Method, system, device, storage medium and program product for monitoring the wear state of an artificial joint

Abstract

This application relates to a method, system, device, storage medium, and program product for monitoring the wear state of artificial joints. It acquires a first voltage signal output by a recognizer when the spherical structure and plate structure in a first joint simulation structure move relative to each other. This first voltage signal is then input into a wear state monitoring model to identify the working state of the first joint simulation structure, thus obtaining its current working state. This method ensures the accuracy and reliability of the artificial joint wear state identification results. Furthermore, by directly capturing the voltage signal generated by the relative movement of the spherical and plate structures, it achieves real-time monitoring of the joint's working state, effectively solving the problem of inefficient and accurate perception of the wear state of artificial joint structures. This provides scientific and reliable technical support for timely maintenance, fault warning, and service life assessment of joint structures.

Description

Technical Field

[0001] This application relates to the field of artificial joint technology, and in particular to a method, system, device, storage medium, and program product for monitoring the wear and tear of artificial joints. Background Technology

[0002] With the increasing use of artificial joint replacement surgery in the treatment of end-stage joint diseases, the number of patients undergoing joint replacement worldwide continues to rise annually. The long-term effectiveness and safety of artificial joints have become one of the core issues of clinical concern. However, during long-term use, artificial joints are prone to wear and tear due to repeated friction and impact loads on the joint surfaces. The particles generated by this wear can trigger periprosthetic inflammation and even lead to serious complications such as prosthesis loosening and subsidence, directly impacting the patient's quality of life and the lifespan of the prosthesis.

[0003] Traditional methods for monitoring wear and tear on artificial joints often involve implanting sensors or electronic modules into the prosthesis or surrounding tissues. However, this method relies on external power and is difficult to operate stably for extended periods. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, system, device, storage medium, and program product for monitoring the wear and tear of artificial joints to address the aforementioned technical problems.

[0005] In a first aspect, this application provides a method for monitoring the wear and tear of an artificial joint, comprising:

[0006] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0007] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0008] In one embodiment, a first voltage signal is input to a wear condition monitoring model to identify the working state of the first joint simulation structure, thereby obtaining the current working state of the first joint simulation structure, including:

[0009] The first voltage signal is input into the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0010] The feature map is input into the pooling layer to compress the feature dimension, resulting in a low-dimensional feature map.

[0011] The low-dimensional feature map is input into the feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained by using the output layer.

[0012] In one embodiment, a low-dimensional feature map is input to a feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained using the output layer, including:

[0013] The low-dimensional feature map is converted into a one-dimensional feature vector based on the flattening layer;

[0014] The one-dimensional feature vector is fused through a fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer.

[0015] In one embodiment, the wear condition monitoring model includes:

[0016] The second voltage signal output by the second identifier in the joint of the second artificial joint structure is collected under various working conditions, and all the collected second voltage signals are used as sample data; the various working conditions include normal working state, high load working state, high friction frequency working state and coating peeling state;

[0017] The sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

[0018] In one embodiment, an initial wear condition monitoring model is trained based on a training set and a validation set to obtain a wear condition monitoring model, including:

[0019] The initial wear state monitoring model is trained in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is generated by fitting.

[0020] The wear status monitoring model after each round of training is tested based on the validation set, and a second accuracy curve is generated after each round of testing.

[0021] The first accuracy curve and the second accuracy curve are compared until they coincide, at which point training stops and the wear condition monitoring model is obtained.

[0022] In one embodiment, the method for monitoring the wear condition of the artificial joint further includes:

[0023] In response to a query request sent by the terminal, information containing the current working status of the first joint simulation structure is sent to the terminal to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure.

[0024] Secondly, this application also provides a monitoring system for the wear and tear of artificial joints, comprising:

[0025] The system includes a host computer, a first artificial joint structure, and a terminal. The first artificial joint structure includes a first joint simulation structure and a first identifier. The host computer is connected to the first identifier and the terminal via a network. The terminal is connected to the first identifier via a network. The first identifier is located inside the first joint simulation structure.

[0026] The host computer is used to implement methods for monitoring the wear and tear of artificial joints.

[0027] Thirdly, this application also provides a device for monitoring the wear and tear of artificial joints, comprising:

[0028] The acquisition module is used to acquire the first voltage signal output by the recognizer when the sphere structure and the plate structure in the first joint simulation structure move relative to each other.

[0029] The identification module is used to input the first voltage signal into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure.

[0030] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0031] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0032] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0033] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0034] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0035] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0036] Sixthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0037] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0038] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0039] The aforementioned method, system, device, storage medium, and program product for monitoring the wear state of artificial joints acquire a first voltage signal output by a recognizer when the spherical structure and plate structure in the first joint simulation structure move relative to each other. This first voltage signal is then input into a wear state monitoring model to identify the working state of the first joint simulation structure, thus obtaining its current working state. The wear state monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions. This method not only improves the adaptability of the wear state monitoring model to different joint structures and complex working conditions by utilizing various types of artificial joint samples and training data covering all working conditions, ensuring the accuracy and reliability of the artificial joint wear state identification results, but also achieves real-time monitoring of the joint's working state by directly capturing the voltage signal of the relative movement of the spherical structure and plate structure. This effectively solves the problem of inefficient and accurate perception of the wear state of artificial joint structures, providing scientific and reliable technical support for timely maintenance, fault warning, and service life assessment of joint structures. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of a method for monitoring the wear and tear of artificial joints in one embodiment;

[0042] Figure 2 This is a fabrication diagram of the first identifier in one embodiment;

[0043] Figure 3 This is one of the flowcharts illustrating a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0044] Figure 4 This is a schematic diagram illustrating the working principle of the first identifier in one embodiment;

[0045] Figure 5 The output voltage diagram of the first identifier under different operating loads in one embodiment;

[0046] Figure 6 The output voltage diagram of the first identifier at different operating frequencies in one embodiment is shown.

[0047] Figure 7 This is a graph showing the output voltage change before and after the coating peels off from the artificial joint in one embodiment.

[0048] Figure 8 This is a construction diagram of a wear condition monitoring model in one embodiment;

[0049] Figure 9 This is a second schematic flowchart of a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0050] Figure 10 This is the third flowchart illustrating a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0051] Figure 11 This is a fourth flowchart illustrating a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0052] Figure 12 This is the fifth flowchart illustrating a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0053] Figure 13 This is a graph showing the accuracy and loss rate of the training process for a wear condition monitoring model in one embodiment.

[0054] Figure 14 This is a confusion matrix diagram output by the wear condition monitoring model in one embodiment;

[0055] Figure 15 This is a flowchart of a method for monitoring the wear and tear of an artificial joint in one embodiment, shown in diagram six.

[0056] Figure 16 This is a diagram illustrating the setup of an intelligent wireless identification system in one embodiment.

[0057] Figure 17 This is the seventh flowchart illustrating a method for monitoring the wear and tear of an artificial joint in one embodiment;

[0058] Figure 18 This is a structural block diagram of a device for monitoring the wear status of an artificial joint in one embodiment;

[0059] Figure 19 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0062] With the increasing use of artificial joint replacement surgery in the treatment of end-stage joint diseases, the number of patients undergoing joint replacement worldwide continues to rise annually. The long-term effectiveness and safety of artificial joints have become one of the core issues of clinical concern. However, during long-term use, artificial joints are prone to wear and tear due to repeated friction and impact loads on the joint surfaces. The particles generated by this wear can trigger periprosthetic inflammation and even lead to serious complications such as prosthesis loosening and subsidence, directly impacting the patient's quality of life and the lifespan of the prosthesis.

[0063] Traditional methods for monitoring wear and tear on artificial joints often involve implanting sensors or electronic modules into the prosthesis or surrounding tissues. However, this method relies on external power and is difficult to operate stably for extended periods.

[0064] In view of the above-mentioned technical problems, this application provides a method for monitoring the wear and tear of artificial joints. The following embodiments will specifically illustrate the method for monitoring the wear and tear of artificial joints.

[0065] The method for monitoring the wear and tear of artificial joints provided in this application can be applied to, for example... Figure 1The system shown is a monitoring system for the wear and tear of an artificial joint. The system includes a first artificial joint structure 101, a host computer 102, and a terminal 103. The first artificial joint structure 101 includes a first joint simulation structure 104 and a first identifier 105. The host computer 102 is connected to the first identifier 105 and the terminal 103 via a network. The first identifier 105 is located within the first joint simulation structure 104. The first artificial joint structure 101 includes a spherical structure (positively charged) and a plate-like structure (negatively charged). The first identifier 105 in the plate-like structure can be embedded into the plate-like structure (such as an acetabular cup structure in an artificial hip joint) through a graded sintering process (such as multi-layer sintering, insulating layer stacking, and structural layer forming). Figure 2 As shown. The first identifier 105 includes an EAP32 chip and a data acquisition module. The data acquisition module collects voltage signals generated when spherical and plate-like structures slide relative to each other under load, and transmits them to the ESP32 chip and the wear condition monitoring model for signal analysis under different conditions. When the first identifier receives a query request from the terminal 103, it transmits the voltage signal to the ESP32 chip for signal analysis. The ESP32 chip integrates a quantized wear condition monitoring model and a Bluetooth communication module. The ESP32 chip establishes a connection with the terminal 103 through the Bluetooth communication module using the analysis results obtained from the quantized wear condition monitoring model, and displays the analysis results on the terminal 103. When the first identifier does not receive a query request from the terminal 103, it can transmit the voltage signal to the wear condition monitoring model in the host computer 102 in real time for signal analysis. The host computer 102 also integrates functional areas. The functional areas include: a real-time signal display area, used to continuously plot the waveform of the output voltage of the first recognizer 105 over time, facilitating observation of the differences in signals under different loads, frequencies, and wear conditions; a recognition process and control area, used to display the current recognition result and its confidence level, and provide control buttons for starting, pausing, and terminating recognition; and an artificial joint working status display area, which uses text, color labels, or icons to indicate in real time whether the joint is in a normal, high-load, high-frequency friction, or coating peeling condition.

[0066] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the monitoring system for the wear state of artificial joints to which the present application is applied. The specific control system may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0067] In one exemplary embodiment, such as Figure 3As shown, a method for monitoring the wear and tear of artificial joints is provided, which can be applied to... Figure 1 Taking the host computer in the example, the explanation includes:

[0068] S201, when the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired.

[0069] Among them, the first joint simulation structure refers to the artificial joint simulation structure in actual application, including but not limited to important joint parts such as hip joint, knee joint and shoulder joint, as well as other joint prostheses or motion joint components that require long-term friction state monitoring; the identifier refers to the artificial joint friction and wear identifier; the spherical structure refers to a highly polished metal sphere, such as a steel ball; the plate structure refers to a hemispherical or slightly deep cup-shaped object that can bear all the loads from the spherical structure, such as ultra-high molecular weight polyethylene (UHMWPE) gaskets.

[0070] In this embodiment, an artificial joint friction and wear detector designed based on triboelectricity and electrostatic induction effects is embedded into a plate structure within a first joint simulation structure using a graded sintering process. During simulated joint movement, the spherical structure and plate structure in the first joint simulation structure move relative to each other under load. Due to triboelectricity, the surface of the spherical structure carries a positive charge, while the surface of the plate structure carries an equal amount of negative charge. The spherical structure has good conductivity, and the positive charge concentrates near the contact area under electrostatic induction, while the negative charge on the surface of the plate structure is basically uniformly distributed across the entire friction surface. The copper electrode below the contact area carries a negative charge under electrostatic induction, while the electrodes at other locations carry a relatively positive charge, creating a potential difference between them. When the potential difference changes, the charge flows back and forth in the external circuit, outputting an alternating current signal (e.g., [missing information]) with a certain frequency and amplitude. Figure 4 As shown in the figure, that is, the first voltage signal. Finally, the recognizer transmits the first voltage signal to the host computer through the network for feature extraction and analysis to determine the current working state of the first joint simulation structure.

[0071] S202, the first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure.

[0072] Among them, the wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions, such as ball-and-socket joints, sliding joints, planar joints and saddle joints.

[0073] In this embodiment, because the first voltage signal and current output by the identifier exhibit a regular response to changes in load and frequency under different normal loads and friction frequencies (e.g., Figure 5 and Figure 6 As shown), during long-term friction, wear particles are generated on the plate structure and enter the contact interface, or the coating peels off. This alters the interface charge distribution and local electric field structure, causing systematic changes in the overall amplitude and local waveform characteristics of the identifier's output signal. This manifests as a significant voltage decrease or a recognizable change in the waveform morphology (e.g., ...). Figure 7 (As shown). By analyzing these changes, the host computer can determine the current working state of the first joint simulation structure. Therefore, when the host computer receives the first voltage signal transmitted by the artificial joint friction and wear identifier integrated in the first joint simulation structure, it imports the first voltage signal into the pre-trained wear state monitoring model in real time for state identification. First, the wear state monitoring model preprocesses and extracts features from the original voltage signal. Through the neural network or machine learning model inside the wear state monitoring model, it mines and processes the deep spatiotemporal features related to friction and wear in the first voltage signal, such as waveform periodicity, amplitude modulation, harmonic distortion, and transient pulse signal features. These signal features can characterize the dynamic changes of the contact interface between the sphere structure and the plate structure during relative motion. Subsequently, the wear state monitoring model fuses and discriminates the extracted signal features and outputs the probability distribution of the first joint simulation structure belonging to each preset working state. Finally, the host computer can accurately obtain the current working state of the first joint simulation structure through this probability distribution.

[0074] In the aforementioned method for monitoring the wear state of artificial joints, a first voltage signal output by the recognizer is acquired when the spherical structure and plate structure in the first joint simulation structure move relative to each other. This first voltage signal is then input into the wear state monitoring model to identify the working state of the first joint simulation structure, thus obtaining its current working state. The wear state monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions. This method not only improves the adaptability of the wear state monitoring model to different joint structures and complex working conditions by utilizing various types of artificial joint samples and training data covering all working conditions, ensuring the accuracy and reliability of the artificial joint wear state identification results, but also achieves real-time monitoring of the joint's working state by directly capturing the voltage signal of the relative movement of the spherical structure and plate structure. This effectively solves the problem of inefficient and accurate perception of the wear state of artificial joint structures, providing scientific and reliable technical support for timely maintenance, fault warning, and service life assessment of joint structures. In an exemplary embodiment, the wear state monitoring model includes an input layer, a convolutional layer, a pooling layer, a feature fusion unit, and an output layer (such as...). Figure 8 As shown), in the above S202, "the first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure, and the current working state of the first joint simulation structure is obtained," as shown in the example. Figure 9 As shown, it includes:

[0075] S301, the first voltage signal is input to the convolutional layer through the input layer to obtain the feature map of the first voltage signal.

[0076] In this embodiment, the wear condition monitoring model is mainly constructed using a one-dimensional convolutional neural network (1D-CNN). The host computer transmits the voltage signal output by the artificial joint friction and wear identifier to the computer in real time via a data acquisition module. First, in the preprocessing module, noise reduction, normalization, and windowing are performed. For example, the first voltage signal is divided into several segments according to a time window (e.g., 1 second), and each segment is input as a one-dimensional signal into the input layer of the 1D-CNN. The input layer receives and preprocesses the first voltage signal, transforming it into the standard one-dimensional voltage signal format in the 1D-CNN. Subsequently, the host computer inputs the standard one-dimensional voltage signal format into the convolutional layer. The convolutional layer automatically extracts local features closely related to friction and wear from each signal segment, such as oscillation patterns at specific frequencies, transient pulse morphologies, and periodic modulation patterns, using multiple sliding convolutional kernels. Finally, the convolutional layer outputs multiple feature maps that can express the inherent patterns of the voltage signal, thus obtaining the feature map of the first voltage signal.

[0077] S302, the feature map is input into the pooling layer to compress the feature dimension and obtain a low-dimensional feature map.

[0078] In this embodiment, the host computer inputs the feature map of the first voltage signal into the pooling layer and performs local downsampling on the feature map using algorithms such as max pooling or average pooling. The feature map is divided into multiple non-overlapping local windows, and the most representative feature data (such as the maximum or average value in each local window) is extracted from each local window, thereby performing feature compression in the spatiotemporal dimension of the feature map and finally obtaining a low-dimensional feature map.

[0079] S303: Input the low-dimensional feature map into the feature fusion unit for feature fusion, and use the output layer to obtain the current working state of the first joint simulation structure.

[0080] In this embodiment, the host computer inputs the low-dimensional feature map output from the pooling layer to the feature fusion unit for feature fusion. For example, the feature fusion unit can combine two features—a periodic signal of a specific frequency and a transient pulse of a specific shape—to indicate a slightly worn working state. Subsequently, the host computer inputs the feature representation obtained by the feature fusion unit to the output layer. The output layer maps multiple fused features to a preset category space and calculates the probability distribution of the first joint simulation structure belonging to each possible working state (such as normal, slightly worn, severely worn, or critically failed). The host computer selects the category with the highest probability as the recognition result, thereby obtaining the current working state of the first joint simulation structure.

[0081] In an exemplary embodiment, the feature fusion unit includes a flattening layer and a fully connected layer. The statement in S303 above, "inputting the low-dimensional feature map to the feature fusion unit for feature fusion, and using the output layer to obtain the current working state of the first joint simulation structure," is as follows: Figure 10 As shown, it includes:

[0082] S401 converts the low-dimensional feature map into a one-dimensional feature vector based on the flattening layer.

[0083] In this embodiment, the host computer inputs multiple low-dimensional feature maps into a flattening layer for structural transformation. That is, by sequentially splicing multiple low-dimensional feature maps, the multiple low-dimensional feature maps are recombined into a continuous one-dimensional feature vector. The length of the one-dimensional feature vector is equal to the product of all elements in the multiple low-dimensional feature maps, and contains a complete set of all local features extracted and compressed by the convolutional layer and the pooling layer.

[0084] S402 performs feature fusion on the one-dimensional feature vector through a fully connected layer, and uses the output layer to obtain the current working state of the first joint simulation structure.

[0085] In this embodiment, the host computer inputs a one-dimensional feature vector into a fully connected layer for feature fusion. The fully connected layer uses its internal weight matrix and bias vector to perform a weighted summation of all elements in the one-dimensional feature vector, and introduces nonlinearity through an activation function (such as ReLU) to fuse the combination relationships between all feature vectors. Subsequently, the host computer inputs the fused feature vector into the output layer. The output layer uses a linear activation function to map the fused feature vector into the original scores of each working state. Finally, the Softmax function in the output layer normalizes the original scores of each working state, converting them into probability distributions corresponding to each working state. Each probability value represents the confidence level of the first joint simulation structure belonging to the corresponding working state (such as normal, slight wear, severe wear, critical failure). The host computer selects the working state corresponding to the highest probability to obtain the current working state of the first joint simulation structure and displays the current working state on the monitoring interface.

[0086] In an exemplary embodiment, the "wear condition monitoring model" in S202 above, such as Figure 11 As shown, it includes:

[0087] S501 collects the second voltage signal output by the second identifier in the second artificial joint structure under various working conditions, and uses all the collected second voltage signals as sample data.

[0088] The various operating conditions include normal operating condition, high load operating condition, high friction frequency operating condition, and coating peeling condition.

[0089] In this embodiment, under normal working conditions (NS, load 50 N, frequency 0.5 Hz), high load working conditions (HL, load 100 N, frequency 0.5 Hz), high friction frequency working conditions (HF, load 50 N, frequency 1.0 Hz), and coating peeling conditions (CD, load 50 N, frequency 0.5 Hz, and obvious wear particles at the contact interface), the data acquisition module collects the second voltage signal output by the second recognizer in the joint of the second artificial joint structure, and uses the collected second voltage signal as sample data for iterative training of the 1D-CNN model on the TensorFlow platform.

[0090] S502, the sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

[0091] In this embodiment, the sample data is divided into a training set and a validation set according to a preset ratio, such as 70% training set and 30% validation set, and the initial wear state monitoring model is trained based on the training set and validation set. The host computer uses the training set to iteratively train the initial wear state monitoring model (i.e., the untrained 1D-CNN model). In each training iteration, the 1D-CNN outputs a prediction result based on the input training set samples, and calculates the error between the predicted value and the true state label using a loss function (such as cross-entropy loss); the optimizer (such as Adam) performs backpropagation based on the error, updating all trainable parameters of the 1D-CNN (such as convolutional kernel weights and fully connected layer weights) to minimize the loss. Then, the host computer uses the validation set to evaluate the performance of the current 1D-CNN model, and stops training when the performance is optimal, thus obtaining the wear state monitoring model.

[0092] In an exemplary embodiment, the phrase "training the initial wear condition monitoring model based on the training set and validation set to obtain the wear condition monitoring model" in S502 above is as follows: Figure 12 As shown, it includes:

[0093] S601 performs multiple rounds of training on the initial wear condition monitoring model. During the multiple rounds of training, the initial wear condition monitoring model is trained on the training set for each round, and the first accuracy curve after each round of training is generated by fitting.

[0094] In this embodiment, the host computer inputs sample data from the training set into the initial wear state monitoring model for training, and predicts the output results through forward propagation, using a loss function to quantify the difference between the predicted value and the true label. Subsequently, all trainable parameters, such as convolutional kernels and fully connected layer weights, are optimized and updated using a backpropagation algorithm and an optimizer (such as Adam) to minimize the loss function. As the number of training rounds increases, the initial wear state monitoring model gradually learns and fits the mapping relationship from voltage signal to wear state in the training data. Simultaneously, after each round, the host computer uses sample data from the same training set to evaluate the performance of the initial wear state monitoring model for the current round, and generates the first accuracy curve after training for the current round.

[0095] S602 tests the wear status monitoring model after each round of training based on the validation set, and fits and generates a second accuracy curve after each round of testing.

[0096] In this embodiment, after the parameters of the initial wear state monitoring model based on the training set are updated in each round, the host computer immediately performs a performance test on the initial wear state monitoring model for the current round based on the validation set. In each round of testing, the initial wear state monitoring model performs forward propagation inference on all samples in the validation set, compares its output predicted state with the true label, and thus calculates the recognition accuracy of the initial wear state monitoring model on the validation set for that round. Simultaneously, after each round, the host computer fits and generates a second accuracy curve after the current round of testing.

[0097] S603, compare the first accuracy curve and the second accuracy curve until the first accuracy curve and the second accuracy curve coincide, then stop training and obtain the wear condition monitoring model.

[0098] In this embodiment, the host computer compares and monitors the first accuracy curve and the second accuracy curve in real time. When the loss function continues to decrease and the first accuracy curve and the second accuracy curve basically overlap, no obvious overfitting occurs (e.g., Figure 13 As shown); while the confusion matrix on the independent test set shows that the overall recognition accuracy can reach 99.91% (as shown). Figure 14 As shown in the figure, the four states of normal, high load, high frequency, and coating peeling are basically completely distinguishable. At this point, the host computer stops training the initial wear state monitoring model and selects the initial wear state monitoring model with stable performance at the end of the training period (which is also the historical high point of the validation set) as the wear state monitoring model.

[0099] In one exemplary embodiment, Figure 3 The specific implementation of S202 in the embodiment, "inputting the first voltage signal into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure," is as follows: Figure 15 As shown, it includes: in response to a query request sent by the terminal, sending information containing the current working status of the first joint simulation structure to the terminal, so as to instruct the terminal to display the current working status of the first joint simulation structure on the application.

[0100] The query request is used to query the working status of the first joint simulation structure.

[0101] In this embodiment, the voltage signal output by the artificial joint friction and wear detector is filtered and amplified by the front-end conditioning circuit, and then sampled by the data acquisition module on the ESP32 chip. The sampled digital signal undergoes simple preprocessing inside the chip before being input into a quantized or simplified 1D-CNN model, thereby achieving local real-time working condition recognition (e.g., Figure 16As shown in the image, after processing, the ESP32 can directly provide the classification result of the current working condition and the necessary confidence information. When the artificial joint friction and wear identifier receives a query request from the terminal, the ESP32 can use its integrated Bluetooth communication module to send the identification result and status flag to the mobile terminal in the form of low-power data packets. The dedicated wireless monitoring application on the mobile terminal can establish a stable Bluetooth connection with the ESP32, receive the artificial joint working status data in real time, and display the current status clearly on the interface. When the artificial joint is in normal working condition, the application continuously displays "Status Normal" and optionally records the status change curve and time axis information. When the artificial joint wear status monitoring system identifies abnormal working conditions, such as long-term high-load operation, abnormal frequency increase, or significant signal changes caused by coating peeling, the ESP32 immediately sends an abnormality flag. The application issues warnings to patients and doctors by popping up prompt boxes, changing interface colors, or emitting sounds and vibrations, prompting them to seek medical attention in time or conduct further imaging examinations and professional evaluations.

[0102] In summary, based on all the above embodiments, a method for monitoring the wear and tear of artificial joints is also provided, such as... Figure 17 As shown, the method includes:

[0103] S701, when the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0104] S702, input the first voltage signal into the wear condition monitoring model to identify the working state of the first joint simulation structure; execute S708-S711 to train the wear condition monitoring model;

[0105] S703, the first voltage signal is input to the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0106] S704: Input the feature map into the pooling layer to compress the feature dimension and obtain a low-dimensional feature map;

[0107] S705 converts low-dimensional feature maps into one-dimensional feature vectors based on the flattening layer;

[0108] S706, the one-dimensional feature vector is fused through a fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer;

[0109] S707, in response to the query request sent by the terminal, sends information containing the current working status of the first joint simulation structure to the terminal, so as to instruct the terminal to display the current working status of the first joint simulation structure in the application;

[0110] S708, collects the second voltage signal output by the second identifier in the second artificial joint structure under various working conditions, and uses all the collected second voltage signals as sample data;

[0111] S709 performs multiple rounds of training on the initial wear state monitoring model. During the multiple rounds of training, the initial wear state monitoring model is trained on the training set for each round, and the first accuracy curve after each round of training is fitted and generated.

[0112] S710 tests the wear status monitoring model after each round of training based on the validation set, and fits and generates a second accuracy curve after each round of testing.

[0113] S711, compare the first accuracy curve and the second accuracy curve until the first accuracy curve and the second accuracy curve coincide, then stop training and obtain the wear condition monitoring model.

[0114] The methods described in each of the above steps have been described in the foregoing embodiments. For details, please refer to the foregoing descriptions. They will not be repeated here.

[0115] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0116] Based on the same inventive concept, this application also provides a system for monitoring the wear condition of an artificial joint to implement the aforementioned method for monitoring the wear condition of an artificial joint. The structural schematic diagram of this system is the same as described above. Figure 1 The structural diagram of the artificial joint wear monitoring system shown is basically the same; for detailed structure, please refer to the aforementioned diagram. Figure 1 The diagram shows the structure of a system for monitoring the wear and tear of artificial joints. For an explanation of the working principle of this system, please refer to the previous section. Figures 2-17 The method for monitoring the wear and tear of artificial joints as described in any embodiment is not elaborated here.

[0117] Based on the same inventive concept, this application also provides an artificial joint wear condition monitoring device for implementing the above-described artificial joint wear condition monitoring method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more artificial joint wear condition monitoring device embodiments provided below can be found in the limitations of the artificial joint wear condition monitoring method described above, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 18 As shown, a device for monitoring the wear and tear of an artificial joint is provided, comprising:

[0119] The acquisition module 11 is used to acquire the first voltage signal output by the recognizer when the sphere structure and the plate structure in the first joint simulation structure move relative to each other.

[0120] The identification module 12 is used to input the first voltage signal into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure.

[0121] In one embodiment, the identification module 12 includes:

[0122] The first recognition unit is used to input the first voltage signal into the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0123] The second recognition unit is used to input the feature map into the pooling layer to compress the feature dimension and obtain a low-dimensional feature map.

[0124] The third recognition unit is used to input the low-dimensional feature map into the feature fusion unit for feature fusion, and use the output layer to obtain the current working state of the first joint simulation structure.

[0125] In one embodiment, the third identification unit includes:

[0126] The first fusion subunit is used to convert the low-dimensional feature map into a one-dimensional feature vector based on the flattening layer;

[0127] The second fusion subunit is used to fuse one-dimensional feature vectors through a fully connected layer and use the output layer to obtain the current working state of the first joint simulation structure.

[0128] In one embodiment, the above-mentioned monitoring device for the wear and tear of artificial joints further includes a training module 13:

[0129] The acquisition unit is used to acquire the second voltage signal output by the second identifier in the joint of the second artificial joint structure under various working conditions, and to use all the acquired second voltage signals as sample data; the various working conditions include normal working condition, high load working condition, high friction frequency working condition and coating peeling condition.

[0130] The partitioning unit is used to divide the sample data into a training set and a validation set, and to train the initial wear condition monitoring model based on the training set and the validation set to obtain the wear condition monitoring model.

[0131] In one embodiment, the above-mentioned dividing unit includes:

[0132] The first sub-unit is used to train the initial wear state monitoring model in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is generated by fitting.

[0133] The second partitioning subunit is used to test the wear state monitoring model after each round of training based on the validation set, and to fit and generate the second accuracy curve after each round of testing.

[0134] The third sub-unit is used to compare the first accuracy curve and the second accuracy curve until the first accuracy curve and the second accuracy curve coincide, at which point training stops and the wear condition monitoring model is obtained.

[0135] In one embodiment, the above-mentioned monitoring device for the wear and tear of the artificial joint further includes a display module 14:

[0136] Display module 14 is used to respond to a query request sent by the terminal and send information containing the current working status of the first joint simulation structure to the terminal, so as to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure.

[0137] Each module in the aforementioned artificial joint wear monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0138] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 19As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for monitoring the wear and tear of artificial joints. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0139] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0140] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0141] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0142] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0143] The first voltage signal is input into the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0144] The feature map is input into the pooling layer to compress the feature dimension, resulting in a low-dimensional feature map.

[0145] The low-dimensional feature map is input into the feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained by using the output layer.

[0146] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0147] The low-dimensional feature map is converted into a one-dimensional feature vector based on the flattening layer;

[0148] The one-dimensional feature vector is fused through a fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer.

[0149] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0150] The second voltage signal output by the second identifier in the joint of the second artificial joint structure is collected under various working conditions, and all the collected second voltage signals are used as sample data; the various working conditions include normal working state, high load working state, high friction frequency working state and coating peeling state;

[0151] The sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0153] The initial wear state monitoring model is trained in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is generated by fitting.

[0154] The wear status monitoring model after each round of training is tested based on the validation set, and a second accuracy curve is generated after each round of testing.

[0155] The first accuracy curve and the second accuracy curve are compared until they coincide, at which point training stops and the wear condition monitoring model is obtained.

[0156] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0157] In response to a query request sent by the terminal, information containing the current working status of the first joint simulation structure is sent to the terminal to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure. In one embodiment, when the processor executes the computer program, it further implements the following steps:

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0159] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0160] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0161] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0162] The first voltage signal is input into the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0163] The feature map is input into the pooling layer to compress the feature dimension, resulting in a low-dimensional feature map.

[0164] The low-dimensional feature map is input into the feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained by using the output layer.

[0165] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0166] The low-dimensional feature map is converted into a one-dimensional feature vector based on the flattening layer;

[0167] The one-dimensional feature vector is fused through a fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer.

[0168] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0169] The second voltage signal output by the second identifier in the joint of the second artificial joint structure is collected under various working conditions, and all the collected second voltage signals are used as sample data; the various working conditions include normal working state, high load working state, high friction frequency working state and coating peeling state;

[0170] The sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

[0171] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0172] The initial wear state monitoring model is trained in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is generated by fitting.

[0173] The wear status monitoring model after each round of training is tested based on the validation set, and a second accuracy curve is generated after each round of testing.

[0174] The first accuracy curve and the second accuracy curve are compared until they coincide, at which point training stops and the wear condition monitoring model is obtained.

[0175] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0176] In response to a query request sent by the terminal, information containing the current working status of the first joint simulation structure is sent to the terminal to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure.

[0177] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0178] When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired;

[0179] The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure. The wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

[0180] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0181] The first voltage signal is input into the convolutional layer through the input layer to obtain the feature map of the first voltage signal;

[0182] The feature map is input into the pooling layer to compress the feature dimension, resulting in a low-dimensional feature map.

[0183] The low-dimensional feature map is input into the feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained by using the output layer.

[0184] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0185] The low-dimensional feature map is converted into a one-dimensional feature vector based on the flattening layer;

[0186] The one-dimensional feature vector is fused through a fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer.

[0187] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0188] The second voltage signal output by the second identifier in the joint of the second artificial joint structure is collected under various working conditions, and all the collected second voltage signals are used as sample data; the various working conditions include normal working state, high load working state, high friction frequency working state and coating peeling state;

[0189] The sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

[0190] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0191] The initial wear state monitoring model is trained in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is generated by fitting.

[0192] The wear status monitoring model after each round of training is tested based on the validation set, and a second accuracy curve is generated after each round of testing.

[0193] The first accuracy curve and the second accuracy curve are compared until they coincide, at which point training stops and the wear condition monitoring model is obtained.

[0194] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0195] In response to a query request sent by the terminal, information containing the current working status of the first joint simulation structure is sent to the terminal to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure.

[0196] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0197] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0198] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring the wear and tear of artificial joints, characterized in that, A host computer is used in a monitoring system, the monitoring system further includes a first artificial joint structure and a terminal, the first artificial joint structure includes a first joint simulation structure and a first identifier, and the method includes: When the sphere structure and plate structure in the first joint simulation structure move relative to each other, the first voltage signal output by the recognizer is acquired. The first voltage signal is input into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure; the wear condition monitoring model is pre-trained based on sample data of various types of second artificial joint structures under various working conditions.

2. The method according to claim 1, characterized in that, The wear state monitoring model includes an input layer, a convolutional layer, a pooling layer, a feature fusion unit, and an output layer. The step of inputting the first voltage signal into the wear state monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure includes: The first voltage signal is input to the convolutional layer through the input layer to obtain the feature map of the first voltage signal; The feature map is input into the pooling layer to compress the feature dimension, resulting in a low-dimensional feature map. The low-dimensional feature map is input into the feature fusion unit for feature fusion, and the current working state of the first joint simulation structure is obtained using the output layer.

3. The method according to claim 2, characterized in that, The feature fusion unit includes a flattening layer and a fully connected layer. The step of inputting the low-dimensional feature map into the feature fusion unit for feature fusion and using the output layer to obtain the current working state of the first joint simulation structure includes: The low-dimensional feature map is converted into a one-dimensional feature vector based on the flattening layer; The one-dimensional feature vector is fused through the fully connected layer, and the current working state of the first joint simulation structure is obtained using the output layer.

4. The method according to claim 1, characterized in that, The method further includes: The second voltage signal output by the second identifier in the joint of the second artificial joint structure is collected under various working conditions, and all the collected second voltage signals are used as sample data; the various working conditions include normal working state, high load working state, high friction frequency working state, and coating peeling state; The sample data is divided into a training set and a validation set, and the initial wear condition monitoring model is trained based on the training set and the validation set to obtain the wear condition monitoring model.

5. The method according to claim 4, characterized in that, The step of training the initial wear state monitoring model based on the training set and validation set to obtain the wear state monitoring model includes: The initial wear state monitoring model is trained in multiple rounds. During the training process, the initial wear state monitoring model is trained in each round based on the training set, and the first accuracy curve after each round of training is fitted and generated. Based on the validation set, the wear status monitoring model after each round of training is tested in each round, and a second accuracy curve is generated after each round of testing. The first accuracy curve and the second accuracy curve are compared until they coincide, at which point training stops and the wear condition monitoring model is obtained.

6. The method according to claim 1, characterized in that, The method further includes: In response to a query request sent by the terminal, information containing the current working status of the first joint simulation structure is sent to the terminal to instruct the terminal to display the current working status of the first joint simulation structure in the application; the query request is used to query the working status of the first joint simulation structure.

7. A system for monitoring the wear and tear of an artificial joint, characterized in that, The monitoring system includes: a host computer, a first artificial joint structure, and a terminal. The first artificial joint structure includes a first joint simulation structure and a first identifier. The host computer is connected to the first identifier via a network, and the terminal is connected to the first identifier via a network. The first identifier is disposed within the first joint simulation structure. The host computer is used to execute the method as described in any one of claims 1-6.

8. A device for monitoring the wear and tear of an artificial joint, characterized in that, The device includes: The acquisition module is used to acquire the first voltage signal output by the recognizer when the sphere structure and the plate structure in the first joint simulation structure move relative to each other. The identification module is used to input the first voltage signal into the wear condition monitoring model to identify the working state of the first joint simulation structure and obtain the current working state of the first joint simulation structure.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images