Monitoring method and friction power generation type intelligent cushion

Abstract

The application relates to the technical field of monitoring, and discloses a monitoring method and a friction power generation type intelligent seat cushion. The method is applied to the friction power generation type intelligent seat cushion, the friction power generation type intelligent seat cushion comprises a plurality of arrays, each array comprises a friction nanometer generator, the friction nanometer generator is connected with an ADC collector in parallel with a corresponding resistor, and the monitoring method comprises the following steps: acquiring a first voltage signal or a second voltage signal; determining a large-amplitude signal and a small-amplitude signal based on the first voltage signal and based on the second voltage signal; and performing action prediction based on the large-amplitude signal, the small-amplitude signal and a deep learning model. The friction nanometer generator is connected with the corresponding resistor in parallel, the first voltage signal or the second voltage signal is utilized, signals of different amplitudes are analyzed, and the deep learning model is used to determine the action corresponding to the signal, so that the monitoring effect of the friction nanometer generator is improved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring technology, and in particular to a monitoring method and a friction-generating intelligent seat cushion. Background Art

[0002] With the advent of the 5G era, the significant increase in data transmission rates has driven the rapid development of IoT technology. Today, a large number of electronic devices, including wearable sensors and processors, are interconnected, transmitting massive amounts of data collected by human sensors to the digital world in real time via high-speed wireless networks. Leveraging artificial intelligence (AI) technology, this data can be efficiently processed and analyzed, accurately assessing human status and enabling real-time posture monitoring. Currently, capacitive and resistive sensors are commonly used in seat cushions. Both require external power supplies to operate, resulting in high maintenance costs.

[0003] As a self-powered sensor, triboelectric nanogenerators (TGNs) convert low-frequency pressure signals into electrical signals through electrostatic friction. Due to the limited output signal of TGNs themselves, numerous improvements have been developed to enhance their electrical output and sensitivity. However, this has increased environmental interference with TGNs, hindering their commercialization.

[0004] When used as a smart cushion, a triboelectric nanogenerator generates signals not only from large movements like sitting and standing, but also from smaller movements like breathing, heartbeat, and center of gravity shifts. When detecting these small movements, interference from muscle movement, clothing friction, and external vibrations can affect the detection of these small movements. Currently, there is no solution to eliminate external interference when using triboelectric nanogenerators to monitor both small and large movements. Summary of the Invention

[0005] Based on this, it is necessary to address the technical problem of poor monitoring effect of friction nanogenerators in the existing technology, and propose a monitoring method, a friction-generating smart cushion and a storage medium.

[0006] In a first aspect, a monitoring method is provided for a triboelectric smart seat cushion, wherein the triboelectric smart seat cushion includes multiple arrays, each array including triboelectric nanogenerators, each triboelectric nanogenerator connected in parallel with a corresponding resistor and then connected to an ADC. The resistors connected in parallel to the triboelectric nanogenerators have different resistance values. The monitoring method includes:

[0007] Acquiring a voltage signal of each triboelectric nanogenerator in the array;

[0008] determining a first voltage signal or a second voltage signal according to whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, wherein the first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator;

[0009] Determining a large-amplitude signal and a small-amplitude signal based on a first voltage signal and a time period during which the first voltage signal appears; or determining a large-amplitude signal and a small-amplitude signal based on a second voltage signal and a time period during which the second voltage signal appears;

[0010] Action prediction is performed based on each of the large-amplitude signals, each of the small-amplitude signals, and a trained deep learning model to obtain a prediction result.

[0011] In a second aspect, a friction-generating intelligent seat cushion is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned monitoring method when executing the computer program.

[0012] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned monitoring method are implemented.

[0013] The monitoring method proposed in the present invention is applied to a triboelectric smart seat cushion, which includes multiple arrays, each of which includes triboelectric nanogenerators. The triboelectric nanogenerators are connected in parallel with their respective corresponding resistors and then connected to an ADC collector. The resistance of the resistors connected in parallel to each triboelectric nanogenerator is different. The monitoring method obtains the voltage signal of each triboelectric nanogenerator in the array, and then determines a first voltage signal or a second voltage signal based on whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state. The first voltage signal refers to the voltage signal corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator when it is in a saturated state, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator. Then, based on the first voltage signal and the time period when the first voltage signal appears, a large amplitude signal and a small amplitude signal are determined; or, based on the second voltage signal and the time when the second voltage signal appears, a large amplitude signal and a small amplitude signal are determined. Finally, based on the large amplitude signals, the small amplitude signals, and a trained deep learning model, action prediction is performed to obtain a prediction result. The present invention utilizes multiple friction nanogenerators in parallel with multi-resistance resistors, uses a first voltage signal or a second voltage signal to analyze signals of different amplitudes, and uses a deep learning model to determine the large-amplitude and small-amplitude actions corresponding to the signal, thereby greatly improving the monitoring effect of the friction nanogenerator. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0015] in:

[0016] Figure 1 A structural block diagram of a triboelectric nanogenerator of a monitoring device in one embodiment;

[0017] Figure 2 is another structural block diagram of a triboelectric nanogenerator of a monitoring device according to one embodiment;

[0018] Figure 3 FIG. 1 is a flow chart of a monitoring method in one embodiment. DETAILED DESCRIPTION

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0020] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] The monitoring method provided by the embodiment of the present invention can be applied to a friction-generating smart cushion. Figure 1 , Figure 1The triboelectric smart seat cushion, the ADC acquisition device, and the host computer are connected in sequence, wherein the triboelectric smart seat cushion communicates with the host computer through the ADC acquisition device. The host computer can also be replaced by a server, which can receive the voltage signal of each triboelectric nanogenerator in the array through the triboelectric smart seat cushion. The server then determines a first voltage signal or a second voltage signal based on whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state. The first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator. The server then determines a large-amplitude signal and a small-amplitude signal based on the first voltage signal and the time period when the first voltage signal appears; or determines a large-amplitude signal and a small-amplitude signal based on the second voltage signal and the time when the second voltage signal appears. Finally, the server performs motion prediction based on each of the large-amplitude signal, each of the small-amplitude signal, and a trained deep learning model to obtain a prediction result. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0023] The triboelectric smart seat cushion comprises an array of multiple triboelectric nanogenerators, and the preparation of the triboelectric smart seat cushion comprises the following steps:

[0024] Step A: First, an array of friction nanogenerators is prepared. In the present invention, the friction nanogenerator is stacked in sequence by a first electrode, a nanocomposite negative friction layer, a spacer layer, a positive friction layer material and a second electrode. Preferably, the first electrode, the nanocomposite negative friction layer, the spacer layer, the positive friction layer material and the second electrode are perpendicular to each other. Preferably, the first electrode and the second electrode materials of the dual-electrode structure friction nanogenerator include but are not limited to one of the conductive materials such as Cu, Al, ITO, Ag nanowires, etc. The preferred positive friction layer material of the dual-electrode structure friction nanogenerator includes but is not limited to nylon, PLA, PFA and other polymer films and metal materials. Usually, the spacer layer material is selected from one of the nanocomposite materials or insulating materials; further, the insulating material includes glass, nylon, etc.;

[0025] The method for preparing the above-mentioned triboelectric nanogenerator comprises the following steps:

[0026] Step A1: combining the nanomaterial with the negative friction layer material to form a nanocomposite material.

[0027] Step A2: Introducing the nanocomposite material into the mold to prepare nanocomposite negative friction layers with spacer layer structures of various sizes

[0028] Step A3: The nanocomposite negative friction layer, the first electrode array and the second electrode array are stacked and combined to obtain dual-electrode friction nanogenerators of various sizes.

[0029] Step A4: The first electrodes and the second electrodes of the obtained multiple friction nanogenerators are respectively combined with flexible PCB boards to form a friction nanogenerator array.

[0030] Step A5: Multiple electrodes are designed on the flexible PCB board, which are respectively connected to multiple friction nanogenerators and output to the data acquisition device through cables.

[0031] Step A6: The flexible PCB board includes an electrode layer and a protective layer. The electrode layers of the two flexible PCB boards are respectively connected to the first electrode and the second electrode of the friction nanogenerator, forming a structure from top to bottom of the protective layer, PCB electrode, first electrode, nanocomposite negative friction layer, spacer layer, positive friction layer material, second electrode, PCB electrode and protective layer.

[0032] The connection methods of the PCB electrodes and the first and second electrodes of the triboelectric nanogenerator include, but are not limited to, silver paste, vertical conductive glue, or spin coating.

[0033] Preferably, the arrangement of the flexible PCB includes but is not limited to combining 3-5 triboelectric nanogenerators into an array, and then arranging 9 arrays into a 3*3 large array for use as a seat cushion. The number of large arrays can be expanded as needed, including 5*5 to n*n, refer to Figure 2 , the friction nanogenerator is represented by a square, and four friction nanogenerators form an array.

[0034] Step B: Connect the array of friction nanogenerators to the resistor array. Specifically, the friction nanogenerators in the array are connected to resistors with resistance values ​​ranging from 100MΩ to 10GΩ, respectively, for gradient detection of large pressure signals and small pressure signals. (Principle explanation: The principle and basis of connecting resistors of different sizes in parallel: According to the characteristics of the friction nanogenerator, the larger the resistance connected in parallel with the friction nanogenerator, the larger the voltage signal it generates. At the same time, since the friction nanogenerator itself can be regarded as a capacitor, according to the formula τ=RC, where R is the external resistor and C is the equivalent capacitance of the friction nanogenerator, it can be seen that the larger the resistance connected in parallel with the friction nanogenerator, the longer its discharge time. According to this principle, the source of the external signal can be distinguished by analyzing the signal size and discharge time at the same time in the array. According to the formula for collecting voltage in the system, V=Voc*R1 / R1+R2, where R1 is the external resistor, R2 is the internal resistance of the friction nanogenerator, and Voc is the equivalent capacitance of the friction nanogenerator. The open-circuit voltage of the nanogenerator. It can be seen that after the friction nanogenerator is connected in parallel with different resistors, the voltage signal collected by it increases with the increase of the external resistance. Take the four acquisition channels of four small columns with external resistances of 100MΩ, 500MΩ, 1GΩ and 10GΩ as an example, corresponding to acquisition channels 1-4. For large movements, the voltage signal is very easy to saturate under the external resistance of 10G ohm (channel 4), or a signal with obvious peak value will appear. The large movement signals of other channels (channels 1-3) are extracted through the saturation time or the time when the peak occurs, and with the assistance of artificial intelligence. For small movement signals, the signal amplitude can be amplified and the discharge time can be extended through channels 3 and 4 with external large resistors to facilitate signal extraction)

[0035] Step C: Connecting the data acquisition system, specifically, connecting the triboelectric nanogenerator array connected in parallel with the resistor array to the acquisition system. Preferably, the acquisition chip used in the acquisition system includes but is not limited to ADI 1298, with a sampling frequency of 500Hz-1000Hz.

[0036] See also Figure 2 As shown, Figure 2 This is a flow chart of a monitoring method provided in accordance with an embodiment of the present invention. The monitoring method is applied to a triboelectric smart seat cushion comprising a plurality of arrays, each comprising a triboelectric nanogenerator. The triboelectric nanogenerators are connected in parallel with respective corresponding resistors and then connected to an ADC. The resistors connected in parallel to the respective triboelectric nanogenerators have different resistance values. The monitoring method comprises the following steps:

[0037] Step S101: acquiring a voltage signal of each triboelectric nanogenerator in the array;

[0038] In this embodiment, when pressure is applied to the triboelectric nanogenerators, voltage signals of the respective triboelectric nanogenerators are acquired.

[0039] As an example, an array of triboelectric nanogenerators is placed on a chair to collect external interference signals. Preferably, external interference signals include but are not limited to wind interference, floor vibrations, and passers-by walking by. Subsequently, pressure change signals are collected when the person is sitting still and switching actions, including but not limited to common actions such as standing up, sitting down, raising a leg, leaning forward, and leaning back. (The test signal contains small signals such as center of gravity shift and heartbeat, as well as large signals during switching actions.) The collected pressure change signal is filtered out by a notch filter to remove the 50Hz power frequency signal interference, and a low-pass filter is used to obtain the required voltage signal of each triboelectric nanogenerator in the array.

[0040] Step S102: determining a first voltage signal or a second voltage signal based on whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, wherein the first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator;

[0041] Step S103: determining a large-amplitude signal and a small-amplitude signal based on the first voltage signal and the time period in which the first voltage signal appears; or determining a large-amplitude signal and a small-amplitude signal based on the second voltage signal and the time in which the second voltage signal appears;

[0042] Step S104: performing motion prediction based on each of the large-amplitude signals, each of the small-amplitude signals, and the trained deep learning model to obtain a prediction result.

[0043] As an example, the method for obtaining a trained deep learning model includes the following: preprocessing the collected voltage signal, with specific preprocessing methods including but not limited to filtering, wavelet transform, Z-Score normalization, sliding window segmentation, etc., and labeling all preprocessed data according to the action category at the time of collection, and dividing them into training set, validation set, and test set in the deep learning process in an 8:1:1 ratio. Constructing a deep learning network to perform multi-classification tasks, wherein the main network layer architecture includes but is not limited to convolutional neural network (CNN) and long short-term memory network (LSTM), and adding functional layers such as batch normalization (BatchNorm) and random dropout (Dropout) to prevent overfitting of the deep learning network during training. The input data of the deep learning network is the preprocessed signal, and the output result is the action category number. The deep learning network trains network parameters in a supervised learning manner, updates parameters through the backpropagation algorithm, and optimizes the training process by setting strategies such as early stopping and learning rate decay. After training, the deep learning network can accept the preprocessed signal as input, calculate the category with the highest probability of the signal through forward reasoning, and return it as the classification result.

[0044] In this embodiment, each large-amplitude signal is input into a trained deep learning model for motion prediction to obtain the large-amplitude motion type corresponding to the large-amplitude signal, and each small-amplitude signal is input into a trained deep learning model for motion prediction to obtain the small-amplitude motion type corresponding to the small-amplitude signal.

[0045] In one embodiment, the step of determining the first voltage signal and the second voltage signal based on whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state includes:

[0046] Step 201: When the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, determining the voltage signal corresponding to the saturation state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator as a first voltage signal, and recording the time period in which the first voltage signal appears;

[0047] Step 202: When the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is not in a saturated state, the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is recorded as the second voltage signal.

[0048] As an example, for an array, when the force applied to the array (100N) is large, the signal of each channel in the array may be saturated. Therefore, it is necessary to query from high to low according to the size of the channel's external resistance. When the resistor channel with the largest resistance (10GΩ) is saturated, the time when the saturation signal appears is recorded. Based on this time, the signal of the next resistor channel in the same array (100MΩ) is continued to be queried. If it is not saturated, this signal will be recorded. If it is saturated, the query will continue downward. Similarly, the signals of the four channels in an array are queried, and the unsaturated signals in the four channels are recorded. This group of signals is recorded as a large-amplitude signal.

[0049] In one embodiment, the step of determining the large-amplitude signal and the small-amplitude signal based on the first voltage signal and the time period in which the first voltage signal appears includes:

[0050] Step 301: For each array, according to the time period when the first voltage signal appears, extract the voltage signals corresponding to the resistors in the array within the same time period as a first voltage signal set;

[0051] Step 302: extracting an unsaturated voltage signal from the first voltage signal set, and using the unsaturated voltage signal as the large-amplitude signal;

[0052] Step 303: Perform artificial intelligence decoupling and noise filtering based on the large-amplitude signal to obtain a small-amplitude signal.

[0053] In this embodiment, based on the peak value of the voltage signal in the resistor with the largest resistance connected in parallel with the friction nanogenerator and the discharge time of different channels, the signal corresponding to the recorded signal in channel 4 of other channels in the array is filtered out, and the filtered signal is filtered out by the characteristic value of the interference signal learned by artificial intelligence to filter out the required small-amplitude signal.

[0054] In one embodiment, the step of determining the large-amplitude signal and the small-amplitude signal based on the second voltage signal and the time when the second voltage signal occurs includes:

[0055] Step 401: For each array, based on the time period when the second voltage signal appears, extract the voltage signal corresponding to each resistor in the array within the same time period as the large-amplitude signal;

[0056] Step 402: Perform artificial intelligence decoupling and noise filtering based on the large-amplitude signal to obtain a small-amplitude signal.

[0057] In this embodiment, when the force (0.1 N) is relatively small, the signals of each channel in the array will not be saturated. Therefore, according to the time period when the second voltage signal appears, the voltage signals corresponding to each resistor in the array in the same time period are extracted.

[0058] The present invention utilizes multiple friction nanogenerators connected in parallel with multi-resistance resistors, analyzes signals of different amplitudes by utilizing the differences in amplitude and discharge time, and determines the large-amplitude and small-amplitude actions corresponding to the signals through the analyzed different signals.

[0059] It should be noted that in current applications of triboelectric nanogenerators, many wearable devices only connect to a single input impedance to collect signals. Although filtering can remove most noise signals, the mixture of various physiological signals of varying amplitudes, such as human movement, heartbeat, and center of gravity shift, makes it impossible to distinguish the specific movements and physiological states corresponding to the signals. By connecting multiple triboelectric nanogenerators in parallel with resistors of varying sizes and collecting and analyzing the voltage, it is possible to distinguish the collected signals.

[0060] In one embodiment, a friction-generating smart cushion is provided, which includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the friction-generating smart cushion is used to provide computing and control capabilities. The memory of the friction-generating smart cushion includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the friction-generating smart cushion is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a monitoring method.

[0061] In one embodiment, a friction-generating smart cushion is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0062] Acquiring a voltage signal of each triboelectric nanogenerator in the array;

[0063] determining a first voltage signal or a second voltage signal when the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, wherein the first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator;

[0064] Determining a large-amplitude signal and a small-amplitude signal based on a first voltage signal and a time period during which the first voltage signal appears; or determining a large-amplitude signal and a small-amplitude signal based on a second voltage signal and a time period during which the second voltage signal appears;

[0065] Action prediction is performed based on each of the large-amplitude signals, each of the small-amplitude signals, and a trained deep learning model to obtain a prediction result.

[0066] The present invention utilizes multiple friction nanogenerators in parallel with multi-resistance resistors, uses a first voltage signal or a second voltage signal to analyze signals of different amplitudes, and uses a deep learning model to determine the large-amplitude and small-amplitude actions corresponding to the signal, thereby greatly improving the monitoring effect of the friction nanogenerator.

[0067] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0068] Acquiring a voltage signal of each triboelectric nanogenerator in the array;

[0069] determining a first voltage signal or a second voltage signal when the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, wherein the first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator;

[0070] Determining a large-amplitude signal and a small-amplitude signal based on a first voltage signal and a time period during which the first voltage signal appears; or determining a large-amplitude signal and a small-amplitude signal based on a second voltage signal and a time period during which the second voltage signal appears;

[0071] Action prediction is performed based on each of the large-amplitude signals, each of the small-amplitude signals, and a trained deep learning model to obtain a prediction result.

[0072] The present invention utilizes multiple friction nanogenerators in parallel with multi-resistance resistors, uses a first voltage signal or a second voltage signal to analyze signals of different amplitudes, and uses a deep learning model to determine the large-amplitude and small-amplitude actions corresponding to the signal, thereby greatly improving the monitoring effect of the friction nanogenerator.

[0073] It should be noted that the functions or steps that can be achieved by the computer-readable storage medium or the friction-generating smart cushion can be found in the corresponding descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0074] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0075] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0076] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A monitoring method, characterized in that: The invention is applied to a triboelectric smart seat cushion, wherein the triboelectric smart seat cushion includes multiple arrays, each of which includes triboelectric nanogenerators. The triboelectric nanogenerators are connected in parallel with corresponding resistors and then connected to an ADC collector. The resistors connected in parallel with the triboelectric nanogenerators have different resistance values. The monitoring method includes: Acquiring a voltage signal of each triboelectric nanogenerator in the array; determining a first voltage signal or a second voltage signal according to whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, wherein the first voltage signal refers to the voltage signal corresponding to the saturated state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator, and the second voltage signal refers to the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator; Determining a large-amplitude signal and a small-amplitude signal based on a first voltage signal and a time period during which the first voltage signal appears; or determining a large-amplitude signal and a small-amplitude signal based on a second voltage signal and a time period during which the second voltage signal appears; Action prediction is performed based on each of the large-amplitude signals, each of the small-amplitude signals, and a trained deep learning model to obtain a prediction result.

2. The monitoring method according to claim 1, characterized in that: The step of determining the first voltage signal and the second voltage signal according to whether the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state comprises: When the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is in a saturated state, determining the voltage signal corresponding to the saturation state of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator as the first voltage signal, and recording the time period in which the first voltage signal appears; When the voltage signal of the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is not in a saturated state, the voltage signal with the largest amplitude among the voltage signals corresponding to the resistor with the largest resistance connected in parallel with the triboelectric nanogenerator is recorded as the second voltage signal.

3. The monitoring method according to claim 2, characterized in that: The step of determining a large-amplitude signal and a small-amplitude signal based on the first voltage signal and a time period in which the first voltage signal appears includes: For each array, according to the time period in which the first voltage signal appears, extract the voltage signals corresponding to the resistors in the array within the same time period as the first voltage signal set; extracting an unsaturated voltage signal from the first voltage signal set, and using the unsaturated voltage signal as the large-amplitude signal; Artificial intelligence decoupling and noise filtering are performed based on the large-amplitude signal to obtain a small-amplitude signal.

4. The monitoring method according to claim 2, characterized in that: The step of determining the large-amplitude signal and the small-amplitude signal based on the second voltage signal and the time when the second voltage signal appears includes: For each array, according to the time period in which the second voltage signal appears, extract the voltage signal corresponding to each resistor in the array in the same time period as the large-amplitude signal; Artificial intelligence decoupling and noise filtering are performed based on the large-amplitude signal to obtain a small-amplitude signal.

5. A friction-generating intelligent seat cushion, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the monitoring method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the monitoring method according to any one of claims 1 to 4 are implemented.

Images