Lower limb rehabilitation training system for intelligent weight loss

Abstract

The application provides a lower limb rehabilitation training system for intelligent weight loss, which can be applied to the fields of artificial intelligence technology and medical technology. The system comprises a weight loss device, a weight loss motor, a floating motor and a floating spring; the weight loss motor is used for adjusting the stretching length of the weight loss spring according to the rotation angle of the weight loss motor to obtain the spring stretching distance; the floating motor is used for fine-tuning the stretching length of the floating spring according to the rotation angle of the floating motor; a lower limb exoskeleton device is used for measuring the plantar pressure and joint running angle of a user during walking; a tension monitoring device is used for measuring the output tension of the weight loss device; a control device is used for inputting the spring stretching distance, the plantar pressure and the output tension into a prediction model of the rotation angle of the weight loss motor to obtain the predicted value of the rotation angle of the weight loss motor; and inputting the joint running angle into a prediction model of the floating rotation angle to obtain the predicted value of the floating rotation angle.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence technology and medical technology, and more particularly to a lower limb rehabilitation training system for intelligent weight reduction. BACKGROUND

[0002] Stroke is a sudden central nervous disease, and is a high disability rate of nervous system disease. The incidence of stroke is increasing year by year. Walking rehabilitation training is effective for the rehabilitation treatment of stroke, which not only can prevent muscle atrophy of patients and maintain joint flexibility of patients, but also can improve the recovery degree of patients.

[0003] The lower limbs of stroke patients bear limited pressure, and an equipment is urgently needed to assist patients in accurately reducing the pressure on the lower limbs during walking training, so that the patients can walk stably and safely. SUMMARY

[0004] In view of the above problems, the present application provides a lower limb rehabilitation training system for intelligent weight reduction.

[0005] According to a first aspect of the present application, there is provided a lower limb rehabilitation training system for intelligent weight reduction, comprising:

[0006] A weight reduction device connected to the body of a user wearing a lower limb exoskeleton device, to reduce the force on the lower limbs of the user during walking on a treadmill device, the weight reduction device comprising a weight reduction spring, a weight reduction motor, a floating motor and a floating spring;

[0007] The weight reduction motor is used to adjust the stretching length of the weight reduction spring according to the rotation angle of the weight reduction motor, to obtain the spring stretching distance;

[0008] The floating motor is used to fine-tune the stretching length of the floating spring according to the rotation angle of the floating motor, to reduce the influence of the center of gravity of the user during walking on the output tension of the weight reduction device;

[0009] The lower limb exoskeleton device is used to measure the plantar pressure and joint operating angle of the user during walking;

[0010] The tension monitoring device is used to measure the output tension of the weight reduction device;

[0011] The control device is used to input the spring stretching distance, the plantar pressure and the output tension into a prediction model of the rotation angle of the weight reduction motor, to obtain a predicted value of the rotation angle of the weight reduction motor; and input the joint operating angle into a prediction model of the floating rotation angle, to obtain a predicted value of the floating rotation angle.

[0012] According to an embodiment of the present application, the control device comprises a distance sensor for measuring the spring stretching distance.

[0013] According to an embodiment of the present disclosure, the lower extremity exoskeleton device comprises a foot bottom pressure detector for measuring the foot bottom pressure of the user during walking.

[0014] According to an embodiment of the present disclosure, the lower extremity exoskeleton device further comprises a joint module driving module, which comprises:

[0015] a driving motor for driving the joint of the user to move so as to make the user walk on the treadmill device;

[0016] an encoder detector for measuring the joint running angle of the user during walking.

[0017] According to an embodiment of the present disclosure, the joint module driving module further comprises a brake for supplying power to the driving motor in the case of power failure of the lower extremity exoskeleton device.

[0018] According to an embodiment of the present disclosure, the prediction model is a grey prediction model, and the prediction model for inputting the spring stretching distance, the foot bottom pressure and the output tension to obtain the predicted value of the rotation angle of the weight reduction motor comprises: inputting the spring stretching distance, the foot bottom pressure and the output tension into the grey prediction model to obtain the predicted weight reduction of the weight reduction device; obtaining the predicted value of the rotation angle of the weight reduction motor according to the error value between the predicted weight reduction and a preset value.

[0019] According to an embodiment of the present disclosure, the control device further comprises a main control module for feedback controlling the operation of the weight reduction motor according to the error value between the predicted weight reduction and the preset value.

[0020] According to an embodiment of the present disclosure, the formula of the rotation angle of the weight reduction motor is:

[0021]

[0022] Φ1 is the rotation angle of the weight reduction motor, f z is a coupling function, the output tension is x, the foot bottom pressure is y i , the spring stretching distance is xl, the spring tension of the weight reduction spring is x T , and the weight reduction of the weight reduction device is m j .

[0023] According to an embodiment of the present disclosure, the formula of the coupling function f z is:

[0024]

[0025] f is a control function among the output tension, the foot bottom pressure and the spring tension, f1 is a foot bottom pressure compensation function, f2 is a spring function, f3 is a control function between the weight reduction motor and the spring stretching distance, and the formulas of f, f1, f2 and f3 are as follows:

[0026]

[0027]

[0028]

[0029]

[0030] The weight of the user is m r k is the elastic coefficient of the weight reduction spring.

[0031] According to the embodiment of the present disclosure, the formula of the floating motor rotation angle is as follows:

[0032]

[0033] Φ2(t) is the floating motor rotation angle at time t, m is the spring tension x T (t) and the control function between the user's center of gravity height change value h(t), the formula of the center of gravity height change value h(t) is as follows:

[0034]

[0035] The length of the user's thigh is l0, the length of the user's calf is l1, and the joint operation angle includes the hip joint angle θ0 and the knee joint angle θ1.

[0036] According to the embodiment of the present disclosure, the weight reduction device includes a weight reduction spring and a floating spring, the influence of the center of gravity floating on the output tension of the weight reduction device can be reduced by fine-tuning the stretching length of the floating spring, the plantar pressure is combined with the spring stretching distance and the output tension of the weight reduction device to predict the weight reduction motor rotation angle, and the joint operation angle is used to predict the floating motor rotation angle. Since the influence of the center of gravity floating on the weight reduction is considered, the support weight of the user during the exercise rehabilitation training is accurately reduced to provide a smooth and safe walking environment. BRIEF DESCRIPTION OF DRAWINGS

[0037] The above content and other purposes, features and advantages of the present application will be more clearly understood through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:

[0038] Figure 1 A scene diagram of user lower limb rehabilitation training according to the embodiment of the present application is shown;

[0039] Figure 2 A structural block diagram of a lower limb rehabilitation training system for intelligent weight reduction according to the embodiment of the present application is shown;

[0040] Figure 3A structural block diagram of a weight loss device according to an embodiment of the present application is shown;

[0041] Figure 4 A schematic diagram of a mounting position of a distance sensor according to an embodiment of the present application is shown;

[0042] Figure 5 A structural block diagram of a lower limb rehabilitation training system for intelligent weight loss according to another embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It should be understood, however, that the description which follows is merely illustrative and is not intended to limit the scope of the present application. In the following detailed description of embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that one or more embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring the concepts of the present application.

[0044] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present application. The terms "include", "comprise" and the like used herein indicate the presence of the features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components.

[0045] All terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0046] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should be generally interpreted as including one or more of the items enumerated in the list (e.g., "a system having at least one of A, B, and C" should include, but not be limited to, a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.).

[0047] Stroke, as a sudden central nervous disease, is a neural system disease with a high disability rate, and the incidence rate is increasing year by year. Patients often have limb movement disorders after the disease, and need long-term rehabilitation training and treatment, which brings great mental distress and heavy economic burden to the individual, family and society.

[0048] During the rehabilitation training, the learning process of re-mastering the limb movement function, the central nervous system in the brain will produce positive plasticity changes, change the brain function connection and structure to adapt to the movement demand. Clinical practice proves that the movement rehabilitation training is effective for the rehabilitation treatment of hemiplegia, which can not only prevent muscle atrophy of the patient and maintain the joint flexibility of the patient, but also improve the recovery degree of the patient. The lower limbs of the stroke patient bear limited pressure, and an equipment is urgently needed to assist the patient in accurately reducing the pressure on the lower limbs during walking training, so that the patient can walk stably and safely.

[0049] The embodiment of the application provides a lower limb rehabilitation training system for intelligent weight reduction, which comprises: a weight reduction device connected with the body of a user wearing a lower limb exoskeleton device to reduce the force borne by the lower limbs of the user during walking on a treadmill device, the weight reduction device comprising a weight reduction spring, a weight reduction motor, a floating motor and a floating spring; the weight reduction motor is used for adjusting the stretching length of the weight reduction spring according to the rotation angle of the weight reduction motor to obtain the spring stretching distance; the floating motor is used for fine-tuning the stretching length of the floating spring according to the rotation angle of the floating motor to reduce the influence of the center of gravity of the user on the output tension of the weight reduction device during walking; the lower limb exoskeleton device is used for measuring the plantar pressure and the joint operating angle of the user during walking; the tension monitoring device is used for measuring the output tension of the weight reduction device; the control device is used for inputting the spring stretching distance, the plantar pressure and the output tension into a prediction model of the rotation angle of the weight reduction motor to obtain the predicted value of the rotation angle of the weight reduction motor; and inputting the joint operating angle into a prediction model of the floating rotation angle to obtain the predicted value of the floating rotation angle.

[0050] Figure 1 A scene diagram of lower limb rehabilitation training of a user according to the embodiment of the application is shown.

[0051] As shown in Figure 1 The weight reduction device 110 is connected with the body of a user wearing a lower limb exoskeleton device 120 to reduce the force borne by the lower limbs of the user during walking on a treadmill device 130. The support device 140 is used for fixing the treadmill device 130 to prevent the movement of the treadmill device 130 caused by the walking of the user.

[0052] According to the embodiment of the application, the user can be a stroke patient, the plantar pressure value can be measured by the sole of the lower limb exoskeleton device 120, and the weight borne by the lower limbs of the user can be measured in real time. The lower limb exoskeleton device 120 also has a sensor for detecting the joint operating angle in real time, and the training state of the user can be monitored in real time.

[0053] According to the embodiment of the application, the weight reduction device 110 is connected with the body of the user, and the reduced force can be measured by the tension monitoring device. The weight reduction device can provide an upward supporting force or a tension device.

[0054] The weight loss device 110 and the foot bottom pressure value measured by the lower limb exoskeleton device 120 can be used to real-time feedback the force condition of the lower limbs of the user, and then adjust the parameters of the weight loss device 110, so as to realize precise weight loss, effectively protect the joints and muscles of the lower limbs of the user, and provide a healthy, effective and safe rehabilitation training environment.

[0055] The following will be based on Figure 1 The scene described, through Figures 2-5 The intelligent weight loss lower limb rehabilitation training system is described in detail.

[0056] Figure 2 The structure block diagram of the intelligent weight loss lower limb rehabilitation training system according to the embodiment of the application is shown.

[0057] As Figure 2 shown, the intelligent weight loss lower limb rehabilitation training system 200 of the embodiment includes a weight loss device 110, a lower limb exoskeleton device 120, a tension monitoring device 150 and a control device 160.

[0058] The weight loss device 110 is connected to the body of the user wearing the lower limb exoskeleton device 120 to reduce the force of the lower limbs of the user during walking on the treadmill device 130.

[0059] Figure 3 The structure block diagram of the weight loss device according to the embodiment of the application is shown.

[0060] As Figure 3 shown, the weight loss device 110 includes a weight loss spring 111, a weight loss motor 112, a floating spring 113 and a floating motor 114.

[0061] The weight loss motor 112 is used to adjust the stretching length of the weight loss spring 111 according to the weight loss motor rotation angle, so as to obtain the spring stretching distance.

[0062] According to the embodiment of the application, the weight loss motor rotation angle represents the angle of the weight loss motor 112 adjusting the weight loss spring 111. For example, the weight loss motor rotation angle is the rotation angle of the output shaft of the weight loss motor, which can be determined by measuring the angle of one rotation of the weight loss motor.

[0063] The floating motor 114 is used to fine-tune the stretching length of the floating spring 113 according to the floating motor rotation angle, so as to reduce the influence of the center of gravity of the user during walking on the output tension of the weight loss device 110.

[0064] According to an embodiment of the present application, the floating motor rotation angle represents the angle of rotation of the floating spring 113 by the floating motor 114. For example, the floating motor rotation angle is the rotation angle of the output shaft of the floating motor, which can be determined by measuring the angle of one rotation of the floating motor.

[0065] For example, the weight reduction motor rotation angle and the floating motor rotation angle can be measured by using a motor rotation angle encoder or an optical sensor.

[0066] The lower extremity exoskeleton device 120 is used to measure the plantar pressure and joint operating angle of the user during walking.

[0067] According to an embodiment of the present application, the lower extremity exoskeleton device 120 can be a lower extremity exoskeleton robot, which is installed with a plurality of precision sensors, and can measure the plantar pressure, center of gravity change, joint operating angle, etc. of the user during walking, so as to adjust the stretching length of the weight reduction spring and the floating spring in the weight reduction device, so as to balance the body of the user and reduce the stress on the lower limbs.

[0068] The tension monitoring device 150 is used to measure the output tension of the weight reduction device 110.

[0069] According to an embodiment of the present application, the output tension represents the weight reduced by the weight reduction device 110.

[0070] According to an embodiment of the present application, the tension monitoring device 150 is mainly used to measure the weight reduced by the weight reduction device, and then feedback controls the output of the weight reduction device 110. The tension monitoring device 150 is usually a pressure sensor.

[0071] The control device 160 is used to input the spring stretching distance, the plantar pressure and the output tension into a prediction model of the weight reduction motor rotation angle, to obtain a weight reduction motor rotation angle prediction value; and input the joint operating angle into a prediction model of the floating rotation angle, to obtain a floating rotation angle prediction value.

[0072] The control device 160 can be a server that provides various services.

[0073] According to an embodiment of the present application, the prediction model can be a machine learning algorithm, for example, the prediction model can be a neural network algorithm, a random forest algorithm, a support vector machine algorithm, a grey prediction algorithm, etc.

[0074] For example, in the case of a large amount of data of the spring stretching distance, the plantar pressure, the output tension and the joint operating angle, the prediction model can be a neural network algorithm. By training the prediction model with a large amount of data, the prediction model parameters can be updated by continuously acquiring new data, and the performance of the prediction model can be continuously improved. The prediction model can be trained based on the historical spring stretching distance, the historical plantar pressure and the historical output tension of other users.

[0075] The prediction model can be used for feature extraction of the spring stretching distance, the plantar pressure and the output tension, to obtain a state feature, which can represent the plantar stress intensity of the user; a predicted output tension of the weight reduction device is predicted according to the state feature; a predicted spring stretching distance is calculated according to the predicted output tension based on a formula of the spring tension (for example, spring tension = spring constant * spring stretching distance); and a required rotation angle of the weight reduction motor is inversely deduced according to the predicted spring stretching distance, to obtain a predicted value of the rotation angle of the weight reduction motor.

[0076] For example, due to different recovery stages of the stroke patients, the lower limb stress standards of the patient walking training can also be different. In order to adapt to users in different recovery stages, the prediction model of the intelligent weight reduction lower limb rehabilitation training system can be a random forest algorithm. The random forest algorithm has multiple decision trees, and each decision tree corresponds to a different recovery stage. For example, the users of the lower limb rehabilitation training for 1-10 times can be the decision tree corresponding to the early stage. The decision tree corresponding to the early stage can be obtained by training the historical spring stretching distance, the historical plantar pressure and the historical output tension of other users for 1-10 times.

[0077] The recovery stage of the user can be set in advance, and the spring stretching distance, the plantar pressure and the output tension are input into the decision tree corresponding to the recovery stage in the random forest algorithm of the rotation angle of the weight reduction motor, so as to accurately predict the rotation angle of the weight reduction motor. The joint running angle is input into the decision tree corresponding to the recovery stage in the random forest algorithm of the floating rotation angle, so as to accurately predict the floating rotation angle.

[0078] Meanwhile, the spring stretching distance, the plantar pressure, the output tension and the joint running angle can be input into the random forest algorithm, the recovery stage of the user is identified first, and then the spring stretching distance, the plantar pressure and the output tension are input into the decision tree corresponding to the recovery stage in the random forest algorithm of the rotation angle of the weight reduction motor, and the joint running angle is input into the decision tree corresponding to the recovery stage in the random forest algorithm of the floating rotation angle.

[0079] For example, in the case of small amount of data of the spring stretching distance, the plantar pressure, the output tension and the joint running angle, the prediction model can be a grey prediction algorithm. The grey prediction algorithm does not need an explicit mathematical assumption model, and can effectively predict under the condition of incomplete information and small sample data. Common grey prediction algorithms such as GM(1,1) have relatively simple model structures, few parameters and are easy to implement.

[0080] The weight reduction device 110, the lower limb exoskeleton device 120, the tension monitoring device 150 and the control device 160 can be connected through a network, for example, a wired, wireless communication link or an optical fiber cable, etc.

[0081] According to the embodiment of the present application, the weight loss device includes a weight loss spring and a floating spring. The influence of the center of gravity floating on the output tension of the weight loss device can be reduced by fine-tuning the stretching length of the floating spring. The stretching distance of the spring of the weight loss device and the foot pressure are combined to predict the rotation angle of the weight loss motor, and the joint operation angle is used to predict the rotation angle of the floating motor. The influence of the center of gravity floating on the weight loss is considered, so that the support weight of the user is accurately reduced during the exercise rehabilitation training, and a smooth and safe walking environment is provided.

[0082] According to the embodiment of the present application, the lower extremity exoskeleton device includes a foot pressure detector for measuring the foot pressure of the user during walking.

[0083] According to the embodiment of the present application, the lower extremity exoskeleton device further includes a joint module driving module, which includes a driving motor for driving the joint of the user to move to make the user walk on the treadmill device, and an encoder detector for measuring the joint operation angle of the user during walking.

[0084] According to the embodiment of the present application, the driving motor can be used to drive the joint to move in a specific direction, and the driving motor can be composed of a direct current motor, a planetary reduction unit, and a torque sensor.

[0085] According to the embodiment of the present application, the encoder detector can be used to measure the joint operation angle and then feedback the rotation of the motor. In order to facilitate installation, the encoder detector can adopt a Hall encoder.

[0086] According to the embodiment of the present application, the joint module driving module further includes a brake for supplying power to the driving motor in the case of power failure of the lower extremity exoskeleton device.

[0087] According to the embodiment of the present application, the brake can be used to maintain the state of the driving motor in the state of power failure, and then provide support force to prevent the user from falling and causing secondary injury.

[0088] According to the embodiment of the present application, the control device includes a distance sensor for measuring the stretching distance of the spring.

[0089] For example, the weight loss device is realized by using a weight loss spring and a floating spring structure. During use, the range of the weight loss spring is stretched or compressed by the weight loss motor to realize different tensions. The floating amplitude of the lower extremity exoskeleton device is calculated according to the gait, and the range of the floating spring is controlled in real time to compensate for the change of the output tension of the weight loss device caused by the up and down floating during walking, and then the constant force output is realized.

[0090] Figure 4 The installation position of the distance sensor according to the embodiment of the present application is shown.

[0091] As shown in Figure 4 , the weight reduction device in the support device 170 is pulled up by the pulley 410, and the weight reduction motor 112 is fixed in the relative position on the first spring fixing frame by the first lead screw 420. At the same time, the floating motor 114 is fixed in the relative position on the second spring fixing frame by the second lead screw 430. The two ends of the weight reduction spring 111 are connected with the first spring fixing frame and the second spring fixing frame respectively. The first distance sensor 440 and the second distance sensor 450 are installed on the first spring fixing frame and the second spring fixing frame respectively.

[0092] According to the setting of the weight reduction requirement, the weight reduction motor 112 is started to pull the weight reduction spring 111 to stretch, and the spring stretching distance is obtained. The spring stretching distance is measured by using the first distance sensor 410 and the second distance sensor 420 in pairs. The weight reduction motor rotation angle of the weight reduction motor 112 and the foot pressure of the lower limb exoskeleton device are combined and adjusted, so that the output tension of the weight reduction device meets the requirements. In the process of gravity floating, the stretching of the floating spring is fine-tuned by using the floating motor 114, so as to compensate for the change of the output tension caused by the up and down floating in the process of walking, and then the constant force output is realized.

[0093] For example, the distance sensor can be a laser distance measuring device.

[0094] According to the embodiment of the present application, the formula of the weight reduction motor rotation angle is:

[0095] (1)

[0096] Φ1 is the weight reduction motor rotation angle, f z is a coupling function, the output tension is x, the foot pressure is y i , the spring stretching distance is xl, the spring tension of the weight reduction spring is x T , the weight reduction weight of the weight reduction device is m j .

[0097] According to the embodiment of the present application, the formula of the coupling function f z is:

[0098] (2)

[0099] f is a control function between the output tension, the foot pressure and the spring tension, f1 is a foot pressure compensation function, f2 is a spring function, f3 is a control function between the weight reduction motor and the spring stretching distance, and the formulas of f, f1, f2 and f3 are as follows:

[0100] (3)

[0101] (4)

[0102] (5)

[0103] (6)

[0104] The weight of the user is m r , k is the elastic coefficient of the weight reduction spring.

[0105] According to the embodiment of the present application, the grey prediction algorithm can be used to predict the operation of the weight reduction motor.

[0106] For example, let X1, X2…X6 represent the weight reduction weight m j , the output tension x, the spring tension x T , the spring stretching distance xl, the plantar pressure y0 of the left foot, and the plantar pressure y1 of the right foot of the weight reduction device, respectively.

[0107] (7)

[0108] As , n is the number of collected data points, and the production is obtained through one accumulation.

[0109] (8)

[0110] wherein, .

[0111] The whitening equation group is established as follows:

[0112] (9)

[0113] Exemplarily, the least square method is used to solve , and then the differential equation formula (10) is solved, so that the prediction function of the rotation angle of the weight reduction motor (such as formula 1) is generated according to the differential equation formula of m j , x, x T , xl, y0, and y1, respectively, and the predicted value of the rotation angle of the weight reduction motor can be obtained.

[0114] (10)

[0115] wherein, t=2, 3…n.

[0116] The predicted value is obtained by the inversion column addition generation algorithm. For example, the predicted value of the weight reduction weight m j is .

[0117] (11)

[0118] An example of the weight loss device is a weight loss device with a weight loss weight m j , an output tension x, a spring tension x of the weight loss spring T , a spring extension distance xl, a plantar pressure y0 of the left foot, and a plantar pressure y1 of the right foot, and a weight loss motor rotation angle prediction value.

[0119] According to an embodiment of the present application, the prediction model is a grey prediction model, and the input of the spring extension distance, the plantar pressure, and the output tension into the prediction model of the weight loss motor rotation angle obtains the weight loss motor rotation angle prediction value, which comprises: inputting the spring extension distance, the plantar pressure, and the output tension into the grey prediction model to obtain a predicted weight loss weight of the weight loss device; and obtaining the weight loss motor rotation angle prediction value according to an error value between the predicted weight loss weight and a preset value.

[0120] According to the error value between the predicted weight loss weight and the preset value, a control device can be used for feedback control to obtain an adjusted length of the weight loss spring. The weight loss motor rotation angle prediction value is determined according to the adjusted length of the weight loss spring.

[0121] According to an embodiment of the present application, the control device further comprises: a main control module, configured to feedback control the operation of the weight loss motor according to an error value between the predicted weight loss weight and a preset value.

[0122] For example, according to the error value between the prediction value and the preset value, a PID (Proportional-Integral-Derivative) feedback control is used to control the operation of the weight loss motor.

[0123] During the walking of the user, the change of the body center of gravity causes the traction to float up and down, and then causes the output tension to change, which causes the user to feel uncomfortable during the rehabilitation training. If the rope is pulled in real time, the foot cannot touch the ground to form a so-called space step, which is not conducive to rehabilitation.

[0124] According to an embodiment of the present application, the formula of the floating motor rotation angle is as follows:

[0125] (12)

[0126] Φ2(t) is the floating motor rotation angle at time t, m is the spring tension x T at time t, and h(t) is a control function between the floating motor rotation angle Φ2(t) at time t and the center of gravity height change value h(t) of the user, and the formula of the center of gravity height change value h(t) is as follows:

[0127] (13)

[0128] The thigh length of the user is l0, the calf length of the user is l1, and the joint operating angle includes the hip joint angle θ0 and the knee joint angle θ1. For example, the function relationship of the floating motor rotation angle is solved by using a grey prediction algorithm (such as formula (12)).

[0129] The output tension of the weight reduction device changes due to the up-and-down floating during walking. Through the prediction of the floating motor rotation angle, the output tension of the weight reduction device can achieve constant output, and the user can walk smoothly.

[0130] Figure 5 A structural block diagram of a lower limb rehabilitation training system for intelligent weight reduction according to another embodiment of the application is shown.

[0131] As shown in Figure 5 , the lower limb rehabilitation training system for intelligent weight reduction 500 of this embodiment includes a weight reduction device 110, a lower limb exoskeleton device 120, a treadmill device 130, a support device 140, a tension monitoring device 150, a control device 160, and a human-computer interaction device 170.

[0132] The treadmill device 130 can include a treadmill track, a pressure sensor, a displacement sensor, a rolling motor, and is connected to the support device 140 and installed on a flat ground. The treadmill device 130 can also carry a pressure sensor inside. The displacement sensor is connected to a direct current power supply circuit; the treadmill device 130 can be provided with a free walking mode and a set speed mode. In the free walking mode, the user's walking does not change the relative position between the user and the treadmill. The installation direction of the treadmill device 130 and the handrails of the support device 140 is fixed, and the handrails are arranged on both sides of the support device 140 in the vertical direction.

[0133] The weight reduction device 110 is connected to the body of the user wearing the lower limb exoskeleton device 120 to reduce the stress on the lower limbs of the user during walking on the treadmill device 130. Figure 3

[0134] The lower limb exoskeleton device 120 is used to measure the plantar pressure and joint operating angle of the user during walking.

[0135] The tension monitoring device 150 is used to measure the output tension of the weight reduction device 110.

[0136] The control device 160 is used to input the spring stretching distance, the plantar pressure, and the output tension into the prediction model of the weight reduction motor rotation angle to obtain the prediction value of the weight reduction motor rotation angle; and input the joint operating angle into the prediction model of the floating rotation angle to obtain the prediction value of the floating rotation angle.

[0137] ​The control device 160 further comprises an exoskeleton robot motion control unit, a weight reduction unit control unit, a treadmill control unit, and a main control unit.

[0138] The exoskeleton robot motion control unit not only preprocesses the plantar pressure sensor data, but is not limited to signal amplification, analog-to-digital conversion, and filtering processing, etc. The exoskeleton robot motion control unit mainly controls a length adjustment subunit, a joint module driving subunit, and a waist adjustment subunit, etc. The waist adjustment subunit and the length adjustment subunit each comprise an adjustment motor, a speed reducer, a rolling gear device, and laser ranging, etc. The exoskeleton robot motion control unit is connected with the lower limb exoskeleton device 120.

[0139] The weight reduction unit control unit is used for real-time detection of the length of the adjustment weight reduction spring by laser ranging. The weight reduction unit control unit is connected with the weight reduction device 110, and uses PID feedback control to adjust the operation of the weight reduction motor. It can also be used for real-time detection of the length of the adjustment floating spring by laser ranging, and uses PID feedback control to adjust the operation of the floating motor.

[0140] The treadmill control unit is used for controlling the running speed of the treadmill according to the required parameters of the main control motor.

[0141] The main control unit is used for generating control commands according to the setting parameters of the human-computer interaction device 170 and the running parameters of each device, to control the normal operation of each device.

[0142] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0143] Those skilled in the art can understand that the features described in various embodiments of the present application can be combined and / or integrated in various combinations, even if such combinations or integrations are not explicitly described in the present application. In particular, the features described in various embodiments of the present application can be combined and / or integrated in various combinations without departing from the spirit and teachings of the present application. All such combinations and / or integrations fall within the scope of the present application.

[0144] The above described embodiments of the application have been described. However, these embodiments are merely meant to be illustrative and not limiting of the scope of the application. Although each of the embodiments has been described separately, this does not mean that measures from the individual embodiments cannot be used advantageously in combination. Numerous alternatives and modifications will be apparent to those skilled in the art without departing from the scope of the present application, which is defined in the appended claims.

Claims

1. A lower limb rehabilitation training system for intelligent weight loss, characterized in that, The system comprises: a weight reduction device connected to the body of a user wearing a lower limb exoskeleton device to reduce the force on the lower limbs of the user during walking on a treadmill device, the weight reduction device comprising a weight reduction spring, a weight reduction motor, a floating motor and a floating spring; the weight reduction motor is used to adjust the stretching length of the weight reduction spring according to the rotation angle of the weight reduction motor, so as to obtain the spring stretching distance; the floating motor is used to fine-tune the stretching length of the floating spring according to the rotation angle of the floating motor, so as to reduce the influence of the center of gravity of the user on the output tension of the weight reduction device during the walking process; the lower limb exoskeleton device is used to measure the plantar pressure and joint operating angle of the user during the walking process; a tension monitoring device is used to measure the output tension of the weight reduction device; a control device is used to input the spring stretching distance, the plantar pressure and the output tension into a prediction model of the rotation angle of the weight reduction motor to obtain a predicted value of the rotation angle of the weight reduction motor, the prediction function in the prediction model of the rotation angle of the weight reduction motor being generated according to the weight reduction weight of the weight reduction device, the spring tension of the weight reduction spring, the spring stretching distance, the output tension and the differential equation formula of the plantar pressure of the left foot of the user and the plantar pressure of the right foot of the user; the joint operating angle and the center of gravity height change value of the user are input into a prediction model of the floating rotation angle to obtain a predicted value of the floating rotation angle, so as to maintain the constant output of the output tension by using the predicted value of the floating rotation angle; the formula of the prediction function in the prediction model of the rotation angle of the weight reduction motor is as follows: Φ1 is the rotation angle of the weight-reducing motor, f z is a coupling function, the output tension is x, the plantar pressure is y i , the spring stretching distance is xl, the spring tension of the weight-reducing spring is x T , the weight-reducing weight of the weight-reducing device is m j ; The coupling function f z The formula is: f is a control function between the output tension, the plantar pressure and the spring tension, f1 is a plantar pressure compensation function, f2 is a spring tension function, f3 is a control function between the weight reduction motor and the spring stretching distance, and the formulas of f, f1, f2 and f3 are as follows: the weight of the user is m r k is the elastic coefficient of the weight loss spring the function relationship of the floating rotation angle is solved by using the prediction model, and the formula of the function relationship of the floating rotation angle is as follows: Φ2(t) is the rotation angle of the floating motor at time t, m is the spring tension at time t T a control function between the function f(t) and the user's center of gravity height change value h(t), the formula of the center of gravity height change value h(t) is as follows: the length of the thigh of the user is l0, the length of the calf of the user is l1, and the joint operating angle includes the hip joint angle θ0 and the knee joint angle θ1.

2. The system of claim 1, wherein, the control device comprises a distance sensor for measuring the spring stretching distance.

3. The system of claim 1, wherein, the lower limb exoskeleton device comprises a plantar pressure detector for measuring the plantar pressure of the user during the walking process.

4. The system of claim 3, wherein, the lower limb exoskeleton device further comprises a joint module driving module, and the joint module driving module comprises: a driving motor for driving the joints of the user to move, so that the user walks on the treadmill device; an encoder detector for measuring the joint operating angle of the user during the walking process.

5. The system of claim 4, wherein, the joint module driving module further comprises a brake for supplying power to the driving motor in the case of power failure of the lower limb exoskeleton device.

6. The system of claim 1, wherein, The prediction model inputs the spring stretching distance, the plantar pressure and the output tension to obtain a predicted value of the rotation angle of the weight-reducing motor, and the prediction model comprises: The prediction model inputs the spring stretching distance, the plantar pressure and the output tension to obtain a predicted value of the rotation angle of the weight-reducing motor, and the prediction model comprises: The prediction model inputs the spring stretching distance, the plantar pressure and the output tension to obtain a predicted value of the rotation angle of the weight-reducing motor, and the prediction model comprises:

7. The system of claim 6, wherein, The control device further comprises: The main control module is configured to feedback control the operation of the weight-reducing motor according to the error value between the predicted weight-reducing weight and the preset value.

Images