阅读说明：本技术 一种基于扭矩和角度反馈融合的步态周期识别方法 (Gait cycle identification method based on torque and angle feedback fusion ) 是由 李哲 张岩岭 冯琴琴 金坤锋 玄利圣 于 2019-11-05 设计创作，主要内容包括：本发明公开了一种基于扭矩和角度反馈融合的步态周期识别方法,其特征在于,根据假肢佩戴者的假腿延长杆的轴向受力和弯矩,建立地面支反力模型,根据安装在所述假腿延长杆末端的压力传感器,得到所述假脚掌受到的地面支反力数据和支反力分布情况,再根据安装在所述假腿膝关节的角度传感器,得到膝关节转角数据；根据所述支反力数据和所述膝关节转角数据,对照步态数据库中的数据,确定当前步态周期所属阶段。本发明克服了肌电信号识别步态周期方法的测量数据易受皮肤表面状态干扰,不能在皮肤出汗或是不洁净等状态下准确判断步态周期的缺陷,且传感器测试结果可靠,不会出现传感器脱落的风险。(The invention discloses a gait cycle recognition method based on torque and angle feedback fusion, which is characterized in that a ground support reaction model is established according to axial stress and bending moment of a leg prosthesis extension rod of a prosthesis wearer, ground support reaction data and support reaction distribution conditions borne by a prosthetic foot sole are obtained according to a pressure sensor arranged at the tail end of the leg prosthesis extension rod, and knee joint corner data are obtained according to an angle sensor arranged at a knee joint of a leg prosthesis; and determining the stage of the current gait cycle according to the support reaction force data and the knee joint corner data and by contrasting data in a gait database. The invention overcomes the defects that the measured data of the gait cycle identification method by electromyographic signals is easy to be interfered by the skin surface state and the gait cycle can not be accurately judged under the states of skin sweating or unclean and the like, and the test result of the sensor is reliable without the risk of falling off of the sensor.)

1. A gait cycle identification method based on torque and angle feedback fusion is characterized in that a ground support reaction force model is established according to axial stress and bending moment of a leg prosthesis extension rod of a prosthesis wearer, ground support reaction force data and support reaction force distribution conditions of a prosthetic foot are obtained according to a pressure sensor arranged at the tail end of the leg prosthesis extension rod, and knee joint corner data are obtained according to an angle sensor arranged at a knee joint of the prosthetic leg; and determining the stage of the current gait cycle according to the support reaction force data and the knee joint corner data and by contrasting data in a gait database.

2. The gait cycle recognition method according to claim 1, wherein establishing a ground support reaction force model includes:

in the formula (I), the compound is shown in the specification,

3. The gait cycle recognition method according to claim 1, wherein the pressure sensor attached to the distal end of the leg prosthesis extension rod is connected to the ankle joint of the foot prosthesis at the distal end of the calf of the leg prosthesis by an elastic piece, and the pressure sensor is attached to the elastic piece.

4. A gait cycle identification method according to claim 1, characterized in that the gait database comprises a CGA gait database.

5. The gait cycle recognition method according to claim 3, wherein the pressure sensor is a strain gauge type pressure sensor.

6. The gait cycle recognition method according to claim 5, wherein the strain gauge type pressure sensor expresses the pressure by deformation, converts the elastic deformation formed by the axial force and the bending moment into voltage form for output, and calculates the axial force and the bending moment by the MCU processor on the leg prosthesis extension rod.

Technical Field

The invention relates to the technical field of computer identification, in particular to a gait identification method based on the fusion of torque and angle feedback.

Background

With the development of modern industry, accidental injuries such as natural disasters, traffic accidents, diseases and the like frequently occur, the number of thigh amputees is rapidly increasing, and for the thigh amputees, the amputation causes the thigh amputees to lose basic walking ability, and the installation of intelligent artificial limbs is an effective method for restoring the basic walking ability of the thigh amputees. One of the key technologies of the intelligent artificial limb is gait cycle recognition, so that the gait cycle recognition is researched, and the gait cycle recognition is of great significance for improving the life of thigh amputees.

The current gait cycle identification method mainly comprises the step of identifying the gait cycle by electromyographic signals. The gait cycle of the electromyographic signal recognition is that an electromyographic sensor is attached to the position of skin surface muscle of a thigh amputee subject, multichannel stump surface electromyographic signals in an asynchronous state are collected, the collected electromyographic signals are analyzed and preprocessed, feature values of the preprocessed electromyographic signals are extracted, corresponding feature vectors are constructed, and the gait cycle of the thigh amputee is recognized by using an improved supervised Kohonen neural network clustering algorithm. However, the electromyographic signal identification gait cycle needs to make the electromyographic sensor completely contact with the skin surface of a human body, the signal is weak, the dryness degree, the cleaning degree, the sweating condition and the like of the skin surface all influence the output signal of the electromyographic sensor, and the situations of inaccurate measuring result, wrong gait cycle judgment and the like easily occur.

Disclosure of Invention

Aiming at the defects in the prior art, the invention provides a gait cycle recognition method based on the fusion of torque and angle feedback, which can accurately judge which stage of the gait cycle a human body is in at any period and determine the action which the intelligent artificial limb should do next, so that the intelligent artificial limb wearer can walk more naturally and comfortably.

The invention provides a gait cycle recognition method based on the fusion of torque and angle feedback, which is characterized in that a ground support reaction model is established according to the axial stress and bending moment of a leg prosthesis extension rod of a prosthesis wearer, ground support reaction data and support reaction distribution conditions borne by a prosthetic foot are obtained according to a pressure sensor arranged at the tail end of the leg prosthesis extension rod, and knee joint corner data are obtained according to an angle sensor arranged at the knee joint of the prosthetic leg; and determining the stage of the current gait cycle according to the support reaction force data and the knee joint corner data and by contrasting data in a gait database. And establishing a statistical table according to the distribution condition of the support reaction force for counting the gait cycle.

Wherein, establishing the ground support reaction force model comprises:

in the formula (I), the compound is shown in the specification,

is the stress of the front sole of the artificial foot matched with the artificial leg;

the upper heel and the lower heel of the artificial foot matched with the artificial leg are stressed;

the artificial leg is stressed in the axial direction by the extension rod;

bending moment of the leg prosthesis extension rod;

the distance from the center point of the sole to the shank of the foot;the distance from the heel landing central point of the prosthetic foot to the lower leg.

The pressure sensor arranged at the tail end of the leg prosthesis extension rod is connected with the ankle joint of the artificial foot through an elastic sheet, the pressure sensor is arranged on the elastic sheet, and the axial pressure and the bending moment at the position of the leg prosthesis extension rod are calculated through the deformation of the strain gauge.

Wherein the gait database comprises a CGA gait database.

Wherein, the pressure sensor is a strain gauge type pressure sensor.

The strain gauge type pressure sensor expresses the borne pressure through deformation, converts elastic deformation formed by axial stress and bending moment into a voltage form to be output, and calculates the axial stress and the bending moment through the MCU processor on the leg prosthesis extension rod.

In the technical scheme of the invention, the defects that the measurement data of the gait cycle identification method by the electromyographic signals are easily interfered by the skin surface state and the gait cycle cannot be accurately judged under the states of skin sweating or unclean and the like are overcome, the test result of the sensor is reliable, and the risk of sensor falling is avoided.

Drawings

FIG. 1 is a schematic flow chart of a gait cycle recognition method according to an embodiment of the invention;

FIG. 2 is a schematic diagram of the sole reaction force exerted on the ground according to the embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings by way of examples of preferred embodiments. It should be noted, however, that the numerous details set forth in the description are merely for the purpose of providing the reader with a thorough understanding of one or more aspects of the present invention, which may be practiced without these specific details.

In the gait cycle recognition method based on the fusion of torque and angle feedback provided by the embodiment, a flow schematic diagram is shown in fig. 1, specifically, a ground support reaction model is established according to the axial stress and bending moment of a leg prosthesis extension rod of a prosthesis wearer, ground support reaction data and support reaction distribution conditions received by a prosthetic foot sole are obtained according to a pressure sensor installed at the tail end of the leg prosthesis extension rod, and knee joint corner data is obtained according to an angle sensor installed at a knee joint of the prosthetic leg; and according to the support reaction data and the knee joint corner data, determining the stage of the current gait cycle by comparing the data in the CGA gait database.

Specifically, the present embodiment can be divided into four parts:

in the first part, in a gait cycle, the stress condition of the sole and the stress condition of the shank extension rod are analyzed:

in the gait cycle, the sole is acted by the ground support reaction force, and simultaneously, the distribution condition of the ground support reaction force applied to the sole is continuously changed due to the continuous deviation of the gravity center of the human body in the walking process. The ground support reaction force received by the sole can be transmitted to the artificial limb along the lower leg extension rod, axial stress is formed on the lower leg extension rod, the continuous change of the ground support reaction force distribution condition caused by the shift of the gravity center can also be transmitted to the artificial limb along the lower leg extension rod, and bending moment stress is formed on the lower leg extension rod.

Due to the structure of the foot, the front sole and the rear heel are in contact with the ground, the arch part is not in contact with the ground, and the analysis can be simplified into a schematic diagram shown in figure 2, wherein the front sole is stressed

At a vertical distance from the shank extension rod of

The heel is stressed by

At a vertical distance from the shank extension rod of

The shank extension rod is stressed by

The bending moment of the shank extension rod is

The force analysis was as follows:

axial stress of the shank extension rod:

bending moment of shank extension rod:

the following two equations are obtained:

in the formula (I), the compound is shown in the specification,is the stress of the front sole of the artificial foot matched with the artificial leg;

the upper heel and the lower heel of the artificial foot matched with the artificial leg are stressed;

the artificial leg is stressed in the axial direction by the extension rod;bending moment of the leg prosthesis extension rod;

the distance from the center point of the sole to the shank of the foot;

the distance from the heel landing central point of the prosthetic foot to the lower leg.

Therefore, the ground support reaction force condition received by the sole can be determined by measuring the axial force and bending moment of the shank extension rod.

The second part, the installation pressure sensor measures the axial atress and the moment of flexure of shank extension rod, confirms ground back-up force distribution condition:

as can be seen from the first section, the condition that the sole of a foot receives the ground support reaction can be determined by measuring the axial force and bending moment of the shank extension rod. The axial stress is the supporting reaction force of the ground to the shank extension rod, and the bending moment is a force generated on the shank extension rod due to the shift of the gravity center in the walking process of a human body. The pressure sensor arranged at the tail end of the leg prosthesis extension rod is connected with the ankle joint of the artificial foot through an elastic sheet, and the pressure sensor is arranged on the elastic sheet. The pressure sensor of the embodiment is a strain gauge type pressure sensor, the pressure born by the pressure sensor is expressed through deformation, elastic deformation formed by axial stress and bending moment is converted into a voltage form to be output, and the axial stress and the bending moment are calculated through an MCU processor on the extension rod of the artificial leg.

The third part, installation angle sensor measures the knee joint angle:

in the walking process of a person, the knee joint corner can be changed continuously according to different stages in one gait cycle, and an angle sensor is installed at the knee joint and used for measuring the knee joint corner.

And the fourth part identifies the gait of the thigh stump by referring to the CGA gait database data:

and comparing the measured ground support reaction force and knee joint rotation angle data with corresponding data curve threshold values in the CGA gait database to determine which stage the current gait cycle is in.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.