Method, system and equipment for monitoring surface roughness of part in numerical control machining process, medium and product

Abstract

The invention discloses a method, system and equipment for monitoring the surface roughness of a part in the numerical control machining process, a medium and a product, and relates to the field of numerical control machining.The method comprises the steps that three-way vibration signals and sound signals of the part in the numerical control machining process are collected in real time; performing feature extraction on the three-way vibration signal and the sound signal to obtain a plurality of feature values; based on the plurality of feature values, adopting a recursive feature elimination method and a cross validation method to obtain an optimal feature subset; and obtaining the surface roughness of the part by adopting a long-short-term memory network and a Kolmogov-Arnod network based on the optimal feature subset, so that the surface roughness of the part can be monitored in real time, and the monitoring precision of the surface roughness of the part is improved through the correlation between the optimal feature subset and the surface roughness of the part.

Description

Technical Field

[0001] The present application relates to the field of numerical control machining, and in particular to a method, system, equipment, medium and product for monitoring the surface roughness of parts during numerical control machining. Background Art

[0002] Due to the requirements of high efficiency and high quality, achieving high speed, high precision and high material removal efficiency through machining has become an important goal in production. In addition, given the importance of tribological properties, fatigue strength and assembly accuracy of mechanical products, machined parts with high surface finish are also favored. Dimensional accuracy and surface quality are affected by various factors, such as cutting parameters, tool geometry and vibration, machining dynamics and machining environment. Machining vibration caused by improper machining conditions and machining parameters will affect the surface quality.

[0003] Surface roughness is an important parameter in the surface quality assessment system. It may be affected by various factors, some of which are within the controllable range, such as basic cutting parameter settings, while others are not, such as cutting vibration and tool wear. However, due to the complex environment of the processing site and the influence of multiple factors such as cutting fluid, tool vibration, and chips during the processing, it is impossible to directly monitor the surface roughness of the workpiece online in situ. The only way is to stop the machine and take out the parts for surface roughness measurement after the processing is completed, which seriously reduces the processing efficiency.

[0004] Moreover, the time-varying dynamic characteristics of precision parts in CNC machining determine the complexity of state recognition. When machining parameters, tools, materials, and processes change, the surface roughness monitoring model needs to be retrained, which is obviously not conducive to improving production efficiency. Therefore, the difficulty in obtaining real-time status in CNC machining precision parts surface roughness monitoring and the complex adjustment process for different machining conditions have become the key technical bottlenecks restricting the development of quality monitoring technology for CNC machining of precision parts. Summary of the invention

[0005] The purpose of this application is to provide a method, system, equipment, medium and product for monitoring the surface roughness of parts during CNC machining, which can monitor the surface roughness of parts in real time and improve the monitoring accuracy of surface roughness.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for monitoring the surface roughness of a part during a CNC machining process, comprising:

[0008] Real-time collection of three-way vibration and sound signals of parts during CNC machining;

[0009] Performing feature extraction on the three-way vibration signal and the sound signal to obtain a plurality of feature values; the plurality of feature values ​​include a plurality of feature values ​​of the three-way vibration signal and a plurality of feature values ​​of the sound signal;

[0010] Based on the multiple feature values, a recursive feature elimination method and a cross-validation method are used to obtain an optimal feature subset;

[0011] Based on the optimal feature subset, the long short-term memory network and Kolmogorov-Arnold network are used to obtain the surface roughness of the parts.

[0012] In a second aspect, the present application provides a system for monitoring the surface roughness of parts during CNC machining, comprising:

[0013] Signal acquisition module, used to collect three-way vibration signals and sound signals of parts during CNC machining in real time;

[0014] A feature value acquisition module, connected to the signal acquisition module, for performing feature extraction on the three-way vibration signal and the sound signal to obtain a plurality of feature values; the plurality of feature values ​​include a plurality of feature values ​​of the three-way vibration signal and a plurality of feature values ​​of the sound signal;

[0015] An optimal feature subset acquisition module, connected to the feature value acquisition module, for obtaining an optimal feature subset based on the multiple feature values ​​by using a recursive feature elimination method and a cross-validation method;

[0016] The surface roughness value acquisition module is connected to the optimal feature subset acquisition module and is used to obtain the surface roughness of the part based on the optimal feature subset by using a long short-term memory network and a Kolmogorov-Arnold network.

[0017] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned method for monitoring the surface roughness of parts during CNC machining.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned method for monitoring the surface roughness of parts during CNC machining.

[0019] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for monitoring the surface roughness of parts during CNC machining.

[0020] According to the specific embodiments provided in this application, this application has the following technical effects:

[0021] The present application provides a method, system, device, medium and product for monitoring the surface roughness of parts during CNC machining. By real-time acquisition of three-dimensional vibration signals and sound signals of parts during CNC machining, the surface roughness of parts can be monitored in real time, and features of the three-dimensional vibration signals and sound signals are further extracted. A recursive feature elimination method is used to eliminate several low-weight features, and a cross-validation method is used to avoid feature redundancy or filter out important features to obtain an optimal feature subset. Based on the optimal feature subset, the correlation between surface roughness and features is determined through a long short-term memory network and a Kolmogorov-Arnold network, thereby improving the monitoring accuracy of the surface roughness of parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is an application environment diagram of a method for monitoring the surface roughness of parts during CNC machining in one embodiment of the present application;

[0024] Figure 2 A schematic flow chart of a method for monitoring the surface roughness of a part during a CNC machining process provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram of the principles of a recursive feature elimination method and a cross-validation method provided in another embodiment of the present application;

[0026] Figure 4 A schematic diagram of a long short-term memory network provided by another embodiment of the present application;

[0027] Figure 5 A schematic diagram of a long short-term memory network and a Kolmogorov-Arnold network provided in another embodiment of the present application;

[0028] Figure 6 A schematic diagram of the comparison between the predicted value and the actual value provided in another embodiment of the present application;

[0029] Figure 7 A schematic diagram of functional modules of a system for monitoring the surface roughness of parts during CNC machining provided by another embodiment of the present application;

[0030] Figure 8 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0033] The method for monitoring the surface roughness of parts during CNC machining provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the three-way vibration signal and sound signal to be processed to the server 104. After the server 104 receives the three-way vibration signal and sound signal to be processed, it extracts features of the three-way vibration signal and the sound signal to obtain multiple eigenvalues; based on the multiple eigenvalues, the recursive feature elimination method and the cross-validation method are used to obtain the optimal feature subset; based on the optimal feature subset, the long short-term memory network and the Kolmogorov-Arnold network are used to obtain the surface roughness of the part. The server 104 can feed back the obtained surface roughness of the part to the terminal 102. In addition, in some embodiments, the method for monitoring the surface roughness of the part during CNC machining can also be implemented separately by the server 104 or the terminal 102.

[0034] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0035] In an exemplary embodiment, Figure 2 As shown, a method for monitoring the surface roughness of parts during CNC machining is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1Taking the server 104 in [the relevant context] as an example for illustration, it includes the following steps 201 to 204. Among them:

[0036] Step 201, collect the three-axis vibration signal and sound signal of the part in the numerical control machining process in real time.

[0037] Specifically, the three-axis vibration signal and sound signal of the part in the numerical control machining process can be collected by a three-axis vibration sensor and a sound sensor.

[0038] Step 202, perform feature extraction on the three-axis vibration signal and the sound signal to obtain a plurality of feature values; the plurality of feature values include a plurality of feature values of the three-axis vibration signal and a plurality of feature values of the sound signal.

[0039] Step 203, based on the plurality of feature values, adopt the recursive feature elimination method and the cross-validation method to obtain the optimal feature subset.

[0040] Step 204, based on the optimal feature subset, adopt the long short-term memory network and the Kolmogorov-Arnold network to obtain the surface roughness of the part.

[0041] In another exemplary embodiment of the present application, step 203 specifically includes: for the Nth iteration, based on the (N - 1)th feature subset, adopt the recursive feature elimination method to obtain the weight of each feature value in the (N - 1)th feature subset; and adopt the cross-validation method to obtain the average score of the (N - 1)th feature subset; 0 < N; when N = 1, the 0th feature subset includes all feature values.

[0042] Based on the weight of each feature value in the (N - 1)th feature subset, sort the plurality of feature values in the (N - 1)th feature subset, select a specified number of feature values with the top rankings as the Nth feature subset; and adopt the cross-validation method to obtain the average score of the Nth feature subset; judge whether the average score of the Nth feature subset is less than the average score of the (N - 1)th feature subset; if so, stop the iteration and take the (N - 1)th feature subset as the optimal feature subset; otherwise, perform the (N + 1)th iteration.

[0043] In another exemplary embodiment of the present application, such as Figure 3As shown, the zeroth feature subset includes feature 1, feature 2, feature 3, feature 4 and feature 5; the zeroth feature subset obtained by cross-validation method is 80%. The recursive feature elimination method uses all the feature training models in the zeroth feature subset to obtain the weight of each feature value. The model is a supervised learning model, and the present application can be a support vector machine. Feature 1, feature 3, feature 4 and feature 5 with high weights are selected as the first feature subset; the first feature subset is obtained by cross-validation method. The cycle is repeated successively, and feature 1, feature 3 and feature 5 with high weights are selected as the second feature subset; the second feature subset is obtained by cross-validation method. 85%. Based on the average score of each feature subset, the first feature subset is selected as the optimal feature subset.

[0044] In another exemplary embodiment of the present application, the multiple eigenvalues ​​include multiple time domain eigenvalues ​​and multiple frequency domain eigenvalues; the multiple time domain eigenvalues ​​include maximum value, minimum value, average value, peak-to-peak value, kurtosis factor, skewness factor and standard deviation; the multiple frequency domain eigenvalues ​​include power spectrum average value, power spectrum amplitude, power spectrum power value and power spectrum variance value.

[0045] Specifically, the calculation formula of the average value M is: Among them, x i is the true value of the ith sample, n is the total number of samples; the average value represents the central trend of the signal. The formula for calculating the peak-to-peak value PP is: PP = max(x i )-min(x i ); the peak-to-peak value represents the overall variation range of the signal. The standard deviation σ is calculated as: i is the i-th sample value of the signal; M is the signal average; the standard deviation represents the degree of fluctuation of the signal. The calculation formula of the kurtosis factor Kur is: The kurtosis factor indicates the peak height of the probability density distribution curve of the signal at the mean value. The calculation formula of the skewness factor Ske is: The skewness factor indicates how asymmetric the probability density distribution curve of a signal is relative to the mean.

[0046] In another exemplary embodiment of the present application, feature extraction is performed on the three-way vibration signal and the sound signal to obtain a plurality of feature values, and then the method further includes: normalizing the plurality of feature values ​​to obtain a plurality of processed feature values.

[0047] In another exemplary embodiment of the present application, step 204 specifically includes:

[0048] Multiple eigenvalues ​​in the optimal feature subset are taken as eigenvalue sequences and input into the long short-term memory network to obtain the hidden state of the eigenvalue sequence.

[0049] The hidden state of the eigenvalue sequence is input into the Kolmogorov-Arnold network to obtain the surface roughness of the part.

[0050] In another exemplary embodiment of the present application, the method for monitoring the surface roughness of a part during CNC machining further includes:

[0051] Train long short-term memory networks and Kolmogorov-Arnold networks.

[0052] When training the long short-term memory network and the Kolmogorov-Arnold network, the historical optimal feature subset is used as the input of the long short-term memory network and the Kolmogorov-Arnold network, the historical part surface roughness is used as a label, and the predicted part surface roughness is output. The historical part surface roughness is obtained by offline measurement.

[0053] The mean absolute error, root mean square error and mean absolute percentage error between the historical part surface roughness and the predicted part surface roughness are used as the optimization targets of the long short-term memory network and the Kolmogorov-Arnold network. The specific formula is as follows:

[0054]

[0055] Among them, RMSE is the root mean square error, MAE is the mean absolute error, MAPE is the mean absolute percentage error, n is the total number of samples, x is i is the true value of the i-th sample, y i is the predicted value of the ith sample. During the training process, 80% of the data is used to train the neural network, and 20% of the data is used to verify the performance of the network after training.

[0056] Among them, the Long Short-Term Memory Network (LSTM) is a recurrent neural network that introduces a gating mechanism to more effectively capture and process long-term dependencies in sequence data, such as Figure 4 As shown. LSTM can solve many time series tasks that feedforward networks cannot solve, and has shown excellent performance in prediction. These gates use the sigmoid activation function (the output range is (0,1), representing the probability value) to determine the degree of information flow: Among them, the forget gate (ForgetGate): determines which information in the cell state at the previous moment should be forgotten, and its output value is between 0 and 1 (0 means completely forgotten, 1 means completely retained), and the calculation formula is: f t =σ(W f ·[h t-1 ,x t ]+b f ), where σ is the s-type activation function, Wf and b f are the weight of the forget gate and the bias value of the forget gate, respectively, h t-1 and x t are the concatenation of the current input and the previous hidden state, respectively, t is the output of the forget gate.

[0057] The input gate consists of two parts: the decision gate and the candidate input gate, which decides which parts of the most recently input data should be added to the cell state at the current moment. The candidate input gate provides new candidate information that can be added to the cell state, and the input gate decides which new information is important enough to be written to the cell state.

[0058] i t =σ(W i ·[h t-1 ,x t ]+b i ); Among them, it is

[0059] The output of the input gate, W i and b i They are the weight of the input gate and the bias value of the input gate respectively; is the output of the candidate unit state, W C and b C are the weight of the candidate unit state and the bias value of the candidate unit state respectively.

[0060] o t =σ(W o ·[h t-1 ,x t ]+b o ), where o t is the output of the output gate, W o and b o They are the weights of the output gate and the bias values ​​of the output gate, respectively. They indicate how the output gate selects which unit state data should be sent as hidden states to the layers after it or used for final prediction at any given time.

[0061] Based on the above gating mechanism, LSTM updates the cell state and calculates the hidden state at the current moment. The cell state is updated Among them, C t is the unit state at the current moment, C t-1 is the unit state at the previous moment. Hidden state h t =o t ⊙tanh(C t ), where h tis the hidden state at the current moment. The results of hidden state calculation and cell state update generated by LSTM based on the above gate control mechanism are shown respectively. The cell state can be compressed into the range of (-1,1) by the tanh function for subsequent calculations, and the symbol ⊙ represents the multiplication of the value at the corresponding index.

[0062] The Kolmogorov-Arnold Network (Knowledge Attention Network, KAN) is a new neural network architecture that represents functions through learnable nonlinear transformations and summation operations on nodes, and can achieve higher accuracy in mathematical and physical problems with fewer parameters. In KAN, each connection is no longer a simple weight, but a learnable one-dimensional function. These functions are usually parameterized by splines or other smooth functions, so that the network can learn the nonlinear transformation that best suits the data in each dimension. However, the KAN network runs slowly because different activation functions cannot utilize batch calculations. This paper combines LSTM to construct a regression combination model. The LSTM layer extracts the time dependency in the input sequence, and the hidden state of the last time step is used as the input of the KAN layer, which is further processed by the KAN layer to generate the final output. Among them, the LSTM-KAN network architecture is as follows Figure 5 shown.

[0063] This application monitors the surface roughness of parts online in situ during CNC machining. When working parameters, tools, and materials change, only the model needs to be retrained, without repeatedly transmitting data and model debugging, training, and observation, which improves efficiency, expands the scope of application, and realizes roughness monitoring for flexible manufacturing. In the CNC machining process of precision optical parts, due to the variable feature evolution law caused by the time-varying dynamic characteristics of the cutting system, the characteristic values ​​of the signal are effectively screened by considering the correlation with the prediction results in the feature extraction, thereby improving the calculation efficiency and accuracy.

[0064] In another exemplary embodiment of the present application, taking CNC machining of titanium alloy parts as an example, a series of milling tests were carried out on the vertical milling machining center Mikron HEM 1000, using a carbide milling cutter, and the machining material was TC4 alloy with a size of 50mm×100mm×25mm. The milling experiments were carried out under different cutting parameter combinations and tool wear levels. In order to facilitate processing and considering that tool wear is insensitive to cutting width, the cutting width is set to 8mm, and the single pass is 100mm. In order to ensure the diversity and comprehensiveness of the cutting parameter combination, the Taguchi experimental design was selected, and other cutting parameters were determined based on the suggestions of the production department and preliminary experiments, as shown in Table 1.

[0065] Table 1 Variation range of working parameters during processing

[0066]

[0067]

[0068] The time domain and frequency domain features of the collected multi-source signals are extracted; the multi-source signal feature values ​​are screened, and the feature values ​​are trained for multiple rounds based on the recursive feature elimination method (RFE). After each round of training, several low-weight features are eliminated, and the next round of training is performed based on the new feature set. In order to avoid feature redundancy or filter out important features, after obtaining the feature ranking, model training and cross-validation (CV) are performed on feature subsets with different numbers of features, and finally the feature subset with the highest average score is selected. Model training is performed based on the feature subsets after feature selection and surface roughness data. After the model training is completed, the working parameters are changed, and the CNC machining test is carried out again. Multi-source signals are collected for online in-situ monitoring, and the detection values ​​are compared with the true values. Figure 6 The detection results are MAE: 0.03662, RMSE: 0.04746, and MAPE: 5.8816%. It can be seen that the detection accuracy is high and meets the needs of online original text monitoring.

[0069] Based on the same inventive concept, the embodiment of the present application also provides a monitoring system for the surface roughness of parts during CNC machining. Figure 7 As shown, the monitoring system for the surface roughness of parts during the CNC machining process includes:

[0070] The signal acquisition module 301 is used to collect the current three-way vibration signal and the current sound signal of the part during the CNC machining process.

[0071] The feature value acquisition module 302 is connected to the signal acquisition module 301 and is used to extract features from the three-way vibration signal and the sound signal to obtain multiple feature values; the multiple feature values ​​include multiple feature values ​​of the three-way vibration signal and multiple feature values ​​of the sound signal.

[0072] The optimal feature subset acquisition module 303 is connected to the feature value acquisition module and is used to obtain the optimal feature subset based on the multiple feature values ​​by using a recursive feature elimination method and a cross-validation method.

[0073] The surface roughness value acquisition module 304 is connected to the optimal feature subset acquisition module 303 and is used to obtain the surface roughness of the part based on the optimal feature subset by using a long short-term memory network and a Kolmogorov-Arnold network.

[0074] Specifically, the present application uses vibration sensors and sound sensors to collect vibration signals and sound signals during the milling process. The vibration sensor is adsorbed on the spindle through a magnetic seat, perpendicular to the feed direction, and anti-static treatment is performed to avoid signal interference. The sound sensor is placed on one side of the spindle and waterproofed to prevent the infiltration of cutting fluid. Both transmit and display the sampled signals on the PC through a data acquisition card, and collect data for further processing. The sampling frequency is 10khz, and signal acquisition is performed through trigger instructions to ensure that the collected signals are all signals in the effective processing process.

[0075] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for monitoring the surface roughness of parts during CNC machining is implemented.

[0076] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0077] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the above-mentioned method for monitoring the surface roughness of a part during a numerical control machining process.

[0078] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned method for monitoring the surface roughness of parts during numerical control machining when executed by a processor.

[0079] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0080] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0081] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0082] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0083] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for monitoring the surface roughness of parts during CNC machining, characterized in that: The method for monitoring the surface roughness of a part during numerical control machining includes: Real-time collecting the three-direction vibration signal and the sound signal of the part during numerical control machining; Performing feature extraction on the three-direction vibration signal and the sound signal to obtain a plurality of feature values; the plurality of feature values include a plurality of feature values of the three-direction vibration signal and a plurality of feature values of the sound signal; Based on the plurality of feature values, using the recursive feature elimination method and the cross-validation method to obtain an optimal feature subset; Based on the optimal feature subset, using the long short-term memory network and the Kolmogorov-Arnold network to obtain the surface roughness of the part.

2. The method for monitoring the surface roughness of parts during CNC machining according to claim 1, characterized in that: Based on the plurality of feature values, using the recursive feature elimination method and the cross-validation method to obtain an optimal feature subset, specifically including: For the Nth iteration, based on the (N-1)th feature subset, using the recursive feature elimination method to obtain the weight of each feature value in the (N-1)th feature subset; and using the cross-validation method to obtain the average score of the (N-1)th feature subset; 0 < N; when N = 1, the 0th feature subset includes all feature values; Based on the weight of each feature value in the (N-1)th feature subset, sorting the plurality of feature values in the (N-1)th feature subset, selecting a specified number of feature values with the top rankings as the Nth feature subset; and using the cross-validation method to obtain the average score of the Nth feature subset; determining whether the average score of the Nth feature subset is less than the average score of the (N-1)th feature subset; if so, stopping the iteration and taking the (N-1)th feature subset as the optimal feature subset; otherwise, performing the (N+1)th iteration.

3. The method for monitoring the surface roughness of parts during CNC machining according to claim 1, characterized in that: The plurality of feature values include a plurality of time-domain feature values and a plurality of frequency-domain feature values; the plurality of time-domain feature values include the maximum value, the minimum value, the average value, the peak-to-peak value, the kurtosis factor, the skewness factor, and the standard deviation; the plurality of frequency-domain feature values include the average value of the power spectrum, the amplitude of the power spectrum, the power value of the power spectrum, and the variance value of the power spectrum.

4. The method for monitoring the surface roughness of parts during CNC machining according to claim 1, characterized in that: After performing feature extraction on the three-direction vibration signal and the sound signal to obtain a plurality of feature values, the method for monitoring the surface roughness of the part during numerical control machining further includes: performing normalization processing on the plurality of feature values to obtain a plurality of processed feature values.

5. The method for monitoring the surface roughness of parts during CNC machining according to claim 1, characterized in that: Based on the optimal feature subset, using the long short-term memory network and the Kolmogorov-Arnold network to obtain the surface roughness of the part, specifically including: Taking the plurality of feature values in the optimal feature subset as a feature value sequence and inputting it into the long short-term memory network to obtain the hidden state of the feature value sequence; Inputting the hidden state of the feature value sequence into the Kolmogorov-Arnold network to obtain the surface roughness of the part.

6. The method for monitoring the surface roughness of parts during CNC machining according to claim 1, characterized in that: The method for monitoring the surface roughness of the part during numerical control machining further includes: Training the long short-term memory network and the Kolmogorov-Arnold network; When training the long short-term memory network and the Kolmogorov-Arnold network, taking the historical optimal feature subset as the input of the long short-term memory network and the Kolmogorov-Arnold network, taking the historical surface roughness of the part as the label, and outputting the predicted surface roughness of the part. The mean absolute error, root mean square error and mean absolute percentage error between the historical part surface roughness and the predicted part surface roughness are used as the optimization objectives of the long short-term memory network and the Kolmogorov-Arnold network.

7. A system for monitoring the surface roughness of parts during CNC machining, using the method for monitoring the surface roughness of parts during CNC machining according to any one of claims 1 to 6, characterized in that: The monitoring system for the surface roughness of parts during the CNC machining process includes: Signal acquisition module, used to collect three-way vibration signals and sound signals of parts during CNC machining in real time; A feature value acquisition module, connected to the signal acquisition module, for extracting features from the three-way vibration signal and the sound signal to obtain a plurality of feature values; the plurality of feature values ​​include a plurality of feature values ​​of the three-way vibration signal and a plurality of feature values ​​of the sound signal; An optimal feature subset acquisition module, connected to the feature value acquisition module, for obtaining an optimal feature subset based on the multiple feature values ​​by using a recursive feature elimination method and a cross-validation method; The surface roughness value acquisition module is connected to the optimal feature subset acquisition module and is used to obtain the surface roughness of the part based on the optimal feature subset by using a long short-term memory network and a Kolmogorov-Arnold network.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for monitoring the surface roughness of parts during CNC machining according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for monitoring the surface roughness of a part during a numerical control machining process according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for monitoring the surface roughness of a part during a numerical control machining process according to any one of claims 1 to 6 is implemented.

Images