CN-122016159-A - Balance adjustment method and system for balance weight of main spindle box of machine tool

CN122016159ACN 122016159 ACN122016159 ACN 122016159ACN-122016159-A

Abstract

The application provides a balance adjustment method and a balance adjustment system for a main shaft box of a machine tool, which belong to the technical field of machining, and comprise the steps of collecting sensor data and image data of the main shaft box of the machine tool; the method comprises the steps of determining a first unbalance position based on image data, determining a first unbalance amount based on sensor data, fusing the sensor data and the image data to obtain fused data, inputting a pre-trained neural network model to obtain a second unbalance position and a second unbalance amount, taking the position, which is overlapped with the first unbalance position and the second unbalance position, as a target unbalance position, calculating an unbalance value of the first unbalance amount and the second unbalance amount corresponding to the target unbalance position, taking a mean value of the first unbalance amount and the second unbalance amount, which corresponds to the unbalance value smaller than a preset first threshold value, as a target unbalance amount, and driving a balance weight adjusting device to adjust based on the target unbalance amount and the target unbalance position. The application ensures the running stability of the main shaft box of the machine tool.

Inventors

WU XINGFEI
DENG GUANGYA
LV GUIFANG
Deng Juehua
Wu Daohan
ZHAO YONGMIN
TANG SHENGFU

Assignees

北京博鲁斯潘精密机床有限公司

Dates

Publication Date: 20260512
Application Date: 20260206

Claims (10)

1. The balance adjustment method for the balance weight of the main shaft box of the machine tool is characterized by comprising the following steps of: acquiring sensor data and image data of the running state of a main spindle box of the machine tool through a camera and a sensor; determining a first imbalance position based on the image data and determining a first imbalance amount based on the sensor data; fusing the sensor data with the image data to obtain fused data; inputting the fusion data into a pre-trained neural network model to obtain a second unbalance position and a second unbalance amount; Taking the position where the first unbalanced position coincides with the second unbalanced position as a target unbalanced position; Calculating a difference value between a first unbalance amount and a second unbalance amount corresponding to the target unbalance position to obtain an unbalance amount difference value; taking the average value of the first unbalance amount and the second unbalance amount corresponding to the unbalance amount difference value smaller than a preset first threshold value as a target unbalance amount; driving a counterweight adjustment device to adjust based on the target unbalance amount and the target unbalance position; and acquiring the regulated sensor data and the regulated image data to verify the regulation effect.
2. The method of claim 1, wherein determining a first imbalance position based on the image data and determining a first imbalance amount based on the sensor data comprises: performing time sequence analysis on the image data, and extracting image displacement amounts of the machine tool spindle box relative to a static reference frame at a plurality of characteristic running moments; Fitting and generating a swinging track of the machine tool spindle box in a three-dimensional space according to the image displacement amounts of the plurality of characteristic running moments; Calculating the first unbalanced position based on the amplitude phase information of the swing track; and carrying out spectrum analysis and amplitude calculation on the sensor data, and calculating and determining the first unbalance amount corresponding to the first unbalance position based on a preset unbalance amount mapping model.
3. The method for adjusting balance of a machine tool headstock counterweight according to claim 2, wherein the fitting to generate a swing track of the machine tool headstock in a three-dimensional space according to the image displacement amounts of the plurality of feature operation moments includes: Acquiring vibration sensor data corresponding to the characteristic operation moments; correlating the image displacement quantity of each characteristic operation moment with the amplitude of the vibration sensor corresponding to the characteristic operation moment to obtain correlated image displacement quantity; Converting the associated image displacement into three-dimensional space displacement based on a preset calibration coefficient; And generating a swing track in the three-dimensional space through a space curve interpolation algorithm based on the three-dimensional space displacement and the phase information in the vibration sensor data.
4. The method for adjusting balance of a headstock weight of a machine tool according to claim 3, wherein the generating a swing trajectory in the three-dimensional space by a space curve interpolation algorithm based on the three-dimensional space displacement amount and phase information in the vibration sensor data comprises: Determining time sequence distribution of the characteristic operation moments in a spindle rotation period according to the phase information in the vibration sensor data; fitting the three-dimensional space displacement by adopting a non-uniform rational B spline curve interpolation algorithm based on the time sequence distribution, wherein the weight of curve control points is adjusted according to the vibration energy at the corresponding moment; In the interpolation process of the non-uniform rational B spline curve interpolation algorithm, constraint optimization is carried out on curvature continuity of a track curve generated by fitting on the basis of the known geometric structure and kinematic constraint of the machine tool spindle box as an optimization condition, so that the swing track is generated.
5. The method according to claim 2, wherein after the calculating the first unbalance position based on the amplitude phase information of the swing locus, the method further comprises: Acquiring the spindle rotating speed and processing load information of a current machine tool; Inquiring a pre-established machine tool working condition-rigidity mapping relation table according to the spindle rotating speed and the processing load information, and determining the equivalent dynamic rigidity of a machine tool spindle box suspension system under the current working condition; And carrying out rigidity compensation correction on the first unbalanced position according to the equivalent dynamic rigidity to obtain the corrected first unbalanced position.
6. The method for adjusting the balance weight of a headstock of a machine tool according to claim 1, wherein driving the balance weight adjusting device based on the target unbalance amount and the target unbalance position to adjust the balance weight comprises: Converting the target imbalance position to a target phase angle on a counterweight disc; Calculating the required target counterweight mass according to the target unbalance amount and the preset counterweight unit mass; if the counterweight adjusting device is a movable counterweight, calculating the target radial displacement of the counterweight on the counterweight disc radial guide rail according to the target unbalance and the counterweight mass; generating a counterweight adjustment drive command according to the target phase angle and the target counterweight mass or the target radial displacement; and controlling the servo driving unit to drive the balancing weight to move to the target phase angle and the corresponding target radial position based on the driving instruction.
7. The method for adjusting the balance weight of a headstock of a machine tool according to claim 6, further comprising: in the driving process, obtaining feedback data of current and torque of the servo driving unit; Comparing the feedback data with an expected current torque value calculated based on the target counterweight mass, the moving acceleration and a mechanism friction model to obtain a comparison difference value; and if the comparison difference value is larger than a preset safety tolerance, stopping driving and triggering and adjusting fault diagnosis and alarm processes.
8. The method for adjusting balance of a headstock weight of a machine tool according to claim 7, wherein the comparing the feedback data with an expected current torque value calculated based on the target weight mass, the moving acceleration and a mechanism friction model, after obtaining a comparison difference, further comprises: if the comparison difference is not greater than the preset safety margin but is continuously greater than a preset early warning threshold, correcting the friction coefficient in the mechanism friction model based on the feedback data to obtain a corrected mechanism friction model; Calculating an expected current torque value again by using the corrected mechanism friction model to obtain a target expected current torque value; and adjusting the driving parameters of the servo driving unit based on the target expected current torque value until the comparison difference value is smaller than the early warning threshold value.
9. The method according to claim 7, wherein after controlling the servo driving unit to drive the balancing weight to move to the target phase angle and the corresponding target radial position based on the driving command, further comprises: Collecting a local image of the balancing weight after being in place through the camera; Identifying the actual contour center position of the balancing weight in the partial image, and comparing the actual contour center position with the theoretical contour center position calculated based on the target phase angle and the target radial displacement; If the deviation between the actual contour center position and the theoretical contour center position is larger than a preset installation tolerance, generating a position compensation instruction; and controlling the servo driving unit to adjust according to the position compensation instruction until the deviation between the actual contour center position and the theoretical contour center position is smaller than a preset installation tolerance.
10. A balance adjustment system for a headstock weight of a machine tool, comprising: the data acquisition module is used for acquiring sensor data and image data of the running state of the main spindle box of the machine tool through a camera and a sensor; A preliminary analysis module for determining a first imbalance location based on the image data and a first imbalance amount based on the sensor data; The data fusion module is used for fusing the sensor data with the image data to obtain fusion data; The intelligent recognition module is used for inputting the fusion data into a pre-trained neural network model to obtain a second unbalance position and a second unbalance amount; A position determination module configured to set a position where the first unbalanced position coincides with the second unbalanced position as a target unbalanced position; the difference value calculation module is used for calculating the difference value between the first unbalance amount and the second unbalance amount corresponding to the target unbalance position to obtain an unbalance amount difference value; the unbalance amount determining module is used for taking the average value of the first unbalance amount and the second unbalance amount corresponding to the unbalance amount difference value smaller than a preset first threshold value as a target unbalance amount; the control execution module is used for driving the counterweight adjusting device to adjust based on the target unbalance amount and the target unbalance position; And the effect verification module is used for collecting the regulated sensor data and the regulated image data to verify the regulating effect.

Description

Balance adjustment method and system for balance weight of main spindle box of machine tool Technical Field The application relates to the technical field of machining, in particular to a balance adjustment method and system for a main shaft box counterweight of a machine tool. Background In the rotating process of the main spindle box of the machine tool, the unbalanced vibration is caused by the uneven mass distribution easily caused by factors such as manufacturing errors, assembly deviation, long-term running abrasion, load change and the like of parts. The control device is composed of a mechanical structure for driving the balance of the main shaft box balance weight and a balance weight adjusting method for controlling the mechanical structure. The existing balance weight adjusting method is low in efficiency and cannot meet the real-time adjusting requirement of a high-speed processing scene due to the fact that the existing balance weight adjusting method is partially dependent on a manual detection method, vibration data are collected by a single sensor, unbalance amount can be estimated only, unbalance positions are difficult to position, the balance weight is easy to interfere with the environment, and the balance weight adjusting method is not suitable for the real-time adjusting requirement of the high-speed processing scene. Therefore, a method and a system for balancing and adjusting the balance of a spindle box of a machine tool are needed. Disclosure of Invention In order to solve the technical problems, the application provides a balance adjustment method and a balance adjustment system for a main spindle box of a machine tool. In a first aspect of an embodiment of the present application, a method for adjusting balance of a spindle box of a machine tool is provided, including: acquiring sensor data and image data of the running state of a main spindle box of the machine tool through a camera and a sensor; determining a first imbalance position based on the image data and determining a first imbalance amount based on the sensor data; fusing the sensor data with the image data to obtain fused data; inputting the fusion data into a pre-trained neural network model to obtain a second unbalance position and a second unbalance amount; Taking the position where the first unbalanced position coincides with the second unbalanced position as a target unbalanced position; Calculating a difference value between a first unbalance amount and a second unbalance amount corresponding to the target unbalance position to obtain an unbalance amount difference value; taking the average value of the first unbalance amount and the second unbalance amount corresponding to the unbalance amount difference value smaller than a preset first threshold value as a target unbalance amount; and driving a counterweight adjusting device to adjust based on the target unbalance amount and the target unbalance position, and collecting the adjusted sensor data and image data to verify the adjusting effect. In a second aspect of the embodiment of the present application, there is provided a balance adjustment system for a spindle box of a machine tool, including: the data acquisition module is used for acquiring sensor data and image data of the running state of the main spindle box of the machine tool through a camera and a sensor; A preliminary analysis module for determining a first imbalance location based on the image data and a first imbalance amount based on the sensor data; The data fusion module is used for fusing the sensor data with the image data to obtain fusion data; The intelligent recognition module is used for inputting the fusion data into a pre-trained neural network model to obtain a second unbalance position and a second unbalance amount; A position determination module configured to set a position where the first unbalanced position coincides with the second unbalanced position as a target unbalanced position; the difference value calculation module is used for calculating the difference value between the first unbalance amount and the second unbalance amount corresponding to the target unbalance position to obtain an unbalance amount difference value; the unbalance amount determining module is used for taking the average value of the first unbalance amount and the second unbalance amount corresponding to the unbalance amount difference value smaller than a preset first threshold value as a target unbalance amount; the control execution module is used for driving the counterweight adjusting device to adjust based on the target unbalance amount and the target unbalance position; And the effect verification module is used for collecting the regulated sensor data and the regulated image data to verify the regulating effect. In a third aspect of the embodiment of the present application, there is provided an electronic device including a memory, a processor, and a computer program stored in the memory and run