Intelligent analysis decision method based on big data platform

Abstract

The invention discloses an intelligent analysis decision-making method based on a big data platform, and the method comprises the steps: S1, building a three-dimensional model of an initial machine tool, S2, changing the elastic modulus of each part of the initial machine tool, and S3, obtaining related data through a test: carrying out the rigidity test of the machine tool after the elastic modulus is changed each time, and obtaining the rigidity of the machine tool; the method comprises the steps of S1, recording position precision data, cutting force data or vibration data and the like of a machine tool under various conditions, S2, establishing a machine tool rigidity model: establishing a model for describing the machine tool rigidity according to the data obtained by testing, S5, establishing a linear regression equation model: determining factors of each change quantity having significant influence on the machine tool rigidity, and S5, establishing a linear regression equation model, and S6, outputting theoretical maximum rigidity data: determining a combination of one or more component materials and geometrical shapes to generate the maximum rigidity, further optimizing the rigidity of the machine tool, and finally performing experimental verification, thereby solving the problem that high-accuracy data is difficult to quickly obtain by calculation due to the influence of conditions and measurement errors on a test result.

Description

Technical Field

[0001] This invention relates to the field of CNC machine tool technology, and in particular to an intelligent analysis and decision-making method based on a big data platform. Background Technology

[0002] Currently, industrialized countries place great emphasis on the machine tool industry, vying to develop advanced mechatronics, high-precision, high-efficiency, and highly automated machine tools to accelerate industrial and national economic development. This reflects the crucial role of machine tools in driving industrial and national economic growth. Advanced machine tools not only enable high-precision and high-efficiency processing, thereby improving production efficiency, which for industrialized countries means producing high-quality products faster to meet market demands, but also reduce manual operation and lower labor costs through highly efficient and automated machine tools. Possessing advanced machine tool technology enhances a country's competitiveness in the international market.

[0003] Machine tool stiffness refers to the machine tool's ability to resist deformation under external forces. The greater the stiffness of a machine tool, the higher its dynamic accuracy. Machine tool stiffness includes the stiffness of the machine tool components themselves and the contact stiffness between the components. The stiffness of the machine tool components themselves mainly depends on the material properties, cross-sectional shape, and size of the components. The contact stiffness between components is not only related to the contact material, the geometric dimensions and hardness of the contact surface, but also to factors such as the surface roughness, geometric accuracy, machining method, contact medium, and preload of the contact surface.

[0004] In existing technologies, stiffness analysis of CNC machine tools employs multi-system theory, which involves complex data equations. This presents a high theoretical barrier for engineers and presents certain difficulties in solving the problems. Furthermore, the stiffness values ​​of the machine tool vary under different working conditions during the stiffness analysis process, requiring testing and analysis under multiple conditions. For example, under different cutting parameters, the relative stiffness of the machine tool will also change due to factors such as cutting torque. Experimental testing requires multiple comparisons to obtain the optimal solution, but the test results are affected by conditions and measurement errors, making it difficult to quickly obtain highly accurate data during the calculation process.

[0005] Therefore, this application provides an intelligent analysis and decision-making method based on a big data platform, offering machine tool design engineers a specific and operable approach. Summary of the Invention

[0006] This invention overcomes the shortcomings of existing technologies and provides an intelligent analysis and decision-making method based on a big data platform.

[0007] To achieve the above objectives, the technical solution adopted by this invention is: an intelligent analysis and decision-making method based on a big data platform, comprising the following steps:

[0008] S1. Establish the initial 3D model of the machine tool: Perform 3D modeling of the initial machine tool, import the model into the finite element simulation analysis software, establish each component and input material properties to generate the mesh;

[0009] S2. Change the elastic modulus of each component of the initial machine tool: By inputting different elastic material data for each component of the machine tool in the finite element simulation software, the elastic modulus can be changed, or the geometry of the component can be changed to change the elastic modulus.

[0010] S3. Obtain relevant data through testing: After each change in the elastic modulus, test the stiffness of the machine tool and record the positional accuracy data, cutting force data, or vibration data of the machine tool under various conditions.

[0011] S4. Establish a machine tool stiffness model: Based on the test data, establish a model describing the stiffness of the machine tool, and based on the distribution of the obtained data and the complexity of the machine tool model, establish a linear mathematical machine tool model.

[0012] S5. Establish a linear regression equation model: Analyze the test data using the linear regression equation model to determine the factors that affect the machine tool stiffness for each change.

[0013] S6. Output theoretical maximum stiffness data: Based on the linear regression model, determine the combination of materials and geometries of one or more components to produce the maximum stiffness, and then optimize the stiffness of the machine tool.

[0014] S7. Conduct experimental verification: Verify the machine tool stiffness optimized by the linear regression model through actual experiments, and determine whether the machine tool performance before and after optimization meets the expected performance by comparing the machine tool performance before and after optimization. If the expected performance is not met, rebuild the machine tool stiffness model by the linear regression model until the expected performance is met.

[0015] In a preferred embodiment of the present invention, in step S1, the finite element model is established by setting the four-sided foot structure at the bottom of the machine tool as fixed boundary conditions and performing mesh generation.

[0016] In a preferred embodiment of the present invention, after establishing the initial machine tool model in step S1, the assembled three-dimensional model of the machine tool is preliminarily verified to check the positional relationship of each component and ensure that the components are in the correct positions.

[0017] In a preferred embodiment of the present invention, step S1 involves geometric simplification of the initial model of the machine tool, removing structures that have a relatively small impact on the stiffness of large components in the machine tool through finite element analysis, including small chamfers, fillets, and small holes.

[0018] A CNC lathe model, based on the intelligent analysis and decision-making method based on a big data platform as described in any one of claims 1-5, includes: a bed, a fixed component disposed on the bed, and a machining component installed in cooperation with the fixed component;

[0019] The fixing assembly includes: a cradle, a workpiece spindle mounted on the cradle, and an X-saddle fixedly mounted below the cradle; each X-saddle is equipped with a first transmission unit, and each workpiece spindle is equipped with a clamp.

[0020] In a preferred embodiment of the present invention, a plurality of columns are symmetrically mounted on the bed, and a crossbeam is mounted on the plurality of columns. The machining assembly is mounted on the crossbeam. The machining assembly includes: a Y-saddle, a spindle box mounted on the Y-saddle, and a tool spindle disposed at the bottom of the spindle box.

[0021] In a preferred embodiment of the present invention, the first transmission unit includes: a plurality of first slide grooves and a first slide rail installed in each of the first slide grooves; the first slide grooves are symmetrically arranged on the bed, and the bottom of the X slide saddle is fitted onto the first slide rail.

[0022] In a preferred embodiment of the present invention, a second transmission unit is installed on the Y-saddle, and a tool magazine is installed on one side wall of the column. The second transmission unit includes: a plurality of second slide grooves, a second slide rail installed in the second slide grooves, and a Y-feed shaft installed between the plurality of second slide rails.

[0023] In a preferred embodiment of the present invention, a plurality of X feed axes are provided on the bed near the two side walls of the X slide saddle, and the Y slide saddle is concave. The spindle box is disposed on the inner wall of the Y slide saddle, and a plurality of Z feed axes are symmetrically installed on the two side walls of the spindle box.

[0024] In a preferred embodiment of the present invention, the Z-feed axis is mounted on the spindle box, and a transmission block is mounted on the Y-saddle, the transmission block being configured to cooperate on the Z-feed axis.

[0025] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0026] (1) This invention proposes an intelligent analysis and decision-making method based on a big data platform. An initial three-dimensional model of the machine tool is established. Then, different elastic material data of each component of the machine tool are input into the finite element simulation software to change the elastic modulus, or the geometry of the component is changed to change the elastic modulus. After each change, the stiffness of the machine tool is tested, and the position accuracy data, cutting force data, or vibration data of the machine tool under various conditions are recorded. A model describing the stiffness of the machine tool is established. The data obtained from the test is analyzed using a linear regression equation model to determine the factors that have a significant impact on the stiffness of the machine tool for each change, such as the elastic modulus of the component and cutting parameters. Based on the linear regression model, the combination of materials and geometry of one or more components is determined to produce the maximum stiffness, thereby optimizing the stiffness of the machine tool. Finally, experimental verification is carried out. This solves the problem that the stiffness value of the machine tool will be different under different working conditions during the stiffness analysis process, requiring testing and analysis under multiple conditions, and the test results are affected by conditions and measurement errors, making it difficult to quickly obtain accurate data.

[0027] (2) This invention uses a linear regression equation model to analyze the factors affecting the stiffness of machine tools. The linear regression equation determines whether the combination of materials and geometry of one or more components can produce the maximum stiffness. When the elastic modulus continues to change, the changed value is input into the linear regression model for calculation to obtain the optimal solution that produces the maximum stiffness. This optimizes the machine tool and solves the problem that the data equations used in the multi-system theory for stiffness analysis of CNC machine tools are relatively complex and have a high theoretical threshold for engineers, making it difficult to solve. Moreover, compared with traditional analog design and experience design, it greatly improves design efficiency and accuracy.

[0028] (3) This invention performs finite element simulation analysis on a lathe model, changes the elastic modulus, inputs different elastic modulus values, and obtains deformation result data. Engineers can obtain relevant data more intuitively, and then perform corresponding calculations on the structure based on the data results. This solves the problem that design decisions lack theoretical basis and it is difficult to provide specific basis for design optimization in the process of designing the structure. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart of a preferred embodiment of the present invention;

[0031] Figure 2 This is a structural diagram of a machine tool model according to a preferred embodiment of the present invention;

[0032] In the diagram: 1. Bed; 2. Column; 3. Crossbeam; 4. X-saddle; 5. Cradle; 6. Workpiece spindle; 7. Tool spindle; 8. Y-saddle; 9. Y-feed axis; 10. Z-feed axis; 11. X-feed axis. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein. Therefore, the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0035] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the scope of protection of this application. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0036] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this application based on the specific circumstances.

[0037] Example 1

[0038] like Figure 1 As shown, an intelligent analysis and decision-making method based on a big data platform includes the following steps:

[0039] S1. Establish the initial 3D model of the machine tool: Perform 3D modeling of the initial machine tool, import the model into the finite element simulation analysis software, establish each component and input material properties to generate the mesh;

[0040] S2. Change the elastic modulus of each component of the initial machine tool: By inputting different elastic material data for each component of the machine tool in the finite element simulation software, the elastic modulus can be changed, or the geometry of the component can be changed to change the elastic modulus.

[0041] S3. Obtain relevant data through testing: After each change in the elastic modulus, test the stiffness of the machine tool and record the positional accuracy data, cutting force data, or vibration data of the machine tool under various conditions.

[0042] S4. Establish a machine tool stiffness model: Based on the test data, establish a model describing the stiffness of the machine tool, and based on the distribution of the obtained data and the complexity of the machine tool model, establish a linear mathematical machine tool model.

[0043] S5. Establish a linear regression equation model: Analyze the test data using the linear regression equation model to determine the factors that affect the machine tool stiffness for each change.

[0044] S6. Output theoretical maximum stiffness data: Based on the linear regression model, determine the combination of materials and geometries of one or more components to produce the maximum stiffness, and then optimize the stiffness of the machine tool.

[0045] S7. Conduct experimental verification: Verify the machine tool stiffness optimized by the linear regression model through actual experiments, and determine whether the machine tool performance before and after optimization meets the expected performance by comparing the machine tool performance before and after optimization. If the expected performance is not met, rebuild the machine tool stiffness model by the linear regression model until the expected performance is met.

[0046] In step S1, the finite element model is established, and the four-sided foot structure at the bottom of the machine tool is set as a fixed boundary condition for mesh generation. After the initial machine tool model is established in step S1, the assembled three-dimensional model of the machine tool is initially verified to check the positional relationship of each component and ensure that the components are in the correct position. The initial model of the machine tool is geometrically simplified to remove structures with small stiffness finite element analysis impact on large components of the machine tool, including small chamfers, fillets, and small holes.

[0047] A CNC lathe model includes: a bed 1, a fixed assembly mounted on the bed 1, and machining components installed in conjunction with the fixed assembly, such as... Figure 2 As shown, the fixing assembly includes: a cradle 5, a workpiece spindle 6 mounted on the cradle 5, and an X-saddle 4 fixedly mounted below the cradle 5; each X-saddle 4 is equipped with a first transmission unit, and each workpiece spindle 6 is equipped with a clamp.

[0048] The bed 1 is symmetrically equipped with several columns 2, and a crossbeam 3 is installed on the columns 2. The machining assembly is installed on the crossbeam 3. The machining assembly includes: a Y-saddle 8, a spindle box installed on the Y-saddle 8, and a tool spindle 7 set at the bottom of the spindle box. The first transmission unit includes: several first slides, and a first slide rail installed in each first slide. The first slides are symmetrically arranged on the bed 1, and the bottom of the X-saddle 4 is fitted onto the first slide rail.

[0049] A second transmission unit is installed on the Y-saddle 8, and a tool magazine is installed on one side wall of the column 2. The second transmission unit includes: several second slide grooves, second slide rails installed in the second slide grooves, and a Y-feed axis 9 installed between the several second slide rails.

[0050] Several X feed axes 11 are provided on the two side walls of the bed 1 near the X slide 4, and the Y slide 8 is concave. The spindle box is located on the inner wall of the Y slide 8, and several Z feed axes 10 are symmetrically installed on the two side walls of the spindle box. The Z feed axes 10 are installed on the spindle box, and a transmission block is installed on the Y slide 8. The transmission block is fitted on the Z feed axes 10.

[0051] Example 2

[0052] Based on Example 1, the proposed analysis and decision-making method involves specific data calculations. First, according to the steps, different elastic material data are input into the finite element simulation software to change the elastic modulus of each machine tool component, or the geometry of the component is changed to change the elastic modulus. Based on the test data, a model describing the stiffness of the machine tool is obtained. Then, the model is experimentally verified using linear regression equations. The specific verification method is as follows:

[0053] Experiments were conducted by changing the machine tool thickness, the elastic modulus of the component, and the cutting rate. The stiffness data obtained under these conditions are shown in the table below. The predictor variables are the machine tool thickness, the elastic modulus of the component, and the cutting rate. The predictor is the machine tool stiffness.

[0054] Table 1 shows the stiffness data obtained by using the bed as the component and changing the elastic modulus of the bed.

[0055] <![CDATA[Machine tool thickness X1 (mm)]]> <![CDATA[Elastic modulus of the bed X2 (GPa)]]> <![CDATA[Cutting rate X3 (m / min)]]> Stiffness Y (N / m) 10 34.52 65.32 89.36 12 36.33 69.25 90.32 14 45.62 55.36 126.26 16 31.56 36.82 109.03 18 43.69 55.03 111.20 20 52.36 33.59 99.56

[0056] Using JMP7 software, a quadratic multiple regression was performed. Based on the data obtained in the table above, the least squares method was used to estimate the values ​​of each regression coefficient, resulting in the following model:

[0057] Stiffness Y = 118.35 + 26.34X1 - 24.58X2 + 48.05X3 - 9.65X1X2 + 55.36X1X3 - 39.15X2X3 - 61.08X1 2 -89.06X2 2 -136.21X3 2

[0058] Based on the regression equation, predictions were made using some data from the table above. These predictions were compared with measured values ​​to evaluate the accuracy of the stiffness model. Furthermore, it was determined that outliers significantly impacting the machine tool stiffness model were examined. After verification, it was confirmed that changes to the bed's elastic modulus had a significant effect on the machine tool's stiffness.

[0059] Linear regression equations are used to determine whether a combination of materials and geometries of one or more components can produce maximum stiffness. The table above shows that, in the test data, the stiffness value is highest when X1 = 14 mm, X2 = 45.62 GPa, and X3 = 55.36 m / min. When the elastic modulus of the components continues to change, such as changing the elastic modulus of the spindle box or the Z-axis slide saddle, the changed values ​​are input into the linear regression model for calculation to obtain the optimal solution that produces the maximum stiffness. This allows for optimization of the machine tool, solving the problem that machine tools require multi-state testing and analysis under different working conditions, and that test results are affected by conditions and measurement errors, making it difficult to quickly obtain accurate data during calculation. Furthermore, compared to traditional analogical design and experience-based design, this method significantly improves design efficiency and accuracy.

[0060] With increased rigidity, the machine tool experiences less deformation during machining, ensuring the stability of the relative positions of each component and thus improving machining accuracy; for example... Figure 2 The machine tool model shown has two working states when machining workpieces;

[0061] In the first working state, the workpiece is installed vertically with the end face of the workpiece spindle 6 facing upwards, i.e., the axis is parallel to the tool spindle 7; the tool spindle 7 is equipped with a turning tool, which is oriented and locked with a brake to prevent the turning tool from rotating; the tool can turn the workpiece from the four directions of +X, -X, +Y and -Y.

[0062] In the second working state, the end face of the workpiece spindle 6 is horizontal, that is, the axis is perpendicular to the tool spindle 7; the tool spindle 7 is equipped with a cutting tool, which is oriented and locked with a brake to prevent the cutting tool from rotating; the tool can perform turning from the workpiece in the three directions of +Z, +Y and -Y.

[0063] After obtaining the optimal value of machine tool stiffness using the linear regression equation, the vibration of the tool spindle 7 is smaller under high-speed and high-load conditions during machining. Larger cutting parameters can be used to improve the material removal rate and improve machining efficiency to a certain extent. It also effectively suppresses the vibration of the machine tool during machining and reduces the increase in surface roughness caused by vibration.

[0064] Based on the preferred embodiments of the present invention described above, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. An intelligent analysis and decision-making method based on a big data platform, characterized in that, Includes the following steps: S1. Establish the initial 3D model of the machine tool: Perform 3D modeling of the initial machine tool, import the model into the finite element simulation analysis software, establish each component and input material properties to generate the mesh; S2. Change the elastic modulus of each component of the initial machine tool: By inputting different elastic material data for each component of the machine tool in the finite element simulation software, the elastic modulus can be changed, or the geometry of the component can be changed to change the elastic modulus. S3. Obtain relevant data through testing: After each change in the elastic modulus, test the stiffness of the machine tool and record the positional accuracy data, cutting force data, or vibration data of the machine tool under various conditions. S4. Establish a machine tool stiffness model: Based on the test data, establish a model describing the stiffness of the machine tool, and based on the distribution of the obtained data and the complexity of the machine tool model, establish a linear mathematical machine tool model. S5. Establish a linear regression equation model: Analyze the test data using the linear regression equation model to determine the factors that affect the machine tool stiffness for each change. S6. Output theoretical maximum stiffness data: Based on the linear regression model, determine the combination of materials and geometries of one or more components to produce the maximum stiffness, and then optimize the stiffness of the machine tool. S7. Conduct experimental verification: Verify the machine tool stiffness optimized by the linear regression model through actual experiments, and determine whether the machine tool performance before and after optimization meets the expected performance by comparing the machine tool performance before and after optimization. If the expected performance is not met, rebuild the machine tool stiffness model by the linear regression model until the expected performance is met.

2. The intelligent analysis and decision-making method based on a big data platform according to claim 1, characterized in that: In step S1, the finite element model is established by setting the four foot structures at the bottom of the machine tool as fixed boundary conditions and performing mesh generation.

3. The intelligent analysis and decision-making method based on a big data platform according to claim 1, characterized in that: After establishing the initial machine tool model in step S1, the assembled three-dimensional machine tool model is preliminarily verified to check the positional relationship of each component and ensure that the components are in the correct positions.

4. The intelligent analysis and decision-making method based on a big data platform according to claim 1, characterized in that: In step S1, the initial model of the machine tool is geometrically simplified, and structures with minimal impact on the stiffness of large components in the machine tool, including small chamfers, fillets, and small holes, are removed.

5. A CNC lathe model, based on the intelligent analysis and decision-making method based on a big data platform as described in any one of claims 1-5, comprising: A bed, a fixing component disposed on the bed, and a machining component installed in cooperation with the fixing component, characterized in that, The fixing assembly includes: a cradle, a workpiece spindle mounted on the cradle, and an X-saddle fixedly mounted below the cradle; each X-saddle is equipped with a first transmission unit, and each workpiece spindle is equipped with a clamp.

6. A CNC lathe model according to claim 5, characterized in that: The machine bed is symmetrically equipped with several columns, and a crossbeam is installed on each of the columns. The machining assembly is installed on the crossbeam. The machining assembly includes: a Y-saddle, a spindle box installed on the Y-saddle, and a tool spindle located at the bottom of the spindle box.

7. A CNC lathe model according to claim 6, characterized in that: The first transmission unit includes: a plurality of first slide grooves, and a first slide rail installed in each of the first slide grooves; the first slide grooves are symmetrically arranged on the bed, and the bottom of the X slide saddle is fitted onto the first slide rail.

8. A CNC lathe model according to claim 6, characterized in that: A second transmission unit is installed on the Y-saddle, and a tool magazine is installed on one side wall of the column. The second transmission unit includes: a plurality of second slide grooves, a second slide rail installed in the second slide grooves, and a Y-feed axis installed in the middle of the plurality of second slide rails.

9. A CNC lathe model according to claim 6, characterized in that: The bed is provided with several X feed axes near the two side walls of the X slide saddle, and the Y slide saddle is concave. The spindle box is located on the inner wall of the Y slide saddle, and several Z feed axes are symmetrically installed on the two side walls of the spindle box.

10. A CNC lathe model according to claim 9, characterized in that: The Z-feed axis is mounted on the spindle box, and a transmission block is mounted on the Y-saddle. The transmission block is fitted onto the Z-feed axis.

Images