Space parameter measuring system based on three-coordinate measuring machine

Abstract

The invention belongs to the technical field of three-coordinate measurement, and particularly discloses a space parameter measuring system based on a three-coordinate measuring machine, which comprises a measuring platform, a supporting arm, an X-axis driving module, a Y-axis driving module, a Z-axis driving module and a measuring assembly, and is characterized in that a motion controller is arranged at the top of a control box to control each driving module to move. A data acquisition module, a dynamic compensation module, a parameter fusion module and an execution control module are integrated in the box, the data acquisition module acquires multi-source and environmental parameters, the dynamic compensation module outputs a compensation instruction according to the parameters, the parameter fusion module outputs fusion point cloud coordinates, and the execution control module sends the instruction to a motion controller to drive three axes to move according to a preset path. According to the invention, a multi-module collaborative architecture is constructed, contact and non-contact measurement modes are combined, the problem of precision attenuation of a traditional three-coordinate measuring machine is solved, error dynamic correction is realized, and the measurement adaptability to high-precision workpieces is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of three - coordinate measurement, and particularly relates to a spatial parameter measurement system based on a three - coordinate measuring machine. Background Technique

[0002] As the core equipment in the field of precision measurement, a three - coordinate measuring machine realizes high - precision detection of spatial parameters such as the geometric dimensions and form - position tolerances of workpieces through the cooperation of motion systems in three orthogonal directions (X, Y, and Z) and measuring components. Traditional three - coordinate measuring machines mainly rely on contact probes or non - contact sensors to obtain point - cloud data, and achieve parameter measurement through coordinate system conversion and algorithm processing. However, with the development of the manufacturing industry towards high precision and complexity, higher requirements are put forward for the environmental adaptability and dynamic measurement accuracy of measuring equipment.

[0003] Existing three - coordinate measuring machines generally have the problem of lacking a dynamic error compensation mechanism during the measurement process. On the one hand, when the probe contacts the workpiece, the contact force, moving speed, and path changes of the probe will cause elastic deformation or mechanical vibration of the probe, resulting in coordinate acquisition deviation; on the other hand, fluctuations in environmental temperature will cause thermal expansion and contraction of mechanical structures such as the measurement platform and support arm, further amplifying the measurement error. In addition, the reliability of point - cloud data of non - contact scanning units in reflective surface and steep feature areas is insufficient, and existing systems fail to effectively fuse multi - source data for error correction, unable to meet the measurement requirements of high - precision workpieces such as aerospace and precision instruments. Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects existing in the prior art and provide a spatial parameter measurement system based on a three - coordinate measuring machine.

[0005] The present invention provides a spatial parameter measurement system based on a three - coordinate measuring machine, including a measurement platform arranged on the top of a control box and a support arm arranged on one side of the top of the control box. An X - axis drive module, a Y - axis drive module, and a Z - axis drive module are arranged on the top of the support arm, and a measurement component is arranged at the bottom of the Z - axis drive module; A motion controller is further arranged on the top of the control box. The motion controller is used to control the X - axis drive module to drive the Y - axis drive module to move in the X - axis direction; and control the Y - axis drive module to drive the Z - axis drive module to move in the Y - axis direction; and control the Z - axis drive module to drive the measurement component to move in the Z - axis direction; The interior of the control box is integrated with: A data acquisition module, which is used to acquire multi - source parameter information of the workpiece to be measured and environmental parameter information; A dynamic compensation module, which is connected to the data acquisition module and outputs a dynamic compensation instruction based on the multi - source parameter information and environmental parameter information; An execution control module, connected to the dynamic compensation module, sends the dynamic compensation instruction to the motion controller to control the X-axis drive module, Y-axis drive module, and Z-axis drive module to move along a preset path.

[0006] In a further solution, the measurement component includes a sliding frame arranged at the output end of the Z-axis drive module and slidably connected to the Z-axis drive module. A rotating motor is arranged inside the sliding frame, a probe is arranged at the output end of the rotating motor, a laser scanning module is arranged on one side of the probe, a connecting block is arranged at the bottom of the sliding frame, the probe penetrates through the connecting block, and binocular structured light cameras are arranged on both sides of the connecting block.

[0007] In a further solution, the data acquisition module includes a contact acquisition unit, a non-contact scanning unit, and an environmental parameter acquisition unit; The contact acquisition unit is a probe for obtaining the three-dimensional coordinates (X, Y, Z) of the probe, the probe speed (Vx, Vy, Vz), and the probe contact force Fz; The non-contact scanning unit is composed of a laser scanning module and a binocular structured light camera for obtaining the surface point cloud data of the workpiece to be measured; The environmental parameter acquisition unit includes a temperature sensor for collecting the environmental temperature T.

[0008] In a further solution, the dynamic compensation module includes: A multi-source data input unit for receiving in real time the three-dimensional coordinates (X, Y, Z) of the probe, the probe speed (Vx, Vy, Vz), the probe contact force Fz, and the environmental temperature T; An error prediction model, adopting a hybrid architecture of depthwise separable convolutional layers and gated recurrent units, where: The input is 8-channel time series data (Xr, Yr, Zr, Vx, Vy, Vz, Fz, T) composed of the three-dimensional coordinates (X, Y, Z) of the probe, the probe speed (Vx, Vy, Vz), the probe contact force Fz, and the environmental temperature T; The depthwise separable convolutional layer includes 8 independent 3×3 convolutional kernels to extract spatial features channel by channel, outputting an 8×N×N feature map. After extracting the spatial features, 1×1 pointwise convolution is used to fuse the channel information to generate an 8-channel feature map, where N is the size of the time window; The hidden layer dimension of the gated recurrent unit is 128. The 8-channel feature map generated by the depthwise separable convolutional layer is flattened into an 8×N×N-dimensional vector as the input, and the hidden state is output; A fully connected mapping layer is used to splice the global pooling result of the depthwise separable convolutional layer and the hidden state of the gated recurrent unit, and map and generate compensation parameters ΔR, (ΔX, ΔY, ΔZ); where ΔR is the probe radius compensation coefficient, and ΔX, ΔY, ΔZ are the coordinate offsets. A compensation instruction generation unit is used to convert the compensation parameters into analog signals recognizable by the motion controller through the FPGA acceleration unit. The compensation instruction generation unit is connected to the execution control module and is used to send the analog signals to the motion controller in real time.

[0009] Furthermore, the construction process of the error prediction model is as follows: Collect several groups of three-dimensional coordinates (X, Y, Z), velocities (Vx, Vy, Vz), probe contact force Fz, and ambient temperature T of the probe under different measurement conditions. Divide the continuous time series data according to the set time window size N to form an 8×N×N feature map; use high-precision measurement equipment to obtain the true measurement values, compare them with the collected data, obtain the true compensation parameters corresponding to each sample, and obtain the paired data samples of the feature map and the true compensation parameters through manual experts' marking. Input the paired data samples into the model and perform multiple iterative trainings to obtain an error prediction model with the three-dimensional coordinates (X, Y, Z), velocities (Vx, Vy, Vz), probe contact force Fz, and ambient temperature T of the probe as the input and the compensation parameters ΔR, (ΔX, ΔY, ΔZ) as the output.

[0010] Furthermore, a parameter fusion module is also integrated inside the control box and is connected to the data acquisition module for fusing multi-source parameter information to output the fused point cloud coordinates; the parameter fusion module includes: A multi-source data acquisition unit is configured to synchronously acquire laser scan point cloud data and probe contact point cloud data; the laser scan point cloud data includes three-dimensional coordinates (X1, Y1, Z1) and signal intensity; the probe contact point cloud data contains three-dimensional coordinates (X2, Y2, Z2). A data preprocessing unit is used to calculate the normal vectors of the laser point cloud data, obtain the normal vectors of each point, and calculate the signal-to-noise ratio of the laser point cloud; a dynamic weight allocation unit is configured as: The initial weight of the laser point cloud is set to W = 0.5. Adjust the laser point cloud weight W1 for the regions that meet the following conditions: Plane continuity region: when the included angle between the normal vectors of adjacent points < 5°, the laser point cloud weight W1 is multiplied by the gain factor α, where α = 1.2 ± 0.1. Reflective area: When the signal-to-noise ratio is less than the preset threshold, the weight W1 of the laser point cloud is multiplied by the attenuation factor β, and the weight of the probe point cloud is W2 = 1 - W1, where β = 0.5 ± 0.1; The point cloud fusion unit obtains the fused point cloud coordinates based on the dynamic weight distribution unit. The fused point cloud coordinates are (Xr, Yr, Zr), where: ; The point cloud fusion unit is connected to the error prediction model, and the fused point cloud coordinates (Xr, Yr, Zr) are input into the error prediction model to output compensation parameters ΔR, (ΔX, ΔY, ΔZ).

[0011] A further solution is that the measurement platform includes a support base provided on the top of the control box. A fixture fixing plate is provided on the top of the support base. A circular hole is formed on the fixture fixing plate to form a measurement area. A fixed clamping part and two sliding clamping parts are provided along the circumference of the measurement area on the fixture fixing plate. A first guide rail is provided at the bottom of the sliding clamping part, and the sliding clamping part is slidably connected to the first guide rail; A second guide rail is also provided on the fixture fixing plate, and the second guide rail is located between the two sliding clamping parts. A Y-shaped push rod is slidably provided on the second guide rail. A chute is provided in the middle of the sliding clamping part, and the Y-shaped push rod is slidably connected to the chute; A clamping cylinder is also provided on the fixture fixing plate, and the output end of the clamping cylinder is fixedly connected to the Y-shaped push rod.

[0012] A further solution is that the included angle between the two sliding clamping parts is 120°. One end of the Y-shaped push rod away from the clamping cylinder is two inclined rods with an included angle of 60°. The inclined rods are slidably connected to the chute, so that when the Y-shaped push rod slides along the second guide rail, the two inclined rods respectively drive the two sliding clamping parts to slide along the first guide rail.

[0013] A further solution is that the X-axis drive module and the Y-axis drive module have the same structure, both of which are screw drive mechanisms. The Z-axis drive module includes a Z-axis fixing plate slidably connected to the Y-axis drive module. A Z-axis guide rail is provided on one side of the Z-axis fixing plate. A sliding frame is provided on the Z-axis guide rail, and the sliding frame is slidably connected to the Z-axis guide rail; A Z-axis cylinder is provided on the top of the Z-axis fixing plate, and the output end of the Z-axis cylinder is fixedly connected to the sliding frame; A rotating motor is provided inside the sliding frame for driving the binocular structured light camera and the laser scanning module to rotate.

[0014] A further solution is that the control box is also connected to an external obstacle avoidance module; The obstacle avoidance module includes a workpiece model construction unit, a fixture model construction unit, a model superposition unit, and a boundary extraction unit; The workpiece model construction unit constructs a three-dimensional model of the workpiece to be measured based on the workpiece scanning point cloud of the non-contact scanning unit; The fixture model construction unit establishes a three-dimensional model of the fixture based on the fixture scanning point cloud of the non-contact scanning unit; The model superposition unit is used to superpose the three-dimensional model of the workpiece to be measured and the three-dimensional model of the fixture in the same coordinate system; The boundary extraction unit is used to traverse the three-dimensional models of the workpiece to be measured and the fixture and identify boundary points, connect the boundary points into a closed loop, and form an edge path of the overlapping area; The boundary extraction unit is connected to the execution control module, sends the edge path to the motion controller, and controls the X-axis drive module, Y-axis drive module, and Z-axis drive module to move along the edge path.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By constructing an integrated multi-module collaborative measurement system, the present invention solves the problem of accuracy attenuation of traditional coordinate measuring machines caused by working condition changes and environmental interference. Specifically, through the data acquisition module, multi-source parameters such as the three-dimensional coordinates of the probe, probe contact force, and environmental temperature are obtained in real time, a real-time compensation instruction is generated by the dynamic compensation module, combined with the high-precision point cloud data of the parameter fusion module, and finally the execution control module drives the three axes to move along the preset path to realize the dynamic correction of measurement errors. By combining the high-precision single-point measurement of the contact probe with the large-area rapid scanning of non-contact laser scanning and binocular structured light, the system can not only meet the sub-micron-level precision measurement of key features, but also efficiently complete the global scanning of complex surfaces, significantly improving the measurement adaptability to high-precision workpieces.

[0016] The dynamic compensation module of the present invention adopts a hybrid architecture of depthwise separable convolutional layers and gated recurrent units, performs spatio-temporal feature fusion on the 8-channel time-series data composed of the three-dimensional coordinates, speed, contact force, and environmental temperature of the probe, and outputs the probe radius compensation coefficient and coordinate offset in real time. Compared with traditional empirical formula compensation, this model is trained with a large amount of working condition data, can accurately capture non-linear error sources such as mechanical deformation and thermal drift, reduce the coordinate error caused by temperature changes, and meet the measurement requirements of aerospace components in a variable temperature environment.

[0017] The present invention uses the FPGA acceleration unit to realize the high-speed conversion of compensation parameters into analog signals, combined with the three-axis linkage control of the motion controller, reduces the dynamic positioning error of the system during high-speed measurement, and effectively solves the problem of trajectory deviation caused by compensation lag of traditional equipment.

[0018] The parameter fusion module of the present invention significantly improves the measurement blind area problem of complex surfaces by dynamically adjusting the weights of the laser point cloud and the probe contact point cloud. By using a temperature sensor to monitor the ambient temperature in real time and embedding an error prediction model, the system can automatically compensate for the displacement of the mechanical structure caused by thermal deformation without frequent manual calibration, significantly enhancing the stability of long-term continuous measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The following drawings are only schematic illustrations and explanations of the present invention and are not used to limit the scope of the present invention, where: Figure 1 : Schematic structural diagram of the present invention; Figure 2 : Schematic structural diagram of the three-axis drive structure of the present invention; Figure 3 : Figure 2 Enlarged view of part A in; Figure 4 : Schematic structural diagram of the measurement platform; Figure 5 : Schematic block diagram of the collaborative control principle of each module of the control box of the present invention; Figure 6 : Schematic connection diagram of the error budget model structure of the present invention; In the figure: 1, control box; 2, measurement platform; 3, X-axis drive module; 4, Y-axis drive module; 5, Z-axis drive module; 6, measurement component; 7, motion controller; 8, support base; 9, fixture fixing plate; 10, measurement area; 11, fixed clamping part; 12, first guide rail; 13, sliding clamping part; 14, Y-shaped push rod; 15, second guide rail; 16, clamping cylinder; 17, Z-axis fixing plate; 18, Z-axis guide rail; 19, sliding frame; 20, rotating motor; 21, Z-axis cylinder; 22, connecting block; 23, arc-shaped frame; 24, binocular structured light camera; 25, fixed tube; 26, laser scanning module; 27, probe; 28, data acquisition module; 29, dynamic compensation module; 30, execution control module; 31, parameter fusion module; 32, obstacle avoidance module; 33, multi-source data input unit; 34, error prediction model; 35, compensation instruction generation unit; 36, contact acquisition unit; 37, non-contact scanning unit; 38, environmental parameter acquisition unit; 39, multi-source data acquisition unit; 40, data preprocessing unit; 41, dynamic weight distribution unit; 42, point cloud fusion unit; 43, workpiece model construction unit; 44, fixture model construction unit; 45, model superposition unit; 46, boundary extraction unit; 47, depth convolution layer; 48, 3×3 convolution kernel; 49, pointwise convolution layer; 50, gated recurrent unit; 51, global average pooling layer; 52, splicing layer; 53, fully connected mapping layer. DETAILED DESCRIPTION OF THE INVENTION

[0020] In order to make the objectives, technical solutions, design methods, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] As Figure 1 and Figure 5 shown, the present invention provides a spatial parameter measurement system based on a coordinate measuring machine, which supports multi-source parameter synchronous acquisition and real-time compensation, and solves the problem of accuracy attenuation caused by environmental changes and mechanical errors in traditional equipment. It includes a measurement platform 2 provided on the top of the control box 1 and a support arm provided on one side of the top of the control box 1. An X-axis drive module 3, a Y-axis drive module 4, and a Z-axis drive module 5 are provided on the top of the support arm. A measurement component 6 is provided at the bottom of the Z-axis drive module 5; a motion controller 7 is also provided on the top of the control box 1. The motion controller 7 is used to control the X-axis drive module 3 to drive the Y-axis drive module 4 to move in the X-axis direction; and control the Y-axis drive module 4 to drive the Z-axis drive module 5 to move in the Y-axis direction; and control the Z-axis drive module 5 to drive the measurement component 6 to move in the Z-axis direction; integrated inside the control box 1 are: a data acquisition module 28, which is used to acquire multi-source parameter information of the workpiece to be measured and environmental parameter information; a dynamic compensation module 29, which is connected to the data acquisition module 28 and outputs a dynamic compensation instruction based on the multi-source parameter information and environmental parameter information; a parameter fusion module 31, which is connected to the data acquisition module 28 and is used to fuse the multi-source parameter information to output the fused point cloud coordinates; an execution control module 30, which is connected to the dynamic compensation module 29, sends the dynamic compensation instruction to the motion controller 7, and controls the X-axis drive module 3, the Y-axis drive module 4, and the Z-axis drive module 5 to move along a preset path.

[0022] As Figure 4As shown in the figure, in order to ensure the fixation of the workpiece to be measured, in this embodiment, the measurement platform 2 includes a support base 8 provided on the top of the control box 1. A fixture fixing plate 9 is provided on the top of the support base 8. A circular hole is formed on the fixture fixing plate 9 to form a measurement area 10 for the workpiece to be measured. A fixed clamping part 11 and two sliding clamping parts 13 are arranged along the circumferential side of the measurement area 10 on the fixture fixing plate 9. A first guide rail 12 is provided at the bottom of the sliding clamping part 13, and the sliding clamping part 13 is slidably connected to the first guide rail 12. A second guide rail 15 is further provided on the fixture fixing plate 9, and the second guide rail 15 is located between the two sliding clamping parts 13. A Y-shaped push rod 14 is slidably arranged on the second guide rail 15. A chute is provided in the middle of the sliding clamping part 13, and the Y-shaped push rod 14 is slidably connected to the chute. A clamping cylinder 16 is further provided on the fixture fixing plate 9, and the output end of the clamping cylinder 16 is fixedly connected to the Y-shaped push rod 14. Among them, the included angle between the two sliding clamping parts 13 is 120°, and the included angle between each sliding clamping part 13 and the fixed clamping part 11 is also 120°. One end of the above-mentioned Y-shaped push rod 14 away from the clamping cylinder 16 is two inclined rods with an included angle of 60°, and the inclined rods are slidably connected to the chute, so that when the Y-shaped push rod 14 slides along the second guide rail 15, the two inclined rods respectively drive the two sliding clamping parts 13 to slide along the first guide rail 12. The measurement platform 2 adopts a linkage design of the Y-shaped push rod 14 and the sliding clamping part 13, and realizes the rapid positioning and adaptive clamping of the workpiece through the drive of the clamping cylinder 16. The clamping force is evenly distributed, and the workpiece clamping efficiency is improved.

[0023] As Figure 2 shown, in this embodiment, the X-axis drive module 3 and the Y-axis drive module 4 have the same structure, and both are screw drive mechanisms. The Z-axis drive module 5 includes a Z-axis fixing plate 17 slidably connected to the Y-axis drive module 4. A Z-axis guide rail 18 is provided on one side of the Z-axis fixing plate 17. A sliding frame 19 is provided on the Z-axis guide rail 18, and the sliding frame 19 is slidably connected to the Z-axis guide rail 18. A Z-axis cylinder 21 is provided on the top of the Z-axis fixing plate 17, and the output end of the Z-axis cylinder 21 is fixedly connected to the sliding frame 19. A rotating motor 20 is provided inside the sliding frame 19. As Figure 3As shown in the figure, the above-mentioned measurement component 6 includes a sliding frame 19 arranged at the output end of the Z-axis driving module 5 and slidably connected to the Z-axis driving module 5. A rotating motor 20 is arranged inside the sliding frame 19. A probe 27 is arranged at the output end of the rotating motor 20. A fixed tube 25 is sleeved outside the probe 27. A laser scanning module 26 is arranged on the fixed tube 25. A connecting block 22 is arranged at the bottom of the sliding frame 19. The probe 27 penetrates through the connecting block 22, and arc-shaped frames 23 are arranged on both sides of the connecting block 22. A binocular structured light camera 24 is arranged on the arc-shaped frames 23. The rotating motor 20 drives the binocular structured light camera 24 and the laser scanning module 26 to rotate, and cooperates with the Z-axis cylinder 21 and the Z-axis guide rail 18 for coordinated control, realizing multi-angle adjustment of the binocular structured light camera 24 and the laser scanning module 26, expanding the detection range of the measurement component 6, and is especially suitable for non-contact scanning of complex structures such as deep holes and inner cavities.

[0024] In this embodiment, the data acquisition module 28 includes a contact acquisition unit 36, a non-contact scanning unit 37, and an environmental parameter acquisition unit 38; the contact acquisition unit 36 is the probe 27, which is used to obtain the three-dimensional coordinates (X, Y, Z) of the probe 27, the speed (Vx, Vy, Vz) of the probe 27, and the probe contact force Fz; among them, the probe contact force Fz is monitored in real time by a force-sensitive sensor, which is integrated inside the probe 27 and is used to sense the normal force when the probe 27 contacts the workpiece in real time; the non-contact scanning unit 37 is composed of the laser scanning module 26 and the binocular structured light camera 24, which is used to obtain the surface point cloud data of the workpiece to be measured; the environmental parameter acquisition unit 38 includes a temperature sensor, which is used to collect the environmental temperature T. Among them, the temperature sensor is arranged inside the control box 1 or near the measurement platform 2 to ensure real-time monitoring of the temperature change of the measurement environment and avoid the thermal expansion and contraction errors of the support arm, the driving module, and the probe 27 caused by temperature fluctuations. The comprehensive acquisition of the three-dimensional coordinates, speed, contact force, surface point cloud data, and environmental temperature of the workpiece is realized. This multi-source data synchronous acquisition mechanism provides rich input information for subsequent error compensation and point cloud fusion, solves the problem of information loss of traditional single-modal measurement equipment. The contact acquisition unit 36 can obtain high-precision single-point coordinates and contact force data, which is suitable for the precise measurement of key features; the non-contact scanning unit 37 can quickly obtain a large-area surface point cloud, which is suitable for the measurement of complex curved surfaces or easily damaged workpieces; the temperature sensor monitors the environmental temperature in real time, providing a basis for thermal deformation error compensation. The combination of the three enables the system to balance accuracy, efficiency, and adaptability and meet the measurement requirements under different working conditions.

[0025] In this embodiment, the dynamic compensation module 29 includes: a multi-source data input unit 33, an error prediction model 34, and a compensation instruction generation unit 35. Among them, the multi-source data input unit 33 is used to receive in real time the three-dimensional coordinates (X, Y, Z) of the probe 27, the speed (Vx, Vy, Vz) of the probe 27, the probe contact force Fz, and the ambient temperature T. The error prediction model 34 adopts a hybrid architecture of a depthwise separable convolutional layer and a gated recurrent unit 50, which can effectively extract the spatial features and temporal dependence features in the time series data. Specifically: the input is an 8-channel time series data (Xr, Yr, Zr, Vx, Vy, Vz, Fz, T) composed of the three-dimensional coordinates (X, Y, Z) of the probe 27, the speed (Vx, Vy, Vz) of the probe 27, the probe contact force Fz, and the ambient temperature T. The depthwise separable convolutional layer includes 8 independent 3×3 convolutional kernels 48 to extract spatial features channel by channel, output an 8×N×N feature map, and after extracting the spatial features, fuse the channel information through a 1×1 pointwise convolutional layer 49 to generate an 8-channel feature map, where N is the size of the time window. The hidden layer dimension of the gated recurrent unit is 128, and the 8-channel feature map generated by the depthwise separable convolutional layer is flattened into an 8×N×N-dimensional vector as the input, and the hidden state is output. A fully connected mapping layer 53 is used to splice the global pooling result of the depthwise separable convolutional layer and the hidden state of the gated recurrent unit, and map to generate compensation parameters ΔR, (ΔX, ΔY, ΔZ). Among them, ΔR is the radius compensation coefficient of the probe 27, and ΔX, ΔY, ΔZ are coordinate offsets. Through the input of 8-channel time series data (three-dimensional coordinates, three-dimensional speed, probe contact force, temperature), the model can output in real time the radius compensation coefficient ΔR of the probe 27 and the coordinate offsets (ΔX, ΔY, ΔZ), and perform dynamic compensation on the mechanical motion error, thermal deformation error, and deformation error of the probe 27 caused by the contact force, solving the problem of accuracy attenuation of traditional coordinate measuring machines due to environmental changes and working condition fluctuations. The compensation instruction generation unit 35 is used to convert the compensation parameters into an analog signal recognizable by the motion controller 7 through the FPGA acceleration unit. The compensation instruction generation unit 35 is connected to the execution control module 30 and is used to send the analog signal to the motion controller 7 in real time. In this process, the compensation parameters ΔR, (ΔX, ΔY, ΔZ) are the key data for compensating the errors generated during the measurement process of the coordinate measuring machine. The FPGA acceleration unit can quickly convert these digital compensation parameters into an analog signal recognizable by the motion controller 7. After receiving the analog signal, the motion controller 7 drives the motor according to the information carried by the signal, thereby controlling the X-axis drive module 3, the Y-axis drive module 4, and the Z-axis drive module 5 to move precisely to achieve the purpose of error compensation. Specifically, the motion controller 7 performs motion planning according to the parsed compensation parameters, combined with the current measurement task and the current positions of the three axes. Determine parameters such as the target position, moving speed, and acceleration of each axis to ensure that the three axes can accurately move to the compensated position.

[0026] The construction process of the error prediction model 34 is as follows: Under different measurement conditions, several groups of three-dimensional coordinates (X, Y, Z), velocities (Vx, Vy, Vz), probe contact force Fz, and ambient temperature T of the probe 27 are collected. The collected data is normalized and mapped to the interval [0, 1] or [-1, 1] to eliminate the influence of the dimension between different features and accelerate the convergence speed of the model; The continuous time series data is divided according to the set time window size N to form an 8×N×N feature map; where N is the time window. In this embodiment, N is 50, that is, the data of every 50 time points is used as a sample. Each sample contains data of 8 channels (X, Y, Z, Vx, Vy, Vz, Fz, T), and then an 8×N×N feature map is formed. A high-precision measurement device is used to obtain the true measurement value, which is compared with the collected data to obtain the true compensation parameter corresponding to each sample. The paired data samples of the feature map and the true compensation parameter are obtained through manual expert marking; The paired data samples are input into the model for multiple iterative trainings to obtain an error prediction model 34 with the three-dimensional coordinates (X, Y, Z), velocities (Vx, Vy, Vz), probe contact force Fz, and ambient temperature T of the probe 27 as the input and the compensation parameters ΔR, (ΔX, ΔY, ΔZ) as the output.

[0027] As Figure 6 shown, in the above, the depthwise separable convolution layer includes a depth convolution layer 47 and a pointwise convolution layer 49. Among them, the depth convolution layer 47 performs convolution operations on each channel of the input 8×N×N feature map using 8 independent 3×3 convolution kernels 48, and extracts spatial features channel by channel. For example, separately extract the spatial change features of temperature data, or the spatial change features of the X coordinate of the probe 27, etc. The output is still an 8×N×N feature map. The pointwise convolution layer 49 performs convolution operations on the feature map output by the depth convolution using a 1×1 convolution kernel to fuse the features of each channel and generate a new 8-channel feature map. The gated recurrent unit 50 flattens the 8-channel feature map output by the depthwise separable convolution layer into an 8×N×N-dimensional vector, which is used as the input of the gated recurrent unit. The gated recurrent unit 50 outputs a 128-dimensional hidden state vector. The fully connected mapping layer 53: The feature map output by the depthwise separable convolution layer is globally average pooled 51 by the global average pooling layer to be compressed into an 8-dimensional vector, and then concatenated with the 128-dimensional hidden state vector output by the gated recurrent unit through the concatenation layer 52 to obtain a 136-dimensional vector. The concatenated 136-dimensional vector is input into the fully connected mapping layer 53, and is mapped to the 4-dimensional compensation parameters ΔR, (ΔX, ΔY, ΔZ) through a linear transformation.

[0028] Continue to refer to Figure 5 , the parameter fusion module 31 includes a multi-source data acquisition unit 39, a data preprocessing unit 40, a dynamic weight allocation unit 41, and a point cloud fusion unit 42; specifically, the multi-source data acquisition unit 39 is configured to synchronously acquire laser scan point cloud data and probe 27 contact point cloud data; the laser scan point cloud data includes three-dimensional coordinates (X1, Y1, Z1) and signal intensity; the probe 27 contact point cloud data contains three-dimensional coordinates (X2, Y2, Z2); the data preprocessing unit 40 is used to calculate the normal vector of the laser point cloud data, obtain the normal vector of each point, and calculate the signal-to-noise ratio of the laser point cloud; the dynamic weight allocation unit 41 is configured as follows: the initial weight of the laser point cloud is set to W = 0.5; for areas that meet the following conditions, adjust the laser point cloud weight W1: planar continuity area: when the included angle between adjacent point normal vectors < 5°, the laser point cloud weight W1 is multiplied by the gain factor α, where α = 1.2 ± 0.1; reflective area: signal-to-noise ratio ≤ 20dB, the laser point cloud weight W1 is multiplied by the attenuation factor β, and the probe 27 point cloud weight is W2 = 1 - W1, where β = 0.5 ± 0.1; for the planar continuity area (included angle between adjacent point normal vectors < 5°), the weight of the laser scan point cloud data is increased by the gain factor α because laser scanning has the characteristics of high efficiency and high precision in large-area plane measurement. For the reflective area (signal-to-noise ratio ≤ 20dB), the weight of the laser scan point cloud data is reduced by the attenuation factor β, and the weight of the probe 27 contact point cloud data is increased because the probe 27 contact measurement can provide more accurate measurement results in the reflective area; the point cloud fusion unit 42 obtains the fused point cloud coordinates according to the weighted average method, and the fused point cloud coordinates are (Xr, Yr, Zr), where .

[0029] The point cloud fusion unit 42 is connected to the error prediction model 34, and inputs the fused point cloud coordinates (Xr, Yr, Zr) into the error prediction model 34 to output compensation parameters ΔR, (ΔX, ΔY, ΔZ). By fusing the coordinates, the accuracy of the compensation parameters ΔR, (ΔX, ΔY, ΔZ) is further improved.

[0030] In this embodiment, the control box 1 is further connected to an external obstacle avoidance module 32; the obstacle avoidance module 32 includes a workpiece model construction unit 43, a fixture model construction unit 44, a model superposition unit 45, and a boundary extraction unit 46; among them, the workpiece model construction unit 43 constructs a three-dimensional model of the workpiece to be measured based on the workpiece scanning point cloud of the non-contact scanning unit 37. Specifically, when the non-contact scanning unit 37 scans the workpiece, the laser scanning module 26 emits a laser beam onto the workpiece surface, and obtains the depth information of the workpiece surface by measuring the time or phase difference of the laser reflected light. The binocular structured light camera 24 takes pictures of the structured light pattern on the workpiece surface from different angles with two cameras, and calculates the three-dimensional coordinates of the points on the workpiece surface through the triangulation principle; the fixture model construction unit 44 is similar to the workpiece model construction unit 43. The non-contact scanning unit 37 scans the fixture to obtain the point cloud coordinates of the fixture and then constructs a three-dimensional model of the fixture; the model superposition unit 45 is used to superpose the three-dimensional model of the workpiece to be measured and the three-dimensional model of the fixture in the same coordinate system. It is necessary to determine a unified global coordinate system, and transform the three-dimensional models of the workpiece and the fixture into this coordinate system. In this embodiment, by selecting a fixed reference point or reference plane, the coordinates of the two models can be transformed using a coordinate transformation matrix. In the unified coordinate system, the three-dimensional models of the workpiece and the fixture are superposed, and the coordinate data of the two models are merged into the same data structure for subsequent boundary extraction; the boundary extraction unit 46 is used to traverse the three-dimensional models of the workpiece to be measured and the fixture and identify the boundary points, connect the boundary points into a closed loop to form the edge path of the overlapping area. In this embodiment, the sixteen-neighborhood method is adopted to judge the boundary position of the model. For example, if there are a large number of points in the neighborhood of a point that do not belong to the same model, or the distance change from this point to its neighborhood points is large, then this point can be identified as a boundary point. When connecting the boundary points, start from a boundary point and sequentially find the nearest unconnected boundary point until a closed loop is formed; the boundary extraction unit 46 is connected to the execution control module 30, and sends the edge path to the motion controller 7 in the form of a digital signal to control the X-axis drive module 3, the Y-axis drive module 4, and the Z-axis drive module 5 to move along the edge path.

[0031] The various embodiments of the present invention have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other ordinary skill in the art in the technical field to understand the disclosed embodiments.

Claims

1. A spatial parameter measurement system based on a coordinate measuring machine, characterized in that It includes a measurement platform arranged on the top of the control box and a support arm arranged on one side of the top of the control box. An X-axis drive module, a Y-axis drive module and a Z-axis drive module are arranged on the top of the support arm, and a measurement component is arranged at the bottom of the Z-axis drive module; A motion controller is also arranged on the top of the control box, and the motion controller is used to control the X-axis drive module to drive the Y-axis drive module to move in the X-axis direction; And control the Y-axis drive module to drive the Z-axis drive module to move in the Y-axis direction; and control the Z-axis drive module to drive the measurement component to move in the Z-axis direction; Inside the control box, there is integrated: A data acquisition module, which is used to acquire multi-source parameter information of the workpiece to be measured and environmental parameter information; A dynamic compensation module, connected to the data acquisition module, and based on the multi-source parameter information and environmental parameter information, outputs compensation parameters through an error prediction model and then generates a dynamic compensation instruction; A parameter fusion module, connected to the data acquisition module, is used to fuse multi-source parameter information to output the fused point cloud coordinates; And use the fused point cloud coordinates as an input parameter of the error prediction model to optimize the compensation parameters; An execution control module, connected to the dynamic compensation module, sends the dynamic compensation instruction to the motion controller, and controls the X-axis drive module, the Y-axis drive module and the Z-axis drive module to move along a preset path.

2. The spatial parameter measurement system based on a coordinate measuring machine according to claim 1, characterized in that, The measurement component includes a sliding frame arranged at the output end of the Z-axis drive module and slidably connected to the Z-axis drive module. A rotating motor is arranged inside the sliding frame, a probe is arranged at the output end of the rotating motor, a laser scanning module is arranged on one side of the probe, a connecting block is arranged at the bottom of the sliding frame, the probe penetrates through the connecting block, and binocular structured light cameras are arranged on both sides of the connecting block.

3. A spatial parameter measurement system based on a coordinate measuring machine according to claim 2, characterized in that, The dynamic compensation module includes: A multi-source data input unit, which is used to receive the parameter information of the data acquisition module in real time; The error prediction model is configured to input parameter information and output compensation parameters ΔR, (ΔX, ΔY, ΔZ); where ΔR is the probe radius compensation coefficient, and ΔX, ΔY, ΔZ are coordinate offsets; A compensation instruction generation unit, connected to the execution control module, is used to send the compensation parameters to the motion controller in real time.

4. A spatial parameter measurement system based on a coordinate measuring machine according to claim 3, characterized in that, The parameter fusion module includes: A multi-source data acquisition unit, which is configured to synchronously acquire laser scanning point cloud data and probe contact point cloud data; A dynamic weight distribution unit, which is configured to: Adjust the laser point cloud weight W1 for areas that meet the following conditions, and the probe point cloud weight is W2 = 1 - W1: Plane continuity area: When the included angle between the normal vectors of adjacent points is less than a preset angle, the laser point cloud weight W1 is multiplied by a gain factor; Reflective area: When the signal-to-noise ratio is less than a preset threshold, the laser point cloud weight W1 is multiplied by an attenuation factor; The point cloud fusion unit obtains the fused point cloud coordinates through weighted averaging based on the laser point cloud weight W1 and the probe point cloud weight W2; the point cloud fusion unit is also configured to input the fused point cloud coordinates into the error prediction model to output compensation parameters ΔR, (ΔX, ΔY, ΔZ).

5. The spatial parameter measurement system based on a coordinate measuring machine according to claim 4, wherein The measurement platform includes a support base arranged on the top of the control box. A fixture fixing plate is arranged on the top of the support base. A circular hole is formed on the fixture fixing plate to form a measurement area. A fixed clamping part and two sliding clamping parts are arranged along the circumference of the measurement area on the fixture fixing plate. A first guide rail is arranged at the bottom of the sliding clamping part, and the sliding clamping part is slidably connected to the first guide rail; A second guide rail is also arranged on the fixture fixing plate, and the second guide rail is located between the two sliding clamping parts. A Y-shaped push rod is slidably arranged on the second guide rail. A chute is arranged in the middle of the sliding clamping part, and the Y-shaped push rod is slidably connected to the chute; A clamping cylinder is also arranged on the fixture fixing plate, and the output end of the clamping cylinder is fixedly connected to the Y-shaped push rod.

6. The spatial parameter measurement system based on a coordinate measuring machine according to claim 5, wherein The included angle between the two sliding clamping parts is 120°. One end of the Y-shaped push rod away from the clamping cylinder is two inclined rods with an included angle of 60°. The inclined rods are slidably connected to the chute, so that when the Y-shaped push rod slides along the second guide rail, the two inclined rods respectively drive the two sliding clamping parts to slide along the first guide rail.

7. A spatial parameter measurement system based on a coordinate measuring machine according to claim 6, characterized in that, The X-axis drive module and the Y-axis drive module have the same structure, and both are screw drive mechanisms. The Z-axis drive module includes a Z-axis fixing plate slidably connected to the Y-axis drive module. A Z-axis guide rail is arranged on one side of the Z-axis fixing plate. A sliding frame is arranged on the Z-axis guide rail, and the sliding frame is slidably connected to the Z-axis guide rail; A Z-axis cylinder is arranged on the top of the Z-axis fixing plate, and the output end of the Z-axis cylinder is fixedly connected to the sliding frame; A rotating motor is arranged inside the sliding frame to drive the binocular structured light camera and the laser scanning module to rotate.

8. A spatial parameter measurement system based on a coordinate measuring machine according to claim 7, characterized in that, The control box is also connected to an external obstacle avoidance module; The obstacle avoidance module includes a workpiece model construction unit, a fixture model construction unit, a model superposition unit, and a boundary extraction unit; The workpiece model construction unit constructs a three-dimensional model of the workpiece to be measured based on the workpiece scan point cloud of the non-contact scanning unit; The fixture model construction unit establishes a three-dimensional model of the fixture based on the fixture scan point cloud of the non-contact scanning unit; The model superposition unit is used to superpose the three-dimensional model of the workpiece to be measured and the three-dimensional model of the fixture in the same coordinate system; The boundary extraction unit is used to traverse the three-dimensional models of the workpiece to be measured and the fixture and identify the boundary points, connect the boundary points into a closed loop, and form the edge path of the overlapping area; The boundary extraction unit is connected to the execution control module, and sends the edge path to the motion controller to control the X-axis drive module, the Y-axis drive module, and the Z-axis drive module to move along the edge path.

Images