A method for predicting dimensional errors in CNC machining

Abstract

This invention discloses a method for predicting dimensional errors in CNC machining. The method includes: collecting various historical data from the CNC machining process of aerospace parts and preprocessing them; performing feature analysis on the preprocessed data to identify features related to the CNC machining of aerospace parts, obtaining a feature dataset, and analyzing the changing trends of each feature; based on the analysis results, constructing a dimensional error prediction model using machine learning algorithms to predict the dimensional errors in the CNC machining process of aerospace parts; combining the prediction results of the dimensional error prediction model with the feature data of the feature dataset to obtain a dimensional error trend coefficient and analyze the changing trends of the dimensional errors of parts in the production environment; applying the constructed dimensional error prediction model to the actual production process, monitoring key parameters in the machining process in real time, and predicting the dimensional error status of aerospace parts; judging abnormal dimensional error situations based on the prediction results of the dimensional error status, determining whether to issue a warning signal, and implementing corresponding adjustment measures. The technical solution provided by this invention solves the problem that existing CNC machining methods suffer from various interference factors in the actual production environment, which can cause dimensional errors in the CNC machining process of aerospace parts, thereby affecting the machining quality of aerospace CNC parts.

Description

Technical Field

[0001] This invention relates to, but is not limited to, the field of CNC parts machining technology, and specifically to a method for predicting dimensional errors in CNC machining. Background Technology

[0002] The production and processing of CNC aerospace components is a crucial link in the aerospace manufacturing industry, characterized by small-batch and diversified production. With the continuous development of the manufacturing industry, the requirements for the machining accuracy and product quality of CNC aerospace components are becoming increasingly stringent. As a vital pillar of modern manufacturing, the machining accuracy of CNC machining technology directly affects the quality and performance of products. Therefore, by predicting dimensional errors during the CNC machining process and taking corresponding measures for control and compensation, machining accuracy can be significantly improved, ensuring the consistency and stability of the production quality of CNC aerospace components.

[0003] Existing CNC machining methods are subject to various interference factors in actual production environments, which can cause dimensional errors in the CNC machining process of aerospace parts, thereby affecting the machining quality of aerospace CNC parts. Summary of the Invention

[0004] The purpose of this invention is to solve the above-mentioned technical problems. This invention provides a method for predicting dimensional errors in CNC machining, which addresses the problem that various interference factors exist in the actual production environment of existing CNC machining methods, causing dimensional errors in the CNC machining process of aerospace parts, and thus affecting the machining quality of aerospace CNC parts.

[0005] The technical solution of the present invention: The embodiments of the present invention provide a method for predicting dimensional errors in CNC machining, including:

[0006] Step 1: Collect various historical data during the CNC machining process of aerospace parts, and preprocess the collected historical data.

[0007] Step 2: Perform feature analysis on the preprocessed historical data, filter out features related to CNC machining of aerospace parts, obtain feature dataset, and analyze the changing trends of each feature;

[0008] Step 3: Based on the analysis results of the feature dataset, a dimensional error prediction model is constructed using machine learning algorithms to predict the dimensional errors in the CNC machining process of aerospace parts.

[0009] Step 4: Combine the prediction results of the size error prediction model with the feature data of the feature dataset to obtain the size error trend coefficient and analyze the changing trend of component size error in the production environment.

[0010] Step 5: Apply the constructed dimensional error prediction model to the actual production process, monitor key parameters in the processing in real time, and predict the dimensional error status of aerospace parts processing.

[0011] Step 6: Based on the predicted results of the dimensional error status, determine the abnormal situation of the dimensional error, determine whether to issue an early warning signal, and implement corresponding adjustment measures.

[0012] Optionally, in the CNC machining dimensional error prediction method described above, step 1, the collection and preprocessing of historical data of the CNC machining process for aerospace parts, includes:

[0013] Step 1.1: Determine the types of data to be collected for the CNC machining of aerospace parts, including: machining parameters, equipment feature values, and part size error data;

[0014] Step 1.2: Utilize the data acquisition function built into the CNC machine tool to read the machine tool operation data through the interface of the CNC control system, collect historical data of processing parameters and equipment characteristic values ​​for a preset evaluation time period, and use measuring tools to measure the dimensions of the aerospace parts, compare them with the design dimensions, and calculate the part size error data.

[0015] Step 1.3: Preprocess the collected historical data. The preprocessing operations include data cleaning and data transformation.

[0016] Step 1.4: Match and integrate the preprocessed processing parameters, equipment feature values, and part size error data according to processing batches to form a unified dataset.

[0017] Optionally, in the CNC machining dimensional error prediction method described above, the analysis process of the changing trends of each feature in step 2 is as follows:

[0018] Step 2.1: Perform statistical analysis on the preprocessed historical data, extract CNC machining feature data of aerospace parts from machining parameters, equipment feature values ​​and part size error data, and obtain feature dataset by comprehensively filtering the feature data;

[0019] Specifically, for machining parameter data, feature data such as spindle speed, cutting speed, feed rate, and depth of cut are extracted; for equipment feature value data, feature data such as machine tool vibration, spindle current, and lubricating oil temperature are extracted; and for part size error data, feature data such as size deviation, size deviation change rate, shape deviation, and positional deviation are extracted.

[0020] Step 2.2: Based on the feature data of each processing parameter in the feature dataset, and combined with the benchmark value of each feature data of the processing parameter, calculate the process trend index and analyze the changing trend of the processing parameter within the preset evaluation time period.

[0021] Step 2.3: Based on the feature data of each feature value of the equipment in the feature dataset, and combined with the benchmark value of each feature data of the equipment feature value, calculate the mechanical performance trend index and analyze the changing trend of the equipment feature value within the preset evaluation time period.

[0022] Step 2.4: Based on the feature data of part size error in the feature dataset, and combined with the benchmark value of each feature data of part size error, calculate the part error trend index and analyze the changing trend of part size error within the preset evaluation time period.

[0023] Optionally, in the CNC machining dimensional error prediction method described above, the process trend index is calculated as follows:

[0024]

[0025] Wherein, ATI is the process trend index, SP is the current value of the spindle speed, BP is the reference value of the cutting speed, LP is the current value of the feed rate, RP is the reference value of the depth of cut, and α is the coefficient of the depth of cut, which is used to adjust the degree of influence of the depth of cut on the index.

[0026] The mechanical performance trend index is calculated as follows:

[0027]

[0028] Wherein, MTI is the mechanical property trend index, V m V0 is the current machine tool vibration value, and V0 is the reference value for machine tool vibration. max I is the maximum permissible value for machine tool vibration. s I0 is the current spindle current value, and I0 is the reference value for the spindle current. max The maximum allowable value of spindle current, T oil T is the current lubricating oil temperature value, T0 is the reference value of the lubricating oil temperature, and T max This refers to the maximum permissible temperature of the lubricating oil.

[0029] The calculation method for the part error tendency index is as follows:

[0030]

[0031] in,

[0032] Where PTI is the part error tendency index, F(d, r, f) is the deviation influence function, and ds The current dimensional deviation is given by d0, where d is the reference value for the dimensional deviation. max r is the maximum permissible value for dimensional deviation. s Here, r is the current rate of change of dimensional deviation, and r0 is the baseline value for the rate of change of dimensional deviation. max f is the maximum permissible value of the rate of change of dimensional deviation. s f is the current shape deviation, f0 is the reference value of the shape deviation, f max p is the maximum permissible value for shape deviation. s p0 is the current position deviation, and p is the reference value of the position deviation. max This represents the maximum permissible value for positional deviation.

[0033] Optionally, in the CNC machining dimensional error prediction method described above, the process of constructing the dimensional error prediction model in step 3 includes:

[0034] Step 3.1: Randomly divide the entire feature dataset into a training set and a test set. For the size error prediction problem, select a linear regression model for model training.

[0035] Step 3.2: Use the training set data to learn and adjust the parameters of the selected linear regression model, calculate the model parameters to minimize the error between the predicted value and the actual value, and then build a size error prediction model.

[0036] Step 3.3: Use test set data to evaluate the trained dimensional error prediction model, compare the difference between the predicted value and the actual value, and adjust and optimize the dimensional error prediction model according to the evaluation results, so as to predict the dimensional error of the CNC machining process of aerospace parts.

[0037] Optionally, in the CNC machining dimensional error prediction method described above, the analysis process of the variation trend of component dimensional errors in the production environment in step 4 is as follows:

[0038] Step 4.1: Compare the prediction results of the size error prediction model with the actual size error data in the feature dataset one by one, calculate the prediction error, and analyze the distribution and magnitude of the prediction error.

[0039] Step 4.2: Combining the prediction results of the dimensional error prediction model with the relevant data of the feature dataset, calculate the process trend index, mechanical performance trend index and part error trend index, and analyze the changing trends of processing parameters, equipment characteristic values ​​and part dimensional errors.

[0040] Step 4.3: Combine the process trend index, mechanical performance trend index and part error trend index to obtain a comprehensive dimensional error trend coefficient. Analyze the time series changes of the dimensional error trend coefficient to determine its magnitude and direction of change, and clarify the changing trend of part dimensional errors in the production environment.

[0041] Step 4.4: Based on the changing trend of the dimensional error trend coefficient, perform anomaly detection on the production environment. If the dimensional error trend coefficient exceeds the normal range, it is determined that there is an anomaly in the production environment.

[0042] Optionally, in the CNC machining dimensional error prediction method described above, the dimensional error tendency coefficient in step 4.3 is calculated as follows:

[0043]

[0044] Among them, ECI is the dimensional error trend coefficient, ATI is the process trend index, which reflects the changing trend of processing parameters, MTI is the mechanical performance trend index, which reflects the changing trend of equipment characteristic values, PTI is the part error trend index, which reflects the changing trend of part dimensional error, ∈ is a positive number, close to 0, used to avoid division by 0, and the value of ECI is between 0 and 1.

[0045] Optionally, in the CNC machining dimensional error prediction method described above, step 5, which involves predicting the dimensional error state of aerospace parts, includes:

[0046] Step 5.1: Save the trained dimensional error prediction model in a loadable format, deploy it to the server in the production environment, and integrate the dimensional error prediction model into the CNC control system.

[0047] Step 5.2: Configure sensors and data acquisition modules in the CNC control system to monitor key parameter data in real time during the machining process. Send the real-time monitored key parameter data to the data server through the data interface of the CNC control system. Develop a data preprocessing module in the data server to perform preprocessing operations such as cleaning, format conversion, and normalization on the acquired key parameter data.

[0048] Step 5.3: Input the preprocessed key parameter data into the size error prediction model;

[0049] Step 5.4: Call the dimensional error prediction model through the interface of the CNC control system, pass the input data to the dimensional error prediction model for processing, calculate and output the dimensional error state prediction result of the aerospace parts processing based on the input data, and output the prediction result to the operator through the interface of the CNC control system.

[0050] Optionally, in the CNC machining dimensional error prediction method described above, the process of issuing the early warning signal in step 6 is as follows:

[0051] Step 6.1: Obtain the predicted results of the dimensional error status from the CNC control system; set the warning threshold for dimensional error based on product quality standards and historical data; compare the predicted results with the preset warning threshold to determine whether the predicted results exceed the allowable error range.

[0052] Step 6.2: If the prediction result exceeds the allowable error range, it is judged as an abnormal size error, and then the cause of the abnormality is analyzed.

[0053] Step 6.3: Combining the dimensional error trend coefficient and the degree of deviation of the prediction results, the dimensional error anomaly level is divided into slight anomaly, moderate anomaly and severe anomaly, and corresponding deviation thresholds are matched for different levels of dimensional error anomaly. Different levels of dimensional error anomaly correspond to different early warning signals and adjustment measures.

[0054] Step 6.4: Based on the level of dimensional error anomaly, set corresponding warning signal rules: issue a yellow warning for minor anomalies, an orange warning for moderate anomalies, and a red warning for severe anomalies. Then, according to the set warning rules, issue warning signals through the interface of the CNC control system and take corresponding countermeasures.

[0055] Step 6.5: Integrate data and feedback from the actual processing process, optimize the dimensional error prediction model, and continuously monitor the dimensional error status during the processing after implementing adjustment measures.

[0056] Optionally, in the CNC machining dimensional error prediction method described above, multiple dimensional error anomaly levels correspond to multiple deviation thresholds, wherein the deviation thresholds include an upper limit threshold and a lower limit threshold;

[0057] The multiple dimensional error anomaly levels and the multiple deviation thresholds satisfy the following relationship:

[0058] Mild abnormal ECI L ≤ECI<1;

[0059] Moderately abnormal ECI M ≤ECI <ECI L ;

[0060] Serious abnormality 0 <ECI<ECI M ;

[0061] Where ECI is the dimensional error tendency coefficient, ECI L ECI represents the lower threshold for minor anomalies and the upper threshold for moderate anomalies. MECI represents the lower threshold for moderate anomalies and the upper threshold for severe anomalies. L =0.9, ECI M =0.7.

[0062] The beneficial effects of the present invention: The embodiments of the present invention provide a method for predicting dimensional errors in CNC machining. Compared with the prior art, the method for predicting dimensional errors in CNC machining has achieved the following technical advancements:

[0063] First, the CNC machining dimensional error prediction method provided by this invention acquires data during the machining process and analyzes it using a dimensional error prediction model to discover and warn of potential dimensional errors. This not only improves the accuracy of the dimensions of aerospace parts but also significantly enhances the stability of product quality. During the production process, even in the face of minor changes in machining parameters or equipment wear, it can respond quickly and guide operators to adjust machining conditions, thereby avoiding the accumulation and amplification of dimensional errors.

[0064] Secondly, the CNC machining dimensional error prediction method provided by this invention can avoid rework and scrap due to non-compliant dimensions by discovering potential problems in advance. This not only reduces the waste of raw materials but also lowers production costs. At the same time, it can also detect equipment failures or signs of wear in a timely manner, thereby enabling early maintenance and replacement. This avoids production interruptions and delays caused by equipment failures and greatly reduces the risks and uncertainties in the production process. Attached Figure Description

[0065] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of the present invention and do not constitute a limitation on the technical solutions of the present invention.

[0066] Figure 1 A flowchart of the CNC machining dimensional error prediction method provided in the embodiments of the present invention;

[0067] Figure 2 This is a flowchart illustrating the trend analysis of the variation of error characteristics of each dimension in an embodiment of the present invention;

[0068] Figure 3 This is a flowchart illustrating the trend analysis of component dimensional error changes in the production environment in an embodiment of the present invention;

[0069] Figure 4 This is a flowchart illustrating the prediction of dimensional error states in the machining of aerospace components in an embodiment of the present invention;

[0070] Figure 5 This is a flowchart illustrating the issuance of a warning signal in an embodiment of the present invention. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

[0072] As explained in the background section, existing CNC machining methods are subject to various interference factors in actual production environments, which can cause dimensional errors in the CNC machining process of aerospace parts, thereby affecting the machining quality of aerospace CNC parts.

[0073] Therefore, how to analyze the key parameters in the processing of aerospace parts and promptly detect changes and anomalies in the production environment is the problem that this invention aims to solve. To this end, this invention provides a method for predicting dimensional errors in CNC machining. By acquiring data during the machining process and analyzing it using a dimensional error prediction model, potential dimensional errors can be detected and warned. This not only improves the accuracy of aerospace parts dimensions but also significantly enhances the stability of product quality. During the production process, even in the face of minor changes in machining parameters or equipment wear, it can respond quickly and guide operators to adjust machining conditions, thereby avoiding the accumulation and amplification of dimensional errors.

[0074] The present invention provides the following specific embodiments, which can be combined with each other. For the same or similar concepts or processes, they may not be described again in some embodiments.

[0075] The following examples illustrate the implementation of the CNC machining dimensional error prediction method provided by the present invention.

[0076] Example 1:

[0077] like Figure 1 , Figure 2 As shown, the present invention provides a method for predicting dimensional errors in CNC machining, comprising the following steps:

[0078] Step 1: Collect various historical data during the CNC machining process of aerospace parts, and preprocess the collected historical data.

[0079] The implementation of this step is as follows: First, the data types of CNC machining of aerospace parts to be collected are defined, including machining parameters, equipment characteristic values, and part size error data. Second, using the data acquisition function built into the CNC machine tool, the machine tool operation data is read through the interface of the CNC control system to collect historical data of machining parameters and equipment characteristic values ​​for a preset evaluation period. The dimensions of the aerospace parts are measured using measuring tools and compared with the design dimensions to calculate the part size error data. Subsequently, the collected historical data is preprocessed. Preprocessing operations include data cleaning and data transformation. Data cleaning checks for duplicate records in the dataset and deletes them. For missing data, padding (e.g., using mean, median, mode, etc.) or deletion is selected based on the specific situation. Outliers in the data are identified and processed. Non-numerical data is converted into numerical data for subsequent analysis and processing. Data with different dimensions is standardized to eliminate the influence of dimensions on the data. Finally, the preprocessed machining parameters, equipment characteristic values, and part size error data are matched and integrated according to machining batches to form a unified dataset.

[0080] Step 2: Perform feature analysis on the preprocessed historical data, filter out features related to CNC machining of aerospace parts, obtain feature dataset, and analyze the changing trends of each feature;

[0081] The implementation method of this step is as follows: statistical analysis is performed on the preprocessed historical data, and CNC machining feature data of aerospace parts are extracted from machining parameters, equipment feature values ​​and part size error data respectively. The feature dataset is obtained by comprehensively filtering the feature data. Among them, for machining parameter data, feature data of spindle speed, cutting speed, feed rate and cutting depth are extracted. Spindle speed affects the linear velocity of the tool and workpiece contact, thus affecting the quality of the machined surface. Changes in cutting speed directly affect cutting force and cutting temperature, thus affecting the dimensional accuracy of the part. An increase in feed rate will lead to an increase in cutting force, thus affecting the dimensional stability of the part. An increase in cutting depth will aggravate the friction and wear between the tool and the workpiece, thus affecting the dimensional error of the part.

[0082] Among them, for the equipment characteristic data, the characteristic data of machine tool vibration, spindle current and lubricating oil temperature are extracted. The magnitude of machine tool vibration directly affects the machining accuracy. In particular, high-frequency vibration may lead to an increase in the surface roughness and dimensional error of the parts. The change of spindle current reflects the load of the spindle motor and indirectly reflects the change of cutting force during the cutting process. The change of lubricating oil temperature will affect the lubrication effect and the thermal expansion of machine tool components, thus affecting the dimensional accuracy of the parts.

[0083] Among them, for the part size error data, feature data such as size deviation amount, size deviation change rate, shape deviation and position deviation are extracted. The size deviation amount is the deviation between the actual size of the part and the design size, which directly reflects the magnitude of the size error. The size deviation change rate is the change rate of the size deviation between adjacent workpieces, which reflects the stability of the processing process. The shape deviation is the difference between the shape of the processed part and the design shape. The position deviation is the deviation between the position of the processed part and the design position.

[0084] Based on the feature data of each processing parameter in the feature dataset, and combined with the benchmark values ​​of each feature data of the processing parameter, the process trend index is calculated to analyze the changing trend of the processing parameter within a preset evaluation period. Based on the feature data of each equipment feature value in the feature dataset, and combined with the benchmark values ​​of each feature data of the equipment feature value, the mechanical performance trend index is calculated to analyze the changing trend of the equipment feature value within a preset evaluation period. Based on the feature data of each part size error in the feature dataset, and combined with the benchmark values ​​of each feature data of the part size error, the part error trend index is calculated to analyze the changing trend of the part size error within a preset evaluation period.

[0085] In practical implementation, the process trend index is calculated as follows:

[0086]

[0087] Wherein, ATI is the process trend index, SP is the current value of the spindle speed, BP is the reference value of the cutting speed, LP is the current value of the feed rate, RP is the reference value of the depth of cut, and α is the coefficient of the depth of cut, used to adjust the degree of influence of the depth of cut on the index.

[0088] It should be noted that when ATI is close to 1, it indicates that the machining parameters are very close to the reference value, and the machining process is under good control. When ATI is close to 0, it indicates that the machining parameters differ significantly from the reference value, and adjustments may be needed to improve machining quality. (Using root formulas...) The deviation between spindle speed and cutting speed is measured and combined with an exponential function. To smooth the effect of spindle speed and cutting speed deviations on the final index, the difference is used. The deviation between feed rate and depth of cut is measured using the squared difference method, since the effects of feed rate and depth of cut are less significant than those of spindle speed and cutting speed. Reduce the impact of feed rate and depth of cut on the index.

[0089] In practical implementation, the mechanical performance tendency index is calculated as follows:

[0090]

[0091] Wherein, MTI is the mechanical property trend index, V m V0 is the current machine tool vibration value, and V0 is the reference value for machine tool vibration. max I is the maximum permissible value for machine tool vibration. s I0 is the current spindle current value, and I0 is the reference value for the spindle current. max The maximum allowable value of spindle current, T oil T is the current lubricating oil temperature value, T0 is the reference value of the lubricating oil temperature, and T max This is the maximum permissible value for lubricating oil temperature.

[0092] It should be noted that when MTI is close to 1, it indicates that the equipment's characteristic value is close to its reference value, and the mechanical performance is in good condition. When MTI is close to 0, it indicates that the equipment's characteristic value deviates significantly from its reference value, and there is a risk of performance degradation or failure. (Root part) The exponential function measures the deviation of vibration levels. The effect of smoothing vibration level deviation on the final index, using square terms for spindle current and lubricating oil temperature. and To measure the degree of deviation from the maximum allowable value, the effect of the deviation is amplified by the squared term.

[0093] In practical implementation, the part error tendency index is calculated as follows:

[0094]

[0095] in,

[0096] Where PTI is the part error tendency index, F(d, r, f) is the deviation influence function, and d s The current dimensional deviation is given by d0, where d is the reference value for the dimensional deviation. max r is the maximum permissible value for dimensional deviation. s Here, r is the current rate of change of dimensional deviation, and r0 is the baseline value for the rate of change of dimensional deviation. max f is the maximum permissible value of the rate of change of dimensional deviation. s Here, f represents the current shape deviation, and f is the baseline value for the shape deviation. max p is the maximum permissible value for shape deviation. s p0 is the current position deviation, and p is the reference value of the position deviation. max This represents the maximum permissible value for positional deviation.

[0097] It should be noted that when PTI is close to 1, it means that the part's dimensional error characteristic value is close to its reference value, and the part's processing quality is in good condition. When PTI is close to 0, it means that the part's dimensional error characteristic value deviates significantly from its reference value, and there may be processing quality problems.

[0098] Step 3: Based on the analysis results of the feature dataset, a dimensional error prediction model is constructed using machine learning algorithms to predict the dimensional errors in the CNC machining process of aerospace parts.

[0099] The implementation process of this step is as follows: The entire feature dataset is randomly divided into a training set and a test set to ensure that the data distribution of the training set and the test set is consistent, avoiding the introduction of bias. For the dimensional error prediction problem, a linear regression model is selected for model training. The selected linear regression model is trained and its parameters are adjusted using the training set data. The model parameters are calculated to minimize the error between the predicted and actual values, thereby constructing a dimensional error prediction model. The trained dimensional error prediction model is evaluated using the test set data. The difference between the predicted and actual values ​​is compared to assess the accuracy and generalization ability of the dimensional error prediction model. Based on the evaluation results, the dimensional error prediction model is adjusted and optimized to improve its accuracy and generalization ability, thereby predicting the dimensional errors in the CNC machining process of aerospace parts.

[0100] Step 4: Combine the prediction results of the size error prediction model with the relevant data of the feature dataset to obtain the size error trend coefficient and analyze the changing trend of component size error in the production environment.

[0101] In this embodiment of the invention, the stability of the production environment and whether adjustment measures need to be taken are determined based on the magnitude and direction of change of the dimensional error tendency coefficient.

[0102] Step 5: Apply the constructed dimensional error prediction model to the actual production process, monitor key parameters in the processing in real time, and predict the dimensional error status of aerospace parts processing.

[0103] Step 6: Based on the predicted results of the dimensional error status, determine the abnormal situation of the dimensional error, determine whether to issue an early warning signal, and implement corresponding adjustment measures.

[0104] Example 2:

[0105] like Figures 3 to 5 As shown, based on Example 1, the CNC machining dimensional error prediction method provided in Example 2 is preferably as follows: Figure 3 As shown, step 4 of embodiment 2, the analysis process of the trend of changes in the dimensional error of parts in the production environment, includes:

[0106] The prediction results of the dimensional error prediction model are compared one by one with the actual dimensional error data in the feature dataset to ensure that the prediction results and actual data correspond in time series, so as to conduct accurate analysis and calculate the prediction error, and analyze the distribution and magnitude of the prediction error to evaluate the accuracy and reliability of the prediction model. Combining the prediction results of the dimensional error prediction model with relevant data in the feature dataset, the process trend index, mechanical performance trend index, and part error trend index are calculated to analyze the changing trends of processing parameters, equipment characteristic values, and part dimensional errors. Finally, the process trend index, mechanical performance trend index, and part error trend index are combined... The comprehensive dimensional error trend coefficient is obtained, and its time series changes are analyzed to determine its magnitude and direction of change, thus clarifying the trend of dimensional error changes in the production environment. Based on the trend of the dimensional error trend coefficient, anomaly detection is performed on the production environment. If the dimensional error trend coefficient exceeds the normal range, it is determined that there is an anomaly in the production environment, and the stability of the production environment is assessed. If the dimensional error trend coefficient remains relatively stable within a certain period of time and the range of change is within an acceptable range, the production environment is considered stable. If the dimensional error trend coefficient fluctuates frequently or exceeds the normal range, adjustment measures need to be taken to optimize the production environment.

[0107] Furthermore, the dimensional error tendency coefficient is calculated as follows:

[0108] Among them, ECI is the dimensional error trend coefficient, ATI is the process trend index, which reflects the changing trend of processing parameters, MTI is the mechanical performance trend index, which reflects the changing trend of equipment characteristic values, PTI is the part error trend index, which reflects the changing trend of part dimensional error, and ∈ is a very small positive number, close to 0, used to avoid division by 0. The value range of ECI is between 0 and 1.

[0109] It should be noted that when ECI is close to 1, it means that all three trend indices are close to or equal to 1, that is, the production environment is stable and the dimensional error is controlled within an acceptable range. When ECI is close to 0, it means that at least one trend index is low, which may indicate problems with processing parameters, equipment performance or part dimensional error, requiring further analysis and adjustment.

[0110] like Figure 4 As shown, step 5 of this embodiment 2, the process of predicting the dimensional error state of aerospace parts, includes:

[0111] The trained dimensional error prediction model is saved in a loadable format and deployed to a server in the production environment. A stable network connection between the server and the production CNC control system is ensured. The dimensional error prediction model is integrated into the CNC control system, ensuring that the CNC control system can access the model server in real time and send and receive data. Sensors and data acquisition modules are configured in the CNC control system to monitor key parameters during machining (such as cutting speed, feed rate, depth of cut, spindle speed, tool wear, etc.) in real time. The monitored key parameter data is sent to the data server through the CNC control system's data interface to ensure data integrity and accuracy, avoiding data loss or errors. A data preprocessing module is developed in the data server to clean, convert, and normalize the collected key parameter data. The preprocessed data should meet the input requirements of the dimensional error prediction model. The preprocessed key parameter data is used as input into the dimensional error prediction model. The dimensional error prediction model is called through the CNC control system's interface, and the input data is passed to the dimensional error prediction model for processing. Based on the input data, the dimensional error state prediction result for aerospace parts machining is calculated and output. The prediction result is then output to the operator through the CNC control system's interface.

[0112] like Figure 5 As shown, in step 6 of embodiment 2, the process of issuing the warning signal includes:

[0113] The system obtains the predicted dimensional error status from the CNC control system. Based on product quality standards and historical data, it sets a warning threshold for dimensional errors. The predicted results are compared with the preset warning thresholds to determine if they exceed the allowable error range. If they do, the dimensional error is considered abnormal. The causes of the abnormality are then analyzed, such as improper machining parameter settings, equipment malfunction, or material problems. Combining the dimensional error tendency coefficient and the degree of deviation in the predicted results, the dimensional error abnormality levels are categorized into minor, moderate, and severe abnormalities. Corresponding deviation thresholds are assigned to different levels of dimensional error abnormalities. Different levels of dimensional error abnormalities correspond to different warning signals and adjustment measures. Based on the level of dimensional error abnormality, corresponding warning signal rules are set: a yellow warning for minor abnormalities, an orange warning for moderate abnormalities, and a severe warning for severe abnormalities. A red alert is issued, and according to the set alert rules, an alert signal is sent through the CNC control system interface to ensure that operators can notice the alert signal in time and take corresponding countermeasures. Based on the prediction results and the cause of the anomaly, the machining parameters such as cutting speed, feed rate, and depth of cut are adjusted to optimize the machining process and reduce dimensional errors. Regular inspections and maintenance of CNC equipment are carried out to ensure the accuracy and stability of the equipment and avoid dimensional errors caused by equipment failure. If the prediction results show that the dimensional error is caused by material or tool problems, the material or tool is replaced in time. Materials and tools with stable quality and excellent performance are selected to improve machining accuracy. Data and feedback from the actual machining process are integrated to optimize the dimensional error prediction model. After the adjustment measures are implemented, the dimensional error status during the machining process is continuously monitored to ensure the effectiveness of the adjustment measures and to promptly identify new problems.

[0114] Furthermore, multiple dimensional error anomaly levels correspond to multiple deviation thresholds, where the deviation thresholds include an upper limit threshold and a lower limit threshold;

[0115] The following relationship exists between multiple dimensional error anomaly levels and multiple deviation thresholds:

[0116] Mild abnormal ECI L ≤ECI<1;

[0117] Moderately abnormal ECI M ≤ECI <ECI L ;

[0118] Serious abnormality 0 <ECI<ECI M ;

[0119] Where ECI is the dimensional error tendency coefficient, ECI L ECI represents the lower threshold for minor anomalies and the upper threshold for moderate anomalies. M ECI represents the lower threshold for moderate anomalies and the upper threshold for severe anomalies.L =0.9, ECI M =0.7.

[0120] This invention provides a method for predicting dimensional errors in CNC machining. Compared with existing technologies, this method achieves the following technical advancements:

[0121] First, the CNC machining dimensional error prediction method provided by this invention acquires data during the machining process and analyzes it using a dimensional error prediction model to discover and warn of potential dimensional errors. This not only improves the accuracy of the dimensions of aerospace parts but also significantly enhances the stability of product quality. During the production process, even in the face of minor changes in machining parameters or equipment wear, it can respond quickly and guide operators to adjust machining conditions, thereby avoiding the accumulation and amplification of dimensional errors.

[0122] Secondly, the CNC machining dimensional error prediction method provided by this invention can avoid rework and scrap due to non-compliant dimensions by discovering potential problems in advance. This not only reduces the waste of raw materials but also lowers production costs. At the same time, it can also detect equipment failures or signs of wear in a timely manner, thereby enabling early maintenance and replacement. This avoids production interruptions and delays caused by equipment failures and greatly reduces the risks and uncertainties in the production process.

[0123] While the embodiments disclosed in this invention are as described above, they are merely illustrative of the embodiments to facilitate understanding of the invention and are not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and variations in the form and details of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection for this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method for predicting dimensional errors in CNC machining, characterized in that, include: Step 1: Collect various historical data during the CNC machining process of aerospace parts, and preprocess the collected historical data. Step 2: Perform feature analysis on the preprocessed historical data, filter out features related to CNC machining of aerospace parts, obtain feature dataset, and analyze the changing trends of each feature; Step 3: Based on the analysis results of the feature dataset, a dimensional error prediction model is constructed using machine learning algorithms to predict the dimensional errors in the CNC machining process of aerospace parts. Step 4: Combine the prediction results of the size error prediction model with the feature data of the feature dataset to obtain the size error trend coefficient and analyze the changing trend of component size error in the production environment. Step 5: Apply the constructed dimensional error prediction model to the actual production process, monitor key parameters in the processing in real time, and predict the dimensional error status of aerospace parts processing. Step 6: Based on the predicted results of the dimensional error status, determine the abnormal situation of the dimensional error, and determine whether to issue an early warning signal and implement corresponding adjustment measures. In step 2, the analysis process for the changing trends of each characteristic is as follows: Step 2.1: Perform statistical analysis on the preprocessed historical data, extract CNC machining feature data of aerospace parts from machining parameters, equipment feature values ​​and part size error data, and obtain feature dataset by comprehensively filtering the feature data; Specifically, for machining parameter data, feature data such as spindle speed, cutting speed, feed rate, and depth of cut are extracted; for equipment feature value data, feature data such as machine tool vibration, spindle current, and lubricating oil temperature are extracted; and for part size error data, feature data such as size deviation, size deviation change rate, shape deviation, and positional deviation are extracted. Step 2.2: Based on the feature data of each processing parameter in the feature dataset, and combined with the benchmark value of each feature data of the processing parameter, calculate the process trend index and analyze the changing trend of the processing parameter within the preset evaluation time period. Step 2.3: Based on the feature data of each feature value of the equipment in the feature dataset, and combined with the benchmark value of each feature data of the equipment feature value, calculate the mechanical performance trend index and analyze the changing trend of the equipment feature value within the preset evaluation time period. Step 2.4: Based on the feature data of part size error in the feature dataset, and combined with the benchmark value of each feature data of part size error, calculate the part error trend index and analyze the changing trend of part size error within the preset evaluation time period. The process trend index is calculated as follows: ； in, As a process trend index, The current value of the spindle speed. This is the reference value for cutting speed. The current value of the feed rate. This serves as the reference value for the depth of cut. This is a coefficient representing the depth of cut, used to adjust the degree of influence of the depth of cut on the index; The mechanical performance trend index is calculated as follows: ； in, It is a mechanical property trend index. The current machine tool vibration value, This serves as the reference value for machine tool vibration. This represents the maximum permissible value for machine tool vibration. This is the current spindle current value. The reference value for the spindle current. This is the maximum allowable value of the spindle current. This is the current lubricating oil temperature value. This is the reference value for lubricating oil temperature. This refers to the maximum permissible temperature of the lubricating oil. The calculation method for the part error tendency index is as follows: ； in, ; in, This is the component error tendency index. Let the deviation influence function be... This is the current dimensional deviation. This serves as the reference value for dimensional deviation. This represents the maximum permissible value for dimensional deviation. This represents the current rate of change of dimensional deviation. This serves as the baseline value for the rate of change of dimensional deviation. This is the maximum permissible value for the rate of change of dimensional deviation. For the current shape deviation, This serves as the baseline value for shape deviation. This represents the maximum permissible value for shape deviation. This represents the current positional deviation. This serves as the reference value for positional deviation. This represents the maximum permissible value for positional deviation. The construction process of the size error prediction model in step 3 includes: Step 3.1: Randomly divide the entire feature dataset into a training set and a test set. For the size error prediction problem, select a linear regression model for model training. Step 3.2: Use the training set data to learn and adjust the parameters of the selected linear regression model, calculate the model parameters to minimize the error between the predicted value and the actual value, and then build a size error prediction model. Step 3.3: Use test set data to evaluate the trained dimensional error prediction model, compare the difference between the predicted value and the actual value, and adjust and optimize the dimensional error prediction model according to the evaluation results, so as to predict the dimensional error of the CNC machining process of aerospace parts.

2. The method for predicting dimensional errors in CNC machining according to claim 1, characterized in that, Step 1, the collection and preprocessing of historical data for the CNC machining of aerospace parts, includes: Step 1.1: Determine the types of data to be collected for the CNC machining of aerospace parts, including: machining parameters, equipment feature values, and part size error data; Step 1.2: Utilize the data acquisition function built into the CNC machine tool to read the machine tool operation data through the interface of the CNC control system, collect historical data of processing parameters and equipment characteristic values ​​for a preset evaluation time period, and use measuring tools to measure the dimensions of the aerospace parts, compare them with the design dimensions, and calculate the part size error data. Step 1.3: Preprocess the collected historical data. The preprocessing operations include data cleaning and data transformation. Step 1.4: Match and integrate the preprocessed processing parameters, equipment feature values, and part size error data according to processing batches to form a unified dataset.

3. The method for predicting dimensional errors in CNC machining according to claim 1, characterized in that: In step 4, the analysis process for the changing trend of component dimensional errors in the production environment is as follows: Step 4.1: Compare the prediction results of the size error prediction model with the actual size error data in the feature dataset one by one, calculate the prediction error, and analyze the distribution and magnitude of the prediction error. Step 4.2: Combining the prediction results of the dimensional error prediction model with the relevant data of the feature dataset, calculate the process trend index, mechanical performance trend index and part error trend index, and analyze the changing trends of processing parameters, equipment characteristic values ​​and part dimensional errors. Step 4.3: Combine the process trend index, mechanical performance trend index and part error trend index to obtain a comprehensive dimensional error trend coefficient. Analyze the time series changes of the dimensional error trend coefficient to determine its magnitude and direction of change, and clarify the changing trend of part dimensional errors in the production environment. Step 4.4: Based on the changing trend of the dimensional error trend coefficient, perform anomaly detection on the production environment. If the dimensional error trend coefficient exceeds the normal range, it is determined that there is an anomaly in the production environment.

4. The method for predicting dimensional errors in CNC machining according to claim 3, characterized in that, The method for calculating the dimensional error tendency coefficient in step 4.3 is as follows: ； in, This is the dimensional error tendency coefficient. As a process trend index, It is a mechanical property trend index. This is the component error tendency index. It is a positive number, close to 0. The value ranges from 0 to 1.

5. The method for predicting dimensional errors in CNC machining according to claim 4, characterized in that: The process of predicting the dimensional error status of aerospace parts in step 5 includes: Step 5.1: Save the trained dimensional error prediction model in a loadable format, deploy it to the server in the production environment, and integrate the dimensional error prediction model into the CNC control system. Step 5.2: Configure sensors and data acquisition modules in the CNC control system to monitor key parameter data in real time during the machining process. Send the real-time monitored key parameter data to the data server through the data interface of the CNC control system. Develop a data preprocessing module in the data server to perform preprocessing operations such as cleaning, format conversion, and normalization on the acquired key parameter data. Step 5.3: Input the preprocessed key parameter data into the size error prediction model; Step 5.4: Call the dimensional error prediction model through the interface of the CNC control system, pass the input data to the dimensional error prediction model for processing, calculate and output the dimensional error state prediction result of the aerospace parts processing based on the input data, and output the prediction result to the operator through the interface of the CNC control system.

6. The method for predicting dimensional errors in CNC machining according to claim 5, characterized in that: The process of issuing the warning signal in step 6 is as follows: Step 6.1: Obtain the predicted results of the dimensional error status from the CNC control system; set the warning threshold for dimensional error based on product quality standards and historical data; compare the predicted results with the preset warning threshold to determine whether the predicted results exceed the allowable error range. Step 6.2: If the prediction result exceeds the allowable error range, it is judged as an abnormal size error, and then the cause of the abnormality is analyzed. Step 6.3: Combining the dimensional error trend coefficient and the degree of deviation of the prediction results, the dimensional error anomaly level is divided into slight anomaly, moderate anomaly and severe anomaly, and corresponding deviation thresholds are matched for different levels of dimensional error anomaly. Different levels of dimensional error anomaly correspond to different early warning signals and adjustment measures. Step 6.4: Based on the level of dimensional error anomaly, set corresponding warning signal rules: issue a yellow warning for minor anomalies, an orange warning for moderate anomalies, and a red warning for severe anomalies. Then, according to the set warning rules, issue warning signals through the interface of the CNC control system and take corresponding countermeasures. Step 6.5: Integrate data and feedback from the actual processing process, optimize the dimensional error prediction model, and continuously monitor the dimensional error status during the processing after implementing adjustment measures.

7. The method for predicting dimensional errors in CNC machining according to claim 6, characterized in that, The multiple dimensional error anomaly levels correspond to multiple deviation thresholds, wherein the deviation thresholds include an upper limit threshold and a lower limit threshold; The multiple dimensional error anomaly levels and the multiple deviation thresholds satisfy the following relationship: Minor abnormality ; Moderate abnormality ; Serious abnormality ; in, This is the dimensional error tendency coefficient. These are the lower threshold for minor anomalies and the upper threshold for moderate anomalies. These are the lower threshold for moderate anomalies and the upper threshold for severe anomalies. , .

Images