Multi-type signal-based tool wear state monitoring method and system

Abstract

A multi-type signal-based tool wear state monitoring method and system. The method comprises: acquiring cutting force, acoustic emission signal and vibration signal data, and extracting a plurality of statistical features from the cutting force and acoustic emission signal data; extracting singularity features of a vibration signal on the basis of singularity analysis and wavelet transform; constructing a random forest-based tool wear state monitoring model, using the obtained features to perform preliminary training, and outputting a wear prediction result; if the preliminary prediction result satisfies a preset condition, acquiring real-time cutting force, acoustic emission signal and vibration signal data, and monitoring the wear state of a tool by means of a preliminarily trained model, or otherwise, determining key features by means of feature importance evaluation, and using the key features to finely train the model; and on the basis of the real-time cutting force, acoustic emission signal and vibration signal data, monitoring the wear state of the tool by means of the finely trained model. According to the tool wear state monitoring method and system, excessive consumption of computing resources is avoided, the real-time performance and processing efficiency of the system are improved, the ability of the model to identify an early wear state is improved, and monitoring precision is significantly improved.

Description

A tool wear state monitoring method and system based on multiple types of signals TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a tool wear state monitoring method and system based on multiple types of signals. BACKGROUND

[0002] Tool wear is one of the key factors affecting machining precision and product quality in manufacturing. In precision manufacturing, the wear state of the tool directly affects the machining quality, production efficiency and the service life of the equipment. With the continuous development of industrial automation and intelligent manufacturing, tool wear monitoring technology has gradually become an important means to improve production efficiency and reduce costs. Currently, there are various methods for monitoring tool wear, including acoustic signals, vibration signals, temperature signals, and current signals. With the development of technology, single signal monitoring gradually cannot meet the demand for high precision and high efficiency. Therefore, comprehensive monitoring methods based on multiple types of signals have gradually become a research hotspot, which can achieve more comprehensive and accurate tool wear state evaluation.

[0003] With the progress of technology, in recent years, monitoring methods based on multiple types of signal fusion have gradually appeared. These methods combine the features of multiple signals, such as vibration, acoustics, temperature, and current, for comprehensive analysis, thereby improving the accuracy and reliability of tool wear monitoring.

[0004] However, although the existing multi-signal fusion method can make up for the shortcomings of single signal, it still faces the problems of complex signal processing and large amount of calculation, which is difficult to meet the real-time demand. In addition, due to the nonlinearity and uncertainty of the tool wear process, the monitoring accuracy of the existing method is low when the signal changes are not significant in the early stage of wear. SUMMARY

[0005] In order to solve the technical problems that the existing multi-signal fusion method can make up for the shortcomings of single signal, but still faces the problems of complex signal processing and large amount of calculation, which is difficult to meet the real-time demand. In addition, due to the nonlinearity and uncertainty of the tool wear process, the monitoring accuracy of the existing method is low when the signal changes are not significant in the early stage of wear, the present application provides a tool wear state monitoring method and system based on multiple types of signals.

[0006] The technical scheme provided by the embodiments of the present application is as follows:

[0007] First aspect:

[0008] The tool wear state monitoring method based on multiple types of signals provided by the embodiments of the present application comprises:

[0009] S1: acquiring cutting force data, acoustic emission signal data and vibration signal data of a tool in a machining process;

[0010] S2: extracting a plurality of statistical features of the cutting force data and the acoustic emission signal data;

[0011] S3: extracting a singular point feature of the vibration signal data through singularity analysis combined with wavelet transform;

[0012] S4: constructing a tool wear state monitoring model based on a random forest;

[0013] S5: taking each statistical feature and the singular point feature as input, preliminarily training the tool wear state monitoring model, and outputting a preliminary tool wear result;

[0014] S6: judging whether the preliminary tool wear result meets a preset condition; if yes, proceeding to S9; otherwise, proceeding to S7;

[0015] S7: using the preliminarily trained tool wear state monitoring model to evaluate feature importance of each statistical feature and the singular point feature, and determining a key feature affecting a tool wear state;

[0016] S8: finely training the tool wear state monitoring model according to the key feature;

[0017] S9: acquiring real-time cutting force data, real-time acoustic emission signal data and real-time vibration signal data;

[0018] S10: monitoring the tool wear state of the tool through the trained tool wear state monitoring model according to the real-time cutting force data, the real-time acoustic emission signal data and the real-time vibration signal data.

[0019] The second aspect:

[0020] The embodiment of the application provides a tool wear state monitoring system based on multiple types of signals, which comprises:

[0021] a processor;

[0022] a memory, wherein the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to realize the tool wear state monitoring method based on multiple types of signals.

[0023] The third aspect:

[0024] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the tool wear state monitoring method based on multiple types of signals.

[0025] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0026] (1) In the embodiment of the present application, the processing flow of the original signal is effectively simplified by extracting statistical features and combining wavelet transform and singularity analysis, and the computational complexity is significantly reduced. The tool wear state monitoring model constructed by the random forest can efficiently process large-scale features, thereby avoiding excessive consumption of computing resources and improving the real-time performance and processing efficiency of the system.

[0027] (2) In the embodiment of the present application, the preliminary training model can provide effective wear judgment in the early stage of weak signal change, and ensure that preliminary prediction can be performed even when the signal change is not significant. At the same time, by evaluating the importance of the features, the key features affecting the tool wear are screened out, so that the model can focus on the features that can effectively distinguish the wear state when the signal change is small in the early stage. Based on the key features, the model is finely trained, which further improves the recognition ability of the model to the early wear state, thereby significantly improving the monitoring accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Fig. 1 is a flowchart of a tool wear state monitoring method based on multiple types of signals provided by the embodiment of the present application;

[0030] Fig. 2 is a structural diagram of a tool wear state monitoring system based on multiple types of signals provided by the embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the present application will be described below with reference to the drawings.

[0032] In the embodiments of the present application, the words such as "example", "for example" are used to represent an example, illustration, or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0033] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. "Of", "corresponding" and "corresponding" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0034] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1, and the meanings expressed are consistent when the distinction is not emphasized.

[0035] In order to make the technical problems, technical schemes and advantages to be solved by the present application more clear, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0036] Referring to FIG. 1 of the specification, a flowchart of a multi-type signal-based tool wear state monitoring method according to an embodiment of the present application is shown.

[0037] The embodiments of the present application provide a multi-type signal-based tool wear state monitoring method, which can be implemented by a multi-type signal-based tool wear state monitoring device. The multi-type signal-based tool wear state monitoring device can be a terminal or a server. The processing flow of the multi-type signal-based tool wear state monitoring method can include the following steps:

[0038] S1: Obtain cutting force data, acoustic emission signal data and vibration signal data of the tool in the machining process.

[0039] Specifically, the cutting force data is obtained by using a force sensor, and a three-axis force sensor (or a force / torque sensor) is usually used to measure the cutting force. The sensor can measure the cutting force of the tool in three directions (X, Y, Z).

[0040] The acoustic emission signal data is obtained by using an acoustic emission signal data acquisition system (such as an oscilloscope with appropriate bandwidth, a digital acoustic emission system) for real-time acquisition. Since the acoustic emission signal frequency is high, a sampling frequency of 100 kHz or higher is usually required to ensure accurate capture of the signal.

[0041] The vibration signal data is obtained, and an acceleration sensor or a vibration sensor (e.g., a piezoelectric sensor) can be used to measure the vibration signal generated by the tool during machining.

[0042] S2: Extracting multiple statistical features of the cutting force data and the acoustic emission signal data.

[0043] In a possible implementation, the statistical features specifically include:

[0044] The maximum value, the median, the mean, the standard deviation, the peak value, and the root mean square of the cutting force data.

[0045] The maximum value, the median, the mean, the standard deviation, and the root mean square of the acoustic emission signal data.

[0046] In the present application, by extracting multiple statistical features of the cutting force data and the acoustic emission signal data, the complex time series data can be converted into simple and structured features, making the model easy to process. At the same time, different statistical features can describe different aspects of the signal, helping the model to better understand the signal.

[0047] S3: Extracting singularity point features of the vibration signal data by singularity analysis combined with wavelet transform.

[0048] The singularity analysis is a signal processing technique used to detect abrupt points, singular points, or irregularities in signals. It is particularly suitable for analyzing signals with non-stationary and nonlinear characteristics, such as mechanical vibration signals, acoustic emission signals, and seismic wave signals.

[0049] The wavelet transform is a powerful signal processing tool that can analyze the characteristics of signals at different scales and frequencies. Unlike traditional Fourier transform, wavelet transform not only provides frequency domain information but also preserves the time domain information of the signal, making it very suitable for processing non-stationary signals such as mechanical vibration and acoustic signals.

[0050] In a possible implementation, S3 specifically includes:

[0051] S301: Using wavelet transform to analyze the multi-scale features of the vibration signal data.

[0052] Optionally, the wavelet transform selects the Mexican Hat wavelet.

[0053] Mexican Hat wavelet is a commonly used wavelet function with good time-frequency localization properties. Mexican Hat wavelet is chosen because it can effectively detect mutations and sharp features in the signal, especially suitable for vibration signal analysis.

[0054] Specifically, wavelet transform is performed on the vibration signal data to extract the features of the signal from multiple scales (frequency intervals). Through wavelet transform, you can obtain the components of the signal in low and high frequency regions, revealing the multi-scale characteristics of the signal.

[0055] S302: Perform modulus maxima analysis on the wavelet transform coefficients at each scale to determine the number and intensity of the maximum points.

[0056] It should be noted that modulus maxima analysis is performed on the wavelet transform coefficients to extract local maximum points. These maximum points usually correspond to irregularities or mutations in the signal.

[0057] S303: Calculate the Lipschitz exponent at each scale based on the number and intensity of the maximum points:

[0058] where α q represents the Lipschitz exponent at the qth scale, N q represents the number of maximum points at the qth scale, m p represents the pth maximum point, m p-1 represents the p-1th maximum point, I(m p ) represents the intensity of the pth maximum point, I(m p-1 ) represents the intensity of the p-1th maximum point, and log represents the logarithmic function.

[0059] where the Lipschitz exponent is a mathematical index used to describe the smoothness or mutation of a function or signal at a certain position. It is a quantitative description of Lipschitz continuity, widely used in signal analysis, image processing, and machine learning, especially in processing non-stationary signals and mutation characteristics.

[0060] It should be noted that the larger α q , the smoother the signal at the qth scale. Conversely, the smaller α q , the more obvious the mutation characteristics of the signal at that scale.

[0061] In the present application, the Lipschitz exponent can quantify the smoothness of the signal. When there is a sudden change in the signal (such as tool wear, crack or equipment failure), the Lipschitz exponent will significantly decrease, reflecting that the change in the signal is no longer smooth. In this way, the Lipschitz exponent can help the model automatically identify sudden events or abnormal changes.

[0062] S304: Weighted average of the Lipschitz exponent on each scale to obtain the comprehensive Lipschitz exponent of the vibration signal data:

[0063] where HE represents the comprehensive Lipschitz exponent, Q represents the total number of scales after wavelet transform decomposition, N k represents the number of maximum points on the kth scale, represents the sum of the number of maximum points on the Q scales.

[0064] In the present application, the comprehensive Lipschitz exponent is obtained by weighted average of the Lipschitz exponent on each scale, which combines the mutation information of the signal at different scales and can provide a more comprehensive signal description. This weighted average makes the model more sensitive to changes in different frequency bands of the signal, thereby improving the overall prediction ability.

[0065] S305: Output the comprehensive Lipschitz exponent as a singular point feature.

[0066] S4: Construct a tool wear state monitoring model based on random forest.

[0067] where the tool wear state monitoring model based on random forest (RF) is a prediction model that combines machine learning and sensor data, which can monitor the wear state of the tool in real time. Random forest is a powerful ensemble learning method widely used in regression and classification problems. This model is particularly suitable for handling complex, multi-dimensional data involved in tool wear monitoring.

[0068] In one possible implementation, S4 specifically includes:

[0069] S401: Based on each statistical feature, construct an original data set: D={(x1,y1),(x2,y2),...,(x N ,y N )}

[0070] where D represents the original data set, x i represents the feature vector of the ith sample, y iyi, i = 1, 2, 3…, N, N represents the number of samples in the data set.

[0071] S402: Randomly generate a plurality of bootstrap samples from the original data set. Each bootstrap sample contains a plurality of sample data.

[0072] In the present application, the plurality of samples generated by the bootstrap sample can train each tree on an independent sample set, avoiding the problem of overfitting due to certain specific data points.

[0073] S403: Based on each bootstrap sample, a plurality of decision trees are constructed:

[0074] wherein T b (x, h b ) represents the prediction value of the bth decision tree on the input data x, x represents the input data point, h b represents the tree structure of the bth decision tree, M represents the total number of leaf nodes in the decision tree, μ m represents the average value of the target values of all samples in the mth leaf node, R m represents the sample set of the mth leaf node I() represents an indicator function, I(xεR m ) = 1 indicates that the sample x belongs to the leaf node R m , I(xεR m ) = 0 indicates that the sample x does not belong to the leaf node R m .

[0075] In one possible implementation, S403 specifically includes:

[0076] S4031: Select a plurality of split variables in the bootstrap sample.

[0077] S4032: Select a split point in each split variable, and split each split variable into two subsets based on the split point: R1(j, s) = {X | X j ≤ s}, R2(j, s) = {X | X j > s}

[0078] wherein R1 represents the left subset after splitting, R2 represents the right subset after splitting, X represents a single sample in the data set, X j represents the jth feature of the sample, and s represents the split point.

[0079] In the present application, by randomly selecting split variables, it is ensured that the knowledge learned by each tree is different, avoiding the case that all trees learn the same features, thereby enhancing the generalization ability of the model.

[0080] S4033: Determine the optimal split point to minimize the residual sum of squares of each subset:

[0081] where min denotes minimization, m1 denotes the mean of the target variable in the left subset, x i denotes the feature vector of the i-th sample, R1 denotes the left subset after splitting, y i denotes the target variable of the i-th sample, m2 denotes the mean of the target variable in the right subset, R2 denotes the right subset after splitting, j denotes the feature, and s denotes the split point.

[0082] In the present application, by selecting the optimal split point (i.e., minimizing the residual sum of squares of the subset), the model can split the data into more pure subsets, thereby improving the prediction accuracy of the tool wear state.

[0083] S4034: According to the optimal split point, split the current node into left and right child nodes, and recursively perform steps S4031 to S4034 on the left and right child nodes.

[0084] S4035: When the number of samples in the bootstrap sample is less than a preset number or the depth of the tree reaches the maximum depth, stop splitting and complete the construction of each decision tree.

[0085] S404: Combine each decision tree to construct a tool wear state monitoring model:

[0086] where, denotes the final prediction value of the random forest for input data x, B denotes the total number of trees in the random forest, x denotes the input data point, h b denotes the tree structure of the b-th decision tree, T b (x, h b ) denotes the prediction value of the b-th decision tree on the input data x.

[0087] In summary, by recursively splitting the nodes, the random forest can extract the features of the data at multiple levels, capture different patterns of tool wear state changes, provide more comprehensive predictions, reduce the bias and variance of a single tree, and make the model more accurate in predicting tool wear.

[0088] S5: Use each statistical feature and outlier feature as input to preliminarily train the tool wear state monitoring model and output a preliminary tool wear result.

[0089] S6: Determine whether the preliminary tool wear result meets the preset condition. If yes, go to S9. Otherwise, go to S7.

[0090] In a possible implementation, the preset condition is specifically that the prediction accuracy of the preliminary tool wear result is greater than 80%.

[0091] S7: using the preliminarily trained tool wear state monitoring model, performing feature importance evaluation on the statistical features and the singular point features, and determining key features affecting the tool wear state.

[0092] The feature importance evaluation is a technique in machine learning for measuring the contribution degree of each feature to model prediction. By evaluating the feature importance, it can be identified which features have stronger prediction ability for the target variable (such as the tool wear state), so as to optimize the model, improve the prediction accuracy, and reduce redundant features.

[0093] In a possible implementation, S7 specifically includes:

[0094] S701: calculating the feature importance evaluation value of each statistical feature and singular point feature by the following formula: Δ i (s t ,t)=i(t)-p1i(t1)-p2i(t2)

[0095] Wherein, VarImp(x i ) represents the importance evaluation value of the feature x i , T represents a decision tree in the random forest, N T represents the total number of trees in the random forest, v(s t ) represents the feature of the tth split node, v(s t ) = x i represents that the feature of the tth split node is obtained by splitting the feature xi, p(t) represents the sample proportion in the node t, Δ i (s t ,t) represents the residual sum of squares reduction amount brought by the feature x i when the tth node is split, i(t) represents the residual sum of squares of the tth node, p1 represents the sample proportion of the left child node, p2 represents the sample proportion of the right child node, i(t1) represents the residual sum of squares of the left child node, i(t2) represents the residual sum of squares of the right child node, R1 represents the left subset after splitting, R2 represents the right subset after splitting, x i represents the ith sample, y i represents the target variable of the ith sample, represents the mean of the target variable of the samples in the left subset, represents the mean of the target variable of the samples in the right subset.

[0096] In the present application, by analyzing the feature importance, it can be intuitively understood how the model makes decisions. For the tool wear monitoring model, it can be clearly known which features (such as the mean of cutting force, the standard deviation of vibration, etc.) are most critical to the prediction of the wear state, thereby providing valuable information for maintenance personnel. At the same time, features that are not relevant or have less impact on the target variable will be underestimated in importance, and redundant features can be effectively removed, thereby simplifying the subsequent model and improving computational efficiency.

[0097] It should be noted that Δ i (s t The greater the value, the more helpful the feature is to the prediction of the target variable.

[0098] S702: Sort the feature importance evaluation values in descending order, and select the features corresponding to the top feature importance evaluation values as key features.

[0099] In the present application, by using only features with strong predictive ability for the target variable (tool wear state), the model can reduce the interference of noise and focus on key features, thereby improving the overall prediction performance of the model. At the same time, it is clear which features (such as certain statistical features in the cutting force, vibration or acoustic emission signal) have the greatest impact on wear prediction, which can provide valuable guidance for further tool management and maintenance. First use these features to improve the efficiency of real-time decision-making.

[0100] S8: Fine-tune the tool wear state monitoring model according to the key features.

[0101] In one possible implementation, the fine-tuning of the tool wear state monitoring model is specifically as follows:

[0102] The tool wear state monitoring model is fine-tuned by an improved particle swarm optimization algorithm, with the goal of minimizing the function value of the mean square error loss function.

[0103] The mean square error loss function is specifically as follows:

[0104] Wherein, MSE represents the mean square error loss function, y i represents the true target value of the i-th sample, and represents the predicted value of the i-th sample, and N represents the total number of samples in the data set.

[0105] Optionally, the improved particle swarm optimization algorithm specifically includes:

[0106] S801: Initialize the particle swarm, which contains multiple particles, each particle representing a feasible solution.

[0107] S802: Improve the fitness function of the particle swarm optimization algorithm with the inverse of the mean squared error loss function.

[0108] S803: Calculate the fitness function value for each particle in the swarm.

[0109] S804: Update the position of the particle with the highest fitness value to the global optimum.

[0110] S805: Determine the neighborhood of each particle, and based on the particle information within the neighborhood, determine the local optimal position of the particle with the highest fitness value within the neighborhood.

[0111] In this invention, the search capability of particles within a local region can be improved by guiding them to their local optimal position and sharing neighborhood information. Particles adjust their positions based on the particle with the highest fitness value in their neighborhood, thereby improving the accuracy of the local search.

[0112] S806: Update the particle's velocity and position using the following formula: V u =ωV u +c1r1(Pbset u -X u )+c2r2(Gbset-X u )

[0113] Among them, V u Let ω represent the particle velocity, ω represent the inertial weight, c1 and c2 represent the acceleration constants, and r1 and r2 represent random numbers. Pbest u Gbest represents the historical best position of the u-th particle, and Gbest represents the global best position.

[0114] S807: Generate a random number and determine if the generated random number is less than the preset mutation probability. If yes, proceed to S808. Otherwise, proceed to S809.

[0115] S808: Using a mutation operation, update the particle's position using the following formula, and then proceed to S812: T uv =X uv +A(Lbest-X uv )

[0116] Among them, T uv X represents the position of the u-th particle after mutation in the v-th dimension. uv This represents the current position information of the u-th particle in the v-th dimension, and A represents the magnification factor.

[0117] S809: Apply a random permutation function to the local optimum to increase the diversity of the solution space: Lbest := permuting(Lbest)

[0118] wherein Lbest represents the optimal solution position found by the particle in its neighborhood, and permuting() represents a random permutation function.

[0119] In the present application, by introducing the mutation operation and local solution space permutation, the diversity of the solution space can be maintained during the optimization process, the global search ability is enhanced, and a better solution can be found.

[0120] S810: Generate the trial position of the particle through the following formula: Mutant = X + F(Lbest-X)

[0121] wherein Mutant represents the mutated particle position, X represents the current position of the particle, Lbest represents the local optimal position, and F represents the amplification factor.

[0122] S811: Perform a crossover operation on the current particle using a crossover operator to generate the solution of the next offspring, and enter S812.

[0123] S812: Calculate the fitness of each particle and update the global optimal position according to the fitness of the particle.

[0124] S813: Determine whether the maximum number of iterations is met, if yes, output the optimal result, otherwise, return to S805.

[0125] S9: Obtain real-time cutting force data, real-time acoustic emission signal data, and real-time vibration signal data.

[0126] S10: According to the real-time cutting force data, the real-time acoustic emission signal data and the real-time vibration signal data, the tool wear state of the tool is monitored through the trained tool wear state monitoring model.

[0127] Optionally, the tool wear state is divided into light wear, moderate wear and severe wear.

[0128] Specifically, the real-time cutting force data, the real-time acoustic emission signal data and the real-time vibration signal data are obtained, the key features affecting the tool wear state are found according to the feature importance analysis result, the key features are mainly used, and the remaining features are used as auxiliary, which are input into the trained tool wear state monitoring model, and the tool wear state is output.

[0129] In the present application, by selecting key features based on feature importance analysis and inputting them into the trained tool wear state monitoring model, the prediction accuracy and computational efficiency of the model can be significantly improved. In this way, not only the performance of the model is optimized, the redundant features and computational burden are reduced, but also the stability and robustness of the model are enhanced, avoiding overfitting. At the same time, by focusing on the most relevant features, more accurate and flexible decision support can be provided for real-time monitoring of tool wear state, reducing maintenance costs and improving the real-time response capability and adaptability of the system.

[0130] In one possible implementation, after S10, it further includes:

[0131] Recording the tool wear state to generate a tool wear state report.

[0132] In the present application, real-time recording of tool wear state can provide valuable historical data for subsequent analysis. By tracking the wear changes of each tool throughout its life cycle, it can clearly trace back to any specific time point, helping engineers understand the trend of wear and historical events. This has important value for later maintenance decisions and optimized operations.

[0133] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0134] (1) In the embodiments of the present application, by extracting statistical features and combining wavelet transform and singularity analysis, the processing flow of the original signal is effectively simplified, and the computational complexity is significantly reduced. The tool wear state monitoring model constructed by random forest can efficiently process large-scale features, thereby avoiding excessive consumption of computing resources and improving the real-time performance and processing efficiency of the system.

[0135] (2) In the embodiments of the present application, by preliminarily training the model, effective wear judgment can be provided in the early stage of weak signal change, ensuring that preliminary prediction can be made even when signal change is not significant. At the same time, by evaluating the feature importance, key features affecting tool wear are selected, ensuring that the model focuses on features that can effectively distinguish the wear state when the signal changes slightly in the early stage. Based on the key features, the model is fine-tuned, further improving the recognition ability of the model for early wear state, thereby significantly improving the monitoring accuracy.

[0136] Referring to FIG. 2 of the specification, a structural schematic diagram of a tool wear state monitoring system based on multiple types of signals is shown.

[0137] The present application also provides a tool wear state monitoring system 20 based on multiple types of signals, which is applied to the tool wear state monitoring method based on multiple types of signals described above, and includes:

[0138] The processor 201.

[0139] The memory 202, wherein the computer readable instructions stored on the memory 202 are executed by the processor 201 to implement the tool wear state monitoring method based on multiple types of signals as in the method embodiment.

[0140] The tool wear state monitoring system 20 based on multiple types of signals provided by the present application can execute the tool wear state monitoring method based on multiple types of signals as described above, and achieve the same or similar technical effects. To avoid repetition, the present application will not be described again.

[0141] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0142] (1) In the embodiments of the present application, the processing process of the original signal is effectively simplified by extracting statistical features and combining wavelet transform and singularity analysis, and the computational complexity is significantly reduced. The tool wear state monitoring model constructed by the random forest can efficiently process large-scale features, thereby avoiding excessive consumption of computing resources and improving the real-time performance and processing efficiency of the system.

[0143] (2) In the embodiments of the present application, the preliminary training model can provide effective wear judgment in the early stage of weak signal change, ensuring that preliminary prediction can be made even when the signal change is not significant. At the same time, by evaluating the importance of features, the key features affecting tool wear are screened out, ensuring that the model focuses on features that can effectively distinguish the wear state when the signal change is small in the early stage. Based on the key features, the model is fine-tuned, further improving the recognition ability of the model for early wear state, thereby significantly improving the monitoring accuracy.

[0144] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0145] It should also be understood that the memory in the embodiments of the present application can be volatile or nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be random access memory (RAM) used as external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0146] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0147] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0148] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0149] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0150] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0151] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0152] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0154] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0155] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the tool wear condition monitoring method based on multiple types of signals as described in the method embodiment.

[0157] The present invention provides a computer-readable storage medium that can implement the steps and effects of the tool wear condition monitoring method based on multiple types of signals in the above-described method embodiments. To avoid repetition, the present invention will not elaborate further.

[0158] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0159] (1) In this embodiment of the invention, by extracting statistical features and combining wavelet transform and singularity analysis, the processing flow of the original signal is effectively simplified, and the computational complexity is significantly reduced. The tool wear state monitoring model constructed using random forest can efficiently process large-scale features, thereby avoiding excessive consumption of computing resources and improving the system's real-time performance and processing efficiency.

[0160] (2) In this embodiment of the invention, by initially training the model, effective wear judgment can be provided in the early stage when signal changes are weak, ensuring that preliminary predictions can be made even when signal changes are not significant. Simultaneously, by evaluating the importance of features, key features affecting tool wear are selected, ensuring that the model focuses on those features that can still effectively distinguish wear states when signal changes are small in the early stages. Fine-tuning the model based on these key features further enhances its ability to identify early wear states, thereby significantly improving monitoring accuracy.

[0161] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0162] The following points need to be explained:

[0163] (1) The attached drawings of the embodiments of the present application only involve the structures involved in the embodiments of the present application, and other structures can be referred to the general design.

[0164] (2) In order to be clear, the thickness of the layer or area is enlarged or reduced in the drawings used for describing the embodiments of the present application, that is, the drawings are not drawn according to the actual proportion. It can be understood that when the elements such as layers, films, areas or substrates are referred to as being located "on" or "under" another element, the element can be "directly" located "on" or "under" another element or there can be intermediate elements.

[0165] (3) In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other to obtain new embodiments.

[0166] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for monitoring tool wear condition based on multiple signal types, characterized in that, include: S1: Acquire cutting force data, acoustic emission signal data, and vibration signal data of the tool during the machining process; S2: Extract multiple statistical features from the cutting force data and the acoustic emission signal data; S3: Extract the singularity features of the vibration signal data by combining singularity analysis with wavelet transform; S4: Construct a tool wear condition monitoring model based on random forest; S5: Using the statistical features and the singular point features as inputs, perform preliminary training on the tool wear state monitoring model and output preliminary tool wear results; S6: Determine whether the preliminary tool wear result meets the preset conditions; If so, proceed to S9; Otherwise, proceed to S7; S7: Using the pre-trained tool wear state monitoring model, evaluate the feature importance of each statistical feature and the singular point feature to determine the key features affecting the tool wear state. S8: Based on the key features, perform fine training on the tool wear condition monitoring model; S9: Acquire real-time cutting force data, real-time acoustic emission signal data, and real-time vibration signal data; S10: Based on the real-time cutting force data, the real-time acoustic emission signal data, and the real-time vibration signal data, the tool wear state of the tool is monitored using the trained tool wear state monitoring model.

2. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, The statistical characteristics specifically include: The maximum value, median, mean, standard deviation, peak value, and root mean square of the cutting force data; The maximum value, median, mean, standard deviation, and root mean square of the acoustic emission signal data.

3. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, S3 specifically includes: S301: Use wavelet transform to analyze the multi-scale characteristics of the vibration signal data; S302: Perform modulus maxima analysis on the wavelet transform coefficients at various scales to determine the number and intensity of maxima points; S303: Calculate the Lipschitz index at each scale based on the number and intensity of the maxima: Where, α q Let N represent the Lipschitz index at the q-th scale. q m represents the number of maxima at the q-th scale. p Let m represent the p-th local maximum. p-1 Let I(m) represent the (p-1)th local maximum. p I(m) represents the intensity of the p-th maximum point. p-1 ) represents the intensity of the (p-1)th maximum point, and log represents the logarithmic function; S304: Calculate the weighted average of the Lipschitz indices at each scale to obtain the comprehensive Lipschitz index of the vibration signal data. Where HE represents the comprehensive Lipschitz exponent, Q represents the total number of scales after wavelet transform, and N... k This represents the number of maxima at the k-th scale. This represents the sum of the number of maxima on Q scales; S305: Output the comprehensive Lipschitz index as the singularity feature.

4. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, S4 specifically includes: S401: Construct the original dataset based on each of the aforementioned statistical features; S402: Randomly generate multiple bootstrap samples from the original dataset; wherein each bootstrap sample contains multiple sample data; S403: Based on each of the aforementioned bootstrap samples, construct multiple decision trees: Among them, T b (x,h b ) represents the prediction value of the b-th decision tree on the input data x, where x represents the input data point, and h b Let M represent the tree structure of the b-th decision tree, and let μ represent the total number of leaf nodes in the decision tree. m R represents the average of the target values ​​of all samples in the m-th leaf node. m I() represents the sample set of the m-th leaf node, and I(x∈R) represents the indicator function. m ) = 1 indicates that sample x belongs to leaf node R m ,I(x∈R) m ) = 0 indicates that sample x does not belong to the leaf node R. m ; S404: Combine the decision trees to construct the tool wear condition monitoring model: in, Let B represent the final prediction value of the random forest for the input data x, where B represents the total number of trees in the random forest, x represents the input data point, and h represents the final prediction value of the random forest for the input data x. b Let T represent the tree structure of the b-th decision tree. b (x,h b ) represents the predicted value of the b-th decision tree on the input data x.

5. The tool wear condition monitoring method based on multiple signal types according to claim 4, characterized in that, Specifically, S403 includes: S4031: Select multiple splitting variables from the bootstrap sample; S4032: Select a split point among the split variables and divide each split variable into two subsets, left and right, based on the split point; S4033: Determine the optimal split point with the objective of minimizing the sum of squared residuals for each subset: Where min represents minimization, μ1 represents the mean of the objective variable in the left subset, and x i Let y represent the feature vector of the i-th sample, R1 represent the left subset after splitting, and y i Let represent the target variable of the i-th sample, μ2 represent the mean of the target variable in the right subset, R2 represent the right subset after splitting, j represent the feature, and s represent the split point; S4034: Based on the optimal split point, divide the current node into a left child node and a right child node, and recursively execute steps S4031 to S4034 on the left child node and the right child node. S4035: When the number of samples in the self-service sample is lower than the preset number or the depth of the tree reaches the maximum depth, stop splitting and complete the construction of each decision tree.

6. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, The preset condition is specifically: the prediction accuracy of the preliminary tool wear result is greater than 80%.

7. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, Specifically, S7 includes: S701: Calculate the feature importance evaluation value of each of the statistical features and the singular point features using the following formula: Δ i (s t ,t)=i(t)-p1i(t1)-p2i(t2) Among them, VarImp(x i ) represents feature x i Importance evaluation value, T represents a decision tree in the random forest, N T v(s) represents the total number of trees in the random forest. t ) represents the feature of the t-th split node, v(s) t )=x i The feature of the t-th split node is represented by feature x. i The split yields p(t), which represents the proportion of samples in node t, Δ i (s t ,t) represents feature x i The reduction in the sum of squared residuals resulting from splitting at the t-th node, where i(t) represents the sum of squared residuals at the t-th node, p1 represents the proportion of samples from the left child node, p2 represents the proportion of samples from the right child node, i(t1) represents the sum of squared residuals from the left child node, i(t2) represents the sum of squared residuals from the right child node, R1 represents the left subset after splitting, R2 represents the right subset after splitting, and x i Let y represent the i-th sample. i Let i represent the target variable for the i-th sample. This represents the mean of the target variable for the samples in the left subset. This represents the mean of the target variable for the samples in the right subset; S702: Sort the importance evaluation values ​​of each feature in descending order, and select the feature corresponding to the feature with the highest importance evaluation value as the key feature.

8. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, The specific method for fine-tuning the tool wear condition monitoring model is as follows: With the goal of minimizing the mean square error loss function, the tool wear condition monitoring model is finely trained using an improved particle swarm optimization algorithm.

9. The tool wear condition monitoring method based on multiple signal types according to claim 1, characterized in that, Following S10, the following is also included: The wear condition of the tool is recorded, and a tool wear condition report is generated.

10. A tool wear condition monitoring system based on multiple signal types, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the tool wear condition monitoring method based on multiple types of signals as described in any one of claims 1 to 9.

Images