Hard cutter machining stability control device

Abstract

The invention relates to a hard cutter machining stability control device which comprises a monitoring module which comprises a vibration monitoring unit used for collecting vibration signals in the machining process in real time and a temperature monitoring unit used for obtaining the temperature of a cutter and the temperature of cooling liquid in real time. The visual detection unit is used for periodically acquiring image data of the surface of the workpiece and the cutting edge of the cutter; the control module is used for receiving, fusing and analyzing data from the vibration monitoring unit, the temperature monitoring unit and the visual detection unit so as to judge the abnormal type in the machining process; the execution module comprises a temperature control unit used for adjusting parameters of cooling liquid, a rotating speed adjusting unit used for adjusting the rotating speed of a main shaft, a feeding adjusting unit used for adjusting the feeding speed and a shutdown control unit used for controlling shutdown of a machine tool. Wherein the control module is used for triggering at least one corresponding unit in the execution module to execute a control action according to the exception type. The stable state of the machining system is maintained under the complex dynamic working condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of machining, in particular to a hard tool machining stability control device. BACKGROUND

[0002] Hard tools are widely used in high-precision and high-efficiency metal cutting processes due to their excellent hardness and wear resistance. However, in actual machining, especially in precise or heavy-load cutting conditions, the stability of the machining system is easily disturbed and destroyed by various complex factors. For example, harmful vibrations and chatter generated during machining can cause deterioration of workpiece surface quality, size out-of-tolerance, and may even cause abnormal wear or damage to the tool; abnormal fluctuations in cutting area temperature can affect the mechanical properties of tool materials, exacerbate wear, and may change the machining characteristics of workpiece materials, thereby affecting the final machining precision; in addition, unpredictable changes in tool state (such as blade edge micro-collapse) and failure of cooling and lubrication effect of cutting fluid also directly threaten the continuity and stability of the machining process. The above factors interfere with each other, making the machining process exhibit complex dynamic characteristics, and once unstable, it will directly restrict the machining efficiency, product qualification rate and tool service life.

[0003] In order to deal with the problem of machining stability, it is common to monitor a single physical quantity (such as vibration, temperature or tool image) independently and implement a corresponding single-variable control strategy accordingly. For example, by monitoring the vibration signal to adjust the spindle speed, or by monitoring the temperature to adjust the cooling fluid flow. However, such a scheme based on a single information source or independent control loop has inherent limitations. Since various disturbance factors in the machining process often coexist and interact with each other, relying on a single dimension of information is difficult to comprehensively and accurately determine the type and source of instability of the overall system. This leads to the existing method having a monitoring blind area, insufficient recognition ability for complex abnormalities; the control action is not targeted and has limited precision; and the system response is lagging, making it difficult to achieve rapid and accurate intervention in complex and dynamic machining processes, thereby failing to fundamentally guarantee the comprehensive stability of the machining system. SUMMARY

[0004] Therefore, it is necessary to provide a hard tool machining stability control device that can comprehensively monitor and cooperatively control various disturbance factors in the machining process, thereby maintaining the stability of the machining system under complex dynamic conditions.

[0005] The hard tool machining stability control device provided by the present application comprises:

[0006] The monitoring module comprises a vibration monitoring unit for collecting vibration signals in real time during the machining process, a temperature monitoring unit for acquiring tool temperature and coolant temperature in real time, and a visual detection unit for periodically acquiring image data of the workpiece surface and the tool edge;

[0007] The control module is in communication connection with the monitoring module, configured to receive and fuse analyze data from the vibration monitoring unit, the temperature monitoring unit and the visual detection unit to determine the abnormal type in the machining process; and

[0008] The execution module is connected with the control module, comprising a temperature control unit for adjusting coolant parameters, a rotation speed adjusting unit for adjusting the rotation speed of the main shaft, a feed adjusting unit for adjusting the feed speed, and a shutdown control unit for controlling the shutdown of the machine tool;

[0009] The control module is configured to trigger the corresponding at least one unit in the execution module to perform a control action according to the abnormal type.

[0010] In one embodiment, the control module is an industrial controller with a multi-source information fusion analysis algorithm built-in, which is in communication connection with the vibration monitoring unit, the temperature monitoring unit and the visual detection unit respectively, configured to receive and fuse analyze data transmitted by each unit to determine the abnormal type in the machining process, and trigger the corresponding specific execution unit action based on the fusion analysis result.

[0011] In one embodiment, the multi-source information fusion analysis algorithm is configured to:

[0012] Timestamp alignment and normalization preprocessing of real-time data from the vibration monitoring unit, the temperature monitoring unit and the visual detection unit;

[0013] Multi-dimensional feature extraction, respectively from the preprocessed vibration signal, temperature signal and image data, extracting time domain, frequency domain and image feature parameters related to machining stability;

[0014] Weighted fusion decision, inputting the extracted multi-dimensional feature parameters into a preset fusion decision model, and generating a machining stability comprehensive evaluation index through weighted calculation;

[0015] Comparing the comprehensive evaluation index with a plurality of preset abnormal judgment thresholds, when the comprehensive evaluation index exceeds any abnormal threshold, determining the corresponding abnormal type, and generating a control instruction triggering the specific execution unit action.

[0016] In one embodiment, the feature extraction comprises:

[0017] Vibration feature extraction, calculating the energy proportion E v and the amplitude A of the main frequencyv ;

[0018] temperature feature extraction, calculating the instantaneous value T of the tool tip temperature t and its change rate ΔT in unit time t / Δt;

[0019] image feature extraction, performing edge detection and contrast analysis on the tool edge image to calculate the edge integrity coefficient C e ;

[0020] texture analysis on the workpiece surface image to calculate the surface roughness estimate R s ; wherein the fusion decision model takes the feature parameter set {E v , A v , T t , ΔT t / Δt, C e , R s} as input.

[0021] In one of the embodiments, the weighted fusion decision specifically includes:

[0022] To reflect the difference in the contribution of different feature parameters to each type of anomaly, a dynamic weight w i is assigned to each feature parameter related to the current machining condition.

[0023] The comprehensive evaluation index I k is calculated using the following formula to correspond to the kth type of anomaly:

[0024]

[0025] where F i is the normalized value of the ith feature parameter, w i,k is the dynamic weight of the ith feature parameter for the kth type of anomaly, and n is the total number of feature parameters; the dynamic weight w i,k is output in real time online based on a classification model trained based on historical machining data, or is adaptively adjusted according to the evaluation feedback of the control module on the adjustment effect of the previous control cycle.

[0026] In one of the embodiments, the control module is further configured to:

[0027] When the abnormal type is determined to be tool edge damage, the stop control unit is triggered to act; when the abnormal type is determined to be tool tip temperature, coolant temperature, or coolant temperature change rate exceeding the corresponding threshold, the temperature control unit is triggered to act; when the abnormal type is determined to be vibration signal amplitude exceeding the amplitude threshold, the rotation speed adjustment unit and the feed adjustment unit are triggered to act.

[0028] In one embodiment, the control module is further configured to:

[0029] When the vibration is determined to be unstable, the spindle speed is first adjusted to a preset stable speed range by the speed adjustment unit. Then, the feed adjustment unit is dynamically and dynamically adjusted in real time according to the amplitude of the chatter signal fed back by the vibration monitoring unit to achieve coordinated adaptation between the spindle speed and the feed speed.

[0030] In one embodiment, the coordinated adaptation of spindle speed and feed rate specifically includes:

[0031] Based on the current workpiece material, tool type, and depth of cut, the system queries the preset process parameter database to map the corresponding stable spindle speed range [S]. min S max ];

[0032] Control the speed adjustment unit to change the spindle speed from the current value S c Adjust to a target value S within the stability interval t ,in To achieve initial suppression of vibration instability;

[0033] When the spindle speed stabilizes at S t Then, the flutter signal fed back by the vibration monitoring unit is acquired in real time at a sampling frequency not lower than the preset frequency, and its amplitude envelope A is calculated. e (t);

[0034] According to the amplitude envelope A e (t) and the preset safety threshold A th The real-time deviation is calculated, the instantaneous adjustment amount ΔF(t) of the feed speed is calculated, and the feed adjustment unit is controlled to perform the adjustment.

[0035] In one embodiment, the calculation of the instantaneous adjustment amount ΔF(t) of the feed rate includes:

[0036] Calculate the flutter amplitude deviation e(t) = A e (t)-A th ;

[0037]

[0038] The calculated ΔF(t) is subjected to amplitude limiting to ensure that |ΔF(t)| ≤ ΔF max At the same time, set the dead zone threshold e db When |e(t)| <e db At that time, let ΔF(t) = 0 to avoid frequent operation of the actuator.

[0039] In one of the embodiments, the proportional, integral, and differential coefficients are adaptive parameters that are online set based on the dynamic characteristics of the machining process, and the specific setting process includes:

[0040] After the spindle speed is adjusted to a target value within the stable range, a small feed speed excitation signal of a set of pseudo-random binary sequences is applied, and response data of the chatter amplitude are collected simultaneously, and a second-order discrete transfer function model G(z) is identified online using the recursive least squares method to describe the influence of the feed speed variation on the chatter amplitude under the current working condition.

[0041] Based on the identified model G(z), a quadratic performance index J = ∑e 2 (t) and meets the control amount variation amplitude constraint as the optimization target, a model predictive control algorithm is used to solve and update the optimal values of the proportional, integral, and differential coefficients in each control cycle.

[0042] The above hard tool machining stability control device synchronously and real-timely collects multiple types of physical quantities in the machining process by setting a monitoring module containing vibration, temperature, and visual units, overcoming the monitoring blind area of a single information source; the control system can comprehensively judge the abnormal type by fusing and analyzing the above multiple source monitoring data, thereby accurately identifying the root cause of the machining instability; further, by configuring an execution module containing multiple execution units such as temperature control, speed regulation, feed regulation, and shutdown control, and triggering the corresponding specific control action according to the identified abnormal type by the control module, the differentiated and collaborative accurate control for different abnormal roots is realized. This scheme combines multi-source information perception, fusion decision, and multi-execution mechanism collaborative control organically to form a complete closed-loop control system, thereby being able to cope with multiple interference factors in the complex dynamic machining environment as a whole, effectively improving the comprehensiveness, accuracy, and response real-time of the control, and ultimately ensuring the comprehensive stability of the machining system. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0044] Figure 1 A schematic diagram of a hard tool machining stability control device of an embodiment.

[0045] Reference signs:

[0046] 110. Monitoring module; 112. Vibration monitoring unit; 114. Temperature monitoring unit; 116. Visual inspection unit; 120. Control module; 130. Execution module; 132. Temperature control unit; 134. Speed ​​adjustment unit; 136. Feed adjustment unit; 138. Stop control unit. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] It should be noted that when a component is referred to as being "fixed to" or "set on" another component, it can be directly on the other component or there may be an intermediate component. When a component is considered to be "connected to" another component, it can be directly connected to the other component or there may be an intermediate component present. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used in this specification are for illustrative purposes only and do not represent the only possible implementation.

[0049] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0050] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature and the second feature are in indirect contact through an intermediate medium. Furthermore, "above," "over," and "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0051] Unless otherwise defined, all technical and scientific terms used in the specification of the present application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. All publications, patent applications, patents, and other references mentioned in the specification of the present application are incorporated by reference. In case of a conflict in terminology, the present specification controls.

[0052] The application will be described below with reference to the following drawings. Figure 1 A hard tool machining stability control device of the present application is described.

[0053] As Figure 1As shown, in one embodiment, a hard tool machining stability control device includes a monitoring module 110, a control module 120 and an execution module 130, the monitoring module 110 contains a vibration monitoring unit 112, a temperature monitoring unit 114 and a visual detection unit 116, the vibration monitoring unit 112 is installed at the spindle of the machine tool or the tool holder to capture the chatter signal in real time during the machining process, the temperature monitoring unit 114 includes a temperature sensor for real-time acquisition of the tool tip temperature and a temperature sensor for real-time acquisition of the cooling liquid temperature, the visual detection unit 116 includes a high-speed camera for periodic scanning of the workpiece surface and the tool edge to obtain image data. The control module 120 is in communication connection with the monitoring module 110, which is an industrial controller with a multi-source information fusion analysis algorithm built-in, for receiving and fusion analysis of data from the vibration monitoring unit 112, the temperature monitoring unit 114 and the visual detection unit 116 to determine the type of abnormality in the machining process. The execution module 130 is connected with the control module 120, which includes a temperature control unit 132, a speed regulation unit 134, a feed regulation unit 136 and a shutdown control unit 138, wherein the temperature control unit 132 is an intelligent temperature control device for adjusting the flow and temperature of each nozzle cooling liquid according to the instruction, the speed regulation unit 134 is used to adjust the spindle speed with an accuracy of ±5 rpm according to the instruction, the feed regulation unit 136 is used to dynamically adjust the feed speed according to the instruction, and the shutdown control unit 138 is used to control the machine tool shutdown according to the instruction. The control module 120 is configured to trigger at least one corresponding unit in the execution module to perform control actions according to the determined type of abnormality, thereby realizing targeted intervention on multiple types of stability problems such as chatter, temperature abnormality, tool damage and excessive cutting during the machining process. The vibration monitoring unit 112 uses a high-frequency response acceleration sensor with a sampling frequency not less than 10 kHz, and its output end is connected with a signal conditioning circuit for filtering and amplifying the chatter signal, which can effectively capture high-frequency micro-vibration signals and improve the signal-to-noise ratio, laying a foundation for accurate identification of chatter. The temperature sensor is preferably an infrared temperature sensor with a temperature measurement range of 0℃-1000℃ and an accuracy of ±1℃, which accurately measures the tool tip temperature in a non-contact manner. The temperature sensor is a platinum resistance temperature sensor and is installed at the cutting fluid storage tank and the outlet of each cooling liquid nozzle, thereby comprehensively monitoring the temperature state of the cooling liquid system. The scanning period of the visual detection unit 116 can be adjusted, with an adjustment range of 0.1-1 seconds / time, and a light supplementing lamp is provided to irradiate the tool, taking into account the detection real-time performance and image acquisition quality, ensuring that the tool edge state and workpiece surface topography can be clearly captured.

[0054] The intelligent temperature control device includes a cooling liquid circulating pump, an electric heating element, a refrigerator, and a flow control valve corresponding to each cooling liquid nozzle, and realizes fine collaborative control of the cooling liquid flow and temperature through the integration of various actuators. The specific judgment and triggering logic of the control module 120 is: when the abnormal type is judged to be tool edge damage, the stop control unit 138 is triggered to act, realizing safety protection; when the tool tip temperature, the cooling liquid temperature or the change rate thereof exceeds the corresponding threshold value, the temperature control unit 132 is triggered to act, so as to maintain a stable cutting heat environment; when the vibration signal amplitude exceeds the amplitude threshold value, the rotation speed adjustment unit 134 and the feed adjustment unit 136 are triggered to act, so as to suppress vibration; when it is determined according to the visual detection data that there is excess cutting on the workpiece surface, it is judged whether it is caused by unstable vibration, if so, the rotation speed and the feed adjustment are triggered, if not, an alarm is issued, this process integrates multi-source information, improves the accuracy of fault attribution and avoids misadjustment.

[0055] In the control of vibration instability, the control module 120 is further used for: when the vibration instability is determined, the rotation speed adjustment unit 134 is controlled to adjust the spindle speed to a preset stable rotation speed interval, and the feed adjustment unit 136 is dynamically fine-tuned in real time according to the amplitude of the chatter signal fed back by the vibration monitoring unit 112, so as to realize the collaborative adaptation of the spindle speed and the feed speed. Specifically, according to the current workpiece material, tool type and cutting depth, the preset process parameter database is queried to map the corresponding spindle speed stable interval [S min , S max ]; the rotation speed adjustment unit 134 is controlled to adjust the spindle speed from the current value S c to a target value S t in the stable interval, wherein to realize the preliminary suppression of vibration instability, and the feed adjustment unit 136 is dynamically fine-tuned in real time according to the amplitude of the chatter signal fed back by the vibration monitoring unit, so as to realize the collaborative adaptation of the spindle speed and the feed speed. Compared with independent adjustment, this collaborative control strategy can more quickly and smoothly suppress chatter. When processing the cooling liquid temperature abnormality, the control module 120 preferentially controls the temperature control unit 132 to adjust the cooling liquid flow, and if the temperature still does not meet the standard after the flow adjustment, the heating or refrigeration function is started, this hierarchical adjustment mode optimizes the energy consumption while ensuring the temperature control effect. The control module 120 is further used for calculating an adjustment effect evaluation value by comparing the change amount of the monitoring parameters before and after the execution of the control action, and optimizing the adjustment strategy and triggering the execution again when the evaluation value is less than a preset threshold value, forming a closed-loop control including effect feedback and strategy optimization, and improving the self-adaptation ability and long-term control precision of the system.

[0056] To achieve the multi-source information fusion analysis, the algorithm built-in the control module 120 performs the following steps: first, data synchronization and preprocessing are performed, and the real-time data from the vibration monitoring unit, the temperature monitoring unit and the visual detection unit are subjected to timestamp alignment and normalization preprocessing to eliminate the influence of different dimensions and time synchronization; then, multi-dimensional feature extraction is performed, and time domain, frequency domain and image feature parameters related to machining stability are extracted from the preprocessed vibration signal, temperature signal and image data, specifically including: calculating the energy ratio E v of the vibration signal in the set frequency band v ; calculating the instantaneous value T t of the tool tip temperature and the change rate ΔT t / Δt of the tool tip temperature per unit time; performing edge detection and contrast analysis on the tool edge image to calculate the edge integrity coefficient C e , and performing texture analysis on the workpiece surface image to calculate the surface roughness estimate R s , so as to convert the original data into a set of key feature parameters {E v , A v , T t , ΔT t / Δt, C e , R s} representing the machining state; then, a weighted fusion decision is made, the multi-dimensional feature parameters extracted are input into a preset fusion decision model, first, a dynamic weight w i is assigned to each feature parameter to reflect the difference in the contribution of different feature parameters to each type of abnormality, then the comprehensive evaluation index I is calculated using the formula k to correspond to the kth type of abnormality, where F i is the normalized value of the ith feature parameter, w i,k is the dynamic weight of the ith feature parameter for the kth type of abnormality, and n is the total number of feature parameters. The dynamic weight w i,k is output in real time online based on a classification model trained based on historical machining data, or is adaptively adjusted according to the evaluation feedback of the control module on the adjustment effect of the previous control period, which enables the fusion decision to adapt to changing machining conditions and continuously optimize; finally, the comprehensive evaluation index I k is compared with a plurality of preset abnormality judgment thresholds, when I k exceeds any abnormality threshold, the corresponding abnormality type is determined, and a control instruction triggering the action of a specific execution unit is generated. Through quantitative fusion and adaptive weighting, the algorithm significantly improves the accuracy and reliability of abnormality recognition and classification.

[0057] In the implementation of dynamic fine adjustment of the feed speed, the control module 120 performs chatter signal tracking, and when the spindle speed is stabilized at St Subsequently, the chatter signal is acquired in real time at a sampling frequency no less than a preset frequency (e.g., 1 kHz) and the amplitude envelope A(t) is calculated e (t) is calculated e (t) and a preset safety threshold A th . The instantaneous adjustment amount ΔF(t) of the feed speed is calculated by the following process: first, the chatter amplitude deviation e(t) = A e (t) - A th is calculated; subsequently, a discrete proportional-integral-derivative controller with an overshoot suppression feature is used to generate the adjustment amount, whose control law is defined by the formula , where K p , K i , and K d are the proportional, integral, and derivative coefficients, respectively, and T s is the control period; then, the calculated ΔF(t) is subjected to amplitude limiting to ensure that |ΔF(t)| ≤ ΔF max , and a dead zone threshold e db is set, such that when |e(t)| < e db , ΔF(t) = 0, so as to avoid frequent action of the actuator, thereby ensuring the motion stability and service life of the feed system while effectively suppressing chatter. To further optimize the control performance, the proportional, integral, and derivative coefficients K p , K i , and K d of the controller are set as adaptive parameters that are online tuned based on the dynamic characteristics of the machining process, and the tuning method includes: after the speed priority regulation step is completed, a small amplitude feed speed excitation signal of a set of pseudo-random binary sequences is applied, and the response data of the chatter amplitude is collected, and a recursive least squares method is used to online identify a second-order discrete transfer function model G(z) to describe the influence dynamics of the change in the feed speed on the chatter amplitude under the current working condition; subsequently, based on the model G(z) obtained by the identification, a quadratic performance index J = Σe 2 (t) is minimized and the control amount change amplitude constraint is satisfied, a model predictive control algorithm is used to solve and update the optimal values of the proportional, integral, and derivative coefficients K p , K i , and K d at each control period in real time, and this process can online perceive and adapt to the dynamic changes of the machining system, thereby realizing self-tuning and adaptive optimization of the controller parameters and maintaining excellent chatter suppression effect under various complex working conditions.

[0058] Any combination of the technical features in the above-described embodiments can be made, and for the sake of brevity, not all possible combinations are described, however, as long as there is no conflict, any combination of the technical features should be considered within the scope of the present disclosure.

[0059] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A stability control device for machining hardened cutting tools, characterized in that, The device includes: The monitoring module includes a vibration monitoring unit for real-time acquisition of vibration signals during the machining process, a temperature monitoring unit for real-time acquisition of tool temperature and coolant temperature, and a visual inspection unit for periodically acquiring image data of the workpiece surface and tool cutting edge. The control module, communicatively connected to the monitoring module, is used to receive and analyze data from the vibration monitoring unit, temperature monitoring unit, and visual inspection unit to determine the type of abnormality during processing; and The execution module, connected to the control module, includes a temperature control unit for adjusting coolant parameters, a speed adjustment unit for adjusting spindle speed, a feed adjustment unit for adjusting feed rate, and a shutdown control unit for controlling machine tool shutdown. The control module is used to trigger at least one corresponding unit in the execution module to perform a control action based on the exception type.

2. The hard tool machining stability control device according to claim 1, characterized in that, The control module is an industrial controller with a built-in multi-source information fusion analysis algorithm. It is communicatively connected to the vibration monitoring unit, temperature monitoring unit, and visual inspection unit, respectively. It is used to receive and fuse the data transmitted by each unit to determine the abnormality type of the processing process, and trigger the corresponding specific execution unit action based on the fusion analysis result.

3. The hard tool machining stability control device according to claim 2, characterized in that, The multi-source information fusion analysis algorithm is used for: The real-time data from the vibration monitoring unit, temperature monitoring unit, and visual inspection unit are preprocessed with timestamp alignment and normalization. Multi-dimensional feature extraction was performed, extracting time-domain, frequency-domain, and image feature parameters related to processing stability from the preprocessed vibration signal, temperature signal, and image data respectively; A weighted fusion decision is performed by inputting the extracted multi-dimensional feature parameters into a preset fusion decision model, and generating a comprehensive evaluation index of processing stability through weighted calculation. The comprehensive evaluation index is compared with multiple preset anomaly detection thresholds. When the comprehensive evaluation index exceeds any anomaly threshold, the corresponding anomaly type is determined, and a control instruction that triggers the action of a specific execution unit is generated.

4. The hard tool machining stability control device according to claim 3, characterized in that, The feature extraction includes: Vibration feature extraction, calculation of the energy proportion E of the vibration signal within a set frequency band. v With the main frequency amplitude A v ; Temperature feature extraction, calculation of the instantaneous value T of the tool tip temperature. t and its rate of change ΔT per unit time t / Δt; Image feature extraction is performed, edge detection and contrast analysis are conducted on the cutting edge image, and the cutting edge integrity coefficient C is calculated. e ; Perform texture analysis on the workpiece surface image and calculate the estimated surface roughness R. s ; wherein, the fusion decision model will use the feature parameter set {E} v A v ,T t ,ΔT t / Δt, C e R s } as input.

5. The hard tool machining stability control device according to claim 3, characterized in that, The weighted fusion decision-making process specifically includes: To reflect the differences in the contribution of different feature parameters to various anomalies, a dynamic weight w related to the current processing condition is assigned to each feature parameter. i ; The comprehensive evaluation index I is calculated using the following formula. k To correspond to the kth exception type: Among them, F i w is the normalized value of the i-th feature parameter. i,k The dynamic weight w is the weight of the i-th feature parameter for the k-th anomaly type, where n is the total number of feature parameters; i,k The system outputs data online in real time through a classification model trained on historical processing data, or it adaptively adjusts based on the evaluation feedback from the control module regarding the adjustment effect of the previous control cycle.

6. The hard tool machining stability control device according to claim 1, characterized in that, The control module is also used for: When the abnormality type is determined to be a tool edge defect, the shutdown control unit is triggered; when the abnormality type is determined to be that the tool tip temperature, coolant temperature, or coolant temperature change rate exceeds the corresponding threshold, the temperature control unit is triggered; when the abnormality type is determined to be that the vibration signal amplitude exceeds the amplitude threshold, the speed adjustment unit and the feed adjustment unit are triggered.

7. The hard tool machining stability control device according to claim 6, characterized in that, The control module is also used for: When the vibration is determined to be unstable, the spindle speed is first adjusted to a preset stable speed range by the speed adjustment unit. Then, the feed adjustment unit is dynamically and dynamically adjusted in real time according to the amplitude of the chatter signal fed back by the vibration monitoring unit to achieve coordinated adaptation between the spindle speed and the feed speed.

8. The hard tool machining stability control device according to claim 7, characterized in that, The coordinated adaptation of spindle speed and feed rate specifically includes: Based on the current workpiece material, tool type, and depth of cut, the system queries the preset process parameter database to map the corresponding stable spindle speed range [S]. min ,S max ]; Control the speed adjustment unit to change the spindle speed from the current value S c Adjust to a target value S within the stability interval t ,in To achieve initial suppression of vibration instability; When the spindle speed stabilizes at S t Then, the flutter signal fed back by the vibration monitoring unit is acquired in real time at a sampling frequency not lower than the preset frequency, and its amplitude envelope A is calculated. e (t); According to the amplitude envelope A e (t) and the preset safety threshold A th The real-time deviation is calculated, the instantaneous adjustment amount ΔF(t) of the feed speed is calculated, and the feed adjustment unit is controlled to perform the adjustment.

9. The hard tool machining stability control device according to claim 8, characterized in that, The instantaneous adjustment ΔF(t) for calculating the feed rate includes: Calculate the flutter amplitude deviation e(t) = A e (t)-A th ; The calculated ΔF(t) is subjected to amplitude limiting to ensure that |ΔF(t)| ≤ ΔF max At the same time, set the dead zone threshold e db When |e(t)| <e db At that time, let ΔF(t) = 0 to avoid frequent operation of the actuator.

10. The hard tool machining stability control device according to claim 1, characterized in that, The proportional, integral, and derivative coefficients are adaptive parameters that are tuned online based on the dynamic characteristics of the machining process. The specific tuning process includes: After the spindle speed is adjusted to a target value within the stable range, a set of pseudo-random binary sequence small-amplitude feed speed excitation signals are applied, and at the same time, the response data of chatter amplitude is collected. A second-order discrete transfer function model G(z) is identified online using the recursive least squares method to describe the dynamic influence of feed speed change on chatter amplitude under the current working condition. Based on the identified model G(z), the quadratic performance index J = ∑e is used to minimize the amplitude deviation. 2 (t) and satisfying the control quantity change amplitude constraint as the optimization objective, the model predictive control algorithm is used to solve the problem in each control cycle and update the optimal values ​​of the proportional, integral and derivative coefficients in real time.

Images