Diamond cutting tooth self-adaptive vibration suppression method based on fuzzy control algorithm

Abstract

The invention discloses a diamond cutting tooth self-adaptive vibration suppression method based on a fuzzy control algorithm. The diamond cutting tooth self-adaptive vibration suppression method comprises the following steps that S1, a multi-channel signal data set in the diamond cutting tooth machining process is collected in real time; s2, acquiring a preprocessed multi-channel signal data set; s3, carrying out integration to form a feature vector containing multi-dimensional dynamic features; s4, inputting the feature vectors into a fuzzy control module, and performing fuzzy processing on the feature vectors of the channel signals to realize fuzzy quantization of the processing state; s5, generating a control output quantity by using a fuzzy reasoning algorithm according to the fuzzy quantization result, and converting the control output quantity into an executable process control instruction through a defuzzification algorithm; and S6, the process control instruction is fed back to a machining execution mechanism. The method has higher sensitivity and adaptability in unstable machining state recognition, the judgment accuracy of the initial vibration stage can be remarkably improved, and the judgment basis of a control system under complex disturbance is enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of diamonds, and in particular to a diamond pick self-adaptive vibration suppression method based on a fuzzy control algorithm. Background Art

[0002] With the development of high-end manufacturing and complex working condition cutting technology, diamond picks, as a high-hardness, high-wear-resistant precision machining tool, are widely used in high-load, high-speed metal and composite material cutting scenarios. However, in the actual processing process, since diamond picks are subjected to severe mechanical and thermal loads during cutting, they are very likely to produce nonlinear, time-varying and strong vibration phenomena. Vibration not only destroys the stability of the processing process, but also shortens the tool life and reduces cutting accuracy. In severe cases, it may even cause equipment damage and process failure.

[0003] Existing vibration suppression methods often rely on damping design of mechanical structures or traditional control strategies with fixed parameters to adjust process parameters to mitigate vibration effects. While these control methods are somewhat effective under static or regular vibration conditions, they suffer from the following drawbacks when faced with nonlinear vibrations caused by complex factors such as tool wear, workpiece material changes, temperature fluctuations, and load disturbances during diamond pick machining: First, they lack the ability to comprehensively perceive multi-source disturbance signals, failing to fully reflect the cause of vibration and the overall operating conditions of the system in real time; second, the control system is slow to respond and has fixed parameters, making it difficult to achieve rapid adaptive adjustment based on changes in the actual machining environment; and third, they fail to fully utilize the interactive characteristics of different physical signals for collaborative analysis and judgment, resulting in insufficiently targeted and precise vibration control.

[0004] In addition, some studies have attempted to apply fuzzy control algorithms to processing control to enhance the system's nonlinear processing capabilities and uncertainty adaptability. However, fuzzy control is often only performed on a single signal source, ignoring the coupling characteristics between multi-channel information during diamond cutter processing, resulting in the control strategy being unable to perform as expected in complex environments. Furthermore, the current fuzzy control methods are mostly based on static rule bases, lack self-learning capabilities, and cannot cope with real-time updates of control logic under dynamic changes in working conditions.

[0005] In summary, there is an urgent need for a new vibration suppression method that can integrate multi-channel signals and has real-time reasoning and adaptive feedback capabilities to achieve efficient and stable control of vibration problems under complex machining conditions. Summary of the Invention

[0006] An object of the present invention is to propose an adaptive vibration suppression method for diamond picks based on a fuzzy control algorithm. The present invention has higher sensitivity and adaptability in the identification of unstable machining states, can significantly improve the discrimination accuracy in the initial stage of vibration, and enhance the judgment basis of the control system under complex disturbances.

[0007] According to an embodiment of the present invention, an adaptive vibration suppression method for diamond picks based on a fuzzy control algorithm includes the following steps: S1. Arrange a plurality of high-sensitivity sensors at key parts of the diamond pick processing equipment to collect a multi-channel signal data set during the diamond pick processing in real time; S2. Preprocess the multi-channel signal data set to obtain the preprocessed multi-channel signal data set; S3. Based on the preprocessed multi-channel signal data set, extract vibration characteristic parameters, temperature characteristic parameters, and load characteristic parameters respectively, and integrate them to form a feature vector containing multi-dimensional dynamic characteristics; S4. Input the feature vector into the fuzzy control module. The fuzzy control module performs fuzzy processing on the feature vectors of each channel signal according to a preset multi-channel fuzzy control rule base and membership function to realize fuzzy quantization of the machining state; S5. According to the fuzzy quantization result, use a fuzzy inference algorithm to generate a control output quantity, and convert the control output quantity into an executable process control instruction through a defuzzification algorithm; S6. Feed back the process control instruction to the processing execution mechanism, and adjust key process parameters in real time, including tool rotation speed, feed speed, and cooling parameters, to actively suppress the vibration state and temperature and load condition parameters.

[0008] Optionally, the S1 includes the following steps: S11. Arrange multiple groups of sensor arrays at the spindle end, tool fixing structure, and workpiece support area of the diamond pick processing equipment. The sensor array includes vibration sensors, temperature sensors, and load sensors; S12. During the diamond pick processing, obtain the multi-channel signal original data stream at fixed time intervals to construct a multi-channel signal data set , and each piece of data in the multi-channel signal data set corresponds to the physical state of different sensor acquisition positions during the diamond pick processing, and is used to reflect the real-time dynamic working conditions of the processing: Among them, represents the multi-channel signal data of the th sampling point, is the time stamp of the sampling point; represents the The vibration signals collected by a vibration sensor at time are denoted as the temperature signals collected by the th temperature sensor at time are denoted as the load signals collected by the th load sensor at time are denoted as where

[0009] is the total number of sampling points. Optionally, S2 includes the following steps: S21. Perform band-pass filtering on each type of sensor signal in the multi-channel signal dataset The frequency band range retained for the vibration signals is the frequency interval formed between the minimum effective frequency and the maximum effective frequency of the vibration signals. Corresponding minimum and maximum effective frequencies are also set for the temperature signals and the load signals respectively, filtering out the noise and interference components in each channel signal that are located in the non-working frequency band, and obtaining a multi-channel signal dataset after filtering processing; S22. Perform denoising processing on each type of sensor signal after band-pass filtering. Taking the signal value of each sampling point as a unit with a time window of a set length, calculate the average value of multiple consecutive sampling points within the time window to smooth the local fluctuations in each channel signal, and obtain a multi-channel signal dataset composed of the denoised vibration signals, temperature signals, and load signals; S23. Normalize the multi-channel signal dataset after denoising respectively, and recombine the normalized vibration signals, temperature signals, and load signals according to the corresponding timestamps to form a preprocessed multi-channel signal dataset

[0010] Optionally, S3 includes the following steps: S31. Extract features based on the preprocessed multi-channel signal dataset to obtain a vibration feature parameter set The vibration feature parameter set includes the root mean square value representing the energy intensity of the vibration signal, the peak factor representing the ratio between the maximum amplitude and the effective value of the signal, the main frequency component representing the energy concentration frequency of the signal in the frequency domain, the kurtosis and skewness used to measure the non-Gaussianity and symmetry of the signal; S32. Extract features based on the preprocessed multi-channel signal dataset to extract a temperature feature parameter set The temperature feature parameter set includes the instantaneous temperature rise rate representing the temperature change rate between two adjacent time points, the sliding window average temperature value used to reflect the local stable thermal state, and the temperature fluctuation amplitude used to characterize the local thermal non-uniformity; S33. Extract features based on the preprocessed multi-channel signal dataset to extract a load feature parameter set , the set of load characteristic parameters representing the average load level during the machining process includes the average cutting force, the cutting force volatility representing the degree of load change per unit time, and the load peak duration representing the duration maintained under the overload state; S34. At each time point corresponding vibration characteristic parameter set , temperature characteristic parameter set and load characteristic parameter set are fused and integrated to form a feature vector containing multi-dimensional dynamic features .

[0011] Optionally, the S4 includes the following steps: S41. Input the feature vector of multi-dimensional dynamic features into the fuzzy control module as the combined input quantity of fuzzy control; S42. For each feature input variable in the feature vector of multi-dimensional dynamic features, establish fuzzy linguistic variables, set the fuzzy linguistic value levels as low, medium, and high, and use membership functions to perform fuzzy processing on the feature input variables to form a fuzzy input set; S43. Construct a fuzzy control rule base. Based on actual machining experience and historical data analysis, establish fuzzy control rules in the fuzzy control rule base. The input conditions consist of the fuzzy levels of three channels: vibration, temperature, and load. The output control level reflects the stability of the current machining state: If the root mean square value of the vibration signal is high, the instantaneous temperature rise rate is medium, and the cutting force volatility of the load signal is high, the machining state is unstable; If the main frequency component of the vibration signal is medium, the average temperature is low, and the average value of the load signal is medium, the machining state is stable; If the kurtosis of the vibration signal is low, the temperature fluctuation amplitude is high, and the peak duration of the load signal is medium, the machining state is average; S44. Based on the membership function and the fuzzy control rule base, perform fuzzy inference on the feature input variables to generate a fuzzy output quantity. The fuzzy level of the machining state is set to three levels: stable, average, and unstable.

[0012] Optionally, the S5 includes the following steps: S51. According to the fuzzy level of the machining state, establish a fuzzy set of control output quantities , and define the fuzzy output levels of the tool speed adjustment amount , feed speed adjustment amount and coolant parameter adjustment amount as decrease, unchanged, and increase respectively according to the machining state levels of stable, average, and unstable; S52. Based on the fuzzy inference results of stable, general, and unstable processing state levels, construct the membership functions of the control output quantities respectively. The value range of the membership functions of the control output quantities represents the adjustment amounts of the tool rotation speed, feed speed, and cooling parameters respectively. S53. For the fuzzy set of the control output quantity Perform defuzzification processing, and determine the exact numerical values of each control output quantity based on the improved centroid defuzzification algorithm with dynamic weight correction : Wherein, Represents the value of the th control quantity corresponding to the tool rotation speed adjustment amount, feed speed adjustment amount, and cooling parameter adjustment amount, Is the membership degree corresponding to the stable, general, or unstable processing state level when the control quantity takes this value, Is the number of elements in the output quantity fuzzy set, Is the dynamic weight coefficient, Determined in combination with the nonlinear degree of the actual machining vibration characteristics of the diamond pick. According to the kurtosis and peak factor of the vibration signal monitored in real time, dynamically adjust the size of the weight coefficient, so that the weight coefficient of the control quantity value close to the actual vibration state required in the output quantity fuzzy set is increased, and the weight coefficient of the control quantity value deviating from the actual vibration state required is decreased; S54. Convert the exact numerical values of each control output quantity Into a specific process control instruction set , including the tool rotation speed control instruction adjusted according to the processing state level , used to suppress the vibration amplitude in real time; the feed speed control instruction adjusted according to the processing state level , used to adapt to the load change; the cooling parameter control instruction adjusted according to the processing state level , used to regulate the processing temperature state, and realize the real-time active suppression of the vibration during the diamond pick processing process.

[0013] The beneficial effects of the present invention are: (1) By introducing three types of high-frequency sampling signals of vibration, temperature, and load, the present invention constructs a unified multi-channel signal data set, and designs a multi-dimensional dynamic feature extraction method. At the fuzzy control input stage, the vibration energy, temperature rise change rate, and load fluctuation trend parameters are considered simultaneously, and a feature vector is fused and constructed for fuzzy inference. Compared with the existing fuzzy control methods that only rely on a single vibration channel, the present invention has higher sensitivity and adaptability in the identification of unstable processing states, can significantly improve the discrimination accuracy in the initial stage of vibration, and enhance the judgment basis of the control system under complex disturbances.

[0014] (2) The present invention constructs a hierarchical fuzzy rule base covering stable, general and unstable processing states. The rule input is based on the composite characteristics of vibration root mean square value, temperature fluctuation amplitude and load continuous peak value, and the output is directly mapped to the actual process response variables such as tool speed, feed speed and cooling flow adjustment direction. The fuzzy reasoning process dynamically adjusts the weight through the membership function, thereby achieving accurate mapping of state changes to control instructions, opening up the logical chain from signal recognition to process control, and improving the interpretation transparency and consistency of the control response of the fuzzy control system.

[0015] (3) The present invention uses the center of gravity method to defuzzify the fuzzy control output in the control output stage, accurately calculates the adjustment amount of tool speed, feed speed and cooling parameters, and constructs a numerical mapping model between the processing state level and the actuator instruction to form a stable control closed loop, which solves the problems of unclear control force and low feedback accuracy at the execution end of the traditional fuzzy control system, improves the system's response sensitivity and dynamic control accuracy, and effectively ensures the processing stability and anti-interference ability of diamond picks under high load environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of a diamond pick adaptive vibration suppression method based on fuzzy control algorithm proposed by the present invention. DETAILED DESCRIPTION

[0017] The present invention will now be described in further detail with reference to the accompanying drawings, which are simplified schematic diagrams that illustrate the basic structure of the present invention in a schematic manner.

[0018] refer to Figure 1 A method for adaptive vibration suppression of diamond picks based on fuzzy control algorithm comprises the following steps: S1. Multiple highly sensitive sensors are deployed at key locations on the diamond pick processing equipment to collect multi-channel signal data sets during the diamond pick processing process in real time; S2. Preprocessing the multi-channel signal dataset to obtain a preprocessed multi-channel signal dataset; S3. Extract vibration characteristic parameters, temperature characteristic parameters, and load characteristic parameters from the preprocessed multi-channel signal dataset and integrate them to form a feature vector containing multi-dimensional dynamic characteristics; S4. Input the feature vectors into the fuzzy control module. The fuzzy control module performs fuzzy processing on the feature vectors of each channel signal according to the preset multi-channel fuzzy control rule base and membership functions to achieve fuzzy quantization of the machining state; S5. Generate a control output based on the fuzzy quantization result using a fuzzy inference algorithm, and convert the control output into an executable process control instruction through a defuzzification algorithm; S6. Feed the process control instruction back to the machining execution mechanism to adjust the key process parameters in real time, including the tool rotation speed, feed rate, and cooling parameters, to actively suppress the vibration state and temperature and load condition parameters.

[0019] In this embodiment, S1 includes the following steps: S11. Arrange multiple sensor arrays at the spindle end, tool fixing structure, and workpiece support area of the diamond pick machining equipment. The sensor arrays include vibration sensors, temperature sensors, and load sensors; S12. During the diamond pick machining process, obtain the original data stream of multi-channel signals at fixed time intervals to construct a multi-channel signal dataset , and each piece of data in the multi-channel signal dataset corresponds to the physical state of different sensor acquisition positions during the diamond pick machining process and is used to reflect the real-time dynamic working conditions of the machining: Among them, represents the multi-channel signal data at the -th sampling point, is the time stamp of the sampling point; represents the vibration signal collected by the -th vibration sensor at time , represents the temperature signal collected by the -th temperature sensor at time , represents the load signal collected by the -th load sensor at time , is the total number of sampling points.

[0020] In this embodiment, by introducing three types of high-frequency sampling signals of vibration, temperature, and load, a unified multi-channel signal dataset is constructed, and a multi-dimensional dynamic feature extraction method is designed. At the fuzzy control input stage, parameters such as vibration energy, temperature rise change rate, and load fluctuation trend are considered simultaneously, and a feature vector is fused and constructed for fuzzy inference. Compared with the existing fuzzy control method that only relies on a single vibration channel, the present invention has higher sensitivity and adaptability in the identification of unstable machining states, can significantly improve the discrimination accuracy in the initial stage of vibration, and enhance the judgment basis of the control system under complex disturbances.

[0021] In this embodiment, S2 includes the following steps: S21. Perform band-pass filtering on each type of sensor signal in the multi-channel signal dataset . The frequency band range retained by the vibration signal is the frequency interval formed between the minimum effective frequency and the maximum effective frequency of the vibration signal. Corresponding minimum and maximum effective frequencies are also set for the temperature signal and the load signal respectively, filtering out the noise and interference components in each channel signal that are located in the non-working frequency band, and obtaining a multi-channel signal dataset after filtering processing; S22. Perform denoising on each type of sensor signal after band-pass filtering. Take the average value of multiple consecutive sampling points within a time window of a set length for the signal value of each sampling point to smooth the local fluctuations in each channel signal, and obtain a multi-channel signal dataset composed of the denoised vibration signal, temperature signal, and load signal; S23. Perform linear range normalization on the denoised multi-channel signal dataset respectively. All signals must be independently normalized within the channel, and cross-channel normalization is prohibited. Then, recombine the normalized vibration signal, temperature signal, and load signal according to the corresponding timestamps to form a preprocessed multi-channel signal dataset .

[0022] The steps of filtering, denoising, and normalizing the multi-channel signal dataset in this embodiment significantly improve the data quality and reliability. By performing band-pass filtering and sliding denoising on the vibration, temperature, and load signals respectively, abnormal fluctuations caused by machining environment interference, mechanical resonance, or electrical noise are effectively removed, significantly improving the stability and accuracy of the input data of the subsequent fuzzy control system. The sensitivity to weak vibration changes is enhanced. The filtered vibration signal retains high-frequency details related to tool wear and workpiece hard point contact, which helps to timely identify small but practically significant vibration changes and achieve more refined vibration response regulation. The unity of multi-channel signal normalization processing is realized. By normalizing data with different dimensions and amplitudes, the problem of inconsistent scales of the three types of signals of vibration, temperature, and load is effectively solved, providing an equal-weight and equivalent input basis for the fuzzy control module and improving the accuracy and generalization ability of fuzzy inference.

[0023] In this embodiment, S3 includes the following steps: S31. Extract features from the preprocessed multi-channel signal dataset using the root mean square value method to obtain a vibration feature parameter set , where the vibration feature parameter set includes the root mean square value representing the energy intensity of the vibration signal, the peak factor representing the ratio between the maximum amplitude and the effective value of the signal, the main frequency component representing the energy concentration frequency of the signal in the frequency domain, the kurtosis and skewness used to measure the non-Gaussianity and symmetry of the signal; S32. Extract features based on the preprocessed multi-channel signal dataset to extract a temperature feature parameter set , where the temperature feature parameter set includes the instantaneous temperature rise rate representing the temperature change rate between two adjacent time points, the sliding window average temperature value used to reflect the local stable thermal state, and the temperature fluctuation amplitude used to characterize the local thermal non-uniformity; S33. Extract features based on the preprocessed multi-channel signal dataset to extract a load feature parameter set , and the load feature parameter set representing the average load level during the processing includes the average cutting force, the cutting force volatility representing the degree of load change per unit time, and the load peak duration representing the duration maintained under the overload state; S34. At each time point , fuse the corresponding vibration feature parameter set , temperature feature parameter set and load feature parameter set to integrate and form a feature vector containing multi-dimensional dynamic features .

[0024] The steps of extracting multi-channel feature parameters and constructing a feature vector based on the preprocessed data in this embodiment strengthen the multi-dimensional characterization ability of the vibration state. By extracting multiple statistical and frequency domain indicators including the root mean square value of vibration, peak factor, main frequency, kurtosis, and skewness of vibration, the energy level, non-Gaussianity, and periodic characteristics of the vibration signal can be comprehensively characterized, enhancing the perception ability of complex vibration states. Introducing temperature and load features to achieve state coupling expression, during the processing, vibration is often affected by the coupling of temperature rise and sudden change of load. The introduction of parameters such as temperature rise rate, temperature fluctuation, and cutting force fluctuation enables the control system to more accurately understand the physical mechanism behind the vibration, expanding from "single control" to "coupled control". Constructing a unified time-series dynamic feature vector, by integrating the feature parameters of all channels at each sampling moment to form a dynamic feature vector, provides a high-dimensional and strongly time-series continuous input for the subsequent fuzzy control module, making the fuzzy control decision have time continuity and dynamic sensitivity, which helps to improve the response speed and regulation accuracy of the overall system.

[0025] In this embodiment, S4 includes the following steps: S41. Input the feature vector of the multi-dimensional dynamic feature into the fuzzy control module as the combined input quantity of the fuzzy control; S42. Establish fuzzy linguistic variables for each feature input variable in the feature vector of the multi-dimensional dynamic feature, set the fuzzy linguistic value levels as low, medium, and high, and use the membership function to perform fuzzy processing on the feature input variables to form a fuzzy input set; The fuzzy linguistic variables are as follows: Vibration feature variable (root mean square value of vibration), fuzzy linguistic variable name: vibration intensity, fuzzy linguistic value levels: {low, medium, high}, typical explanation: low: small vibration energy, stable machining process; medium: slight instability signs appear; high: intense vibration, risk of instability Temperature feature variable (instantaneous temperature rise rate), fuzzy linguistic variable name: temperature rise rate, fuzzy linguistic value levels: {slow, medium, rapid}, typical explanation: slow: stable temperature change, good thermal stability; medium: local heat accumulation may occur; rapid: obvious thermal effect between tool and workpiece, cooling needs to be regulated Load feature variable (load volatility), fuzzy linguistic variable name: load change amplitude, fuzzy linguistic value levels: {small, medium, large}, typical explanation: small: stable load, controllable machining load; medium: load fluctuates, entering the regulation boundary; large: unstable cutting force, tendency of out-of-control.

[0026] The membership function is a mathematical tool in the fuzzy control system used to map precise numerical inputs (vibration intensity, temperature change rate, load fluctuation) to fuzzy linguistic variables (low, medium, high). Specifically, the membership function defines the degree (i.e., membership degree w) to which an input variable belongs to a certain fuzzy set. In this embodiment, the triangular membership function is used.

[0027] S43. Construct a fuzzy control rule base. The fuzzy control rule base is established based on actual machining experience and historical data analysis. The input conditions consist of the fuzzy levels of three channels: vibration, temperature, and load. The output control level reflects the stability of the current machining state: If the root mean square value of the vibration signal is high, the instantaneous temperature rise rate is medium, and the cutting force volatility of the load signal is high, then the machining state is unstable; If the main frequency component of the vibration signal is medium, the average temperature is low, and the average value of the load signal is medium, then the machining state is stable; If the kurtosis of the vibration signal is low, the temperature fluctuation amplitude is high, and the peak duration of the load signal is medium, then the machining state is average; S44. Based on the membership function and fuzzy control rule base, fuzzy reasoning is performed on the characteristic input variables to generate fuzzy output quantities. The fuzzy level of the processing state is set to three levels: stable, general, and unstable.

[0028] In this embodiment, fuzzy reasoning: The current moment The language values corresponding to each fuzzy input variable are matched with the condition items in the rule base to identify the rules that meet the premise conditions.

[0029] In this embodiment, the current input variables after fuzzification are: vibration root mean square = high (membership: 0.8), temperature rise rate = medium (membership: 0.6), load fluctuation rate = high (membership: 0.9); Then and rule: If "high" "medium" "high", then the state is "unstable" - activated Calculate rule activation strength (inference strength) Use the "minimum membership method" to perform conjunction logic processing (AND relationship): , indicating that this rule is activated with a strength of 0.6.

[0030] The inference outputs a fuzzy set, which assigns the above activation intensity to the output item of the rule, that is, the fuzzy set "processing state = unstable", and its membership function will be truncated or weighted on this basis.

[0031] If multiple rules are activated at the same time, the outputs of all rules are synthesized using "maximization" to finally obtain a joint output of the processing state fuzzy set: All the rules are combined with the maximum membership of the inference results of "stable", "general" and "unstable", and finally a comprehensive output fuzzy set is formed. , which is used for subsequent defuzzification.

[0032] This implementation method constructs a hierarchical fuzzy rule library covering stable, general and unstable processing states. The rule input is based on complex characteristics such as the root mean square value of vibration, temperature fluctuation amplitude and continuous load peak, and the output is directly mapped to the actual process response variables such as tool speed, feed speed and adjustment direction of cooling flow. The fuzzy inference process dynamically adjusts the weight through the membership function, thereby achieving accurate mapping of state changes to control instructions, opening up the logical chain from signal recognition to process control, and improving the interpretation transparency and consistency of the fuzzy control system.

[0033] In this embodiment, S5 includes the following steps: S51. Establish the control output fuzzy set according to the fuzzy level of the processing state , define the tool speed adjustment amount according to the machining status level stable, general, and unstable and the adjustment amount of the feed rate and the adjustment amount of the cooling parameters have fuzzy output levels of decrease, unchanged, and increase; S52. Based on the fuzzy inference results of stable, general, and unstable machining state levels, construct the membership functions of the control output quantities respectively. The value range of the membership functions of the control output quantities represents the adjustment amounts of the tool rotation speed, feed rate, and cooling parameters respectively; S53. Defuzzify the fuzzy set of the control output quantities and determine the exact numerical values of each control output quantity based on the improved centroid defuzzification algorithm with dynamic weight correction : wherein, represents the value of the th control quantity corresponding to the adjustment amount of the tool rotation speed, the adjustment amount of the feed rate, and the adjustment amount of the cooling parameters, is the membership degree corresponding to the stable, general, or unstable machining state level when the value of this control quantity is taken, is the number of elements in the fuzzy set of the output quantity, is the dynamic weight coefficient, which is determined by combining the non - linear degree of the actual machining vibration characteristics of the diamond pick. According to the kurtosis and peak factor of the vibration signal monitored in real - time, the size of the weight coefficient is dynamically adjusted, so that the weight coefficient of the numerical value of the control quantity close to the required value of the actual vibration state in the fuzzy set of the output quantity is increased, and the weight coefficient of the numerical value of the control quantity deviating from the required value of the actual vibration state is decreased; The improved centroid defuzzification algorithm based on dynamic weight correction proposed by the formula can significantly improve the accuracy and pertinence of the vibration suppression control output quantity during the machining process of the diamond pick. Compared with the traditional centroid method, the algorithm can adaptively adjust the weight coefficient according to the differences in the vibration signal characteristics monitored in real - time, accurately reflect the changes in the actual machining conditions, and effectively avoid the defect of the non - differentiated averaging process of each fuzzy control quantity in the traditional method. Through this method, the key process control quantities of the tool rotation speed, feed rate, and cooling parameters can be adjusted accurately and in real - time, effectively improving the active vibration suppression effect of machining, and significantly extending the tool life and improving the machining accuracy.

[0034] S54. Convert the exact numerical values of each control output quantity into a specific process control instruction set , including the tool rotation speed control instruction adjusted according to the machining state level for suppressing the vibration amplitude in real - time; the feed rate control instruction adjusted according to the machining state level for adapting to the load change; the cooling parameter control instruction adjusted according to the machining state level , which is used to regulate the processing temperature state and achieve real-time active suppression of the vibration during the processing of diamond picks.

[0035] In this embodiment, the centroid method is used to defuzzify the fuzzy control output in the control output stage, accurately calculate the adjustment amounts of the tool rotation speed, feed speed, and cooling parameters, and construct a numerical mapping model between the processing state level and the actuator command to form a stable control closed-loop, solving the problems of unclear control force and low feedback accuracy at the execution end of the traditional fuzzy control system, improving the response sensitivity and dynamic control accuracy of the system, and effectively ensuring the processing stability and anti-interference ability of diamond picks in a high-load environment.

[0036] Example 1: At 9:32 am on November 18, 2024, a high-precision equipment manufacturing enterprise located in Wuxi, Jiangsu started the diamond pick adaptive vibration suppression system using the present invention when executing a processing task of a batch of key aviation structural parts. This task required precise cutting operations on a batch of high-strength titanium alloy components for 6 consecutive hours, and the processing error had to be controlled within ±20μm.

[0037] During the execution of this task, the system operated stably in the initial stage of cutting (9:32:00 - 9:32:10). At 9:32:11, the system captured a set of abnormal signals from the vibration sensor (serial number: S_v_04): the peak acceleration reached 1.62g, which was much higher than the average value of 0.9g in the historical stable state. The sampling data is as follows: ; Based on the three characteristics of the vibration root mean square value (RMS = 0.45g), temperature rise rate (2.8°C / s), and cutting force fluctuation rate (14.2%) at this moment, the system made a fuzzy control judgment. According to the preset fuzzy rule base, it was satisfied that: If the RMS is high, the temperature rise rate is medium, and the fluctuation rate is high, then the state is "unstable". [[ID=2,1]]

[0038] The system determined that the current processing state was "unstable" and generated a fuzzy output set : The adjustment level of the tool rotation speed was "decrease"; The adjustment level of the feed speed was "decrease"; The adjustment level of the cooling parameter was "increase".

[0039] Subsequently, the system called the centroid method for defuzzification and generated the following precise control output: ; At 9:32:13, this set of control instructions was sent to the execution controller of the machining center through the system bus, and the dynamic adjustment of process parameters was completed in real time, avoiding the risk of machining tool jumping or local deformation caused by excessive load and vibration accumulation.

[0040] At 9:36:47, the system captured another abnormal fluctuation from the temperature sensor (serial number: S_t_02). The average temperature within the sliding window rapidly rose from 78.6°C to 89.4°C, and the temperature rise rate exceeded 3.3°C / s. At the same time, the peak load duration feedback by the load sensor (serial number: S_f_01) exceeded 4.2 seconds, far higher than the historical average of 1.7 seconds.

[0041] After being re-evaluated as "unstable" by the fuzzy inference result, the system immediately generated dynamic instructions again. The control output for this round is as follows: ; At the same time, the system recorded the complete abnormal segment data in the background and automatically generated a diagnostic report at the control terminal, indicating that the machining process entered the "thermal-load-vibration coupling abnormal section", and it was recommended to prioritize the optimization of the cutting path in subsequent batches.

[0042] In the control group of the same batch without enabling the present invention, the following data comparison differences were recorded for the same workpiece in the same time period: According to the statistics of the process records, the method of the present invention identified 47 vibration-thermal-load abnormal combination events in the entire 6-hour machining task, and all completed closed-loop response control. Among them, the average time taken for the first control response was 1.7 seconds, which was significantly shorter than the average response delay of 5.4 seconds of the traditional method. Finally, this task achieved the machining and delivery of 98 aviation parts in the whole batch. After inspection, all the dimensional errors were controlled within the range of ±17μm, exceeding the enterprise's established standard of ±20μm. The tool wear was reduced by 28%, and the tool replacement frequency was reduced by nearly one-third.

[0043] In summary, this embodiment truly demonstrates the online application process of the method of the present invention in the high-precision diamond cutting scenario, the closed-loop response of vibration control, the fuzzy inference decision-making process, and the implementation effect of control instructions, verifying the multiple advantages of the robustness, response speed, and control accuracy of the present invention in the dynamic non-linear machining environment.

[0044] The above is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. An adaptive vibration suppression method for diamond picks based on fuzzy control algorithm, characterized in that, It includes the following steps: S1. Deploy multiple highly sensitive sensors at key parts of the diamond pick processing equipment to collect a multi-channel signal dataset during the diamond pick processing in real time; S2. Preprocess the multi-channel signal dataset to obtain the preprocessed multi-channel signal dataset; S3. Based on the preprocessed multi-channel signal dataset, extract vibration characteristic parameters, temperature characteristic parameters and load characteristic parameters respectively, and integrate them to form a feature vector containing multi-dimensional dynamic characteristics; S4. Input the feature vector into the fuzzy control module. The fuzzy control module performs fuzzy processing on the feature vectors of each channel signal according to the preset multi-channel fuzzy control rule base and membership function to realize the fuzzy quantization of the processing state; S5. According to the fuzzy quantization result, use the fuzzy inference algorithm to generate a control output quantity, and convert the control output quantity into an executable process control instruction through the defuzzification algorithm; S6. Feed back the process control instruction to the processing execution mechanism, and adjust the key process parameters in real time, including tool rotation speed, feed speed and cooling parameters, to realize the active suppression of the vibration state and temperature and load condition parameters; 2. The adaptive vibration suppression method of diamond picks based on fuzzy control algorithm according to claim 1, characterized in that The S1 includes the following steps: S11. Deploy multiple groups of sensor arrays at the spindle end, tool fixing structure and workpiece support area of the diamond pick processing equipment. The sensor array includes vibration sensors, temperature sensors and load sensors; S12. During the processing of diamond picks, obtain the original data stream of multi-channel signals at fixed time intervals and construct a multi-channel signal dataset , each piece of data in the multi-channel signal dataset corresponds to the physical state of different sensor acquisition positions during the processing of diamond picks and is used to reflect the real-time dynamic working conditions of the processing: Among them, represents the multi-channel signal data of the th sampling point, is the time stamp of the sampling point; represents the vibration signal collected by the th vibration sensor at time ; represents the temperature signal collected by the th temperature sensor at time ; represents the load signal collected by the th load sensor at time ; is the total number of sampling points.

3. An adaptive vibration suppression method for diamond picks based on a fuzzy control algorithm according to claim 2, characterized in that, The S2 includes the following steps: S21. Perform band-pass filtering on each type of sensor signal in the multi-channel signal dataset respectively. The frequency band range retained for the vibration signal is the frequency interval formed between the minimum effective frequency and the maximum effective frequency of the vibration signal. The minimum and maximum effective frequencies are also respectively set for the temperature signal and the load signal, and the noise and interference components in each channel signal located in the non-operating frequency band are filtered out, obtaining a multi-channel signal dataset after filtering processing; S22. Denoise each type of sensor signal after band-pass filtering, and take the average value of multiple consecutive sampling points within a time window of a set length for each sampling point of the signal value to smooth the local fluctuations in each channel signal, and obtain a multi-channel signal dataset composed of the denoised vibration signal, temperature signal and load signal; S23. Normalize the denoised multi-channel signal datasets respectively, and recombine the vibration signals, temperature signals, and load signals after normalization according to the corresponding timestamps to form a preprocessed multi-channel signal dataset .

4. A diamond pick self-adaptive vibration suppression method based on a fuzzy control algorithm according to claim 3, characterized in that, The S3 includes the following steps: S31. Extract features from the preprocessed multi-channel signal dataset to obtain a vibration feature parameter set , where the vibration feature parameter set includes the root mean square value representing the energy intensity of the vibration signal, the peak factor representing the ratio between the maximum amplitude and the effective value of the signal, the main frequency component representing the energy concentration frequency of the signal in the frequency domain, and the kurtosis and skewness used to measure the non-Gaussianity and symmetry of the signal; S32. Extract feature parameters based on the preprocessed multi-channel signal dataset, and extract a temperature feature parameter set , where the temperature feature parameter set includes an instantaneous temperature rise rate representing the temperature change rate between two adjacent time points, a sliding window average temperature value used to reflect the local stable thermal state, and a temperature fluctuation amplitude used to characterize the local thermal non-uniformity; S33. Extract feature parameters of the load by performing feature extraction on the preprocessed multi-channel signal dataset to obtain a set of load feature parameters , where the set of load feature parameters representing the average load level during the machining process includes the average cutting force, the cutting force volatility representing the degree of load change per unit time, and the load peak duration representing the duration maintained under the overload state; S34. At each time point the corresponding vibration characteristic parameter set , temperature characteristic parameter set and load characteristic parameter set are fused and integrated to form a feature vector containing multi-dimensional dynamic characteristics.

5. The adaptive vibration suppression method for diamond picks based on the fuzzy control algorithm according to claim 4, characterized in that The S4 includes the following steps: S41. Input the feature vector of the multi-dimensional dynamic feature into the fuzzy control module as the combined input quantity of fuzzy control; S42. Establish fuzzy linguistic variables for each feature input variable in the feature vector of multi-dimensional dynamic characteristics, set the fuzzy linguistic value levels as low, medium and high, and perform fuzzy processing on the feature input variables using the membership function to form a fuzzy input set; S43. Construct a fuzzy control rule base. The fuzzy control rules in the fuzzy control rule base are established based on actual processing experience and historical data analysis. The input conditions are composed of the fuzzy levels of three channels: vibration, temperature and load, and the output control level reflects the stability of the current processing state; S44. Based on the membership function and the fuzzy control rule base, perform fuzzy inference on the feature input variables to generate a fuzzy output quantity. The fuzzy levels of the processing state are set as stable, general and unstable; 6. The adaptive vibration suppression method for diamond picks based on the fuzzy control algorithm according to claim 5, characterized in that, The three levels of stable, general and unstable are constructed as follows: If the root mean square value of the vibration signal is high, the instantaneous temperature rise rate is medium, and the cutting force fluctuation rate of the load signal is high, the processing state is unstable; If the main frequency component of the vibration signal is medium, the average temperature is low, and the average value of the load signal is medium, the processing state is stable; If the kurtosis of the vibration signal is low, the temperature fluctuation amplitude is high, and the peak duration of the load signal is medium, the processing state is general; 7. An adaptive vibration suppression method for diamond picks based on a fuzzy control algorithm according to claim 5, characterized in that, The S5 includes the following steps: S51. Establish a fuzzy set of control output quantities according to the fuzzy level of the processing state , and define the adjustment amounts of the cutter rotation speed , the adjustment amount of the feed speed and the adjustment amount of the cooling parameter respectively according to the stable, general, and unstable levels of the processing state. The fuzzy output levels are decrease, unchanged, and increase; S52. Based on the fuzzy inference results of stable, general, and unstable machining state levels, construct the membership functions of the control output quantity respectively. The value range of the membership function of the control output quantity represents the adjustment amounts of the tool rotation speed, feed rate, and cooling parameters respectively; S53. Defuzzify the fuzzy set of the control output quantity Perform defuzzification processing, and determine the exact numerical values of each control output quantity based on the improved centroid defuzzification algorithm corrected by dynamic weights : Among them, represents the value of the th control quantity corresponding to the tool rotation speed adjustment amount, feed speed adjustment amount, and cooling parameter adjustment amount, is the membership degree corresponding to the processing state level being stable, general, or unstable when the control quantity takes this value, is the number of elements in the output quantity fuzzy set, is the dynamic weight coefficient, which is determined by combining the non - linear degree of the actual machining vibration characteristics of the diamond pick. Based on the kurtosis and peak factor of the vibration signal monitored in real - time, the size of the weight coefficient is dynamically adjusted, so that the weight coefficient of the control quantity value close to the required value for the actual vibration state in the output quantity fuzzy set is increased, and the weight coefficient of the control quantity value deviating from the required value for the actual vibration state is decreased; S54. Convert the exact numerical values of each control output quantity into specific process control instruction sets , including the tool speed control instruction adjusted according to the machining status level , which is used to suppress the vibration amplitude in real time; the feed speed control instruction adjusted according to the machining status level , which is used to adapt to load changes; the cooling parameter control instruction adjusted according to the machining status level , which is used to regulate the machining temperature state and realize the real-time active suppression of the vibration during the diamond pick machining process.

Images