Vertical superfinishing machine intelligent servo control method based on dynamic parameter identification

Abstract

The invention discloses a vertical superfinishing machine intelligent servo control method based on dynamic parameter identification, and relates to the technical field of servo control. Comprising the steps that first sensing equipment is arranged on a key motion axis of target equipment and used for obtaining vibration data of the motion axis, and vibration information items are obtained; and second sensing equipment is arranged on the oilstone unit, is pressure and temperature integrated sensing equipment and is used for acquiring real-time pressure data and temperature data of the oilstone to obtain a pressure information item and a temperature information item. According to the method, damage sorting is combined, low-damage combinations with different oscillation frequencies and feeding speeds are preferentially selected to serve as equipment execution, updating information of vibration information items, pressure information items and temperature information items is deeply obtained, secondary adjustment is conducted on initial information items, and the accuracy of the equipment is improved. Therefore, oilstone driving control based on dynamic parameter identification of vibration data, temperature data and pressure data combination is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of servo control, in particular to an intelligent servo control method for a vertical ultra-precision machine based on dynamic parameter identification. BACKGROUND

[0002] A vertical ultra-precision machine refers to a vertical structure ultra-precision machine tool, which is commonly used for high-precision machining tasks such as grinding, polishing and micro-sculpting. Servo control is a feedback-based control system that uses servo motors and sensors to adjust output in real time, ensuring accurate action and fast response. The common basic method is PID control. The intelligent servo control method for a vertical ultra-precision machine refers to an advanced control system applied to a vertical ultra-precision machine tool, which combines servo control technology and artificial intelligence algorithms to achieve higher precision, efficiency and self-adaptive machining processes. It is a technical method that optimizes the operation of servo motors through intelligent algorithms to improve the performance and reliability of the ultra-precision machine.

[0003] The patent with publication number CN111624873A is a three-axis inertial stabilization platform system servo loop variable gain control method. It overcomes the problem of servo loop stability decline caused by the change of system bandwidth when the rotational inertia changes under full attitude conditions with non-zero βyk and βzk. It realizes robust stability under full attitude conditions. It overcomes the problem of servo loop static and dynamic precision decline caused by the change of rotational inertia under full attitude conditions with non-zero βyk and βzk. It realizes precision maintenance capability under full attitude conditions. There is no solution area in the calculation process, which can cover any attitude angle. Compared with existing calculation methods, it is more accurate and has wider applicability.

[0004] The above and similar technical solutions have the problem of precision drift caused by the wear of the guide rail, ball screw, oil stone and other components inside the equipment due to long-term mechanical wear during the servo control process of the vertical ultra-precision machine. The precision is further affected. The oscillation data caused by the oil stone under the influence of different oscillation frequencies and feed speeds during machining is also different. Therefore, under the influence of fixed oscillation frequency and feed speed combination, the lowest precision drift effect cannot be obtained. SUMMARY

[0005] The present application relates to the technical field of servo control, in particular to an intelligent servo control method for a vertical ultra-precision machine based on dynamic parameter identification.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solution: an intelligent servo control method for a vertical ultra-precision machine based on dynamic parameter identification, comprising: The first sensing device is arranged on a key motion axis of the target device to obtain vibration data of the motion axis, and vibration information is obtained; The second sensing device is arranged on the oil stone unit, and the second sensing device is a pressure and temperature integrated sensing device, which is used to obtain real-time pressure data and temperature data of the oil stone, and pressure information and temperature information are obtained; The processing requirement is obtained, and the processing requirement is a processing surface precision requirement. Based on the processing requirement, the actual precision data of the target workpiece is obtained through the image acquisition device, and a real-time precision item is obtained; The initial data of the oil stone is obtained, including the oscillation frequency and the feed speed, and the initial information item is obtained. Based on the difference between the real-time precision item and the processing requirement, a first correlation model is created based on the initial information. The first correlation model outputs the correlation data of different initial data and processing surface precision data. Based on the processing requirement as input, the initial information item is preliminarily adjusted through the first correlation model, and an initial adjustment item is obtained; Based on the initial adjustment item, the update information of the vibration information item, the pressure information item and the temperature information item is obtained, and the initial information item is adjusted twice through the adjustment method, so as to realize the dynamic parameter identification of the oil stone driving control based on the combination of vibration data, temperature data and pressure data.

[0007] Further, the first sensing device is a vibration sensing device, and the vibration information item is obtained by: The motion axis assembly information of the target vertical superfinishing machine is obtained, including the oil stone supply guide rail, the lead screw and the C shaft, and the installation information item is obtained; Based on the installation information item, an interval value is set, the interval value is a fixed value, the installation information item is regionally divided based on the interval value, at least three regionally divided items are obtained, and the vibration sensing device is arranged based on the regionally divided items to obtain vibration data, and a vibration data set is obtained; The average vibration information of the vibration data set is obtained, and the vibration information item is obtained.

[0008] Further, the second sensing device is a flexible multi-modal sensing patch, and the pressure information item and the temperature information item are obtained by: The oil stone working scene information is obtained, including the workpiece contact area and the oscillation area, and the oil stone working scene information is regionally divided based on the workpiece contact area and the oscillation area, and a first region and a second region are obtained; Based on the first region and the second region, the flexible sensing patch is respectively attached, the flexible sensing patch integrates the microcavity pressure sensor and the thin film thermocouple sensor, and the installation information item is obtained; Based on the installation information item, the pressure data and the temperature data are obtained, and the pressure information item and the temperature information item are obtained.

[0009] Further, the method for obtaining the processing requirement comprises: obtaining target workpiece processing data, including processing drawings, performing information scanning based on the processing data, obtaining precision marking data, and obtaining marking information items; generating processing parameter instructions based on the marking information items, taking the processing parameter instructions as input of the target vertical super-precision machine, obtaining output data, and further obtaining the processing requirement.

[0010] Further, the image acquisition device comprises a non-contact detection probe, and the method for obtaining the real-time precision item comprises: The non-contact detection probe comprises a red-blue-ultraviolet three-waveband confocal microscopic probe assembly for penetrating oil mist to obtain nanoscale three-dimensional topography, obtaining processing images, setting arrangement points based on the processing images, integrating the arrangement points on the side of the oil stone, installing the non-contact probe based on the arrangement points, and obtaining probe installation items; Based on the probe installation items, a scanning threshold value is set, the scanning threshold value is a fixed time value, the processing surface is scanned based on the scanning threshold value, a 3D point cloud map is reconstructed, roughness information is calculated in real time, and real-time precision items are obtained.

[0011] Further, the method for creating the first correlation model comprises: Based on the initial information items, the physical relationship between the initial information items and the real-time precision items is extracted to obtain first extraction items; A physical information neural network is designed, taking the initial information items as the input layer, the LSTM processing time series data as the hidden layer, and the real-time precision items as the output layer, the first extraction items are taken as training data for model training, the correlation data between the oscillation frequency and the feed speed and the real-time precision items are output, and further the first correlation model is obtained.

[0012] Further, the method for obtaining the initial adjustment item comprises: Based on the first correlation model, taking the processing requirement as input, based on the model output result, obtaining the information combination of the initial information items, obtaining the combination information set; Based on the combination information set, combination damage data including oscillation frequency damage and feed speed damage are obtained, damage sorting is performed based on the combination damage data, damage sorting items are obtained, based on the damage sorting items, the combination corresponding to the lowest damage is taken as the benchmark adjustment combination, and further the initial adjustment item is obtained.

[0013] Further, the adjustment method comprises: Based on the damage sorting items, a damage range is set, the damage range is a fixed range value, based on the damage range and the combination result of the lowest damage, a damage fluctuation item is obtained; The combination corresponding to the damage fluctuation term is obtained as a secondary adjustment combination, the update information of the vibration information term, the pressure information term and the temperature information term is respectively obtained, the fluctuation range of the update information is obtained, the combination with the lowest fluctuation range is obtained as an adaptive adjustment combination, and the initial information term is then secondarily adjusted.

[0014] Further, the adjustment method further comprises: The weight combination term is obtained based on the benchmark weight and the fluctuation range combination result of the update information, the combination with the lowest weight in the weight combination term is obtained as an update adaptive adjustment combination, and the initial information term is secondarily adjusted.

[0015] Compared with the prior art, the present application has the following beneficial effects: The intelligent servo control method of the vertical super-precision machine based on dynamic parameter identification constructs a vibration-pressure-temperature-topography four-dimensional sensing network by integrating a flexible patch of microcavity / thermocouple and a three-waveband confocal probe, and constructs a first correlation model therefrom, preferentially selects a low-damage combination of different oscillation frequencies and feed speeds as the device to be executed according to the output result of the first correlation model through combination damage sorting, and deeply obtains update information of the vibration information term, the pressure information term and the temperature information term to secondarily adjust the initial information term, so as to realize oilstone driving control based on dynamic parameter identification of vibration data, temperature data and pressure data combination. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The figure is a schematic diagram of the overall process of the present application; Figure 2 The figure is a schematic diagram of the vibration information term acquisition process of the present application; Figure 3 The figure is a schematic diagram of the processing requirement acquisition process of the present application; Figure 4 The figure is a schematic diagram of the initial adjustment term acquisition process of the present application; Figure 5 The figure is a schematic diagram of the combination information set of the present application. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0018] The vertical superfinishing machine is affected by mechanical wear caused by long-term operation and vibration in the machining process, which can cause precision drift, which seriously restricts the machining quality. Precision drift refers to the deviation between the actual machining position and the theoretical position of the machine due to various factors during long-term machining. This deviation can directly lead to a decrease in machining precision, and even cause the workpiece to be scrapped. The guide rail is an important component that supports and guides the movement of the moving part. Wear can cause the geometric precision of the guide rail to decrease, increase the frictional resistance of the moving part, and affect its stability and precision. Local wear of the guide rail can also cause the movement trajectory of the moving part to deviate, thereby affecting the machining precision. The oil stone directly contacts the workpiece during superfinishing, and its wear has a direct impact on the machining precision. The wear of the oil stone can cause changes in its shape, affecting the contact area and contact pressure with the workpiece, thereby affecting the smoothness and precision of the machined surface. The technical solution provided by the present application constructs a vibration-pressure-temperature-topography four-dimensional sensing network through the integration of a flexible patch of microcavity / thermocouple and a three-waveband confocal probe, and builds a first correlation model based on this. According to the output results of the first correlation model, the low-damage combination of different oscillation frequencies and feed speeds is preferentially selected as the device for execution through combined damage sorting, and the update information of the vibration information item, the pressure information item and the temperature information item is deeply obtained to perform secondary adjustment on the initial information item, thereby realizing oil stone driving control based on dynamic parameter identification of vibration data, temperature data and pressure data combination, such as Figure 1 as shown, comprising steps S100-S600.

[0019] Step S100: A first sensing device is arranged on the key motion axis of the target device for acquiring vibration data of the motion axis to obtain vibration information items.

[0020] It should be noted that, as Figure 2 shown, the first sensing device is a vibration sensing device, and the method for acquiring vibration information items includes: acquiring motion axis component information of the target vertical superfinishing machine, including the oil stone supply guide rail, the lead screw and the C-axis, to obtain installation information items; based on the installation information items, an interval value is set, which is a fixed value, and the installation information items are regionally divided based on the interval value to obtain at least three regional division items; vibration sensing devices are arranged based on the division region items to acquire vibration data to obtain a vibration data set; the average vibration information of the vibration data set is acquired to obtain the vibration information items.

[0021] Specifically, the set interval value is 200mm, i.e. the oil stone supply guide rail, lead screw and C-axis information of the target vertical superfinishing machine is regionally divided at intervals of 200mm to obtain multiple division region items, and vibration sensing devices are arranged in each division region item for acquiring vibration data, and the average vibration data acquired by each vibration sensing device is calculated as the vibration information items.

[0022] Step S200: A second sensing device is arranged on the oil stone unit to obtain real-time pressure data and temperature data of the oil stone, to obtain a pressure information item and a temperature information item.

[0023] It should be noted that the second sensing device is a pressure and temperature integrated sensing device, the second sensing device is a flexible multi-modal sensing patch, and the obtaining method of the pressure information item and the temperature information item comprises: obtaining oil stone working scene information, including a workpiece contact area and an oscillation area, performing regional division on the oil stone working scene information based on the workpiece contact area and the oscillation area to obtain a first region and a second region; based on the first region and the second region, respectively, the flexible sensing patch is attached, the flexible sensing patch integrates a micro-cavity pressure sensor and a thin-film thermocouple sensor, to obtain an installation information item; based on the installation information item, pressure data and temperature data are obtained, to obtain the pressure information item and the temperature information item.

[0024] Specifically, the thickness of the flexible multi-modal sensing patch is <0.5mm, which does not interfere with processing, and the working scene is divided into regions under the working state of the oil stone, wherein the position in contact with the workpiece is determined as the contact area, and the area for clamping and supporting the oil stone is determined as the oscillation area, so the flexible sensing patch integrating the micro-cavity pressure sensor and the thin-film thermocouple sensor is attached respectively, to obtain the clamping pressure data of the oil stone and the temperature data of the oscillation area.

[0025] Step S300: Obtain the processing requirement, the processing requirement is the processing surface precision requirement, based on the processing requirement, obtain the actual precision data of the target workpiece through the image acquisition device, to obtain a real-time precision item.

[0026] It should be noted that, as Figure 3 The obtaining method of the processing requirement comprises: obtaining target workpiece processing data, including processing drawings, performing information scanning based on the processing data to obtain precision marking data, to obtain a marking information item; generating a processing parameter instruction based on the marking information item, taking the processing parameter instruction as input of the target vertical superfinishing machine, obtaining output data, and then obtaining the processing requirement.

[0027] Specifically, before starting, the workpiece drawing is scanned, the precision marking such as Ra, roundness and the like is recognized by AI, and then the processing parameter instruction is generated, for example, the conical raceway: Ra≤0.1μm, roundness improvement≥25% and the like, taking the processing parameter instruction as input of the target vertical superfinishing machine, obtaining output data, and then obtaining the processing requirement.

[0028] It should be noted that the image acquisition device includes a non-contact detection probe, and the method for acquiring the real-time precision item includes: the non-contact detection probe includes a red-blue-ultraviolet three-band confocal microscopic probe assembly for penetrating through oil mist to acquire nanoscale three-dimensional topography, to acquire a processing image, to set a layout point based on the processing image, to integrate the layout point on the side of the oil stone, to install the non-contact probe based on the layout point, and to obtain a probe installation item; based on the probe installation item, a scanning threshold is set, the scanning threshold is a fixed time value, the processing surface is scanned based on the scanning threshold, a 3D point cloud map is reconstructed, and roughness information is calculated in real time to obtain the real-time precision item.

[0029] Specifically, according to the processing image, the contact point of the oil stone and the workpiece in the processing image is taken as a judgment point, the layout point is arranged on the side of the judgment point, and the non-contact probe is installed based on the layout point. Since the non-contact detection probe includes a red-blue-ultraviolet three-band confocal microscopic probe assembly, the spectral range is set to 400-1000 nm, the Z-axis resolution is 0.05 μm, the set scanning threshold is 5 s, and based on the scanning threshold, the processing surface is continuously scanned by the non-contact detection probe, the scanning path is synchronized, the probe is linked with the oil stone through a ball screw, and the scanning track is ensured to cover the processing area. The imaging process is as follows: in the super-precision circulation step, after completing a section of the raceway processing, the probe triggers high-speed scanning, the single-frame scanning time is <0.5 seconds, which meets the beat requirement, and is collected through a multi-spectral channel. Among them, the morphology layer: 6-wavelength light beams scan the surface to generate a 3D point cloud with a resolution of 0.1 μm, and the material layer: analyzes the difference in reflected spectrum to identify residual cutting fluid and oil stone material adhesion. Then, an AI demand analysis engine is constructed, and the data processing process includes defect classification. Among them, image segmentation: AI identifies the raceway and the edge area, and excludes non-processing area interference. Defect classification: a CNN model is trained to identify 7 typical defects such as scratches, pits, and adhesive wear, and is associated with oil stone parameters. Then, AI is used for output, real-time precision is calculated by fusing a physical model, and then the real-time precision item is obtained.

[0030] Step S400: acquiring oil stone initial data, including oscillation frequency and feed speed, obtaining initial information item, based on the difference between real-time precision item and processing requirement, creating a first correlation model based on initial information.

[0031] It should be noted that the first correlation model outputs the correlation data of different initial data and processing surface precision data, and the creation method of the first correlation model includes: based on the initial information item, the physical relationship between the initial information item and the real-time precision item is extracted to obtain a first extraction item; a physical information neural network is designed, the initial information item is taken as an input layer, the LSTM processes time sequence data as a hidden layer, and the real-time precision item is taken as an output layer, the first extraction item is taken as training data for model training, and the correlation data of the oscillation frequency and the feed speed and the real-time precision item is output, and then the first correlation model is obtained.

[0032] Specifically, the physical relationship between the initial information item and the real-time precision item is extracted, including the extraction of the physical relationship between the roughness Ra and the oscillation frequency f to obtain the first extraction item, the design of the physical information neural network, the model architecture of which includes sensor data, physical constraint layer, neural network backbone, optimization control instruction and device execution, the fusion core of which includes embedding the physical relationship equation and outputting the physical law, the physical constraint equation includes the guideway wear model and the oil stone fatigue accumulation model, wherein the guideway wear model is: ; wherein is the guideway positioning error, is the wear rate coefficient, is the sliding friction force, is the feed speed, is the material activation energy, is the ideal gas constant, is the workbench temperature; the oil stone fatigue accumulation model is: ; wherein is the oil stone fatigue accumulation value, is the oil stone contact stress amplitude, is the oil stone fatigue limit stress, is the material fatigue index, is the oscillation frequency, and then the neural network backbone is constructed: import torch import torch.nn as nn class PINN_Model(nn.Module): def __init__(self): super().__init__() # Sensor data input layer (4 dimensions: vibration, temperature, pressure, frequency) self.input_layer = nn.Linear(4, 64) # Physical information embedding layer self.physics_constraint = nn.Sequential( nn.Linear(64, 32), PhysicsActivation() # Custom activation function, step 1 equation is forced to execute ) # Double task output self.task_branch = nn.ModuleDict({ "wear_comp": nn.Linear(32, 1), # Output wear compensation amount Δx "life_pred": nn.Linear(32, 1) # Outputs the remaining lifespan of the oilstone. }) def forward(self, x): x = torch.relu(self.input_layer(x)) x = self.physics_constraint(x) # Physics constraints take effect return { "compensation": self.task_branch["wear_comp"](x), "life_left": torch.sigmoid(self.task_branch["life_pred"](x)) } # Physical activation function (forces satisfaction of differential equations) class PhysicsActivation(nn.Module): def forward(self, x): # The wear model differential equation from step 1 is embedded here. dxdt = k1×F_f× v× torch.exp(-Q / (R×T)) return x× dxdt # Physical laws as constraints Simultaneously, loss functions are designed, including data fitting loss and physical law loss, which include constraint one and constraint two. Constraint one: the rate of change of positioning error must satisfy the wear model. Constraint two: the probability of fracture when the oilstone life is exhausted is >99%. Then, real-time control closed loop and model output are performed to obtain the first correlation model.

[0033] Step S500: Based on the processing requirements as input, the initial information items are initially adjusted through the first association model to obtain the initial adjustment items.

[0034] It is important to note that, such as Figure 4As shown, the method for obtaining the initial adjustment term includes: based on the first correlation model, taking the processing requirements as input, and based on the model output results, obtaining the information combination of the initial information terms to obtain the combined information set; based on the combined information set, obtaining the combined damage data, including oscillation frequency damage and feed speed damage; based on the combined damage data, sorting the damage to obtain the damage sorting term; based on the damage sorting term, taking the combination corresponding to the lowest damage as the benchmark adjustment combination, and thus obtaining the initial adjustment term.

[0035] Specifically, such as Figure 5 As shown, under the premise of fixed processing requirements, multiple combinations of initial information items can be obtained based on the model's output. For example, when the surface roughness Ra of the arc does not exceed 0.15μm, it can be achieved through multiple combinations of different oscillation frequencies and feed rates, including combination 1: oscillation frequency A, feed rate B; combination 2: oscillation frequency C, feed rate D; combination 3: oscillation frequency E, feed rate F, etc. Different oscillation frequencies and feed rates will cause different damage to the machine. At this time, the combined damage data is obtained. For example, the damage caused by oscillation frequencies A, C, and E is 2%, 3%, and 3%, respectively, and the damage caused by feed rates B, D, and F is 4%, 2%, and 1%, respectively. At this time, the combined damage data of combination 1, combination 2, and combination 3 are 6%, 5%, and 4%, respectively. Then, the damage is sorted based on the combined damage data to obtain the damage sorting item, that is, combination 3 < combination 2 < combination 1. Based on the damage sorting item, the combination corresponding to the lowest damage is used as the benchmark adjustment combination, and then the initial adjustment item is obtained, that is, the initial information item is adjusted with oscillation frequency E and feed rate F.

[0036] Step S600: Based on the initial adjustment terms, obtain the updated information of vibration information terms, pressure information terms, and temperature information terms, and perform secondary adjustment on the initial information terms through the adjustment method.

[0037] It is important to note that secondary adjustment of the initial information items enables oilstone drive control based on dynamic parameter identification of combinations of vibration, temperature, and pressure data. The adjustment method includes: setting a damage range based on the damage ranking item, with the damage range being a fixed range value; obtaining the damage fluctuation item based on the combination result of the damage range and the lowest damage; obtaining the combination corresponding to the damage fluctuation item as the secondary adjustment combination; using the secondary adjustment combination as the adjustment pattern; obtaining the update information of the vibration, pressure, and temperature information items respectively; obtaining the fluctuation range of the update information; obtaining the combination with the lowest comprehensive fluctuation range as the adaptive adjustment combination; and then performing secondary adjustment of the initial information items.

[0038] Specifically, the set damage range is 50%, based on the combination result of the damage range and the minimum damage, the damage fluctuation item is obtained, when the combination information is: combination 1: oscillation frequency A, feed speed B; combination 2: oscillation frequency C, feed speed D; combination 3: oscillation frequency E, feed speed F, etc., and different oscillation frequencies and feed speeds will bring different damages to the machine, at this time, the combined damage data is obtained, for example, the damages caused by oscillation frequencies A, C, E are 2%, 3% and 3% respectively, and the damages caused by feed speeds B, D, F are 4%, 2% and 1% respectively, at this time, the combined damage data of combination 1, combination 2 and combination 3 is 6%, 5% and 4% respectively, when the minimum damage combination result is 4%, the damage fluctuation item is 6% at this time, the combination corresponding to the damage fluctuation item is obtained as the secondary adjustment combination, that is, combination 2 and combination 3, the update information of the vibration information item, the pressure information item and the temperature information item is obtained respectively by taking the secondary adjustment combination as the adjustment style, the fluctuation range of the update information is obtained, and the obtained data is shown in Table 1: Table 1

[0039] The lowest combination of the comprehensive fluctuation range is obtained as the adaptive adjustment combination, that is, the oscillation frequency C corresponding to combination 2 and the feed speed D, and then the initial information item is secondary adjusted.

[0040] It should be noted that the adjustment method further comprises: based on the vibration information item, the pressure information item and the temperature information item, the weight is set respectively, based on the combination result of the weight and the fluctuation range of the update information, the weight combination item is obtained, the lowest combination in the weight combination item is obtained as the update adaptive adjustment combination, and the initial information item is secondary adjusted.

[0041] Specifically, since the importance of the vibration information item, the pressure information item and the temperature information item is different in different machines, for example, due to equipment aging, the influence of the vibration information item will be much greater than that of the pressure information item and the temperature information item, at this time, the weight is adjusted, for example, the weight corresponding to the vibration information item is adjusted to 60%, and the weights corresponding to the pressure information item and the temperature information item are 20% respectively, at this time, the lowest combination is obtained as the update adaptive adjustment combination according to the adjusted weight and the update information, and the initial information item is secondary adjusted.

[0042] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended embodiments and their equivalents.

Claims

1. A method for intelligent servo control of a vertical ultraprecision machine based on dynamic parameter identification, comprising: A first sensing device is arranged on the key motion axis of the target device to acquire vibration data of the motion axis and obtain vibration information items. Its characteristic is that it further includes: A second sensing device is installed on the oilstone unit. The second sensing device is an integrated pressure and temperature sensing device, which is used to acquire real-time pressure data and temperature data of the oilstone to obtain pressure information items and temperature information items. The processing requirements are obtained, which are the accuracy requirements of the processing surface. Based on the processing requirements, the actual accuracy data of the target workpiece is obtained through image acquisition equipment to obtain the real-time accuracy item. Acquire initial data of the oilstone, including oscillation frequency and feed rate, to obtain initial information items. Based on the difference between the real-time accuracy item and the processing requirements, create a first correlation model based on the initial information. The first correlation model outputs correlation data between different initial data and processing surface accuracy data. Based on the processing requirements as input, perform preliminary adjustment on the initial information items through the first correlation model to obtain initial adjustment items. Based on the initial adjustment term, the updated information of vibration, pressure and temperature information terms is obtained. The initial information terms are then adjusted a second time using the adjustment method, thereby realizing the oilstone drive control based on the dynamic parameter identification of the combination of vibration data, temperature data and pressure data.

2. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The first sensing device is a vibration sensing device, and the method for acquiring vibration information items includes: Obtain information on the motion axis components of the target vertical ultraprecision machine, including the oilstone supply guide rail, lead screw, and C-axis, and obtain the installation information items; Based on the installation information items, an interval value is set. The interval value is a fixed value. The installation information items are divided into regions based on the interval value to obtain at least three region division items. Vibration sensing devices are arranged according to the region division items to obtain vibration data and obtain a vibration dataset. The average vibration information of the vibration dataset is obtained, and then the vibration information item is obtained.

3. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The second sensing device is a flexible multimodal sensing patch, and the methods for acquiring pressure and temperature information items include: Obtain oilstone working scene information, including workpiece contact area and oscillation area. Divide the oilstone working scene information into regions based on workpiece contact area and oscillation area to obtain first region and second region. Based on the first region and the second region, flexible sensing patches are attached respectively. The flexible sensing patches integrate a microcavity pressure sensor and a thin-film thermocouple sensor to obtain installation information items. Based on the installation information items, pressure data and temperature data are obtained, resulting in pressure information items and temperature information items.

4. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The methods for obtaining the processing requirements include: Acquire the target workpiece machining data, including machining drawings; perform information scanning based on the machining data to obtain precision annotation data and obtain annotation information items; Based on the labeled information items, processing parameter instructions are generated. These processing parameter instructions are then used as input to the target vertical ultraprecision machine to obtain output data, thereby obtaining the processing requirements.

5. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The image acquisition device includes a non-contact detection probe, and the method for obtaining the real-time accuracy item includes: The non-contact detection probe includes a confocal microscopic probe assembly with red-blue-ultraviolet three-bands, which is used to penetrate oil mist to obtain nanoscale three-dimensional morphology and acquire processing images. Based on the processing images, placement points are set, which are integrated on the side of the oilstone. The non-contact probe is installed based on the placement points to obtain the probe installation item. Based on the probe installation item, a scanning threshold is set, which is a fixed time value. The processing surface is scanned based on the scanning threshold, a 3D point cloud map is reconstructed, and the roughness information is calculated in real time to obtain the real-time accuracy item.

6. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The method for creating the first association model includes: Based on the initial information item, the physical relationship between the initial information item and the real-time accuracy item is extracted to obtain the first extraction item; Design a physical information neural network, using initial information terms as the input layer, LSTM to process time-series data as the hidden layer, real-time accuracy terms as the output layer, and the first extracted terms as training data for model training. Output the correlation data between oscillation frequency and feed rate and real-time accuracy terms, and then obtain the first correlation model.

7. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 1, characterized in that: The method for obtaining the initial adjustment term includes: Based on the first association model, with processing requirements as input, and based on the model output, the information combination of the initial information items is obtained to obtain the combined information set; Combined damage data, including oscillation frequency damage and feed rate damage, is obtained based on the combined information set. Damage is sorted based on the combined damage data to obtain damage sorting terms. Based on the damage sorting terms, the combination corresponding to the lowest damage is used as the benchmark adjustment combination to obtain the initial adjustment term.

8. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 7, characterized in that: The adjustment method includes: Based on the damage ranking term, a damage range is set, which is a fixed range value. Based on the combination result of the damage range and the lowest damage, the damage fluctuation term is obtained. The combination corresponding to the damage fluctuation term is obtained as the secondary adjustment combination. The secondary adjustment combination is used as the adjustment pattern. The update information of vibration information, pressure information and temperature information is obtained respectively. The fluctuation range of the update information is obtained. The combination with the lowest comprehensive fluctuation range is obtained as the adaptation adjustment combination. Then, the initial information term is adjusted in a secondary manner.

9. The intelligent servo control method for a vertical ultraprecision machine based on dynamic parameter identification according to claim 8, characterized in that: The adjustment method further includes: Based on the vibration information item, pressure information item, and temperature information item, respectively set the benchmark weights. Based on the combination result of the fluctuation range of the benchmark weights and the update information, the weight combination item is obtained. The lowest combination among the weight combination items is taken as the update adaptation adjustment combination, and the initial information item is adjusted a second time.

Images