A dynamic data acquisition processing method for wearable exoskeleton devices

Abstract

The present application relates to the field of dynamic data acquisition of wearable exoskeleton equipment, and particularly relates to a dynamic data acquisition processing method for wearable exoskeleton equipment, comprising: S1, obtaining wearable exoskeleton equipment dynamic monitoring data by using wearable exoskeleton equipment corresponding dynamic data; S2, establishing a wearable exoskeleton equipment dynamic data acquisition screening model by using wearable exoskeleton equipment dynamic monitoring data corresponding historical data; S3, obtaining dynamic data acquisition processing results by using time sequence screening processing according to the wearable exoskeleton equipment dynamic data acquisition screening model, realizing overall processing verification process of exoskeleton equipment real-time data after data acquisition, and verifying screening basis by combining with historical data of the same equipment and corresponding working conditions, considering the overall scheme and the internal data flow of the equipment, and realizing the accuracy and real-time performance of data acquisition.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of dynamic data acquisition of wearable exoskeleton equipment, and in particular to a dynamic data acquisition processing method for wearable exoskeleton equipment. BACKGROUND

[0002] The wearable exoskeleton equipment can improve the limit of human motion function, but its best play scene is usually limited to laboratory environment, and it takes half an hour to one hour to adjust the software algorithm of the robot to adapt to each user, wherein the dynamic data acquisition of the equipment plays a more important role in subsequent monitoring processing, the traditional scheme is to analyze the data after the equipment is running in advance, and there are problems such as lag in acquisition and certain error in dynamic data analysis for the scene on the human body wearing the equipment, therefore, a practical wearable exoskeleton equipment dynamic data acquisition scheme is urgently needed. SUMMARY

[0003] In view of the deficiencies of the prior art, the present application provides a dynamic data acquisition processing method for wearable exoskeleton equipment, which establishes an adaptive model for reasonable monitoring and processing of dynamic data acquisition through real-time and corresponding historical data of the current equipment.

[0004] To achieve the above-mentioned purpose, the present application provides a dynamic data acquisition processing method for wearable exoskeleton equipment, characterized in that it comprises:

[0005] S1, obtaining wearable exoskeleton equipment dynamic monitoring data by using corresponding dynamic data of wearable exoskeleton equipment;

[0006] S2, establishing a wearable exoskeleton equipment dynamic data acquisition screening model by using the wearable exoskeleton equipment dynamic monitoring data corresponding to the historical data;

[0007] S3, obtaining a dynamic data acquisition processing result by performing time series screening processing according to the wearable exoskeleton equipment dynamic data acquisition screening model.

[0008] Preferably, the wearable exoskeleton equipment dynamic monitoring data is obtained by using corresponding dynamic data of wearable exoskeleton equipment, comprising:

[0009] S1-1, obtaining motion posture data of wearable exoskeleton equipment, acceleration data of wearable exoskeleton equipment and joint signal data of wearable exoskeleton equipment as dynamic data;

[0010] S1-2, obtaining wearable exoskeleton equipment dynamic monitoring data by using the dynamic data;

[0011] The motion posture data of the wearable exoskeleton device is a horizontal posture of the wearable exoskeleton device and a vertical posture of the wearable exoskeleton device, and the joint signal data of the wearable exoskeleton device is a joint motion control signal data of the wearable exoskeleton device.

[0012] Further, obtaining the wearable exoskeleton device dynamic monitoring data by using the dynamic data comprises:

[0013] S1-2-1, judging whether the motion posture data of the wearable exoskeleton device meets the current motion standard of the wearable exoskeleton device, if yes, executing S1-2-2, otherwise, abandoning the processing;

[0014] S1-2-2, judging whether the acceleration data of the wearable exoskeleton device meets the current motion standard of the wearable exoskeleton device, if yes, executing S1-2-3, otherwise, abandoning the processing;

[0015] S1-2-3, using the joint signal data of the wearable exoskeleton device as the main data of the dynamic acquisition and detection of the wearable exoskeleton device, and using the motion posture data and the acceleration data of the wearable exoskeleton device corresponding to the joint signal data of the wearable exoskeleton device as the auxiliary data of the dynamic acquisition and detection of the wearable exoskeleton device;

[0016] S1-2-4, using the main data of the dynamic acquisition and detection of the wearable exoskeleton device and the auxiliary data of the dynamic acquisition and detection of the wearable exoskeleton device as the wearable exoskeleton device dynamic monitoring data.

[0017] Further, establishing the dynamic data acquisition and screening model of the wearable exoskeleton device by using the wearable exoskeleton device dynamic monitoring data corresponding to the historical data comprises:

[0018] S2-1, obtaining the joint signal data of the wearable exoskeleton device corresponding to the wearable exoskeleton device dynamic monitoring data to establish a first training set;

[0019] S2-2, obtaining the motion posture data and the acceleration data of the wearable exoskeleton device corresponding to the first training set to establish a first verification set;

[0020] S2-3, establishing a dynamic data acquisition and initial screening model based on deep learning by using the first training set and the first verification set;

[0021] S2-4, obtaining the dynamic data acquisition and screening model of the wearable exoskeleton device according to the dynamic data acquisition and initial screening model by using the wearable exoskeleton device dynamic monitoring data.

[0022] Further, the establishing of the dynamic data acquisition initial screening model based on deep learning using the first training set and the first verification set comprises:

[0023] S2-3-1, using the first training set as input and the first training set corresponding to the dynamic data acquisition initial screening result as output, training based on an unsupervised deep learning algorithm to obtain a dynamic data acquisition basic screening model;

[0024] S2-3-2, bringing the first verification set into the dynamic data acquisition basic screening model to obtain a dynamic data acquisition basic screening result;

[0025] S2-3-3, determining whether the dynamic data acquisition basic screening result and the first verification set corresponding dynamic data acquisition initial screening result are completely matched, if yes, outputting the dynamic data acquisition basic screening model as the dynamic data acquisition initial screening model, otherwise, adding the subset of the first verification set that does not have a corresponding dynamic data acquisition basic screening result to the first training set and returning to S2-3-1;

[0026] Wherein, the complete match is that each subset in the first verification set has a corresponding correct dynamic data acquisition basic screening result.

[0027] Further, the dynamic data acquisition initial screening model is used to obtain a dynamic data acquisition screening model of the wearable exoskeleton device according to the dynamic data acquisition initial screening model using the wearable exoskeleton device dynamic monitoring data.

[0028] S2-4-1, bringing the dynamic data acquisition main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data into the dynamic data acquisition initial screening model to obtain a dynamic data acquisition initial screening result;

[0029] S2-4-2, determining whether the dynamic data acquisition main data of the wearable exoskeleton device has corresponding historical data, if yes, executing S2-4-3, otherwise, directly outputting the dynamic data acquisition initial screening model as the dynamic data acquisition screening model of the wearable exoskeleton device;

[0030] S2-4-3, determining whether the dynamic data acquisition initial screening result and the historical data corresponding dynamic data acquisition initial screening result are the same, if yes, outputting the dynamic data acquisition initial screening model as the dynamic data acquisition screening model of the wearable exoskeleton device, otherwise, executing S2-4-4;

[0031] S2-4-4, judge whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is in a normal state, if yes, acquire the wearable exoskeleton device dynamic monitoring data of the adjacent next moment as the current wearable exoskeleton device dynamic monitoring data, and return to S2-4-1, otherwise, acquire the wearable exoskeleton device dynamic monitoring data of the adjacent next moment as the current wearable exoskeleton device dynamic monitoring data, and return to S2-1;

[0032] Wherein, the normal state is that the motion posture data of the wearable exoskeleton device of the dynamic acquisition detection auxiliary data of the wearable exoskeleton device and the acceleration data of the wearable exoskeleton device are all corresponding to the associated posture.

[0033] Further, the dynamic data acquisition screening model of the wearable exoskeleton device is used for time sequence screening processing to obtain a dynamic data acquisition processing result, which includes:

[0034] S3-1, acquire the current moment as a real-time screening starting moment t;

[0035] S3-2, judge whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data of the real-time screening starting moment t is in a normal state, if yes, the dynamic acquisition detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition screening model of the wearable exoskeleton device to obtain a dynamic data acquisition real-time screening front result, and S3-3 is executed, otherwise, the dynamic acquisition detection auxiliary data of the wearable exoskeleton device is used for verification backtracking processing;

[0036] S3-3, judge whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data of the moment t+1 is in a normal state, if yes, the dynamic acquisition detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition screening model of the wearable exoskeleton device to obtain a dynamic data acquisition real-time screening rear result, and S3-4 is executed, otherwise, the dynamic acquisition detection auxiliary data of the wearable exoskeleton device is used for verification backtracking processing;

[0037] S3-4, judge whether the dynamic data acquisition real-time screening front result and the dynamic data acquisition real-time screening rear result correspond, if yes, output the dynamic data acquisition real-time screening front result as the dynamic data acquisition initial screening result of the moment t, otherwise, execute S3-5;

[0038] S3-5, judging whether the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data at the t+2 moment is in a normal state, if yes, bringing the dynamic acquisition and detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data into a wearable exoskeleton device dynamic data acquisition screening model to obtain a dynamic data acquisition real-time screening additional result, and executing S3-6, otherwise, abandoning the processing;

[0039] S3-6, judging whether the dynamic data acquisition real-time screening additional result corresponds to the dynamic data acquisition real-time screening post result, if yes, outputting the dynamic data acquisition real-time screening pre result as the dynamic data acquisition initial screening result at the t moment, otherwise, abandoning the processing, and respectively outputting the wearable exoskeleton device dynamic monitoring data at the t, t+1 and t+2 moments;

[0040] Wherein, the normal state is that the motion posture data and the acceleration data of the wearable exoskeleton device of the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device correspond to the associated posture.

[0041] Further, the verification backtracking processing by using the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device includes:

[0042] Judging whether the current dynamic acquisition and detection auxiliary data of the wearable exoskeleton device and the historical dynamic acquisition and detection auxiliary data of the wearable exoskeleton device exist correspondence, if yes, verifying normal, and ending the processing, otherwise, acquiring the dynamic acquisition and detection main data of the wearable exoskeleton device corresponding to the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device;

[0043] The backtracking processing is performed by using the dynamic acquisition and detection main data of the wearable exoskeleton device and the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device to establish a backtracking set.

[0044] Further, the backtracking processing by using the dynamic acquisition and detection main data of the wearable exoskeleton device and the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device to establish a backtracking set includes:

[0045] The backtracking training set is established by using the dynamic acquisition and detection main data of the wearable exoskeleton device;

[0046] The backtracking verification set is established by using the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device;

[0047] The current first training set is established by using the backtracking training set and the first training set, and returns to S2-3-1;

[0048] The first verification set is replaced by using the backtracking verification set, and returns to S2-3-2.

[0049] Compared with the closest prior art, the present application has the beneficial effects of:

[0050] The present application realizes the collection of exoskeleton device real-time data, overall processing verification process, and verification screening basis combined with historical data of the device and corresponding working conditions, and considers the overall scheme and the internal data flow of the device, so as to realize the accuracy and efficiency of data collection. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 is a flowchart of a dynamic data collection and processing method for a wearable exoskeleton device provided by the present application. DETAILED DESCRIPTION

[0052] The specific embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0053] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0054] Embodiment 1: The present application provides a dynamic data collection and processing method for a wearable exoskeleton device, as shown in Figure 1 , comprising:

[0055] S1, obtaining wearable exoskeleton device dynamic monitoring data by using corresponding dynamic data of the wearable exoskeleton device;

[0056] S2, establishing a dynamic data collection and screening model of the wearable exoskeleton device by using corresponding historical data of the wearable exoskeleton device dynamic monitoring data;

[0057] S3, obtaining a dynamic data collection and processing result by performing time series screening processing according to the dynamic data collection and screening model of the wearable exoskeleton device.

[0058] S1 specifically includes:

[0059] S1-1, obtaining motion posture data of the wearable exoskeleton device, acceleration data of the wearable exoskeleton device, and joint signal data of the wearable exoskeleton device as dynamic data;

[0060] S1-2, obtaining wearable exoskeleton device dynamic monitoring data by using the dynamic data;

[0061] The motion posture data of the wearable exoskeleton device is a horizontal posture of the wearable exoskeleton device and a vertical posture of the wearable exoskeleton device, and the joint signal data of the wearable exoskeleton device is a joint motion control signal data of the wearable exoskeleton device.

[0062] In this embodiment, a dynamic data acquisition processing method for a wearable exoskeleton device is provided. For the selection of basic data types, the horizontal and vertical posture angles of the motion posture data are considered for processing, the device is abstracted as a whole, and the overall pitch and tilt angles are considered.

[0063] S1-2 specifically includes:

[0064] S1-2-1, determining whether the motion posture data of the wearable exoskeleton device meets the motion standard of the current wearable exoskeleton device, if yes, executing S1-2-2, otherwise, abandoning the processing;

[0065] S1-2-2, determining whether the acceleration data of the wearable exoskeleton device meets the motion standard of the current wearable exoskeleton device, if yes, executing S1-2-3, otherwise, abandoning the processing;

[0066] S1-2-3, using the joint signal data of the wearable exoskeleton device as the main data for dynamic acquisition and detection of the wearable exoskeleton device, and using the motion posture data and the acceleration data of the wearable exoskeleton device corresponding to the joint signal data of the wearable exoskeleton device as the auxiliary data for dynamic acquisition and detection of the wearable exoskeleton device;

[0067] S1-2-4, using the main data for dynamic acquisition and detection of the wearable exoskeleton device and the auxiliary data for dynamic acquisition and detection of the wearable exoskeleton device as the dynamic monitoring data of the wearable exoskeleton device.

[0068] In this embodiment, a dynamic data acquisition processing method for a wearable exoskeleton device is provided. The motion standard of the wearable exoskeleton device is a normal use motion posture threshold range of the wearable exoskeleton device.

[0069] S2 specifically includes:

[0070] S2-1, acquiring the joint signal data of the wearable exoskeleton device corresponding to the historical data of the dynamic monitoring data of the wearable exoskeleton device to establish a first training set;

[0071] S2-2, acquiring the motion posture data and the acceleration data of the wearable exoskeleton device corresponding to the first training set to establish a first verification set;

[0072] S2-3, establishing a dynamic data acquisition initial screening model based on deep learning using the first training set and the first validation set;

[0073] S2-4, obtaining a wearable exoskeleton device dynamic data acquisition screening model according to the dynamic data acquisition initial screening model using the wearable exoskeleton device dynamic monitoring data.

[0074] S2-3 specifically includes:

[0075] S2-3-1, using the first training set as input and the first training set corresponding dynamic data acquisition initial screening result as output, training based on an unsupervised deep learning algorithm to obtain a dynamic data acquisition basic screening model;

[0076] S2-3-2, bringing the first validation set into the dynamic data acquisition basic screening model to obtain a dynamic data acquisition basic screening result;

[0077] S2-3-3, determining whether the dynamic data acquisition basic screening result and the first validation set corresponding dynamic data acquisition initial screening result are completely matched, if yes, outputting the dynamic data acquisition basic screening model as the dynamic data acquisition initial screening model, otherwise, adding a subset of the first validation set that does not have a corresponding dynamic data acquisition basic screening result to the first training set and returning to S2-3-1;

[0078] Wherein, the complete match is that each subset in the first validation set has a corresponding correct dynamic data acquisition basic screening result.

[0079] S2-4 specifically includes:

[0080] S2-4-1, bringing the wearable exoskeleton device dynamic acquisition detection main data of the wearable exoskeleton device dynamic monitoring data into the dynamic data acquisition initial screening model to obtain a dynamic data acquisition initial screening result;

[0081] S2-4-2, determining whether the wearable exoskeleton device dynamic acquisition detection main data has corresponding historical data, if yes, executing S2-4-3, otherwise, directly outputting the dynamic data acquisition initial screening model as the wearable exoskeleton device dynamic data acquisition screening model;

[0082] S2-4-3, determining whether the dynamic data acquisition initial screening result and the historical data corresponding dynamic data acquisition initial screening result are the same, if yes, outputting the dynamic data acquisition initial screening model as the wearable exoskeleton device dynamic data acquisition screening model, otherwise, executing S2-4-4;

[0083] S2-4-4, judging whether the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is in a normal state, if yes, acquiring wearable exoskeleton device dynamic monitoring data of an adjacent next moment as current wearable exoskeleton device dynamic monitoring data, and returning to S2-4-1, otherwise, acquiring wearable exoskeleton device dynamic monitoring data of an adjacent next moment as current wearable exoskeleton device dynamic monitoring data, and returning to S2-1;

[0084] The normal state is that the motion posture data of the wearable exoskeleton device of the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device and the acceleration data of the wearable exoskeleton device are both corresponding to the associated posture.

[0085] S3 specifically comprises:

[0086] S3-1, acquiring a current moment as a real-time filtering starting moment t;

[0087] S3-2, judging whether the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data of the real-time filtering starting moment t is in a normal state, if yes, bringing the dynamic acquisition and detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data into a dynamic data acquisition and screening model of the wearable exoskeleton device to obtain a dynamic data acquisition real-time filtering pre-result, and executing S3-3, otherwise, performing verification backtracking processing by using the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device;

[0088] S3-3, judging whether the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data of the moment t+1 is in a normal state, if yes, bringing the dynamic acquisition and detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data into a dynamic data acquisition and screening model of the wearable exoskeleton device to obtain a dynamic data acquisition real-time filtering post-result, and executing S3-4, otherwise, performing verification backtracking processing by using the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device;

[0089] S3-4, judging whether the dynamic data acquisition real-time filtering pre-result and the dynamic data acquisition real-time filtering post-result correspond, if yes, outputting the dynamic data acquisition real-time filtering pre-result as a dynamic data acquisition initial screening result of the moment t, otherwise, executing S3-5;

[0090] S3-5, judging whether the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data at the t+2 moment is in a normal state, if yes, bringing the dynamic acquisition and detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data into the dynamic data acquisition screening model to obtain a dynamic data acquisition real-time screening additional result, and executing S3-6, otherwise, abandoning the processing;

[0091] S3-6, judging whether the dynamic data acquisition real-time screening additional result corresponds to the dynamic data acquisition real-time screening post result, if yes, outputting the dynamic data acquisition real-time screening pre result as the dynamic data acquisition initial screening result at the t moment, otherwise, abandoning the processing, and respectively outputting the wearable exoskeleton device dynamic monitoring data at the t, t+1 and t+2 moments;

[0092] Wherein, the normal state is that the motion posture data and the acceleration data of the wearable exoskeleton device of the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device correspond to the associated posture.

[0093] S3-3 specifically includes:

[0094] S3-3-1, judging whether the dynamic acquisition and detection auxiliary data of the current wearable exoskeleton device corresponds to the dynamic acquisition and detection auxiliary data of the historical wearable exoskeleton device, if yes, verifying normal and ending the processing, otherwise, acquiring the dynamic acquisition and detection main data of the wearable exoskeleton device corresponding to the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device;

[0095] S3-3-2, using the dynamic acquisition and detection main data of the wearable exoskeleton device and the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device to establish a backtracking set for backtracking processing.

[0096] S3-3-2 specifically includes:

[0097] S3-3-2-1, using the dynamic acquisition and detection main data of the wearable exoskeleton device to establish a backtracking training set;

[0098] S3-3-2-2, using the dynamic acquisition and detection auxiliary data of the wearable exoskeleton device to establish a backtracking verification set;

[0099] S3-3-2-3, using the backtracking training set and the first training set to establish a current first training set, and returning to S2-3-1;

[0100] S3-3-2-4, using the backtracking verification set to replace the first verification set, and returning to S2-3-2.

[0101] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0102] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the present application. It will be understood that each block of the flowchart and / or block diagrams, and combinations of blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0103] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0105] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing the technical solutions of the present application, but not for limiting it. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the technical solutions of the present application can still be modified or equivalent replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered in the protection scope of the claims of the present application.

Claims

1. A dynamic data acquisition processing method for a wearable exoskeleton device, characterized by, The method comprises the following steps: S1, obtaining wearable exoskeleton device dynamic monitoring data by using corresponding dynamic data of the wearable exoskeleton device, comprising: S1-1, acquiring motion posture data of the wearable exoskeleton device, acceleration data of the wearable exoskeleton device and joint signal data of the wearable exoskeleton device as dynamic data; S1-2, obtaining wearable exoskeleton device dynamic monitoring data by using the dynamic data; wherein the motion posture data of the wearable exoskeleton device is the horizontal posture of the wearable exoskeleton device and the vertical posture of the wearable exoskeleton device, and the joint signal data of the wearable exoskeleton device is the joint motion control signal data of the wearable exoskeleton device; S2, establishing a wearable exoskeleton device dynamic data collection screening model by using the wearable exoskeleton device dynamic monitoring data corresponding to historical data, comprising: S2-1, obtaining the joint signal data of the wearable exoskeleton device corresponding to the wearable exoskeleton device dynamic monitoring data to establish a first training set; S2-2, obtaining the motion posture data of the wearable exoskeleton device and the acceleration data of the wearable exoskeleton device corresponding to the first training set to establish a first verification set; S2-3, establishing a dynamic data collection initial screening model based on deep learning by using the first training set and the first verification set, comprising: S2-3-1, using the first training set as input, the dynamic data collection initial screening result corresponding to the first training set as output, and training based on unsupervised deep learning algorithm to obtain a dynamic data collection basic screening model; S2-3-2, bringing the first verification set into the dynamic data collection basic screening model to obtain a dynamic data collection basic screening result; S2-3-3, judging whether the dynamic data collection basic screening result and the dynamic data collection initial screening result corresponding to the first verification set are completely matched, if yes, outputting the dynamic data collection basic screening model as the dynamic data collection initial screening model, otherwise, adding a subset of the first verification set which does not have a corresponding dynamic data collection basic screening result to the first training set and returning to S2-3-1; wherein the complete match is that each subset in the first verification set has a corresponding correct dynamic data collection basic screening result; S2-4, obtaining the wearable exoskeleton device dynamic data collection screening model according to the dynamic data collection initial screening model by using the wearable exoskeleton device dynamic monitoring data; S3, performing time sequence screening processing to obtain a dynamic data collection processing result according to the wearable exoskeleton device dynamic data collection screening model.

2. A dynamic data acquisition and processing method for wearable exoskeleton devices as claimed in claim 1, wherein, The method comprises the following steps: S1-2-1, judging whether the motion posture data of the wearable exoskeleton device meets the current motion standard of the wearable exoskeleton device, if yes, executing S1-2-2, otherwise, abandoning the processing; S1-2-2, judging whether the acceleration data of the wearable exoskeleton device meets the current motion standard of the wearable exoskeleton device, if yes, executing S1-2-3, otherwise, abandoning the processing; S1-2-3, using the joint signal data of the wearable exoskeleton device as the dynamic acquisition detection main data of the wearable exoskeleton device, using the joint signal data of the wearable exoskeleton device corresponding to the motion posture data of the wearable exoskeleton device and the acceleration data of the wearable exoskeleton device as the dynamic acquisition detection auxiliary data of the wearable exoskeleton device; S1-2-4, using the dynamic acquisition detection main data of the wearable exoskeleton device and the dynamic acquisition detection auxiliary data of the wearable exoskeleton device as the dynamic monitoring data of the wearable exoskeleton device.

3. A dynamic data acquisition process for a wearable exoskeleton device as recited in claim 1, wherein, Using the dynamic monitoring data of the wearable exoskeleton device, the dynamic data acquisition screening model of the wearable exoskeleton device is obtained according to the dynamic data acquisition initial screening model, which includes: S2-4-1, the dynamic acquisition detection main data of the wearable exoskeleton device in the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition initial screening model to obtain the dynamic data acquisition initial screening result; S2-4-2, it is judged whether the dynamic acquisition detection main data of the wearable exoskeleton device exists corresponding historical data, if yes, S2-4-3 is executed, otherwise, the dynamic data acquisition initial screening model is directly output as the dynamic data acquisition screening model of the wearable exoskeleton device; S2-4-3, it is judged whether the dynamic data acquisition initial screening result and the historical data corresponding dynamic data acquisition initial screening result are same, if yes, the dynamic data acquisition initial screening model is output as the dynamic data acquisition screening model of the wearable exoskeleton device, otherwise, S2-4-4 is executed; S2-4-4, it is judged whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device in the wearable exoskeleton device dynamic monitoring data is normal state, if yes, the adjacent next time wearable exoskeleton device dynamic monitoring data is obtained as the current wearable exoskeleton device dynamic monitoring data, and returns to S2-4-1, otherwise, the adjacent next time wearable exoskeleton device dynamic monitoring data is obtained as the current wearable exoskeleton device dynamic monitoring data, and returns to S2-1; Wherein, the normal state is that the motion posture data of the wearable exoskeleton device and the acceleration data of the wearable exoskeleton device in the dynamic acquisition detection auxiliary data of the wearable exoskeleton device are all corresponding to the associated posture.

4. A dynamic data acquisition and processing method for a wearable exoskeleton device as claimed in claim 3, characterized in that, According to the dynamic data acquisition screening model of the wearable exoskeleton device, the dynamic data acquisition processing result is obtained by time sequence screening processing, which includes: S3-1, the current time is obtained as the real-time screening starting time t; S3-2, it is judged whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device in the wearable exoskeleton device dynamic monitoring data at the real-time screening starting time t is normal state, if yes, the dynamic acquisition detection main data of the wearable exoskeleton device in the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition screening model of the wearable exoskeleton device to obtain the dynamic data acquisition real-time screening front result, and S3-3 is executed, otherwise, the dynamic acquisition detection auxiliary data of the wearable exoskeleton device is used for verification backtracking processing; S3-3, judging whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data at t+1 time is in a normal state, if yes, the dynamic acquisition detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition screening model of the wearable exoskeleton device to obtain the dynamic data acquisition real-time screening post-result, and S3-4 is executed, otherwise, the verification backtracking processing is performed by using the dynamic acquisition detection auxiliary data of the wearable exoskeleton device; S3-4, judging whether the dynamic data acquisition real-time screening pre-result and the dynamic data acquisition real-time screening post-result correspond, if yes, the dynamic data acquisition real-time screening pre-result is output as the dynamic data acquisition initial screening result at t time, otherwise, S3-5 is executed; S3-5, judging whether the dynamic acquisition detection auxiliary data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data at t+2 time is in a normal state, if yes, the dynamic acquisition detection main data of the wearable exoskeleton device of the wearable exoskeleton device dynamic monitoring data is brought into the dynamic data acquisition screening model of the wearable exoskeleton device to obtain the dynamic data acquisition real-time screening additional result, and S3-6 is executed, otherwise, the processing is abandoned; S3-6, judging whether the dynamic data acquisition real-time screening additional result and the dynamic data acquisition real-time screening post-result correspond, if yes, the dynamic data acquisition real-time screening pre-result is output as the dynamic data acquisition initial screening result at t time, otherwise, the processing is abandoned, and the wearable exoskeleton device dynamic monitoring data at t, t+1 and t+2 times is output respectively; Wherein, the normal state is that the motion posture data and the acceleration data of the wearable exoskeleton device of the dynamic acquisition detection auxiliary data of the wearable exoskeleton device correspond to the associated posture.

5. A dynamic data acquisition and processing method for a wearable exoskeleton device as claimed in claim 4, characterized in that, The verification backtracking processing by using the dynamic acquisition detection auxiliary data of the wearable exoskeleton device includes: Judging whether the current dynamic acquisition detection auxiliary data of the wearable exoskeleton device and the historical dynamic acquisition detection auxiliary data of the wearable exoskeleton device correspond, if yes, the normal is verified, and the processing is ended, otherwise, the dynamic acquisition detection main data of the wearable exoskeleton device corresponding to the dynamic acquisition detection auxiliary data of the wearable exoskeleton device is obtained; The backtracking processing is performed by using the dynamic acquisition detection main data of the wearable exoskeleton device and the dynamic acquisition detection auxiliary data of the wearable exoskeleton device to establish a backtracking set.

6. A dynamic data acquisition and processing method for wearable exoskeleton devices as claimed in claim 1, wherein, The backtracking processing by using the dynamic acquisition detection main data of the wearable exoskeleton device and the dynamic acquisition detection auxiliary data of the wearable exoskeleton device to establish a backtracking set includes: The backtracking training set is established by using the dynamic acquisition detection main data of the wearable exoskeleton device; The backtracking verification set is established by using the dynamic acquisition detection auxiliary data of the wearable exoskeleton device; The current first training set is established by using the backtracking training set and the first training set, and returns to S2-3-1; The first verification set is replaced by using the backtracking verification set, and returns to S2-3-2.

Images