Wear testing machine and monitoring method for self-monitoring multi-degree-of-freedom motion of artificial knee joint

Abstract

This invention belongs to the field of knee joint friction testing technology, and discloses a wear testing machine and monitoring method for self-monitoring multi-degree-of-freedom motion of an artificial knee joint. The machine includes a frame and testing components. The testing components include a support base, a hydraulic cylinder, a hydraulic rod, a femoral end assembly, and a third motor. Below the femoral end assembly, a tibial end assembly, a centering platform, a pressure sensor, and a sliding platform are sequentially arranged. A second slide rail parallel to the support base is provided between the sliding platform and the frame. A monitoring device is installed on one corner of the frame near the centering platform. The pressure sensor is sleeved on a torsion shaft, and the other end of the torsion shaft is fixedly connected to a first reducer and a first motor. A crossbeam is fixedly connected to the bottom of the sliding platform, and the crossbeam is connected to a swinging component, which is also connected to a second reducer and a second motor. This invention adopts a design combining hydraulic, electric, and mechanical methods to achieve comprehensive simulation of the real multi-degree-of-freedom motion of the human knee joint.

Description

Technical Field

[0001] This invention relates to the field of knee joint friction testing technology, and in particular to a wear testing machine and monitoring method for self-monitoring multi-degree-of-freedom motion of artificial knee joints. Background Technology

[0002] Because artificial knee joint prostheses wear down within the human body, their lifespan is relatively short. Therefore, the wear resistance of artificial knee joint prostheses determines their lifespan. To verify the wear resistance of artificial knee joint prostheses, in vitro wear evaluation should be conducted. However, current biomimetic knee joint friction and wear testing machines mostly use three-dimensional or six-dimensional force sensors to monitor multi-degree-of-freedom forces, which has high hardware costs and limited force freedom. Furthermore, the installation and calibration of force sensors also makes hardware structure design and subsequent maintenance more difficult.

[0003] Chinese invention patent, publication number CN116256262A, entitled "A Knee Joint Friction Testing Mechanism and Test Method Thereof," discloses a knee joint friction testing mechanism and test method, including a knee joint prosthesis, a frame, a six-dimensional force sensor, a slide base plate, a slide fixing plate, a first gait drive device, a transition shaft, a second gait drive device, a third gait drive device, and a controller. The controller is connected to the six-dimensional force sensor, the first gait drive device, the second gait drive device, and the third gait drive device, respectively. This technical solution uses the controller to activate the first gait drive device, the second gait drive device, and the third gait drive device according to gait data to complete femoral flexion gait movements, anterior-posterior displacement gait movements, and vertical load gait movements. The six-dimensional force sensor acquires the mechanical data corresponding to each gait movement, thereby simulating the complex multi-degree-of-freedom physiological movements of the human knee joint and displaying the correct biological movement characteristics of the knee joint. However, this technical solution uses a six-dimensional force sensor, resulting in high hardware costs and limited force freedom.

[0004] Chinese Invention Patent: Publication No. CN118483090A, entitled "A Four-Degree-of-Freedom Knee Joint Prosthesis Friction and Wear Testing Machine", discloses a four-degree-of-freedom knee joint prosthesis friction and wear testing machine, which includes a frame; a femoral flexion mechanism, which is set on the frame and can be vertically raised and lowered along the frame; the femoral flexion mechanism is used to position the femoral prosthesis and drive the femoral prosthesis to rotate along a vertical plane; a tibial rotation mechanism, located below the tibial prosthesis and used to support the tibial prosthesis, and also used to drive the tibial prosthesis to rotate along a horizontal plane; an anterior-posterior displacement mechanism, set on the frame and supporting the tibial rotation mechanism; the anterior-posterior displacement mechanism is used to drive the tibial rotation mechanism to move back and forth to drive the tibial prosthesis to move back and forth relative to the femoral prosthesis; a vertical load application mechanism, set on the frame and connected to the lower part of the femoral flexion mechanism; the vertical load application mechanism is used to pull down and release the femoral flexion mechanism to drive the femoral prosthesis to press down and release the tibial prosthesis. This technical solution can achieve four degrees of freedom of motion, simulating the complex movement state of the human knee joint and providing effective data for evaluating artificial knee joints. However, this technical solution still uses traditional multi-dimensional force sensors to collect the force state at the current point of application, and cannot perform simulation control that more closely matches the movement law of the human knee joint based on joint posture information. Summary of the Invention

[0005] To address the limitations of existing technologies that rely on traditional multi-dimensional force sensors to collect data on the force applied to the current point of force, which cannot provide simulation control that more closely reflects the movement patterns of the human knee joint based on joint posture information, and the high hardware cost and limited degrees of freedom of traditional multi-dimensional force sensors, this invention proposes a self-monitoring wear testing machine and monitoring method for multi-degree-of-freedom motion of artificial knee joints. This solves the problems of artificial knee joint wear testing machines being unable to provide real-time monitoring and accurately simulate the complex motion and wear conditions of the human knee joint.

[0006] This invention is achieved through the following technical solution: It includes a test bench and a test assembly mounted on the test bench. The test assembly includes a support fixedly connected to the test bench, a vertically arranged hydraulic cylinder penetrating the support, a hydraulic rod fixedly connected to the hydraulic cylinder, a femoral end assembly fixedly connected to the hydraulic rod, and a third motor perpendicular to the hydraulic cylinder with its output end fixedly connected to the femoral end assembly. Below the femoral end assembly, a tibial end assembly, a centering platform, a pressure sensor, and a sliding platform are sequentially arranged. The support bench includes a vertical column and a horizontal column. One end of the vertical column is fixedly connected to the test bench, and the other end is fixedly connected to the horizontal column. The hydraulic cylinder penetrates the horizontal column of the support bench. One end of the hydraulic cylinder facing the platform is fixedly connected to a hydraulic rod; a second slide rail parallel to the support base is provided between the sliding platform and the platform, and the slider of the sliding platform and the second slide rail are fixedly connected, and the second slide rail is fixedly connected to the platform; a monitoring device is provided on one corner of the platform near the centering platform, and the pressure sensor is sleeved on the torsion shaft, the other end of the torsion shaft is fixedly connected to the first reducer and the first motor; a crossbeam is fixedly connected to the bottom of the sliding platform, the crossbeam is connected to the swinging component, and the swinging component is also connected to the second reducer and the second motor; the monitoring device, the first motor, the second motor, and the third motor are all connected to the computer host.

[0007] As a further preferred option, the test components are in two sets, arranged side by side along the long side of the test bench.

[0008] As a further preferred embodiment, a crank-connecting rod assembly is also connected to the torsion shaft, and the crank-connecting rod assembly is rotatably connected to the torsion shaft on each set of test components.

[0009] As a further preferred embodiment, a counterweight is provided between the hydraulic rod and the femoral end assembly; the counterweight is fixedly connected to both the hydraulic rod and the femoral end assembly.

[0010] As a further preferred embodiment, a first slide rail is vertically provided on the column of the support base, and the slider of the first slide rail is fixedly connected to the counterweight.

[0011] The present invention also provides a monitoring method applicable to the wear testing machine for self-monitoring multi-degree-of-freedom motion of the artificial knee joint described in the present invention, comprising the following steps:

[0012] S1. The monitoring device acquires images containing artificial knee joint prosthesis components;

[0013] S2. Using the pixel content of the knee joint prosthesis component as the foreground target, extract the image of the knee joint prosthesis component using the image target detection algorithm Yolov5, and set the background image pixels to 0;

[0014] S3. Based on the knee joint prosthesis component images extracted in step S2, use the pre-trained SAM model as a lightweight image segmentation algorithm to extract the images of the tibial end component and the femoral end component respectively.

[0015] S4. Based on the images of the tibial end component and the femoral end component obtained in step S3, the key points A1, A2, A3, A4, A5, A6 of the femoral end component and the key points B1, B2, B3, B4 of the tibial end component 3 are extracted using the pre-trained OpenPose model to obtain the two-dimensional coordinates of the key points of the femoral end component and the tibial end component.

[0016] S5. Based on the two-dimensional coordinates of the key points of the femoral end component and the tibial end component obtained in step S4, the intrinsic parameter K and extrinsic parameter E of the monitoring device are used to obtain the attitude parameters T = [TA, TB] of the femoral end component and the tibial end component, where TA is the homogeneous transformation matrix of the femoral end component with A2 as the reference point, and TB is the homogeneous transformation matrix of the tibial end component with A2 as the reference point.

[0017] S6. The pressure sensor collects the pressure value of the image at the current moment, which is used as the force parameter W before attitude fine-tuning;

[0018] S7. Substitute the posture parameters T of the femoral and tibial components obtained in step S5 into the real human knee joint motion model database, and filter out the most similar posture parameters. The similarity calculation formula is as follows:

[0019] argmin||T-Tref||2

[0020] Where Tref represents the posture parameters of a real human knee joint motion model database, and ||·||2 represents the second norm of the matrix.

[0021] S8. Based on the most similar posture parameter Tref obtained in step S7 and the posture parameters T of the femoral and tibial end components obtained in step S5, the posture motion parameters are obtained, as follows:

[0022] T △ =Tref-T

[0023] The attitude motion parameter T △ The force parameters W obtained from the steps are input into the computer host.

[0024] S9. Collect the pressure value of the pressure sensor after attitude fine-tuning, and use it as the force parameter W' under this attitude;

[0025] S10. Repeat steps S1 to S9 until the experiment is completed.

[0026] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0027] 1. This invention adopts a design that combines hydraulic, electric and mechanical technologies to achieve a comprehensive simulation of the real multi-degree-of-freedom movement of the human knee joint. The hydraulic device can simulate the high-frequency movement of the human knee joint and provide the movement load it bears, thereby achieving a movement mode that is closer to the movement characteristics of the human knee joint.

[0028] 2. This invention employs an image-based intelligent algorithm for monitoring and controlling the posture of artificial knee joint prostheses. By collecting posture information from the testing machine via a camera and combining it with real human knee joint motion data, the invention controls and adjusts equipment such as motors. This solves the problems of high cost and space occupation associated with traditional multi-dimensional force sensors, and allows for timely feedback of monitoring results to correct motion tasks, thereby obtaining more accurate and comprehensive wear test data.

[0029] 3. The crank-connecting rod mechanism used in this invention can realize multi-degree-of-freedom motion with synchronous operation at multiple stations, thereby improving test efficiency and reducing test errors caused by different angles. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0031] Figure 2 This is a schematic diagram of the structure of a single operating station in this invention.

[0032] Figure 3 for Figure 2 A partially enlarged schematic diagram of the transmission part.

[0033] Figure 4 for Figure 3 A horizontal side view.

[0034] Figure 5a This is a schematic diagram of the artificial knee joint prosthesis assembly collected by the monitoring device in this invention.

[0035] Figure 5b This is a schematic diagram illustrating the extraction of the femoral end component and the tibial end component by the lightweight image segmentation algorithm in this invention.

[0036] Figure 5c This is a schematic diagram showing the key point arrangement of the femoral end component and the tibial end component in this invention.

[0037] The image shows:

[0038] 1. Hydraulic cylinder; 2. Femoral end assembly; 3. Tibial end assembly; 4. Alignment platform; 5. Pressure sensor; 6. Monitoring device; 7. Sliding platform; 8. First reducer; 9. First motor; 10. Hydraulic rod; 11. First slide rail; 12. Second slide rail; 13. Second reducer; 14. Second motor; 15. Lifting foot; 16. Counterweight; 17. Third motor; 18. Torsion shaft; 19. Crank connecting rod assembly; 20. Crossbeam; 21. Swing assembly. Detailed Implementation

[0039] The advantages and features of the present invention will be illustrated and explained by the following non-limiting description of preferred embodiments, which are given by way of example only with reference to the accompanying drawings.

[0040] like Figures 1 to 4As shown, this invention provides a wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint, including a frame on which a testing assembly is mounted. The testing assembly includes a support base fixedly connected to the frame. The support base comprises uprights and horizontal columns. One end of the uprights is fixedly connected to the frame, and the other end is fixedly connected to the horizontal column. Preferably, there are four uprights, respectively positioned at the four corners of the horizontal column. The testing assembly also includes a hydraulic cylinder 1, a femoral end assembly 2, a tibial end assembly 3, a centering platform 4, a pressure sensor 5, a sliding platform 7, and a third motor 17. The hydraulic cylinder 1 is vertically mounted and runs through the horizontal column of the support base. A hydraulic rod 10 is fixedly connected to one end of the hydraulic cylinder 1 facing the frame, and the other end of the hydraulic rod 10 is fixedly connected to the femoral end assembly 2. The hydraulic cylinder 1 drives the hydraulic rod 10 to move up and down, applying pressure to the femoral end assembly 2 to simulate different body weights and achieve different frequencies of pressure application. Below the femoral end component 2, a tibial end component 3 is disposed. A centering platform 4 is fixedly connected below the tibial end component 3, and a pressure sensor 5 is fixedly connected below the centering platform 4. A sliding platform 7 is disposed below the pressure sensor 5. A second slide rail 12 is disposed between the sliding platform 7 and the test bench, and the slider of the sliding platform 7 and the second slide rail 12 is fixedly connected. The second slide rail 12 is fixedly connected to the test bench. The second slide rail 12 is parallel to the support base. The centering platform 4 is used for vertical centering of the tibial end component 3, and the pressure sensor 5 is used to sense the pressure value experienced by the tibial end component 3. The sliding platform 7 and the second slide rail 12 form a horizontal movement platform for the tibial end component 3. Preferably, two sets of test components are arranged side-by-side along the long side of the test bench. A monitoring device 6 is installed at one corner of the test bench near the centering platform 4. This monitoring device 6 collects image data from the testing machine and sends it to the computer host. The computer host uses an image intelligent algorithm to identify the posture of the artificial knee joint prosthesis, monitors the machine's operation in real time, and sends commands to the motor control system to correct the motion tasks in real time, thereby obtaining comprehensive and accurate wear test data and achieving precise wear results for the artificial knee joint prosthesis. The pressure sensor 5 is mounted on the torsion shaft 18, the other end of which is fixedly connected to the first reducer 8 and the first motor 9. The first reducer 8 is positioned above the first motor 9 to match the rotational speed and transmit torque, serving as the torsional power device for the tibial end assembly 3. To facilitate adjustment of the overall level of the test bench, lifting feet 15 are installed at the four corners of the bottom of the test bench, and these lifting feet 15 are fixedly connected to the test bench by bolts.

[0041] In the case of multiple test components, a crank-connecting rod assembly 19 is also connected to the torsion shaft 18. The crank-connecting rod assembly 19 is rotatably connected to the torsion shaft 18 on each test component. The advantage of this design is that the first reducer 8 and the first motor 9 can be set on only one test component, and the multiple tibial end components 3 can be driven to twist through the crank-connecting rod assembly 19.

[0042] A crossbeam 20 is fixedly connected to the bottom of the sliding platform 7. The crossbeam 20 is connected to the swing member 21, which is also connected to the second reducer 13 and the second motor 14. The second motor 14 and the second reducer 13 drive the swing member 21 to swing, thereby moving the crossbeam 20 and ultimately causing the sliding platform 7 to move horizontally under the constraint of the second slide rail 12.

[0043] like Figure 2 As shown, to ensure smoother simulation and reduce the load on the hydraulic cylinder 1, a counterweight 16 can be installed between the hydraulic rod 10 and the femoral end assembly 2. The counterweight 16 is fixedly connected to both the hydraulic rod 10 and the femoral end assembly 2. Simultaneously, a first slide rail 11 is vertically installed on the column of the support base, and the slider of the first slide rail 11 is fixedly connected to the counterweight 16. The hydraulic cylinder 1 drives the counterweight 16, connected to the hydraulic rod 10, to move up and down, applying pressure to the femoral end assembly 2 to simulate different body weights and achieve different frequencies of pressure application. The output end of the third motor 17 is fixedly connected to the femoral end assembly 2, driving the femoral end assembly 2 to rotate, forming a swing mechanism to simulate different angles of knee flexion. The third motor 17 is positioned perpendicular to the hydraulic cylinder 1.

[0044] The first motor 9, the second motor 14, and the third motor 17 are all connected to the computer host and receive control signals from the computer host. The femoral end assembly 2 and the tibial end assembly 3, driven by the first motor 9, the second motor 14, and the third motor 17, realize multi-degree-of-freedom movement simulating the human knee joint.

[0045] The present invention also provides a monitoring method applicable to the wear testing machine for self-monitoring multi-degree-of-freedom motion of the artificial knee joint described in the present invention, comprising the following steps:

[0046] Step 1: The monitoring device 6 acquires images containing the artificial knee joint prosthesis components.

[0047] like Figure 5a The image shown is an image of the artificial knee joint prosthesis assembly acquired using monitoring device 6.

[0048] Step 2: Using the pixel content of the knee joint prosthesis component as the foreground target, extract the image of the knee joint prosthesis component using the image target detection algorithm YOLOv5, and set the background image pixels to 0.

[0049] Step 3: Based on the knee joint prosthesis component images extracted in Step 2, use the pre-trained cropped SegmentAnything Model (SAM model) as a lightweight image segmentation algorithm to extract the images of the tibial end component 3 and the femoral end component 2 respectively.

[0050] like Figure 5b The image shown is an image of the femoral end component 2 and the tibial end component 3 extracted using the SAM model.

[0051] Step 4: Based on the images of tibial end component 3 and femoral end component 2 obtained in Step 3, use the pre-trained OpenPose model to extract key points A1, A2, A3, A4, A5, A6 of femoral end component 2 and key points B1, B2, B3, B4 of tibial end component 3, to obtain the two-dimensional coordinates of the key points of femoral end component 2 and tibial end component 3.

[0052] like Figure 5c As shown, there are six key points on the femoral end component 2: A1: the center of the end furthest from the tibial end component 3; A2: the center of the end closest to the tibial end component 3; A3 and A4: the centers of the left and right lateral walls; A5 and A6: the two protrusions on the left and right sides of the end closest to the tibial end component 3. There are four key points on the tibial end component 3: B1 and B2: the left and right ends; B3: the center of the end furthest from the femoral end component 2; and B4: the center of the end closest to the femoral end component 2.

[0053] Step 5: Based on the two-dimensional coordinates of the key points of the femoral end component 2 and the tibial end component 3 obtained in Step 4, the intrinsic parameter K and extrinsic parameter E of the monitoring device 6 are used to obtain the attitude parameters T = [TA, TB] of the femoral end component 2 and the tibial end component 3, where TA is the homogeneous transformation matrix of the femoral end component 2 with A2 as the reference point, and TB is the homogeneous transformation matrix of the tibial end component 3 with A2 as the reference point.

[0054] Step 51: Measure the internal parameter K and external parameter E of the monitoring device 6, using the following formula:

[0055]

[0056] Among them, f x and f y It is the focal length in the x and y directions, c x and c y R is the principal point coordinates, R is a 3x3 rotation matrix, and t is a 3x1 translation vector.

[0057] Step 52: Convert the two-dimensional coordinates of the key points of the femoral end component 2 obtained in Step 4 into three-dimensional coordinates;

[0058] Step 521: Convert the two-dimensional coordinates to homogeneous coordinates, using the following formula:

[0059]

[0060] Where i = 1, 2, 3, 4, 5, 6; and These represent the homogeneous coordinates of a key point before and after the change.

[0061] Step 522: Based on the intrinsic parameters K of the monitoring device 6 obtained in step 51 and the homogeneous coordinates obtained in step 521, the normalized image plane coordinates are obtained, as follows:

[0062]

[0063] Among them, u i norm and u i ' norm K represents the normalized image plane coordinates of a key point before and after the change; -1 Let K be the inverse matrix of the intrinsic parameter K.

[0064]

[0065] Step 523: Based on the normalized image plane obtained in step 522 and the external parameters E of the monitoring device 6 measured in step 51, obtain the world coordinates using the following formula:

[0066]

[0067] in It is the transpose of the inverse matrix of the extrinsic parameter E; x i and x i 'Represents the world coordinates of a key point before and after the change.

[0068] Step 524: Based on the world coordinates obtained in step 523 and the external parameters E of the monitoring device 6 measured in step 51, obtain the camera coordinates using the following formula:

[0069]

[0070] in and These represent the camera coordinates of a key point before and after the change.

[0071] Step 525: Based on the camera coordinates and the inverse matrix of the extrinsic parameter E obtained in step 524, obtain the three-dimensional coordinates of the object coordinate system, as shown in the following formula:

[0072]

[0073] Where P i and Pi 'Represents the three-dimensional coordinates of a key point in the object's coordinate system before and after the change.

[0074] Step 53: Based on the three-dimensional coordinates of the object coordinate system obtained in step 525, obtain the rotation matrix relative to the reference point A2.

[0075] Step 531: Based on the three-dimensional coordinates of the object coordinate system obtained in Step 225, obtain the coordinates of each key point relative to the reference point A2, using the following formula:

[0076]

[0077] Among them, P i rel and P i ' rel P1 and P2' represent the coordinates of a key point relative to the reference point A2 before and after the change; P2 and P2' are the three-dimensional coordinates of the key point A2 in the object coordinate system obtained in step 525.

[0078] Step 532, based on P obtained in step 531 i rel and P i ’rel Using singular value decomposition (SVD), the rotation matrix relative to the reference point A2 is obtained, as shown in the following formula:

[0079]

[0080] Step 54: Based on the rotation matrix R relative to reference point A2 rel Using the 3D coordinates of key point A2 obtained in step 525 in the object coordinate system, the translation vector relative to reference point A2 is obtained, as shown in the following formula:

[0081] t rel =p′2-R rel p2

[0082] Step 55: Combine rotation and translation to obtain the homogeneous transformation matrix TA of femoral end component 2 with A2 as the reference point.

[0083] Step 551: Construct the homogeneous transformation matrix relative to the reference point A2:

[0084]

[0085] Step 552: Apply the homogeneous transformation matrix relative to reference point A2 to obtain the TA of the homogeneous transformation matrix of femoral end component 2 with A2 as the reference point, as shown in the following formula:

[0086]

[0087] p′ rel =T rel p hom

[0088] TA = T rel

[0089] Where P is a point on the object; P hom Let p' be the homogeneous coordinates of point P; rel These are the coordinates of the point after transformation relative to the reference point A2.

[0090] Step 56: Replace the key points of femoral end component 2 in step 52 with the key points of tibial end component 3 and key point A2 in femoral end component 2, and repeat steps 52 to 55 to obtain the homogeneous transformation matrix TB of tibial end component 3 with A2 as the reference point.

[0091] Step 6: Pressure sensor 5 collects the pressure value of the image at the current moment, which is used as the force parameter W before attitude fine-tuning.

[0092] Step 7: Substitute the posture parameters T of the femoral end component 2 and tibial end component 3 obtained in Step 5 into the real human knee joint motion model database, and filter the most similar posture parameters. The similarity calculation formula is argmin||T-Tref||2.

[0093] Where Tref represents the posture parameters of a real human knee joint motion model database, and ||·||2 represents the second norm of the matrix.

[0094] Step 8: Based on the most similar posture parameter Tref obtained in Step 7 and the posture parameters T of the femoral end component 2 and the tibia end component 3 obtained in Step 5, the posture motion parameters are obtained, as follows:

[0095] T △ =Tref-T

[0096] The attitude motion parameter T △ The force parameters W obtained in step 6 are input into the computer host to realize the automatic fine adjustment of the machine.

[0097] Step 9: Collect the pressure value of pressure sensor 5 after attitude fine-tuning, and use it as the force parameter W' under this attitude.

[0098] Step 10: Repeat steps 1 to 9 until the test is completed, that is, the number of tests reaches the set value or the force parameter W' exceeds the set threshold.

Claims

1. A wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint, comprising a frame and testing components mounted on the frame, characterized in that: The test assembly includes a support base fixedly connected to a test bench, a vertically arranged hydraulic cylinder (1) penetrating the support base, a hydraulic rod (10) fixedly connected to the hydraulic cylinder (1), a femoral end assembly (2) fixedly connected to the hydraulic rod (10), and a third motor (17) perpendicular to the hydraulic cylinder (1) and whose output end is fixedly connected to the femoral end assembly (2). Below the femoral end assembly (2) are arranged a tibial end assembly (3), a centering platform (4), a pressure sensor (5), and a sliding platform (7). The support base includes a vertical column and a horizontal column. One end of the vertical column of the support base is fixedly connected to the test bench, and the other end is fixedly connected to the horizontal column. The hydraulic cylinder (1) penetrates the horizontal column of the support base. The end of the hydraulic cylinder (1) facing the test bench is fixedly connected to the hydraulic rod (10). The sliding platform (7) is connected to the test bench. A second slide rail (12) parallel to the support base is provided. The sliding platform (7) is fixedly connected to the slider of the second slide rail (12). The second slide rail (12) is fixedly connected to the platform. A monitoring device (6) is provided on one corner of the platform near the centering platform (4). The pressure sensor (5) is sleeved on the torsion shaft (18). The other end of the torsion shaft (18) is fixedly connected to the first reducer (8) and the first motor (9). A crossbeam (20) is fixedly connected to the bottom of the sliding platform (7). The crossbeam (20) is connected to the swinging component (21). The swinging component (21) is also connected to the second reducer (13) and the second motor (14). The monitoring device (6), the first motor (9), the second motor (14) and the third motor (17) are all connected to the computer host.

2. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 1, characterized in that: The test components consist of two sets, arranged side by side along the long side of the test bench.

3. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 2, characterized in that: A crank-connecting rod assembly (19) is also connected to the torsion shaft (18), and the crank-connecting rod assembly (19) is rotatably connected to the torsion shaft (18) on each test assembly.

4. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 1, characterized in that: A counterweight (16) is provided between the hydraulic rod (10) and the femoral end assembly (2); the counterweight (16) is fixedly connected to the hydraulic rod (10) and the femoral end assembly (2) respectively.

5. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 4, characterized in that: A first slide rail (11) is vertically arranged on the column of the support base, and the slider of the first slide rail (11) is fixedly connected to the counterweight (16).

6. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 1, characterized in that: The four corners of the bottom of the platform are also provided with lifting feet (15), which are fixedly connected to the platform by bolts.

7. The wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint according to claim 1, characterized in that: The support base has four uprights, which are respectively set at the four corners of the horizontal column.

8. A monitoring method applicable to the wear testing machine for self-monitoring multi-degree-of-freedom motion of an artificial knee joint as described in any one of claims 1 to 7, characterized in that: It includes the following steps: S1. The monitoring device (6) acquires images containing artificial knee joint prosthesis components; S2. Using the pixel content of the knee joint prosthesis component as the foreground target, extract the image of the knee joint prosthesis component using the image target detection algorithm Yolov5, and set the background image pixels to 0; S3. Based on the knee joint prosthesis component images extracted in step S2, use the pre-trained SAM model as a lightweight image segmentation algorithm to extract the images of the tibial end component (3) and the femoral end component (2) respectively. S4. Based on the images of the tibial end component (3) and the femoral end component (2) obtained in step S3, the key points A1, A2, A3, A4, A5, A6 of the femoral end component (2) and the key points B1, B2, B3, B4 of the tibial end component (3) are extracted using the pre-trained OpenPose model to obtain the two-dimensional coordinates of the key points of the femoral end component (2) and the tibial end component (3). S5. Based on the two-dimensional coordinates of the key points of the femoral end component (2) and tibial end component (3) obtained in step S4, the intrinsic parameter K and extrinsic parameter E of the monitoring device (6) are used to obtain the attitude parameters T = [TA, TB] of the femoral end component (2) and tibial end component (3), where TA is the homogeneous transformation matrix of the femoral end component (2) with A2 as the reference point, and TB is the homogeneous transformation matrix of the tibial end component (3) with A2 as the reference point. S6. Pressure sensor (5) collects the pressure value of the image at the current moment and uses it as the force parameter W before attitude fine-tuning. S7. Substitute the posture parameters T of the femoral end component (2) and tibial end component (3) obtained in step S5 into the real human knee joint motion model database, and filter the most similar posture parameters. The similarity calculation formula is as follows: argmin||T-Tref||2 Where Tref represents the posture parameters of the real human knee joint motion model database, and ||·||2 represents the second norm of the matrix; S8. Based on the most similar posture parameter Tref obtained in step S7 and the posture parameters T of the femoral end component (2) and tibial end component (3) obtained in step S5, the posture motion parameters are obtained, as follows: T △ =Tref-T The attitude motion parameter T △ The force parameters W obtained in step (6) are input into the computer host. S9. Collect the pressure value of the pressure sensor (5) after attitude fine-tuning, and use it as the force parameter W' under this attitude; S10. Repeat steps S1 to S9 until the experiment is completed.

9. The monitoring method of the wear testing machine for self-monitoring multi-degree-of-freedom motion of artificial knee joint according to claim 8, characterized in that: The specific steps of step S5 are as follows: S51. The internal parameter K and external parameter E of the monitoring device (6) are measured, and the formulas are as follows: Among them, f x and f y It is the focal length in the x and y directions, c x and c y R is the principal point coordinates, R is a 3x3 rotation matrix, and t is a 3x1 translation vector; S52. Convert the two-dimensional coordinates of the key points of the femoral end component (2) into three-dimensional coordinates; S521. Convert two-dimensional coordinates to homogeneous coordinates using the following formula: Where i = 1, 2, 3, 4, 5, 6; and These represent the homogeneous coordinates of a key point before and after the change; S522. Based on the intrinsic parameter K and the homogeneous coordinates obtained in step S521, the normalized image plane coordinates are obtained, as shown in the following formula: Among them, u i norm and u i ' norm K represents the normalized image plane coordinates of a key point before and after the change; -1 Let K be the inverse matrix of the intrinsic parameter K; S523. Based on the normalized image plane and the extrinsic parameter E, the world coordinates are obtained using the following formula: in It is the transpose of the inverse matrix of the extrinsic parameter E; x i and x' i These represent the world coordinates of a key point before and after the change; S524. Based on the world coordinates and the external parameter E, the camera coordinates are obtained using the following formula: in and These represent the camera coordinates of a key point before and after the change; S525. Based on the inverse matrix of the camera coordinates and the extrinsic parameter E, the three-dimensional coordinates of the object coordinate system are obtained, as shown in the following formula: Where P i and P i 'Represents the three-dimensional coordinates of the object's coordinate system before and after the change; S53. Based on the three-dimensional coordinates of the object's coordinate system, obtain the rotation matrix relative to the reference point A2; S531. Based on the three-dimensional coordinates of the object's coordinate system, obtain the coordinates of each key point relative to the reference point A2, using the following formula: Among them, P i rel and P i ' rel P1 and P2' represent the coordinates of a key point relative to the reference point A2 before and after the change; P2 and P2' are the three-dimensional coordinates of the key point A2 in the object coordinate system obtained in step 525. S532, according to P i rel and P i ' rel Using singular value decomposition (SVD), the rotation matrix relative to the reference point A2 is obtained, as shown in the following formula: S54, According to the rotation matrix R rel Given the 3D coordinates of key point A2 in the object coordinate system obtained in step S525, the translation vector relative to reference point A2 is obtained, as shown in the following formula: t rel =p′2-R rel p2 S55. Combine rotation and translation to obtain the homogeneous transformation matrix TA of the femoral end component (2) with A2 as the reference point; S551. Construct the homogeneous transformation matrix relative to the reference point A2: S552. Applying the homogeneous transformation matrix relative to reference point A2, obtain the TA of the homogeneous transformation matrix of the femoral end component (2) with A2 as the reference point, as shown in the following formula: p′ rel =T rel p hom TA=T rel Where P is a point on the object; P hom Let p' be the homogeneous coordinates of point P; rel These are the coordinates of the point after transformation relative to reference point A2; S56. Replace the key points of the femoral end component (2) in step S52 with the key points of the tibial end component (3) and the key point A2 in the femoral end component (2). Repeat steps S52 to S55 to obtain the homogeneous transformation matrix TB of the tibial end component (3) with A2 as the reference point.

10. The monitoring method of the wear testing machine for self-monitoring multi-degree-of-freedom motion of artificial knee joint according to claim 9, characterized in that: The key points of the femoral end component (2) in step S4 are as follows: A1: the center of the end away from the tibial end component (3); A2: the center of the end close to the tibial end component (3); A3, A4: the center of the left and right side walls; A5, A6: the two protrusions on the left and right sides close to the end of the tibial end component (3); the key points of the tibial end component (3) are as follows: B1, B2: the left and right ends; B3: The center of the end furthest from the femoral end component (2); B4: The center of the end closest to the femoral end component (2).

Images