Intelligent suspension safety guarantee method, system and device for rehabilitation training treadmill

Abstract

The application provides a kind of rehabilitation training treadmill with intelligent suspension safety guarantee method, system and device, comprising: the training data of the trainer is collected, the training data includes: body posture data and tension data;The training data is input into state judgment model, and training state data is obtained;According to the training state data, control instructions are obtained;The running state of the treadmill and the running state of the suspension device are controlled using the control instructions.The application solves the problem of excessive protection affecting the training effect and the inability to handle emergency situations in a timely manner in the prior art, and the potential safety hazard.

Description

Technical Field

[0001] This invention relates to the field of medical rehabilitation technology, and in particular to a method, system and device for intelligent suspension safety protection of a rehabilitation training treadmill. Background Technology

[0002] Many patients with stroke, traumatic brain injury, and spinal cord injury commonly experience slow walking, abnormal walking posture, and a tendency to fall, which seriously affects their quality of life.

[0003] For patients with lower limb dysfunction, numerous clinical studies have confirmed that weight-bearing gait training is one of the important means of rehabilitation therapy. During weight-bearing gait training, patients need to unload some of their body weight according to their own rehabilitation progress to reduce excess load on the lower limbs and achieve better rehabilitation training results.

[0004] Most treadmills have manual emergency stop settings, which cannot guarantee that users can activate the emergency stop device in time in the event of an accident. This is especially true for patients with lower limb dysfunction, who are more likely to fall during treadmill rehabilitation training and require a more convenient and timely emergency stop device to ensure user safety.

[0005] Patients have a certain ability to adjust their posture during rehabilitation training, which is the purpose and effect of such training. However, triggering the emergency stop device immediately upon detecting a potential fall, resulting in overprotection, can negatively impact the training effect. To make the safety device more intelligent, artificial intelligence methods are needed to optimize the safety system. Summary of the Invention

[0006] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide a method, system and device for intelligent suspension safety protection of rehabilitation training treadmills. This invention solves the problems of overprotection affecting training effect and inability to deal with emergencies in a timely manner, which pose safety hazards in the prior art.

[0007] To achieve the above objectives, the present invention provides the following solution:

[0008] A smart suspension safety method for a rehabilitation training treadmill includes:

[0009] Collect training data from trainees, including body posture data and tension data;

[0010] The training data is input into the state judgment model to obtain the training state data;

[0011] Control commands are obtained based on the training status data;

[0012] The control commands are used to control the operating status of the treadmill and the suspension device.

[0013] Preferably, the control commands include:

[0014] Treadmill normal speed operation command, treadmill deceleration operation command, treadmill emergency stop command.

[0015] Preferably, the control command is obtained based on the training state data, including:

[0016] The system measures the acceleration and attitude angles of the three axes to determine whether the trainee has a tendency to fall. If there is a tendency to fall, a deceleration command is generated for the treadmill; if there is no tendency to fall, a normal speed command is generated for the treadmill.

[0017] If the tension exceeds the pre-set threshold, an emergency stop command for the treadmill will be generated.

[0018] Preferably, the method for constructing the state judgment model is as follows:

[0019] Obtain a sample dataset; the sample dataset includes: a test set and a training set;

[0020] Based on the body posture data, obtain acceleration and attitude angle data features;

[0021] The tensile threshold data is obtained based on the height and weight data of the trainee;

[0022] An initial model is constructed based on the tensile threshold data, acceleration, and attitude angle data characteristics.

[0023] The initial model is trained using the training set to obtain the trained model;

[0024] The trained model is evaluated using the test set to obtain a state judgment model.

[0025] A smart suspension safety system for a rehabilitation training treadmill includes:

[0026] Information acquisition module, information processing module, communication module, and control module;

[0027] The information acquisition module and the information processing module are connected. The information processing module is connected to the control module through the communication module. The communication module is wirelessly connected to the treadmill and the suspension device.

[0028] The information acquisition module is used to collect the trainee's training data, which includes: body posture data and tension data;

[0029] The information processing module is used to generate control commands based on the training data;

[0030] The control module is used to control the operating status of the treadmill and the operating status of the suspension device according to the control commands.

[0031] Preferably, the communication module includes:

[0032] Both the first communication submodule and the second communication submodule are connected to the control module;

[0033] The first communication submodule is used for wireless communication with the treadmill, and the second communication submodule is used for wireless communication with the suspension device.

[0034] A smart suspension safety device for a rehabilitation training treadmill includes:

[0035] Suspension base, suspension column, suspension rod, suspension rope, tension sensor, attitude sensor, inverted T-shaped bracket, sling and safety belt body;

[0036] The suspension base is fixed to the front end of the treadmill's metal frame. One end of the suspension column is fixed to the suspension base, and the other end of the suspension column is connected to one end of the suspension rod. The other end of the suspension rod is connected to one end of the tension sensor via a suspension rope. The upper end of the inverted T-shaped bracket is connected to the other end of the tension sensor. The lower end of the inverted T-shaped bracket is connected to two straps above the main body of the safety belt. The lower ends of the two straps are connected to the main body of the safety belt. The posture sensor is attached to a preset position on the main body of the safety belt.

[0037] Preferably, the suspension rod is a bent right triangle.

[0038] Preferably, the length of the suspension rope is adjusted within a preset range.

[0039] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0040] This invention provides a method, system, and device for intelligent suspension safety assurance of a rehabilitation training treadmill. The method includes: collecting training data from the trainee, including body posture data and tension data; inputting the training data into a state judgment model to obtain training state data; obtaining control commands based on the training state data; and using the control commands to control the operating state of the treadmill and the suspension device. This invention determines the state of the treadmill and the trainee through body posture data and tension data, providing dual protection and improving the safety and training efficiency of the trainee. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 A flowchart illustrating a smart suspension safety assurance method for a rehabilitation training treadmill, provided by an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the control logic flow provided in an embodiment of the present invention;

[0044] Figure 3 A schematic block diagram illustrating the modules and their interrelationships provided in embodiments of the present invention;

[0045] Figure 4 A schematic diagram of the workflow provided for an embodiment of the present invention;

[0046] Figure 5 This is a structural diagram of the suspension device provided in an embodiment of the present invention.

[0047] Explanation of reference numerals in the attached figures:

[0048] 1-Suspension rod, 2-Suspension column, 3-Treadmill metal frame, 4-Suspension base, 5-Suspension rope, 6-Tension sensor, 7-Inverted T-shaped bracket, 8-Sling, 9-Safety belt body, 10-Safety belt preset position, 11-Posture sensor. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] The purpose of this invention is to provide a method, system, and device for intelligent suspension safety protection of rehabilitation training treadmills. This invention solves the problems of overprotection affecting training effects and inability to handle emergencies in the prior art, which pose safety hazards.

[0051] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] like Figure 1As shown, this invention provides a smart suspension safety method for a rehabilitation training treadmill, comprising:

[0053] Step 100: Collect training data from the trainee, including body posture data and tension data;

[0054] Step 200: Input the training data into the state judgment model to obtain training state data;

[0055] Step 300: Obtain control commands based on the training state data;

[0056] Step 400: Use the control commands to control the running status of the treadmill and the running status of the suspension device.

[0057] Specifically, the information acquisition module collects real-time data on the patient's body posture and tension during training; the information processing module determines the patient's training status based on pre-set parameter thresholds and generates control commands for each training status according to control logic; the suspension device's communication module sends control commands; the treadmill's communication module receives control commands; and the treadmill's control module controls the treadmill's operation according to the control commands.

[0058] Furthermore, the control commands include:

[0059] Treadmill normal speed operation command, treadmill deceleration operation command, treadmill emergency stop command.

[0060] Furthermore, control commands are obtained based on the training state data, including:

[0061] The system measures the acceleration and attitude angles of the three axes to determine whether the trainee has a tendency to fall. If there is a tendency to fall, a deceleration command is generated for the treadmill; if there is no tendency to fall, a normal speed command is generated for the treadmill.

[0062] If the tension exceeds the pre-set threshold, an emergency stop command for the treadmill will be generated.

[0063] Specifically, such as Figure 2 As shown, after the treadmill starts normally, posture sensor 11 acts as the first layer of safety, measuring the acceleration and posture angles along three axes to determine if the user is prone to falling. If a falling tendency is detected, a treadmill deceleration command is generated, allowing the user to adjust their posture and enhance training effectiveness. If no falling tendency is detected, a command to maintain the treadmill at normal speed is generated. The tension sensor 6 acts as the second layer of safety. If the tension exceeds a pre-set threshold, an emergency stop command is generated, and the suspension device provides support to the user, ensuring their safety. If the threshold is not exceeded, the system returns to the first layer of safety.

[0064] Furthermore, the method for constructing the state judgment model is as follows:

[0065] Obtain a sample dataset; the sample dataset includes: a test set and a training set;

[0066] Based on the body posture data, obtain acceleration and attitude angle data features;

[0067] The tensile threshold data is obtained based on the height and weight data of the trainee;

[0068] An initial model is constructed based on the tensile threshold data, acceleration, and attitude angle data characteristics.

[0069] The initial model is trained using the training set to obtain the trained model;

[0070] The trained model is evaluated using the test set to obtain a state judgment model.

[0071] like Figure 3 As shown, this embodiment also provides an intelligent suspension safety system for a rehabilitation training treadmill, including:

[0072] Information acquisition module, information processing module, communication module, and control module;

[0073] The information acquisition module and the information processing module are connected. The information processing module is connected to the control module through the communication module. The communication module is wirelessly connected to the treadmill and the suspension device.

[0074] The information acquisition module is used to collect the trainee's training data, which includes: body posture data and tension data;

[0075] The information processing module is used to generate control commands based on the training data;

[0076] The control module is used to control the operating status of the treadmill and the operating status of the suspension device according to the control commands.

[0077] like Figure 4 As shown, the information processing module is divided into two modes: model training and state detection.

[0078] Specifically, the preparation process involves model training, including the following steps: adjusting model parameters based on the user's rehabilitation status, data preprocessing, feature extraction, model training, model saving, and model accuracy testing. Threshold values ​​for the tension sensor 6 are set based on the user's height and weight. Simultaneously, a training classification sample dataset matching the user's physical condition is selected for training. Acceleration and posture angle data features collected by the posture sensor 11 are extracted, and artificial intelligence recognition technology is applied to distinguish abnormal behaviors from other normal behaviors. Model parameters are recorded and the model is saved. The effectiveness of the model is then evaluated using a test sample dataset.

[0079] In patient rehabilitation training, a state detection mode is used, including the following steps: data preprocessing, feature extraction, state classification, and command generation. A pre-trained model is directly used to extract features from the acceleration and posture angle data collected by the posture sensor 11 during rehabilitation training. The trained model is then used for classification to determine the user's body posture and rehabilitation training state, and relevant control commands are generated based on the body posture. For the tension sensor 6, a threshold set during preparation is used for direct state detection. If the reading detected by the tension sensor 6 during rehabilitation training is greater than the threshold, a stop command is generated; otherwise, a normal speed operation command is generated.

[0080] Furthermore, the communication module includes:

[0081] Both the first communication submodule and the second communication submodule are connected to the control module;

[0082] The first communication submodule is used for wireless communication with the treadmill, and the second communication submodule is used for wireless communication with the suspension device.

[0083] like Figure 5 As shown, this embodiment further provides an intelligent suspension safety device for a rehabilitation training treadmill, characterized in that it includes:

[0084] 4. Suspension base, 2. Suspension column, 1. Suspension rod, 5. Suspension rope, 6. Tension sensor, 11. Attitude sensor, 7. Inverted T-shaped bracket, 8. Sling and 9. Safety belt body;

[0085] The suspension base 4 is fixed to the front end of the metal outer frame 3 of the treadmill. One end of the suspension column 2 is fixed to the suspension base 4, and the other end of the suspension column 2 is connected to one end of the suspension rod 1. The other end of the suspension rod 1 is connected to one end of the tension sensor 6 through the suspension rope 5. The upper end of the inverted T-shaped bracket 7 is connected to the other end of the tension sensor 6. The lower end of the inverted T-shaped bracket 7 is connected to two straps 8 above the safety belt body 9. The lower ends of the two straps 8 are connected to the safety belt body 9. The posture sensor 11 is attached to a preset position 11 of the safety belt body 9.

[0086] The preset position shown is the center connection point.

[0087] Furthermore, the suspension rod 1 is a bent right-angled triangle.

[0088] Furthermore, the length of the suspension rope 5 is adjusted within a preset range.

[0089] Specifically, the preparation process is as follows: When the user wears the seat belt, it is necessary to ensure that the seat belt fits tightly against the body to bear the force and ensure that the posture sensor 11 is located directly behind the body so that it can accurately capture the body posture data.

[0090] Determine the weight reduction for normal training based on the user's physical condition and recovery progress. Adjust the length of the suspension rope 5 so that the reading of the tension sensor 6 is within the specified range.

[0091] In the signal processing module, a threshold of 6 for the tension sensor is set to deal with falls. The basic parameters of the treadmill, normal training speed and deceleration adjustment speed are set according to the user's rehabilitation status.

[0092] Switch the signal processing module to model training mode, input the user's height, weight, and other data, and the module will find matching data from the training sample dataset to train the model and save the trained model.

[0093] Normal usage: Switch the signal processing module to status detection mode to detect the user's body posture and rehabilitation training status in real time, start the treadmill, and begin rehabilitation training with the suspension device reducing weight.

[0094] Fall Response: The first layer of safety is activated. Posture sensor 11 measures the acceleration and posture angle along three axes to determine if the user is prone to falling. If a fall is detected, the control platform issues a deceleration command to the treadmill, allowing the user to adjust their posture and enhance training effectiveness. If the user fails to adjust, the second layer of safety is activated. When the reading of tension sensor 6 exceeds a threshold, the control platform issues an emergency stop command to the treadmill. Simultaneously, the suspension components provide support to the user, ensuring their safety.

[0095] The beneficial effects of this invention are as follows:

[0096] This invention is designed for patients with lower limb dysfunction, and it specifies the environment in which rehabilitation training can be performed, making it highly specific and professional.

[0097] The suspension device described in this invention can reduce weight and assist in patient rehabilitation training. Patients can unload part of their own weight according to their own rehabilitation progress, reducing the excess load on the lower limbs, thereby achieving better training results.

[0098] Compared to manual emergency stop devices, this invention uses a novel suspension device to achieve automatic emergency stop via sensors, which greatly improves safety.

[0099] Compared to other automatic safety emergency stop devices, this invention has dual safety protection. The first layer of safety protection detects the tendency to fall through posture sensors and slows down the treadmill instead of stopping it directly, minimizing the impact on the training process and improving training efficiency. At the same time, it assists patients in adjusting their posture themselves, enhancing the training effect and realizing the intelligence of the safety emergency stop device.

[0100] This invention uses an artificial intelligence-optimized control method, employing relevant algorithms in the field of artificial intelligence to process the data collected by the posture sensor, in order to classify and identify human walking postures.

[0101] This invention allows for the adjustment of the suspension rope length and sensor threshold according to the patient's different physical conditions and rehabilitation status, in order to achieve different weight loss effects and training intensities, and has flexibility and wide applicability.

[0102] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems and apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0103] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A smart suspension safety method for a rehabilitation training treadmill, characterized in that, include: Collect training data from trainees, including body posture data and tension data; The training data is input into the state judgment model to obtain the training state data; Control commands are obtained based on the training status data; The control commands are used to control the operating status of the treadmill and the suspension device. The control commands include: Treadmill normal speed operation command, treadmill deceleration operation command, and treadmill emergency stop command; Control commands are obtained based on the training state data, including: The first layer of safety is activated by measuring the acceleration and attitude angles of the three axes to determine whether the trainee is prone to falling. If there is a tendency to fall, a treadmill deceleration command is generated, allowing the trainee to adjust their posture on their own; if there is no tendency to fall, a treadmill normal speed command is generated. If the trainee fails to adjust, the second safety measure is activated. If the tension exceeds the pre-set threshold, an emergency stop command for the treadmill is generated, and the suspension device is controlled to support the trainee. If the tensile force does not exceed the pre-set threshold, the system returns to the first level of safety assurance for further judgment; the method for constructing the state judgment model is as follows: Obtain a sample dataset; the sample dataset includes: a test set and a training set; Based on the body posture data, obtain acceleration and attitude angle data features; The tensile threshold data is obtained based on the height and weight data of the trainee; An initial model is constructed based on the tensile threshold data, acceleration, and attitude angle data characteristics. The initial model is trained using the training set to obtain the trained model; The trained model is evaluated using the test set to obtain a state judgment model.

2. A smart suspension safety device for a rehabilitation training treadmill, applied to the method described in claim 1, characterized in that, The device includes: Suspension base, suspension column, suspension rod, suspension rope, tension sensor, attitude sensor, inverted T-shaped bracket, sling and safety belt body; The suspension base is fixed to the front end of the treadmill's metal frame. One end of the suspension column is fixed to the suspension base, and the other end of the suspension column is connected to one end of the suspension rod. The other end of the suspension rod is connected to one end of the tension sensor via a suspension rope. The upper end of the inverted T-shaped bracket is connected to the other end of the tension sensor. The lower end of the inverted T-shaped bracket is connected to two straps above the main body of the safety belt. The lower ends of the two straps are connected to the main body of the safety belt. The posture sensor is attached to a preset position on the main body of the safety belt.

3. The intelligent suspension safety device for a rehabilitation training treadmill according to claim 2, characterized in that, The suspension rod is a bent right-angled triangle.

4. The intelligent suspension safety device for a rehabilitation training treadmill according to claim 2, characterized in that, The length of the suspension rope is adjustable within a preset range.

Images