Numerical control machine tool control system based on big data

Abstract

The invention discloses a numerical control machine tool control system based on big data. A data acquisition module is used for acquiring cutter abrasion loss during production of a numerical control machine tool, load information of the machine tool in a machining process, a machining precision error of workpiece machining and a machining precision error change rate; according to the system, big data and a fuzzy self-adaptive control algorithm are comprehensively utilized, the fuzzy self-adaptive control algorithm determines a feed amount adjusting range based on fuzzy information of a machining state, a feed amount scheme with the highest fitness function is selected from a scheme set containing all possible feed amounts by setting the fitness function, and the feed amount adjusting range is adjusted according to the feed amount scheme with the highest fitness function. The feed amount correction and adjustment module dynamically adjusts the feed amount according to the actual machining precision, and the difference between the feed amount scheme determined by the fitness function and actual machining is made up. Through the synergistic effect of the technologies, the machining precision and efficiency of the numerical control machine tool are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly relates to a numerical control machine tool control system based on big data. Background Art

[0002] A numerical control machine tool, abbreviated as a CNC machine tool, is an automated machine tool equipped with a program control system. This control system can logically process a program with control codes or other symbolic instructions, decode it, represent it in coded numbers, and input it into the numerical control device through an information carrier. After arithmetic processing, the numerical control device issues various control signals to control the operation of the machine tool, and automatically processes parts according to the shape and size required by the drawing.

[0003] Publication No. CN115639781B discloses a numerical control machine tool control method and system based on big data. By obtaining the production data when each workpiece is produced by the numerical control machine tool; obtaining the feed error index of the numerical control machine tool, screening out the machine tools with abnormal feed; obtaining the position error vector of the machine tools without abnormal feed, and identifying the abnormal machine tools; arbitrarily selecting multiple abnormal machine tools, obtaining multiple vibration-audio sequences corresponding to the selected abnormal machine tools, and dividing all the selected abnormal machine tools into three groups; based on the similarity between each vibration-audio sequence of each abnormal machine tool and the abnormal machine tools in different groups, obtaining the group to which the sequence belongs, and making corresponding control actions.

[0004] However, the above application still has the following problems: The feed rate adjustment in the above application only fixes the adjustment by 0.5 mm each time according to the machining gear accuracy requirements, without considering the influence of the tool wear degree factor on the feed rate adjustment. The adjustment strategy lacks flexibility and pertinence, which is not conducive to accurately controlling the machining accuracy. Summary of the Invention

[0005] To solve the technical problems in the background art, the present invention proposes a numerical control machine tool control system based on big data.

[0006] A numerical control machine tool control system based on big data proposed by the present invention includes:

[0007] Data acquisition module: Collect the tool wear amount during the production of the numerical control machine tool, the load information during the machining process of the machine tool, the machining accuracy error of the workpiece machining, and the change rate of the machining accuracy error;

[0008] Feed rate adjustment range determination module: Determine the feed rate adjustment range through fuzzy adaptive control;

[0009] Feed rate plan generation and determination module: Generate a set of plans including all possible feed rates within the feed rate adjustment range given by the feed rate adjustment range determination module. Each feed rate value within the feed rate adjustment range corresponds to an independent feed rate plan;

[0010] Set the fitness function. From the set of all possible feed rate schemes, select the feed rate scheme with the highest fitness function value.

[0011] Feed rate correction and adjustment module: During the machining process of the feed rate scheme with the highest fitness function value, when the actual machining size is greater than the standard size and exceeds the allowable range, or when the actual machining size is less than the standard size and exceeds the allowable range, the feed rate of the feed rate scheme with the highest fitness function value is corrected in real time.

[0012] And continuously monitor the machining accuracy and adjust the feed rate.

[0013] Preferably, in the feed rate adjustment range determination module, the fuzzy adaptive control determines the feed rate adjustment range as follows:

[0014] Take the tool wear amount, the current machining accuracy error, and the change rate of the machining accuracy error as the input variables of the fuzzy adaptive control, and the feed rate adjustment value as the output variable.

[0015] Perform fuzzy processing on the input variables, divide the fuzzy subsets, and determine the membership functions corresponding to each subset.

[0016] The fuzzy subsets include negative large, negative medium, negative small, zero, positive small, positive medium, and positive large.

[0017] The determination of the membership function can be based on machining experience and experimental data. The membership function is used to accurately describe the belonging degree of the input variable in different fuzzy states.

[0018] Generate fuzzy rules for formulating the feed rate adjustment value through the decision tree algorithm.

[0019] The feed rate adjustment values output by the output variable of the decision tree algorithm are negative large, negative medium, negative small, zero, positive small, positive medium, and positive large.

[0020] Adopt the Mamdani inference method for fuzzy inference and calculate the fuzzy set of the output variable.

[0021] The Mamdani inference method has unique advantages in dealing with fuzziness and uncertainty. Although the rules generated by the decision tree are clear, they may not fully reflect the fuzzy relationship between the input variables and the transmission of fuzziness. When more detailed processing of fuzzy information and accurate characterization of the mutual influence between different fuzzy subsets are required, the Mamdani inference method can, through steps such as input fuzzyification, fuzzy relation composition, and defuzzification, more accurately calculate the fuzzy set of the feed rate adjustment value, thereby obtaining a more reasonable feed rate adjustment result.

[0022] Through the fuzzy relation composition operation, determine the fuzzy output of the feed rate adjustment value according to the fuzzy values of the input variables and the fuzzy rules.

[0023] The centroid method is used to defuzzify the fuzzy output and convert it into an accurate feed rate adjustment range. The centroid method determines the accurate value by calculating the centroid of the area enclosed by the membership function of the output fuzzy set and the abscissa, enabling the result of the fuzzy control to be directly applied to the actual feed rate adjustment.

[0024] Preferably, through the decision tree algorithm, fuzzy rules for formulating the feed rate adjustment value are generated as follows:

[0025] A decision tree model is constructed based on the relationship between the input variables of tool wear, current machining accuracy error, machining accuracy error change rate, and the output variable of feed rate adjustment value. Through training the decision tree model, the decision tree model automatically divides the output categories corresponding to the input combinations of different input variables, thereby generating fuzzy rules.

[0026] Preferably, in the feed rate plan generation and determination module, the fitness function is as follows:

[0027] For each feed rate plan, during simulated machining, the corresponding simulated tool wear, simulated machining accuracy error, and simulated machining accuracy error change rate are calculated;

[0028] The simulated machining here is the prior art;

[0029] The simulated tool wear, simulated machining accuracy error, and simulated machining accuracy error change rate are quantified and normalized;

[0030] Let the weight of tool wear be w1, the weight of simulated machining accuracy error be w2, and the weight of simulated machining accuracy error change rate be w3;

[0031] Let the quantified and normalized tool wear be T, the simulated machining accuracy error be E, and the simulated machining accuracy error change rate be ΔE;

[0032] The fitness function F is:

[0033] where ∈ is a positive number to avoid the denominator being zero. In an alternative embodiment, ∈ = 10 -6 ;

[0034] During actual machining, the values of w1, w2, and w3 can be manually adjusted;

[0035] Among the set of plans including all possible feed rates, select the feed rate plan with the highest fitness function.

[0036] Preferably, the value range of w1 is 0.2 - 0.3, the value range of w2 is 0.4 - 0.5, and the value range of w3 is 0.2 - 0.3;

[0037] Preferably, in the feed rate correction adjustment module, during the machining process of the feed rate plan with the highest fitness function, assume that in the feed rate plan with the highest fitness function, the determined initial feed rate is D 初始 ;

[0038] The allowable precision deviation range is E 允许偏差 ;

[0039] The actual size of the workpiece obtained by the on-line measurement system in real time is X 实际 , and the preset standard size of the workpiece is X 标准 ;

[0040] The real-time precision deviation is E 实时偏差 , E 实时偏差 = X 实际 - X 标准 ;

[0041] Assume that the feed rate after real-time correction is D 修正 ;

[0042] The correction coefficient is k, which is used to control the amplitude of feed rate adjustment; k can be manually adjusted according to machine tool performance and machining material factors;

[0043] When E 实时偏差 > E 允许偏差 , that is, the actual machining size is larger than the standard size and exceeds the allowable range. At this time, it is necessary to appropriately reduce the feed rate, and at this time, the feed rate is corrected,

[0044] Calculate the relative proportion of the allowable deviation exceeded, multiply it by the initial feed rate D 初始 to obtain the part of the feed rate that needs to be reduced, and then multiply it by the correction coefficient k to control the reduction amplitude;

[0045] When E 实时偏差 < -E 允许偏差 , that is, the actual machining size is smaller than the standard size and exceeds the allowable range. At this time, it is necessary to appropriately increase the feed rate, and at this time, the feed rate is corrected,

[0046] Calculate the relative proportion of the allowable negative deviation exceeded, multiply it by the initial feed rate D 初始 to obtain the part of the feed rate that needs to be increased, and also multiply it by the correction coefficient k to control the increase amplitude;

[0047] If -E 允许偏差 ≤ E 实时偏差 ≤ E 允许偏差 , that is, the deviation between the actual machining size and the standard size is within the allowable range. At this time, the feed rate does not need to be corrected, that is, D 修正 = D初始 。

[0048] A numerical control machine tool control method based on big data, characterized by comprising the following steps:

[0049] S1. Collect the tool wear amount during the production of the numerical control machine tool, the load information during the machining process, the machining accuracy error of the workpiece machining, and the change rate of the machining accuracy error;

[0050] S2. Determine the feed rate adjustment range through fuzzy adaptive control;

[0051] S3. In the feed rate adjustment range given in S2, generate a set of solutions including all possible feed rates, and each feed rate value in the feed rate adjustment range corresponds to an independent feed rate solution;

[0052] Set a fitness function, and select the feed rate solution with the highest fitness function in the set of solutions including all possible feed rates;

[0053] S4. During the machining process of the feed rate solution with the highest fitness function, when the actual machining size is greater than the standard size and exceeds the allowable range, or when the actual machining size is less than the standard size and exceeds the allowable range, perform real-time correction on the feed rate of the feed rate solution with the highest fitness function;

[0054] And continuously monitor the machining accuracy and continuously adjust the feed rate.

[0055] In the present invention, the proposed numerical control machine tool control system based on big data has the following beneficial technical effects:

[0056] 1. This system comprehensively utilizes big data and the fuzzy adaptive control algorithm. The fuzzy adaptive control algorithm determines the feed rate adjustment range based on the fuzzy information of the machining state. By setting a fitness function, select the feed rate solution with the highest fitness function in the set of solutions including all possible feed rates, and the feed rate correction and adjustment module dynamically adjusts the feed rate according to the actual machining accuracy, making up for the difference between the feed rate solution determined by the fitness function and the actual machining. Through the synergistic effect of these technologies, the machining accuracy and efficiency of the numerical control machine tool are effectively improved, the scrap rate is reduced, the production cost is lowered, and the competitiveness of the enterprise is enhanced.

[0057] 2. By setting a fitness function, the fuzzy adaptive control algorithm determines the feed rate adjustment range based on the fuzzy information of the machining state, and then calculates the optimal feed rate within the determined feed rate adjustment range by the fitness function, thereby determining the feed rate solution and improving the accuracy of feed rate adjustment.

[0058] 3. By adjusting the settings of the feed rate correction adjustment module, during the machining process, the actual size of the workpiece will deviate due to various factors. The settings of the feed rate correction adjustment module can monitor these deviations in real time and correct the feed rate in a timely manner. Moreover, the machining process is a dynamically changing process, and factors such as material properties, tool wear, and machine tool performance will change over time. The feed rate correction adjustment module can adapt to these dynamic changes by continuously monitoring the machining accuracy and adjusting the feed rate, thereby improving the machining accuracy. In addition, since the feed rate can be corrected in a timely manner, the rework and scrap situations caused by insufficient machining accuracy are greatly reduced, and the rework and scrap rates are decreased.

[0059] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a principle block diagram of the system of the present invention;

[0061] Figure 2 is a flowchart of the method of the present invention;

[0062] Figure 3 is a partial fuzzy rule example of the system of the present invention;

[0063] Figure 4 is a partial fuzzy rule example of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar symbols represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0065] As Figure 1 - Figure 2 shown, a numerical control machine tool control system based on big data includes:

[0066] Data acquisition module: Collect the tool wear amount during the production of the numerical control machine tool, the load information during the machining process of the machine tool, the machining accuracy error and the machining accuracy error change rate of the workpiece machining;

[0067] Feed rate adjustment range determination module: Determine the feed rate adjustment range through fuzzy adaptive control;

[0068] Feed rate scheme generation and determination module: Generate a set of schemes including all possible feed rates within the feed rate adjustment range given by the feed rate adjustment range determination module. Each feed rate value within the feed rate adjustment range corresponds to an independent feed rate scheme;

[0069] Set the fitness function. From the set of all possible feed rate solutions, select the feed rate solution with the highest fitness function;

[0070] Feed rate correction and adjustment module: During the processing of the feed rate solution with the highest fitness function, when the actual processed size is greater than the standard size and exceeds the allowable range, or when the actual processed size is less than the standard size and exceeds the allowable range, the feed rate of the feed rate solution with the highest fitness function is corrected in real time;

[0071] And continuously monitor the machining accuracy and adjust the feed rate continuously.

[0072] Furthermore, in the feed rate adjustment range determination module, the fuzzy adaptive control determines the feed rate adjustment range as follows:

[0073] Take the tool wear amount, the current machining accuracy error, and the change rate of the machining accuracy error as the input variables of the fuzzy adaptive control, and the feed rate adjustment value as the output variable;

[0074] Perform fuzzy processing on the input variables, divide the fuzzy subsets, and determine the membership functions corresponding to each subset;

[0075] The fuzzy subsets include negative large, negative medium, negative small, zero, positive small, positive medium, and positive large;

[0076] The determination of the membership function can be based on machining experience and experimental data. The membership function is used to accurately describe the belonging degree of the input variable in different fuzzy states;

[0077] Generate fuzzy rules for formulating the feed rate adjustment value through the decision tree algorithm;

[0078] The feed rate adjustment value output by the output variable of the decision tree algorithm is negative large, negative medium, negative small, zero, positive small, positive medium, and positive large;

[0079] Adopt the Mamdani inference method for fuzzy inference and calculate the fuzzy set of the output variable;

[0080] The Mamdani inference method has unique advantages in dealing with fuzziness and uncertainty. Although the rules generated by the decision tree are clear, they may not fully reflect the fuzzy relationship and the transmission of fuzziness between the input variables. When more detailed processing of fuzzy information is required to accurately describe the mutual influence between different fuzzy subsets, the Mamdani inference method can calculate the fuzzy set of the feed rate adjustment value more accurately through steps such as fuzzy input, fuzzy relation synthesis, and defuzzification, so as to obtain a more reasonable feed rate adjustment result;

[0081] Through the fuzzy relation synthesis operation, based on the fuzzy values of the input variables and the fuzzy rules, determine the fuzzy output of the feed rate adjustment value;

[0082] Apply the centroid method to defuzzify the fuzzy output and convert it into an accurate feed rate adjustment range; the centroid method determines the accurate value by calculating the centroid of the area enclosed by the membership function of the output fuzzy set and the abscissa, enabling the result of the fuzzy control to be directly applied to the actual feed rate adjustment.

[0083] Furthermore, through the decision tree algorithm, generate the fuzzy rules for formulating the feed rate adjustment value as follows:

[0084] Construct a decision tree model based on the relationship between the input variables of tool wear, current machining accuracy error, machining accuracy error change rate, and the output variable of feed rate adjustment value. Through training the decision tree model, automatically divide the output categories corresponding to the input combinations of different input variables by the decision tree model, thereby generating fuzzy rules.

[0085] Furthermore, in the feed rate scheme generation and determination module, the fitness function is as follows:

[0086] For each feed rate scheme, during the simulated machining, calculate the corresponding simulated tool wear, simulated machining accuracy error, and simulated machining accuracy error change rate;

[0087] The simulated machining here is the prior art;

[0088] Quantify and normalize the simulated tool wear, simulated machining accuracy error, and simulated machining accuracy error change rate;

[0089] Let the weight of the tool wear be w1, the weight of the simulated machining accuracy error be w2, and the weight of the simulated machining accuracy error change rate be w3;

[0090] Let the quantified and normalized tool wear be T, the simulated machining accuracy error be E, and the simulated machining accuracy error change rate be ΔE;

[0091] The fitness function F is:

[0092] where ∈ is a positive number to avoid the denominator being zero. In an optional embodiment, ∈ = 10 -6 ;

[0093] In actual machining, the values of w1, w2, and w3 can be manually adjusted;

[0094] Among the set of schemes including all possible feed rates, select the feed rate scheme with the highest fitness function.

[0095] Further, in an optional embodiment, the value range of w1 is 0.2 - 0.3, the value range of w2 is 0.4 - 0.5, and the value range of w3 is 0.2 - 0.3.

[0096] By setting the fitness function, the fuzzy adaptive control algorithm determines the feed rate adjustment range based on the fuzzy information of the machining state, and then calculates the optimal feed rate within the determined feed rate adjustment range by the fitness function, so as to determine the feed rate scheme and improve the accuracy of feed rate adjustment.

[0097] Further, in the feed rate correction and adjustment module, during the machining process of the feed rate scheme with the highest fitness function, assume that in the feed rate scheme with the highest fitness function, the determined initial feed rate is D 初始 ;

[0098] The allowed precision deviation range is E 允许偏差 ;

[0099] The actual size of the workpiece monitored in real time by the on-line measurement system is X 实际 , and the preset standard size of the workpiece is X 标准 ;

[0100] The real-time precision deviation is E 实时偏差 , E 实时偏差 = X 实际 - X 标准 ;

[0101] Assume that the feed rate after real-time correction is D 修正 ;

[0102] The correction coefficient is k, which is used to control the amplitude of feed rate adjustment; k can be manually adjusted according to machine tool performance and machining material factors;

[0103] When E 实时偏差 > E 允许偏差 , that is, the actual machining size is greater than the standard size and exceeds the allowable range. At this time, it is necessary to appropriately reduce the feed rate, and at this time, the feed rate is corrected.

[0104] Calculate the relative proportion exceeding the allowable deviation, multiply it by the initial feed rate D 初始 to obtain the part of the feed rate that needs to be reduced, and then multiply it by the correction coefficient k to control the reduction amplitude;

[0105] When E 实时偏差 < -E 允许偏差 , that is, the actual machining size is less than the standard size and exceeds the allowable range. At this time, it is necessary to appropriately increase the feed rate, and at this time, the feed rate is corrected.

[0106] Calculate the relative proportion exceeding the allowable negative deviation, and multiply it by the initial feed rate D 初始 Obtain the part of the feed rate that needs to be increased, and also multiply it by the correction coefficient k to control the increase amplitude;

[0107] If -E 允许偏差 ≤ E 实时偏差 ≤ E 允许偏差 That is, the deviation between the actual machining size and the standard size is within the allowable range. At this time, the feed rate does not need to be corrected, that is, D 修正 = D 初始 .

[0108] The on-line measurement system is a prior art. The on-line measurement system of the prior art includes a laser measurement system, a vision measurement system, a contact measurement system, an ultrasonic measurement system, and a capacitive measurement system;

[0109] If the accuracy deviation exceeds the allowable range, immediately adjust the feed rate to make the machining process always proceed in the direction of high precision, continuously optimize the feed rate adjustment, and ensure the stability and improvement of the machining accuracy.

[0110] Through the setting of the feed rate correction adjustment module, during the machining process, the actual size of the workpiece will deviate due to various factors. The setting of the feed rate correction adjustment module can monitor these deviations in real time and correct the feed rate in a timely manner. Moreover, the machining process is a dynamically changing process, and factors such as material properties, tool wear, and machine tool performance will change over time. The feed rate correction adjustment module can adapt to these dynamic changes by continuously monitoring the machining accuracy and adjusting the feed rate, thereby improving the machining accuracy. In addition, since the feed rate can be corrected in a timely manner, the rework and scrap situations caused by insufficient machining accuracy are greatly reduced, and the rework and scrap rates are reduced

[0111] This system comprehensively utilizes big data and fuzzy adaptive control algorithms. The fuzzy adaptive control algorithm determines the feed rate adjustment range based on the fuzzy information of the machining state. By setting the fitness function, among the set of all possible feed rate solutions, select the feed rate solution with the highest fitness function, and the feed rate correction adjustment module dynamically adjusts the feed rate according to the actual machining accuracy, making up for the difference between the feed rate solution determined by the fitness function and the actual machining. Through the synergistic effect of these technologies, the machining accuracy and efficiency of the CNC machine tool are effectively improved, the scrap rate is reduced, the production cost is lowered, and the competitiveness of the enterprise is enhanced.

[0112] A CNC machine tool control method based on big data includes the following steps:

[0113] S1. Collect the tool wear amount during the production of the CNC machine tool, the load information during the machining process, the machining accuracy error of the workpiece machining, and the change rate of the machining accuracy error;

[0114] S2. Determine the feed rate adjustment range through fuzzy adaptive control;

[0115] S3. Within the feed rate adjustment range given in S2, generate a set of solutions including all possible feed rates. Each feed rate value within the feed rate adjustment range corresponds to an independent feed rate solution;

[0116] Set the fitness function, and select the feed rate solution with the highest fitness function from the set of solutions including all possible feed rates;

[0117] S4. During the machining process of the feed rate solution with the highest fitness function, when the actual machining size is greater than the standard size and exceeds the allowable range, or when the actual machining size is less than the standard size and exceeds the allowable range, perform real-time correction on the feed rate of the feed rate solution with the highest fitness function;

[0118] And continuously monitor the machining accuracy and adjust the feed rate continuously.

[0119] Meanwhile, the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0120] In the embodiments provided by the present invention, it should be understood that the disclosed system or method can be implemented in other ways. For example, the above-described invention embodiments are merely illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.

[0121] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional module in various embodiments of the present invention can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0123] For those skilled in the field of operation and maintenance, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the basic characteristics of the present invention.

[0124] As described above, it is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered within the protection scope of the present invention.

Claims

1. A numerical control machine tool control system based on big data, characterized in that, Including: Data acquisition module: It acquires the tool wear amount during the production of the numerically controlled machine tool, the load information during the machining process, the machining precision error of the workpiece machining, and the change rate of the machining precision error. Feed rate adjustment range determination module: It determines the feed rate adjustment range through fuzzy adaptive control. Feed rate scheme generation and determination module: Within the feed rate adjustment range given by the feed rate adjustment range determination module, it generates a set of schemes including all possible feed rates, and each feed rate value within the feed rate adjustment range corresponds to an independent feed rate scheme. Set the fitness function, and select the feed rate scheme with the highest fitness function from the set of schemes including all possible feed rates. Feed rate correction and adjustment module: During the machining process of the feed rate scheme with the highest fitness function, when the actual machining size is greater than the standard size and exceeds the allowable range, or when the actual machining size is less than the standard size and exceeds the allowable range, it makes real-time correction to the feed rate of the feed rate scheme with the highest fitness function. And continuously monitor the machining precision and continuously adjust the feed rate.

2. The numerical control machine tool control system based on big data according to claim 1, characterized in that, In the feed rate adjustment range determination module, the fuzzy adaptive control determines the feed rate adjustment range as follows: Taking the tool wear amount, the current machining precision error, and the change rate of the machining precision error as the input variables of the fuzzy adaptive control, and the feed rate adjustment value as the output variable. Perform fuzzy processing on the input variables, divide the fuzzy subsets, and determine the membership functions corresponding to each subset. The fuzzy subsets include negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. Generate the fuzzy rules for formulating the feed rate adjustment value through the decision tree algorithm. The feed rate adjustment value output by the output variable of the decision tree algorithm is negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. Adopt the Mamdani inference method for fuzzy inference to calculate the fuzzy set of the output variable. Through the fuzzy relation synthesis operation, determine the fuzzy output of the feed rate adjustment value according to the fuzzy values of the input variables and the fuzzy rules. Use the centroid method to defuzzify the fuzzy output and convert it into an accurate feed rate adjustment range.

3. The CNC machine tool control system based on big data according to claim 2, characterized in that, Generate the fuzzy rules for formulating the feed rate adjustment value through the decision tree algorithm as follows: Construct a decision tree model based on the relationship between the input variables of the tool wear amount, the current machining precision error, the change rate of the machining precision error, and the output variable of the feed rate adjustment value. Through training the decision tree model, the decision tree model automatically divides the output categories corresponding to the input combinations of different input variables, thereby generating fuzzy rules.

4. The numerical control machine tool control system based on big data according to claim 3, characterized in that, In the feed rate scheme generation and determination module, the fitness function is as follows: For each feed rate scheme, during the simulated machining, calculate the corresponding simulated tool wear amount, simulated machining precision error, and simulated change rate of the machining precision error. Quantify and normalize the simulated tool wear amount, simulated machining precision error, and simulated change rate of the machining precision error. Let the weight of the tool wear amount be w1, the weight of the simulated machining precision error be w2, and the weight of the simulated change rate of the machining precision error be w3. Let the quantified and normalized tool wear amount be T, the simulated machining precision error be E, and the simulated change rate of the machining precision error be ΔE. The fitness function F is as follows: Where ∈ is a positive number to avoid the denominator being zero. Among the set of feed rate solutions that include all possible feed rates, select the feed rate solution with the highest fitness function value.

5. The numerical control machine tool control system based on big data according to claim 4, characterized in that, The value range of w1 is 0.2 - 0.3, the value range of w2 is 0.4 - 0.5, and the value range of w3 is 0.2 - 0.

3.

6. The CNC machine tool control system based on big data according to claim 5, characterized in that, In the feed rate correction and adjustment module, during the machining process of the feed rate plan with the highest fitness function, assume that in the feed rate plan with the highest fitness function, the determined initial feed rate is D 初始 ; The allowable precision deviation range is E 允许偏差 ; The actual size of the workpiece obtained by real-time monitoring of the on-line measurement system is X 实际 , and the preset standard size of the workpiece is X 标准 ; The real-time precision deviation is E 实时偏差 , E 实时偏差 = X 实际 - X 标准 ; Let the feed rate after real-time correction be D 修正 ; The correction coefficient is k, which is used to control the amplitude of feed rate adjustment; When E 实时偏差 > E 允许偏差 , that is, the actual processing size is greater than the standard size and exceeds the allowable range. At this time When E 实时偏差 < -E 允许偏差 That is, the actual processing size is smaller than the standard size and exceeds the allowable range. At this time If -E 允许偏差 ≤ E 实时偏差 ≤ E 允许偏差 , that is, the deviation between the actual machining size and the standard size is within the allowable range. At this time, the feed rate does not need to be corrected, that is, D 修正 = D 初始 .

7. The control method for a numerically controlled machine tool based on big data according to any one of claims 1-6, characterized in that It includes the following steps: S1. Collect the tool wear amount during the production of the CNC machine tool, the load information during the machining process, the machining accuracy error of the workpiece machining, and the change rate of the machining accuracy error; S2. Determine the feed rate adjustment range through fuzzy adaptive control; S3. In the feed rate adjustment range given in S2, generate a set of solutions that include all possible feed rates, and each feed rate value in the feed rate adjustment range corresponds to an independent feed rate solution; Set the fitness function, and among the set of solutions that include all possible feed rates, select the feed rate solution with the highest fitness function value; S4. During the machining process of the feed rate solution with the highest fitness function value, when the actual machining size is greater than the standard size and exceeds the allowable range, or when the actual machining size is less than the standard size and exceeds the allowable range, perform real-time correction on the feed rate of the feed rate solution with the highest fitness function value; And continuously monitor the machining accuracy and continuously adjust the feed rate.

Images