Intelligent compensation method and device for machining errors of large die gears

Abstract

The present invention discloses an intelligent compensation method and device for machining errors of large-module gears, and relates to the technical field of gear manufacturing. The method comprises: analyzing the original error of a target machining machine tool to obtain multiple error sources; establishing an error source-error type mapping, and constructing an error separation model; arranging sensor modules based on key parts of the target machining machine tool to obtain real-time error data, performing error separation in combination with an error separation model, and obtaining multiple single machining errors; performing interference analysis on multiple single machining errors, and dynamically adjusting the machining plan based on the error interference analysis results to achieve error compensation. The present invention solves the technical problem in the prior art that due to the large size of large-module gears, additional error interference will be generated on the machining machine tool, affecting the machining accuracy of the gear, and achieves the technical effect of improving the machining accuracy of the gear by performing error separation and performing error compensation on the machine tool parameters and the machining parameters respectively.

Description

Technical Field

[0001] The invention relates to the technical field of gear manufacturing, and in particular to an intelligent compensation method and device for machining errors of large-module gears. Background Art

[0002] Large modulus gears are a type of gear with special requirements. Their tooth width, number of teeth and tooth surface width are relatively large. They are usually used in heavy-duty, low-speed or high-speed transmission systems and special projects. Large gear processing machines can provide support carriers for the gears to be measured and additional devices, provide the necessary rotary motion and linear motion for measurement, and facilitate the adjustment and alignment of the measurement. However, due to the large size and inertia of the gears to be measured, additional error interference will be generated on the processing machine, such as guide rail errors, transmission chain errors, etc., affecting the overall processing accuracy of the gears. Summary of the invention

[0003] The present application provides an intelligent compensation method and device for large-module gear machining errors, which are used to solve the technical problem in the prior art that the large size of large-module gears will cause additional error interference to the machining machine tool, thereby affecting the gear machining accuracy.

[0004] The first aspect of the present application provides an intelligent compensation method for large-scale gear machining errors, the method comprising: analyzing the original error of a target machining machine tool, identifying the error source, and obtaining a plurality of error sources, wherein the plurality of error sources are divided into two categories: guide rail error and gear machining error; obtaining historical machining data of the target machining machine tool, establishing an error source-error type mapping in combination with the plurality of error sources, and constructing an error separation model according to the mapping relationship; obtaining key parts of the target machining machine tool based on the plurality of error sources, deploying sensor modules, and obtaining real-time error data based on the sensor modules; performing error separation based on the real-time error data in combination with the error separation model, and obtaining a plurality of single machining errors, wherein the plurality of single machining errors carry error position identifiers and numerical information; performing interference analysis on the plurality of single machining errors, and obtaining error interference analysis results; dynamically adjusting the machining plan based on the plurality of single machining errors and the error interference analysis results to achieve error compensation.

[0005] The second aspect of the present application provides an intelligent compensation device for large-scale gear processing errors, the device comprising: an error source identification module, the error source identification module is used to analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources, the multiple error sources are divided into two categories: guide rail error and gear processing error; an error separation model construction module, the error separation model construction module is used to obtain the historical processing data of the target processing machine tool, combine the multiple error sources, establish an error source-error type mapping, and construct an error separation model according to the mapping relationship; a real-time error data acquisition module, the real-time error data acquisition module is used to obtain the target based on the multiple error sources. A sensor module is arranged at a key part of a processing machine tool, and real-time error data is acquired based on the sensor module; an error separation module is used to perform error separation according to the real-time error data in combination with the error separation model, and acquire multiple single processing errors, wherein the multiple single processing errors carry error position identifiers and numerical information; an error interference analysis module is used to perform interference analysis on the multiple single processing errors and acquire error interference analysis results; an error compensation module is used to dynamically adjust the processing plan based on the multiple single processing errors and the error interference analysis results to achieve error compensation.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The intelligent compensation method and device for large-module gear processing errors provided in the present application relate to the field of gear manufacturing technology. The method and device obtain multiple error sources by analyzing the original errors of a target processing machine tool, and construct an error separation model to obtain real-time error data. Error separation is performed in combination with the error separation model to obtain multiple single processing errors. Interference analysis is performed on the multiple single processing errors, and based on the error interference analysis results, the processing plan is dynamically adjusted to achieve error compensation. The technical problem in the prior art that the large size of large-module gears will cause additional error interference to the processing machine tool, thereby affecting the gear processing accuracy, is solved. The technical effect of improving the gear processing accuracy by performing error compensation on the machine tool parameters and the processing parameters respectively through error separation is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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.

[0009] Figure 1A schematic flow chart of the intelligent compensation method for machining errors of large-module gears provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the process of constructing an error separation model in the intelligent compensation method for large-module gear machining errors provided in an embodiment of the present application.

[0011] Figure 3 This is a schematic diagram of the structure of the intelligent compensation device for large-module gear machining errors provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: error source identification module 11 , error separation model construction module 12 , real-time error data acquisition module 13 , error separation module 14 , error interference analysis module 15 , error compensation module 16 . DETAILED DESCRIPTION

[0013] The present application provides an intelligent compensation method and device for large-module gear machining errors, which are used to solve the technical problem in the prior art that the large size of large-module gears will cause additional error interference to the machining machine tool, thereby affecting the gear machining accuracy.

[0014] 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.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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 that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] Embodiment 1

[0017] like Figure 1 As shown, the present application provides an intelligent compensation method for machining errors of large-module gears, the method comprising:

[0018] P10: Analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources. The multiple error sources are divided into two categories: guide rail error and gear processing error.

[0019] Furthermore, step P10 of the embodiment of the present application further includes:

[0020] P11: Obtain the original error data set of the target processing machine tool, perform central trend analysis, and obtain multiple high-frequency error categories; P12: Based on the multiple high-frequency error categories, perform error tracing and obtain the multiple error sources; P13: Perform cluster analysis on the multiple error sources to obtain the guide rail error set and gear processing error set. The guide rail error set includes but is not limited to straightness error, parallelism error, verticality error, flatness error, rolling or sliding friction error, and the gear processing error set includes but is not limited to cutting force fluctuation error, tool wear error, thermal deformation error, programming and positioning error.

[0021] It should be understood that a comprehensive analysis of the target processing machine tool identifies multiple error sources that affect its processing accuracy. These error sources are divided into two categories: guideway errors and gear processing errors. Guideway errors mainly affect the overall stability and motion accuracy of the machine tool, while gear processing errors are directly related to the processing quality of the gear.

[0022] Specifically, the original error data set of the target processing machine tool is first collected. This data set contains various error records of the machine tool during long-term operation and is the basis for subsequent analysis. Then, the original error data set is processed using the central tendency analysis method in statistics (such as mean, median, etc.) to identify frequently occurring high-frequency error categories. The high-frequency error category usually represents the most common error type in the machine tool processing process and has a significant impact on the processing accuracy.

[0023] Furthermore, based on the identified high-frequency error categories, error tracing is performed. The error tracing is a reverse analysis process. By tracing the root causes of the errors, the specific factors that cause these high-frequency errors, i.e., the error sources, can be revealed. For example, through the knowledge of the mechanical structure, kinematic principles, material properties, etc. of the machine tool, combined with previous error detection records, comprehensive analysis and judgment can be performed to identify and obtain multiple error sources.

[0024] Furthermore, cluster analysis is performed on the identified multiple error sources. Cluster analysis is an unsupervised learning method that can group similar objects together to discover the inherent structure and regularity in the data. In the present application, according to the nature and characteristics of the error sources, they are divided into two categories: guide rail error set and gear processing error set. Among them, the guide rail error set mainly focuses on the errors related to the machine tool guide rail system, including but not limited to straightness error (i.e., the degree of deviation of the linear motion of the guide rail), parallelism error (deviation of the parallel relationship between the guide rails), verticality error (deviation of the vertical relationship between the guide rails), flatness error (error caused by insufficient flatness of the guide rail surface), and rolling or sliding friction error (error caused by friction during the movement of the guide rail). These errors directly affect the motion accuracy and stability of the machine tool.

[0025] On the other hand, the gear machining error set focuses on errors directly related to the gear machining process, including but not limited to cutting force fluctuation error (error caused by unstable cutting force during cutting), tool wear error (error caused by tool wear due to long-term use), thermal deformation error (error caused by shape change of machine tool or workpiece due to temperature change), and programming and positioning error (error caused by inaccurate CNC programming or machine tool positioning). These errors are directly related to the machining quality and accuracy of the gear.

[0026] By classifying the complex error sources into two categories: guide rail error and gear processing error, it can provide guidance and data basis for the subsequent establishment of error models, error separation and compensation.

[0027] P20: Acquire historical processing data of the target processing machine tool, combine the multiple error sources, establish an error source-error type mapping, and construct an error separation model based on the mapping relationship.

[0028] Further, such as Figure 2 As shown, step P20 of the embodiment of the present application also includes:

[0029] P21: Acquire historical processing data of the target processing machine tool, wherein the historical processing data includes processing error data of multiple historical processing processes and corresponding error analysis data; P22: Perform regression analysis based on the processing error data and error analysis data, and establish an error source-error type mapping; P23: According to the historical processing data, respectively extract error source-related features corresponding to the multiple error sources, and screen and obtain multiple strongly correlated feature sets; P24: Based on the multiple strongly correlated feature sets of the multiple error sources, collect sample feature data for training to obtain the error separation model.

[0030] Optionally, by collecting historical processing data of the machine tool and combining it with the identified error sources, a mapping relationship between the error sources and specific error types, i.e., error source-error type mapping, is established. Based on this mapping relationship, an error separation model is constructed to separate single errors from complex processing errors.

[0031] Specifically, first, the historical processing data of the target processing machine tool is comprehensively collected. The historical processing data not only includes the processing error data in multiple historical processing processes, that is, the deviation between the actual processing results and the ideal state, but also includes the corresponding error analysis data, such as detailed records of the cause of the error, the degree of influence, etc. Further, regression analysis is performed based on the processing error data and error analysis data. Regression analysis aims to reveal the quantitative relationship between variables, and establishes a mapping between error sources and error types by fitting the functional relationship between one or more independent variables (here, error sources) and dependent variables (error types). This mapping relationship can help us understand how different error sources affect processing errors and predict the types of errors that may occur under specific conditions.

[0032] Furthermore, according to the historical processing data, the relevant features corresponding to each error source, namely the error source related features, are extracted respectively. These features may be physical quantities, process parameters or other quantifiable indicators directly related to the error source. At the same time, in order to improve the accuracy and efficiency of the model, the corresponding strongly correlated feature set is screened out from the error source related features corresponding to each error source through correlation analysis, principal component analysis (PCA), etc. Strongly correlated features refer to features that are highly correlated with the error type and can more accurately reflect the impact of the error source on the error type.

[0033] Furthermore, based on the strongly correlated feature sets of the selected multiple error sources, sample feature data are collected respectively, and the sample feature data are used as training data, combined with machine learning or deep learning algorithms, such as neural networks, support vector machines (SVM), etc., to perform supervised training until the model converges. Through training, an error separation model that can accurately separate different error sources is obtained. This model can automatically identify and separate each error source and the corresponding error value when receiving new processing error data, providing accurate data support for subsequent error compensation.

[0034] P30: Based on the multiple error sources, key parts of the target processing machine tool are obtained, sensor modules are deployed, and real-time error data is obtained based on the sensor modules.

[0035] Specifically, based on the multiple error sources and combined with the mechanical structure and kinematic principles of the machine tool, the impact paths of the multiple error sources on the machine tool processing accuracy are obtained, so as to determine the key parts of the target processing machine tool, that is, the machine tool components that are directly related to the error source and whose state changes will significantly affect the processing quality, such as the guide rail system, spindle, transmission mechanism, etc.

[0036] Furthermore, sensor modules are deployed for the key parts of the target processing machine tool. The sensor module is a system composed of multiple sensors, which is used to sense and measure the state parameters of the key parts of the machine tool in real time. According to the specific characteristics of the key parts and the influence mechanism of the error source, multiple sensor types, such as displacement sensors, temperature sensors, vibration sensors, etc., are selected and installed at the key positions of the machine tool. These sensors can capture various physical quantity changes during the operation of the machine tool in real time, such as displacement deviation, temperature change, vibration amplitude, etc., and provide basic data for subsequent error analysis.

[0037] Furthermore, based on the sensor module, the real-time state parameters of the target gear are obtained, converted into digital signals, and transmitted to the data processing unit. The data processing unit pre-processes the received data, including filtering, denoising, calibration, etc., and obtains a real-time gear model after virtual modeling based on the pre-processed data. The real-time gear model is compared with the standard gear model at multiple points to obtain real-time error data of the target gear at multiple points. Among them, the standard gear model is an ideal gear model constructed according to the design parameters of the target gear, and the multiple points are the key error detection parts of the target gear, which can be determined based on the gear processing experience data.

[0038] P40: According to the real-time error data, error separation is performed in combination with the error separation model to obtain multiple single processing errors, wherein the multiple single processing errors are provided with error position identifiers and numerical value information.

[0039] Optionally, the real-time error data is subjected to error source related feature extraction to obtain real-time error source feature data. These features should be consistent with the features used in the previous training of the error separation model so that the model can accurately identify and process real-time data. Further, the extracted real-time error source feature data is used as input and input into the error separation model for error separation. The model will perform calculations based on these features and output multiple estimated values ​​of single processing errors. The single errors may include guide rail errors, spindle errors, tool errors, errors caused by cutting force fluctuations, and thermal deformation errors. The multiple single processing errors not only represent the degree of influence of each error source, but also carry error position identification, that is, clearly indicate which part of the machine tool or which processing link the error occurs. At the same time, each single processing error is also accompanied by specific numerical information, which intuitively reflects the size and severity of the error. Through these numerical values, the operator can clearly understand the main problems and weak links in the current processing process, and then take targeted measures to improve and optimize.

[0040] By using the error separation model to deeply process the real-time error data, the complex error signal can be decomposed into multiple specific single processing errors, providing accurate data support for subsequent error compensation and processing optimization.

[0041] P50: Perform interference analysis on the multiple single processing errors to obtain error interference analysis results.

[0042] Furthermore, step P50 of the embodiment of the present application also includes:

[0043] P51: Extract multiple target processing error sources for the multiple single processing errors; P52: Perform correlation analysis based on the multiple target processing error sources to generate multiple error source influencing factors; P53: Perform error sensitivity analysis based on the multiple target processing error sources through the control variable method to obtain error sensitivity analysis results; P54: Combine the multiple error source influencing factors and the error sensitivity analysis results to obtain the error interference analysis results.

[0044] In a possible embodiment of the present application, interference analysis between each error source is performed for the multiple single processing errors to obtain the interaction between each single processing error and its comprehensive impact on the processing process. First, the target processing error sources that are currently occurring in real time and have a significant impact on the processing quality are extracted from the multiple single processing errors. These error sources are dynamically changing and are constantly updated as the processing conditions and environment change, but the number is usually less than the total number of error sources that may exist in the machine tool. Extracting the target error source helps to focus on the main problem and avoid falling into information redundancy in subsequent analysis.

[0045] Furthermore, a correlation analysis was performed based on the extracted multiple target processing error sources. By using statistical and machine learning methods, the mutual influence relationship between the error sources was quantified to generate multiple error source influence factors. The multiple error source influence factors are quantitative expressions of the interaction strength between the error sources, which can reflect the degree of mutual interference between different error sources.

[0046] Furthermore, the control variable method is used to perform error sensitivity analysis on the multiple target processing error sources. The control variable method is a commonly used experimental design method, which observes the influence of a variable on the experimental results by changing the value of a certain variable one by one while keeping other variables unchanged. In the present application, by adjusting the value of each target error source one by one and observing its contribution and change trend to the processing error, the sensitivity of the error source to the processing accuracy is evaluated, thereby obtaining the error sensitivity analysis results. The error sensitivity analysis results can reflect the types of error sources that have a significant impact on the processing error, and serve as the focus of subsequent optimization and adjustment.

[0047] Finally, the error interference analysis results are obtained by combining the influencing factors of multiple error sources and the error sensitivity analysis results. This result not only reflects the interaction between the error sources, but also clarifies the sensitivity of the influence of each error source on the processing error, which can provide a basis for formulating effective error compensation strategies and optimizing processing parameters.

[0048] P60: Based on the multiple individual processing errors and the error interference analysis results, the processing plan is dynamically adjusted to achieve error compensation.

[0049] Furthermore, step P60 of the embodiment of the present application also includes:

[0050] P61: Based on the error interference analysis result, obtain the error sensitivity analysis result; P62: Obtain the error values ​​of the multiple single processing errors, and perform single error impact assessment in combination with the error sensitivity analysis result to obtain the error impact assessment result; P63: According to the error impact assessment result, prioritize the multiple single processing errors to obtain an error compensation priority sequence; P64: With reference to the error compensation priority sequence, in combination with the multiple error source influencing factors, dynamically adjust the processing plan to perform error compensation for the multiple single processing errors.

[0051] It should be understood that the multiple single processing errors and the error interference analysis results are used to dynamically adjust the processing plan to achieve error compensation during the processing. Specifically, based on the error interference analysis results, the error sensitivity analysis results are further extracted. The error sensitivity analysis structure reveals the degree of influence of different error sources on the processing accuracy, that is, which error sources have a more significant impact on the final processing results.

[0052] Furthermore, the specific values ​​of multiple single processing errors are obtained, and the single error impact assessment is performed in combination with the error sensitivity analysis results, that is, the numerical values ​​of multiple single processing errors and the sensitivity of the errors are comprehensively considered to perform a comprehensive impact assessment on the overall processing quality. Exemplarily, the weighted sum method can be used to multiply the numerical value of the single error by its sensitivity coefficient to obtain the weighted value of each error, and then all weighted values ​​are summed or sorted to reflect the comprehensive impact of each single error. In addition, the evaluation results can be further verified and optimized in combination with expert experience, historical data, simulation analysis and other methods to obtain error impact assessment results.

[0053] Furthermore, according to the comprehensive impact values ​​of multiple single processing errors in the error impact assessment results, multiple single processing errors are prioritized to generate an error compensation priority sequence. This sequence clarifies which error sources should be solved first under limited resources to ensure the maximum improvement of processing quality. The sorting process can also use a variety of algorithms, such as hierarchical analysis method, fuzzy comprehensive evaluation method, etc., to ensure the rationality and scientificity of the sorting results.

[0054] Finally, referring to the error compensation priority sequence and combining multiple error source influencing factors, the processing plan is dynamically adjusted, including optimization of machine tool parameters, processing technology, tool selection, etc. By adjusting the relevant parameters and strategies in the processing plan, effective compensation for multiple single processing errors is achieved, ensuring that the adjustment measures can work together to improve the processing quality.

[0055] Furthermore, step P64 of the embodiment of the present application also includes:

[0056] P64-1: Based on the error compensation priority sequence, traverse multiple single compensation errors in turn to adjust the processing parameters and obtain a first compensation scheme; P64-2: For the first compensation scheme, correct the compensation result according to the multiple error source influencing factors to obtain a second compensation scheme; P64-3: According to the second compensation scheme, dynamically adjust the processing scheme, including adjusting the machine tool parameters and cutting parameters to achieve processing error compensation.

[0057] Specifically, referring to the error compensation priority sequence and the multiple error source influencing factors, the specific process of dynamically adjusting the processing scheme can be to first follow the order of the error compensation priority sequence, and make preliminary adjustments to the processing parameters for each single compensation error one by one, to ensure that the error source with the greatest impact on the processing quality is solved first. For each single error, we use expert systems, machine learning models or optimization algorithms to calculate and determine the optimal processing parameter adjustment amount, such as feed speed, cutting depth, spindle speed, etc., to minimize the impact of the error. By traversing all single errors and completing the corresponding parameter adjustments, a preliminary first compensation scheme is obtained.

[0058] Furthermore, on the basis of the first compensation scheme, the mutual influence relationship between multiple error sources is further considered. By introducing the error source influence factor, the indirect influence that each error source may have during the adjustment process is evaluated, and the first compensation scheme is corrected as necessary. Exemplarily, a mathematical model or simulation tool is used to establish a model based on historical data, experimental results or expert experience, and the error changes under different compensation strategies are simulated to quantify the specific influence of each error source influence factor on the processing error. Then, based on the quantified results of the error source influence factor, the compensation parameters in the first compensation scheme are adjusted, including machine tool parameter adjustment, such as modifying the geometric accuracy, stiffness adjustment, thermal compensation strategy, etc. of the machine tool to offset the changes in the dynamic characteristics of the machine tool caused by the mutual influence of the error sources. Cutting parameter adjustment is performed to adjust the cutting speed, feed rate, cutting depth, etc. to reduce the problems of cutting force fluctuation, thermal deformation, etc. caused by the mutual influence of the error sources during the cutting process. Additional compensation measures are introduced, such as adding an error compensation device, adjusting the tool path, or adopting a more advanced control algorithm, etc., to more comprehensively consider the mutual influence between the error sources. At the same time, the adjusted compensation scheme is verified using simulation software. By simulating the machining process, we can observe whether the mutual influence between the error sources is effectively controlled and whether the target error is further reduced. If the simulation results show that there are still deficiencies, we return to the previous step for iterative optimization until a satisfactory compensation effect is achieved, thereby generating a second compensation solution.

[0059] Furthermore, under the guidance of the second compensation scheme, the processing scheme is dynamically adjusted. This adjustment process is not limited to the adjustment of cutting parameters, but also includes the comprehensive optimization of machine tool parameters. According to the specific parameter settings in the second compensation scheme, the key components of the machine tool, such as the feed system, spindle system, and cooling system, are adjusted accordingly. At the same time, the tool path, cutting speed, cutting depth and other parameters in the cutting process are adjusted to ensure the stability and accuracy of the processing process. Through the implementation of the above dynamic adjustment measures, effective compensation for multiple single processing errors is achieved, and the processing quality and efficiency of large mold gears are improved.

[0060] In summary, the embodiments of the present application have at least the following technical effects:

[0061] This application obtains multiple error sources by analyzing the original errors of the target processing machine tool, and constructs an error separation model to obtain real-time error data. It performs error separation in combination with the error separation model to obtain multiple single processing errors, performs interference analysis on multiple single processing errors, and dynamically adjusts the processing plan based on the error interference analysis results to achieve error compensation.

[0062] The technical effect of improving gear machining accuracy by performing error compensation for machine tool parameters and machining parameters respectively through error separation is achieved.

[0063] Embodiment 2

[0064] Based on the same inventive concept as the intelligent compensation method for machining errors of large die gears in the aforementioned embodiment, Figure 3 As shown, the present application provides an intelligent compensation device for machining errors of large-scale gears, and the device and method embodiments in the present application are based on the same inventive concept. The device includes:

[0065] The error source identification module 11 is used to analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources. The multiple error sources are divided into two categories: guide rail error and gear processing error.

[0066] The error separation model building module 12 is used to obtain the historical processing data of the target processing machine tool, combine the multiple error sources, establish an error source-error type mapping, and build an error separation model according to the mapping relationship.

[0067] The real-time error data acquisition module 13 is used to acquire key parts of the target processing machine tool based on the multiple error sources, deploy sensor modules, and acquire real-time error data based on the sensor modules.

[0068] The error separation module 14 is used to perform error separation according to the real-time error data in combination with the error separation model to obtain multiple single processing errors, wherein the multiple single processing errors are provided with error position identifiers and numerical value information.

[0069] The error interference analysis module 15 is used to perform interference analysis on the multiple single processing errors and obtain error interference analysis results.

[0070] The error compensation module 16 is used to dynamically adjust the processing plan based on the multiple single processing errors and the error interference analysis results to achieve error compensation.

[0071] Furthermore, the error source identification module 11 is further configured to perform the following steps:

[0072] The original error data set of the target processing machine tool is obtained, and a central trend analysis is performed to obtain multiple high-frequency error categories; based on the multiple high-frequency error categories, error tracing is performed to obtain the multiple error sources; cluster analysis is performed on the multiple error sources to obtain the guide rail error set and the gear processing error set. The guide rail error set includes but is not limited to straightness error, parallelism error, verticality error, flatness error, rolling or sliding friction error, and the gear processing error set includes but is not limited to cutting force fluctuation error, tool wear error, thermal deformation error, programming and positioning error.

[0073] Furthermore, the error separation model building module 12 is also used to perform the following steps:

[0074] Acquire historical processing data of a target processing machine tool, wherein the historical processing data includes processing error data of multiple historical processing processes and corresponding error analysis data; perform regression analysis based on the processing error data and error analysis data, and establish an error source-error type mapping; extract error source-related features corresponding to the multiple error sources respectively according to the historical processing data, and screen and obtain multiple strongly correlated feature sets; based on the multiple strongly correlated feature sets of the multiple error sources, collect sample feature data for training, and obtain the error separation model.

[0075] Furthermore, the error interference analysis module 15 is further configured to perform the following steps:

[0076] Extract multiple target processing error sources for the multiple single processing errors; perform correlation analysis based on the multiple target processing error sources to generate multiple error source influencing factors; perform error sensitivity analysis based on the multiple target processing error sources through a control variable method to obtain error sensitivity analysis results; and obtain the error interference analysis results by combining the multiple error source influencing factors and the error sensitivity analysis results.

[0077] Furthermore, the error compensation module 16 is further configured to perform the following steps:

[0078] Based on the error interference analysis result, the error sensitivity analysis result is obtained; the error values ​​of the multiple single processing errors are obtained, and in combination with the error sensitivity analysis result, a single error impact assessment is performed to obtain an error impact assessment result; according to the error impact assessment result, the multiple single processing errors are prioritized to obtain an error compensation priority sequence; with reference to the error compensation priority sequence, in combination with the multiple error source influencing factors, the processing plan is dynamically adjusted to perform error compensation on the multiple single processing errors.

[0079] Furthermore, the error compensation module 16 is further configured to perform the following steps:

[0080] Based on the error compensation priority sequence, multiple single compensation errors are traversed in turn to adjust the processing parameters and obtain a first compensation scheme; for the first compensation scheme, the compensation result is corrected according to the multiple error source influencing factors to obtain a second compensation scheme; according to the second compensation scheme, the processing scheme is dynamically adjusted, including adjusting the machine tool parameters and the cutting parameters, to achieve processing error compensation.

[0081] 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. In addition, 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.

[0082] 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 should be included in the protection scope of the present application.

[0083] This specification and the 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 intelligent compensation method for machining errors of large die gears, characterized in that: The method comprises: Analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources, which are divided into two categories: guide rail error and gear processing error; Acquire historical processing data of the target processing machine tool, establish an error source-error type mapping based on the multiple error sources, and construct an error separation model based on the mapping relationship; Based on the multiple error sources, key parts of the target processing machine tool are obtained, sensor modules are arranged, and real-time error data is obtained based on the sensor modules; According to the real-time error data, error separation is performed in combination with the error separation model to obtain a plurality of single processing errors, wherein the plurality of single processing errors are provided with error position identifiers and numerical value information; Perform interference analysis on the multiple single processing errors to obtain error interference analysis results; Based on the multiple single processing errors and the error interference analysis results, dynamically adjust the processing plan to achieve error compensation; Acquire historical processing data of the target processing machine tool, combine the multiple error sources, establish an error source-error type mapping, and construct an error separation model based on the mapping relationship, including: Acquire historical processing data of a target processing machine tool, wherein the historical processing data includes processing error data of multiple historical processing processes and corresponding error analysis data; Perform regression analysis based on the machining error data and the error analysis data to establish an error source-error type mapping; Extracting error source related features corresponding to the multiple error sources respectively according to the historical processing data, and screening to obtain multiple strongly correlated feature sets; Based on the multiple strongly correlated feature sets of the multiple error sources, sample feature data is collected for training to obtain the error separation model.

2. The large-module gear machining error intelligent compensation method according to claim 1 is characterized in that: Analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources, including: Obtain the original error data set of the target processing machine tool, perform central trend analysis, and obtain multiple high-frequency error categories; Based on the multiple high-frequency error categories, error tracing is performed to obtain the multiple error sources; Cluster analysis is performed on the multiple error sources to obtain a guide rail error set and a gear processing error set.

3. The intelligent compensation method for machining errors of large mold gears according to claim 2, characterized in that: The guide rail error set includes but is not limited to straightness error, parallelism error, perpendicularity error, flatness error, rolling or sliding friction error, and the gear processing error set includes but is not limited to cutting force fluctuation error, tool wear error, thermal deformation error, programming and positioning error.

4. The intelligent compensation method for machining errors of large-module gears according to claim 1, characterized in that: Perform interference analysis on the multiple single processing errors to obtain error interference analysis results, including: extracting a plurality of target machining error sources for the plurality of single machining errors; Performing correlation analysis based on the multiple target machining error sources to generate multiple error source influencing factors; Performing an error sensitivity analysis based on the multiple target machining error sources by a control variable method to obtain an error sensitivity analysis result; The error interference analysis result is obtained by combining the multiple error source influencing factors and the error sensitivity analysis result.

5. The intelligent compensation method for machining errors of large mold gears as claimed in claim 4 is characterized in that: Based on the multiple single processing errors and the error interference analysis results, dynamically adjusting the processing plan includes: Based on the error interference analysis result, obtaining the error sensitivity analysis result; Obtain error values ​​of the multiple single processing errors, and perform single error impact assessment in combination with the error sensitivity analysis result to obtain an error impact assessment result; According to the error impact assessment result, the plurality of single processing errors are prioritized to obtain an error compensation priority sequence; With reference to the error compensation priority sequence and in combination with the multiple error source influencing factors, the processing scheme is dynamically adjusted to perform error compensation on the multiple single processing errors.

6. The intelligent compensation method for machining errors of large-module gears according to claim 5, characterized in that: Referring to the error compensation priority sequence and combining the multiple error source influencing factors, the processing plan is dynamically adjusted, including: Based on the error compensation priority sequence, sequentially traverse multiple single compensation errors to adjust processing parameters and obtain a first compensation solution; For the first compensation scheme, correct the compensation result according to the multiple error source influencing factors to obtain a second compensation scheme; The processing scheme is dynamically adjusted according to the second compensation scheme, including adjusting the machine tool parameters and the cutting parameters, to achieve processing error compensation.

7. Intelligent compensation device for machining errors of large die gears, characterized in that: The device is used to implement the method according to any one of claims 1 to 6, and the device comprises: An error source identification module, which is used to analyze the original error of the target processing machine tool, identify the error source, and obtain multiple error sources, wherein the multiple error sources are divided into two categories: guide rail error and gear processing error; An error separation model building module, the error separation model building module is used to obtain historical processing data of the target processing machine tool, combine the multiple error sources, establish an error source-error type mapping, and build an error separation model according to the mapping relationship; A real-time error data acquisition module, the real-time error data acquisition module is used to acquire key parts of the target processing machine tool based on the multiple error sources, deploy sensor modules, and acquire real-time error data based on the sensor modules; An error separation module, the error separation module is used to perform error separation according to the real-time error data in combination with the error separation model to obtain a plurality of single processing errors, wherein the plurality of single processing errors are provided with error position identifiers and numerical value information; An error interference analysis module, the error interference analysis module is used to perform interference analysis on the multiple single processing errors and obtain error interference analysis results; An error compensation module is used to dynamically adjust the processing plan based on the multiple single processing errors and the error interference analysis results to achieve error compensation.

Images