A positioning method and system for part machining

Abstract

The application relates to the technical field of positioning methods, in particular to a positioning method and system for part machining, which comprises the following steps: acquiring a part image of a part to be machined and position parameters of a positioning feature on the part to be machined; constructing a kinematics prediction model based on the position parameters of the positioning feature, obtaining a velocity vector of the positioning feature at the next moment, and obtaining a predicted position of the positioning feature at the next moment based on the velocity vector; determining an adaptive search domain at the next moment based on the change degree of the motion state of the positioning feature; and performing local Hough transformation on the part image collected at the current moment within the adaptive search domain range to obtain the current position parameters of the positioning feature; the application realizes high-frequency and low-delay tracking of the part pose in the machining process, and improves the accuracy and response speed of dynamic compensation.

Description

Technical Field

[0001] This invention relates to the field of positioning methods, and in particular to a positioning method and system for parts processing. Background Technology

[0002] In manufacturing fields such as CNC machining and laser welding, to ensure the dimensional accuracy and surface quality of the final product, it is necessary to monitor and dynamically compensate for the actual position of the parts in real time during the machining process. Parts are affected by various factors such as cutting forces and thermal stress during machining, resulting in minute displacements and changes in posture. Without compensation, these changes will directly cause the machining trajectory to deviate from the theoretical path, leading to out-of-tolerance precision.

[0003] Machine vision-based localization technology is key to achieving dynamic compensation. Among these technologies, the Hough Transform, a classic geometric feature detection algorithm, is used for part localization because it can reliably identify key geometric features such as reference holes and reference edges from complex images. The Hough Transform determines the parameters of geometric features, such as the center coordinates and radius of a circle, by mapping edge points in image space to a parameter space and then searching for accumulated peaks in the parameter space.

[0004] However, the traditional Hough transform has a limitation when applied to dynamic compensation in processing. To ensure detection accuracy, the standard Hough transform requires a global, indiscriminate search and voting across the entire preset parameter space for each frame of the acquired image. For example, when detecting a radius of... When creating a circular hole, it needs to be within the width of the entire image. ,high The calculations are performed within a three-dimensional parameter space comprising possible radius ranges. This global search strategy incurs significant computational overhead. In dynamic compensation scenarios, the response frequency of the compensation system is required to reach tens or even hundreds of hertz, leaving only milliseconds for processing a single frame of image. The traditional Hough transform has a large computational delay, which cannot meet real-time requirements, resulting in poor stability in part processing. Summary of the Invention

[0005] To address the technical problem that existing Hough transforms, due to their large computational load caused by global search, cannot meet the dynamic compensation requirements of the machining process, this invention provides a positioning method and system for part machining.

[0006] In a first aspect, the present invention provides a positioning method for machining parts, which adopts the following technical solution:

[0007] Acquire the part image of the part to be processed and the position parameters of the positioning features on the part; based on the position parameters of the positioning features, construct a kinematic prediction model to obtain the velocity vector of the positioning features at the next moment, and obtain the predicted position of the positioning features at the next moment based on the velocity vector; determine the adaptive search domain at the next moment based on the degree of change of the motion state of the positioning features; within the adaptive search domain, perform a local Hough transform on the part image acquired at the current moment to obtain the current position parameters of the positioning features.

[0008] The method for determining the adaptive search domain is as follows: calculate the motion acceleration factor at the current moment, which represents the motion change state of the part to be processed; calculate the disturbance factor at the current moment, which is positively correlated with the motion acceleration factor; use the disturbance factor to adjust the preset search boundary to obtain the disturbance boundary; and obtain the adaptive search domain based on the predicted position of the positioning features and the disturbance boundary.

[0009] Compared to existing technologies that require a global Hough transform search for each frame of image, resulting in massive computational load and poor real-time performance, this invention constructs a dynamic prediction model based on kinematic constraints and generates a dynamically adaptive search domain. Then, it performs a local Hough transform within this small search domain, reducing the search space and computational overhead, and improving the running speed of the positioning algorithm. This enables it to meet the high-frequency real-time dynamic compensation requirements of tens or even hundreds of hertz during the processing, thereby effectively improving the stability and final accuracy of part processing.

[0010] Preferably, the positioning method further includes: acquiring the vibration signal of the fixture of the part to be processed, further obtaining the vibration amplitude at each moment, calculating the rate of change of the vibration amplitude based on the vibration amplitude at each moment, and normalizing the rate of change using a linear normalization method.

[0011] By additionally acquiring and analyzing the vibration signals of the part's mounting base, a direct data source for external physical impacts is provided, in addition to image information. Compared to inferring motion state indirectly through image displacement alone, introducing vibration signal analysis can directly and sensitively perceive sudden disturbances caused by cutting forces, equipment vibrations, etc., providing key physical evidence for more accurate assessment of part motion trends and uncertainties, thereby improving the accuracy and robustness of the prediction model.

[0012] Preferably, the velocity vector of the localization feature at the next moment is calculated, and the expression is:

[0013] ;

[0014] In the formula, For the next moment of prediction The velocity vector, This represents the preset motion trend damping factor. It's time. Historical average speed to date For a moment The instantaneous velocity vector.

[0015] The current instantaneous velocity and the historical average velocity are weighted by a damping factor. Compared to simply using instantaneous velocity for linear extrapolation, this method introduces a smoothing mechanism, which can effectively suppress drastic fluctuations in predicted values ​​caused by single-frame measurement errors or brief jumps. This allows the velocity prediction results to respond to current changes while also taking into account the stability of historical motion trends, thus obtaining a smoother and more reliable predicted position.

[0016] The preferred method for calculating the motion trend damping factor is as follows:

[0017]

[0018] In the formula, Indicates the damping factor of motion trend. Represents the normalized time. The rate of change of the vibration amplitude of the vibration signal and It is a moment The location feature coordinates, and It is a moment The location feature coordinates, This represents the activation function. It is a local minimum.

[0019] This allows the damping factor to adaptively adjust based on vibration signals and displacement changes. When vibration is severe and displacement is large (such as during an impact), the weight of the current instantaneous velocity is increased for a rapid response; when the motion is smooth, it relies more on the historical average velocity to maintain stability. Compared to using a fixed damping factor, this adaptive adjustment mechanism enables the prediction model to combine the agility of impact response with the stability of smooth operation, making it adaptable to different processing conditions.

[0020] Preferably, the expression for the motion acceleration factor is:

[0021]

[0022] in, For a moment The motion acceleration factor, Denotes the Euclidean norm. It's time. Historical average speed to date For a moment The instantaneous velocity vector, where tanh represents the hyperbolic tangent function.

[0023] By calculating the difference between the current velocity vector and the historical average velocity vector, the drastic degree of change in the part's motion state is quantified. This provides a crucial, calculable input parameter for subsequent dynamic adjustment of the adaptive search domain size, ensuring that the search domain adjustment is based not on empirical estimation, but on a precise quantification of changes in motion trends.

[0024] Preferably, the method for calculating the disturbance factor is as follows: starting from the current moment, obtain the rate of change of vibration amplitude of vibration signal at multiple moments along the historical direction, construct a rate of change sequence using the rate of change, calculate the percentile rank of the rate of change at the current moment in the rate of change sequence, and use the product of the motion acceleration factor at the current moment and the percentile rank as the disturbance factor.

[0025] The significance of the disturbance was assessed by considering the current rate of change of vibration and calculating its percentile rank in the historical sequence. Compared with directly using the vibration amplitude, this approach can better determine whether the current disturbance is within the normal fluctuation range or an anomalous shock, thus more accurately assessing the degree of external influence and providing a more reliable basis for generating more reasonable disturbance boundaries.

[0026] Preferred, perturbation boundary The expression is:

[0027]

[0028] in, This is for predicting the time. The set perturbation boundary, These represent the maximum and minimum values ​​of the preset search boundaries, respectively. Indicates time The disturbance factor.

[0029] Linear interpolation is performed between preset maximum and minimum boundary values ​​based on the disturbance factor. This transforms the abstract disturbance factor into a specific pixel-level search range, directly enabling the search area to dynamically scale with the stability of the part's movement. When machining is smooth, the search domain shrinks to improve efficiency; when disturbances occur, the search domain expands to ensure the target is not lost, achieving a balance between computational efficiency and tracking robustness.

[0030] Preferably, the method for obtaining the position parameters of the positioning features on the part to be processed is as follows:

[0031] At the initial moment of part processing, the first frame of part image is acquired, and a global Hough transform is performed on the part image to obtain the position parameters of the localization features.

[0032] Preferably, the localization method further includes: at the next moment, acquiring a new part image and performing edge detection, performing Hough transform within the adaptive search domain, finding the accumulator peak, and obtaining the localization result of the localization feature at the next moment.

[0033] Secondly, the present invention provides a positioning system for machining parts, which adopts the following technical solution:

[0034] A positioning system for machining parts includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a positioning method for machining parts as described above is implemented.

[0035] A computer program is generated using the aforementioned part machining positioning method and stored in a memory for loading and execution by a processor. Thus, a system is created based on the memory and processor for convenient use.

[0036] The present invention has the following technical effects:

[0037] This invention solves the problems of high computational cost and poor real-time performance of traditional Hough transform global search. Instead of relying on global search, this method constructs a kinematic prediction model and integrates motion acceleration from image analysis with vibration information monitored by sensors to adaptively generate a compact and dynamically changing adaptive search domain. Subsequently, local Hough transforms are performed only within this small domain, thereby greatly reducing computational complexity and achieving high-frequency, low-latency tracking of part pose during processing, improving the accuracy and response speed of dynamic compensation. Attached Figure Description

[0038] Figure 1 This is a flowchart of a positioning method for part processing according to the present invention. Detailed Implementation

[0039] 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, not all, of the embodiments of the present invention. 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.

[0040] This invention discloses a positioning method for machining parts, referring to... Figure 1 The process includes the following steps, as detailed below:

[0041] S1: Obtain the part image of the part to be processed.

[0042] At the initial moment of machining the parts Acquire the first frame of the part image. Since there is no prior information about the part's position at this time, a standard global Hough transformation is first performed to obtain the initial parameters of the positioning features, such as the center coordinates and radius of the reference hole.

[0043] First, the Canny operator is used to process the image. Perform edge detection to obtain an edge point set. Then, in the preset global parameter space The Hough transform is performed internally, and the size of the global parameter space is determined by the full size of the image (width). ,high The radius range is determined by the part specifications. , This is confirmed to be existing technology; the specific steps will not be elaborated further. Through... By searching for the peak value of the accumulator, the center coordinates of the reference circular hole at the initial time can be obtained. and radius .

[0044] S2: Construct a dynamic prediction model based on kinematic constraints.

[0045] Within the high-frequency sampling interval required for dynamic compensation (e.g., 10 milliseconds), the changes in the motion state (displacement and velocity) of the part due to physical inertia are continuous and finite. Firstly, from two consecutive frames... and Location results and In the middle, calculate the current time. instantaneous velocity vector :

[0046]

[0047] in, For a moment The instantaneous velocity vector, and It is a moment The coordinates of the center of the circle, and It is a moment The coordinates of the center of the circle, This is the time interval for image acquisition. Instantaneous velocity vector. The motion state of the part in the latest time step is quantified.

[0048] Vibration and impact occur during the machining process of parts, and the speed of the parts' movement cannot be constant. Therefore, a motion tendency damping factor is introduced. To smooth velocity prediction and reflect the damping effect, the motion trend damping factor is combined with instantaneous velocity. and historical average speed This results in a more robust prediction speed. The expression is:

[0049]

[0050] In the formula, For the next moment of prediction The velocity vector, This represents the damping factor for motion trends, with values ​​between 0 and 1. It's time. Historical average speed to date For a moment The instantaneous velocity vector.

[0051] The calculation method for the motion trend damping factor is as follows: The vibration signal of the fixed seat of the part to be processed is obtained, and the vibration amplitude at each moment is further obtained. The rate of change of the vibration amplitude is calculated based on the vibration amplitude at each moment, and the rate of change is normalized using a linear normalization method. The expression for the motion trend damping factor is:

[0052]

[0053] In the formula, Indicates the damping factor of motion trend. Represents the normalized time. The rate of change of the vibration amplitude of the vibration signal and It is a moment The coordinates of the center of the circle, and It is a moment The coordinates of the center of the circle, This represents the activation function, used for normalization. To set a minimum value to prevent the denominator from being 0, for example: The value is 0.01.

[0054] When a workpiece is subjected to an impact, the impact force is reflected on the machine tool base, causing a change in the base's vibration amplitude. The rate of change of the vibration amplitude indicates the magnitude of the impact force; the larger the rate of change, the greater the impact force on the workpiece. This reflects the degree of impact a part is subjected to from external forces. A higher value indicates a greater impact from the external force. Therefore, when... When the value is large, at the current time Instantaneous changes for the next moment The velocity vector has a significant impact and is suitable for impact responses; when A smaller value indicates that the part is less affected by external forces at the current moment, and the historical average trend has less influence on the next moment. The velocity vector has a significant impact and is suitable for smooth drifting.

[0055] S3: Generate time-varying perturbation boundaries and dynamic adaptive search domains.

[0056] To define the range of uncertainty regarding the position at the next moment, a time-varying perturbation boundary needs to be constructed. This boundary is not a fixed tolerance, but rather positively correlated with the intensity of the part's movement. The more intense the movement, the greater the uncertainty, and the larger the search range should be. Therefore, it is first necessary to quantify the intensity of the movement.

[0057] The acceleration factor at the current moment is calculated using the following expression:

[0058]

[0059] in, For a moment The motion acceleration factor represents the degree of drastic change in motion state. Denotes the Euclidean norm. It's time. Historical average speed to date For a moment The instantaneous velocity vector, where tanh represents the hyperbolic tangent function, is used for normalization. The larger the value, the more drastic the change in the motion state of the part.

[0060] The perturbation factor at the current moment is calculated as follows: [Calculation method follows, but is not explicitly stated in the original text.] Starting from the historical data point, the rate of change of vibration amplitude of the vibration signal at n time points is obtained. A rate of change sequence is constructed using this rate of change, and the current time point is calculated. rate of change The percentile rank S in the rate of change sequence Percentile rank refers to the relative position of a value within a set of data. Specifically, the percentile rank of a particular data point is equal to the percentage of all values ​​smaller than that data point out of the total number of data points. This is existing technology, and the specific calculation method will not be elaborated here. If S( The larger the value of S, the more it indicates that the impact on the workpiece is ongoing or gradually increasing; if S( The smaller the value of S(), the more it indicates that the impact on the workpiece is attenuating; in other words, the smaller the value of S(), the less impact is on the workpiece. This indicates the degree of influence the part being processed is subject to external factors; a higher value indicates a greater influence, and vice versa. (The value represents the time interval between these parameters.) The product of the motion acceleration factor and the percentile rank is used as the disturbance factor, which comprehensively reflects the motion change state of the part.

[0061] Construct time-varying perturbation boundaries based on perturbation factors. The expression is:

[0062]

[0063] in, This is for predicting the time. The set perturbation boundary (unit: pixels). These represent the maximum and minimum values ​​of the preset search boundaries, respectively. Indicates time The disturbance factor.

[0064] When the processing is stable and less affected by external factors As it approaches 0, the perturbation boundary shrinks to its minimum value. Nearby; when impact vibration occurs As the perturbation increases, the perturbation boundary expands to ensure that the subsequent adaptive search domain can cover the true location of the reference circular hole.

[0065] Finally, based on the prediction speed Predicting the next moment Center position of the reference hole : It is understandable The coordinates are: ( , ); then, with Centered on, with Define the Hough transform dynamic adaptive search domain for the next time step as the radius. The search domain is a very small parametric subspace, whose center coordinates (X, Y) range as follows:

[0066] ;

[0067] ;

[0068] in, , They represent the next moment. The x and y coordinates of the center position of the reference circular hole. This is for predicting the time. The defined perturbation boundary.

[0069] Because the radius changes very little during the processing, the search range for the radius can be fixed within a small interval. Inside, This indicates a preset fluctuation range, the size of which is manually set according to actual conditions. For example... The value is 5 pixels.

[0070] S4: Perform a local Hough transform within the dynamic search domain and update iteratively.

[0071] exist At any moment, capture a new frame of image. Edge detection is then performed. The dynamic adaptive search domain generated in step S3... Perform the Hough transform internally, because Its volume is much smaller than the global parameter space. Therefore, it can effectively reduce the amount of computation.

[0072] The accumulator peak found within the dynamic adaptive search domain is... Location results at any time and This result will be used as the basis for the next iteration (calculation). The input of the dynamic adaptive search domain at any given time is simultaneously sent to the CNC system of the machine tool for real-time calculation and compensation of the machining path.

[0073] This invention also discloses a positioning system for part processing, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a positioning method for part processing according to the present invention.

[0074] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0075] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A positioning method for machining parts, characterized in that, Including the following steps: Acquire the part image of the part to be processed and the position parameters of the positioning features on the part; based on the position parameters of the positioning features, construct a kinematic prediction model to obtain the velocity vector of the positioning features at the next moment, and obtain the predicted position of the positioning features at the next moment based on the velocity vector; determine the adaptive search domain at the next moment based on the degree of change of the motion state of the positioning features; within the adaptive search domain, perform a local Hough transform on the part image acquired at the current moment to obtain the current position parameters of the positioning features. The method for determining the adaptive search domain is as follows: calculate the motion acceleration factor at the current moment, which represents the motion change state of the part to be processed; calculate the disturbance factor at the current moment, which is positively correlated with the motion acceleration factor; use the disturbance factor to adjust the preset search boundary to obtain the disturbance boundary; and obtain the adaptive search domain based on the predicted position of the positioning features and the disturbance boundary. The positioning method also includes: acquiring the vibration signal of the fixed seat of the part to be processed, further obtaining the vibration amplitude at each moment, calculating the rate of change of the vibration amplitude based on the vibration amplitude at each moment, and normalizing the rate of change using a linear normalization method. The expression for the motion acceleration factor is: ； in, For a moment The motion acceleration factor, Denotes the Euclidean norm. It's time. Historical average speed to date For a moment The instantaneous velocity vector, where tanh represents the hyperbolic tangent function; The method for calculating the disturbance factor is as follows: Starting from the current moment, obtain the rate of change of vibration amplitude of the vibration signal at multiple moments along the historical direction. Construct a rate of change sequence using the rate of change, calculate the percentile rank of the rate of change at the current moment in the rate of change sequence, and use the product of the motion acceleration factor at the current moment and the percentile rank as the disturbance factor. The disturbance boundary... The expression is: ； in, This is for predicting the time. The set perturbation boundary, These represent the maximum and minimum values ​​of the preset search boundaries, respectively. Indicates time The disturbance factor.

2. The positioning method for machining parts according to claim 1, characterized in that, The velocity vector of the localization feature at the next moment is calculated using the following expression: ； In the formula, For the next moment of prediction The velocity vector, This represents the preset motion trend damping factor. It's time. Historical average speed to date For a moment The instantaneous velocity vector.

3. The positioning method for machining parts according to claim 2, characterized in that, The method for calculating the motion trend damping factor is as follows: ； In the formula, Indicates the damping factor of motion trend. Represents the normalized time. The rate of change of the vibration amplitude of the vibration signal and It is a moment The location feature coordinates, and It is a moment The location feature coordinates, This represents the activation function. It is a local minimum.

4. The positioning method for machining a part according to claim 1, characterized in that, The method for obtaining the position parameters of the positioning features on the part to be processed is as follows: At the initial moment of part processing, the first frame of part image is acquired, and a global Hough transform is performed on the part image to obtain the position parameters of the localization features.

5. The positioning method for machining parts according to claim 1, characterized in that, The localization method also includes: at the next time step, acquiring a new part image and performing edge detection, performing Hough transform within the adaptive search domain, finding the accumulator peak, and obtaining the localization result of the localization feature at the next time step.

6. A positioning system for machining parts, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a positioning method for machining a part according to any one of claims 1-5.

Images