Personalized rehabilitation training method and system based on condition monitoring

Abstract

The present invention provides a personalized rehabilitation training method and system based on state monitoring, which relates to the field of rehabilitation training technology. The method includes: obtaining electromyographic amplitude, root mean square, and spectrum median, calculating the rate of change, monitoring muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extracting the rate of change of joint angles and moment of inertia, and obtaining a training load reference value. In the present invention, by real-time monitoring and analysis of multiple physiological parameters including electromyographic signals, blood oxygen saturation, and heart rate variability, an accurate training load reference value is established to improve the accuracy of neuromuscular coordination assessment. By comparing the rate of change of electromyographic signals in short and long time windows, the training load is accurately adjusted to reduce fatigue risk. By real-time adjustment of the rehabilitation robot's motion trajectory and optimization of the training rhythm, it is ensured that the training intensity matches the individual's metabolic capacity, and dynamic matching and personalized adjustment of the training plan are achieved, effectively improving the safety and effectiveness of training.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation training, and in particular to a personalized rehabilitation training method and system based on state monitoring. Background Art

[0002] The field of rehabilitation training technology includes a variety of methods and systems for intervening in patients' physical dysfunctions, aiming to restore patients' motor ability, improve physiological functions and enhance their quality of life. This technical field involves multiple aspects such as biomechanical analysis, electromyographic signal acquisition and processing, motion control and feedback regulation, and virtual reality-assisted training. Rehabilitation training systems usually combine sensor technology, computer-assisted evaluation and training program optimization to achieve personalized intervention by accurately monitoring the patient's physiological and motor status. In addition, this field includes a variety of modes such as robot-assisted rehabilitation training, neurorehabilitation training, and biofeedback training to meet the needs of different patients. In recent years, with the development of artificial intelligence, big data, and wearable devices, rehabilitation training technology has gradually evolved towards intelligence and adaptability, improving the accuracy and pertinence of training programs.

[0003] Among them, the personalized rehabilitation training method and system based on state monitoring refers to a method and implementation system for formulating and dynamically adjusting rehabilitation training plans by real-time collection and analysis of data such as the patient's motion status and physiological parameters. The subject of this patent covers physiological signal acquisition, data analysis and processing, training plan generation and adjustment, training execution feedback and other links. Specifically, the system uses sensors to collect information such as electromyography, joint angles, gait parameters, etc., uses signal processing and pattern recognition technology to extract key features, formulates personalized training plans based on individual physiological models and rehabilitation theories, and adjusts training parameters based on real-time monitoring results. The training plan is presented through visual, tactile or force feedback. The patient performs training movements based on the feedback, and the system continuously monitors state changes to optimize subsequent training content.

[0004] In terms of training load assessment, existing technologies lack detailed analysis of multiple physiological signals. The training benchmark is mainly based on fixed parameters, which makes it difficult to match individual physiological characteristics, resulting in insufficient adaptability of training intensity settings. Neuromuscular response monitoring does not fully consider the time differences between the main and auxiliary muscle groups, and cannot accurately assess coordination, affecting the fine-tuning of training programs. Fatigue assessment methods are relatively simple and rely heavily on individual physiological parameters. It is difficult to accurately identify the state of muscle fiber mobilization, resulting in difficulty in effectively controlling fatigue accumulation during training. The exercise state adjustment method is relatively static, and changes in training load lack dynamic feedback on the real-time physiological state, resulting in unstable training effects. Training rhythm optimization usually relies on preset time intervals and fails to make adjustments based on individual metabolic capacity, which reduces training efficiency and may lead to a mismatch between training rhythm and metabolic needs. Training mode conversion does not fully consider the matching of active and passive movements, and cannot accurately adjust training strategies, which may affect training effects and add additional physiological burdens. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a personalized rehabilitation training method and system based on state monitoring.

[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical solution: a personalized rehabilitation training method based on state monitoring, comprising the following steps:

[0007] S1: Obtain EMG amplitude, root mean square, and spectrum median, calculate the rate of change, monitor muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extract joint angle change rate and moment of inertia, and obtain the training load baseline value;

[0008] S2: calling the training load baseline value, calculating the time difference between myoelectric triggering and joint angle change, monitoring the neuromuscular response of the main and auxiliary muscle groups, analyzing the mobilization rate, control torque, and delay, screening the deviation data, and obtaining the matching evaluation parameters;

[0009] S3: calling the neuromuscular matching evaluation parameters, calculating the ratio of the short-window and long-window electromyographic signal change rates, identifying the muscle fiber mobilization rate, extracting the fatigue accumulation index, analyzing the fatigue inflection point threshold, calculating the stability based on the joint angle change rate, screening the training load correction parameters, monitoring the ICUAW rehabilitation robot's motion state, extracting the electromyographic control parameters, analyzing the active and passive motion matching, adjusting the robot's motion trajectory, and generating dynamic training load adjustment parameters;

[0010] S4: calling the dynamic training load adjustment parameters, calculating the heart rate recovery rate, analyzing the glycogen metabolism trend, screening the training rhythm optimization threshold, calling the energy metabolism load index, judging the metabolic limit, and generating the training rhythm optimization parameters.

[0011] As a further solution of the present invention, the training load benchmark value includes an electromyographic signal benchmark, a metabolic state benchmark, and a joint movement benchmark; the matching evaluation parameters include a neuromuscular response parameter, a motion control parameter, and a deviation evaluation parameter; the dynamic training load adjustment parameters include a muscle fiber mobilization parameter, a fatigue state parameter, a joint stability parameter, and a motion matching parameter; and the training rhythm optimization parameters include a heart rate recovery parameter, a metabolic limit parameter, and an interval adjustment parameter.

[0012] As a further embodiment of the present invention, the specific steps of obtaining the myoelectric amplitude, root mean square, and spectrum median, calculating the rate of change, monitoring muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extracting the rate of change of joint angles and moment of inertia, and obtaining a training load baseline value are as follows:

[0013] S101: Acquire the myoelectric signal of the target muscle group, extract the amplitude, root mean square value, and spectrum median, compare the amplitude changes at adjacent moments, calculate the change rate within the time window, and obtain the characteristic change rate of the myoelectric signal;

[0014] S102: Based on the characteristic change rate of the electromyographic signal, the number of peak mobilization times per unit time is calculated, and combined with the amplitude fluctuation range to obtain the muscle fiber mobilization rate. At the same time, the blood oxygen saturation is monitored, the blood oxygen saturation decrease rate is calculated, and the blood oxygen fluctuation range is obtained. The average of the blood oxygen level decrease per unit time is calculated to generate the muscle fiber mobilization rate and the blood oxygen metabolism rate.

[0015] S103: Call the muscle fiber mobilization rate and blood oxygen metabolism rate, calculate the lactate metabolism rate, monitor heart rate variability, extract the joint angle change rate and moment of inertia, and obtain a training load baseline value.

[0016] As a further embodiment of the present invention, the specific steps of calling the training load baseline value, calculating the time difference between myoelectric triggering and joint angle change, monitoring the neuromuscular response of the main and auxiliary muscle groups, analyzing the mobilization rate, control torque, and delay, screening the deviation data, and obtaining the matching evaluation parameters are as follows:

[0017] S201: calling the training load baseline value, extracting the myoelectric signal triggering time and the joint angle change starting time, calculating the time difference, and monitoring the neuromuscular response time difference between the main muscle group and the auxiliary muscle group to obtain the neuromuscular response time parameter;

[0018] S202: Based on the neuromuscular response time parameters, calculating the variation interval of the muscle fiber mobilization rate, extracting the muscle control torque, calculating the torque fluctuation amplitude per unit time, and simultaneously performing time series analysis on the neuromuscular response delay to extract the offset of the differentiated muscle group response. Data with deviations exceeding a set threshold on the time axis are screened, and outliers are removed to obtain muscle fiber mobilization and neural response analysis parameters;

[0019] S203: Calling the muscle fiber mobilization and neural response analysis parameters, extracting the matching degree of the muscle fiber mobilization rate, muscle control torque, and neural response delay, and calculating the consistency offset interval on the time axis to obtain matching evaluation parameters.

[0020] As a further solution of the present invention, the specific steps of calling the neuromuscular matching evaluation parameters, calculating the ratio of the change rate of the short- and long-window electromyographic signals, identifying the muscle fiber mobilization rate, extracting the fatigue accumulation index, analyzing the fatigue inflection point threshold, calculating the stability in combination with the joint angle change rate, screening the training load correction parameters, monitoring the motion state of the ICUAW rehabilitation robot, extracting the electromyographic control parameters, analyzing the active and passive motion matching, adjusting the robot motion trajectory, and generating the dynamic training load adjustment parameters are as follows:

[0021] S301: calling the matching evaluation parameter, calculating the ratio of the myoelectric signal change rate in the short time window to the long time window, and determining whether it exceeds the training load adjustment threshold, and identifying the muscle fiber mobilization rate, and obtaining the training load threshold determination parameter;

[0022] S302: Based on the training load threshold determination parameter, extract the time series of the electromyographic signal change rate, calculate the cumulative fatigue index per unit time, analyze the electromyographic signal change trend, extract the change of the muscle fiber mobilization rate in the differentiated time window, analyze the fatigue inflection point threshold, and simultaneously call the joint angle change rate to identify the joint stability parameter. Then, screen the data that meets the training load adjustment requirements to obtain the fatigue accumulation and joint stability parameters.

[0023] S303: Call the fatigue accumulation and joint stability parameters, obtain the ICUAW rehabilitation robot motion state monitoring data, extract the electromyographic signal control parameters, calculate the matching index of passive motion and active motion, and adjust the robot motion trajectory to obtain the dynamic training load adjustment parameters.

[0024] As a further solution of the present invention, the calculation formula of the matching index of passive exercise and active exercise is specifically:

[0025] ;

[0026] in, Represents the matching index of passive movement and active movement, represents the total number of discrete moments within the active movement time window, Representative The instantaneous amplitude of the electromyographic signal at this moment, Representative The external torque applied by the rehabilitation robot at this moment, Representative The neuromuscular response delay of represents the total number of discrete moments within the passive motion time window, Representative The restorative force generated by muscle stretching during passive movement at each moment Representative The instantaneous angular acceleration of the rehabilitation robot performing the movement at that moment.

[0027] As a further embodiment of the present invention, the specific steps of calling the dynamic training load adjustment parameter, calculating the heart rate recovery rate, analyzing the glycogen metabolism trend, screening the training rhythm optimization threshold, calling the energy metabolism load index, determining the metabolic limit, and generating the training rhythm optimization parameter are as follows:

[0028] S401: Calling the dynamic training load adjustment parameter, extracting the heart rate signal, calculating the heart rate recovery rate per unit time, analyzing the glycogen metabolism ratio trend, extracting the change of the glycogen metabolism ratio on the time axis, and obtaining the heart rate recovery and metabolism trend parameters;

[0029] S402: Based on the heart rate recovery and metabolic trend parameters, extract the time series of the proportion of glycogen metabolism under the differentiated training rhythm, calculate the metabolic fluctuation range index per unit time, and screen the training rhythm optimization threshold. At the same time, call the instantaneous energy metabolic load index, compare the training rhythm with the metabolic limit, extract the load adjustment range of the training rhythm, and identify the change of the load increment per unit time to obtain the training rhythm metabolic matching parameter;

[0030] S403: calling the training rhythm metabolism matching parameter, calculating the adjustment interval index of the training interval, screening the training rhythm optimization threshold, extracting the rhythm adjustment requirement parameter, and generating the training rhythm optimization parameter.

[0031] As a further solution of the present invention, the calculation formula for the adjustment interval index of the training interval is specifically:

[0032] ;

[0033] in, Represents the adjustment interval indicator of the training interval time, represents the number of training cycles considered, Representative The value of the training rhythm metabolism matching parameter within a cycle, Representative The adjustment coefficient of each cycle reflects the sensitivity of rhythm changes to training effects.

[0034] As a further embodiment of the present invention, the method further includes, S5: calling the training rhythm optimization parameters, combining the myoelectric change rate, matching assessment, and load adjustment, calculating the personalized training load, adjusting the movement amplitude, matching the training plan, identifying the training conversion strategy, and generating a personalized rehabilitation training plan;

[0035] The personalized rehabilitation training program includes training load parameters, training rhythm parameters, and movement pattern parameters;

[0036] S501: Calling the training rhythm optimization parameters, combining the electromyographic signal change rate, the neuromuscular matching evaluation parameters, and the dynamic training load adjustment parameters, extracting the change trend of the training indicators on the time axis, calculating the personalized training load configuration indicators, and obtaining the personalized load configuration parameters;

[0037] S502: Based on the personalized load configuration parameters, extract the training movement amplitude variation range, calculate the motion trajectory deviation index per unit time, and compare with the stage training plan to extract the training movement amplitude that meets the load matching requirements. At the same time, identify the active-passive training conversion strategy, analyze the load switching point between active and passive training, and select the time interval that meets the conversion threshold to obtain the active-passive conversion and training amplitude parameters;

[0038] S503: Calling the active-passive conversion and training amplitude parameters, extracting the movement of the rehabilitation robot, analyzing the offset interval of the robot's movement trajectory on the time axis, and matching the personalized training load configuration to generate a personalized rehabilitation training plan.

[0039] Personalized rehabilitation training system based on condition monitoring, including:

[0040] The myoelectric and load monitoring module obtains the myoelectric amplitude, root mean square, and spectrum median, monitors muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extracts the rate of change of joint angles and moment of inertia, and obtains the training load baseline value;

[0041] The neural response analysis module calls the training load baseline value, calculates the time difference between myoelectric triggering and joint angle change, monitors the neuromuscular response of the main and auxiliary muscle groups, analyzes the mobilization rate, control torque, and delay, and obtains matching evaluation parameters;

[0042] The dynamic load adjustment module calls the neuromuscular matching evaluation parameters, calculates the ratio of the short- and long-window electromyographic signal change rates, identifies the muscle fiber mobilization rate, extracts the fatigue accumulation index, analyzes the fatigue inflection point threshold, calculates stability based on the joint angle change rate, screens the training load correction parameters, monitors the ICUAW rehabilitation robot's motion state, extracts the electromyographic control parameters, analyzes the active and passive motion matching, and generates dynamic training load adjustment parameters;

[0043] The rhythm optimization control module calls the dynamic training load adjustment parameter, calculates the heart rate recovery rate, analyzes the glycogen metabolism trend, screens the training rhythm optimization threshold, calls the energy metabolism load index, and generates the training rhythm optimization parameter;

[0044] The personalized rehabilitation planning module calls the training rhythm optimization parameters, combines the myoelectric change rate, matching assessment, and load adjustment, calculates the personalized training load, adjusts the movement range, matches the training plan, and generates a personalized rehabilitation training plan.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, by real-time monitoring and analysis of multiple physiological parameters including electromyographic signals, blood oxygen saturation, and heart rate variability, an accurate training load baseline value is established to improve the accuracy of neuromuscular coordination assessment. By comparing the rate of change of electromyographic signals in short and long time windows, the training load is accurately adjusted to reduce the risk of fatigue. By real-time adjustment of the motion trajectory of the rehabilitation robot and optimization of the training rhythm, it is ensured that the training intensity matches the individual's metabolic capacity, and dynamic matching and personalized adjustment of the training plan are achieved, effectively improving the safety and effectiveness of training. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 Schematic diagram of the steps of the present invention;

[0049] Figure 2 is a flow chart of the steps of S1 of the present invention;

[0050] Figure 3 This is a flow chart of the steps of S2 of the present invention;

[0051] Figure 4 This is a flow chart of the steps of S3 of the present invention;

[0052] Figure 5 This is a flow chart of the steps of S4 of the present invention;

[0053] Figure 6 This is a flow chart of the steps of S5 of the present invention;

[0054] Figure 7 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0057] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same. The terms "of," "corresponding," and "corresponding" may sometimes be used interchangeably. It should be noted that, when the distinction is not emphasized, the meanings they convey are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0060] See also Figure 1 ,The personalized rehabilitation training method based on condition monitoring includes the following steps:

[0061] S1: Obtain the amplitude, root mean square value, and spectrum median of the target muscle group's electromyographic signal, calculate the rate of change within the time window, monitor the muscle fiber mobilization rate and blood oxygen saturation, calculate the lactate metabolism rate and heart rate variability, extract the joint angle change rate and moment of inertia, and obtain the training load baseline value;

[0062] S2: Call the training load baseline value, calculate the time difference between the triggering moment of the electromyographic signal and the starting moment of the joint angle change, monitor the neuromuscular response time difference between the main muscle group and the auxiliary muscle group, analyze the muscle fiber mobilization rate, muscle control torque, neuromuscular response delay, filter the deviation data, and obtain the matching evaluation parameters;

[0063] S3: Invoke matching evaluation parameters, calculate the ratio of the EMG signal change rate in the short-time window to the long-time window, determine whether the training load adjustment threshold is exceeded, identify the muscle fiber mobilization rate, extract the fatigue accumulation index, analyze the fatigue inflection point threshold, calculate the joint stability parameters by calling the joint angle change rate, select the training load correction calculation parameters, call the ICUAW rehabilitation robot motion state monitoring, extract the EMG signal control parameters, analyze the matching of passive and active motion, adjust the robot motion trajectory, and obtain the dynamic training load adjustment parameters;

[0064] S4: Call dynamic training load adjustment parameters, calculate heart rate recovery rate, analyze glycogen metabolism ratio trend, screen training rhythm optimization threshold, call instantaneous energy metabolism load index, determine whether the training rhythm is close to the metabolic limit, adjust training interval time, and generate training rhythm optimization parameters;

[0065] S5: Call the training rhythm optimization parameters, combine the electromyographic signal change rate, neuromuscular matching evaluation parameters, and dynamic training load adjustment parameters, calculate the personalized training load configuration indicators, adjust the training movement amplitude, match the stage training plan, identify the active and passive training conversion strategy, extract the rehabilitation robot movement status, and generate a personalized rehabilitation training plan.

[0066] The training load benchmark values ​​include the electromyographic signal benchmark, metabolic state benchmark, and joint movement benchmark. The matching evaluation parameters include neuromuscular response parameters, motion control parameters, and deviation evaluation parameters. The dynamic training load adjustment parameters include muscle fiber mobilization parameters, fatigue state parameters, joint stability parameters, and motion matching parameters. The training rhythm optimization parameters include heart rate recovery parameters, metabolic limit parameters, and interval adjustment parameters. The personalized rehabilitation training plan includes training load parameters, training rhythm parameters, and motion pattern parameters.

[0067] See also Figure 2 , the specific steps of S1 are:

[0068] S101: Acquire the myoelectric signal of the target muscle group, extract the amplitude, root mean square value, and spectrum median, compare the amplitude changes at adjacent moments, calculate the change rate within the time window, and obtain the characteristic change rate of the myoelectric signal;

[0069] First, surface electromyography (sEMG) electrodes are attached to the target muscle groups, and the electrode spacing is ensured to be appropriate to reduce artifact interference. Subsequently, the raw EMG signal data is collected at a sampling frequency of more than 1kHz to ensure the timing accuracy of the data. After data acquisition, filtering preprocessing is performed, including 50Hz power frequency filtering to eliminate power supply noise, and a bandpass filter (20Hz450Hz) is used to extract the effective EMG signal components to obtain the processed time domain EMG signal. When calculating the amplitude, the absolute value of the collected signal is processed to obtain the full-wave rectified signal, and its mean and root mean square (RMS) value are calculated. When the time domain electromyographic signal is squared, the average is calculated, and then the square root is taken. When calculating the median of the spectrum, the signal is first subjected to a fast Fourier transform (FFT) to obtain its power spectrum density distribution, and the frequency value that makes half of the total power is found as the median frequency. Subsequently, the amplitude changes at adjacent moments are compared, and the amplitude change trend is determined by calculating the difference in the absolute values ​​of the amplitude changes of adjacent sampling points and averaging them. Then, the amplitude change rate within a fixed time window (such as 500ms) is set, and the amplitude change rate within the time window is counted. This rate can be calculated by setting the average of all amplitude changes within the window, and finally the characteristic change rate of the electromyographic signal is obtained.

[0070] S102: Based on the characteristic change rate of the electromyographic signal, the number of peak mobilizations per unit time is calculated. Combined with the amplitude fluctuation range, the muscle fiber mobilization rate is obtained. At the same time, the blood oxygen saturation is monitored, the blood oxygen saturation decrease rate is calculated, and the blood oxygen fluctuation range is obtained. The average of the blood oxygen level decrease per unit time is calculated to generate the muscle fiber mobilization rate and the blood oxygen metabolism rate.

[0071] First, peak detection is performed on the electromyographic signal within a fixed time window. A threshold is set to determine the peak point. For example, the peak point is defined as the point where the signal within a time window is higher than the mean + 2 times the standard deviation of the time period. The number of peak points is counted to calculate the number of peak mobilizations per unit time. Furthermore, an amplitude fluctuation interval is set. The difference between the maximum and minimum amplitudes of the electromyographic signal within the time window is calculated to obtain the amplitude fluctuation range within this interval. Based on this, the muscle fiber mobilization rate is calculated as the ratio of the number of peak mobilizations per unit time to the amplitude fluctuation interval. Simultaneously, a photoelectric sensor is used to monitor blood oxygen saturation (SpO2). Within a fixed time window, the rate of decrease in SpO2 is calculated by calculating the change in SpO2 between the first and last moments within the window and dividing it by the length of the time window to obtain the SpO2 decrease rate. Furthermore, by setting the SpO2 fluctuation interval, the difference between the maximum and minimum SpO2 values ​​within the window is calculated. Furthermore, the mean of the decrease in SpO2 per unit time is calculated. This mean is obtained by averaging the SpO2 decrease rates within multiple windows. Ultimately, the muscle fiber mobilization rate and the SpO2 metabolic rate are obtained.

[0072] S103: Invoke the muscle fiber mobilization rate and blood oxygen metabolism rate, calculate the lactate metabolism rate, monitor heart rate variability, extract the joint angle change rate and moment of inertia, and obtain the training load baseline value;

[0073] First, the lactate metabolic rate is calculated. This calculation is based on the relationship between the blood oxygen metabolic rate and the muscle fiber mobilization rate. The oxygen consumption rate is calculated from the blood oxygen decline rate, and the corresponding lactate production rate is estimated in combination with the muscle fiber mobilization rate. Lactate accumulation at different time points is calculated using a fixed time window. The calculation formula can be expressed as: lactate metabolic rate = (lactate production per unit time / lactate clearance per unit time) / time window. Simultaneously, heart rate variability (HRV) is monitored. The collected heart rate signals are subjected to RR interval detection, and HRV metrics such as SDNN (standard deviation) and RMSSD (root mean square difference between adjacent RR intervals) are calculated to assess physiological load. Furthermore, an inertial measurement unit (IMU) is used to acquire joint motion data. The rate of change of joint angle is calculated by calculating the angle change within the time window and dividing it by the duration. The moment of inertia is also calculated based on angular velocity, mass, and lever arm length. Finally, a baseline training load value is calculated based on these parameters. The baseline training load value is obtained through a weighted comprehensive calculation of muscle fiber mobilization rate, blood oxygen metabolic rate, lactate metabolic rate, heart rate variability, and joint motion characteristics.

[0074] See also Figure 3 , the specific steps of S2 are:

[0075] S201: Calling the training load baseline value, extracting the electromyographic signal triggering time and the starting time of the joint angle change, calculating the time difference, and monitoring the neuromuscular response time difference between the main muscle group and the auxiliary muscle group to obtain the neuromuscular response time parameter;

[0076] First, the trigger moment of the myoelectric signal is extracted. This trigger moment is detected by setting a threshold, such as the moment when the signal exceeds the mean + 3 standard deviations within a certain time window as the trigger point. Subsequently, the starting moment of the joint angle change is extracted. This moment is monitored by the inertial measurement unit (IMU). When the angular velocity exceeds the set static threshold, the moment is considered the starting moment of the angle change. To calculate the time difference, the timestamp of the myoelectric signal trigger moment and the timestamp of the joint angle change start moment are directly subtracted to obtain the time difference. Next, the neuromuscular response time difference between the primary and auxiliary muscle groups is monitored. The same threshold method is applied to the myoelectric signals of the primary and auxiliary muscle groups to detect the trigger moment, and the time interval between the two is calculated. To minimize the influence of individual differences on the time difference, it is necessary to compare the response time changes under different training loads. The mean time difference between the primary and auxiliary muscle groups under different loads is calculated, and the stability of this time difference is calculated based on the standard deviation. Ultimately, the neuromuscular response time parameter is obtained.

[0077] S202: Based on the neuromuscular response time parameters, the variation range of the muscle fiber mobilization rate is calculated, and the muscle control torque is extracted. The torque fluctuation amplitude per unit time is calculated. At the same time, a time series analysis of the neuromuscular response delay is performed to extract the offset of the differentiated muscle group response. Data with deviations exceeding the set threshold on the time axis are screened, and outliers are removed to obtain muscle fiber mobilization and neural response analysis parameters;

[0078] First, the variation interval of the muscle fiber mobilization rate is calculated. The calculation method of this variation interval is to count the maximum and minimum values ​​of the muscle fiber mobilization rate within a fixed time window, and take the difference between the two as the fluctuation interval of the mobilization rate. Then, the muscle control torque is extracted. The torque calculation method is based on the measured joint angle, angular velocity and muscle force. The torque calculation formula is M=F×r, where M is the muscle control torque, F is the tension generated by the muscle, and r is the length of the lever arm. The torque value is calculated by the measured muscle tension and joint biomechanical parameters. On this basis, the torque fluctuation per unit time is calculated. The amplitude of the movement is to calculate the difference between the maximum and minimum torques within a fixed time window, and take the mean as the fluctuation amplitude per unit time. At the same time, a time series analysis is performed on the neuromuscular response delay. During the time series analysis, the window length is set, the response delay in different time windows is calculated, and the response offset of the differentiated muscle groups is extracted. The data with a deviation exceeding the set threshold on the time axis is screened. The threshold can be set by the mean ±2 times the standard deviation of the statistical historical data. The data exceeding the threshold is regarded as an outlier and is eliminated, and finally the muscle fiber mobilization and neural response analysis parameters are obtained.

[0079] S203: Invoking muscle fiber mobilization and neural response analysis parameters, extracting the matching degree of muscle fiber mobilization rate, muscle control torque, and neural response delay, and calculating the consistency offset interval on the time axis to obtain matching evaluation parameters;

[0080] First, the matching degree of muscle fiber mobilization rate, muscle control torque, and neural response delay was extracted. When calculating the matching degree, the correlation coefficients between muscle fiber mobilization rate and muscle control torque in different time windows, as well as the correlation coefficients between muscle fiber mobilization rate and neural response delay, were calculated respectively. The Pearson correlation coefficient R was used to quantify the matching degree. The calculation formula is R=Cov(X,Y) / (σX×σY), where Cov(X,Y) is the covariance of X and Y, σX and σY are the standard deviations of X and Y, respectively. The closer the matching degree is to 1, the more consistent the changing trends of the two are. Subsequently, the consistency offset interval on the time axis was calculated. That is, the variation range of the matching degree in different time windows was counted, and its mean and standard deviation were calculated to obtain the matching evaluation parameter, which can be used to determine the rationality of training load adjustment.

[0081] See also Figure 4 , the specific steps of S3 are:

[0082] S301: Calling matching evaluation parameters, calculating the ratio of the electromyographic signal change rate in the short time window to the long time window, and determining whether it exceeds the training load adjustment threshold. At the same time, identifying the muscle fiber mobilization rate, and obtaining the training load threshold determination parameter;

[0083] First, the ratio of the EMG signal change rate within the short time window to the long time window is calculated. The short time window can be set to 500 ms, and the long time window can be set to 5 s. The EMG signal change rate is calculated within each window by extracting the root mean square (RMS) value or amplitude change rate of the EMG signal and calculating the average within the time window. Subsequently, the change rate value of the short time window is compared with the change rate value of the long time window to obtain the short time window / long time window ratio. The ratio is then used to determine whether the training load adjustment threshold is exceeded. This threshold can be set based on the mean and standard deviation of the trainee's historical data. For example, a ratio exceeding the mean ± 2 standard deviation is considered an abnormal load. Next, the muscle fiber mobilization rate is identified by extracting the peak mobilization times and amplitude fluctuation range within the unit time window. The range of the muscle fiber mobilization rate is calculated. Combined with the ratio of the short time window to the long time window, the training load threshold judgment parameter is obtained. This parameter is used to assess whether the current load is within a stable range or whether the training plan needs to be adjusted.

[0084] S302: Based on the training load threshold determination parameter, extract the time series of the electromyographic signal change rate, calculate the cumulative fatigue index per unit time, analyze the electromyographic signal change trend, extract the changes in the muscle fiber mobilization rate in the differentiated time window, analyze the fatigue inflection point threshold, and simultaneously call the joint angle change rate to identify the joint stability parameter. Then, screen the data that meets the training load adjustment requirements to obtain the fatigue accumulation and joint stability parameters.

[0085] First, the time series of the EMG signal change rate was extracted. The change rate at each time point was calculated within a fixed time window to construct a time series dataset. Subsequently, the cumulative fatigue index per unit time was calculated. This cumulative fatigue index was calculated based on the amplitude of the median decrease in the EMG signal spectrum and the root mean square decay rate. The change between the initial and final values ​​within a set time window was calculated, and the trend of change within multiple windows was cumulatively calculated. The EMG signal trend was then analyzed, and the mean and standard deviation of the change rate were calculated within different time windows. The changes in the muscle fiber mobilization rate within differentiated time windows were extracted. Specifically, the range of changes in the muscle fiber mobilization rate within short and long time windows was statistically analyzed. The fatigue inflection point threshold was calculated by setting the slope of change in different time periods. This threshold was determined by comparing the change rate before and after the maximum endurance time point. A fatigue inflection point was identified if the median EMG signal spectrum decreased by more than 20% within 5 minutes before and after the fatigue inflection point. Furthermore, joint angle change rate data was used to extract the mean angular velocity and angular acceleration per unit time. Joint stability parameters were calculated. The fluctuation range of angular acceleration was used to determine whether there were any abnormal changes. Data that met the training load adjustment requirements were selected to obtain fatigue accumulation and joint stability parameters.

[0086] S303: Calling fatigue accumulation and joint stability parameters, obtaining ICUAW rehabilitation robot motion state monitoring data, extracting electromyographic signal control parameters, calculating the matching index of passive motion and active motion, and adjusting the robot motion trajectory to obtain dynamic training load adjustment parameters;

[0087] The calculation formula for the matching index of passive exercise and active exercise is as follows:

[0088] ;

[0089] in, Represents the matching index of passive movement and active movement, represents the total number of discrete moments within the active movement time window, Representative The instantaneous amplitude of the electromyographic signal at this moment, Representative The external torque applied by the rehabilitation robot at this moment, Representative The neuromuscular response delay of represents the total number of discrete moments within the passive motion time window, Representative The restorative force generated by muscle stretching during passive movement at each moment Representative The instantaneous angular acceleration of the rehabilitation robot performing the movement at that moment;

[0090] The purpose of the formula calculation is to determine the matching index of passive movement and active movement This index assesses the degree of coordination between passive mechanically assisted movements and the patient's own movements during rehabilitation. The calculation involves two parts: the numerator represents a measure of the correlation of active movements, and the denominator represents a measure of the stability of passive movements.

[0091] First, for the molecular part, Indicates the The instantaneous amplitude of the electromyographic signal at a certain moment is obtained by real-time monitoring of the electromyographic sensor. The amplitude of the electromyographic signal is 0.8mV, so Similarly, For the The external torque applied by the rehabilitation robot at a certain moment is obtained through the data read by the sensor. If the torque is 15Nm, then record . The neuromuscular response delay is calculated by analyzing the time difference between the EMG signal and the motor response, and is assumed to be 0.03 seconds.

[0092] Assume that in a window period There are 10 moments in , then calculate the above terms for each moment and sum them. For example:

[0093] ;

[0094] For the denominator, Indicates the The restoring force generated by muscle stretching during passive movement at a certain moment, if the measured data is 0.5N, then record . Indicates the The instantaneous angular acceleration of the rehabilitation robot when it performs the movement is 0.02rad / s2, so record .

[0095] In a window period There are 10 moments in , then calculate:

[0096] ;

[0097] Substituting the above two parts into the formula, we get:

[0098] ;

[0099] This result shows that the motion matching index between the rehabilitation robot and the patient is 0.8517, indicating a high degree of coordination between the two. The patient's active participation and the robot's passive assistance are relatively consistent in torque and response time, which can effectively support the patient's dynamic load adjustment during rehabilitation training.

[0100] See also Figure 5 , the specific steps of S4 are:

[0101] S401: Calling dynamic training load adjustment parameters, extracting heart rate signals, calculating the heart rate recovery rate per unit time, analyzing the glycogen metabolism ratio trend, extracting the change in glycogen metabolism ratio on the time axis, and obtaining heart rate recovery and metabolic trend parameters;

[0102] First, extract the heart rate signal, use the heart rate monitoring equipment to record the heart rate data per unit time, and calculate the heart rate recovery rate. Set a fixed time window, such as the 60-second period after the end of training, calculate the change between the initial heart rate and the final heart rate, and divide the change by the length of the time window to obtain the heart rate recovery rate per unit time. Then, analyze the glycogen metabolism ratio trend and extract the change in glycogen metabolism ratio per unit time. When calculating the glycogen metabolism ratio, first measure the blood lactate concentration, extract the blood lactate value at the set time interval, and calculate the ratio of glycogen and fat metabolism in combination with the respiratory exchange rate to obtain the change in glycogen metabolism on the time axis. Further calculate the average value of the glycogen metabolism rate in the time window, and finally obtain the heart rate recovery and metabolic trend parameters.

[0103] S402: Based on the heart rate recovery and metabolic trend parameters, extract the time series of the glycogen metabolism ratio under the differentiated training rhythm, calculate the metabolic fluctuation range index per unit time, and select the training rhythm optimization threshold. Simultaneously, call the instantaneous energy metabolic load index, compare the training rhythm with the metabolic limit, extract the load adjustment range of the training rhythm, and identify the change of the load increment per unit time to obtain the training rhythm metabolic matching parameter;

[0104] First, the time series of glycogen metabolism percentage under differentiated training rhythms are extracted. The training rhythm data is divided into fixed time windows, and the mean glycogen metabolism percentage within each window is calculated. Subsequently, the metabolic fluctuation range index per unit time is calculated. This index is obtained by statistically analyzing the difference between the maximum and minimum glycogen metabolism percentage within the time window. The mean metabolic fluctuation within multiple windows is further calculated. At the same time, the training rhythm optimization threshold is screened. The setting of this threshold can be obtained from historical training data. For example, a fluctuation of glycogen metabolism percentage exceeding 20% ​​is set as an unstable interval. Subsequently, the instantaneous energy metabolic load index is called to extract the energy load consumed per unit time, and the training rhythm is compared with the metabolic limit. The correlation between energy consumption and glycogen metabolism within the time window is statistically analyzed, and the load adjustment interval of the training rhythm is extracted, that is, the glycogen metabolism fluctuation range under different rhythms is calculated. The optimal rhythm is selected in combination with the heart rate recovery rate. Finally, the change in load increment per unit time is identified, the load increment change rate is calculated, and the change trend within multiple windows is statistically analyzed to obtain the training rhythm metabolic matching parameter.

[0105] S403: calling the training rhythm metabolism matching parameter, calculating the adjustment interval index of the training interval, and screening the training rhythm optimization threshold, extracting the rhythm adjustment requirement parameter, and generating the training rhythm optimization parameter;

[0106] The specific calculation formula for the adjustment interval index of training interval time is:

[0107] ;

[0108] in, Represents the adjustment interval indicator of the training interval time, represents the number of training cycles considered, Representative The value of the training rhythm metabolism matching parameter within a cycle, Representative The adjustment coefficient of each cycle reflects the sensitivity of rhythm changes to training effects;

[0109] The formula is designed to calculate the adjustment interval index of training interval time , by analyzing a certain period The training data is used to adjust the future training plan. This formula combines the training rhythm metabolism matching parameters of each cycle and the adjustment coefficient of the corresponding period , to obtain a weighted average, which represents the optimized threshold.

[0110] Set up a practical example: Assume that the number of cycles considered , indicating that five training cycles were analyzed. The training rhythm metabolic matching parameters for each cycle , assuming that it is obtained through electromyographic signal analysis and energy consumption calculation, the specific value is:

[0111] ;

[0112] Adjustment factor Represents dynamic adjustments to individual fitness, assuming these values ​​are based on previous training responses and the coach's assessment. The values ​​are set to:

[0113] ;

[0114] The specific calculation process is as follows: 1. Calculation of the first cycle: 2. Calculation of the second cycle: 3. Calculation of the third cycle: 4. Calculation of the fourth cycle: 5. Calculation of the fifth cycle:

[0115] Adding these results gives:

[0116] ;

[0117] Then divide by the number of cycles :

[0118] ;

[0119] This numerical result shows that after analyzing the dynamic adjustment and matching of five training cycles, the adjustment interval index for training intervals is 0.88662. This means that subsequent training rhythm adjustments can be optimized around this threshold to improve training adaptability and effectiveness. This threshold is calculated based on actual training data and the dynamic adjustment coefficient, ensuring a personalized and scientific training plan.

[0120] See also Figure 6 , the specific steps of S5 are:

[0121] S501: Invoking training rhythm optimization parameters, combining electromyographic signal change rate, neuromuscular matching evaluation parameters, and dynamic training load adjustment parameters, extracting the change trend of training indicators on the time axis, calculating personalized training load configuration indicators, and obtaining personalized load configuration parameters;

[0122] First, combined with the EMG signal change rate, the root mean square value (RMS) and amplitude fluctuation range of the EMG signal within a fixed time window are extracted, the EMG signal change rate is calculated, and the change trend is extracted on the time axis. Subsequently, combined with the neuromuscular matching evaluation parameters, the EMG signal triggering time of different muscle groups is extracted, the time difference between the main muscle group and the auxiliary muscle group is calculated, and the consistency of the neural response is analyzed. Further combined with the dynamic training load adjustment parameters, the training load change value per unit time is extracted, the degree of motion state matching under different load levels is calculated, and by setting the time series window, the change trend of each parameter during the training process is calculated. At the same time, the personalized load configuration indicator is set. First, the mean of the training load in different time periods is calculated, and then the standard deviation of the training load change is analyzed to set the personalized load configuration parameter threshold. This threshold can be set based on historical training data. For example, a training load fluctuation range not exceeding 20% ​​of the mean is considered a stable state. Finally, the personalized load configuration parameters are obtained.

[0123] S502: Based on the personalized load configuration parameters, the training movement amplitude variation range is extracted, the motion trajectory deviation index per unit time is calculated, and the training movement amplitude that meets the load matching requirements is extracted by comparing with the stage training plan. At the same time, the active-passive training conversion strategy is identified, the load switching point between active and passive training is analyzed, and the time interval that meets the conversion threshold is selected to obtain the active-passive conversion and training amplitude parameters;

[0124] First, the range of variation of the training movement amplitude is extracted, a unit time window is set, and the maximum and minimum joint angles within each window are extracted and their variation range is calculated. At the same time, the motion trajectory offset index within the unit time is calculated, the angular deviation between the target trajectory and the actual trajectory is set, and the root mean square error (RMSE) within each time window is calculated. Subsequently, the stage training plans are compared to extract the training movement amplitude that meets the load matching requirements. The target amplitude range of training in different stages is counted, and the deviation threshold of the training movement is set. If the deviation is less than 5%, the matching is successful. At the same time, the active-passive training conversion strategy is identified, the electromyographic signal triggering status of different training stages is extracted, and the time point of transition from active training to passive training is analyzed. The load switching point between active and passive training is calculated, that is, the time point when the peak value of the electromyographic signal drops by more than 50% during the training process is counted, and the time interval that meets the conversion threshold is screened. The threshold can be set to when the training load drops by more than 15% of the mean. Finally, the active-passive conversion and training amplitude parameters are obtained.

[0125] S503: Calling active-passive conversion and training amplitude parameters, extracting the rehabilitation robot's motion situation, analyzing the offset interval of the robot's motion trajectory on the time axis, and matching the personalized training load configuration to generate a personalized rehabilitation training plan;

[0126] First, the movement of the rehabilitation robot is extracted, the robot motion trajectory data on the time axis is recorded, and the trajectory change range in different time windows is calculated. At the same time, the offset interval of the robot motion trajectory on the time axis is analyzed, the trajectory offset per unit time is calculated, and the offset threshold is set. For example, the trajectory offset exceeding 10% of the target trajectory is set as abnormal data. Subsequently, the personalized training load configuration is matched, the personalized load configuration parameters are extracted, and the matching degree between the robot motion trajectory and the training load is calculated. The motion load change per unit time window is counted, and its correlation coefficient is calculated to finally generate a personalized rehabilitation training plan.

[0127] See also Figure 7 , a personalized rehabilitation training system based on condition monitoring, including:

[0128] The myoelectric and load monitoring module obtains the myoelectric amplitude, root mean square, and spectrum median, monitors muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extracts the rate of change of joint angles and moment of inertia, and obtains the training load baseline value;

[0129] The neural response analysis module calls the training load baseline value, calculates the time difference between myoelectric triggering and joint angle change, monitors the neuromuscular response of the main and auxiliary muscle groups, analyzes the mobilization rate, control torque, and delay, and obtains matching evaluation parameters;

[0130] The dynamic load adjustment module uses neuromuscular matching evaluation parameters, calculates the ratio of the short- and long-window electromyographic signal change rates, identifies muscle fiber mobilization rates, extracts fatigue accumulation indexes, analyzes fatigue inflection point thresholds, calculates stability based on joint angle change rates, selects training load correction parameters, monitors the motion state of the ICUAW rehabilitation robot, extracts myoelectric control parameters, analyzes active and passive motion matching, and generates dynamic training load adjustment parameters.

[0131] The rhythm optimization control module calls dynamic training load adjustment parameters, calculates heart rate recovery rate, analyzes glycogen metabolism trends, screens training rhythm optimization thresholds, calls energy metabolism load index, and generates training rhythm optimization parameters;

[0132] The personalized rehabilitation planning module calls the training rhythm optimization parameters, combines the electromyographic change rate, matching assessment, and load adjustment, calculates the personalized training load, adjusts the movement range, matches the training plan, and generates a personalized rehabilitation training plan.

[0133] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A personalized rehabilitation training system based on condition monitoring, characterized by: A method for performing personalized rehabilitation training based on condition monitoring, the method comprising the following steps: S1: Obtain EMG amplitude, root mean square, and spectrum median, calculate the rate of change, monitor muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extract joint angle change rate and moment of inertia, and obtain the training load baseline value; S2: calling the training load baseline value, calculating the time difference between myoelectric triggering and joint angle change, monitoring the neuromuscular response of the main and auxiliary muscle groups, analyzing the mobilization rate, control torque, and delay, screening the deviation data, and obtaining the matching evaluation parameters; S3: calling the neuromuscular matching evaluation parameters, calculating the ratio of the short-window and long-window electromyographic signal change rates, identifying the muscle fiber mobilization rate, extracting the fatigue accumulation index, analyzing the fatigue inflection point threshold, calculating the stability based on the joint angle change rate, screening the training load correction parameters, monitoring the ICUAW rehabilitation robot's motion state, extracting the electromyographic control parameters, analyzing the active and passive motion matching, adjusting the robot's motion trajectory, and generating dynamic training load adjustment parameters; S4: calling the dynamic training load adjustment parameter, calculating the heart rate recovery rate, analyzing the glycogen metabolism trend, screening the training rhythm optimization threshold, calling the energy metabolism load index, determining the metabolic limit, and generating the training rhythm optimization parameter; S5: Calling the training rhythm optimization parameters, combining the electromyographic change rate, matching assessment, and load adjustment, calculating the personalized training load, adjusting the range of motion, matching the training plan, identifying the training conversion strategy, and generating a personalized rehabilitation training program; S301: calling the matching evaluation parameter, calculating the ratio of the myoelectric signal change rate in the short time window to the long time window, and determining whether it exceeds the training load adjustment threshold, and identifying the muscle fiber mobilization rate, and obtaining the training load threshold determination parameter; S302: Based on the training load threshold determination parameter, extract the time series of the electromyographic signal change rate, calculate the cumulative fatigue index per unit time, analyze the electromyographic signal change trend, extract the change of the muscle fiber mobilization rate in the differentiated time window, analyze the fatigue inflection point threshold, and simultaneously call the joint angle change rate to identify the joint stability parameter. Then, screen the data that meets the training load adjustment requirements to obtain the fatigue accumulation and joint stability parameters. S303: Call the fatigue accumulation and joint stability parameters, obtain the ICUAW rehabilitation robot motion state monitoring data, extract the electromyographic signal control parameters, calculate the matching index of passive motion and active motion, and adjust the robot motion trajectory to obtain the dynamic training load adjustment parameters.

2. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: The training load benchmark value includes an electromyographic signal benchmark, a metabolic state benchmark, and a joint movement benchmark; the matching evaluation parameters include a neuromuscular response parameter, a motion control parameter, and a deviation evaluation parameter; the dynamic training load adjustment parameters include a muscle fiber mobilization parameter, a fatigue state parameter, a joint stability parameter, and a motion matching parameter; the training rhythm optimization parameters include a heart rate recovery parameter, a metabolic limit parameter, and an interval adjustment parameter.

3. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: The specific steps for executing a personalized rehabilitation training method based on state monitoring, including obtaining the myoelectric amplitude, root mean square, and spectrum median, calculating the rate of change, monitoring muscle fiber mobilization, blood oxygen, lactate metabolism, and heart rate variability, extracting the rate of change of joint angles and moment of inertia, and obtaining a training load baseline value, are as follows: S101: Acquire the myoelectric signal of the target muscle group, extract the amplitude, root mean square value, and spectrum median, compare the amplitude changes at adjacent moments, calculate the change rate within the time window, and obtain the characteristic change rate of the myoelectric signal; S102: Based on the characteristic change rate of the electromyographic signal, the number of peak mobilization times per unit time is calculated, and combined with the amplitude fluctuation range to obtain the muscle fiber mobilization rate. At the same time, the blood oxygen saturation is monitored, the blood oxygen saturation decrease rate is calculated, and the blood oxygen fluctuation range is obtained. The average of the blood oxygen level decrease per unit time is calculated to generate the muscle fiber mobilization rate and the blood oxygen metabolism rate. S103: Call the muscle fiber mobilization rate and blood oxygen metabolism rate, calculate the lactate metabolism rate, monitor heart rate variability, extract the joint angle change rate and moment of inertia, and obtain a training load baseline value.

4. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: The method for executing a personalized rehabilitation training method based on state monitoring also includes calling the training load baseline value, calculating the time difference between myoelectric triggering and joint angle change, monitoring the neuromuscular response of the main and auxiliary muscle groups, analyzing the mobilization rate, control torque, and delay, screening deviation data, and obtaining the matching evaluation parameters. The specific steps are as follows: S201: calling the training load baseline value, extracting the myoelectric signal triggering time and the joint angle change starting time, calculating the time difference, and monitoring the neuromuscular response time difference between the main muscle group and the auxiliary muscle group to obtain the neuromuscular response time parameter; S202: Based on the neuromuscular response time parameters, calculating the variation interval of the muscle fiber mobilization rate, extracting the muscle control torque, calculating the torque fluctuation amplitude per unit time, and simultaneously performing time series analysis on the neuromuscular response delay to extract the offset of the differentiated muscle group response. Data with deviations exceeding a set threshold on the time axis are screened, and outliers are removed to obtain muscle fiber mobilization and neural response analysis parameters; S203: Calling the muscle fiber mobilization and neural response analysis parameters, extracting the matching degree of the muscle fiber mobilization rate, muscle control torque, and neural response delay, and calculating the consistency offset interval on the time axis to obtain matching evaluation parameters.

5. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: The method for performing a personalized rehabilitation training method based on state monitoring also includes a formula for calculating the matching index of the passive movement and the active movement: ； in, Represents the matching index of passive movement and active movement, represents the total number of discrete moments within the active movement time window, Representative The instantaneous amplitude of the electromyographic signal at this moment, Representative The external torque applied by the rehabilitation robot at this moment, Representative The neuromuscular response delay of represents the total number of discrete moments within the passive motion time window, Representative The restorative force generated by muscle stretching during passive movement at each moment Representative The instantaneous angular acceleration of the rehabilitation robot performing the movement at that moment.

6. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: The method for executing a personalized rehabilitation training method based on state monitoring further includes calling the dynamic training load adjustment parameter, calculating the heart rate recovery rate, analyzing the glycogen metabolism trend, screening the training rhythm optimization threshold, calling the energy metabolism load index, determining the metabolic limit, and generating the training rhythm optimization parameter. The specific steps are: S401: Calling the dynamic training load adjustment parameter, extracting the heart rate signal, calculating the heart rate recovery rate per unit time, analyzing the glycogen metabolism ratio trend, extracting the change of the glycogen metabolism ratio on the time axis, and obtaining the heart rate recovery and metabolism trend parameters; S402: Based on the heart rate recovery and metabolic trend parameters, extract the time series of the proportion of glycogen metabolism under the differentiated training rhythm, calculate the metabolic fluctuation range index per unit time, and screen the training rhythm optimization threshold. At the same time, call the instantaneous energy metabolic load index, compare the training rhythm with the metabolic limit, extract the load adjustment range of the training rhythm, and identify the change of the load increment per unit time to obtain the training rhythm metabolic matching parameter; S403: calling the training rhythm metabolism matching parameter, calculating the adjustment interval index of the training interval, screening the training rhythm optimization threshold, extracting the rhythm adjustment requirement parameter, and generating the training rhythm optimization parameter.

7. The personalized rehabilitation training system based on condition monitoring according to claim 6, characterized in that: The method for executing a personalized rehabilitation training method based on state monitoring also includes a calculation formula for the adjustment interval index of the training interval time, which is specifically: ； in, Represents the adjustment interval indicator of the training interval time, represents the number of training cycles considered, Representative The value of the training rhythm metabolism matching parameter within a cycle, Representative The adjustment coefficient of each cycle reflects the sensitivity of rhythm changes to training effects.

8. The personalized rehabilitation training system based on condition monitoring according to claim 1, characterized in that: A method for performing personalized rehabilitation training based on state monitoring, further comprising the personalized rehabilitation training program including training load parameters, training rhythm parameters, and movement pattern parameters; The specific steps of S5 are: S501: Calling the training rhythm optimization parameters, combining the electromyographic signal change rate, the neuromuscular matching evaluation parameters, and the dynamic training load adjustment parameters, extracting the change trend of the training indicators on the time axis, calculating the personalized training load configuration indicators, and obtaining the personalized load configuration parameters; S502: Based on the personalized load configuration parameters, extract the training movement amplitude variation range, calculate the motion trajectory deviation index per unit time, and compare with the stage training plan to extract the training movement amplitude that meets the load matching requirements. At the same time, identify the active-passive training conversion strategy, analyze the load switching point between active and passive training, and select the time interval that meets the conversion threshold to obtain the active-passive conversion and training amplitude parameters; S503: Calling the active-passive conversion and training amplitude parameters, extracting the movement of the rehabilitation robot, analyzing the offset interval of the robot's movement trajectory on the time axis, and matching the personalized training load configuration to generate a personalized rehabilitation training plan.

Images