Self-adaptive process parameter adjusting method used in saw blade production process

Abstract

The invention discloses a self-adaptive process parameter adjusting method used in the saw blade production process, and relates to the technical field of machining control. The method comprises the following steps: acquiring a plurality of process nodes of a target saw blade and saw blade form information corresponding to the process nodes; performing heat sensitivity and vibration sensitivity analysis to generate a plurality of heat sensitivity parameters and a plurality of vibration sensitivity parameters corresponding to the plurality of process nodes; acquiring a plurality of node process parameters currently used by the plurality of process nodes; node saw blade machining damage analysis is conducted in combination with the multiple node process parameters, the multiple heat sensitivity parameters and the multiple vibration sensitivity parameters, and multiple damage indexes are generated; and based on the plurality of damage indexes, positioning the node to be optimized, and performing optimization adjustment on the node process parameters of the node to be optimized. The technical problems of unstable machining quality and low production efficiency in the saw blade production process in the prior art are solved, and the technical effect of improving the machining quality and the production efficiency of the saw blade is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of processing control, and in particular to a method for adjusting self-adaptive process parameters in a saw blade production process. Background Art

[0002] As a cutting tool widely used in mechanical processing, the production quality and performance of saw blades directly affect the processing efficiency and workpiece quality. In the production process of saw blades, problems such as thermal deformation and vibration interference will have a significant impact on the shape and service life of the saw blades. However, in the current production process, the process parameters for saw blade production are often fixed, and it is difficult to dynamically adjust according to the needs of different production stages and the state of the saw blade, resulting in unstable processing quality and high damage rate. In addition, due to the lack of accurate analysis of thermal sensitivity and vibration sensitivity during the processing process, the production process cannot effectively control thermal damage and vibration damage, which further affects the processing accuracy and reliability of the saw blade. Therefore, how to optimize and adjust the process parameters based on the characteristics of the saw blade at different stages of the production process to improve the saw blade processing quality and production efficiency has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides an adaptive process parameter adjustment method for the saw blade production process, which solves the technical problems of unstable processing quality and low production efficiency in the saw blade production process in the prior art.

[0004] In view of the above problems, the present application provides an adaptive process parameter adjustment method for saw blade production.

[0005] The present application provides an adaptive process parameter adjustment method for a saw blade production process, the method comprising: Acquire multiple process nodes of a target saw blade, and saw blade morphology information corresponding to the multiple process nodes; perform thermal sensitivity and vibration sensitivity analysis based on the saw blade morphology information corresponding to the multiple process nodes, and generate multiple thermal sensitivity parameters and multiple vibration sensitivity parameters corresponding to the multiple process nodes; acquire multiple node process parameters currently used by the multiple process nodes; perform node saw blade processing damage analysis in combination with the multiple node process parameters, the multiple thermal sensitivity parameters and the multiple vibration sensitivity parameters, and generate multiple damage indicators; locate the node to be optimized based on the multiple damage indicators, and optimize and adjust the node process parameters of the node to be optimized.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, obtain multiple process nodes of the target saw blade, and saw blade morphology information corresponding to the multiple process nodes. Then, perform thermal sensitivity and vibration sensitivity analysis based on the saw blade morphology information corresponding to the multiple process nodes, and generate multiple thermal sensitivity parameters and multiple vibration sensitivity parameters corresponding to the multiple process nodes. Further, obtain multiple node process parameters currently used by the multiple process nodes. Then, perform node saw blade processing damage analysis based on multiple node process parameters, multiple thermal sensitivity parameters and multiple vibration sensitivity parameters, and generate multiple damage indicators. Finally, based on multiple damage indicators, locate the nodes to be optimized, and optimize and adjust the node process parameters of the nodes to be optimized. The technical problems of unstable processing quality and low production efficiency in the saw blade production process in the prior art are solved, and the technical effect of improving the saw blade processing quality and production efficiency is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic flow chart of a method for adaptively adjusting process parameters in a saw blade production process provided in an embodiment of the present application.

[0009] Figure 2 A schematic diagram of a process flow for performing node saw blade processing damage analysis in an adaptive process parameter adjustment method in a saw blade production process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The present application solves the technical problems of unstable processing quality and low production efficiency in the saw blade production process in the prior art by providing an adaptive process parameter adjustment method for the saw blade production process.

[0011] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0012] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0013] Examples, such as Figure 1 As shown, the embodiment of the present application provides an adaptive process parameter adjustment method for saw blade production, wherein the method includes: Acquire multiple process nodes of a target saw blade and saw blade morphology information corresponding to the multiple process nodes.

[0014] According to the production process of the target saw blade, multiple key process nodes involved are determined. These process nodes include but are not limited to heat treatment, cutting, grinding, stress relief treatment, etc. Each process node represents an important processing link in the production process of the saw blade.

[0015] At each process node, the saw blade morphology information is collected, including but not limited to the geometric dimensions (such as thickness, diameter), surface flatness, edge morphology characteristics and morphological changes of key parts of the saw blade. In the specific collection process, a variety of technical means can be used, such as optically scanning the saw blade with a high-precision laser scanner to obtain its morphological characteristics, detecting its surface flatness and roughness with a surface morphology analyzer, and accurately measuring the thickness, diameter and other key dimensions of the saw blade with special measuring instruments. By integrating each process node with its corresponding saw blade morphology information, a complete data set containing multiple process nodes and their morphological information is formed, which lays the foundation for subsequent thermal sensitivity and vibration sensitivity analysis, as well as saw blade processing damage analysis, thereby realizing intelligent and refined control of the production process.

[0016] Thermal sensitivity and vibration sensitivity analysis is performed based on saw blade morphology information corresponding to the multiple process nodes to generate multiple thermal sensitivity parameters and multiple vibration sensitivity parameters corresponding to the multiple process nodes.

[0017] By analyzing the saw blade morphology information, the morphological features of each process node are identified, such as the uniformity of saw blade thickness, the integrity of edge morphology, and changes in surface flatness. These features are key factors affecting the thermal sensitivity and vibration sensitivity of the saw blade. Subsequently, according to the thermodynamic and mechanical dynamic characteristics of the saw blade, combined with the temperature rise and vibration frequency changes that may occur during the processing, a corresponding analysis model is established.

[0018] In the thermal sensitivity analysis, the thermal deformation trend of the saw blade under the processing temperature rise conditions is simulated and calculated based on the morphological information and thermodynamic properties. The specific analysis content includes the deformation amount of the saw blade under high temperature, the stress distribution, and the influence of high temperature conditions on the edge integrity. Finally, the thermal sensitivity parameters corresponding to each process node are generated to quantify the sensitivity of the saw blade to the thermal effect during the processing of each node.

[0019] In the vibration sensitivity analysis, by combining the morphological characteristics and vibration response characteristics of the saw blade, the vibration state of the saw blade under different processing conditions is simulated to analyze the risk of deformation, crack propagation or other morphological defects that may occur under vibration conditions. The specific analysis content includes the vibration frequency, amplitude, and the impact of vibration on the edge and surface morphology of the saw blade, and finally generates vibration sensitivity parameters corresponding to each process node to quantify the processing stability of the saw blade under vibration conditions.

[0020] By performing the above-mentioned thermal sensitivity and vibration sensitivity analysis on multiple process nodes respectively, the thermal sensitivity parameters and vibration sensitivity parameters corresponding to each process node can be obtained. These parameters provide a quantitative basis for the subsequent saw blade processing damage analysis and also provide scientific guidance for optimizing process parameters to reduce processing damage.

[0021] Furthermore, performing thermal sensitivity and vibration sensitivity analysis based on the saw blade morphology information corresponding to the plurality of process nodes to generate a plurality of thermal sensitivity parameters and a plurality of vibration sensitivity parameters corresponding to the plurality of process nodes includes: Based on the saw blade morphology information corresponding to the multiple process nodes, the saw blade deformation influence analysis under different temperatures is performed to generate the multiple thermal sensitivity parameters; based on the saw blade morphology information corresponding to the multiple process nodes, the saw blade deformation influence analysis under different vibration intensities is performed to generate the vibration sensitivity parameters.

[0022] For thermal sensitivity analysis, the deformation response of the saw blade under different temperature conditions is simulated to quantitatively evaluate the influence of thermal effects on saw blade processing. Specifically, a thermodynamic model is established based on the saw blade morphology information collected at multiple process nodes, such as geometric dimensions, thickness distribution, surface flatness, etc., combined with the thermal expansion coefficient, thermal conductivity and temperature field distribution characteristics of the saw blade material. In the thermodynamic model, the effects of different processing temperatures on the deformation of the saw blade are gradually simulated, and the deformation trend, stress concentration area and morphological changes of the saw blade under high temperature conditions are analyzed. Based on the above analysis results, multiple thermal sensitivity parameters are generated, including the thermal deformation of the saw blade at different temperatures, the thermal stress distribution characteristics, and the degree of influence of thermal effects on edge morphology. These thermal sensitivity parameters can fully reflect the thermal stability of the saw blade during processing and provide a scientific basis for the optimization of process parameters.

[0023] In the vibration sensitivity analysis, based on the saw blade morphology information corresponding to multiple process nodes, the deformation response of the saw blade under different vibration intensities is simulated, and the influence of vibration effect on saw blade processing is quantitatively analyzed. Specifically, by combining the geometric characteristics and dynamic characteristics of the saw blade, a vibration analysis model is established to simulate the state of the saw blade under different vibration frequencies and amplitudes. In the vibration analysis model, the influence of different vibration frequencies and amplitudes on the deformation of the saw blade is gradually simulated, and the morphological changes of the saw blade under vibration conditions, possible structural defects (such as edge cracks, surface ripples), and the influence of vibration on processing accuracy are analyzed. Based on the above analysis results, multiple vibration sensitivity parameters are generated, including the vibration deformation under different vibration intensities, the vibration stress concentration, and the degree of influence of vibration on the stability of the saw blade morphology. These vibration sensitivity parameters can reflect the adaptability of the saw blade to the dynamic vibration environment during processing, and provide optimization direction for vibration control during processing.

[0024] A plurality of node process parameters currently used by the plurality of process nodes are obtained.

[0025] Determine the operating characteristics and related processing requirements of each process node in the production process of the target saw blade; these process nodes usually cover production steps such as heat treatment, cutting, grinding, stress relief, etc., and each node corresponds to a specific set of processing parameters; through real-time monitoring and data collection of production equipment, extract the process parameter information actually used in each process node, including but not limited to heat treatment process parameters (such as heating temperature, cooling rate, holding time, etc.), cutting parameters (such as cutting speed, feed rate, cutting depth, etc.), grinding parameters (such as grinding speed, grinding force, abrasive particle size, etc.), stress relief parameters (such as temperature during heating stress relief, cooling rate, etc.).

[0026] A node saw blade processing damage analysis is performed by combining the multiple node process parameters, the multiple thermal sensitivity parameters, and the multiple vibration sensitivity parameters to generate multiple damage indicators.

[0027] By associating the processing parameters of each process node (such as cutting speed, grinding force, etc.) with thermal sensitivity parameters (such as thermal deformation, thermal stress concentration area) and vibration sensitivity parameters (such as vibration amplitude, vibration stress distribution), the risk of damage to the saw blade during the processing process can be comprehensively evaluated. Combined with process parameters and thermal sensitivity parameters, the temperature distribution and thermal deformation during the processing process are simulated, the impact of high-temperature processing on the edge, surface morphology and internal stress distribution of the saw blade is evaluated, and the thermal damage characteristics are determined. Based on vibration sensitivity parameters and processing parameters, the impact of vibration frequency and amplitude during processing on the structural stability of the saw blade is analyzed, and whether there are problems such as crack extension, edge chipping or surface unevenness caused by vibration. According to the results of processing damage analysis, damage indicators corresponding to multiple process nodes are generated to quantify the degree of processing damage of the saw blade at different nodes. Among them, damage indicators include but are not limited to thermal damage indicators (such as thermal deformation, thermal stress concentration coefficient, etc.), vibration damage indicators (such as morphological deviation caused by vibration, vibration stress intensity, etc.). By combining multiple node process parameters, thermal sensitivity parameters and vibration sensitivity parameters to perform node saw blade processing damage analysis, multiple damage indicators can be generated to evaluate the damage degree and potential risks of saw blades at different process nodes. This provides important guidance and support for the production and processing of saw blades.

[0028] Furthermore, if Figure 2 As shown, the node saw blade processing damage analysis is performed by combining the multiple node process parameters, the multiple thermal sensitivity parameters and the multiple vibration sensitivity parameters to generate multiple damage indicators, including: Based on the temperature prediction and vibration prediction during processing of the multiple node process parameters, multiple saw blade surface temperature data and multiple saw blade vibration data are generated; based on the multiple saw blade surface temperature data and the multiple thermal sensitivity parameters, a thermal damage risk analysis is performed to generate multiple thermal damage risk indicators; based on the multiple saw blade vibration data and the multiple vibration sensitivity parameters, a vibration damage risk analysis is performed to generate multiple vibration damage risk indicators; based on the multiple thermal damage risk indicators and the multiple vibration damage risk indicators, a fusion analysis of thermal damage and vibration damage is performed on the multiple process nodes to generate the multiple damage indicators.

[0029] Based on the processing parameters of multiple process nodes (such as processing speed, cutting depth, heat treatment temperature, etc.), machine learning or numerical analysis methods (such as finite element analysis) are used to construct temperature prediction models and vibration prediction models in the saw blade processing process. These models take process parameters as input, predict the surface temperature and vibration state of the saw blade at different process nodes, and generate multiple surface temperature data and vibration data of the saw blade in the processing of each process node; then, based on the saw blade surface temperature data and thermal sensitivity parameters (such as thermal expansion coefficient, thermal deformation critical value, etc.), the thermal damage risk caused by temperature rise is analyzed, including the calculation of thermal deformation, thermal stress distribution, and edge breakage probability and other thermal damage risk indicators; at the same time, combined with the saw blade vibration data and vibration sensitivity parameters (such as vibration response characteristics, vibration damage threshold, etc.), the damage risk caused by vibration to the morphology and structural stability of the saw blade is analyzed, and multiple vibration damage risk indicators including vibration deformation amplitude, vibration stress intensity and vibration processing deviation are generated. After obtaining multiple thermal damage risk indicators and multiple vibration damage risk indicators, a fusion analysis is performed on the thermal damage and vibration damage of each process node to evaluate the saw blade processing damage under the combined action of multiple factors, and generate multiple damage indicators. The damage indicators reflect the quantitative evaluation of the degree of damage under different process conditions.

[0030] Furthermore, based on the multiple thermal damage risk indicators and the multiple vibration damage risk indicators, a fusion analysis of thermal damage and vibration damage is performed on the multiple process nodes to generate the multiple damage indicators, including: Connect to the saw blade production monitoring system, collect the historical saw blade temperature record data set, the historical saw blade vibration record data set and the corresponding historical saw blade production quality record set of each process node; analyze the historical saw blade temperature record data set and the historical saw blade vibration record data set to establish a historical thermal damage risk indicator set and a historical vibration damage risk indicator set; train the damage fusion weight of each process node based on the historical saw blade production quality record set, the historical thermal damage risk indicator set and the historical vibration damage risk indicator set; generate the corresponding damage fusion layer with the indicator fusion weight of each process node; fuse the thermal damage and vibration damage of the multiple process nodes with the damage fusion layer of each process node to generate the multiple damage indicators.

[0031] Specifically, the saw blade production monitoring system is connected to collect historical data of each process node, including a historical saw blade temperature record data set, a historical saw blade vibration record data set and a corresponding historical saw blade production quality record set. These historical data record the temperature changes, vibration characteristics and the relationship between the saw blade and the production quality in different process nodes; the historical saw blade temperature record data set and the historical saw blade vibration record data set are deeply analyzed to extract the characteristic information related to thermal damage and the characteristic information related to vibration damage in the processing process, respectively, and establish a historical thermal damage risk indicator set and a historical vibration damage risk indicator set; based on the historical saw blade production quality record set and the extracted thermal damage and vibration damage risk indicator set, the damage fusion weight of each process node is trained, and the indicator fusion weight of each process node is generated by analyzing the relative influence of thermal damage and vibration damage on production quality; the corresponding damage fusion layer is established with the indicator fusion weight of each process node, and the risk indicators of thermal damage and vibration damage are weighted and integrated in the fusion layer to reflect the comprehensive influence of multiple damage factors on the processing quality; based on the damage fusion layer, a fusion analysis of thermal damage and vibration damage is performed on each process node to generate multiple damage indicators.

[0032] Furthermore, a thermal damage risk analysis is performed based on the plurality of saw blade surface temperature data and the plurality of thermal sensitivity parameters to generate a plurality of thermal damage risk indicators, including: Taking the multiple thermal sensitivity parameters as constraints, historical saw blade surface temperature records and historical saw blade damage parameters corresponding to the multiple process nodes are collected; based on the historical saw blade surface temperature records and historical saw blade damage parameters, analysis is performed to identify the relationship between saw blade surface temperature and saw blade deformation parameters, and multiple node damage identification layers are generated; the multiple saw blade surface temperature data are input into the multiple node damage identification layers for damage risk identification, and the multiple thermal damage risk indicators are generated.

[0033] Specifically, taking multiple thermal sensitivity parameters as constraints, historical saw blade surface temperature records and historical saw blade damage parameters corresponding to multiple process nodes are collected. These historical data include the temperature change curve of the saw blade surface during the processing and its corresponding deformation, crack, stress concentration and other damage parameters. These data can reflect the intrinsic correlation between temperature and saw blade damage; based on the historical saw blade surface temperature records and historical saw blade damage parameters, the key characteristics of the saw blade surface temperature (such as temperature peak, heating rate, temperature distribution range, etc.) and the corresponding damage characteristics (such as deformation, crack generation probability, surface damage, etc.) are extracted, and machine learning algorithms (such as regression analysis, neural networks, etc.) or statistical methods (such as correlation analysis, regression analysis, etc.) are used to identify the relationship between the saw blade surface temperature and the saw blade deformation parameters (such as deformation, crack length, etc.), so as to construct a node damage identification layer that can reflect the relationship between temperature and damage risk. Each node damage identification layer corresponds to a process node, and can identify the damage risk at the node based on the saw blade surface temperature data. The saw blade surface temperature data of the current process node is input into the generated node damage identification layer to automatically identify and evaluate the damage risk; the node damage identification layer analyzes the input temperature data and combines the relationship between temperature and damage parameters trained in historical data to identify the potential thermal damage risk of the saw blade under the current temperature conditions and predict the possible deformation, stress distribution and probability of edge damage. Based on the identification results, multiple thermal damage risk indicators are generated, including but not limited to the thermal deformation of the saw blade, the degree of thermal stress concentration and the surface damage risk level.

[0034] The process of generating multiple vibration damage risk indicators by performing vibration damage risk analysis based on multiple saw blade vibration data and multiple vibration sensitivity parameters is similar to the process of generating multiple thermal damage risk indicators mentioned above. Specifically, based on historical vibration data and damage parameters, the key characteristics of vibration (such as amplitude peak, frequency distribution, acceleration change, etc.) and corresponding damage characteristics (such as crack length, structural deformation, etc.) are extracted, and the nonlinear relationship between vibration characteristics and saw blade damage is identified through regression analysis, support vector machine (SVM) or neural network and other technologies, and then a vibration damage identification layer is generated for each process node to analyze the potential damage risk of the saw blade under the current vibration conditions. The saw blade vibration data of the current process node is input into the vibration damage identification layer for analysis to generate vibration damage risk indicators, including quantitative indicators such as deformation amplitude caused by vibration, stress distribution characteristics, crack propagation probability and surface damage risk.

[0035] Based on the multiple damage indicators, the nodes to be optimized are located, and the node process parameters of the nodes to be optimized are optimized and adjusted.

[0036] Combined with the thermal damage risk index and the vibration damage risk index, the damage index of multiple process nodes is comprehensively evaluated. According to the set damage threshold and risk level standard, determine which process nodes have damage indicators that exceed the preset allowable range (such as thermal deformation, vibration stress concentration factor or crack propagation probability, etc.), and mark these process nodes as nodes to be optimized. For each node to be optimized, combined with the current process parameters of the node (such as cutting speed, processing temperature, feed rate, vibration amplitude, etc.), analyze the correlation between process parameters and damage indicators; by looking back at historical data, identify which process parameters have the greatest impact on the thermal damage or vibration damage of the current node (for example, too high processing temperature may lead to increased thermal deformation, or too fast feed rate may cause high-frequency vibration), so as to determine the key process parameters that need to be adjusted. Based on the damage characteristics of the node to be optimized, a process parameter optimization model is constructed; the optimization model can use a multi-objective optimization algorithm (such as genetic algorithm, particle swarm optimization, etc.) to balance the relationship between various process parameters with the goal of reducing damage risk. For example, the risk indicators of thermal damage and vibration damage are used as the objective function, and the current process parameters and sensitivity parameters of the node are used as constraints, and the optimal process parameter combination is calculated through the model. The process parameter results output by the optimization model are applied to the nodes to be optimized, and the process parameters are adjusted in real time. For example, the processing temperature is lowered to reduce the risk of thermal deformation, or the cutting speed and feed rate are optimized to reduce the vibration amplitude. By adjusting the key process parameters, the processing damage of the nodes is minimized and the production quality of the saw blade is improved.

[0037] Furthermore, based on the multiple damage indicators, locating the node to be optimized, and optimizing and adjusting the node process parameters of the node to be optimized, including: Perform full-process fusion impact analysis on the multiple damage indicators to locate the nodes to be optimized; optimize the node process parameters of the nodes to be optimized with the goal of minimizing the damage indicators of the nodes to be optimized to generate process parameter optimization results; and adjust the process parameters of the nodes to be optimized based on the process parameter optimization results.

[0038] Specifically, a full-process fusion impact analysis is performed on multiple damage indicators, and the damage indicators of each node are associated in chronological order according to the process flow to evaluate their impact on downstream nodes or the overall processing quality, so as to accurately locate the nodes to be optimized that are most severely damaged or have the greatest impact on production; with the goal of minimizing the damage indicator of the node to be optimized, a multi-objective optimization model is constructed, and by inputting the current process parameters of the node (such as processing temperature, cutting speed, feed rate, vibration amplitude, etc.) and related constraints, combined with the damage law in historical data, the optimal process parameter combination that can minimize the damage indicator is calculated and generated, such as the adjusted processing temperature range, optimal cutting speed or dynamic feed control value; based on the optimization results, the process parameters of the node to be optimized are actually adjusted.

[0039] Furthermore, a full-process fusion impact analysis is performed on the multiple damage indicators to locate the nodes to be optimized, including: For a first process node and a second process node adjacent to each other among the multiple process nodes, wherein the first process node is located before the second process node; performing damage superposition effect analysis on the first process node and the second process node to generate a first damage superposition effect coefficient, wherein the first damage superposition effect coefficient represents the influence of the damage index of the first process node on the damage index of the second process node; after optimizing the multiple damage indexes with the first damage superposition effect coefficient, locating the process node whose optimized damage index is greater than the preset damage index, and generating the node to be optimized.

[0040] Specifically, the adjacent first process node and second process node in the process flow are selected, wherein the first process node is located before the second process node, representing the chronological relationship in the process flow; based on the damage index data of the two process nodes, the influence of the damage index of the first process node on the damage index of the second process node is analyzed by superposition effect, and the first damage superposition effect coefficient is calculated and generated to quantify the cumulative or amplified effect of the damage of the first process node on the second process node, such as how the thermal damage or vibration damage generated by the first node affects the processing quality and damage risk of the second node; with the first damage superposition effect coefficient as the weight, the damage indicators of all process nodes are optimized and adjusted, the damage index of each process node is recalculated, and the result is compared with the preset damage index threshold, so as to locate the process nodes whose comprehensive damage index is greater than the preset threshold and mark them as nodes to be optimized.

[0041] Calculate the first damage superposition effect coefficient. Optionally, obtain damage index data of the first process node and the second process node, including thermal damage risk indicators (such as thermal deformation, thermal stress concentration value, etc.) and vibration damage risk indicators (such as vibration amplitude, vibration stress distribution, etc.); use the damage index of the first process node as an input variable and the damage index of the second process node as an output variable to establish a correlation model between the two; use linear regression analysis, weighted superposition model or machine learning method (such as support vector machine, neural network, etc.) to identify how the damage of the first process node affects the damage of the second process node through the transmission of the processing process; extract the contribution weight of each damage indicator of the first process node to various damage indicators of the second process node through model training and historical data fitting, for example, the thermal deformation of the first process node may have an amplifying effect on the vibration amplitude of the second process node, and the vibration stress of the first process node may aggravate the thermal stress concentration of the second process node; quantify the above analysis results into the first damage superposition effect coefficient as a parameter to describe the degree of influence of the damage of the first process node on the second process node.

[0042] Furthermore, with the goal of minimizing the damage index of the node to be optimized, the node process parameters of the node to be optimized are optimized to generate a process parameter optimization result, including: A node parameter control memory library of the node to be optimized is established; based on the node parameter control memory library, the node process parameters of the node to be optimized are optimized with the goal of minimizing the damage index of the node to be optimized, and the process parameter optimization result is generated.

[0043] By collecting historical process parameter data related to the node to be optimized, the corresponding damage indicators and related process environment information, a node parameter control memory library is formed. The memory library contains the correspondence between node process parameters (such as processing temperature, cutting speed, feed rate, etc.), external environmental parameters (such as equipment performance, raw material characteristics, etc.) and node damage indicators (such as thermal damage risk value, vibration damage risk value, etc.), and through data cleaning and normalization processing, the structuring and availability of the memory library are ensured.

[0044] With the goal of minimizing the damage index of the node to be optimized, an optimization model is constructed, and an appropriate algorithm (such as genetic algorithm, particle swarm optimization algorithm or gradient descent method) is selected to optimize the node process parameters. During the optimization process, the memory library is used as a parameter reference basis. By calling the historical data and parameter combinations in the memory library, the effective process parameter range for reducing the damage index is preliminarily screened. On this basis, combined with the current damage characteristics and process requirements of the node to be optimized, the parameters are further adjusted, such as reducing the processing temperature to reduce thermal damage, or optimizing the feed speed to reduce the impact of vibration. The optimization model takes minimization of the damage index as the objective function, and at the same time includes constraints such as production efficiency and equipment performance into the optimization range to ensure that the optimization results have both theoretical optimality and practical operability. Through the solution process of the optimization model, the optimal process parameter combination of the node to be optimized is output, such as the precise value of the adjusted processing temperature, cutting speed or feed rate. These optimization results will be directly used for the process parameter adjustment of the node to be optimized and recorded in the node parameter control memory library as the basic data for subsequent optimization and iteration.

[0045] In summary, the embodiments of the present application have at least the following technical effects: First, obtain multiple process nodes of the target saw blade, and saw blade morphology information corresponding to the multiple process nodes. Then, perform thermal sensitivity and vibration sensitivity analysis based on the saw blade morphology information corresponding to the multiple process nodes, and generate multiple thermal sensitivity parameters and multiple vibration sensitivity parameters corresponding to the multiple process nodes. Further, obtain multiple node process parameters currently used by the multiple process nodes. Then, perform node saw blade processing damage analysis based on multiple node process parameters, multiple thermal sensitivity parameters and multiple vibration sensitivity parameters, and generate multiple damage indicators. Finally, based on multiple damage indicators, locate the nodes to be optimized, and optimize and adjust the node process parameters of the nodes to be optimized. The technical problems of unstable processing quality and low production efficiency in the saw blade production process in the prior art are solved, and the technical effect of improving the saw blade processing quality and production efficiency is achieved.

[0046] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0048] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. An adaptive process parameter adjustment method for saw blade production, characterized in that: The method comprises: Acquire multiple process nodes of a target saw blade and saw blade morphology information corresponding to the multiple process nodes; Performing thermal sensitivity and vibration sensitivity analysis based on saw blade morphology information corresponding to the plurality of process nodes, and generating a plurality of thermal sensitivity parameters and a plurality of vibration sensitivity parameters corresponding to the plurality of process nodes; Acquire multiple node process parameters currently used by the multiple process nodes; Perform node saw blade processing damage analysis in combination with the plurality of node process parameters, the plurality of thermal sensitivity parameters, and the plurality of vibration sensitivity parameters to generate a plurality of damage indicators; Based on the multiple damage indicators, the nodes to be optimized are located, and the node process parameters of the nodes to be optimized are optimized and adjusted.

2. The method for adaptively adjusting process parameters in saw blade production according to claim 1, characterized in that: Performing thermal sensitivity and vibration sensitivity analysis based on the saw blade morphology information corresponding to the multiple process nodes to generate multiple thermal sensitivity parameters and multiple vibration sensitivity parameters corresponding to the multiple process nodes includes: Perform saw blade deformation influence analysis at different temperatures based on saw blade morphology information corresponding to the multiple process nodes to generate the multiple thermal sensitivity parameters; The saw blade deformation influence analysis under different vibration intensities is performed based on the saw blade morphology information corresponding to the multiple process nodes to generate the vibration sensitivity parameter.

3. The method for adaptively adjusting process parameters in saw blade production according to claim 1, characterized in that: The node saw blade processing damage analysis is performed in combination with the multiple node process parameters, the multiple thermal sensitivity parameters and the multiple vibration sensitivity parameters to generate multiple damage indicators, including: Based on the temperature prediction and vibration prediction during processing of the plurality of node process parameters, a plurality of saw blade surface temperature data and a plurality of saw blade vibration data are generated; Performing a thermal damage risk analysis based on the plurality of saw blade surface temperature data and the plurality of thermal sensitivity parameters to generate a plurality of thermal damage risk indicators; Performing vibration damage risk analysis based on the plurality of saw blade vibration data and the plurality of vibration sensitivity parameters to generate a plurality of vibration damage risk indicators; Based on the multiple thermal damage risk indicators and the multiple vibration damage risk indicators, a fusion analysis of thermal damage and vibration damage is performed on the multiple process nodes to generate the multiple damage indicators.

4. The method for adaptively adjusting process parameters in saw blade production according to claim 3, characterized in that: Based on the multiple thermal damage risk indicators and the multiple vibration damage risk indicators, a fusion analysis of thermal damage and vibration damage is performed on the multiple process nodes to generate the multiple damage indicators, including: Connect to the saw blade production monitoring system to collect the historical saw blade temperature record data set, historical saw blade vibration record data set and corresponding historical saw blade production quality record set at each process node; Analyze the historical saw blade temperature record data set and the historical saw blade vibration record data set to establish a historical thermal damage risk indicator set and a historical vibration damage risk indicator set; Training the damage fusion weight of each process node based on the historical saw blade production quality record set, the historical thermal damage risk indicator set, and the historical vibration damage risk indicator set; Generate the corresponding damage fusion layer based on the indicator fusion weight of each process node; The thermal damage and vibration damage of the multiple process nodes are fused by using the damage fusion layer of each process node to generate the multiple damage indicators.

5. The method for adaptively adjusting process parameters in saw blade production according to claim 3, characterized in that: A thermal damage risk analysis is performed based on the plurality of saw blade surface temperature data and the plurality of thermal sensitivity parameters to generate a plurality of thermal damage risk indicators, including: Taking the multiple thermal sensitivity parameters as constraints, collecting historical saw blade surface temperature records and historical saw blade damage parameters corresponding to the multiple process nodes; Based on the historical saw blade surface temperature records and historical saw blade damage parameters, the relationship between the saw blade surface temperature and the saw blade deformation parameters is identified to generate multiple node damage identification layers; The plurality of saw blade surface temperature data are input into the plurality of node damage identification layers for damage risk identification to generate the plurality of thermal damage risk indicators.

6. The method for adaptively adjusting process parameters in saw blade production according to claim 1, characterized in that: Based on the multiple damage indicators, the node to be optimized is located, and the node process parameters of the node to be optimized are optimized and adjusted, including: Conduct full-process fusion impact analysis on the multiple damage indicators and locate nodes to be optimized; Taking the damage index of the node to be optimized as the minimum, optimizing the node process parameters of the node to be optimized, and generating a process parameter optimization result; The process parameters of the node to be optimized are adjusted based on the process parameter optimization result.

7. The method for adaptively adjusting process parameters in saw blade production according to claim 6, characterized in that: Perform full-process fusion impact analysis on the multiple damage indicators and locate the nodes to be optimized, including: A first process node and a second process node that are adjacent to each other among the plurality of process nodes, wherein the first process node is located before the second process node; Performing damage superposition effect analysis on the first process node and the second process node to generate a first damage superposition effect coefficient, wherein the first damage superposition effect coefficient represents the influence of the damage index of the first process node on the damage index of the second process node; After optimizing the multiple damage indicators using the first damage superposition effect coefficient, a process node whose optimized damage indicator is greater than a preset damage indicator is located to generate the node to be optimized.

8. The method for adaptively adjusting process parameters in saw blade production according to claim 6, characterized in that: Taking the damage index of the node to be optimized as the minimum as the goal, the node process parameters of the node to be optimized are optimized to generate a process parameter optimization result, including: Establishing a node parameter control memory library of the node to be optimized; Based on the node parameter control memory library, the node process parameters of the node to be optimized are optimized with the goal of minimizing the damage index of the node to be optimized, and the process parameter optimization result is generated.

Images