Multi-parameter sensing and repairing process monitoring method for absorbable biological material

Abstract

The invention relates to the technical field of medical intelligent decision making, in particular to a multi-parameter sensing and repairing process monitoring method for an absorbable biological material. State parameters such as the temperature, the pH value, the stress, the strain and the conductivity of the absorbable biological material are collected in real time through the skin patch sensor and the implantable biocompatible sensor, different stages of the repair process can be accurately recognized in combination with data processing and analysis, the repair process can be effectively optimized, the repair effect can be improved, and the repair cost can be reduced. A potential problem caused by an inaccurate repairing process is avoided; multi-sensor data acquisition and efficient data fusion technologies are adopted, the degradation process and tissue repair conditions of the repair material are accurately mastered through multi-dimensional monitoring, the conditions of abnormal degradation or local instability and the like of the repair material are found in time, it is ensured that the degradation process of the repair material is accurately controlled, and the repair effect is guaranteed to the maximum extent.

Description

Technical Field

[0001] The present invention relates to the field of medical intelligent decision-making technology, and in particular to a multi-parameter sensing and repair process monitoring method for absorbable biomaterials. Background Art

[0002] In the field of medicine and biomedicine, absorbable biomaterials are widely used in various repair processes, especially in fracture repair, trauma treatment, soft tissue repair, etc. Absorbable biomaterials can gradually degrade during the repair process and be naturally absorbed by the human body, avoiding the problem of secondary surgery for removal caused by traditional materials. Common absorbable biomaterials include: absorbable sutures, bone filling materials, silicone, absorbable steel nails, etc.

[0003] However, although absorbable biomaterials have been widely used in medical repair, in actual application, how to accurately monitor their repair process, especially in the process of degradation, absorption and tissue integration, is still a difficult problem. Traditional monitoring methods mainly rely on regular X-ray examinations, CT scans or MRI examinations, and these methods have the following limitations:

[0004] First, traditional monitoring methods cannot monitor the degradation process of materials in real time and can only indirectly reflect the progress of restoration through imaging methods.

[0005] Secondly, traditional monitoring methods only focus on the image information after restoration, ignoring important parameters such as biophysical and chemical changes during material degradation, such as temperature, pH, stress and strain.

[0006] Finally, traditional monitoring methods have difficulty in timely identifying anomalies generated during material absorption and lack timely intervention and optimization strategies.

[0007] In view of the above problems, it is necessary to propose a multi-parameter sensing and repair process monitoring method for absorbable biomaterials. Summary of the invention

[0008] The purpose of the present invention is to solve the problems existing in the background technology and to propose a multi-parameter sensing and repair process monitoring method for absorbable biomaterials.

[0009] The purpose of the present invention can be achieved through the following technical solutions:

[0010] A multi-parameter sensing and repair process monitoring method for absorbable biomaterials comprises the following steps:

[0011] Step 1: Environmental parameter collection and preprocessing;

[0012] The state parameters of the absorbable biomaterial are collected by using skin patch sensors and implantable biocompatible sensors, and the state parameters include temperature, pH value, stress, strain and conductivity.

[0013] At preset time intervals, the original data of the state parameters of the skin patch sensor and the implantable biocompatible sensor are collected through wireless transmission, and the collected original data of the state parameters are transmitted to the computer, and the pre-processed state parameters are obtained through noise and signal smoothing processing.

[0014] The noise and signal smoothing process is specifically as follows:

[0015] The original data of temperature, pH value, stress, strain and conductivity collected at each preset time interval t are collected and recorded as the original data set. , and input it into the Gaussian filter to balance the signal and remove the high-frequency noise. The core operation formula of the Gaussian filter is: ;in is a set of preprocessed state parameters obtained after Gaussian filtering operation, including preprocessed temperature, pH value, stress, strain and conductivity; σ is the preset filter standard deviation, which is used to control the degree of smoothing; N is the size of the preset sliding window, that is, the number of neighboring data points considered around the current data point t, which is used to control the reference range of the Gaussian filter; i is the original data index, which is used to formulate the specific number of the reference value of the original data in the Gaussian filter in the current window; t is the time index of the current data point, that is, the position of the current data point being processed by the Gaussian filter.

[0016] The set of preprocessed state parameters obtained after Gaussian filtering Send it to the data processing center for further data fusion and feature extraction analysis.

[0017] Step 2: Feature extraction analysis and data fusion;

[0018] Feature extraction and data fusion are performed on the set of preprocessed state parameters, and preset values ​​are matched according to the data fusion results to evaluate the state of the absorbable biomaterial.

[0019] PCA principal component analysis is used to perform data feature extraction operations. The specific process is as follows:

[0020] Extract the set of preprocessed state parameters The state parameters in the equation include temperature, pH value, stress, strain and conductivity, and are input into the standardized formula The standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t) are obtained; is the mean of the state parameter sub-items, including the mean of temperature, pH value, stress, strain and conductivity; is the standard deviation of the state parameter items, including the standard deviation of temperature, pH value, stress, strain and conductivity; is the state parameter item obtained after standardization. Where t is the data collection time.

[0021] For the standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t), the formula Calculate the covariance matrix C, where m is the number of samples; and is the data matrix of state parameters and the transposed matrix of the data matrix. ; Calculate the eigenvalue λ and eigenvector v of the covariance matrix C. Among them, the eigenvalue λ represents the variance of each principal component represented by the eigenvalue; the eigenvector v represents the eigenvalue representing each principal component.

[0022] According to the size of the eigenvalue, the first k are selected as the principal component data, where k is the preset number of features. The selected principal component data is the state parameter sub-item data containing the most information. All principal component group data are formed into a principal component data matrix .

[0023] As a preferred method of the present invention, the objective function is established based on the GP Bayesian optimization model, combined with the principal component data matrix The extracted feature parameters are subjected to data fusion and matching operations. The specific process is as follows:

[0024] A set of repair process stages of absorbable biomaterials are preset, including p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; p=4: tissue integration stage; p=5 complete absorption stage; p=6: long-term stability stage, which respectively correspond to the absorbable biomaterial adaptation process of the patient in the repair process from complete wrapping, initial healing, local healing, completion of healing, postoperative recovery and complete recovery.

[0025] Record the characteristic data of temperature, pH value, stress, strain and conductivity of absorbable biomaterials at each stage of the repair process to obtain the preset values ​​under their respective ideal conditions .

[0026] Constructing the objective function in the GP Bayesian optimization model: measure the quality of the current restoration process;

[0027] Where fp(x) is the difference measure between the current repair state and the process stage p, is the preset reference weight of each parameter; where xj(t) is the state parameter item data in the principal component data matrix, including temperature, pH value, stress, strain and conductivity; where is the preset value of xj(t) under ideal conditions. is the original data index; n is the principal component data matrix The total number of raw data in .

[0028] Each time the sensor collects new data, its principal component data matrix is ​​calculated And bring it into the objective function of the GP Bayesian optimization model to obtain the difference measurement fp(x)={f1(x), f2(x), f3(x), f4(x), f5(x)} for each repair process stage. Select the minimum value minfp(x) and extract its corresponding process stage index p. If minfp(x) is less than the preset threshold, it is determined that the repair process stage represented by the stage index p is matched.

[0029] During the repair process, each time the sensor collects new data, the Bayesian optimization model will adjust the repair strategy according to the current data and output the repair process stage p obtained through matching.

[0030] Step 3: Monitoring the repair process based on the identification of the repair process stages;

[0031] Targeted process monitoring is carried out according to the matched repair process stages.

[0032] For p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; during the repair process of absorbable biomaterials, the stress-strain relationship is calculated, the stress-strain distribution diagram of the absorbable biomaterial is drawn, the material repair process is simulated by a finite element analysis model, and the stress-strain distribution diagram is visualized.

[0033] Draw the stress-strain diagram of each microunit.

[0034] When it is identified that the stress or strain relationship appearing in the stress-strain relationship diagram is in the elastic strain region and the strain is greater than a preset threshold, it is determined that the absorbable biomaterial is about to crack or break, and a rupture warning signal is output.

[0035] When the stress or strain appearing in the stress-strain relationship diagram is identified, the elastic strain area is pushed out and the plastic strain area is entered. It is determined that the absorbable biomaterial has cracks or damage, the volume of the plastic area is calculated, the degree of damage is determined, and the location and size of the damaged area are displayed on the computer.

[0036] For p=4: organizational integration stage; p=5: complete absorption stage; p=6: long-term stability stage.

[0037] Targeted analysis is performed on temperature and pH value. If the temperature or pH value exceeds the preset range, an absorption warning signal is output to indicate possible abnormal conditions and determine whether rapid degradation or local instability has occurred.

[0038] Step 4: Data storage and feedback;

[0039] All sensor data, the results of the repair process, and the time, type, and corresponding location of the generated warning signals are stored in the database in real time to facilitate subsequent analysis and research.

[0040] Based on the comparison between the current repair effect and historical data, the system generates a report and sends it to the user to provide data support and repair effect evaluation.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] 1. The present invention uses skin patch sensors and implantable biocompatible sensors to collect state parameters such as temperature, pH value, stress, strain and conductivity of absorbable biomaterials in real time. Combined with data processing and analysis, it can accurately identify the different stages of the repair process (such as physical support stage, fibrosis stage, degradation stage, etc.). By fusing and matching data with the Bayesian optimization model and principal component analysis (PCA), it can not only achieve accurate positioning of the repair process, but also adjust the repair strategy in real time to ensure that the repair process is efficient and smooth. This real-time monitoring and precise matching function can effectively optimize the repair process, improve the repair effect, and avoid potential problems caused by inaccurate repair process;

[0043] 2. The present invention adopts multi-sensor data acquisition and efficient data fusion technology, and through multi-dimensional monitoring of temperature, pH value, stress, strain and conductivity, accurately grasps the degradation process of repair materials and tissue repair conditions. By using the GP Bayesian optimization model and data fusion analysis, the repair process can be dynamically adjusted according to real-time data, and abnormal degradation or local instability of repair materials can be discovered in time. For example, by monitoring the changing trends of temperature and pH values, it is possible to effectively evaluate whether the material is degrading as expected, and avoid repair failures caused by too fast or too slow degradation of the material. This technology can ensure that the degradation process of the repair material is accurately controlled, and maximize the repair effect;

[0044] 3. At different stages of the repair process, the present invention can combine the stress-strain distribution diagram and the finite element analysis model to conduct real-time evaluation of the mechanical properties of the material. When it is found that the stress or strain of the material exceeds the preset safety range, the system can automatically trigger an early warning and give a specific damage assessment. For example, when the material enters the plastic strain zone, the system can calculate the volume of the damaged area in a timely manner, identify the risk of potential cracks or breakage, and visualize it on the computer. This intelligent early warning mechanism can help quickly identify and locate material damage, ensure the safety and stability of the repair process, and avoid repair failure or further damage due to untimely detection of damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings:

[0046] Figure 1 is a flow chart of the method of the present invention; DETAILED DESCRIPTION

[0047] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 As shown, the multi-parameter sensing and repair process monitoring method of absorbable biomaterials includes the following steps:

[0049] Step 1: Environmental parameter collection and preprocessing;

[0050] The state parameters of the absorbable biomaterial are collected by using skin patch sensors and implantable biocompatible sensors, and the state parameters include temperature, pH value, stress, strain and conductivity.

[0051] It should be noted that the biocompatible sensor has biocompatibility and will not induce immune response. It usually uses some materials with good biocompatibility, such as silicon, carbon nanotubes, metal oxides, etc., and is packaged in combination with biocompatible polymers.

[0052] At preset time intervals, the original data of the state parameters of the skin patch sensor and the implantable biocompatible sensor are collected through wireless transmission, and the collected original data of the state parameters are transmitted to the computer, and the pre-processed state parameters are obtained through noise and signal smoothing processing.

[0053] The noise and signal smoothing process is specifically as follows:

[0054] The original data of temperature, pH value, stress, strain and conductivity collected at each preset time interval t are collected and recorded as the original data set. , and input it into the Gaussian filter to balance the signal and remove the high-frequency noise. The core operation formula of the Gaussian filter is: ;in is a set of preprocessed state parameters obtained after Gaussian filtering operation, including preprocessed temperature, pH value, stress, strain and conductivity; σ is the preset filter standard deviation, which is used to control the degree of smoothing; N is the size of the preset sliding window, that is, the number of neighboring data points considered around the current data point t, which is used to control the reference range of the Gaussian filter; i is the original data index, which is used to formulate the specific number of the reference value of the original data in the Gaussian filter in the current window; t is the time index of the current data point, that is, the position of the current data point being processed by the Gaussian filter.

[0055] The set of preprocessed state parameters obtained after Gaussian filtering Send it to the data processing center for further data fusion and feature extraction analysis.

[0056] Step 2: Feature extraction analysis and data fusion;

[0057] Feature extraction and data fusion are performed on the set of preprocessed state parameters, and preset values ​​are matched according to the data fusion results to evaluate the state of the absorbable biomaterial.

[0058] PCA principal component analysis is used to perform data feature extraction operations. The specific process is as follows:

[0059] Extract the set of preprocessed state parameters The state parameters in the equation include temperature, pH value, stress, strain and conductivity, and are input into the standardized formula The standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t) are obtained; is the mean of the state parameter sub-items, including the mean of temperature, pH value, stress, strain and conductivity; is the standard deviation of the state parameter items, including the standard deviation of temperature, pH value, stress, strain and conductivity; is the state parameter item obtained after standardization. Where t is the data collection time.

[0060] For the standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t), the formula Calculate the covariance matrix C, where m is the number of samples; and is the data matrix of state parameters and the transposed matrix of the data matrix. ; Calculate the eigenvalue λ and eigenvector v of the covariance matrix C. Among them, the eigenvalue λ represents the variance of each principal component represented by the eigenvalue; the eigenvector v represents the eigenvalue representing each principal component.

[0061] According to the size of the eigenvalue, the first k are selected as the principal component data, where k is the preset number of features. The selected principal component data is the state parameter sub-item data containing the most information. All principal component group data are formed into a principal component data matrix .

[0062] Furthermore, the objective function is established based on the GP Bayesian optimization model, combined with the principal component data matrix The extracted feature parameters are subjected to data fusion and matching operations. The specific process is as follows:

[0063] A set of repair process stages of absorbable biomaterials are preset, including p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; p=4: tissue integration stage; p=5 complete absorption stage; p=6: long-term stability stage, which respectively correspond to the absorbable biomaterial adaptation process of the patient in the repair process from complete wrapping, initial healing, local healing, completion of healing, postoperative recovery and complete recovery.

[0064] Record the characteristic data of temperature, pH value, stress, strain and conductivity of absorbable biomaterials at each stage of the repair process to obtain the preset values ​​under their respective ideal conditions .

[0065] Constructing the objective function in the GP Bayesian optimization model: measure the quality of the current restoration process;

[0066] Where fp(x) is the difference measure between the current repair state and the process stage p, is the preset reference weight of each parameter; where xj(t) is the state parameter item data in the principal component data matrix, including temperature, pH value, stress, strain and conductivity; where is the preset value of xj(t) under ideal conditions. is the original data index; n is the principal component data matrix The total number of raw data in .

[0067] Each time the sensor collects new data, its principal component data matrix is ​​calculated And bring it into the objective function of the GP Bayesian optimization model to obtain the difference measurement fp(x)={f1(x), f2(x), f3(x), f4(x), f5(x)} for each repair process stage. Select the minimum value minfp(x) and extract its corresponding process stage index p. If minfp(x) is less than the preset threshold, it is determined that the repair process stage represented by the stage index p is matched.

[0068] During the repair process, each time the sensor collects new data, the Bayesian optimization model will adjust the repair strategy according to the current data and output the repair process stage p obtained through matching.

[0069] Step 3: Monitoring the repair process based on the identification of the repair process stages;

[0070] Targeted process monitoring is carried out according to the matched repair process stages.

[0071] For p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; during the repair process of absorbable biomaterials, the stress-strain relationship is calculated, the stress-strain distribution diagram of the absorbable biomaterial is drawn, the material repair process is simulated by a finite element analysis model, and the stress-strain distribution diagram is visualized.

[0072] Draw the stress-strain diagram of each microunit.

[0073] When it is identified that the stress or strain relationship appearing in the stress-strain relationship diagram is in the elastic strain region and the strain is greater than a preset threshold, it is determined that the absorbable biomaterial is about to crack or break, and a rupture warning signal is output.

[0074] When the stress or strain appearing in the stress-strain relationship diagram is identified, the elastic strain area is pushed out and the plastic strain area is entered. It is determined that the absorbable biomaterial has cracks or damage, the volume of the plastic area is calculated, the degree of damage is determined, and the location and size of the damaged area are displayed on the computer.

[0075] It should be noted that cracks or breakages reflect whether the material can provide sufficient mechanical properties in the initial support, especially in the physical support stage (p=1). The main function of the repair material is to provide physical support for the damaged area and ensure the stability of the tissue or bone. If cracks or breakages occur at this stage, it may mean that the repair material fails to provide sufficient support strength, thereby affecting the healing process. In this case, it is crucial to detect and treat cracks or breakages as early as possible to prevent the damage from expanding and affecting the repair process. In the fibrosis stage (p=2) and local degradation stage (p=3), although the degradation and absorption process of the material begins, the material still needs to maintain certain mechanical properties to support the repair of surrounding tissues. At this stage, the appearance of cracks or breakages may indicate that the repair material degrades too quickly or is unevenly stressed, affecting tissue integration and repair effects.

[0076] For p=4: organizational integration stage; p=5: complete absorption stage; p=6: long-term stability stage.

[0077] Targeted analysis is performed on temperature and pH value. If the temperature or pH value exceeds the preset range, an absorption warning signal is output to indicate possible abnormal conditions and determine whether rapid degradation or local instability has occurred.

[0078] It should be noted that temperature and pH are key parameters that reflect the degradation and absorption process of materials. As the material degrades, the local temperature may rise, and the pH value may also fluctuate, especially when inflammation or cell repair activities are more active. Monitor these changes in real time to ensure that they are within the ideal range.

[0079] Step 4: Data storage and feedback;

[0080] All sensor data, the results of the repair process, and the time, type, and corresponding location of the generated warning signals are stored in the database in real time to facilitate subsequent analysis and research.

[0081] Based on the comparison between the current repair effect and historical data, the system generates a report and sends it to the user to provide data support and repair effect evaluation.

[0082] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0083] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations;

[0084] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-parameter sensing and repair process monitoring method for absorbable biomaterials, characterized in that: The following steps are involved: Step 1: Environmental parameter collection and preprocessing; The state parameters of the absorbable biomaterial are collected by using a skin patch sensor and an implantable biocompatible sensor, wherein the state parameters include temperature, pH value, stress, strain and conductivity; and the collected state parameters are subjected to noise and signal smoothing by preprocessing; Step 2: Feature extraction analysis and data fusion; The PCA principal component analysis is used to extract features from the set of preprocessed state parameters, and the extracted features are fused by Bayesian optimization. The preset values ​​are matched according to the data fusion results to evaluate the state of the absorbable biomaterial and match it to a preset set of repair process stages of the absorbable biomaterial, including the physical support stage, fibrosis stage, local degradation stage, tissue integration stage, complete absorption stage and long-term stability stage. Step 3: Monitoring the repair process based on the identification of the repair process stages; Conduct targeted process monitoring based on the matched repair process stages; conduct stress-strain monitoring for the physical support stage, fibrosis stage, and local degradation stage; Temperature and pH monitoring for tissue integration, complete absorption and long-term stability; Step 4: Data storage and feedback; All sensor data, the results of the repair process, and the time, type, and corresponding location of the generated warning signals are stored in the database in real time to facilitate subsequent analysis and research; Based on the comparison between the current repair effect and historical data, the system generates a report and sends it to the user to provide data support and repair effect evaluation.

2. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 1, characterized in that: The specific process of state parameter collection is as follows: At preset time intervals, the original data of the state parameters of the skin patch sensor and the implantable biocompatible sensor are collected through wireless transmission, and the collected original data of the state parameters are transmitted to the computer, and the pre-processed state parameters are obtained through noise and signal smoothing processing.

3. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 1, characterized in that: The specific process of noise and signal smoothing is: The original data of temperature, pH value, stress, strain and conductivity collected at each preset time interval t are collected and recorded as the original data set. , and input it into the Gaussian filter to balance the signal and remove the high-frequency noise. The core operation formula of the Gaussian filter is: ;in is a set of pre-processed state parameters obtained after Gaussian filtering operation, including pre-processed temperature, pH value, stress, strain and conductivity; σ is the preset filter standard deviation, which is used to control the degree of smoothing; N is the size of the preset sliding window, that is, the number of neighboring data points considered around the current data point t, which is used to control the reference range of Gaussian filtering; i is the original data index, which is used to formulate the specific number of the reference value of the original data in the Gaussian filter in the current window; t is the time index of the current data point, that is, the position of the current data point being processed by the Gaussian filter; The set of preprocessed state parameters obtained after Gaussian filtering Send it to the data processing center for further data fusion and feature extraction analysis.

4. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 1, characterized in that: The specific process of feature extraction for the set of preprocessed state parameters is: Extract the set of preprocessed state parameters The state parameters in the equation include temperature, pH value, stress, strain and conductivity, and are input into the standardized formula The standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t) are obtained; is the mean of the state parameter sub-items, including the mean of temperature, pH value, stress, strain and conductivity; is the standard deviation of the state parameter items, including the standard deviation of temperature, pH value, stress, strain and conductivity; is the state parameter item obtained after standardization; t is the data collection time; For the standardized temperature X1(t), pH value X2(t), stress X3(t), strain X4(t) and conductivity X5(t), the formula Calculate the covariance matrix C, where m is the number of samples; and is the data matrix of state parameters and the transposed matrix of the data matrix; ; Calculate the eigenvalue λ and eigenvector v of the covariance matrix C; where the eigenvalue λ represents the variance of each principal component represented by the eigenvalue; the eigenvector v represents the eigenvalue representing each principal component; According to the size of the eigenvalue, the first k are selected as the principal component data, where k is the preset number of features; the selected principal component data is the state parameter sub-item data containing the most information; all principal component group data are formed into a principal component data matrix .

5. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 4, characterized in that: The specific process of data fusion of the extracted features is as follows: Matching operation, the specific process is: A set of repair process stages of absorbable biomaterials is preset, including p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; p=4: tissue integration stage; p=5: complete absorption stage; p=6: long-term stability stage, which respectively correspond to the absorbable biomaterial adaptation process of patients during the repair process from complete wrapping, initial healing, local healing, complete healing, postoperative recovery and complete recovery. Record the characteristic data of temperature, pH value, stress, strain and conductivity of absorbable biomaterials at each stage of the repair process to obtain the preset values ​​under their respective ideal conditions ; Constructing the objective function in the GP Bayesian optimization model: measure the quality of the current restoration process; Where fp(x) is the difference measure between the current repair state and the process stage p, is the reference weight of each preset parameter; Where xj(t) is the state parameter data in the principal component data matrix, including temperature, pH value, stress, strain and conductivity; is the preset value of xj(t) under ideal conditions; Where j principal component data matrix is the original data index; n is the principal component data matrix The total number of raw data in ; Each time the sensor collects new data, its principal component data matrix is ​​calculated And bring it into the objective function of the GP Bayesian optimization model to obtain the difference measurement fp(x)={f1(x), f2(x), f3(x), f4(x), f5(x)} for each repair process stage; select the minimum value minfp(x) and extract its corresponding process stage index p; If minfp(x) is less than the preset threshold, it is determined that the repair process stage represented by the stage index p is matched; During the repair process, each time the sensor collects new data, the Bayesian optimization model will adjust the repair strategy according to the current data and output the repair process stage p obtained through matching.

6. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 5, characterized in that: The specific process of stress-strain monitoring is as follows: For p=1: physical support stage; p=2: fibrosis stage, p=3: local degradation stage; Calculate the stress-strain relationship, draw a stress-strain distribution diagram of the absorbable biomaterial, simulate the repair process of the material through a finite element analysis model, and visualize the stress-strain distribution diagram; Draw the stress-strain diagram of each micro-unit; When it is identified that the stress or strain relationship in the stress-strain relationship diagram is in the elastic strain region and the strain is greater than a preset threshold, it is determined that the absorbable biomaterial is about to crack or break, and a rupture warning signal is output; When the stress or strain appearing in the stress-strain relationship diagram is identified, the elastic strain area is pushed out and the plastic strain area is entered. It is determined that the absorbable biomaterial has cracks or damage, the volume of the plastic area is calculated, the degree of damage is determined, and the location and size of the damaged area are displayed on the computer.

7. The multi-parameter sensing and repair process monitoring method of absorbable biomaterials according to claim 5, characterized in that: The specific process of temperature and pH monitoring is as follows: For p=4: organizational integration stage; p=5: complete absorption stage; p=6: long-term stability stage; Targeted analysis is performed on temperature and pH value. If the temperature or pH value exceeds the preset range, an absorption warning signal is output to indicate possible abnormal conditions and determine whether rapid degradation or local instability has occurred.

Images