Torque measurement method based on three-dimensional negative Poisson's ratio structure and related product
Through the non-contact measurement of the three-dimensional negative Poisson ratio structure and the object to be measured, combined with corner point detection and machine learning model, the problems of friction and interference factors in traditional torque measurement methods are solved, and high-precision and flexible torque are achieved Measurement.
Patent Information
- Application Number
- CN202411203017.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-29
AI Technical Summary
Traditional torque measurement methods have friction and interference factors caused by direct contact, which affects measurement accuracy and limits measurement range and flexibility.
The torque measurement method based on the three-dimensional negative Poisson's ratio structure is adopted to contact the object to be measured through the three-dimensional negative Poisson's ratio structure, deformation images are collected, and the torque value is mapped using corner detection and machine learning models to realize non-contact measurement. .
It improves the accuracy and flexibility of torque measurement, extends the service life of the equipment, expands the measurement range, simplifies the measurement process, and improves the measurement accuracy through data processing.
Smart Images

Figure CN119043553A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of torque measurement, and relates to a torque measurement method based on a three-dimensional negative Poisson's ratio structure and related products. Background Art
[0002] In modern industrial production and scientific research experiments, torque measurement is a key link in evaluating the performance of mechanical systems and ensuring product quality and safety. Its importance is self-evident. Torque, as a physical quantity that describes the product of force and rotation radius, is directly related to the operating efficiency, durability and operational safety of the equipment. Traditionally, the measurement of torque mainly relies on mechanical sensors (such as torque sensors, strain gauges, etc.) and electrical sensors (such as magnetoelectric, inductive, etc.). Although these technologies have been relatively mature in long-term applications, they still face many challenges.
[0003] Accurate measurement of torque is essential to ensure the performance, stability and safety of mechanical systems. Traditional torque measurement methods mostly rely on mechanical sensors, which need to maintain direct contact with the object to sense its deformation or stress changes, and then calculate the torque value. However, this direct contact method has many limitations, such as the possible introduction of additional friction and interference factors, potential damage to the object to be measured, and limited measurement range and flexibility, which has a negative impact on measurement accuracy. Summary of the invention
[0004] The purpose of the present invention is to solve the technical problem that the contact measurement method in the prior art introduces additional friction and interference factors resulting in low torque measurement accuracy, and to provide a torque measurement method and system based on a three-dimensional negative Poisson's ratio structure.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] A first aspect of the present invention provides a method for measuring torque based on a three-dimensional negative Poisson's ratio structure, comprising the following steps:
[0007] Using the three-dimensional negative Poisson's ratio structure as a substrate, bringing the object to be measured into contact with the three-dimensional negative Poisson's ratio structure; collecting a deformation image of the three-dimensional negative Poisson's ratio structure;
[0008] The deformation image is input into a pre-established deformation image and moment mapping model to obtain a moment value; the pre-established deformation image and moment mapping model includes corner point detection, a moment mapping module and a machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
[0009] Preferably, the step of bringing the object under test into contact with the three-dimensional negative Poisson's ratio structure and collecting the deformation image of the three-dimensional negative Poisson's ratio structure comprises:
[0010] The object to be measured is brought into contact with the three-dimensional negative Poisson's ratio structure;
[0011] Use an industrial camera to capture deformation images of three-dimensional negative Poisson's ratio structures.
[0012] Preferably, the step of inputting the deformation image into a pre-established deformation image and moment mapping model to obtain the moment value is specifically as follows:
[0013] The deformed image is subjected to corner point detection to perform feature extraction to obtain a first feature;
[0014] The first feature and the moment are mapped one by one to obtain a mapping relationship between the first feature and the moment;
[0015] Based on the mapping relationship between the first feature and the moment, the first feature is input into a pre-trained machine learning model to obtain the moment value.
[0016] Preferably, the corner point detection adopts SIFT algorithm, SURF algorithm or YOLO algorithm.
[0017] Preferably, the training method of the machine learning model is:
[0018] Acquire a data set of deformation image features; the deformation image feature data set is a data set for extracting features from a deformation image of a three-dimensional negative Poisson's ratio structure in contact with a measured object;
[0019] The dataset of deformable image features is input into the machine learning model for training to obtain a trained machine learning model.
[0020] Preferably, the machine learning model is an SVR model.
[0021] A second aspect of the present invention provides a computer program product, which includes computer instructions, characterized in that the computer instructions instruct a computer to execute the above-mentioned torque measurement method based on the three-dimensional negative Poisson's ratio structure.
[0022] A third aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned torque measurement method based on the three-dimensional negative Poisson's ratio structure when executing the computer program.
[0023] A fourth aspect of the present invention provides a readable storage medium, comprising a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned torque measurement method based on the three-dimensional negative Poisson's ratio structure when executing the computer program.
[0024] A fifth aspect of the present invention provides a torque measurement system based on a three-dimensional negative Poisson's ratio structure, comprising:
[0025] Image acquisition module: used to use the three-dimensional negative Poisson's ratio structure as a substrate, bring the object under test into contact with the three-dimensional negative Poisson's ratio structure, and acquire a deformation image of the three-dimensional negative Poisson's ratio structure;
[0026] Data processing module: used to input the deformation image into a pre-established deformation image and moment mapping model to obtain the moment value; the pre-established deformation image and moment mapping model includes corner point detection, moment mapping module and machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] The present invention discloses a torque measurement method based on a three-dimensional negative Poisson's ratio structure. The three-dimensional negative Poisson's ratio structure is used as a substrate. Through its unique negative Poisson's ratio effect, a significant deformation can be generated when an external force acts on it. The deformation is not limited to a single direction, but a multi-dimensional response in a three-dimensional space. The torque measurement is realized by combining image acquisition with a deformation image and a mapping model of the torque, and there is no need to directly contact the measured object. This non-contact property not only improves the accuracy of the measurement, but also prolongs the service life of the measuring equipment and simplifies the measuring process. The present invention can realize torque measurement of different ranges by adjusting the design parameters of the three-dimensional negative Poisson's ratio structure, such as different cells, different height-to-diameter ratios, etc. The measuring range is not limited and the method has wide adaptability. The mapping model of deformation image and moment of the present invention integrates three modules of corner detection, moment mapping and machine learning, realizing intelligent processing of deformation image and accurate mapping of mechanical properties; the corner detection module quickly identifies key feature points in the deformation image, the moment mapping module performs preliminary calculations based on the mapping relationship between these feature points and the moment, and the machine learning module further optimizes the mapping relationship by learning a large amount of sample data to improve measurement accuracy.
[0029] Furthermore, the hardware equipment relied on by this method is relatively simple, mainly including a three-dimensional negative Poisson's ratio structure, an image acquisition device, and a data processing system. These devices are easy to integrate into the existing measurement system, and the measurement accuracy and performance can also be further improved by upgrading the software algorithm or expanding the hardware equipment.
[0030] Furthermore, the measurement is flexible and easy to replace. By adjusting the design parameters of the three-dimensional negative Poisson's ratio structure, the measurement system can be flexibly configured according to different application scenarios and measurement requirements, and is suitable for a variety of industrial torque measurement occasions.
[0031] Furthermore, industrial cameras usually have high-resolution sensors that can capture the subtle deformation of three-dimensional negative Poisson's ratio structures during force application. This high-resolution image data provides a solid foundation for subsequent image processing and feature extraction, thereby ensuring high-precision torque measurement. By carefully analyzing the deformation details in these images, the magnitude and direction of the torque can be more accurately reflected.
[0032] Furthermore, the present invention obtains a dataset of deformation image features and uses these datasets to train a machine learning model, so that the model can learn the complex relationship between the deformation and torque of the three-dimensional negative Poisson's ratio structure. This big data-based training method enables the model to more accurately predict the torque value corresponding to the deformation image, thereby improving the measurement accuracy.
[0033] The present invention discloses a torque measurement system based on a three-dimensional negative Poisson's ratio structure. By integrating an image acquisition module and a data processing module, high-precision and real-time measurement of torque is achieved. The system uses a three-dimensional negative Poisson's ratio structure as a measurement substrate and utilizes its unique negative Poisson's ratio effect, that is, when the structure is compressed in a certain direction under the action of an external force, it will show expansion on a plane perpendicular to the direction. This deformation characteristic is extremely sensitive to torque changes. The image acquisition module can accurately capture the deformation image of the three-dimensional negative Poisson's ratio structure during the force process, while the data processing module uses a pre-established deformation image and torque mapping model to convert the deformation image into an accurate torque value, thereby achieving high-precision measurement of the torque.
[0034] In summary, the present invention provides a torque measurement method and related products based on a three-dimensional negative Poisson's ratio structure, which can effectively improve the response speed of torque measurement, expand the range of torque measurement, simplify the structure of the measurement system, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0036] Figure 1 It is a schematic diagram of a torque measurement device based on a three-dimensional negative Poisson's ratio structure of the present invention;
[0037] Figure 2 This is a flow chart of the method for measuring moment of a three-dimensional negative Poisson's ratio structure according to the present invention;
[0038] Figure 3 Schematic diagram of deformation of a three-dimensional negative Poisson's ratio structure under torque;
[0039] Figure 4 Schematic diagram of the deformation of a three-dimensional negative Poisson's ratio structure subjected to bending moment.
[0040] Among them: 1-three-dimensional negative Poisson's ratio structure; 2-lens; 3-industrial camera; 4-computer. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention described and marked in the drawings here can be arranged and designed in various different configurations.
[0042] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0044] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.
[0045] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.
[0046] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0047] The present invention is further described in detail below in conjunction with the accompanying drawings:
[0048] See also Figure 1 The present invention discloses a torque detection method based on machine vision and a three-dimensional negative Poisson's ratio structure, which is a method for measuring torque by combining a three-dimensional negative Poisson's ratio structure 1 with a machine vision device; the machine vision device includes a computer 4 and an industrial camera 3; the three-dimensional negative Poisson's ratio structure 1 is placed within the field of view of a lens 2 of the industrial camera 3; the industrial camera 3 is electrically connected to the computer 4; and the computer 4 is equipped with a machine vision system. The three-dimensional negative Poisson's ratio structure 1 can be prepared by 3D printing technology. There is no requirement for the relative position of the industrial camera 3 and the three-dimensional negative Poisson's ratio structure 1, and the three-dimensional negative Poisson's ratio structure only needs to be placed within the field of view of the industrial camera.
[0049] See also Figure 2 The present invention discloses a torque detection method based on a three-dimensional negative Poisson's ratio structure, comprising the following steps:
[0050] S1, using the three-dimensional negative Poisson's ratio structure as a substrate, bringing the object under test into contact with the three-dimensional negative Poisson's ratio structure; collecting a deformation image of the three-dimensional negative Poisson's ratio structure;
[0051] The substrate is made of a material with significant negative Poisson's ratio characteristics (such as composite materials or metal alloys with honeycomb, concave hexagonal structures, etc.). When this structure is subjected to external force, the lateral size will increase with the longitudinal compression, and vice versa. This unique deformation mode makes it extremely sensitive to changes in external force. The object to be measured is brought into contact with the three-dimensional negative Poisson's ratio structure; when the object to be measured is affected by external force, the three-dimensional negative Poisson's ratio structure will deform, and the deformation image of the three-dimensional negative Poisson's ratio structure can be collected by the industrial camera 3.
[0052] S2, inputting the deformation image into a pre-established deformation image and moment mapping model to obtain the moment value; the pre-established deformation image and moment mapping model includes corner point detection, a moment mapping module and a machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
[0053] The mapping model between the deformation image and the torque is constructed based on a large amount of experimental data through a machine learning method, and can accurately convert the information in the deformation image into the corresponding torque value.
[0054] An embodiment of the present invention discloses a torque detection method based on a three-dimensional negative Poisson's ratio structure, comprising the following steps:
[0055] S1. A three-dimensional negative Poisson's ratio structure is prepared using 3D printing technology and placed in the field of view of an industrial camera to ensure that the overall picture of the three-dimensional negative Poisson's ratio structure can be clearly captured. The industrial camera is used to capture the deformation of the three-dimensional negative Poisson's ratio structure in real time. The camera records the deformation of the three-dimensional negative Poisson's ratio structure at different time points through high-speed shooting.
[0056] S2. The object under test is in contact with the negative Poisson's ratio structure, and an external force is applied to the object under test, so that the three-dimensional negative Poisson's ratio structure is deformed, and the industrial camera 3 collects the deformation image of the negative Poisson's ratio structure. Select a high-resolution, high-frame-rate industrial camera, install it and adjust it to an appropriate position and angle, so that the full picture and subtle deformation of the three-dimensional negative Poisson's ratio structure can be clearly captured. The industrial camera 3 is connected to the computer 4, and the high-speed shooting mode is set to ensure that the deformation of the structure at different time points can be recorded.
[0057] The object to be tested is placed in contact with the three-dimensional negative Poisson's ratio structure to ensure that the contact surface is flat and slip-free. An external force of a predetermined direction and magnitude is applied to the object to be tested, and an industrial camera is started to shoot at high speed to record the deformation images of the three-dimensional negative Poisson's ratio structure at different time points.
[0058] S3. The deformed image is transmitted to a computer for image preprocessing.
[0059] The collected deformation images are transferred to a computer and preprocessed using image processing software, including denoising, contrast enhancement, cropping and other steps to improve image quality.
[0060] S4. Use corner detection to extract features from the preprocessed deformed image.
[0061] Apply corner detection algorithms (such as SIFT, SURF, and YOLO, etc.) to extract features from the preprocessed deformed image and mark the key points of the deformed area.
[0062] S5. Map the extracted features to the corresponding torque information one by one; train the SVR model to obtain a trained SVR model.
[0063] Collect a series of datasets with known moments and corresponding deformation features. Use these datasets to build a support vector regression (SVR) model to map deformation features to moment values.
[0064] The SVR model is trained and the model parameters are adjusted to optimize the prediction accuracy. The training method of the machine learning model is:
[0065] Acquire a data set of deformation image features; the deformation image feature data set is a data set for extracting features from a deformation image of a three-dimensional negative Poisson's ratio structure in contact with a measured object;
[0066] The dataset of deformable image features is input into the machine learning model for training to obtain a trained machine learning model.
[0067] S6, inputting the extracted features into the pre-built SVR model to obtain the moment value;
[0068] The deformation features extracted in step S4 are input into the trained SVR model.
[0069] The model calculates the corresponding torque value based on the input deformation characteristics and displays the output results on the computer screen.
[0070] like Figure 3 , Figure 4 The three-dimensional negative Poisson's ratio structure sample that can be used for the substrate of the present invention is shown, which is deformed in both the lateral and longitudinal directions when subjected to bending moment and torque. In the present invention, the three-dimensional negative Poisson's ratio structure produces elastic deformation after being subjected to force, and the camera captures the structural deformation image. By establishing a mapping model between the moment and the deformation image, it is finally realized to input a deformation image subjected to a moment, call the mapping model, and output the magnitude of the moment subjected to the structure.
[0071] The three-dimensional negative Poisson's ratio structure deforms in the lateral and longitudinal directions when subjected to bending moment and torque. The three-dimensional negative Poisson's ratio structure is used as a substrate and is brought into contact with the object to be measured. The shape change of the three-dimensional negative Poisson's ratio structure caused by the force is measured based on machine vision technology.
[0072] The three-dimensional negative Poisson's ratio structure is analyzed based on the image, and the mapping relationship between the base deformation and the moment is obtained. According to the relationship, a mapping model between the moment and the deformation image is established.
[0073] The invention discloses a torque measurement system for a three-dimensional negative Poisson's ratio structure, comprising:
[0074] Image acquisition module: used to use the three-dimensional negative Poisson's ratio structure as a substrate, bring the object under test into contact with the three-dimensional negative Poisson's ratio structure, and acquire a deformation image of the three-dimensional negative Poisson's ratio structure;
[0075] Data processing module: used to input the deformation image into a pre-established deformation image and moment mapping model to obtain the moment value; the pre-established deformation image and moment mapping model includes corner point detection, moment mapping module and machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
[0076] The image acquisition module is used to use a three-dimensional negative Poisson's ratio structure as a base, place the three-dimensional negative Poisson's ratio structure in the field of view of the industrial camera, and the object to be measured is in contact with the three-dimensional negative Poisson's ratio structure to collect the deformation image of the three-dimensional negative Poisson's ratio structure; the data processing module includes image processing and image prediction, which is used to generate a corresponding torque after applying an external force to the object to be measured, and the three-dimensional negative Poisson's ratio structure produces elastic deformation. The mapping relationship between the deformation image and the torque is used to establish a mapping model between the image and the torque, perform image processing on the collected image, convert the pixel signal into a torque signal, and convert the measurement of the measured object into the measurement of the base deformation image. In this way, it is possible to input a picture, call the mapping model, and output the torque exerted on the object to be measured when the picture is collected.
[0077] This embodiment introduces an electronic device, which integrates a three-dimensional negative Poisson's ratio structure, a memory, a processor and a corresponding computer program, and is used to implement a torque measurement method based on a three-dimensional negative Poisson's ratio structure. The method captures the deformation of the three-dimensional negative Poisson's ratio structure under the action of an external force, and uses image processing technology and a machine learning model (such as an SVR model) to calculate and output the torque value. The three-dimensional negative Poisson's ratio structure of the present invention is prepared by high-precision 3D printing technology, has a significant negative Poisson's ratio effect, and can produce a unique deformation mode when subjected to an external force. The three-dimensional negative Poisson's ratio structure is installed in an appropriate position inside or outside the electronic device to ensure contact with the object to be measured and effectively transmit external force. The memory stores an operating system, a computer program, and intermediate files and result files required for data processing. The memory type can be RAM, ROM, Flash memory or other types of non-volatile or volatile memory. The processor is responsible for executing the computer program stored in the memory to realize functions such as data processing, image processing and machine learning model calculation. The processor can be a high-performance computing unit such as a single-core or multi-core CPU, GPU, FPGA, etc. Optionally, the electronic device is equipped with an industrial camera. If the electronic device is designed as an independent system including an image acquisition function, it needs to be equipped with a high-resolution, high-frame-rate industrial camera. The industrial camera is connected to the processor via an interface to transmit deformation image data in real time.
[0078] The present embodiment describes a readable storage medium, which contains a specific computer program that can be executed on a processor connected thereto, thereby realizing a torque measurement method based on a three-dimensional negative Poisson's ratio structure. This method calculates the torque value by capturing and analyzing the deformation of the three-dimensional negative Poisson's ratio structure under the action of an external force, and has high precision and real-time performance. The memory is used to store computer programs, operating systems, intermediate files, and result data, etc. It can be any form of non-volatile or volatile storage medium such as a hard disk, flash memory, optical disk, SD card, USB flash drive, etc. The computer program is a set of instruction sets stored in the memory, and when executed by the processor, it can complete the torque measurement method based on the three-dimensional negative Poisson's ratio structure. The computer program includes an image processing module, a feature extraction module, an SVR model module, and a torque calculation module, etc., which work together to realize the entire measurement method. Although the present embodiment focuses on the storage medium, the image data is usually captured by an external device (such as an industrial camera) and transmitted to the processor in some way (such as a network interface, a USB interface, etc.).
[0079] This embodiment describes a computer program product, which includes one or more computer executable files, which include computer instructions for implementing a method for measuring the moment of a three-dimensional negative Poisson's ratio structure. These instructions are designed to interact with the computer's operating system and other hardware components to implement the method for measuring the moment of a three-dimensional negative Poisson's ratio structure.
[0080] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.
[0081] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A torque measurement method based on a three-dimensional negative Poisson's ratio structure, characterized in that: The following steps are involved: Using a three-dimensional negative Poisson's ratio structure as a substrate, the object to be measured is brought into contact with the three-dimensional negative Poisson's ratio structure; Collect deformation images of three-dimensional negative Poisson's ratio structures; The deformation image is input into a pre-established deformation image and moment mapping model to obtain a moment value; the pre-established deformation image and moment mapping model includes corner point detection, a moment mapping module and a machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
2. The torque measurement method based on the three-dimensional negative Poisson's ratio structure according to claim 1 is characterized in that: The step of bringing the measured object into contact with the three-dimensional negative Poisson's ratio structure and collecting the deformation image of the three-dimensional negative Poisson's ratio structure is specifically as follows: The object to be measured is brought into contact with the three-dimensional negative Poisson's ratio structure; Use an industrial camera to capture deformation images of three-dimensional negative Poisson's ratio structures.
3. The torque measurement method based on a three-dimensional negative Poisson's ratio structure according to claim 1 is characterized in that: The deformation image is input into a pre-established deformation image and moment mapping model to obtain the moment value, specifically: The deformed image is subjected to corner point detection to perform feature extraction to obtain a first feature; The first feature and the moment are mapped one by one to obtain a mapping relationship between the first feature and the moment; Based on the mapping relationship between the first feature and the moment, the first feature is input into a pre-trained machine learning model to obtain the moment value.
4. The torque measurement method based on a three-dimensional negative Poisson's ratio structure according to claim 1 or 3, characterized in that: The corner point detection adopts SIFT algorithm, SURF algorithm or YOLO algorithm.
5. The torque measurement method based on the three-dimensional negative Poisson's ratio structure according to claim 3 is characterized in that: The training method of the machine learning model is: Acquire a data set of deformation image features; the deformation image feature data set is a data set for extracting features from a deformation image of a three-dimensional negative Poisson's ratio structure in contact with a measured object; The dataset of deformable image features is input into the machine learning model for training to obtain a trained machine learning model.
6. The torque measurement method based on a three-dimensional negative Poisson's ratio structure according to claim 3 or 5, characterized in that: The machine learning model is an SVR model.
7. A computer program product, characterized in that The computer program product includes computer instructions, characterized in that the computer instructions instruct a computer to execute the moment measurement method based on a three-dimensional negative Poisson's ratio structure as described in any one of claims 1-6.
8. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the torque measurement method based on the three-dimensional negative Poisson's ratio structure as claimed in any one of claims 1 to 6 when executing the computer program.
9. A readable storage medium, characterized in that: The invention comprises a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the torque measurement method based on the three-dimensional negative Poisson's ratio structure as claimed in any one of claims 1 to 6 when executing the computer program.
10. A torque measurement system based on a three-dimensional negative Poisson's ratio structure, characterized in that: include: Image acquisition module: used to use the three-dimensional negative Poisson's ratio structure as a substrate and bring the object under test into contact with the three-dimensional negative Poisson's ratio structure; Collect deformation images of three-dimensional negative Poisson's ratio structures; Data processing module: used to input the deformation image into a pre-established deformation image and moment mapping model to obtain the moment value; the pre-established deformation image and moment mapping model includes corner point detection, moment mapping module and machine learning module; the output of the corner point detection is connected to the input of the moment mapping module, and the output of the moment mapping module is connected to the input of the machine learning module.
