A method and system for detecting the vibration of a machine tool

Abstract

The present invention relates to the technical field of machine tool vibration detection, and discloses a method and system for detecting machine tool vibration. The method includes: collecting vibration signals in each area to form a first multi-source independent signal dataset; performing de-mixing processing on partially aliased vibration signals; extracting time-frequency characteristics of machine tool vibration; constructing a feature vector set according to the extracted characteristics and inputting it into a machine tool vibration classification model; quantifying the contribution ratio of each vibration source. Compared with the prior art, which can only collect and simply analyze vibration signals in a single area of the machine tool, especially under the conditions of complex vibration signal sources and multi-source aliasing, it is impossible to accurately separate and identify vibration sources. Since the present application combines signal de-mixing with a dynamic convolutional neural network classification model, it realizes precise collection, separation, analysis and identification of multi-area vibration signals of the machine tool, thereby avoiding the problem of inaccurate detection results and improving the accuracy of machine tool vibration detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of machine tool vibration detection, and particularly relates to a method and system for detecting machine tool vibration. Background Art

[0002] Currently, during the operation of a machine tool, vibration problems are important factors affecting machining accuracy, surface quality, and equipment reliability. The vibration of a machine tool may originate from multiple vibration sources such as spindle imbalance, abnormal tool cutting, unstable worktable clamping, and base environmental resonance. These vibration sources often overlap in a complex operating environment, making it difficult to distinguish the source of the vibration signal. In addition, vibration problems can lead to an increase in the surface roughness of the machined workpiece, a decrease in dimensional accuracy, and even accelerate the wear of machine tool components. In severe cases, it may cause machine tool operation failures and shorten the service life of the equipment. In the prior art, the detection methods for machine tool vibration signals have the following deficiencies: on the one hand, traditional vibration detection methods usually use a single sensor to monitor a certain area of the machine tool, failing to achieve a comprehensive coverage of vibration signals in multiple areas of the machine tool, and thus unable to fully reflect the overall vibration characteristics of the machine tool. On the other hand, the sources of vibration signals are complex, and multi-source signals are prone to aliasing during acquisition. The prior art has limited capabilities in signal separation and de-aliasing, and it is difficult to extract effective vibration characteristics from aliased signals. In addition, vibration signals are often accompanied by high-frequency noise, and existing signal denoising methods may lose some key signal characteristics while reducing noise interference, thereby affecting the accuracy and reliability of vibration detection. Therefore, there is an urgent need for a method that can collect multi-source vibration signals in the case of covering the spindle, tool, worktable, and base areas of the machine tool, and combine signal de-aliasing and denoising technologies to achieve accurate separation and identification of multi-source signals in a complex environment, thereby improving the comprehensiveness and accuracy of vibration detection and providing a reliable basis for machine tool fault diagnosis and operation optimization. Summary of the Invention

[0003] Aiming at the above-mentioned technical deficiencies, the purpose of the present invention is to propose a method for detecting machine tool vibration, aiming to solve the technical problem in the prior art that only single-area vibration signal acquisition and simple analysis can be performed on a machine tool, especially in the case of complex vibration signal sources and multi-source aliasing, and accurate separation and identification of vibration sources cannot be achieved.

[0004] To solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a method for detecting machine tool vibration,

[0005] The method for detecting machine tool vibration includes:

[0006] Step S10: installing multi-source sensors in the spindle area, tool area, worktable area and base area of the target machine tool, including: a spindle area sensor, installed on the spindle bearing housing, used to record the unbalanced vibration of high-speed rotation; a tool area sensor, installed on the tool holder, used to collect cutting vibration and tool abnormality signals; a worktable area sensor, installed on the worktable base, used to capture vibration caused by worktable movement or unstable clamping of workpieces; a base area sensor, installed on the machine tool base, used to detect resonance interference transmitted to the machine tool by external vibration;

[0007] The vibration signals of various areas of the target machine tool are collected in real time by multi-source sensors to form a first multi-source independent signal data set S collected ={S spindle ,S tool ,S workbench ,S base}, where S spindle is the vibration signal of the main axis area, S tool is the vibration signal of the tool area, S workbench is the vibration signal of the workbench area, S base is the vibration signal of the base area;

[0008] Step S20: Vibration signal S for the tool area tool and the vibration signal S of the workbench area workbench Performing a de-aliasing process on the second multi-source independent signal data set to form a second multi-source independent signal data set, and performing a denoising process on the second multi-source independent signal data set to generate a third multi-source independent signal data set S optimized , in, is the denoised signal in the spindle region, is the signal after de-aliasing in the tool area, is the signal after de-aliasing in the workbench area, is the denoised signal of the base area;

[0009] Step S30: by performing a third multi-source independent signal data set S optimized Perform short-time Fourier transform to extract the time-frequency feature distribution The formula is:

[0010]

[0011] in, is the third multi-source independent signal dataset S optimized Any signal h(τ-t) is the Hamming window function with 128 sampling points; is the time-frequency distribution of the signal; t is the time center point of the current signal, f is the central value of the frequency component, and τ is the integral variable of time, which is used to traverse the entire time range of the signal;

[0012] Extract the key features of the machine tool vibration from the time-frequency feature distribution , including the main vibration frequency component f main , the vibration energy distribution E(f) and the vibration amplitude dynamic range A range ;

[0013] is the third multi-source independent signal dataset S optimized in Construct a feature vector for any signal, each feature vector contains the corresponding main vibration frequency component, vibration energy distribution and vibration amplitude dynamic range, and generate a feature vector set V optimized ={V spindle ,V tool ,V workbench ,V base}, where V spindle ,V tool ,V workbench ,V base are the feature vectors of the spindle area, the tool area, the workbench area and the base area respectively;

[0014] Step S40: Construct a machine tool vibration classification model. The input of the classification model is the feature vector set V optimized , and the output of the classification model is the vibration factor category, including spindle unbalance vibration, tool cutting vibration, workbench clamping vibration and base environmental interference vibration;

[0015] Step S50: Quantify the contribution ratio of the vibration source corresponding to the output vibration factor category and generate a detection report.

[0016] Preferably, in step S10, a multi-source sensor uses a three-axis acceleration sensor with the model "ADXL356", the range is ±40g, the sensitivity is 10mV / g, and the sampling frequency is set to 20kHz.

[0017] Preferably, in step S20, for the vibration signal S tool of the tool area and the vibration signal S workbench of the workbench area, perform de-aliasing processing, using the formula:

[0018]

[0019] is the signal after de-aliasing of the tool area sensor, and k spindle is the interference coefficient of the spindle vibration on the vibration signal of the tool area, and the value range is [0, 1];

[0020]

[0021] The signal after de - aliasing for the workbench area sensor, k base is the interference coefficient of the vibration signal of the base vibration on the workbench area.

[0022] Preferably, in step S30, the main vibration frequency component f maim has a calculation formula of where is the value of f when it is the maximum; the calculation formula of the vibration energy distribution E(f) is The dynamic range A of the vibration amplitude range has a calculation formula of A range = A max - A min , where A max and A min are respectively the maximum amplitude and the minimum amplitude of the third multi - source independent signal.

[0023] Preferably, in step S40, the steps for the classification model to output the vibration factor category include:

[0024] Obtaining the eigenvalue F conv (i, j) by extracting through the dynamic convolution layer, and the calculation formula is:

[0025]

[0026] where F conv (i, j) represents the eigenvalue at the position (i, j) in the output feature map after the convolution operation, W ′ is the dynamically adjusted convolution kernel weight, k is the size of the convolution kernel, C is the number of input channels, b conv is the bias term, m and n respectively represent the position offsets of the convolution kernel in the vertical and horizontal directions, and c is the input feature map channel;

[0027] Obtaining the final classification probability distribution through the fully - connected layer and the Softmax function, and the calculation formula is:

[0028] P = Softmax(W fc ·F conv (i, j)+b fc )

[0029] where P is the probability distribution of the vibration signal belonging to each classification, W fc is the weight matrix of the fully - connected layer, b fc is the bias parameter of the fully - connected layer;

[0030] Output the vibration factor category according to the value of P.

[0031] Preferably, the dynamic parameter W ′ is adjusted dynamically by the input feature vector, and its formula is:

[0032] W ′ = W · σ(G)

[0033] G = ReLU(W g · V + b g ),

[0034] where W is the initial convolution kernel weight matrix; G is the dynamic adjustment factor generated by the input feature vector, and is calculated by the following formula: W ′ = W · σ(ReLU(W g · V + b g ))), where V is the input feature vector, including the main frequency component, amplitude dynamic range and spectral energy; W g is the preset linear transformation matrix for mapping the input feature vector to the space of the dynamic adjustment factor; b g is the bias vector; ReLU is the activation function to ensure non - negative output; σ is the Sigmoid activation function to normalize the adjustment factor to the range of [0, 1].

[0035] Preferably, in step S50, the vibration source contribution ratio is calculated by the ratio of the spectral energy of the vibration source.

[0036] The present invention also provides a detection system for machine tool vibration, including:

[0037] A vibration signal acquisition module, which is used to install multi - source sensors in the spindle area, tool area, workbench area and base area of the target machine tool, including: a spindle area sensor, installed on the spindle bearing housing, for recording the unbalanced vibration of high - speed rotation; a tool area sensor, installed on the tool holder, for collecting cutting vibration and tool abnormal signals; a workbench area sensor, installed on the workbench base, for capturing the vibration caused by the movement of the workbench or unstable clamping of the workpiece; a base area sensor, installed on the machine tool base, for detecting the resonance interference of external vibration transmitted to the machine tool;

[0038] The vibration signals of each area of the target machine tool are collected in real time by the multi - source sensors to form the first multi - source independent signal dataset S collected = {S spindle , S tool , S workbench , S base}, where S spindle is the vibration signal of the spindle area, S toolis the vibration signal of the tool area, S workbench is the vibration signal of the workbench area, S base is the vibration signal of the base area;

[0039] The signal demixing and denoising module is used for the vibration signal S of the tool area toil and the vibration signal S of the workbench area workbench to perform demixing processing to form a second multi-source independent signal dataset, and perform denoising processing on the second multi-source independent signal dataset to generate a third multi-source independent signal dataset S optimized , wherein, is the denoised signal of the spindle area, is the signal after demixing of the tool area, is the signal after demixing of the workbench area, is the denoised signal of the base area;

[0040] The feature extraction module is used to extract the time-frequency feature distribution by performing short-time Fourier transform on the third multi-source independent signal dataset S optimized The formula is: The formula is:

[0041]

[0042] wherein, is any signal in the third multi-source independent signal dataset S optimized h(τ - t) is the Hamming window function, with 128 sampling points; is the time-frequency distribution of the signal; t is the time center point of the current signal, f is the center value of the frequency component, τ is the integral variable of time, and is used to traverse the entire time range of the signal;

[0043] Extract the key features of machine tool vibration from the time-frequency feature distribution including the main vibration frequency component f main vibration energy distribution E(f) and vibration amplitude dynamic range A range ;

[0044] is any signal in the third multi-source independent signal dataset S optimized to construct a feature vector, and each feature vector contains the corresponding main vibration frequency component, vibration energy distribution and vibration amplitude dynamic range, and generate a feature vector set V optimized ={V spindle , V tool , V worlbemch , V nase}, where V spindle , V tool ​, V workbench , V base They are the eigenvectors of the spindle area, the eigenvectors of the tool area, the eigenvectors of the workbench area, and the eigenvectors of the base area respectively;

[0045] The vibration factor category classification module is used to construct a machine tool vibration classification model. The input of the classification model is the eigenvector set V optimized , and the output of the classification model is the vibration factor category, including spindle unbalance vibration, tool cutting vibration, workbench clamping vibration, and base environmental interference vibration;

[0046] The detection report output module is used to quantitatively output the contribution ratio of the vibration source corresponding to the vibration factor category and generate a detection report.

[0047] The present invention also provides a detection device for machine tool vibration, including a memory, a processor, and a detection program for machine tool vibration stored on the memory and operable on the processor. When the detection program for machine tool vibration is executed by the processor, the detection method for machine tool vibration as described above is implemented.

[0048] The present invention also provides a computer program product, including a detection program for machine tool vibration. When the detection program for machine tool vibration is executed by a processor, the detection method for machine tool vibration as described above is implemented.

[0049] The beneficial effects of the present invention are as follows: Compared with the prior art, which can only collect and simply analyze the vibration signals of a single area of the machine tool, especially under the conditions of complex vibration signal sources and multi-source aliasing, it is impossible to accurately separate and identify the vibration sources. Since the present application combines signal de-aliasing and a dynamic convolutional neural network classification model, it realizes the precise collection, separation, analysis, and identification of the vibration signals in multiple areas of the machine tool, thus avoiding the problem of inaccurate detection results and improving the accuracy of machine tool vibration detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0051] Figure 1 It is a schematic flowchart of the first embodiment of a detection method for machine tool vibration of the present invention.

[0052] Figure 2 It is a schematic diagram of the device of a detection method for machine tool vibration of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] Embodiment 1: As Figure 1 shown, it is a schematic flowchart of the first embodiment of the detection method for the vibration of the machine tool of the present invention, and the first embodiment of the detection method for the vibration of the machine tool of the present invention is proposed.

[0055] In the first embodiment, the detection method for the vibration of the machine tool includes:

[0056] Step S10: Install multi-source sensors in the spindle area, tool area, workbench area, and base area of the target machine tool, including: a spindle area sensor installed on the spindle bearing housing for recording the unbalanced vibration during high-speed rotation; a tool area sensor installed on the tool holder for collecting cutting vibration and tool abnormal signals; a workbench area sensor installed on the workbench base for capturing the vibration caused by the movement of the workbench or unstable clamping of the workpiece; a base area sensor installed on the machine tool base for detecting the resonance interference caused by the transmission of external vibration to the machine tool;

[0057] Real-time collect the vibration signals of each area of the target machine tool through the multi-source sensors to form the first multi-source independent signal dataset S collected ={S spindle , S tool , S workbench , S hase}, where S spindle is the vibration signal of the spindle area, S tool is the vibration signal of the tool area, S workbench is the vibration signal of the workbench area, and S base is the vibration signal of the base area;

[0058] It should be noted that in the first multi-source independent signal dataset, the vibration characteristics corresponding to each signal are the time-domain acceleration signals collected by the area sensors, and the specific form of the signal is time series data.

[0059] It can be understood that S spindle is the vibration signal collected by the spindle area sensor, mainly composed of the unbalanced vibration component caused by the rotation of the spindle; S tool is the vibration signal collected by the tool area sensor, including the cutting vibration signal and the tool abnormal signal; S workbenchis the vibration signal collected by the sensor in the workbench area, mainly reflecting the unstable vibration during the movement of the workbench; S base is the vibration signal collected by the sensor in the base area, mainly composed of the resonance caused by environmental interference transmitted to the base; these signals are independent in the dataset, and the sampling frequencies and sampling points of each signal are the same to ensure the timing consistency and calculation accuracy of subsequent de - aliasing and denoising processing. The construction of the first multi - source independent signal dataset is the basis for analyzing and classifying the vibration characteristics of different regions.

[0060] Step S20: For the vibration signal S tool in the tool area and the vibration signal S workbench in the workbench area, perform de - aliasing processing to form a second multi - source independent signal dataset, and perform denoising processing on the second multi - source independent signal dataset to generate a third multi - source independent signal dataset S optimized , wherein, is the denoised signal in the spindle area, is the signal after de - aliasing in the tool area, is the signal after de - aliasing in the workbench area, is the denoised signal in the base area;

[0061] It should be noted that for the vibration signal S tool in the tool area and the vibration signal S workbench in the workbench area, perform de - aliasing processing using the formula:

[0062]

[0063] is the signal after de - aliasing by the sensor in the tool area, k spindle is the interference coefficient of the spindle vibration on the vibration signal in the tool area, and the value range is [0, 1];

[0064]

[0065] is the signal after de - aliasing by the sensor in the workbench area, k base is the interference coefficient of the base vibration on the vibration signal in the workbench area.

[0066] It is understandable that for the vibration signals in the tool area and the vibration signals in the workbench area, since the vibration signals in these areas are usually interfered by the vibrations in other areas. For example, the signal in the tool area may be affected by the coupling of the spindle vibration, and the signal in the workbench area may be affected by the superposition of the resonance in the base area. Therefore, dealiasing processing is required to separate the independent vibration signals in each area. At the same time, since the signal may contain high-frequency noise, in order to ensure the purity of the signal and the accuracy of subsequent analysis, it is also necessary to further denoise the signal after dealiasing.

[0067] For example, assume that the vibration signal S tool in the tool area is interfered by the signal S spindle in the spindle area, and the interference coefficient k spindle = 0.4, and S tool = [5, 10, 15], S spindle = [1, 2, 3], then the signal after dealiasing in the tool area is The calculation result is Similarly, for the signal S workbench in the workbench area, if it is interfered by the signal S base in the base area, the base interference coefficient k base = 0.3, and S workbench = [10, 20, 30], S base = [2, 4, 6], then the signal after dealiasing is The calculation result is The signals after dealiasing and denoising can more truly reflect the actual vibration characteristics of the tool area and the workbench area, laying a foundation for subsequent analysis.

[0068] Step S30: Extract the time-frequency feature distribution by performing short-time Fourier transform on the third multi-source independent signal dataset S optimized The formula is: Formula:

[0069]

[0070] Among them, is any signal in the third multi-source independent signal dataset S optimized h(τ - t) is the Hamming window function, with 128 sampling points; is the time-frequency distribution of the signal; t is the time center point of the current signal, f is the central value of the frequency component, τ is the integral variable of time, used to traverse the entire time range of the signal;

[0071] From the time-frequency feature distribution Extract the key features of the machine tool vibration, including the main vibration frequency component f main , the vibration energy distribution E(f) and the dynamic range A of the vibration amplitude range ;

[0072] For the third multi-source independent signal dataset S optimized in Construct a feature vector for any signal. Each feature vector contains the corresponding main vibration frequency component, vibration energy distribution and dynamic range of the vibration amplitude, and generate a feature vector set V optimized ={V spindle ,V tool ,V workbench ,V base}, where V spindle ,V tool ,V workbench ,V base are the feature vectors of the spindle area, the tool area, the workbench area and the base area respectively;

[0073] It can be understood that the third multi-source independent signal dataset of the signal processing logic is the signal after dealiasing and denoising, and its signal quality is relatively high, which can reflect the actual characteristics of the vibration signals in each area. By applying the Hamming window function to each signal and performing the short-time Fourier transform, a time-frequency distribution can be generated, and three key features of the vibration signal can be extracted from it; the feature vectors generated by the signals in different areas correspond to the spindle area, the tool area, the workbench area and the base area respectively. These feature vectors together constitute a feature vector set, through which the vibration characteristics of different areas of the machine tool can be comprehensively described, providing input for the subsequent classification model.

[0074] It should be understood that compared with the single time-domain or frequency-domain analysis method, the short-time Fourier transform can simultaneously obtain the time and frequency information of the vibration signal, which is helpful to identify the change patterns of complex signals. For example, the high-frequency components in the vibration signal of the tool area can reflect the abnormalities in the cutting process, while the low-frequency components in the signal of the workbench area may be related to the unstable clamping of the workpiece.

[0075] Step S40: Construct a machine tool vibration classification model. The input of the classification model is the feature vector set V optimized , and the output of the classification model is the vibration factor category, including spindle unbalance vibration, tool cutting vibration, workbench clamping vibration and base environmental interference vibration;

[0076] It should be noted that the output of the classification model is the category of vibration factors, including: spindle unbalance vibration, which is the unbalance vibration caused by the high-speed rotation of the spindle; tool cutting vibration, which is the high-frequency vibration caused by uneven cutting or tool wear during the machining process; workbench clamping vibration, which is the low-frequency vibration caused by unstable workpiece clamping or abnormal workbench movement; base environmental interference vibration, which is the vibration caused by low-frequency resonance in the external environment or unstable support of the machine tool base.

[0077] It can be understood that by analyzing the main frequency components, energy distribution, and amplitude dynamic range in the input feature vector, the classification model can effectively distinguish different types of vibration sources. For example, spindle unbalance vibration usually exhibits low-frequency and high-amplitude characteristics, while tool cutting vibration often exhibits high-frequency and high-energy characteristics. The classification model can combine these characteristic differences to achieve accurate classification of vibration sources; the dynamic convolutional neural network can dynamically adjust the weights of the convolutional kernels according to the input feature vector, making the model more adaptable to the characteristics of different types of vibration signals. Especially in the case of complex vibration signals and variable feature distributions, it can significantly improve the classification accuracy.

[0078] It should be understood that the set of feature vectors V optimized ={V spindle ,V tool ,V workbench ,V base} is the core input of the classification model. Each feature vector contains the core features of the vibration signal in the corresponding area and is the basis for the classification model to distinguish different vibration sources. For example: V spindle ={f main =200Hz, E(f)=0.45, A range =0.35} represents the vibration characteristics of the spindle area; V tool ={f main =10kHz, E(f)=0.65, A range =0.8} represents the vibration characteristics of the tool area; the category of vibration factors output by the classification model can directly reflect the vibration sources in different areas of the machine tool and provide a basis for the analysis and optimization of the machine tool operating state. For example, if the classification result shows that tool cutting vibration is dominant, it can be judged that there may be problems such as tool wear or abnormal cutting during machining, thereby guiding tool replacement or machining parameter adjustment.

[0079] For example, assume that the set of feature vectors extracted from the third multi-source independent signal dataset is: V optimized ={V spindle ={20Hz, 0.45, 0.35}, V tool ={10kHz, 0.65, 0.8}, V workbench ={50Hz, 0.3, 0.4}, V base={20Hz, 0.2, 0.25}}, where: the eigenvector of the main spindle area indicates that the main vibration frequency of the main spindle is 200Hz, with low energy and moderate amplitude variation, indicating that the main spindle is running smoothly; the eigenvector of the tool area indicates that the main vibration frequency of the tool is 10kHz, with high energy and large amplitude variation, indicating that there may be abnormal cutting or tool wear; according to the above eigenvectors, the classification model outputs the following results: Classification result = {unbalanced vibration of the main spindle: 20%, cutting vibration of the tool: 50%, clamping vibration of the workbench: 15%, environmental interference vibration of the base: 15%}. The results show that the cutting vibration of the tool accounts for the main proportion.

[0080] Step S50: Quantify the contribution ratio of the vibration source corresponding to the vibration factor category of the output and generate a detection report.

[0081] It should be noted that the detection report includes the following contents: each vibration factor category and its contribution ratio; key features (such as main frequency component, amplitude dynamic range, etc.); possible fault source analysis and improvement suggestions.

[0082] It should be noted that for each vibration factor i (such as unbalanced vibration of the main spindle, cutting vibration of the tool, etc.), its contribution ratio Contribution Ratio i The calculation formula is as follows:

[0083]

[0084] where E i is the energy of the i-th vibration factor, which is calculated from the output probability of the classification model and the energy distribution E(f) in the eigenvector. E total = ∑ i E i is the total energy of the overall vibration signal.

[0085] It can be understood that the contribution ratio reflects the influence degree of each vibration factor on the overall vibration of the target machine tool. For example, a high proportion of cutting vibration of the tool may mean that there is abnormal cutting or tool wear during the machining process; a high proportion of environmental interference of the base may indicate that the external environment needs to be optimized.

[0086] In addition, a detection system for machine tool vibration provided by the present invention adopts a detection method for machine tool vibration in the above embodiment, and can solve the technical problem of detecting machine tool vibration. Compared with the prior art, the beneficial effects of the detection system for machine tool vibration provided by the present invention are the same as those of the detection method for machine tool vibration provided in the above embodiment, and other technical features in the detection system for machine tool vibration are the same as those disclosed in the above embodiment method, and will not be elaborated here.

[0087] The present invention provides a detection device for the vibration of a machine tool. Please refer to Figure 2 , a detection device for the vibration of a machine tool includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for detecting the vibration of a machine tool in the first embodiment above. A detection device for the vibration of a machine tool in an embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. A detection device for the vibration of a machine tool is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention. A detection device for the vibration of a machine tool may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of a detection device for the vibration of a machine tool are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow a detection device for the vibration of a machine tool to communicate with other devices wirelessly or wiredly to exchange data. Although a detection device for the vibration of a machine tool with various systems is shown in the figure, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be implemented or had alternatively.

[0088] The present invention also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of a method for detecting vibrations of a machine tool as described above. The computer program product provided by the present invention can solve the technical problem of detecting vibrations of a machine tool. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as those of the method for detecting vibrations of a machine tool provided in the above embodiments, and will not be elaborated herein.

[0089] In particular, according to the embodiments disclosed by the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed by the present invention include a computer program product which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, it executes the above-mentioned functions defined in the methods of the embodiments disclosed by the present invention.

[0090] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A method for detecting the vibration of a machine tool, characterized in that, The method includes: Step S10: Install multi-source sensors in the spindle area, tool area, worktable area, and base area of the target machine tool, including: a spindle area sensor installed on the spindle bearing housing for recording unbalanced vibrations during high-speed rotation; a tool area sensor installed on the tool holder for collecting cutting vibrations and tool abnormal signals; a worktable area sensor installed on the worktable base for capturing vibrations caused by unstable movement of the worktable or clamping of the workpiece; a base area sensor installed on the machine tool base for detecting resonance interference caused by external vibrations transmitted to the machine tool; Collect the vibration signals of each area of the target machine tool in real time through multi-source sensors to form the first multi-source independent signal dataset S collected ={S spindle , S tool , S workbench , S base}, where S spindle is the vibration signal of the spindle area, S tool is the vibration signal of the tool area, S workbench is the vibration signal of the workbench area, S base is the vibration signal of the base area; Step S20: For the vibration signal S of the tool area tool and the vibration signal S of the workbench area workbench Perform de - aliasing processing to form a second multi - source independent signal dataset, and perform denoising processing on the second multi - source independent signal dataset to generate a third multi - source independent signal dataset S optimized , wherein, is the denoised signal of the spindle area, is the signal after de - aliasing of the tool area, is the signal after de - aliasing of the workbench area, is the denoised signal of the base area; Step S30: By performing short-time Fourier transform on the third multi-source independent signal dataset S optimized to extract the time-frequency feature distribution The formula is: Among them, is the third multi-source independent signal dataset S optimized any signal in h(τ - t) is the Hamming window function with 128 sampling points; is the time-frequency distribution of the signal; t is the time center point of the current signal, f is the central value of the frequency component, and τ is the integral variable of time, which is used to traverse the entire time range of the signal; Extract the key features of the machine tool vibration from the time-frequency feature distribution , including the main vibration frequency component f main , the vibration energy distribution E(f) and the dynamic range of vibration amplitude A range ; is the third multi-source independent signal dataset S optimized in For any signal, a feature vector is constructed. Each feature vector contains the corresponding main vibration frequency component, vibration energy distribution, and vibration amplitude dynamic range, and a feature vector set V is generated optimized ={V spindle , V tool , V worlbemch , V nase}, where V spindle , V tool , V workbench , V base are the feature vectors of the spindle area, the tool area, the workbench area, and the base area, respectively; Step S40: Construct a machine tool vibration classification model, where the input of the classification model is the feature vector set V optimized , and the output of the classification model is the vibration factor category, including spindle unbalance vibration, tool cutting vibration, workbench clamping vibration, and base environmental interference vibration; Step S50: Quantify and output the contribution ratio of the vibration source corresponding to the vibration factor category and generate a detection report.

2. The detection method of a machine tool vibration according to claim 1, wherein, In step S10, the multi-source sensor uses a three-axis acceleration sensor with the model number ADXL356, a measurement range of ±40g, a sensitivity of 10mV / g, and a sampling frequency set to 20kHz.

3. The detection method of a machine tool vibration according to claim 1, characterized in that In step S20, for the vibration signal S of the tool area tool and the vibration signal S of the workbench area workbench perform anti-aliasing processing using the formula: is the signal after demixing for the tool area sensor, k spindle is the interference coefficient of the spindle vibration on the vibration signal in the tool area, and its value range is [0, 1]; is the signal after demixing the signals of the workbench area sensors, k base is the interference coefficient of the vibration signal of the base vibration on the workbench area.

4. The detection method of a machine tool vibration according to claim 1, characterized in that In step S30, the main vibration frequency component f main is calculated by the formula wherein, is the value of f when is at its maximum; the calculation formula for the vibration energy distribution E(f) is range The calculation formula for the vibration amplitude dynamic range A range is A max = A min - A max and A min are respectively the maximum amplitude and the minimum amplitude of the third multi-source independent signal.

5. The detection method of a machine tool vibration according to claim 1, characterized in that, In step S40, the steps for the classification model to output the vibration factor category include: The eigenvalue F is obtained by extracting through the dynamic convolution layer conv (i, j), and the calculation formula is as follows: Among them, F conv (i, j) represents the feature value at the position (i, j) in the output feature map after the convolution operation. W ′ is the dynamically adjusted convolution kernel weight, k is the size of the convolution kernel, C is the number of input channels, b conv is the bias term, m and n respectively represent the position offsets of the convolution kernel in the vertical and horizontal directions, and c is the input feature map channel; Obtain the probability distribution of the final classification through a fully connected layer and a Softmax function, and the calculation formula is: P = Softmax(W fc ·F conv (i,j) + b fc ) where P is the probability distribution of the vibration signal belonging to each category, and W fc is the weight matrix of the fully connected layer, and b fc is the bias parameter of the fully connected layer; Output the vibration factor category according to the value of P.

6. The detection method of a machine tool vibration according to claim 5, characterized in that, Dynamic parameter W ′ is adjusted dynamically by the input feature vector, and its formula is: W ′ = W·σ(G) G = ReLU(W g ·V + b g ), Among them, W is the initial convolutional kernel weight matrix; G is the dynamic adjustment factor generated by the input feature vector, which is calculated by the following formula: W ′ = W·σ(ReLU(W g ·V + b g ), where V is the input feature vector, including the main frequency component, amplitude dynamic range, and spectral energy; W g is the preset linear transformation matrix for mapping the input feature vector to the space of the dynamic adjustment factor; b g is the bias vector; ReLU is the activation function for ensuring non - negative output; σ is the Sigmoid activation function for normalizing the adjustment factor to the range [0, 1].

7. The detection method for the vibration of a machine tool according to claim 1, wherein In step S50, the contribution ratio of the vibration source is calculated through the ratio of the spectral energy of the vibration source.

8. A detection system for the vibration of a machine tool, characterized in that, The detection system for the machine tool vibration includes: A vibration signal acquisition module for installing multi-source sensors in the spindle area, tool area, worktable area, and base area of the target machine tool, including: a spindle area sensor installed on the spindle bearing housing for recording unbalanced vibrations during high-speed rotation; a tool area sensor installed on the tool holder for collecting cutting vibrations and tool abnormal signals; a worktable area sensor installed on the worktable base for capturing vibrations caused by unstable movement of the worktable or clamping of the workpiece; a base area sensor installed on the machine tool base for detecting resonance interference caused by external vibrations transmitted to the machine tool; Collect vibration signals of each area of the target machine tool in real time through multi-source sensors to form the first multi-source independent signal dataset S collected ={S spindle , S tool , S workbench , S base}, where S spindle is the vibration signal of the spindle area, S tool is the vibration signal of the tool area, S workbench is the vibration signal of the workbench area, S base is the vibration signal of the base area; The signal de - aliasing and denoising module is used for the vibration signal S of the tool area tool and the vibration signal S of the workbench area workbench to perform de - aliasing processing to form a second multi - source independent signal data set, and perform denoising processing on the second multi - source independent signal data set to generate a third multi - source independent signal data set S optimized , wherein, is the denoised signal of the spindle area, is the signal after de - aliasing of the tool area, is the signal after de - aliasing of the workbench area, is the denoised signal of the base area; The feature extraction module is used to extract the third multi-source independent signal data set S optimized Perform short-time Fourier transform to extract the time-frequency feature distribution The formula is: Among them, is the third multi-source independent signal dataset S optimized any signal in h(τ - t) is the Hamming window function with 128 sampling points; is the time-frequency distribution of the signal; t is the time center point of the current signal, f is the central value of the frequency component, and τ is the integral variable of time, used to traverse the entire time range of the signal; Extract the key features of machine tool vibration from the time-frequency feature distribution , including the main vibration frequency component f main , the vibration energy distribution E(f), and the dynamic range A of the vibration amplitude range ; is the third multi-source independent signal data set S optimized in Construct a feature vector for any signal. Each feature vector contains the corresponding vibration main frequency component, vibration energy distribution, and vibration amplitude dynamic range, and generate a feature vector set V optimized ={V spindle , V tool , V workbench , V base}, where V spindle , V tool , V workbench , V base are the feature vectors of the spindle area, the tool area, the workbench area, and the base area respectively; A vibration factor category classification module, which is used to construct a machine tool vibration classification model. The input of the classification model is a set of feature vectors V optimized , and the output of the classification model is the vibration factor category, including spindle unbalance vibration, tool cutting vibration, workbench clamping vibration, and base environmental interference vibration; A detection report output module for quantifying and outputting the contribution ratio of the vibration source corresponding to the vibration factor category and generating a detection report.

9. A detection device for the vibration of a machine tool, characterized in that, The detection device for the machine tool vibration includes: a memory, a processor, and a detection program for the machine tool vibration stored on the memory and executable on the processor. When the detection program for the machine tool vibration is executed by the processor, it implements the detection method for the machine tool vibration described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a detection program for the machine tool vibration. When the detection program for the machine tool vibration is executed by a processor, it implements the detection method for the machine tool vibration described in any one of claims 1 to 7.

Images