Triboelectric pressure sensor for fencing system and fencing suit
By using triboelectric pressure sensors and deep learning models, the problems of inaccurate judgments and lack of training feedback in existing fencing systems have been solved, enabling accurate judgments in fencing matches and real-time evaluation of training effectiveness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- BEIJING INST OF NANOENERGY & NANOSYST
- Filing Date
- 2025-04-11
- Publication Date
- 2026-05-12
AI Technical Summary
Existing fencing referee systems rely on spring-loaded blade tips and electrical signal transmission, which are complex in structure and incompatible with different types of swords. Referee decisions are easily affected by perspective and human error, and lack real-time, multi-dimensional biomechanical feedback, making it difficult to quantify and analyze training effects.
Using a triboelectric pressure sensor, an electrical signal is generated through the contact and separation of positive and negative electric friction material layers. Combined with a deep learning model to analyze the impact information, it can achieve accurate judgment and real-time feedback of fencing actions.
It improves the accuracy of fencing judgments and the real-time nature of training results, provides multi-dimensional biomechanical feedback, reduces human error, and supports the development of personalized training plans.
Smart Images
Figure CN224220708U_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of sports equipment technology, and more specifically to a triboelectric pressure sensor for a fencing system and a fencing suit. Background Technology
[0002] Current fencing refereeing systems primarily rely on spring-loaded blade tips that sense pressure and transmit electrical signals. These spring-loaded tips require dedicated wiring, are structurally complex, and depend on a fixed external force for triggering, making them incompatible with the different requirements of épée and foil. Furthermore, current fencing judging relies mainly on the referee's visual observation, which is susceptible to limitations in perspective and human error, especially in high-speed combat where it's difficult to accurately determine the effectiveness of strikes (such as thrust force and impact location). Wireless technology is easily affected by athlete obstruction or environmental interference, leading to delays and misjudgments, impacting referee accuracy. Additionally, in daily training, fencing equipment cannot accurately determine and record the location and manner of impacts. Athletes lack real-time, multi-dimensional biomechanical feedback during training (such as impact force distribution and movement continuity), making it difficult to quantify technical deficiencies and effectively assist athletes in training.
[0003] Furthermore, current fencing competitions typically use high-speed video replay technology to determine the order and effectiveness of hits, but this method is inefficient and susceptible to subjective bias. Moreover, it cannot accurately reflect training results in real time during daily training, making it difficult to develop training plans tailored to individual athlete differences. Utility Model Content
[0004] The purpose of this disclosure is to provide a triboelectric pressure sensor for fencing systems, which addresses the problem of strong subjectivity and lack of objective data when judging striking behavior using existing technologies in fencing competitions.
[0005] To achieve the above objectives, this disclosure provides a triboelectric pressure sensor for a fencing system. The triboelectric pressure sensor includes: a first support material layer; a positively charged triboelectric material layer disposed on the first support material layer; a second support material layer; a negatively charged triboelectric material layer disposed on the second support material layer and disposed opposite to the positively charged triboelectric material layer, for contacting the positively charged triboelectric material layer when the sword tip or blade strikes the triboelectric pressure sensor, and for separating from the positively charged triboelectric material layer when the sword tip or blade leaves the triboelectric pressure sensor; a sensing electrode electrically connected to the negatively charged triboelectric material layer; and an output electrode electrically connected to the sensing electrode for outputting an electrical signal generated by the contact between the negatively charged triboelectric material layer and the positively charged triboelectric material layer.
[0006] Optionally, the sensing electrode is disposed below the negative friction material.
[0007] Optionally, the sensing electrode is the same size as the negative electrofriction material layer.
[0008] Optionally, the size of the triboelectric pressure sensor can be adjusted according to the required measurement accuracy.
[0009] Optionally, the sensing electrode is made of an elastic conductive material.
[0010] Optionally, the support material is an elastomer.
[0011] Optionally, the positively charged triboelectric material is a dielectric material that generates positive electricity through friction; the negatively charged triboelectric material is a dielectric material that generates negative electricity through friction.
[0012] Optionally, the output electrode is a conductive thin film.
[0013] On the other hand, this disclosure provides a fencing suit, wherein the inner surface of the fencing suit is provided with a triboelectric pressure sensor as described above.
[0014] Optionally, the triboelectric pressure sensors are uniformly arranged in an array on the inner surface of the fencing uniform.
[0015] Thirdly, this disclosure provides a fencing system, the fencing system comprising: an information collection module for acquiring contact information of the fencing sword, generating contact information and transmitting it to a data processing module when the sword strikes; a data processing module for receiving the contact information, extracting feature information from the contact information, and statistically analyzing the feature information and the number of strikes, the feature information including the time of strike, the location of strike, and the force of strike; and a data analysis module for analyzing the contact information to identify and classify the type of strike, wherein the type of strike includes thrust, miss, and whip strike.
[0016] Optionally, the information collection module includes a triboelectric pressure sensor.
[0017] Optionally, the system further includes a data visualization module, used to convert the hit information into an electrical signal graph, and generate a corresponding heat map according to the hit location based on the statistical feature information and the number of hits; when the number of hits at the hit location is greater than or equal to a preset number, the hit location is displayed in a first color on the heat map, when the number of hits at the hit location is less than the preset number, the hit location is displayed in a second color on the heat map, and the location not hit by the fencing is displayed in a third color on the heat map.
[0018] Optionally, the fencing system further includes a competition and training module, which calculates the score based on the feature information and the hit category according to a preset scoring rule; calculates the hit percentage for each category based on the hit category; and displays the heat map, the score, the hit percentage, and the feature information.
[0019] Optionally, the data analysis module analyzes the hit information based on a deep learning model. The construction process of the deep learning model includes: acquiring hit information of known hit categories and dividing the hit information into a training set, a validation set, and a test set; normalizing the hit information using a standardization method and converting the processed hit information into 2D matrix data composed of the number of channels and the time step; initializing the deep learning model, setting the loss function and optimizer, and preset the number of iterations; inputting the training set into the deep learning model for batch training, and following a randomly shuffled data order... Data augmentation is performed using the following methods: After each training round, the loss value and accuracy of the model are calculated using the validation set. When the preset number of iterations is reached, if the loss value reaches a preset loss threshold, the model weights at this time are saved as the model weights after training, and training is completed. If the loss value does not reach the preset loss threshold, training continues. The test set is input into the trained model to output a category prediction score and calculate the accuracy of the predicted category. When the accuracy reaches a preset accuracy, the model construction is completed. If the accuracy does not reach the preset accuracy, training is performed again.
[0020] Optionally, the deep learning model includes: four 1D convolutional layers, a ReLU activation function, a global average pooling layer, and four fully connected layers. The hit information is input into the deep learning model, and temporal feature information is extracted through the four 1D convolutional layers, expanding the number of channels of the feature information. The ReLU activation function is used to enhance the feature representation of the feature information, and the enhanced feature information is input into the global average pooling layer to compress its temporal dimension. The compressed feature information is then input into the fully connected layer, gradually reducing the dimensionality to three dimensions before outputting the predicted scores for three types of signals: stab, miss, and whiplash.
[0021] Optionally, the data analysis module is also used to identify valid hit signals in the hit information according to different competition types.
[0022] Through the above technical solution, when the sword tip or blade strikes the triboelectric pressure sensor, the positive and negative triboelectric material layers in the sensor come into contact and separate. Due to the different charges carried by the two layers of friction materials, a high potential difference is generated, driving the electrons in the external circuit to move in a specific direction, thereby generating an electrical signal. This electrical signal is transmitted from the negative triboelectric material layer to the output electrode via the sensing electrode. Since different striking methods generate different electrical signals, by converting the mechanical energy of the strike into an electrical signal, objective fencing data can be obtained, thus assisting in judgment.
[0023] Other features and advantages of the embodiments disclosed herein will be described in detail in the following detailed description section. Attached Figure Description
[0024] The accompanying drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the following detailed description to explain the embodiments of this disclosure, but do not constitute a limitation thereof. In the drawings:
[0025] Figure 1 This is a schematic diagram of the structure of a triboelectric pressure sensor provided in an embodiment of this disclosure;
[0026] Figure 2 This is a front view of a fencing uniform provided in an embodiment of this disclosure;
[0027] Figure 3 This is a side view of the fencing thrust method hit by the embodiment of this disclosure;
[0028] Figure 4 This is a side view of the fencing whip strike method provided in the embodiments of this disclosure;
[0029] Figure 5 This is a schematic diagram of the electrical signal generated when a fencing strikes a triboelectric pressure sensor, provided in an embodiment of this disclosure.
[0030] Figure 6 This is a schematic diagram of the structure of a fencing system provided in an embodiment of this disclosure;
[0031] Figure 7 This is a flowchart illustrating the deep learning model construction process provided in the embodiments of this disclosure;
[0032] Figure 8 This is a schematic diagram of the structure of a deep learning model provided in an embodiment of this disclosure.
[0033] Explanation of reference numerals in the attached figures
[0034] 1. Positively charged triboelectric material layer; 2. Negatively charged triboelectric material layer; 3. Induction electrode; 4. Output electrode; 5. First support material layer; 6. Second support material layer; 7. Fencing; 8. Triboelectric pressure sensor; 9. Fencing suit. Detailed Implementation
[0035] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of this disclosure.
[0036] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0037] Figure 1 This is a schematic diagram of the structure of a triboelectric pressure sensor provided in an embodiment of this disclosure. Figure 1 As shown, the triboelectric pressure sensor has a layered structure, including a first supporting material layer 5; a positively charged triboelectric material layer 1 disposed on the first supporting material layer 5; a second supporting material layer 6; a negatively charged triboelectric material layer 2 disposed on the second supporting material layer 6 and opposite to the positively charged triboelectric material layer 1, for contacting the positively charged triboelectric material layer 1 when the sword tip or blade strikes the triboelectric pressure sensor, and for separating from the positively charged triboelectric material layer 1 when the sword tip or blade leaves the triboelectric pressure sensor; a sensing electrode 3 electrically connected to the negatively charged triboelectric material layer 2; and an output electrode 4 electrically connected to the sensing electrode 3, for outputting the electrical signal generated by the contact between the negatively charged triboelectric material layer 2 and the positively charged triboelectric material layer 1.
[0038] Specifically, the triboelectric pressure sensor is evenly arranged in an array inside the fencing uniform, as shown in the front view below. Figure 2 As shown. In some embodiments, multiple triboelectric pressure sensors disposed within the fencing suit collect the impact information in a real-time synchronous manner.
[0039] Understandably, when the tip or blade of a fencing sword strikes the fencing uniform, the positive and negative electrostatic friction material layers of the sensor corresponding to the impact point come into contact and separate. Because the two layers of friction material carry different charges, a high potential difference is generated, driving the electrons in the external circuit to move in a specific direction, thus generating an electrical signal. This method collects weak mechanical energy and converts it into electrical energy, and it is self-driving without an external power source.
[0040] In some embodiments, the positively charged triboelectric material is a dielectric material that generates a positive charge during friction, such as PC or Nylon; the negatively charged triboelectric material is a dielectric material that generates a negative charge during friction, such as FEP, PTFE, or PVDF. The sensing electrode 3 can be an elastic conductive material such as conductive sponge or conductive aerogel, the output electrode 4 can be a conductive film such as copper or aluminum, and the support material 5 can be an elastomer such as polyurethane sponge or EVA sponge.
[0041] Figure 6 This is a schematic diagram of the structure of a fencing system provided in an embodiment of this disclosure. Figure 6 As shown, the fencing system includes: an information collection module for acquiring fencing strike information; when hit by the fencing sword, it generates strike information and transmits it to the data processing module; a data processing module for receiving strike information, extracting feature information from the strike information, and statistically analyzing the feature information and the number of strikes, including strike time, strike location, and strike force; and a data analysis module for analyzing the strike information to identify and classify the strike categories, including thrusts, misses, and whips.
[0042] In some embodiments, the information collection module includes a triboelectric pressure sensor. When the fencing sword strikes the fencing uniform, the triboelectric pressure sensor converts the impact into an electrical signal, which is then transmitted to the data processing module. Figure 5 This is a schematic diagram of the electrical signal generated by the triboelectric pressure sensor when a fencing strike is made, as provided in an embodiment of this disclosure. Figure 5 It can be seen that the electrical signals generated by different hitting methods have different characteristics. The characteristic of the thrusting signal is a strong single sine wave signal, the characteristic of the miss signal is a very weak output signal, which is only different from the standby signal, and the characteristic of the whipping signal is a combined signal composed of multiple unit outputs in a short period of time. Therefore, the hitting path of fencing can be deduced based on the different signal generation times. Figure 3 This is a side view of the fencing thrust method hit by the embodiment of this disclosure. When the fencing sword 7 hits the triboelectric pressure sensor 8 under the fencing uniform 9 alone, a peak output electrical signal is generated. The system provided by this disclosure collects the electrical signal of the triboelectric pressure sensor 8 and classifies it by analyzing its electrical signal characteristics. Figure 4This is a side view of the fencing whip strike method provided in the embodiment of this disclosure. When the fencing blade 7 passes through the triboelectric touch sensor 8 located at different positions in sequence, peak output electrical signals will be generated in sequence. The system provided in this disclosure analyzes the characteristics of its electrical signals to classify them and can visualize the hit path.
[0043] When the electrical signal is transmitted to the data processing module, the different impact methods generate electrical signals with different characteristics. Therefore, the data processing module extracts the characteristic information from the electrical signal to obtain the impact time, impact location, and impact force. Specifically, the data processing module marks the impact timestamp based on the time of receiving the electrical signal to determine the impact time. The impact location is precisely located based on the position of the triboelectric pressure sensor that generates the electrical signal in the array arrangement. Since different impact forces generate different electrical signal voltage values, the impact force is calculated based on the different voltage values of the acquired electrical signals. Simultaneously, the number of impacts is counted and recorded based on the number of received impact information. The data is transmitted from the data processing module to the data analysis module for analysis of the impact information to determine and classify the impact categories, which include stabbing, miss, and whipping.
[0044] Because the criteria for determining a valid hit signal differ across different fencing competition types, in some embodiments, the data analysis module is also used to identify valid hit signals in the hit information based on the different competition types. For example, in foil fencing, the hit time is determined first. If both fencers hit simultaneously, it is difficult to determine manually, but objective evidence can be provided based on the signal generation sequence. Regarding the hit location, foil fencing only recognizes hits to the torso, so only signals from the torso are valid. For the hit force, a pre-competition threshold of greater than x N (corresponding to a specific voltage value) is defined; only signals exceeding this voltage value are considered valid. Regarding the hit category, only thrusting hits are valid in foil fencing. This disclosure provides objective data support for fencing competitions by automatically analyzing and determining hit time, hit location, hit force, and hit category, avoiding the subjectivity of human judgment and improving the accuracy and efficiency of competition judging.
[0045] Deep learning is a new branch of machine learning, based on artificial neural networks, especially deep neural networks such as CNN, RNN, and KNN. It can automatically learn multi-level abstract features of data, making it suitable for various application scenarios. Specifically, it automatically extracts features from raw data (such as images and audio) through multi-layer neural networks without human intervention, achieving good application results. The goal of intelligent sports monitoring is to analyze athletes' movements, physical condition, and training effects in real time through technological means, and deep learning, with its powerful data processing capabilities, has become a key driving force. Therefore, the data analysis module in this embodiment is based on a deep learning model to realize the analysis and classification of feature information.
[0046] Specifically, the voltage signal duration for fencing actions (thrust, miss, whip) is 0.2-1 seconds. Since the sampling rate of the triboelectric pressure sensor is 2kHz, the signal data length is truncated to a consistent length of 5000 time steps during data acquisition. The acquired hit information for known categories is divided into training, validation, and test sets. Because the voltage values of the electrical signals differ for different hit methods—for example, the peak voltage of a thrust can reach 9V, while the voltage value of a miss is close to 0V—data preprocessing is required.
[0047] Figure 7 This is a flowchart illustrating the deep learning model construction process provided in the embodiments of this disclosure. Figure 7 As shown, the construction process of the deep learning model includes: acquiring hit information of known hit categories and dividing the hit information into training set, validation set, and test set; normalizing the hit information using a standardization method and converting the processed hit information into 2D matrix data composed of channel number and time step; initializing the deep learning model, setting the loss function and optimizer, and preset the number of iterations; inputting the training set into the deep learning model for batch training and performing data augmentation by randomly shuffling the data order; and completing each training round. Then, the model's loss value and accuracy are calculated using the validation set. After reaching the preset iteration number, if the loss value reaches the preset loss threshold, the model weights at this time are saved as the trained model weights, and training is completed. If the loss value does not reach the preset loss threshold, training continues. The test set is then input into the trained model to output a category prediction score and calculate the accuracy of the predicted category. When the accuracy reaches the preset accuracy, the model construction is complete. If the accuracy does not reach the preset accuracy, training is re-performed.
[0048] Specifically, this embodiment uses a standardization method to normalize the hit information, making its mean 0 and standard deviation 1, thereby optimizing the numerical stability of model training. It should be noted that this example uses a 2×4 sensor array, converting the single hit information into an 8-channel × 5000-time-step 2D matrix to conform to the input format of a convolutional neural network (CNN), that is, adjusting the original shape to a (number of channels, time step) structure to suit the feature extraction method of deep learning models.
[0049] The deep learning model is initialized, and the cross-entropy loss function, Adam optimizer, and a preset 200 iterations are set. The training set is then input into the deep learning model for batch training, and data augmentation is performed by randomly shuffling the data order to enhance the model's generalization ability. After each training round, the model's performance is evaluated using validation set data, and the model's loss value and prediction accuracy are calculated. After the preset number of iterations, if the loss value reaches a preset loss threshold, the model weights at this point are saved as the weights for the next training iteration, and training is complete. If the loss value does not reach the preset loss threshold, training continues. Finally, the trained model is loaded, and the test set data is input into the model. Based on the output category prediction scores, the accuracy of the predicted category is calculated. When the accuracy reaches a preset accuracy, the model construction is complete; if the accuracy does not reach the preset accuracy, training is re-run until the accuracy reaches the preset value.
[0050] Figure 8 This is a schematic diagram of the structure of a deep learning model provided in an embodiment of this disclosure. Figure 8 As shown, the deep learning model structure includes: four 1D convolutional layers (Conv), a ReLU activation function, a global average pooling layer, and four fully connected layers (FC). Specifically, the deep learning model receives electrical signals from each channel at 5000 time steps. These signals are processed by four 1D convolutional layers to extract temporal feature information (mean, standard deviation, peak value, etc.), gradually expanding the number of channels to 512, and combining the ReLU activation function to enhance the feature representation. Subsequently, global average pooling is used to compress the temporal dimension of the feature information, reducing computational complexity. Next, the compressed feature information is gradually reduced to a 3D output through a four-layer fully connected network. This output corresponds to the predicted scores for three types of signals: stab, miss, and whiplash.
[0051] In some embodiments, the system further includes a data visualization module, used to convert the hit information into an electrical signal graph, and generate a corresponding heat map according to the hit location based on the statistical feature information and the number of hits; when the number of hits to the hit location is greater than or equal to a preset number, the hit location is displayed in a first color on the heat map, when the number of hits to the hit location is less than the preset number, the hit location is displayed in a second color on the heat map, and the location not hit by the fencing is displayed in a third color on the heat map.
[0052] Specifically, the data visualization module receives the hit information processed by the data processing module. In this disclosure, this hit information is an electrical signal, which is converted into an electrical signal graph, thereby transforming the fencing hit process information into a schematic diagram. In some embodiments, the deep learning model used by the data analysis module can process both the electrical signal and the converted electrical signal graph. Since the data visualization module can generate a corresponding heatmap based on the hit feature information and the statistically recorded number of hits, it should be noted that when the information collection module is not hit by the fencing weapon, no hit information is generated. In this case, the unhit location, i.e., the location where no hit information is generated, is presented in the third color on the heatmap, which defaults to white. Specifically, during daily combat training, the data processing module counts the number of hits in various areas of the fencing uniform. When the number of hits at a certain location is greater than or equal to a preset number, it means that this location has been hit more frequently. This hit location is presented in the first color on the heatmap, which can be dark red, indicating that this location is a weak defensive area for the athlete and requires strengthened defensive practice. When the number of hits at a certain position is less than the preset number, it means that this position has been hit relatively few times. This hit position will be shown as the second color on the heat map. The second color can be light red, indicating that this position is an area where the athlete's attack is not precise and needs to be strengthened in attack practice.
[0053] Furthermore, in some embodiments, the total number of touches and the number of hits can be counted separately. When the percentage of hits to total touches is greater than P1, the corresponding hit location is displayed in red on the heatmap, representing a weak area in the athlete's defense. Conversely, when the percentage of hits to total touches is less than P2, the corresponding hit location is displayed in blue on the heatmap, representing areas where the athlete's attack is inaccurate. Therefore, the generated heatmap can be used to assess the athlete's offensive habits and defensive weaknesses, helping trainers develop training plans, assisting daily training, optimizing attack strategies, and providing targeted technical improvement suggestions.
[0054] In some embodiments, the fencing system further includes a competition and training module, which calculates a score based on the feature information and the hit category according to a preset scoring rule; calculates the hit percentage for each category based on the hit category; and displays the heatmap, the score, the hit percentage, and the feature information.
[0055] Specifically, the competition and training module receives data processed by the data processing module and can preset scoring rules according to different competition types. For example, in épée, hitting the entire body is considered a valid hit, while in foil, only hitting the torso is considered a valid hit. The module automatically calculates the valid score based on the received hit time, location, and force, and prompts the referee for confirmation. This reduces human error and improves the accuracy of referees' decisions in handling disputes, ensuring the fairness of the competition.
[0056] In daily sabre training, both whipping and thrusting are effective hits. However, unlike foil and épée, there's a lack of targeted testing and training for whipping techniques. After N1 repetitions of practice, the data analysis module categorizes each hit, and the competition and training module outputs the percentages of whipping, thrusting, and misses for each. When the whipping hit rate is greater than S1, the thrusting hit rate is less than S2, and the miss rate is less than S3, the training is considered up to standard. In specialized training, specific areas can be practiced. The competition and training module outputs the hit percentage. When the percentage of specific training repetitions exceeds Q, the hit training is considered up to standard.
[0057] In addition, the competition and training modules can be connected to the visualization module to display the heatmap generated by the visualization module, and to display the calculated score results, hit percentage, and feature information of the hit information. The competition and training modules also support displaying the first hit time and action classification results, and support slow-motion replay of the competition process and review of controversial calls.
[0058] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0059] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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 processor, 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0060] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0061] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0062] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0063] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0064] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0065] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0066] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A triboelectric pressure sensor for a fencing system, characterized in that, The triboelectric pressure sensor includes: First supporting material layer; A positively charged triboelectric material layer is disposed on the first support material layer; Second support material layer; A negatively charged triboelectric material layer is disposed on the second support material layer and is disposed opposite to the positively charged triboelectric material layer. It is used to contact the positively charged triboelectric material layer when the sword tip or the sword body hits the triboelectric pressure sensor, and to separate from the positively charged triboelectric material layer when the sword tip or the sword body leaves the triboelectric pressure sensor. The sensing electrode is electrically connected to the negatively charged triboelectric material layer; and The output electrode is electrically connected to the sensing electrode and is used to output the electrical signal generated by the contact between the negative electro-friction material layer and the positive electro-friction material layer.
2. The triboelectric pressure sensor according to claim 1, characterized in that, The sensing electrode is disposed below the negative electrofriction material layer.
3. The triboelectric pressure sensor according to claim 1, characterized in that, The sensing electrode is the same size as the negative electrofriction material layer.
4. The triboelectric pressure sensor according to claim 1, characterized in that, The size of the triboelectric pressure sensor is adjusted according to the required measurement accuracy.
5. The triboelectric pressure sensor according to claim 1, characterized in that, The sensing electrode is made of an elastic conductive material.
6. The triboelectric pressure sensor according to claim 1, characterized in that, The supporting material is an elastomer.
7. The triboelectric pressure sensor according to claim 1, characterized in that, The positively charged triboelectric material is a dielectric material that generates positive charge through friction; The negatively charged triboelectric material is a dielectric material that generates negative charge through friction.
8. The triboelectric pressure sensor according to claim 1, characterized in that, The output electrode is a conductive thin film.
9. A fencing uniform, characterized in that, The inner surface of the fencing uniform is provided with a triboelectric pressure sensor as described in any one of claims 1-8.
10. The fencing uniform according to claim 9, characterized in that, The triboelectric pressure sensors are evenly arranged in an array on the inner surface of the fencing uniform.