An intelligent shank adjustment system, method, device, and storage medium

Abstract

The application discloses an intelligent tool shank adjusting system, method, device and storage medium. A center processing module, a feature extraction module, an abnormality analysis module and a self-adaptive adjusting module are arranged. The center processing module can acquire and issue instructions to realize orderly starting and accurate control of a process and ensure clear system execution logic. The feature extraction module can synchronously collect time domain vibration features, frequency domain vibration features and image features to comprehensively acquire tool shank running state information in multiple dimensions and improve the integrity and accuracy of state sensing. The center processing module can generate and issue analysis instructions according to feature signals to realize efficient conversion from data to analysis tasks and ensure timely starting of abnormality diagnosis. The abnormality analysis module can analyze multi-source feature signals and feed back results to accurately identify running abnormalities and provide reliable basis for subsequent control and adjustment.

Description

Technical Field

[0001] This invention relates to the field of machining, and in particular to an intelligent tool holder adjustment system, method, device and storage medium. Background Technology

[0002] In the field of mechanical cutting, machining vibration signals can directly reflect the operating status and health of machine tools, tool holders and cutting tools. Intelligent monitoring and adaptive adjustment technology based on vibration signal characteristics has become a key means to improve cutting stability, ensure machining accuracy and equipment safety.

[0003] Most existing adaptive adjustment intelligent tool holder systems integrate basic signal acquisition and analysis components. Some systems can acquire image data during the machining process and make anomaly judgments based on the image data, thereby achieving preliminary monitoring of the tool holder status. Other systems combine sensor technology to acquire simple vibration signals and achieve adaptive adjustment of the tool holder through basic signal processing. Overall, they can meet the basic usage requirements in conventional machining scenarios.

[0004] However, existing adaptive adjustment intelligent toolholder systems still have certain shortcomings and cannot meet the demands of high-precision and high-efficiency machining scenarios. Specific problems include: First, existing intelligent toolholder systems can only judge anomalies in image data, failing to achieve comprehensive acquisition and fusion analysis of time-domain vibration characteristics, frequency-domain vibration characteristics, and image features. This may lead to missed potential faults or misjudgments, affecting the normal operation of the equipment. Second, existing toolholder systems lack a dedicated modular anomaly analysis module. When an anomaly occurs, it cannot automatically locate the anomaly, requiring manual confirmation of the anomaly location, which is time-consuming and labor-intensive, significantly increasing subsequent maintenance costs. Third, the data quality of existing toolholder systems is too high during real-time analysis and judgment, resulting in low data analysis efficiency and affecting the overall operating efficiency of the equipment. This makes it impossible to achieve rapid analysis and timely adjustment of the toolholder status, failing to meet the high-efficiency requirements of precision machining. Summary of the Invention

[0005] This invention provides an intelligent tool holder adjustment system, method, device, and storage medium. By fusing vibration and image features for analysis, automatically tracing anomalies, and integrating and compressing data, it solves the technical problems of existing intelligent tool holders that rely solely on image judgment, are prone to missed detections, require manual location of anomalies, and suffer from large data volumes that affect operating efficiency.

[0006] According to one aspect of the present invention, an intelligent tool holder adjustment system is provided, the system comprising: a central processing module, a feature extraction module and an anomaly analysis module connected to the central processing module; The central processing module is used to acquire tool holder adjustment commands, generate feature extraction commands based on the tool holder adjustment commands, and send the feature extraction commands to the feature extraction module. The feature extraction module is used to acquire feature signals during the tool holder machining process based on feature extraction instructions, and feed the feature signals back to the central processing module. The feature signals include time-domain vibration features, frequency-domain vibration features, and image features. The central processing module is used to generate analysis instructions based on the feature signals and send the analysis instructions to the anomaly analysis module; The anomaly analysis module is used to perform anomaly analysis on feature signals based on analysis commands, obtain anomaly analysis results, and feed the anomaly analysis results back to the central processing module.

[0007] Optionally, the feature extraction module specifically includes: a vibration feature unit, which includes a time-domain feature subunit and a frequency-domain feature subunit; the time-domain feature subunit is used to collect time-domain vibration features during the tool holder machining process, wherein the time-domain vibration features include mean features, variance features, peak features, kurtosis features, skewness features, impulse factor, and margin factor; the frequency-domain feature subunit is used to collect frequency-domain vibration features during the tool holder machining process, wherein the frequency-domain vibration features include spectral features, frequency band energy, and wavelet features.

[0008] Optionally, the feature extraction module specifically includes: an image feature unit, which comprises an image acquisition subunit, an information conversion subunit, a data processing subunit, a position calculation subunit, and a real-time monitoring subunit; the image acquisition subunit is used to acquire equipment images during the tool holder machining process; the information conversion subunit is used to convert the equipment images into binary images; the data processing subunit is used to perform noise reduction, enhancement, and format standardization processing on the binary images to obtain standard images; the position calculation subunit is used to determine the relative position of the tool holder and the workpiece based on the standard image; and the real-time monitoring subunit monitors image features in real time based on the relative position, wherein the image features include the tool holder pose and the tool wear state.

[0009] Optionally, the anomaly analysis module specifically includes: a vibration analysis unit, an image analysis unit, a comparison analysis unit, an anomaly tracing unit, and an anomaly feedback unit; the vibration analysis unit is used to determine the vibration state during the tool holder machining process based on time-domain and frequency-domain vibration characteristics, and obtain the vibration state anomaly determination result; the image analysis unit is used to determine the tool holder pose and tool wear state based on image features, and obtain the image state anomaly determination result; the comparison analysis unit is used to compare the vibration state anomaly determination result and the image state anomaly determination result with a preset normal threshold, and generate anomaly comparison result; the anomaly tracing unit is used to locate the anomaly occurrence location and determine the anomaly type based on the anomaly comparison result, and integrate the anomaly comparison result, the anomaly occurrence location, and the anomaly type to generate anomaly analysis result; the anomaly feedback unit is used to feed the anomaly analysis result back to the central processing module.

[0010] Optionally, the feature extraction module may further include: a data conversion unit and an integration and compression unit; the data conversion unit is used to convert time-domain vibration features, frequency-domain vibration features and image features into standard feature data in a specified format; the integration and compression unit is used to compress the standard feature data to obtain compressed standard feature data.

[0011] Optionally, the system also includes: an adaptive adjustment module connected to the central processing module; the central processing module, used to generate control commands based on the anomaly analysis results and send the control commands to the adaptive adjustment module; the adaptive adjustment module, used to adaptively adjust the tool holder according to the control commands.

[0012] Optionally, the central processing module is specifically used to: acquire a preset strategy library, match the anomaly analysis results with the preset strategy library to determine the target adjustment direction and target adjustment range of the tool holder, and generate control commands based on the target adjustment direction and target adjustment range.

[0013] According to another aspect of the present invention, a smart tool holder adjustment method is provided, the method comprising: The central processing module obtains the tool holder adjustment command, generates a feature extraction command based on the tool holder adjustment command, and sends the feature extraction command to the feature extraction module. The feature extraction module collects feature signals during the tool holder machining process based on feature extraction instructions, and feeds the feature signals back to the central processing module. The feature signals include time-domain vibration features, frequency-domain vibration features, and image features. The central processing module generates analysis instructions based on the characteristic signals and sends the analysis instructions to the anomaly analysis module. The anomaly analysis module performs anomaly analysis on the feature signals based on analysis instructions, obtains the anomaly analysis results, and feeds the anomaly analysis results back to the central processing module.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform an intelligent tool holder adjustment method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a smart tool holder adjustment method according to any embodiment of the present invention.

[0016] The technical solution of this invention comprises a central processing module, a feature extraction module, an anomaly analysis module, and an adaptive adjustment module. The central processing module acquires and issues commands to achieve orderly process startup and precise control, ensuring clear system execution logic. The feature extraction module simultaneously collects time-domain vibration features, frequency-domain vibration features, and image features, enabling comprehensive multi-dimensional acquisition of toolholder operating status information, improving the completeness and accuracy of status perception. The central processing module generates and issues analysis commands based on feature signals, achieving efficient data-to-analysis task conversion and ensuring timely anomaly diagnosis. The anomaly analysis module analyzes multi-source feature signals and provides feedback results, accurately identifying operational anomalies and providing a reliable basis for subsequent control and adjustment.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of an intelligent tool holder adjustment system according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of another intelligent tool holder adjustment system provided in Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of another intelligent tool holder adjustment system provided in Embodiment 2 of the present invention; Figure 4 This is a flowchart of an intelligent tool holder adjustment method provided in Embodiment 3 of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device that implements an intelligent tool holder adjustment method according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Example 1 Figure 1 The present invention provides a schematic diagram of an intelligent tool holder adjustment system according to Embodiment 1. The system includes: a central processing module, a feature extraction module and an anomaly analysis module connected to the central processing module.

[0023] The intelligent tool holder adjustment system, based on the characteristics of machining vibration signals, integrates sensor, signal processing, and automatic control technologies to perform real-time feature acquisition, anomaly analysis, and adaptive adjustment of the cutting process, ensuring stable tool holder operation. The central processing module is the system's control unit, responsible for receiving tool holder adjustment commands, issuing feature extraction and anomaly analysis commands, receiving feedback data from various modules, and coordinating the entire system's command flow and logical decisions. The feature extraction module is the system's signal acquisition and processing unit. Based on the instructions from the central processing module, it acquires time-domain vibration characteristics, frequency-domain vibration characteristics, and image characteristics during tool holder machining, completes signal extraction, and feeds it back to the central processing module. The anomaly analysis module is the system's fault diagnosis unit. Based on the instructions from the central processing module, it performs anomaly judgment, comparison, and source tracing on the feature signals, outputting analysis results such as whether an anomaly is present, the type of anomaly, and the location of the anomaly.

[0024] Specifically, the central processing module acquires tool holder adjustment commands and generates feature extraction commands based on these commands, then sends the feature extraction commands to the feature extraction module. The feature extraction module acquires feature signals during the tool holder machining process based on the feature extraction commands and feeds these feature signals back to the central processing module. These feature signals include time-domain vibration features, frequency-domain vibration features, and image features. The central processing module generates analysis commands based on the feature signals and sends these commands to the anomaly analysis module. The anomaly analysis module performs anomaly analysis on the feature signals based on the analysis commands, obtains the anomaly analysis results, and feeds these results back to the central processing module.

[0025] The toolholder adjustment command, triggered externally or by the system, is a control command that initiates the toolholder adjustment process and serves as the initial command for the central processing module to begin operation. The feature extraction command is issued by the central processing module to the feature extraction module to trigger feature signal acquisition and extraction. Feature signals are signals acquired by the feature extraction module that reflect the toolholder's operating state, including time-domain vibration features, frequency-domain vibration features, and image features. The analysis command is issued by the central processing module to the anomaly analysis module to trigger anomaly detection and analysis of the feature signals. The anomaly analysis result is a diagnostic conclusion output by the anomaly analysis module, containing information such as the presence, type, and location of an anomaly, used for subsequent decision-making by the central processing module.

[0026] Specifically, the central processing module receives a tool holder adjustment command from the upper-level control system or manual operation. This command is the initial signal to initiate the entire intelligent adjustment process. Upon receiving the command, the central processing module first parses it to confirm the target parameters and triggering conditions. Then, based on the parsing results, it generates a feature extraction command according to preset system logic and sends it to the feature extraction module via an internal communication interface, thus enabling the command to flow downwards. The feature extraction module enters its working state upon receiving the feature extraction command from the central processing module. This module incorporates various sensor units, including an accelerometer for capturing vibration signals, a microphone for acquiring sound information, and a camera for obtaining visual information about the tool holder and the machining area. According to the command requirements, the feature extraction module simultaneously begins acquiring multi-dimensional feature signals during the tool holder machining process. For time-domain vibration characteristics, the module samples and records the acquired raw vibration signals in real time, capturing the original morphological information such as amplitude and waveform changes over time. For frequency domain vibration characteristics, the module performs frequency domain transformation processing such as Fast Fourier Transform on the time domain vibration signal, decomposing the signal into different frequency components and extracting features such as energy and spectral peaks at each frequency point. For image features, the module controls the camera to acquire images of the tool holder, tool, and workpiece at a fixed frequency or in real time, and extracts visual features such as tool holder position offset, tool wear degree, and workpiece surface roughness through image recognition algorithms. After acquisition, the feature extraction module feeds back the integrated data containing these three types of features to the central processing module through the communication link, completing the feature data upload.

[0027] Furthermore, after receiving the complete feature signal from the feature extraction module, the central processing module enters the analysis and decision-making stage. The central processing module first cleans and verifies the received feature signal to eliminate abnormal noise data caused by sensor interference, ensuring the accuracy of the input data. Then, based on preset anomaly analysis rules and models, and combining the time-domain, frequency-domain, and image features in the feature signal, it generates corresponding analysis instructions. The analysis instructions specify which features need to be compared, which algorithm model to use for judgment, and the analysis priority. The central processing module accurately sends the analysis instructions to the anomaly analysis module via the internal communication bus, initiating the anomaly diagnosis process. The anomaly analysis module performs in-depth processing and analysis of the feature signal provided by the central processing module according to the algorithm and rules specified in the analysis instructions. The anomaly analysis module compares the real-time acquired time-domain vibration features with the time-domain features under standard normal machining conditions, calculating the difference and deviation rate. Simultaneously, the anomaly analysis module performs spectral matching on the frequency-domain vibration features to identify the presence of abnormal frequency peaks and determine if there are potential faults such as tool chipping or tool holder loosening. Based on image features, the anomaly analysis module uses image segmentation and feature matching algorithms to compare the deviation between the theoretical and actual positions of the tool holder, or to identify wear patches on the tool surface. Through comprehensive analysis and cross-validation of multi-dimensional features, the anomaly analysis module obtains the final anomaly analysis result. After the analysis is completed, the anomaly analysis module feeds back the complete anomaly analysis result to the central processing module for subsequent adjustment decisions.

[0028] Figure 2 This is a schematic diagram of the structure of an intelligent tool holder adjustment system provided in Embodiment 1 of the present invention. Figure 2 The feature extraction module specifically includes: a vibration feature unit and an image feature unit; the vibration feature unit includes a time-domain feature subunit and a frequency-domain feature subunit; the image feature unit includes an image acquisition subunit, an information conversion subunit, a data processing subunit, a position calculation subunit, and a real-time monitoring subunit. The anomaly analysis module specifically includes: a vibration analysis unit, an image analysis unit, a comparative analysis unit, an anomaly tracing unit, and an anomaly feedback unit. The feature extraction module also includes: a data conversion unit and an integration and compression unit.

[0029] Optionally, the feature extraction module specifically includes: a vibration feature unit, which includes a time-domain feature subunit and a frequency-domain feature subunit; the time-domain feature subunit is used to collect time-domain vibration features during the tool holder machining process, wherein the time-domain vibration features include mean features, variance features, peak features, kurtosis features, skewness features, impulse factor, and margin factor; the frequency-domain feature subunit is used to collect frequency-domain vibration features during the tool holder machining process, wherein the frequency-domain vibration features include spectral features, frequency band energy, and wavelet features.

[0030] Specifically, the feature extraction module includes a vibration feature unit, which is further divided into a time-domain feature subunit and a frequency-domain feature subunit. These two subunits work together to acquire features of the machining vibration signal across different dimensions. The time-domain feature subunit is primarily responsible for directly acquiring the relevant features of the original vibration signal of the tool holder during cutting, which changes over time—that is, the time-domain vibration features—and can intuitively reflect the amplitude changes and fluctuations of the vibration signal. Among these features, the mean feature is used to obtain the average amplitude level of the vibration signal over a period of time, reflecting the overall intensity of the vibration. The variance feature is used to measure the degree of dispersion of the vibration signal from the mean, reflecting the stability of the machining process. The peak value feature is used to capture the maximum instantaneous amplitude in the vibration signal, identifying sudden, severe impacts. The kurtosis feature is used to detect the presence of sharp impact components in the signal, facilitating the detection of abnormal vibrations caused by early faults. The skewness feature is used to determine the symmetry of the vibration signal distribution, reflecting the skewness of the vibration. The impulse factor is used to measure the prominence of the impulse component in the signal, characterizing the strength of the impact vibration. The margin factor reflects the ratio of the peak value to the average amplitude of the signal, reflecting the margin state of the vibration. The time-domain feature subunit extracts complete vibration characteristics at the time-domain level through real-time acquisition and calculation of these indicators. The frequency-domain feature subunit transforms the acquired time-domain vibration signal, converts it to the frequency domain, and then acquires features to obtain frequency-domain vibration characteristics, reflecting the operating state of the tool holder from the perspective of frequency distribution. Among them, the spectral feature is used to obtain the amplitude distribution of the vibration signal at different frequencies, determine the main frequency components of the vibration, and identify the source of the vibration. The frequency band energy feature divides the entire spectrum into multiple different frequency bands, calculates the energy proportion in each band, and locates abnormal frequency bands with concentrated energy. The wavelet feature decomposes the signal at different time and frequency scales through wavelet transform, which can capture the local features of non-stationary and complex vibration signals and adapt to the changing vibration state during cutting.

[0031] Optionally, the feature extraction module specifically includes: an image feature unit, which comprises an image acquisition subunit, an information conversion subunit, a data processing subunit, a position calculation subunit, and a real-time monitoring subunit; the image acquisition subunit is used to acquire equipment images during the tool holder machining process; the information conversion subunit is used to convert the equipment images into binary images; the data processing subunit is used to perform noise reduction, enhancement, and format standardization processing on the binary images to obtain standard images; the position calculation subunit is used to determine the relative position of the tool holder and the workpiece based on the standard image; and the real-time monitoring subunit monitors image features in real time based on the relative position, wherein the image features include the tool holder pose and the tool wear state.

[0032] Specifically, the feature extraction module includes an image feature unit. This unit comprises an image acquisition subunit, an information conversion subunit, a data processing subunit, a position calculation subunit, and a real-time monitoring subunit, collectively completing the image-dimensional feature acquisition and processing during the tool holder machining process. The image acquisition subunit captures and acquires real-time images of the tool holder during the cutting process according to the system's set acquisition frequency. The acquired images cover the tool holder body, the cutting tool, and the workpiece contact area, providing raw visual data for subsequent analysis. The information conversion subunit receives the raw equipment images output by the image acquisition subunit and converts the analog or digital image information into computer-recognizable and computable binary image data, completing the conversion of image information from visual to data form, laying the foundation for subsequent digital processing. The data processing subunit performs standardization processing on the converted binary images, sequentially performing noise reduction to eliminate image interference caused by light, dust, and vibration at the machining site, followed by image enhancement processing to improve the clarity of key areas such as tool edges, tool holder contours, and wear areas. Simultaneously, it performs image format standardization processing, unifying resolution, data format, and size specifications to obtain a stable and standardized image. The position calculation subunit uses the processed standard image as a basis and extracts key feature points of the tool holder and workpiece through image matching, contour recognition, and coordinate positioning algorithms. It then calculates and determines the relative positional relationship between the tool holder and workpiece, obtaining positional parameters such as distance and offset. The real-time monitoring subunit, relying on the relative position results obtained by the position calculation subunit, continuously tracks and monitors image features in real time. The monitored image features mainly include the tool holder pose and tool wear state. The tool holder pose reflects the spatial orientation and positional stability of the tool holder during machining, while the tool wear state reflects the degree of wear, wear location, and damage condition of the cutting edge.

[0033] Optionally, the anomaly analysis module specifically includes: a vibration analysis unit, an image analysis unit, a comparison analysis unit, an anomaly tracing unit, and an anomaly feedback unit; the vibration analysis unit is used to determine the vibration state during the tool holder machining process based on time-domain and frequency-domain vibration characteristics, and obtain the vibration state anomaly determination result; the image analysis unit is used to determine the tool holder pose and tool wear state based on image features, and obtain the image state anomaly determination result; the comparison analysis unit is used to compare the vibration state anomaly determination result and the image state anomaly determination result with a preset normal threshold, and generate anomaly comparison result; the anomaly tracing unit is used to locate the anomaly occurrence location and determine the anomaly type based on the anomaly comparison result, and integrate the anomaly comparison result, the anomaly occurrence location, and the anomaly type to generate anomaly analysis result; the anomaly feedback unit is used to feed the anomaly analysis result back to the central processing module.

[0034] Specifically, the routine analysis module includes a vibration analysis unit, an image analysis unit, a comparative analysis unit, an anomaly tracing unit, and an anomaly feedback unit. These units work collaboratively to complete anomaly detection, judgment, location, and feedback. The vibration analysis unit receives time-domain and frequency-domain vibration features from the feature extraction module. Based on the system's preset normal machining vibration parameter standards, it performs item-by-item detection on the mean, variance, peak value, kurtosis, skewness, impulse factor, and margin factor in the time domain, and on the spectral features, band energy, and wavelet features in the frequency domain. It determines whether each feature exceeds the stable operating range, thereby making an anomaly judgment on the vibration state of the tool holder during machining, and obtaining a vibration state anomaly judgment result indicating whether the vibration state is abnormal and the degree of abnormality. The image analysis unit receives the extracted image features and makes judgments based on the tool holder pose and tool wear state. Based on standard pose parameters and normal wear thresholds, it identifies whether the tool holder has experienced positional shifts or tilting, and determines whether the tool has excessive wear, chipping, or nicks, ultimately obtaining an image state anomaly judgment result indicating whether the image state is abnormal. The comparative analysis unit simultaneously acquires vibration state anomaly judgment results and image state anomaly judgment results. It compares these two types of results with the system's built-in preset normal thresholds and standard operating condition data to determine the magnitude of deviation of the vibration signal and image information from the normal state. The two judgment results are then combined to generate an anomaly comparison result including the presence and degree of anomaly. The anomaly tracing unit performs precise location based on the anomaly comparison results output by the comparative analysis unit. Combining the frequency distribution and amplitude changes of vibration characteristics with positional information and wear areas in image features, it determines the specific location of the anomaly. Simultaneously, it determines the anomaly type based on characteristic manifestations, such as tool holder loosening, tool wear, excessive vibration, or positional deviation. The anomaly comparison results, anomaly location, and anomaly type are then integrated to form a complete and detailed anomaly analysis result. The anomaly feedback unit packages and organizes the anomaly analysis results generated by the anomaly tracing unit, transmits them stably through the system's internal communication link, and feeds them back to the central processing module. This provides a basis for the central processing module to subsequently perform adaptive adjustments, alarm prompts, or shutdown protection.

[0035] Optionally, the feature extraction module may further include: a data conversion unit and an integration and compression unit; the data conversion unit is used to convert time-domain vibration features, frequency-domain vibration features and image features into standard feature data in a specified format; the integration and compression unit is used to compress the standard feature data to obtain compressed standard feature data.

[0036] Specifically, the feature extraction module also includes a data conversion unit and an integration and compression unit. The data conversion unit receives time-domain vibration features, frequency-domain vibration features, and image features, and converts these three types of features into standard feature data in a specified format that the computer can directly recognize, read, and process, according to the system's unified data format and encoding rules. This conversion eliminates data format differences between different types of features, ensuring a unified data interface and good compatibility for subsequent analysis and processing. After receiving the standard feature data output by the data conversion unit, the integration and compression unit integrates, classifies, and compresses the standard feature data. Through data simplification, redundancy removal, and encoding compression, it reduces the memory size of the data without losing core feature information, resulting in compressed standard feature data. This effectively avoids problems such as decreased data analysis efficiency and system lag caused by excessive data volume, improving overall data processing speed and equipment operating efficiency.

[0037] The technical solution of this invention comprises a central processing module, a feature extraction module, an anomaly analysis module, and an adaptive adjustment module. The central processing module acquires and issues commands to achieve orderly process startup and precise control, ensuring clear system execution logic. The feature extraction module simultaneously collects time-domain vibration features, frequency-domain vibration features, and image features, enabling comprehensive multi-dimensional acquisition of toolholder operating status information, improving the completeness and accuracy of status perception. The central processing module generates and issues analysis commands based on feature signals, achieving efficient data-to-analysis task conversion and ensuring timely anomaly diagnosis. The anomaly analysis module analyzes multi-source feature signals and provides feedback results, accurately identifying operational anomalies and providing a reliable basis for subsequent control and adjustment.

[0038] Example 2 Figure 3 This is a schematic diagram of the structure of an intelligent tool holder adjustment system provided in Embodiment 2 of the present invention. Figure 3 An adaptive adjustment module has been added based on the first embodiment.

[0039] Optionally, the system also includes: an adaptive adjustment module connected to the central processing module; the central processing module, used to generate control commands based on the anomaly analysis results and send the control commands to the adaptive adjustment module; the adaptive adjustment module, used to adaptively adjust the tool holder according to the control commands.

[0040] Specifically, the system also includes an adaptive adjustment module directly connected to the central processing module to complete the final execution control stage. After receiving the anomaly analysis results from the anomaly analysis module, the central processing module analyzes and judges the results to determine whether an anomaly exists, its specific location, type, and severity. Then, based on the system's preset control strategy and adjustment logic, it generates corresponding control commands. These commands include clear adjustment targets, parameters, and execution methods, accurately addressing anomalies. The central processing module then reliably sends the generated control commands to the adaptive adjustment module. Upon receiving the control commands from the central processing module, the adaptive adjustment module drives the toolholder to perform corresponding adaptive adjustment actions according to the commands. For different anomaly types such as vibration anomalies, toolholder posture deviation, and tool wear, it adjusts the toolholder's operating parameters, posture, or cutting state in real time, enabling the toolholder to quickly return to a stable and normal working state. This achieves full-process adaptive control based on machining vibration signals and image features, ensuring efficient and safe equipment operation.

[0041] In one specific implementation, for example, a CNC lathe uses this system for continuous external diameter cutting of a stainless steel workpiece. During the machining process, the feature extraction module collects real-time data showing a significant increase in kurtosis and impulse factor in the time-domain vibration features, and high-frequency abnormal peaks in the frequency-domain vibration features. Simultaneously, the image feature unit detects localized wear patches at the tool cutting edge position and a slight shift in the tool holder's position relative to the workpiece. The vibration analysis unit in the anomaly analysis module determines the vibration state is abnormal based on the increased time-domain and frequency-domain features. The image analysis unit determines the image state is abnormal based on the wear patches and positional shift. The comparison analysis unit compares the two types of abnormal results with preset normal thresholds, confirming that they exceed the allowable range. The anomaly tracing unit further locates the anomaly type as cutting vibration anomaly caused by localized tool wear. The anomaly location is the tool cutting edge area, and the complete anomaly analysis results are fed back to the central processing module. Upon receiving the anomaly analysis results, the central processing module first analyzes the anomaly type, anomaly location, and anomaly severity, determining that it is a minor anomaly that can be mitigated through parameter adjustment, requiring no machine shutdown. It then generates corresponding control commands according to the system's built-in adaptive adjustment strategy. The control commands can include reducing spindle speed, decreasing feed rate, and making minor corrections to the axial and radial positions of the toolholder. The commands also include specific adjustment values ​​and execution speeds. The central processing module sends the control commands to the adaptive adjustment module. Upon receiving the control commands, the adaptive adjustment module immediately drives the toolholder actuator to automatically reduce the spindle speed and feed rate as required, while simultaneously performing minor axial and radial position compensation on the toolholder to correct positional deviations caused by wear and suppress abnormal vibrations. After adjustment, the toolholder returns to a stable cutting state, vibration characteristics return to the normal range, the force on the worn tool area is uniform, and the machining process continues smoothly.

[0042] Optionally, the central processing module is specifically used to: acquire a preset strategy library, match the anomaly analysis results with the preset strategy library to determine the target adjustment direction and target adjustment range of the tool holder, and generate control commands based on the target adjustment direction and target adjustment range.

[0043] Specifically, the preset strategy library is a set of strategies pre-defined based on the normal operating parameters of the toolholder, common anomaly types, and corresponding handling experience. It includes standardized handling schemes for adjustment direction, adjustment range, and adjustment speed corresponding to different anomaly situations. After receiving the anomaly analysis results, the central processing module matches the key information such as the anomaly type, location, and severity in the analysis results with each strategy in the preset strategy library. By comparing, it finds the handling strategy that perfectly corresponds to the current anomaly, thereby accurately determining the target adjustment direction and target adjustment range that the toolholder needs to perform. The target adjustment direction includes specific adjustment directions such as speed adjustment, feed rate adjustment, toolholder position compensation, and cutting parameter correction, while the target adjustment range is a specific adjustment value calculated based on the severity of the anomaly. After determining the target adjustment direction and target adjustment range, the central processing module generates directly executable control commands according to the system's specified instruction format. The control commands contain complete adjustment information, ensuring that the adaptive adjustment module accurately executes the corresponding adjustment actions, thereby achieving intelligent adaptive control of the toolholder.

[0044] The technical solution of this invention provides the system with closed-loop execution and dynamic adjustment capabilities by adding an adaptive adjustment module connected to the central processing module. The central processing module generates and issues control commands based on the anomaly analysis results, enabling rapid conversion of anomaly information into adjustment commands and ensuring timely and efficient adjustment response. The adaptive adjustment module performs adaptive adjustment on the tool holder according to the control commands, which can quickly correct operating deviations and restore a stable machining state. By retrieving the anomaly analysis results from the preset strategy library, the central processing module can accurately determine the target adjustment direction and adjustment range, making the generation of control commands more scientific and reasonable, and improving the accuracy and reliability of adjustment.

[0045] Example 3 Figure 4 The flowchart illustrates a smart tool holder adjustment method provided in Embodiment 3 of the present invention. This embodiment is applicable to workpiece machining scenarios. Figure 4 As shown, the method includes: S310. Obtain the tool holder adjustment command through the central processing module, generate the feature extraction command based on the tool holder adjustment command, and send the feature extraction command to the feature extraction module.

[0046] The toolholder adjustment command, triggered externally or by the system, is a control command that initiates the toolholder adjustment process and serves as the initial command for the central processing module to begin operation. The feature extraction command is issued by the central processing module to the feature extraction module to trigger feature signal acquisition and extraction. Feature signals are signals acquired by the feature extraction module that reflect the toolholder's operating state, including time-domain vibration features, frequency-domain vibration features, and image features. The analysis command is issued by the central processing module to the anomaly analysis module to trigger anomaly detection and analysis of the feature signals. The anomaly analysis result is a diagnostic conclusion output by the anomaly analysis module, containing information such as the presence, type, and location of an anomaly, used for subsequent decision-making by the central processing module.

[0047] Specifically, the central processing module receives a tool holder adjustment command from the upper-level control system or manual operation. This command serves as the initial signal to initiate the entire intelligent adjustment process. Upon receiving the command, the central processing module first parses it to confirm the target parameters and triggering conditions. Then, based on the parsing results, it generates a feature extraction command according to the preset system logic and sends it to the feature extraction module via the internal communication interface, thus enabling the command to flow downwards.

[0048] S320. The feature extraction module collects feature signals during the tool holder machining process based on feature extraction instructions and feeds the feature signals back to the central processing module. The feature signals include time-domain vibration features, frequency-domain vibration features, and image features.

[0049] Specifically, the feature extraction module enters its working state after receiving the feature extraction command from the central processing module. The feature extraction module incorporates multiple sensor units, including an accelerometer for capturing vibration signals, a microphone for collecting sound information, and a camera for acquiring visual information about the tool holder and machining area. According to the command, the feature extraction module simultaneously initiates the acquisition of multi-dimensional feature signals during the tool holder machining process. For time-domain vibration features, the module samples and records the acquired raw vibration signals in real time, capturing the original morphological information such as amplitude and waveform changes over time. For frequency-domain vibration features, the module performs frequency-domain transformation processing such as Fast Fourier Transform on the time-domain vibration signals, decomposing the signals into different frequency components and extracting features such as energy and spectral peaks at each frequency point. For image features, the module controls the camera to acquire images of the tool holder, cutting tool, and workpiece at a fixed frequency or in real time, extracting visual features such as tool holder position offset, tool wear degree, and workpiece surface roughness through image recognition algorithms. After acquisition, the feature extraction module feeds back the integrated data containing these three types of features to the central processing module via the communication link, completing the feature data upload.

[0050] S330: The central processing module generates analysis instructions based on the characteristic signals and sends the analysis instructions to the anomaly analysis module.

[0051] Furthermore, after receiving the complete feature signal from the feature extraction module, the central processing module enters the analysis and decision-making stage. The central processing module first cleans and verifies the received feature signal to eliminate abnormal noise data caused by sensor interference, ensuring the accuracy of the input data. Then, based on preset anomaly analysis rules and models, and combining the time-domain, frequency-domain, and image features in the feature signal, it generates corresponding analysis instructions. These instructions specify which features need to be compared, which algorithm model to use for judgment, and the analysis priority. The central processing module accurately sends the analysis instructions to the anomaly analysis module via the internal communication bus, initiating the anomaly diagnosis process.

[0052] S340. The anomaly analysis module performs anomaly analysis on the feature signal based on the analysis command, obtains the anomaly analysis result, and feeds the anomaly analysis result back to the central processing module.

[0053] Specifically, the anomaly analysis module performs in-depth processing and analysis on the feature signals provided by the central processing module according to the algorithms and rules specified in the analysis instructions. The anomaly analysis module compares the real-time acquired time-domain vibration features with those under standard normal machining conditions, calculating the difference and deviation rate. Simultaneously, it performs spectral matching on the frequency-domain vibration features to identify abnormal frequency peaks and determine potential faults such as tool chipping or tool holder loosening. For image features, the anomaly analysis module uses image segmentation and feature matching algorithms to compare the deviation between the theoretical and actual positions of the tool holder, or to identify wear patches on the tool surface. Through comprehensive analysis and cross-validation of multi-dimensional features, the anomaly analysis module arrives at the final anomaly analysis result. After analysis, the anomaly analysis module feeds back the complete anomaly analysis results to the central processing module for subsequent adjustment decisions.

[0054] The technical solution of this invention comprises a central processing module, a feature extraction module, an anomaly analysis module, and an adaptive adjustment module. The central processing module acquires and issues commands to achieve orderly process startup and precise control, ensuring clear system execution logic. The feature extraction module simultaneously collects time-domain vibration features, frequency-domain vibration features, and image features, enabling comprehensive multi-dimensional acquisition of toolholder operating status information, improving the completeness and accuracy of status perception. The central processing module generates and issues analysis commands based on feature signals, achieving efficient data-to-analysis task conversion and ensuring timely anomaly diagnosis. The anomaly analysis module analyzes multi-source feature signals and provides feedback results, accurately identifying operational anomalies and providing a reliable basis for subsequent control and adjustment.

[0055] Example 4 Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0056] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) or random access memory (RAM), communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. Input / output (I / O) interfaces are also connected to the bus 14.

[0057] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0058] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a smart tool holder adjustment method.

[0059] In some embodiments, a smart tool holder adjustment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the smart tool holder adjustment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a smart tool holder adjustment method by any other suitable means (e.g., by means of firmware).

[0060] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0061] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0062] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0063] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0064] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0065] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0066] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0067] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An intelligent tool holder adjustment system, characterized in that, include: A central processing module, a feature extraction module and an anomaly analysis module connected to the central processing module; The central processing module is used to acquire the tool holder adjustment command, generate a feature extraction command based on the tool holder adjustment command, and send the feature extraction command to the feature extraction module. The feature extraction module is used to acquire feature signals during the tool holder machining process based on the feature extraction instructions, and feed the feature signals back to the central processing module. The feature signals include time-domain vibration features, frequency-domain vibration features, and image features. The central processing module is used to generate analysis instructions based on the feature signals and send the analysis instructions to the anomaly analysis module. The anomaly analysis module is used to perform anomaly analysis on the feature signal based on the analysis command, obtain the anomaly analysis result, and feed the anomaly analysis result back to the central processing module.

2. The system according to claim 1, characterized in that, The feature extraction module specifically includes: a vibration feature unit, which includes a time-domain feature subunit and a frequency-domain feature subunit; The time-domain feature subunit is used to collect time-domain vibration features during the tool holder machining process, wherein the time-domain vibration features include mean features, variance features, peak features, kurtosis features, skewness features, impulse factor and margin factor; The frequency domain feature subunit is used to collect frequency domain vibration features during the tool holder machining process, wherein the frequency domain vibration features include spectral features, frequency band energy, and wavelet features.

3. The system according to claim 2, characterized in that, The feature extraction module specifically includes: an image feature unit, which comprises an image acquisition subunit, an information conversion subunit, a data processing subunit, a location calculation subunit, and a real-time monitoring subunit; The image acquisition subunit is used to acquire equipment images during the tool holder machining process; The information conversion subunit is used to convert the device image into a binary image; The data processing subunit is used to perform denoising, enhancement, and format standardization processing on the binary image to obtain a standard image; The position calculation subunit is used to determine the relative position of the tool holder and the workpiece based on the standard image; The real-time monitoring subunit monitors image features in real time based on the relative position, wherein the image features include the tool holder pose and the tool wear state.

4. The system according to claim 3, characterized in that, The anomaly analysis module specifically includes: a vibration analysis unit, an image analysis unit, a comparison analysis unit, an anomaly tracing unit, and an anomaly feedback unit; The vibration analysis unit is used to determine the vibration state during the tool holder machining process based on the time-domain vibration characteristics and frequency-domain vibration characteristics, and obtain the vibration state anomaly determination result. The image analysis unit is used to determine the anomaly of the tool holder pose and tool wear state based on the image features, and obtain the image state anomaly determination result. The comparison analysis unit is used to compare the vibration state anomaly determination result and the image state anomaly determination result with a preset normal threshold to generate an anomaly comparison result. The anomaly tracing unit is used to locate the location of the anomaly and determine the anomaly type based on the anomaly comparison results, and to integrate the anomaly comparison results, the location of the anomaly, and the anomaly type to generate anomaly analysis results. The anomaly feedback unit is used to feed back the anomaly analysis results to the central processing module.

5. The system according to claim 3, characterized in that, The feature extraction module further includes: a data conversion unit and an integration and compression unit; The data conversion unit is used to convert the time-domain vibration features, frequency-domain vibration features, and image features into standard feature data in a specified format. The integrated compression unit is used to compress the standard feature data to obtain compressed standard feature data.

6. The system according to any one of claims 1-5, characterized in that, The system also includes an adaptive adjustment module connected to the central processing module; The central processing module is used to generate control commands based on the anomaly analysis results and send the control commands to the adaptive adjustment module. The adaptive adjustment module is used to adaptively adjust the tool holder according to the control command.

7. The system according to claim 6, characterized in that, The central processing module is specifically used to: acquire a preset strategy library, match the anomaly analysis results with the preset strategy library to determine the target adjustment direction and target adjustment range of the tool holder, and generate control commands based on the target adjustment direction and target adjustment range.

8. A method for adjusting an intelligent tool holder, characterized in that, An intelligent tool holder adjustment system as described in any one of claims 1-7, comprising: The central processing module obtains the tool holder adjustment command, generates a feature extraction command based on the tool holder adjustment command, and sends the feature extraction command to the feature extraction module. The feature extraction module collects feature signals during the tool holder machining process based on the feature extraction instructions, and feeds the feature signals back to the central processing module. The feature signals include time-domain vibration features, frequency-domain vibration features, and image features. The central processing module generates analysis instructions based on the characteristic signals and sends the analysis instructions to the anomaly analysis module. The anomaly analysis module performs anomaly analysis on the feature signals based on the analysis instructions, obtains the anomaly analysis results, and feeds the anomaly analysis results back to the central processing module.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method of claim 8.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions that are used to cause the processor to execute the method described in claim 8.

Images