different stages, and finally comprehensively analyzing these data to generate cutting feedback information, so as to realize the performance optimization and adjustment of the saw chain blade. Specifically, based on the cutting simulation results, the entire sawing process is divided into multiple cutting stages, and each stage represents a different stage in the cutting process (for example, the starting stage, the acceleration stage, the stable stage, the ending stage, etc.). Then, cutting tests are carried out in combination with the cutting efficiency parameter, that is, actual cutting tests are carried out based on the cutting efficiency parameter, simulating or actually operating the saw chain blade for cutting to obtain the first blade cutting behavior test data, such as cutting speed, efficiency loss, etc.; in combination with the blade life parameter, actual cutting tests are carried out at different cutting stages to evaluate the wear condition of the blade at each stage and obtain the second blade cutting behavior test data, including the wear degree and life change of the blade at each stage; according to the blade amplitude parameter, tests are carried out at each cutting stage to observe the vibration condition of the blade at different stages and obtain the third blade cutting behavior test data, including the vibration condition of the blade at different cutting stages and the relationship between the amplitude change and the cutting quality; the first blade cutting behavior test data, the second blade cutting behavior test data, and the third blade cutting behavior test data are combined to conduct sawing behavior analysis, including comparing the data of each stage to find out the advantages and disadvantages of the blade at different stages, so as to generate cutting feedback information, usually including cutting efficiency feedback, blade wear feedback, and cutting stability feedback, to ensure the efficient completion of the sawing task and improve the service life and stability of the blade.

[0047] Step S600, synchronize the cutting feedback information to the sawing task to perform a dynamic optimization response to the first blade limit angle information, and generate the second blade limit angle information.

[0048] Preferably, by feeding back the cutting feedback information obtained from the cutting test to the sawing task, the blade limit angle can be dynamically optimized and adjusted according to the actual performance, so as to generate new and more optimized second blade limit angle information to adapt to different cutting conditions and improve the cutting effect. Specifically, the cutting feedback information is combined with the sawing task and a response is made according to the feedback result, that is, the limit angle of the blade is adjusted in real time according to the feedback information. By using the cutting feedback information (such as efficiency, wear, stability, etc.) as input, the first blade limit angle is dynamically adjusted, and a new and more suitable angle is selected to perform the next cutting task, thereby generating the second blade limit angle information. That is, the new blade angle generated according to the dynamic optimization response can better meet the requirements of the current sawing task and environmental conditions. For example, if the first blade limit angle performs poorly in a high-load and high-temperature environment, the limit angle is adjusted according to the cutting feedback information so that the blade can provide higher efficiency and lower wear in the next cutting task. The second blade limit angle information will be used for subsequent cutting tasks to ensure that the blade is always in the best cutting state under different working conditions, improve the cutting effect, extend the blade life, and ensure the stability and efficiency of the cutting process.

[0049] Further, step S600 further includes step S610, evaluating the fitness of the first blade limit angle information based on the synchronization of the first blade cutting behavior test data to the sawing task to generate a first fitness score; step S620, evaluating the fitness of the first blade limit angle information based on the synchronization of the second blade cutting behavior test data to the sawing task to generate a second fitness score; step S630, evaluating the fitness of the first blade limit angle information based on the synchronization of the third blade cutting behavior test data to the sawing task to generate a third fitness score; step S640, performing sawing analysis based on the first fitness score, the second fitness score, the third fitness score, combined with the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to obtain a first sawing effect, and there is a corresponding relationship between the first sawing effect and the first blade limit angle information; step S650, performing comprehensive analysis based on the multiple cutting stages, combined with the first fitness score, the second fitness score, and the third fitness score to generate a dynamic parameter to be optimized, and performing an optimization response on the first sawing effect according to the dynamic parameter to be optimized to generate the second blade limit angle information.

[0050] Preferably, by performing fitness evaluation and multi-dimensional sawing analysis on the first blade limiting angle information, integrating various cutting behavior data (such as cutting efficiency, blade life, blade amplitude, etc.), and then dynamically optimizing the blade limiting angle according to the results of the comprehensive analysis, a new and optimized second blade limiting angle information is generated to improve the cutting effect, reduce blade wear, and improve stability and efficiency. Specifically, the cutting behavior test data of the first blade, the cutting behavior test data of the second blade, and the cutting behavior test data of the third blade are synchronized to the sawing task respectively, and the fitness evaluation of the first blade limiting angle information is performed to generate a first fitness score (indicating the cutting efficiency adaptability at the first blade limiting angle), a second fitness score (indicating the cutting wear fitness at the first blade limiting angle), and a third fitness score (indicating the cutting vibration adaptability at the first blade limiting angle). Then, the first, second, and third fitness scores are combined with the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter for sawing analysis to evaluate the comprehensive performance of the first blade limiting angle information under different cutting tasks, and the first sawing effect is obtained, which describes the comprehensive performance of the blade when performing a specific task, such as cutting efficiency, blade life, cutting stability, etc. Among them, there is a corresponding relationship between the first sawing effect and the first blade limiting angle information.

[0051] Preferably, based on multiple cutting stages, a comprehensive analysis is performed by combining the first fitness score, the second fitness score, and the third fitness score. That is, in the cutting task, the fitness scores and parameters (such as cutting efficiency, blade life, amplitude, etc.) of each stage will be used to generate the dynamic parameters to be optimized. For example, if the first fitness score indicates that the efficiency of a certain cutting stage is low, identify this stage as the part to be optimized and adjust the parameters (such as blade angle, cutting speed, etc.) to improve the efficiency. Similarly, based on the blade life and amplitude parameters, optimize the blade angle, reduce vibration, and extend the blade service life. Finally, according to the generated dynamic parameters to be optimized, an optimized response is made to the first blade limiting angle information to generate a new and more suitable blade angle, that is, the second blade limiting angle information, so as to ensure that the blade is always in the best working state in different sawing tasks and stages, improve the cutting efficiency, extend the blade life, and optimize the stability of the cutting process.

[0052] In the above text, reference is made to Figure 1 A method for automatically optimizing the limiting angle of a saw chain blade according to an embodiment of the present invention is described in detail. Next, a system for automatically optimizing the limiting angle of a saw chain blade according to an embodiment of the present invention will be described with reference to Figure 2

[0053] ​A saw chain blade limit angle automatic optimization system according to an embodiment of the present invention is used to solve the technical problems existing in the prior art, such as the lack of intelligence in the angle adjustment of saw chain blades, and the inability to optimize according to different cutting tasks and environmental changes, resulting in low cutting efficiency and cutting quality. It achieves the technical effects of improving the cutting efficiency, cutting quality and blade service life of actual cutting tasks. A saw chain blade limit angle automatic optimization system includes: a blade state data set acquisition module 10, a fuzzy inference module 20, a deep correlation learning module 30, a first blade limit angle information extraction module 40, a cutting feedback information generation module 50, and a dynamic optimization response module 60.

[0054] The blade state data set acquisition module 10 is used to collect the saw chain blade in real time according to the sawing task through a sensing device to obtain a blade state data set; the fuzzy inference module 20 is used to perform fuzzy inference based on the blade state data set to construct a blade limit angle fuzzy list; the deep correlation learning module 30 is used to perform deep correlation learning on the blade state data set and the blade limit angle fuzzy list to obtain a state-angle correlation network; the first blade limit angle information extraction module 40 is used to map the sawing task to the state-angle correlation network for matching and extract the first blade limit angle information; the cutting feedback information generation module 50 is used to simulate the execution of the sawing task on the saw chain blade according to the first blade limit angle information to obtain a cutting simulation result, perform cutting test analysis on the cutting simulation result, and generate cutting feedback information; the dynamic optimization response module 60 is used to synchronize the cutting feedback information to the sawing task to perform dynamic optimization response on the first blade limit angle information and generate the second blade limit angle information.

[0055] Next, the specific configuration of the deep correlation learning module 30 will be described in detail. The deep correlation learning module 30 further includes: traversing the blade limit angle fuzzy list for defuzzification processing to generate multiple blade limit angle information; using a deep neural network to synchronize the blade state data set and the multiple blade limit angle information to the deep neural network through the input layer for matching, performing correlation capture according to the matching result, and determining multiple state-angle pairs; performing repair cross-validation based on the multiple state-angle pairs, and performing cross-backtracking according to the verification result to construct the state-angle correlation network.

[0056] Next, the specific configuration of the deep association learning module 30 will be further described in detail. The deep association learning module 30 further includes: introducing a plurality of sawing scenario information, traversing the blade limit angle fuzzy list and performing membership calculation in combination with the plurality of sawing scenario information to generate a fuzzy membership degree, where the fuzzy membership degree includes membership area information and membership distribution information; performing weighted calculation on the blade limit angle fuzzy list based on the membership area information and the membership distribution information to generate a plurality of weight coefficients; performing centroid calculation on the blade limit angle fuzzy list according to the plurality of weight coefficients to determine a plurality of blade limit angle information, and there is a corresponding relationship between the plurality of blade limit angle information and the plurality of sawing scenario information.

[0057] Next, the specific configuration of the deep association learning module 30 will be further described in detail. The deep association learning module 30 further includes: setting a plurality of angle constraint conditions according to the plurality of blade limit angle information in combination with the blade state data set; randomly extracting based on the plurality of state-angle pairs to obtain a first state-angle pair and a second state-angle pair; performing cross-validation according to the first state-angle pair and the second state-angle pair to generate the verification result, and determining whether the verification result satisfies a plurality of angle constraint conditions; if the verification result does not meet any one of the plurality of angle constraint conditions, cross-backtracking the first state-angle pair and the second state-angle pair according to the verification result to generate a backtracking result; mapping the backtracking result to the plurality of state-angles, and updating and iterating the first state-angle pair and the second state-angle pair until the plurality of angle constraint conditions are satisfied, and constructing the state-angle association network.

[0058] Next, the specific configuration of the cutting feedback information generation module 50 will be described in detail. The cutting feedback information generation module 50 further includes: matching the plurality of sawing scenario information based on the sawing task to determine simulated sawing environment information; according to the simulated sawing environment information, combining the first blade limit angle information to simulate and execute the sawing task for multi-dimensional analysis to generate multi-dimensional cutting analysis data, where the multi-dimensional cutting analysis data includes cutting performance data, cutting wear data, and cutting stability data; performing performance calculation based on the cutting performance data in combination with the sawing task to obtain a cutting efficiency parameter; performing wear calculation based on the cutting wear data in combination with the sawing task to obtain a blade life parameter; performing stability calculation based on the cutting stability data in combination with the sawing task to obtain a blade amplitude parameter; adding the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to the cutting simulation result.

[0059] Next, the specific configuration of the cutting feedback information generation module 50 will be further described in detail. The cutting feedback information generation module 50 further includes: dividing the sawing task into data according to the cutting simulation result to determine multiple cutting stages; performing cutting tests according to the multiple cutting stages in combination with the cutting efficiency parameter to obtain first blade cutting behavior test data; performing cutting tests according to the multiple cutting stages in combination with the blade life parameter to obtain second blade cutting behavior test data; performing cutting tests according to the multiple cutting stages in combination with the blade amplitude parameter to obtain third blade cutting behavior test data; analyzing the sawing behavior of the saw chain blade according to the first blade cutting behavior test data, the second blade cutting behavior test data, and the third blade cutting behavior test data according to the first blade limit angle information, and generating the cutting feedback information.

[0060] Next, the specific configuration of the dynamic optimization response module 60 will be described in detail. The dynamic optimization response module 60 further includes: synchronizing the first blade cutting behavior test data to the sawing task to evaluate the fitness of the first blade limit angle information, and generating a first fitness score; synchronizing the second blade cutting behavior test data to the sawing task to evaluate the fitness of the first blade limit angle information, and generating a second fitness score; synchronizing the third blade cutting behavior test data to the sawing task to evaluate the fitness of the first blade limit angle information, and generating a third fitness score; performing sawing analysis according to the first fitness score, the second fitness score, and the third fitness score in combination with the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to obtain a first sawing effect, and there is a corresponding relationship between the first sawing effect and the first blade limit angle information; performing comprehensive analysis according to the multiple cutting stages in combination with the first fitness score, the second fitness score, and the third fitness score to generate a dynamic parameter to be optimized, and optimizing the response to the first sawing effect according to the dynamic parameter to be optimized, and generating the second blade limit angle information.

[0061] The saw chain blade limit angle automatic optimization system provided by the embodiment of the present invention can execute the saw chain blade limit angle automatic optimization method provided by any embodiment of the present invention, and has the corresponding function modules and beneficial effects for executing the method.

[0062] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0063] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for automatically optimizing the limiting angle of a saw chain blade, characterized in that: The method comprises: The sensor equipment collects the saw chain blade in real time according to the sawing task to obtain the blade status data set; Perform fuzzy reasoning based on the blade state data set to construct a fuzzy list of blade limit angles; Perform deep association learning on the blade state data set and the blade limit angle fuzzy list to obtain a state-angle association network; Mapping the sawing task to the state-angle association network for matching, and extracting the first blade limit angle information; According to the first blade limit angle information, the saw chain blade is simulated to perform the sawing task, to obtain a cutting simulation result, and the cutting simulation result is subjected to a cutting test analysis to generate cutting feedback information; The cutting feedback information is synchronized with the sawing task to dynamically optimize the response to the first blade limit angle information to generate second blade limit angle information.

2. A method for automatically optimizing the limiting angle of a saw chain blade according to claim 1, characterized in that: The blade state data set and the blade limit angle fuzzy list are subjected to deep association learning to obtain a state-angle association network, the method comprising: Traversing the blade limit angle fuzzy list to perform defuzzification processing to generate multiple blade limit angle information; Using a deep neural network, the blade state data set and the plurality of blade limit angle information are synchronized to the deep neural network through an input layer for matching, and association capture is performed according to the matching results to determine a plurality of state-angle pairs; Repair cross-validation is performed based on the multiple state-angle pairs, cross-backtracking is performed according to the validation results, and the state-angle association network is constructed.

3. A method for automatically optimizing the limiting angle of a saw chain blade according to claim 2, characterized in that: Traversing the blade limit angle fuzzy list to perform defuzzification processing to generate multiple blade limit angle information, the method includes: Introducing multiple sawing scene information, traversing the blade limit angle fuzzy list and combining the multiple sawing scene information to perform membership calculation to generate a fuzzy membership degree, wherein the fuzzy membership degree includes membership area information and membership distribution information; Performing weighted calculation on the blade limit angle fuzzy list based on the membership area information and the membership distribution information to generate a plurality of weight coefficients; The centroid of the blade limit angle fuzzy list is calculated according to the multiple weight coefficients to determine multiple blade limit angle information, and the multiple blade limit angle information has a corresponding relationship with the multiple sawing scene information.

4. A method for automatically optimizing the limiting angle of a saw chain blade according to claim 2, characterized in that: Performing repair cross-validation based on the multiple state-angle pairs, performing cross-backtracking according to the validation results, and constructing the state-angle association network, the method includes: Setting a plurality of angle constraints according to the plurality of blade limit angle information in combination with the blade status data set; Perform random extraction based on the multiple state-angle pairs to obtain a first state-angle pair and a second state-angle pair; Perform cross-validation according to the first state-angle pair and the second state-angle pair to generate the validation result, and determine whether the validation result satisfies multiple angle constraint conditions; If the verification result does not meet any of the multiple angle constraints, cross-backtrack the first state-angle pair and the second state-angle pair according to the verification result to generate a backtracking result; The backtracking result is mapped to the multiple state-angles, and the first state-angle pair and the second state-angle pair are updated and iterated until the multiple angle constraints are satisfied, so as to construct the state-angle association network.

5. The method for automatically optimizing the limiting angle of a saw chain blade according to claim 3, characterized in that: The method includes: simulating the sawing task on the saw chain blade according to the first blade limit angle information to obtain a cutting simulation result. Matching the plurality of sawing scene information based on the sawing task to determine simulated sawing environment information; According to the simulated sawing environment information, combined with the first blade limit angle information, simulate the sawing task to perform multi-dimensional analysis, and generate multi-dimensional cutting analysis data, wherein the multi-dimensional cutting analysis data includes cutting performance data, cutting wear data, and cutting stability data; Performing performance calculation based on the cutting performance data in combination with the sawing task to obtain a cutting efficiency parameter; Perform wear calculation based on the cutting wear data in combination with the sawing task to obtain blade life parameters; Perform stability calculation based on the cutting stability data in combination with the sawing task to obtain blade amplitude parameters; The cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter are added to the cutting simulation result.

6. A method for automatically optimizing the limiting angle of a saw chain blade according to claim 5, characterized in that: The cutting simulation result is subjected to cutting test analysis to generate cutting feedback information, the method comprising: Based on the cutting simulation result, the sawing task is segmented into data to determine a plurality of cutting stages; Perform cutting tests according to the plurality of cutting stages in combination with the cutting efficiency parameters to obtain first blade cutting behavior test data; Performing a cutting test according to the plurality of cutting stages combined with the blade life parameter to obtain second blade cutting behavior test data; Perform cutting tests according to the plurality of cutting stages in combination with the blade amplitude parameters to obtain third blade cutting behavior test data; The first blade cutting behavior test data, the second blade cutting behavior test data, and the third blade cutting behavior test data are used to perform sawing behavior analysis on the saw chain blade according to the first blade limit angle information to generate the cutting feedback information.

7. A method for automatically optimizing the limiting angle of a saw chain blade according to claim 6, characterized in that: The cutting feedback information is synchronized to the sawing task to dynamically optimize the first blade limit angle information to generate second blade limit angle information, the method comprising: Based on the first blade cutting behavior test data synchronized to the sawing task, the adaptability evaluation of the first blade limit angle information is performed to generate a first adaptability score; Generating a second adaptation score based on evaluating the adaptability of the first blade limit angle information synchronized to the sawing task based on the second blade cutting behavior test data; Generating a third adaptation score based on evaluating the adaptability of the first blade limit angle information synchronized to the sawing task based on the third blade cutting behavior test data; Perform sawing analysis based on the first adaptability score, the second adaptability score, the third adaptability score combined with the cutting efficiency parameter, the blade life parameter, and the blade amplitude parameter to obtain a first sawing effect, wherein the first sawing effect corresponds to the first blade limit angle information; A comprehensive analysis is performed based on the multiple cutting stages in combination with the first adaptation score, the second adaptation score, and the third adaptation score to generate dynamic parameters to be optimized, and the first sawing effect is optimized according to the dynamic parameters to be optimized to generate the second blade limit angle information.

8. A saw chain blade limit angle automatic optimization system, characterized in that: The system is used to implement a method for automatically optimizing the limiting angle of a saw chain blade according to any one of claims 1 to 7, and the system comprises: A blade status data set acquisition module is used to acquire a blade status data set by collecting data of the saw chain blade in real time according to the sawing task through a sensor device; A fuzzy reasoning module, used for performing fuzzy reasoning based on the blade state data set to construct a fuzzy list of blade limit angles; A deep association learning module, used for performing deep association learning on the blade state data set and the blade limit angle fuzzy list to obtain a state-angle association network; A first blade limit angle information extraction module, used for mapping the sawing task to the state-angle association network for matching, and extracting the first blade limit angle information; a cutting feedback information generating module, configured to simulate the sawing task performed on the saw chain blade according to the first blade limit angle information, obtain a cutting simulation result, perform a cutting test analysis on the cutting simulation result, and generate cutting feedback information; The dynamic optimization response module is used to synchronize the cutting feedback information to the sawing task to dynamically optimize the first blade limit angle information and generate second blade limit angle information.

Images