Cutter damage monitoring method and system based on acceleration and sound signal fusion

Abstract

The invention provides a cutter damage monitoring method and system based on acceleration and sound signal fusion. The method comprises the steps that a vibration signal and a machining sound signal of a numerical control machine tool spindle are collected; the collected vibration signals and sound signals are preprocessed to enhance sensitive components of the signals, and preprocessed signals are obtained; on the basis of the preprocessed signals, tool damage rapid monitoring indexes are constructed; the monitoring indexes are based on time domain statistical characteristics, comprise at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and are used for quickly responding to cutter damage; based on the monitoring indexes, mutation detection and multi-sensor fusion decision making are conducted, and whether the cutter teeth are damaged or not is judged. According to the method, a tool damage rapid monitoring index which is not restrained by the sliding window step length is provided by utilizing time domain statistical characteristics, the requirement of tool damage monitoring rapid response is met, and the problems that a traditional tool damage monitoring algorithm is too long in response time and high in false alarm rate in a complex machining environment are effectively solved; and the real-time performance and the accuracy of cutter damage monitoring are improved.

Description

Technical Field

[0001] This invention belongs to the field of CNC machining technology, and specifically relates to a tool breakage monitoring method and system based on the fusion of acceleration and sound signals. Background Technology

[0002] The development of smart factories primarily depends on intelligent machine tools, robust cutting tools, and reliable process monitoring systems. Furthermore, the high-performance cutting of high-value-added components in the aerospace field urgently requires the protection of intelligent monitoring systems. In the machining of thin-walled parts, the degree of tool edge deterioration determines the process efficiency and the final surface quality of the parts.

[0003] The three most common failures of end mills are tool wear, breakage, and tool holder breakage. Tool breakage can damage the machine tool spindle and workpiece surface, leading to machine downtime and economic losses. Reliable and efficient real-time tool breakage monitoring is crucial for ensuring final machining quality and machining stability. However, tool breakage is sudden and almost impossible to predict in advance. Therefore, the ability to identify tooth damage and stop cutting in the shortest possible time will be the foundation of fully automated machining in future smart factories.

[0004] The raw signals measured by any sensor are affected by various factors, such as cutting parameters, tool condition, and tool path. Therefore, tool breakage monitoring based on a single sensor often produces false alarms. Fusion of multi-sensor data can effectively reduce false alarms. Patent 201911198571.X invented a tool breakage detection method for time-varying cutting conditions applicable to complex surface milling. It constructs a monitoring index based on the characteristic signal wave of vibration signal within the spindle rotation period T to achieve tool breakage monitoring. However, it requires Fourier transform, a process that relies on a large data size, and the response speed is difficult to meet the fast response requirements of high-speed machining. Patent 202310836694.1 invented a drilling tool condition monitoring method. It uses acoustic emission and vibration sensors to collect signals, and after wavelet packet decomposition, empirical mode decomposition, and PCA dimensionality reduction, it constructs an LS-SVM model and combines it with particle swarm optimization algorithm to optimize parameters and predict tool wear state; at the same time, it processes the workpiece AE signal to determine the tool breakage state. This method is applicable to drilling tools, but the parameters in the model change with cutting conditions, making it difficult to apply to different machining scenarios. Patent 202410400189.7 discloses a method for real-time in-situ monitoring of tool breakage based on multi-source information fusion and multi-algorithm combination. It integrates force, vibration, and image signals, utilizes generative adversarial networks to enhance imbalanced samples, and combines deep feature extraction and classification algorithms to improve the accuracy and stability of breakage detection. However, this method is affected by insufficient abnormal tool breakage samples, which limits the model's generalization ability. Furthermore, its high computational cost may lead to slow response speeds, making it difficult to meet the ultra-fast detection requirements in highly dynamic machining environments. Summary of the Invention

[0005] The purpose of this invention is to provide a tool breakage monitoring method and system based on the fusion of acceleration and sound signals, so as to solve the problems of excessively long response time and easy generation of false alarms in the tool breakage monitoring algorithm during the machining of complex parts.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a tool breakage monitoring method based on the fusion of acceleration and sound signals, comprising: Collect vibration and sound signals from the spindle of a CNC machine tool; The collected vibration and sound signals are preprocessed to enhance the sensitive components of the signals, resulting in preprocessed signals. Based on the preprocessed signal, a rapid tool breakage monitoring index is constructed; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. Based on monitoring indicators, mutation detection and multi-sensor fusion decision-making are performed to determine whether the blade teeth are damaged.

[0007] Furthermore, the acquisition of vibration and sound signals from the CNC machine tool spindle includes: Real-time XYZ vibration data of the spindle is acquired by a triaxial accelerometer installed on the side wall of the spindle; the sound signal of the spindle is acquired by a microphone installed near the spindle.

[0008] Furthermore, the preprocessing of the acquired vibration and sound signals to enhance the sensitive components of the signals, resulting in a preprocessed signal, includes: The acquired data is envelope demodulated to extract the low-frequency cutting signal of the cutting tool. The low-frequency component of the signal is separated by a high-pass filter while the high-frequency impact component is retained, thereby eliminating low-frequency cutting noise interference.

[0009] Furthermore, the construction of rapid tool breakage monitoring indicators based on the preprocessed signal includes: A rapid tool breakage monitoring index, unconstrained by data sliding window step size, was constructed by applying time-domain statistical features to the preprocessed signal. Specifically: Based on the preprocessed signal, four statistical indicators that best reflect signal waveform and amplitude abrupt changes are extracted: root mean square (RMS), peak-to-peak value (peak-to-peak), standard deviation, and kurtosis. The mathematical definition of the rapid response monitoring index for tool breakage monitoring is as follows: (1) in, N signal For sensor signals, f filtering Here is the filter function. Fstatiscal_indocator This is the feature extraction function.

[0010] Furthermore, based on monitoring indicators, mutation detection and multi-sensor fusion are performed to determine whether the blade teeth are damaged. This includes: Further processing of the indicators is performed to obtain a mutation detection index by tracking the amplitude mutation point. When the mutation detection index exceeds the threshold, it indicates that the tool may be damaged. At the decision level, multiple sensors are fused. When the sensors alarm simultaneously, it is determined that the tool has been damaged, thereby reducing false alarms in machining monitoring.

[0011] Further, mutation detection indicators: Potential tool breakage can be identified by tracking abrupt changes in amplitude, based on monitoring indicators. M i The mathematical definition of the mutation detection index is as follows: (2) in, ACP i It is a dimensionless dynamic parameter for mutation detection based on monitoring indicators. M i These are the monitoring indicators designed for this purpose. ACP i By calculating the monitoring indicators at the current moment M i With the past N -1 consecutive time-time indicator M i-1 , M i-2 to M i-N+1 The sum of and the past N Indicators at consecutive time points M i-1 , M i-2 to M i-N The ratio of the sums can be obtained; When mutation detection indicators ACP i Exceeding the tool breakage threshold T j This indicates that the cutting teeth are already damaged under the current cutting condition.

[0012] Furthermore, at the decision-making level, multiple sensors are fused, and the proposed fusion strategy is as follows: (3) in, T alarm For the final judgment result of multi-sensor fusion at the decision-making level, ACP i ( acc This is the result of the acceleration signal alarm. ACP i ( sound The result is an audible alarm signal, which is only valid when the abrupt change detection index is based on acceleration and audible signals. ACP i When the alarm threshold is reached, a final decision is made regarding tool breakage.

[0013] Secondly, the present invention provides a tool breakage monitoring system based on the fusion of acceleration and sound signals, comprising: The data acquisition module is used to collect vibration and sound signals from the spindle of a CNC machine tool. The preprocessing module is used to preprocess the acquired vibration and sound signals to enhance the sensitive components of the signals and obtain the preprocessed signals. The detection index construction module is used to construct a rapid tool breakage monitoring index based on the preprocessed signal; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. The fusion output module is used to perform mutation detection and multi-sensor fusion decision-making based on monitoring indicators to determine whether the blade teeth are damaged.

[0014] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the tool breakage monitoring method based on acceleration and sound signal fusion.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the tool breakage monitoring method based on the fusion of acceleration and sound signals.

[0016] Compared with the prior art, the present invention has the following technical effects: This invention proposes a rapid tool breakage monitoring index that is not constrained by the sliding window step size by utilizing time-domain statistical characteristics. This meets the need for rapid response in tool breakage monitoring, effectively solves the problem of excessively long response time of traditional tool breakage monitoring algorithms in complex machining environments, and improves the real-time performance and accuracy of tool breakage monitoring.

[0017] The mutation detection index proposed in this invention is applicable to a unified monitoring algorithm threshold, which can quickly and accurately identify the damage characteristics of tools, avoid the dependence on multiple threshold settings in traditional methods, simplify system configuration, and improve the stability and consistency of tool damage monitoring.

[0018] This invention proposes to fuse multiple sensors at the decision-making level. When different types of sensors simultaneously issue tool breakage alarms, tool breakage is confirmed, which greatly improves the accuracy of the machining monitoring process, reduces production downtime and resource waste caused by false alarms, and enhances the reliability and stability of the tool monitoring system in practical applications. Attached Figure Description

[0019] Figure 1 A schematic diagram of the hardware and data processing of a tool breakage monitoring system; Figure 2 For data preprocessing based on envelope demodulation; Figure 3 For data preprocessing based on high-pass and low-pass filtering; Figure 4 The monitoring indicators are those after preprocessing the acceleration signal, including (a) root mean square; (b) peak-to-peak value; (c) standard deviation; and (d) kurtosis. Figure 5 The monitoring indicators are those for the preprocessed sound signals, including (a) root mean square; (b) peak-to-peak value; (c) standard deviation; and (d) kurtosis. Figure 6 This is a schematic diagram of a sliding window for detecting abrupt changes in amplitude. Figure 7 Tool breakage monitoring based on peak-to-peak value index: (a) Tool No. 1; (b) Tool No. 2; (c) Tool No. 3.

[0020] Figure 8 This is a flowchart of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings: Example 1, please refer to Figure 8 This invention provides a tool breakage monitoring method based on the fusion of acceleration and sound signals, comprising: Collect vibration and sound signals from the spindle of a CNC machine tool; The collected vibration and sound signals are preprocessed to enhance the sensitive components of the signals, resulting in preprocessed signals. Based on the preprocessed signal, a rapid tool breakage monitoring index is constructed; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. Based on monitoring indicators, mutation detection and multi-sensor fusion decision-making are performed to determine whether the blade teeth are damaged.

[0022] This invention collects vibration and sound signals from the spindle of a CNC machine tool; preprocesses the collected data to enhance the sensitive components of the signals; constructs a rapid tool breakage monitoring index, unconstrained by sliding window step size, using time-domain statistical features on the preprocessed signals; identifies amplitude abrupt change points through cross-sliding windows of the monitoring index, and indicates potential tool breakage when the abrupt change exceeds the breakage threshold; and fuses the vibration and sound signal identification results at the decision level, determining tool breakage when both sensors simultaneously alarm, thereby reducing false alarms in machining monitoring. The tool breakage monitoring index proposed in this invention meets the requirement for rapid response in tool breakage monitoring, and by fusing sensor signals at the decision level, it provides a practical solution to the problems of excessively long response times and susceptibility to false alarms in traditional tool breakage monitoring algorithms under complex machining environments.

[0023] Example 2: This invention provides a rapid monitoring method for blade breakage based on the fusion of acceleration and sound signals, comprising the following steps: Step 1: Synchronously acquire spindle vibration and sound signals On CNC machine tools, the XYZ vibration data of the spindle is collected in real time by a triaxial accelerometer installed on the side wall of the spindle; the sound signal of the spindle is collected by a microphone installed near the spindle. Figure 1 This is a schematic diagram of the hardware and data processing of the rapid monitoring system for blade breakage proposed in this invention.

[0024] Step 2: Enhancement of the sensitive components of the signal The raw signals acquired by sensors cannot be directly used for condition monitoring because they contain a large amount of operating noise interference. Typically, the fault-sensitive components in vibration signals appear in modulated form; therefore, envelope demodulation is performed on the acquired data to extract the low-frequency cutting tooth signal. Figure 2 This is a data preprocessing step based on envelope demodulation. A high-pass filter can separate the low-frequency components of the signal while preserving as many high-frequency impulse components as possible, thus eliminating low-frequency cutting noise interference. Figure 3 This is for data preprocessing based on high-pass and low-pass filtering.

[0025] Step 3: Tool breakage monitoring indicators not constrained by sliding window step size Considering the need for rapid response in tool breakage monitoring, the classic index construction method of extracting signal features in the frequency domain and time-frequency domain is not suitable. Based on the preprocessed signal, four statistical indicators that best reflect signal waveform and amplitude changes are extracted: root mean square, peak-to-peak value, standard deviation, and kurtosis. The mathematical definition of the rapid response monitoring index for tool breakage monitoring is as follows (1): (1) in, S signal For sensor signals, ffiltering Here is the filter function. F statiscal_indocator This is the feature extraction function.

[0026] Figure 4 The detection index is the result of preprocessing the acceleration signal. Figure 5 The detection indicators are the preprocessed sound signals, which shows that the monitoring indicators are very sensitive to the occurrence of tooth breakage.

[0027] Step 4: Amplitude Abrupt Change Point Detection Indicators Tool breakage is accompanied by significant fluctuations in cutting force and machine tool vibration. Abrupt point identification can be achieved by using certain statistical indicators or methods to observe the trend data of tool breakage monitoring indicators over time series, so as to accurately and effectively estimate abnormal data. Considering the abrupt change characteristics of the tool breakage process and the monitoring indicators, potential tool breakage can be identified by tracking the amplitude abrupt change points. The mathematical definition of the abrupt change detection index based on the monitoring indicator Mi is as follows (2): (2) in, ACP i It is a dimensionless dynamic parameter for mutation detection based on monitoring indicators. M i These are the monitoring indicators designed for this purpose. ACP i By calculating the monitoring indicators at the current moment M i With the past N -1 consecutive time-time indicator M i-1 , M i-2 to M i-N+1 The sum of and the past N Indicators at consecutive time points M i-1 , M i-2 to M i-N The ratio of the sums can be obtained. Figure 6 This is a schematic diagram of a sliding window for detecting abrupt changes in amplitude. In this implementation example, N is set to 3. When mutation detection indicators ACP i Exceeding the tool breakage threshold T j This indicates that the cutting teeth are already damaged under the current cutting condition.

[0028] Step 5: Multi-sensor signal decision layer fusion Multi-sensor fusion strategy provides an excellent solution for reducing false alarms in processing monitoring. The proposed fusion strategy for multi-sensor fusion at the decision-making level is as follows (3): (3) in, T alarm For the final judgment result of multi-sensor fusion at the decision-making level, ACP i ( acc This is the result of the acceleration signal alarm. ACP i ( sound The result is an audible alarm signal, which is only valid when the abrupt change detection index is based on acceleration and audible signals. ACP i The system will only make a final decision on tool breakage when the alarm threshold is reached. Figure 7 For tool breakage monitoring based on peak-to-peak index, it can effectively identify the occurrence of tool tooth breakage, and avoid false alarms caused by a single sensor due to decision-level fusion.

[0029] In another embodiment of the present invention, a tool breakage monitoring system based on the fusion of acceleration and sound signals is provided, which can be used to implement the above-mentioned tool breakage monitoring method based on the fusion of acceleration and sound signals. Specifically, the system includes: The data acquisition module is used to collect vibration and sound signals from the spindle of a CNC machine tool. The preprocessing module is used to preprocess the acquired vibration and sound signals to enhance the sensitive components of the signals and obtain the preprocessed signals. The detection index construction module is used to construct a rapid tool breakage monitoring index based on the preprocessed signal; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. The fusion output module is used to perform mutation detection and multi-sensor fusion decision-making based on monitoring indicators to determine whether the blade teeth are damaged.

[0030] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0031] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this embodiment of the present invention can be used for the operation of a tool breakage monitoring method based on the fusion of acceleration and sound signals.

[0032] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the tool breakage monitoring method based on acceleration and sound signal fusion in the above embodiments.

[0033] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0034] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0035] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0036] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A tool breakage monitoring method based on acceleration and sound signal fusion, characterized in that, include: Collect vibration and sound signals from the spindle of a CNC machine tool; The collected vibration and sound signals are preprocessed to enhance the sensitive components of the signals, resulting in preprocessed signals. Based on the preprocessed signal, a rapid tool breakage monitoring index is constructed; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. Based on monitoring indicators, mutation detection and multi-sensor fusion are performed to determine whether the blade teeth are damaged.

2. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 1, characterized in that, The acquisition of vibration and sound signals from the CNC machine tool spindle includes: Real-time XYZ vibration data of the spindle is acquired by a triaxial accelerometer installed on the side wall of the spindle; the sound signal of the spindle is acquired by a microphone installed near the spindle.

3. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 1, characterized in that, The process of preprocessing the acquired vibration and sound signals to enhance the sensitive components of the signals, resulting in a preprocessed signal, includes: The acquired data is envelope demodulated to extract the low-frequency cutting signal of the cutting tool. The low-frequency component of the signal is separated by a high-pass filter while the high-frequency impact component is retained, thereby eliminating low-frequency cutting noise interference.

4. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 1, characterized in that, The method for constructing rapid tool breakage monitoring indicators based on preprocessed signals includes: A rapid tool breakage monitoring index, unconstrained by data sliding window step size, was constructed by applying time-domain statistical features to the preprocessed signal. Specifically: Based on the preprocessed signal, four statistical indicators that best reflect signal waveform and amplitude abrupt changes are extracted: root mean square (RMS), peak-to-peak value (peak-to-peak), standard deviation, and kurtosis. The mathematical definition of the rapid response monitoring index for tool breakage monitoring is as follows: in, N signal For sensor signals, f filtering Here is the filter function. F statiscal_indocator This is the feature extraction function.

5. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 1, characterized in that, The process of determining whether the blade teeth are damaged based on monitoring indicators, including mutation detection and multi-sensor fusion decision-making, includes: Further processing of the indicators is performed to obtain a mutation detection index by tracking the amplitude mutation point. When the mutation detection index exceeds the threshold, it indicates that the tool may be damaged. At the decision level, multiple sensors are fused. When the sensors alarm simultaneously, it is determined that the tool has been damaged, thereby reducing false alarms in machining monitoring.

6. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 5, characterized in that, Mutation detection indicators: Potential tool breakage can be identified by tracking abrupt changes in amplitude. The mathematical definition of the abrupt change detection index based on the monitoring index Mi is as follows: in, ACP i It is a dimensionless dynamic parameter for mutation detection based on monitoring indicators. M i For the designed monitoring indicators; ACP i By calculating the monitoring indicators at the current moment M i With the past N -1 consecutive time-time indicator M i-1 , M i-2 to M i-N+1 The sum of the indicators over the past N consecutive time periods M i-1 , M i-2 to M i-N The ratio of the sums can be obtained; When mutation detection indicators ACP i Exceeding the tool breakage threshold T j This indicates that the cutting teeth are already damaged under the current cutting condition.

7. The tool breakage monitoring method based on acceleration and sound signal fusion according to claim 5, characterized in that, The proposed fusion strategy for multi-sensor fusion at the decision-making level is as follows: in, T alarm For the final judgment result of multi-sensor fusion at the decision-making level, ACP i ( acc This is the result of the acceleration signal alarm. ACP i ( sound The result is an audible alarm signal, which is only valid when the abrupt change detection index is based on acceleration and audible signals. ACP i When the alarm threshold is reached, a final decision is made regarding tool breakage.

8. A tool breakage monitoring system based on the fusion of acceleration and sound signals, characterized in that, include: The data acquisition module is used to collect vibration and sound signals from the spindle of a CNC machine tool. The preprocessing module is used to preprocess the acquired vibration and sound signals to enhance the sensitive components of the signals and obtain the preprocessed signals. The detection index construction module is used to construct a rapid tool breakage monitoring index based on the preprocessed signal; the monitoring index is based on time-domain statistical characteristics, including at least one of root mean square, peak-to-peak value, standard deviation and kurtosis, and is used to quickly respond to tool breakage. The fusion output module is used to perform mutation detection and multi-sensor decision-making fusion based on monitoring indicators to determine whether the blade is damaged.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the tool breakage monitoring method based on the fusion of acceleration and sound signals as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the tool breakage monitoring method based on the fusion of acceleration and sound signals as described in any one of claims 1 to 7.

Images