Optimization Method for Machining Process Parameters Based on Intelligent Numerical Control Machine Tools

Abstract

The present invention relates to the field of data processing, and particularly to an optimization method for machining process parameters based on an intelligent numerical control machine tool. The method includes: obtaining the process parameters of the intelligent numerical control machine tool; obtaining the order of an improved filter; inputting the process parameters into a filtering module, and performing notch filtering using the order of the improved filter to obtain filtered process parameters, and inputting the filtered process parameters into a parameter optimization module to obtain optimized process parameters. By calculating the drift degree of the main frequency of the process parameters and the possibility of periodicity, the present invention dynamically adjusts the order of the filter, so that when the improved filter order is subsequently used to filter the parameters, the interference and noise caused by mechanical resonance can be eliminated or weakened, thereby significantly improving the filtering accuracy and the parameter optimization effect.

Description

Technical Field

[0001] The present invention relates to the field of data processing. More specifically, the present invention relates to an optimization method for machining process parameters based on intelligent numerically controlled machine tools. Background Art

[0002] During the machining process of numerically controlled machine tools, the selection of process parameters such as cutting parameters (cutting speed, feed rate, cutting depth, etc.) and tool parameters (tool radius, etc.) directly affects the machining efficiency. By optimizing these parameters, the machining speed can be significantly increased, the machining cycle can be shortened, and thus the production efficiency can be improved. For example, on the premise of ensuring machining quality, appropriately increasing the cutting speed and feed rate can significantly reduce the machining time.

[0003] The prior art, such as the patent application document with the publication number CN114758064A, discloses a method for optimizing machining process parameters of a machine tool based on digital twin. The method for optimizing machining process parameters of the machine tool includes: realizing multi-dimensional expressions including the characteristics, functions, and behaviors of the actual cutting process of the machine tool through 3D modeling software and a virtual platform; reducing the complexity of the underlying code based on JSON format text data transmission, collecting process data during the cutting process of the machine tool in real time, and analyzing the influence weight of the process data on the cutting force through the grey correlation theory; calling the encapsulated digital twin cutting force prediction model in a visualization mapping manner based on unity3D to analyze the dynamic change of the cutting force in real time; and generating an optimization plan for the cutting force fluctuation situation in real time according to the influence factor weight and the digital twin prediction model.

[0004] However, the above method for optimizing machining process parameters of a machine tool does not consider the influence of mechanical resonance of the machine tool. Due to mechanical resonance, the machine tool generates continuous and regular vibrations, which will interfere with the relative movement between the tool and the workpiece, making the cutting process unable to proceed stably according to the predetermined trajectory and parameters, thus affecting the machining accuracy and surface quality. Summary of the Invention

[0005] To solve the above technical problem of reducing the optimization effect of process parameters, the present invention provides the following technical solutions.

[0006] An optimization method for machining process parameters based on intelligent numerically controlled machine tools, comprising:

[0007] Obtaining the process parameters of the intelligent numerically controlled machine tool;

[0008] Obtaining the improved filter order;

[0009] Inputting the process parameters into a filtering module, performing notch filtering using the improved filter order to obtain filtered process parameters, and inputting the filtered process parameters into a parameter optimization module to obtain optimized process parameters;

[0010] Among them, the relationship satisfied by the improved filter order is:

[0011] ; in the formula, is the improved filter order, is the drift degree of the main frequency of the process parameter, is the possibility that the main frequency of the process parameter has periodicity, is a parameter, is the exponential function with the natural constant e as the base, is the ceiling function.

[0012] By analyzing the drift degree of the main frequency of the process parameter and the possibility of the main frequency having periodicity, the present invention enables the filter to reserve a certain frequency range during design to cope with the small changes in the main frequency, and optimizes these periodic factors to reduce the noise generated by periodic interference. The filtered process parameter can more accurately reflect the machining requirements of the machine tool, thereby guiding the machine tool to perform more precise machining.

[0013] Preferably, a Fourier transform is performed on the process parameter to convert the time-domain signal into a frequency-domain signal, and the main frequency is extracted from the frequency-domain signal.

[0014] Considering that in the actual machining process, the main frequency of the process parameter will be affected by various factors, resulting in drift and periodic changes, the present invention calculates the drift degree and the possibility of having periodicity of the main frequency, and dynamically adjusts the filter order, so that when the improved filter order is subsequently used to filter the parameter, the interference and noise caused by mechanical resonance can be eliminated or weakened, thereby significantly improving the filtering accuracy and the parameter optimization effect.

[0015] Preferably, the process of obtaining the drift degree of the main frequency of the process parameter includes:

[0016] Decompose the main frequency into multiple components, and calculate the change degree of each component and the possibility of the noise component of each component;

[0017] Using the possibility of the noise component of each component as the weight, calculate the weighted average of the change degrees of all components, and use it as the drift degree of the main frequency.

[0018] Decomposing the main frequency into multiple components can analyze the change situation of the main frequency more carefully. Each component may represent the characteristics of the main frequency in different frequency bands or different time periods. Calculating the change degree of each component can quantify the fluctuation situation of the main frequency in different aspects, which helps to identify the main sources and trends of the main frequency drift.

[0019] Preferably, the relationship satisfied by the change degree of each component is:

[0020] ; In the formula, is the degree of change of the th component, is the th value corresponding to the th time point in the th component, is the th value corresponding to the th time point in the th component, is the total number of components obtained by primary frequency decomposition,

[0021] By comparing the degrees of change between different components, the component with the most significant change can be identified, and the filter design can be optimized according to the change characteristics of the component.

[0022] Preferably, the relationship satisfied by the noise component possibility of each component is:

[0023] ; In the formula, is the noise component possibility of the th component, is the variance of the values corresponding to all time points in the th component, is the Pearson correlation coefficient between the th component and the th component, is the total number of components obtained by primary frequency decomposition.

[0024] During the primary frequency decomposition process, by calculating the noise component possibility of each component, it is possible to identify which components in the primary frequency components are more likely to be contaminated by noise. For components with a high noise component possibility, a more stringent filter can be applied to reduce the influence of noise.

[0025] Preferably, the relationship satisfied by the possibility of the primary frequency of the process parameters being periodic is:

[0026] ; In the formula, is that the primary frequency is periodic, is the first-order difference value of the distance between the th maximum point and the th maximum point, is the total number of maximum points in the primary frequency.

[0027] By analyzing the periodicity of the primary frequency, the regular fluctuations in the process parameters can be identified, and then these fluctuations can be removed through notch processing, thereby improving the stability and accuracy during the processing.

[0028] Preferably, the degree of change of each component satisfies the relational expression:

[0029] ; where is the degree of change of the th component, is the value corresponding to the th time point in the th component, is the value corresponding to the th time point in the th component, is the total number of time points in the th component.

[0030] Preferably, the optimization adopts a genetic algorithm or a particle swarm optimization algorithm.

[0031] The beneficial effects of the present invention are as follows:

[0032] The improved filter order is calculated according to the main frequency drift degree of the process parameters, the possibility of the main frequency having periodicity, and specific parameters, realizing the adaptive optimization of the filter. This adaptive optimization can be flexibly adjusted according to the characteristics of different process parameters, improving the filtering effect and further enhancing the machining accuracy.

[0033] By filtering the process parameters, noise and interference can be effectively removed, improving the stability and reliability of the signal. At the same time, by optimizing the filtered process parameters through the parameter optimization module, more accurate machining parameters can be obtained, thereby improving the machining accuracy and efficiency. Description of the Drawings

[0034] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understandable. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0035] Figure 1 is a flowchart of the method of steps S1 - S3 in the optimization method of the machining process parameters based on an intelligent numerical control machine tool according to an embodiment of the present invention. Detailed Embodiments

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0037] The specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0038] The application scenario of the present invention is as follows: first, notch filters are used to process parameter data, and then the processed parameter data is further optimized.

[0039] Referring to Figure 1 , the optimization method for the machining process parameters of intelligent numerical control machine tools includes steps S1 - S3, which are specifically as follows:

[0040] S1: Obtain the process parameters of the intelligent numerical control machine tool.

[0041] In the background database of the intelligent numerical control machine tool, obtain the historical data of the optimization parameters required for the machining process of the intelligent numerical control machine tool within the past month.

[0042] Specifically, the obtained process parameters include cutting parameters (cutting speed, feed speed, etc.), tool parameters (tool radius, etc.), and the obtained data is cleaned to remove invalid or abnormal data.

[0043] Among them, taking any one parameter such as cutting speed as an example for analysis.

[0044] S2: Obtain the order of the improved filter.

[0045] During the machining process of the machine tool, the resonance frequency of the machine tool will change dynamically due to various factors. For example, during the cutting process, the cutting force will change with the change of cutting parameters (such as cutting speed, feed rate, cutting depth, etc.), and the change of the cutting force will cause changes in the rigidity and dynamic response of the machine tool system, thereby affecting the resonance frequency.

[0046] The dynamic change of the machine tool resonance frequency may cause vibration and deformation during the machining process, thereby affecting the machining accuracy, and may also cause the cutting parameters to be continuously adjusted, thereby reducing the machining efficiency.

[0047] In the embodiment of the present invention, notch filters are used during the machining process of the machine tool to eliminate or weaken the influence of the mechanical resonance of the machine tool on the machining parameters. By reducing the interference of the resonance frequency on the machining process, the machining accuracy and efficiency can be improved.

[0048] First, perform Fourier transform on the process parameters to convert the time-domain signal into a frequency-domain signal, and extract the main frequency from the frequency-domain signal, that is, the frequency component that dominates or has the highest energy in the frequency-domain signal.

[0049] Secondly, when the main frequency of the process parameters changes or drifts, which is the frequency drift of the main frequency, the frequency drift causes the filter to be unable to accurately locate the main frequency of the process parameters, thus affecting the filtering effect. To cope with the frequency drift, the filter needs to be able to adapt to these changes to continuously and effectively filter and maintain the tracking of the target frequency. When the main frequency of the process parameters has a large drift, a simple low-order filter may not be competent, so it is necessary to adjust the order of the filter to improve the accuracy and response speed.

[0050] In addition, the frequency components in the frequency signal will change periodically with time. If the signal frequency changes continuously within a certain period, the filter design must be able to adjust dynamically to keep up with these periodic changes. When the frequency changes very frequently (i.e., the period is very short), the signal may contain more complex frequency components. To process these complex frequency components, a higher filter order may be required. Higher-order filters have better frequency selectivity and faster response speed, so they are more suitable for processing signals with frequently changing frequencies.

[0051] In summary, by adjusting the order of the filter according to the degree of frequency drift of the main frequency and the periodicity of frequency changes, the performance of the filter can be significantly improved, making it more effective in filtering out interference signals related to the mechanical resonance of the machine tool.

[0052] Among them, the calculation process of the degree of frequency drift of the main frequency is as follows:

[0053] Perform empirical mode decomposition (EMD) on the main frequency to obtain a series of IMF components;

[0054] Calculate the degree of change of each component, that is, the relationship formula is satisfied as:

[0055]

[0056] In the formula, is the degree of change of the th component, is the value corresponding to the th time point in the th component, is the value corresponding to the th time point in the th component, is the total number of components obtained by decomposing the main frequency, is the th component, and is the total number of time points in the th component. The larger the value of One component contains more noise or abnormal information. By calculating the degree of change of each component, it is possible to identify which components may contain noise, so as to perform corresponding filtering operations in signal processing.

[0057] In one embodiment, another way to calculate the degree of change of a component by considering the change of the component itself between different time points is provided, that is, the relational expression is satisfied as:

[0058]

[0059] In the formula, is the degree of change of the th component, is the value corresponding to the th time point in the th component, is the value corresponding to the th time point in the th component, is the total number of time points in the th component.

[0060] Calculate the possibility of the noise component of each component, that is, the relational expression is satisfied as:

[0061]

[0062] In the formula, is the possibility of the noise component of the th component, is the variance of the values corresponding to all time points in the th component, is the Pearson correlation coefficient between the th component and the th component, is the total number of components obtained by principal frequency decomposition.

[0063] For the th component, its variance represents the average of the squares of the deviations of the data points of this component from its mean. The larger the variance, the more dispersed the data points of this component, that is, the higher the randomness of this component; if the Pearson correlation coefficient between two different components is close to 1 or -1, it means that there is a strong linear correlation between these two components, and if it is close to 0, it means that there is almost no linear correlation between these two components.

[0064] Comprehensively considering the randomness of the component (measured by variance) and its correlation with other components (measured by Pearson correlation coefficient), in practical applications, this index can be used to identify and remove the noise components in the signal, so as to obtain a cleaner signal.

[0065] After calculating the degree of change of each component and the possibility of the noise component of each component, the possibility of the noise component of each component is used as the weight to calculate the weighted mean of the degree of change of all components, which is used as the drift degree of the main frequency. That is, the drift degree of the main frequency satisfies the relational expression as follows:

[0066]

[0067] In the formula, is the drift degree of the main frequency, is the degree of change of the th component, is the possibility of the noise component of the th component, is the total number of components obtained by decomposing the main frequency.

[0068] Among them, the calculation process of the possibility that the main frequency has periodic changes is specifically as follows:

[0069] Obtain all the maximum points in the main frequency and the positions of each maximum point in the main frequency, and calculate the distance between adjacent maximum points (this distance represents the interval between two adjacent frequency components in the frequency domain).

[0070] Furthermore, perform a first-order difference on the distance between adjacent maximum points, that is, calculate the change amount between adjacent distances, and perform a cumulative sum calculation on the result of the first-order difference (this cumulative sum reflects the overall change trend of the distance between adjacent maximum points).

[0071] Furthermore, if the result of the cumulative sum is close to zero or shows periodic fluctuations, then it is considered that the possibility of the main frequency having periodicity is relatively high. This is because periodic signals usually show a series of equally spaced frequency components in the frequency domain, and these components will form a regular distribution of maximum points in the spectrum.

[0072] Then the possibility that the main frequency has periodicity satisfies the relational expression as follows:

[0073]

[0074]

[0075] In the formula, is that the main frequency has periodicity, is the first-order difference value of the distance between the th maximum point and the th maximum point, is the total number of maximum points in the main frequency; is the distance between the th maximum point and the th maximum point, is the The value of the maximum point, is the value of the th maximum point, is the th position of the maximum point, is the th position of the maximum point, is the exponential function with the natural constant e as the base.

[0076] Among them, The smaller the value of

[0077] is, the smaller the change in the distance between adjacent maximum points means. That is to say, these maximum points are more evenly distributed to some extent. In signal processing or data analysis, if the distribution of maximum points is more regular, then the possibility of the existence of the main frequency they represent is higher.

[0078] Finally, improve the order of the filter according to the drift degree of the main frequency and the possibility of the periodicity of the main frequency.

[0079] Specifically, the higher the drift degree of the main frequency, the higher the required filter order to increase the response of the filter; the higher the possibility of the periodicity of the main frequency, the higher the required filter order to ensure that the filter can keep up with this periodic change.

[0079] Then the improved filter order satisfies the relationship:

[0080]

[0081] In the formula, is the improved filter order, is the drift degree of the main frequency of the process parameters, is the possibility of the periodicity of the main frequency of the process parameters, is a parameter, is the exponential function with the natural constant e as the base, is the ceiling function. Among them, .

[0082] S3: Input the process parameters into the filtering module, perform notch filtering using the improved filter order, obtain the filtered process parameters, and input the filtered process parameters into the parameter optimization module to obtain the optimized process parameters.

[0083] Input the process parameters to be optimized, such as the cutting speed, into the filtering module with a built-in notch filter. According to the improved filter order in S2 above, the notch filter will filter the input parameters to remove the noise or interference components.

[0084] The filtered parameters will be input into the parameter optimization module, which is built with optimization algorithms (such as genetic algorithm, particle swarm optimization algorithm, etc.) to further optimize the parameters so that the performance indicators of the processing technology reach the optimal or near-optimal level.

[0085] In the description of this specification, "a plurality of", "several" mean at least two, such as two, three or more, etc., unless otherwise specifically defined.

[0086] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

Claims

1. An optimization method for machining process parameters based on intelligent numerical control machine tools, characterized in that, Including: Obtain the process parameters of the intelligent numerical control machine tool; Obtain the improved filter order; Input the process parameters into the filtering module, perform notch filtering using the improved filter order to obtain the filtered process parameters, and input the filtered process parameters into the parameter optimization module to obtain the optimized process parameters; Among them, the improved filter order satisfies the relationship: ; where, is the improved filter order, is the drift degree of the main frequency of the process parameter, is the possibility that the main frequency of the process parameter is periodic, is a parameter, is the exponential function with the natural constant e as the base, is the ceiling function.

2. The optimization method based on the machining process parameters of an intelligent numerical control machine tool according to claim 1, characterized in that, Perform Fourier transform on the process parameters to convert the time-domain signal into a frequency-domain signal, and extract the main frequency from the frequency-domain signal.

3. The optimization method based on the machining process parameters of an intelligent numerical control machine tool according to claim 2, characterized in that, The obtaining process of the drift degree of the main frequency of the process parameters includes: Decompose the main frequency into multiple components, calculate the change degree of each component and the possibility of the noise component of each component; Use the possibility of the noise component of each component as the weight, calculate the weighted mean of the change degree of all components, and use it as the drift degree of the main frequency.

4. The optimization method based on the processing process parameters of an intelligent numerical control machine tool according to claim 3, characterized in that, The change degree of each component satisfies the relationship: ; In the formula, is the degree of change of the -th component, is the value corresponding to the -th time point in the -th component, is the value corresponding to the -th time point in the -th component, is the total number of components obtained by main frequency decomposition, is the total number of time points in the -th component.

5. The optimization method based on the machining process parameters of an intelligent numerical control machine tool according to claim 4, wherein The possibility of the noise component of each component satisfies the relationship: ; where is the noise component possibility of the -th component, is the variance of the values corresponding to all time points in the -th component, is the Pearson correlation coefficient between the -th component and the -th component, is the total number of components obtained by the main frequency decomposition.

6. The optimization method based on the machining process parameters of an intelligent numerically controlled machine tool according to claim 3, characterized in that, The possibility that the main frequency of the process parameters has periodicity satisfies the relationship: Where, The main frequency has periodicity. For the The maximum point and the The first-order difference value of the distance between the maximum points, The total number of maximum points in the main frequency.

7. The optimization method based on the machining process parameters of an intelligent numerical control machine tool according to claim 3, characterized in that, The change degree of each component satisfies the relationship: ; where, is the degree of change of the th component, is the value corresponding to the th component at the th time point, is the value corresponding to the th component at the th time point, is the total number of time points in the th component.

8. The optimization method based on the machining process parameters of an intelligent numerical control machine tool according to claim 1, characterized in that, The optimization adopts a genetic algorithm or a particle swarm optimization algorithm.

Images