CN-121243736-B - Multifunctional finger rehabilitation training device

CN121243736BCN 121243736 BCN121243736 BCN 121243736BCN-121243736-B

Abstract

The invention relates to the technical field of medical appliances and discloses a multifunctional finger rehabilitation training device which comprises a frame formed by an anti-skid base and an upright post, an orifice plate training module arranged on the frame, a grip training module, a rotating training module and an electric control module, wherein the surface of the orifice plate training module is provided with a through hole and is internally provided with a pressure sensor array, the grip training module comprises an upper pressing plate, a lower pressing plate and a double-spring structure, a displacement sensor is arranged at the joint of a stress plate and a guide rail, the rotating training module comprises a rotating disk with textures and a rotating shaft, the rotating shaft is provided with an photoelectric encoder, the electric control module is arranged inside the anti-skid base and is electrically connected with the pressure sensor array, the displacement sensor and the photoelectric encoder, and the electric control module comprises a micro control unit, an analog-digital conversion interface, a storage unit and a communication interface and is used for collecting, calibrating and analyzing training data and storing or transmitting. The multi-dimensional monitoring and analysis of finger pressing force, grip strength change and rotation action can be realized, and the accuracy and individuation level of rehabilitation training are improved.

Inventors

LEI JING
XU ZHUOJUN
ZHAO CHUNYAN
LI GANG

Assignees

上海市东方医院（同济大学附属东方医院）

Dates

Publication Date: 20260508
Application Date: 20250925

Claims (7)

1. A multi-functional finger rehabilitation trainer, comprising: The framework comprises an anti-skid base and an upright post fixed on the upper surface of the anti-skid base; The pore plate training module is arranged on the frame, through holes are respectively formed in the surface of the pore plate training module, and a pressure sensor array is arranged in the pore plate training module; The grip training module is arranged on the frame and comprises an upper pressing plate, a lower pressing plate and a double-spring structure, wherein the bottom surface of the lower pressing plate is connected with the anti-skid base, the top surface of the lower pressing plate is connected with the double-spring structure, and the bottom surface of the upper pressing plate is respectively connected with the double-spring structure and the lower pressing plate; The rotary training module is mounted on the frame and comprises a rotary disc with textures and a rotary shaft, and a photoelectric encoder is arranged on the rotary shaft; The electronic control module is arranged in the anti-skid base and is respectively and electrically connected with the pressure sensor array, the displacement sensor and the photoelectric encoder, and the electronic control module comprises a micro control unit, an analog-to-digital conversion interface, a storage unit and a communication interface, and is used for carrying out analog-to-digital conversion and calibration processing on the acquired analog signals, generating a data set for analysis and storing analysis results or transmitting the analysis results to an external terminal through the communication interface; the electronic control module is configured to perform space distribution modeling on finger pressing force signals output by the pressure sensor array of the pore plate training module, calculate finger pressing force distribution center point positions, finger pressing force distribution dispersion and finger pressing force distribution dynamic offset tracks, wherein the dynamic offset tracks are used for identifying irregular sliding or compensation actions of fingers in pore plate training; coupling and calculating a finger opening and closing stroke signal output by a displacement sensor of a grip training module and a stress response of the grip training module to generate a grip-displacement response matrix, and extracting a grip elastic recovery coefficient, a grip fatigue accumulation index and a grip coordination index from the grip-displacement response matrix, wherein the grip fatigue accumulation index is obtained through an energy attenuation ratio of a multi-period response matrix and is used for evaluating the rate of endurance reduction; Performing periodic segmentation processing on a rotation angle signal output by a photoelectric encoder of a rotation training module, establishing a rhythm segment set of a rotation action, and calculating a rotation angle consistency coefficient, a rotation rhythm deviation degree and a rotation burst abnormal factor in each rhythm segment set, wherein the rotation burst abnormal factor is obtained by detecting the short-time angular velocity transition quantity in a segment and is used for identifying abnormal tremble or involuntary tremble in the rotation action; Combining the finger pressing force distribution dynamic deviation track, the finger pressing force distribution dispersion degree, the grip elastic recovery coefficient, the grip fatigue accumulation index, the grip coordination index, the rotation angle consistency coefficient, the rotation rhythm deviation degree and the rotation burst abnormal factor to form a comprehensive training feature vector crossing a module, matching the comprehensive training feature vector with a corresponding numerical range condition or feature combination in a preset rehabilitation tag library, and outputting an action quality grade tag, a fatigue risk tag and a coordination grade tag according to a matching result; When the comprehensive training feature vector is matched with the rehabilitation tag library, the electronic control module compares each component of the comprehensive training feature vector with the numerical range conditions in the rehabilitation tag library one by one, adopts a confidence coefficient calculation mode in the matching process, gives high confidence coefficient when the component of the comprehensive training feature vector is positioned in the central area of the numerical range conditions, gives low confidence coefficient when the component is positioned in the edge area of the numerical range conditions, and finally outputs an action quality grade tag, a fatigue risk tag and a coordination grade tag according to the weighted result of each tag confidence coefficient; When the electronic control module outputs a label result, the action quality grade labels, the fatigue risk labels and the coordination grade labels are arranged according to a hierarchical sequence, a confidence level is added to each label, when the confidence level of at least one label is lower than the lower confidence level limit, the prompt label to be confirmed is added, when the confidence level of all labels is higher than the upper confidence level limit, the stable labels are added, and the label combination with the stable labels is transmitted to an external terminal in a recovery label coding mode through a communication interface.
2. The multi-functional finger rehabilitation trainer according to claim 1, wherein the pressure sensor arrays are evenly distributed along the edges of the through holes of the orifice plate training module in a circular manner, each through hole corresponding to at least three pressure sensors for collecting contact reaction forces from different directions when a finger is inserted and a pressing force is applied; the output of the pressure sensor array forms a two-dimensional pressing force distribution matrix through a space mapping relation; the electronic control module calculates the position of a finger pressing force distribution center point by adopting a weighted centroid method based on the two-dimensional pressing force distribution matrix, and calculates the distribution dispersion of the finger pressing force by adopting a second-order center distance; And the electronic control module continuously records the change track of the position of the central point of the finger pressing force distribution in the training period, and represents the dynamic deviation track of the finger pressing force distribution by the accumulated deviation and the instantaneous deviation speed.
3. The multifunctional finger rehabilitation trainer according to claim 2, wherein the electronic control module is used for acquiring the displacement of the upper pressing plate relative to the lower pressing plate in real time by the displacement sensor when coupling and calculating a finger opening and closing stroke signal output by the displacement sensor of the grip training module and the stress response of the grip training module; The electronic control module calculates the stress response of the grip training module according to the displacement and the spring parameter of the double-spring structure, and maps the displacement and the stress response into a grip-displacement response matrix correspondingly; Extracting the rigidity difference between the loading section and the unloading section from the grip-displacement response matrix, and defining the rigidity difference as a grip elastic recovery coefficient; calculating a ratio sequence of single-period energy and initial-period energy in a continuous multi-period grip-force-displacement response matrix, and accumulating to obtain a grip fatigue accumulation index; The ratio of the actual curve area to the ideal rectangular envelope area is used as the grip coordination index in the grip-displacement response matrix in the same period.
4. The multi-functional finger rehabilitation trainer according to claim 3, wherein the electronic control module segments the grip-displacement response matrix in successive training periods cycle by cycle when calculating the grip fatigue accumulation index, calculates the ratio of the load-unload loop energy of each period to the load-unload loop energy of the first period to obtain an energy attenuation sequence, and uses the accumulated average value of the energy attenuation sequence as the grip fatigue accumulation index, determines the high risk fatigue state when the grip fatigue accumulation index is higher than a first threshold, determines the stroke risk fatigue state when the grip fatigue accumulation index is between the first threshold and a second threshold, and determines the low risk fatigue state when the grip fatigue accumulation index is lower than a second threshold.
5. The multifunctional finger rehabilitation training device according to claim 4, wherein when the electric control module establishes a rhythm segment set of the rotation action, the electric control module divides a rotation angle signal output by a photoelectric encoder of the rotation training module into a plurality of equal-length time windows according to a time sequence of a training session, extracts a complete rotation angle period as one rhythm segment in each time window to form the rhythm segment set of the rotation action, and uses an average angular velocity, an angular velocity standard deviation and a duration of each rhythm segment as segment parameters for calculating a rotation angle consistency coefficient and a rotation rhythm deviation degree.
6. The multi-function finger rehabilitation trainer according to claim 5, wherein the electronic control module divides each segment in a rhythmic segment set of a rotational motion into a plurality of short time windows when calculating a rotational burst abnormality factor, calculates a change rate of a rotational angular velocity in each short time window, records an abnormality once when an instantaneous change rate of the rotational angular velocity exceeds an abnormality threshold set based on a mean value and a standard deviation of the segment angular velocity, and sums up the number and the magnitude of all the abnormality events as the rotational burst abnormality factor.
7. The multi-functional finger rehabilitation training device according to claim 6, wherein when the electronic control module forms the comprehensive training feature vector of the cross module, the electronic control module respectively uses the finger pressing force distribution dynamic deviation track, the finger pressing force distribution dispersion, the grip elastic recovery coefficient, the grip fatigue accumulation index, the grip coordination index, the rotation angle consistency coefficient, the rotation rhythm deviation degree and the rotation burst abnormal factor as independent components to construct an eight-dimensional comprehensive training feature vector, and performs normalization processing on the eight-dimensional comprehensive training feature vector to ensure that each component is in a uniform numerical range so as to ensure the comparability of the cross module feature.

Description

Multifunctional finger rehabilitation training device Technical Field The invention relates to the technical field of medical instruments, in particular to a multifunctional finger rehabilitation training device. Background At present, the finger rehabilitation training device mainly takes a mechanical structure, common forms comprise a fixed pore plate, a simple spring-grip or a rotating disc, the training effect depends on autonomous exercise of a patient, and a rehabilitation evaluation means with accurate quantification is lacked. In the prior art, although some devices introduce a single sensor to monitor a certain training index, such as a pressure sensor for detecting finger pressing force and a displacement sensor for recording the opening and closing strokes of the grip, these devices often focus on only local data and fail to form an overall evaluation framework across training modules. On the other hand, the traditional rehabilitation training device is generally remained in threshold judgment or trend curve analysis in the data processing level, and cannot comprehensively analyze multidimensional features in the training process. For example, it is difficult to identify compensatory sliding motion of the finger in the orifice plate training, to quantify the fatigue accumulation effect in the grip training, and to distinguish between stable rhythms and sudden tremors in the rotation training. Due to the lack of joint evaluation of key dimensions such as action quality, fatigue risk and coordination, the prior art has obvious defects in the aspects of accuracy and individuation of rehabilitation training. In view of this, there is a need for a finger rehabilitation trainer that can synchronously collect multidimensional data in multiple training modules and perform joint modeling and analysis on different features through an electronic control system, so as to output a structured rehabilitation label result, so as to solve the problems of data isolation, analysis of one-sided and lack of personalized evaluation in the existing device. Disclosure of Invention In view of the above, the present invention provides a multifunctional finger rehabilitation training device to solve the above problems. The invention provides a multifunctional finger rehabilitation training device, which comprises: The framework comprises an anti-skid base and an upright post fixed on the upper surface of the anti-skid base; The pore plate training module is arranged on the frame, through holes are respectively formed in the surface of the pore plate training module, and a pressure sensor array is arranged in the pore plate training module; The grip training module is arranged on the frame and comprises an upper pressing plate, a lower pressing plate and a double-spring structure, wherein the bottom surface of the lower pressing plate is connected with the anti-skid base, the top surface of the lower pressing plate is connected with the double-spring structure, and the bottom surface of the upper pressing plate is respectively connected with the double-spring structure and the lower pressing plate; The rotary training module is mounted on the frame and comprises a rotary disc with textures and a rotary shaft, and a photoelectric encoder is arranged on the rotary shaft; The electronic control module is arranged inside the anti-skid base and is respectively and electrically connected with the pressure sensor array, the displacement sensor and the photoelectric encoder, and the electronic control module comprises a micro control unit, an analog-to-digital conversion interface, a storage unit and a communication interface and is used for carrying out analog-to-digital conversion and calibration processing on the acquired analog signals, generating a data set for analysis and storing analysis results or transmitting the analysis results to an external terminal through the communication interface. Further, the electronic control module is configured to: Carrying out space distribution modeling on finger pressing force signals output by a pressure sensor array of the pore plate training module, and calculating the position of a finger pressing force distribution center point, the distribution dispersion of the finger pressing force and a dynamic deviation track of the finger pressing force distribution, wherein the dynamic deviation track is used for identifying irregular sliding or compensation actions of the finger in the pore plate training; coupling and calculating a finger opening and closing stroke signal output by a displacement sensor of a grip training module and a stress response of the grip training module to generate a grip-displacement response matrix, and extracting a grip elastic recovery coefficient, a grip fatigue accumulation index and a grip coordination index from the grip-displacement response matrix, wherein the grip fatigue accumulation index is obtained through an energy attenuation ratio of a multi-period