TWI729726B - Methods of modeling, judging running state and compensating for lower limb movement system - Google Patents

Abstract

A method for establishing a model of a lower limb movement system, which includes the steps of collecting parameters such as a motor speed command, a user's foot force and actual knee joint angle, during steady state operation of the lower limb movement system. The fuzzy neural network modeling method is used to identify and model the lower limb movement system. The motor speed command and the user's foot force are used as input parameters, and the actual angle of the knee joint is used as the output parameter to establish a lower limb movement system model. With this model, the operating state of the lower limb movement system can be judged, and at the same time, the control signal compensation method of the controller can be used to compensate and adjust the operation of the lower limb operating system to keep the lower limb movement system running more stable and accurate.

Description

Modeling method, running state judgment method and compensation method of lower limb movement system

The invention relates to a sports fitness system or device, in particular to a lower limb movement system, and relates to a method for constructing an operation model of the lower limb movement system and a method for judging and compensating the operation state.

With the trend of smart manufacturing in industrial productivity 4.0, Taiwan is currently focusing on smart manufacturing and smart machinery. An important part of this is the data collection, modeling and prediction of smart systems composed of smart machinery and equipment, and Use the built model to improve the production efficiency of smart machinery, equipment and other systems, in order to maximize the overall social benefits in Industrial Productivity 4.0.

In addition to modeling the smart system through traditional mathematical model analysis, there are many uncertain parameters and models that are difficult to define in the smart system model itself. In this regard, it is currently possible to perform approximation and modeling in mathematical models through methods such as neural network (also known as artificial neural network; artificial neural network, abbreviated as ANN), genetic algorithm, etc. Under the condition that the amount of collected data is large enough and the signal is constantly excited, the mathematical model of the intelligent system established by the foregoing method has high accuracy; the mathematical model established can be used for the design of the controller and can also be used for the failure of the intelligent system. Make predictions and judgments.

With the implementation of the concept of healthy life, modern people use fitness equipment to exercise more and more frequently; at the same time, industrial productivity 4.0 drives the intelligent development of fitness equipment. In addition to fitness equipment that needs to meet the fitness functions of users, manufacturers and users are also paying more attention to its safety performance. In order to enable users to obtain more diverse fitness modes, the design of the controller in the fitness equipment is very important. For this, the system's more accurate twin model (Twin Model) can be used to simulate the operating status of the system and perform the proportional integral controller. The parameters are adjusted, and then the compensator is used to compensate the deviation of the system due to uncertainty and external interference, so as to improve the accuracy of the system.

The basic data of the fitness equipment system can be uploaded to the back-end database storage via WiFi network, and device applications (APP) can be written to facilitate users to control the exercise mode of the fitness equipment system, increase the applicability of the fitness equipment system and electronic communication Cross-field integration. Then use the established mathematical model to predict the failure and maintenance of the fitness equipment system, and realize the intelligentization of the fitness equipment system's control design and operation status prediction, status diagnosis, system maintenance and other functions.

Among fitness equipment, sports training equipment, equipment and functions for lower limbs are becoming more and more diversified. Driven by the development of intelligence, the use of mathematical models to monitor and predict the real-time operating status of the lower extremity motion system in fitness equipment, so that managers can perform maintenance operations on the lower extremity motion system in time to ensure its safe operation for users Use it at any time.

Therefore, in the field of lower extremity motion system of fitness equipment, how to construct a highly accurate operating model of the lower extremity motion system and judge the operating state of the lower extremity motion system based on this model, as well as the compensation adjustment of the operating model, has become One of the problems that those skilled in the art want to actively solve.

The purpose of the present invention is to provide a method for constructing an operating model of the lower extremity motion system, by which the operating state of the lower extremity motion system can be judged; and to compensate and adjust the lower extremity motion system during operation; The component parts of the lower limb movement system are modeled to make more accurate judgments on the operating status of the system.

In order to achieve at least one of the advantages or other advantages, the first embodiment of the present invention proposes a method for establishing a lower extremity motion system model, which can be used to judge the operating state of the lower extremity motion system. The method mainly includes: collecting The parameters of the lower extremity motion system during steady-state operation. These parameters mainly include the speed command of the motor, the user’s foot force and the actual angle of the knee joint of the lower extremity motion system. These parameters are used to calculate the parameters by the fuzzy neural network modeling method. Recognition modeling of the lower limb movement system is carried out to establish the lower limb movement system model. In the established model, the speed command of the motor and the force exerted by the user's foot are used as input parameters, and the actual angle of the knee joint is used as the output parameter to establish the corresponding relationship between the output parameters and the input parameters in the model.

In some embodiments, the parameters collected in the method of establishing the lower limb movement system model further include the actual speed of the motor, the motor current, and the knee joint angle command of the lower limb movement system.

In order to achieve at least one of the advantages or other advantages, the second embodiment of the present invention proposes a method for judging the operating state of the lower limb movement system, which can be judged through the lower limb movement system model, and the method mainly includes: Recognize and model a lower limb movement system in a steady state by using a fuzzy neural network modeling method to establish a lower limb movement system model; detect the input parameters and output parameters of the lower limb movement system during actual operation; by the movement of the lower limb The system model obtains the output parameters during analog operation; when the error value between the actual operation output parameter of the lower limb movement system and the output parameter during model operation is greater than an allowable error value, it is judged that the operation state of the lower limb movement system is abnormal.

In order to achieve at least one of the advantages or other advantages, the third embodiment of the present invention proposes a method for establishing a lower extremity motion system model. The lower extremity motion system has a plurality of components, and the model can be used to determine the operating state of the lower extremity motion system. To make a judgment, the method mainly includes: collecting the input and output of each component of the lower limb movement system in steady state operation; using the collected input and output data to perform the fuzzy neural network modeling method for each component of the lower limb movement system Recognition and modeling to establish multiple component models corresponding to each component of the lower limb movement system.

In some embodiments, the plurality of components in the method for establishing a lower limb movement system model may include a driver, a motor, a speed reduction gear set, a screw set, and a linkage mechanism.

In order to achieve at least one of the advantages or other advantages, the fourth embodiment of the present invention proposes a method for judging the operating state of a lower limb movement system. The lower limb movement system has a plurality of components, which can be operated by constructing a corresponding model. To make a judgment, the method mainly includes: identifying and modeling the plural parts of the lower extremity motion system by a fuzzy neural network modeling method, so as to establish a model of each part of the lower extremity motion system when the plural parts of the lower extremity motion system are operating in a steady state; Detect the input and output of the plurality of components during the actual operation of the lower extremity movement system; obtain the output during model operation from the model of each component; when the actual operation output of a certain part of the lower extremity movement system is between the output during model operation When the error of is greater than an allowable error value, it is judged that the operating state of the component in the lower limb movement system is abnormal.

In order to achieve at least one of the advantages or other advantages, the fifth embodiment of the present invention proposes a method for establishing a compensator of the lower limb movement system, which can compensate the control signal of the lower limb movement system, and the method mainly includes: collecting the The parameters of the lower limb movement system; and using the parameters to train a fuzzy neural network compensator, where the input parameters are the angle error, the change in the angle error per unit time, the angle error differential, the angular velocity error, and the angular velocity error unit One or any combination of time change and angular velocity error differential, the output parameter is the compensation signal.

In order to achieve at least one of the advantages or other advantages, the sixth embodiment of the present invention proposes a method for compensating the control signal of the lower extremity motion system controller. The method mainly includes: collecting the parameters of the lower extremity motion system; and using the Parameter training a fuzzy neural network compensator, where the input parameters can be angle error, angle error change per unit time, angle error differential, angular velocity error, angular velocity error change per unit time, angular velocity error differential One or any combination thereof, the output parameter is the compensation signal; the parameter when the lower limb movement system is detected; the compensation signal is obtained through the fuzzy neural network compensator after training; the compensation signal is used to move the lower limb The control signal of the system controller is compensated.

Therefore, the operating state of the lower extremity motion system can be judged by using the operating model of the lower extremity motion system provided by the present invention; at the same time, the lower extremity motion system can be adjusted through the trained fuzzy neural network compensator; further, And through the component model of the lower extremity motion system, the operating status of each component of the lower extremity motion system can be more accurately judged.

The above description is only an overview of the technical solution of the present invention. In order to understand the technical means of the present invention more clearly, it can be implemented in accordance with the content of the specification, and in order to make the above and other objectives, features and advantages of the present invention more obvious and understandable. In the following, the preferred embodiments are specially cited, and in conjunction with the accompanying drawings, the detailed description is as follows.

S11~S12: steps

S21~S24: steps

S31~S32: steps

S41~S44: steps

S51~S52: steps

The included drawings are used to provide a further understanding of the embodiments of the present application, which constitute a part of the specification, are used to illustrate the embodiments of the present application, and are consistent with the text description. Let's explain the principle of this application. Obviously, the diagrams in the following description are only some examples of the application, and are not used to limit the implementation of the application to these. For those with ordinary knowledge in the field, they can of course be derived from these diagrams. Other schemas. The schema includes:

[Figure 1] is a flow chart of a method of establishing a lower limb movement system model of the present invention.

[Figure 2] is a flowchart of a method of judging the operating status of the lower limb movement system of the present invention.

[Figure 3] is a flow chart of a method for establishing a model of a lower limb movement system with multiple components of the present invention.

[Figure 4] is a flowchart of a method of judging the operating state of a lower limb movement system with multiple components of the present invention.

[Figure 5] is a flow chart of a method for establishing a compensator of a lower limb movement system of the present invention.

The specific structure and functional details disclosed herein are only representative, and are used for the purpose of describing exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and should not be construed as being limited only to the embodiments set forth herein.

In the description of the present invention, it should be understood that the terms "center", "lateral", "upper", "lower", "left", "right", "vertical", "horizontal", "top", " The orientation or positional relationship indicated by "bottom", "inner", "outer", etc. are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the pointed device or The component must have a specific orientation, or be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, it is limited to "first" and "second" The feature of can explicitly or implicitly include one or more of the feature. In the description of the present invention, unless otherwise specified, "plurality" means two or more. In addition, the term "including" and any variations thereof all mean "including at least".

In the description of the present invention, it should be noted that the terms "installed", "connected", and "connected" should be understood in a broad sense unless otherwise clearly specified and limited. For example, they can be fixed or detachable. It can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two components. For those with ordinary knowledge in the field, the specific meanings of the above terms in the present invention can be understood in specific situations.

The terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments. Unless the context clearly dictates otherwise, the singular forms "a" and "one" used herein are also intended to include the plural. It should also be understood that the terms "including" and/or "comprising" used herein specify the existence of the stated features, integers, steps, operations, units and/or components, and do not exclude the existence or addition of one or more Other features, integers, steps, operations, units, components, and/or combinations thereof.

Under the dual influence of the concept of healthy living and the development of smart manufacturing, people's demand for smart fitness exercise equipment has also shown explosive growth, especially smart lower limb exercise equipment. Please refer to FIG. 1, which is a flowchart of a method for establishing a lower limb movement system model of the present invention. In order to achieve at least one of the advantages or other advantages, the first embodiment of the present invention proposes a method for establishing a lower extremity motion system model, which can be used to judge the operating state of the lower extremity motion system. The method mainly includes the following steps :

S11: Collect the parameters of the lower limb movement system in steady state operation, where the stable The fixed operating state refers to the ideal operating state of the lower limb movement system equipment to be modeled at the factory or the perfect operating state after adjustment. These parameters mainly include the speed command of the motor, the force exerted by the user's foot and the lower limbs. The actual angle of the knee joint of the motion system;

S12: Use these parameters to identify and model the lower extremity motion system by using a fuzzy neural network modeling method. Use the speed command of the motor and the force of the user's foot as input parameters, and the actual angle of the knee joint as output parameters to establish the model. The corresponding relationship between output parameters and input parameters is used to establish the model of the lower limb movement system.

In order to make the established lower extremity motion system model cover its influencing factors as much as possible, the parameters collected in the method for establishing the lower extremity motion system model of the present invention further include the actual speed of the motor, the motor current, and the lower extremity motion system. The angle of the knee joint and other information.

Please refer to FIG. 2, which is a flowchart of a method for judging the operating state of the lower limb movement system of the present invention. In order to achieve at least one of the advantages or other advantages, the second embodiment of the present invention proposes a method for judging the operating state of the lower limb movement system, which can be judged through the lower limb movement system model, and the method mainly includes the following step:

S21: Recognizing and modeling a lower limb movement system in a steady state by using a fuzzy neural network modeling method to establish a lower limb movement system model;

S22: Detect input parameters and output parameters during actual operation of the lower limb movement system, where the input parameters are the speed command of the motor and the force exerted by the user's foot, and the output parameter is the actual angle of the knee joint;

S23: Obtain the output parameters during model operation from the lower limb movement system model; and

S24: When the actual operation output parameters and model operation of the lower limb movement system When the error value between the output parameters is greater than an allowable error value, it is judged that the operating state of the lower limb movement system is abnormal.

It should be particularly noted that the above-mentioned stable operating state refers to the ideal operating state of the lower limb movement system equipment to be modeled in accordance with the ideal operating state set at the factory or the perfect operating state after adjustment. According to the specific abnormal results of the operation status of the lower limb movement system, timely maintenance or replacement of the lower limb movement system shall be carried out to ensure the stable and safe operation of the equipment.

In other words, through the established lower limb movement system model and the actual lower limb movement system operation, the real machine condition is detected. When the error between the output of the real system and the output of the model system reaches a certain ratio, a warning message is generated to stop the machine. Carry out maintenance to ensure the perfection of the lower limb movement system and the safety of the maintenance system. In addition, it can also be considered that if the absolute value of the error between the real system and the model system exceeds a certain value in a certain time interval, it is judged that the real lower limb movement system should be changed from the original normal condition, so it can be repaired through warning reminders. maintenance.

Please refer to FIG. 3, which is a flow chart of a method for establishing a model of a lower limb movement system with a plurality of components according to the present invention. In order to achieve at least one of the advantages or other advantages, the third embodiment of the present invention proposes a method for establishing a lower limb movement system model. The lower limb movement system has a plurality of components, and the corresponding component models can be used to create these models. To judge the respective operating status of the components, the method mainly includes the following steps:

S31: Collect the input and output of each component of the lower extremity motion system during steady-state operation. The stable operation state refers to the ideal operating state of the lower extremity motion system equipment components of the present invention set at the factory or the perfect operating state after adjustment. ；

S32: Use the collected input and output data to The components are identified and modeled by a fuzzy neural network modeling method to establish multiple component models corresponding to each component of the lower limb movement system.

In order to make the lower extremity motion system model cover its influencing factors as much as possible, the plural components in the method for establishing the lower extremity motion system model of the present invention are mainly the drive, the motor, the speed reduction gear set, and the screw. Groups and linkage agencies, etc.

Please refer to FIG. 4, which is a flowchart of a method of judging the operating state of a lower limb movement system with a plurality of components according to the present invention. In order to achieve at least one of the advantages or other advantages, the fourth embodiment of the present invention proposes a method for judging the operating status of the lower limb movement system. The lower limb movement system has a plurality of components, which can be operated by the lower limb movement system model. To judge the status, the method mainly includes the following steps:

S41: Recognizing and modeling the plurality of components of the lower limb movement system by a fuzzy neural network modeling method to establish a model of each component of the lower limb movement system when the plurality of components are operating in a steady state;

S42: Detect the input and output of the plurality of components during the actual operation of the lower limb movement system;

S43: Obtain the output during model operation from the model of each component; and

S44: When the error between the actual operation output of a certain part of the lower limb movement system and the output during model operation is greater than an allowable error value, it is judged that the operating state of the part in the lower limb movement system is abnormal.

With this method, the abnormal components and detailed abnormal conditions in the lower limb movement system can be further clarified, and then the individual abnormal components can be repaired and maintained in a targeted manner. In this way, the judgment of the abnormal operation status of the lower limb movement system will be faster and more accurate.

Please refer to FIG. 5, which is a flowchart of a method for establishing a compensator of a lower limb movement system of the present invention. In order to achieve at least one of the advantages or other advantages, the fifth embodiment of the present invention proposes a method for establishing a compensator of the lower limb movement system, which can compensate the control signal of the lower limb movement system. The method mainly includes the following steps:

S51: Collect the parameters of the lower limb movement system; and

S52: Use this parameter to train a fuzzy neural network compensator, where the input parameters can be angle error, angle error change per unit time, angle error differential, angular velocity error, angular velocity error change per unit time, and angular velocity error Any one of the micro-components or any combination thereof, the output parameter is the compensation signal.

In one embodiment, the above-mentioned angle is the angle of the knee joint. The lower extremity motion system compensator established by this method can compensate and adjust the lower extremity motion system.

In order to achieve at least one of the advantages or other advantages, the sixth embodiment of the present invention proposes a method for compensating the control signal of the lower extremity motion system controller, which can make timely and appropriate adjustments to the operation of the lower extremity motion system. The method mainly includes The following steps: Collect the parameters of the lower limb movement system; and use the parameters to train a fuzzy neural network compensator, where the input parameters can be angle error, angle error change per unit time, angle error differential, angular velocity error, Any one or any combination of angular velocity error per unit time change, angular velocity error differential, as the output parameter is the compensation signal; detects the parameters of the lower limb movement system during operation; the fuzzy neural network compensator completed through training Obtain the compensation signal; use the compensation signal to compensate the control signal of the lower limb motion system controller. In one embodiment, the angle is the angle of the knee joint. Through the compensation method, the control signal of the controller in the lower limb movement system model can be compensated or adjusted to further improve and ensure the operation of the lower limb movement system. Time stability and accuracy.

Therefore, by using a model of the lower limb movement system operation provided by the present invention, the operation status of the lower limb movement system can be judged; at the same time, the lower limb movement system can be adjusted through the established fuzzy neural network compensator to ensure and improve The operating state of the lower limb movement system is maintained stable and accurate. Through various methods of the lower limb movement system model construction, operating state judgment and compensation adjustment in the present invention, the lower limb movement system can be maintained and maintained in real time to ensure the stable and safe operation of the lower limb movement system.

Through the detailed description of the above preferred embodiments, it is hoped that the characteristics and spirit of the present invention can be described more clearly, and the scope of the present invention is not limited by the preferred embodiments disclosed above. On the contrary, the purpose is to cover various changes and equivalent arrangements within the scope of the patent for which the present invention is intended.

S11~S12: steps

Claims (8)

A method for establishing a model of the lower limb movement system, including: Collect the parameters of the lower limb movement system when it is operating in a steady state, the parameters include the speed command of the motor, the force exerted by the user's foot and the actual angle of the knee joint of the lower limb movement system; and Use this parameter to identify and model the lower limb movement system by a fuzzy neural network modeling method to establish a lower limb movement system model, where the speed command of the motor and the force exerted by the user’s foot are used as input parameters, and the knee The actual angle of the joint is used as an output parameter. For example, the method for establishing a lower limb movement system model in claim 1, wherein the parameters further include the actual speed of the motor, the motor current, and the knee joint angle command of the lower limb movement system. A method for judging the operating state of the lower limb movement system, including: Recognize and model a lower limb movement system in a steady state by using a fuzzy neural network modeling method to establish a lower limb movement system model; Detect the input parameters and output parameters of the lower limb movement system during actual operation; Obtain the output parameters during model operation from the lower limb movement system model; and When the error value between the actual operation output parameter of the lower limb movement system and the output parameter during model operation is greater than an allowable error value, it is judged that the operation state of the lower limb movement system is abnormal. A method for establishing a lower limb movement system model, the lower limb movement system having a plurality of components, and the method includes: Collect the input and output of each component of the lower limb movement system in steady state operation; The input and output are used to identify and model each component of the lower extremity motion system by a fuzzy neural network modeling method to establish a plurality of component models corresponding to each component of the lower extremity motion system. For example, in claim 4, a method for establishing a lower limb motion system model, the plurality of components include a driver, a motor, a speed reduction gear set, a screw set, and a linkage mechanism. A method for judging the operating state of a lower limb movement system, the lower limb movement system having a plurality of components, and the method includes: Recognizing and modeling the plurality of components of the lower extremity motion system by the fuzzy neural network modeling method, so as to establish the model of each component of the lower extremity motion system when the plurality of components are operating in a steady state; Detect the input and output of the multiple components during the actual operation of the lower limb movement system; Obtain the output during model operation from the model of each component; and When the error between the actual operation output of a certain component in the lower limb movement system and the output during model operation is greater than an allowable error value, it is determined that the operating state of the component in the lower limb movement system is abnormal. A method for establishing a compensator of a lower limb movement system can compensate the control signal of the lower limb movement system, and the method includes: Collect the parameters of the lower limb movement system; and Use this parameter to train a fuzzy neural network compensator, where the input parameters can be angle error, angle error change per unit time, angle error differential, angular velocity error, angular velocity error change per unit time, angular velocity error differential One or any combination of them, the output parameter is the compensation signal. A method for compensating the control signal of the lower limb movement system controller includes: Collect the parameters of the lower limb movement system; and Use this parameter to train a fuzzy neural network compensator, where the input parameters are angle error, angle error change per unit time, angle error differential, angular velocity error, angular velocity error change per unit time, angular velocity error differential One or any combination of them, the output parameter is the compensation signal; Detect the operating parameters of the lower limb movement system; Obtain the compensation signal through the trained fuzzy neural network compensator; The compensation signal is used to compensate the control signal of the lower limb motion system controller.

Images