A pavement grade identification method and a suspension system embedded with a friction nanogenerator

Abstract

The application discloses a road surface grade identification method and a suspension system embedded with a friction nanogenerator, which comprises the following steps: acquiring a triboelectric signal; the triboelectric signal is output by a friction nanogenerator which synchronously acts with the suspension system; adopting wavelet transform to convert the triboelectric signal into image data; constructing a road surface grade identification model based on a deep learning network; inputting the image data into the road surface grade identification model to obtain a road surface grade identification result; the friction nanogenerator is used as a self-powered sensor, the output triboelectric signal is input into a convolutional neural network after wavelet transform, and the road surface grade is identified, so as to solve the problem that the suspension dynamic stroke sensor used in the prior art needs to be additionally equipped with a power supply device.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicles, in particular to a road surface grade identification method and a suspension system embedded with a friction nanogenerator. BACKGROUND

[0002] To ensure the stability of the driver's operation and the comfort of the passengers, active suspension, as a way to improve the performance of the suspension system, gradually enters people's field of vision and becomes one of the key components of intelligent driving vehicles. Compared with passive suspension, when the suspension system deforms due to road undulations and other reasons, active suspension can actively generate a force opposite to the inertial force to reduce the change in the position of the vehicle body. Therefore, it is usually necessary to accurately and timely identify the road unevenness and convert it into appropriate parameters input into the control system to achieve active control of the suspension. In addition, road unevenness is also related to the driving safety of the vehicle. Poor road conditions can accelerate the damage and aging of vehicle parts, affect the driver's judgment of the road environment, and pose a safety hazard to vehicle driving. Therefore, accurately identifying road unevenness is of great significance to optimizing the suspension control strategy of the vehicle and improving the driving performance and safety of the vehicle.

[0003] Among the ways known to the inventors, common road unevenness identification methods include direct measurement method and response-based identification method. The direct measurement method is divided into traditional measurement method and vehicle-mounted instrument-based method, the former mainly uses three-meter ruler method and level method, which is relatively complex to operate and more subjective; the latter mainly uses laser leveling instrument, which is fast and has good reproducibility, but is expensive. The method based on vehicle dynamics response uses sensors installed on the vehicle to identify road unevenness through vehicle dynamics response, which is more economical and convenient and has broad application prospects.

[0004] Among the ways known to the inventors, existing solutions mainly identify road grades based on suspension dynamic travel. In the solution, first, a suspension dynamic travel sensor is used to measure the dynamic travel of the vehicle suspension, then wavelet denoising is used to pre-process the dynamic travel signal, then the road unevenness coefficient estimate value of the pre-processed signal is calculated and an estimate value feature matrix is constructed, finally a judgment matrix of different road grades is constructed, and the road grade under a given distance is identified by comparing the similarity of the estimate value feature matrix and the judgment matrix of different road grades.

[0005] In order to realize the identification of road unevenness, in the manner known to the inventors, all of the sensors are used without exception, or directly identify the road elevation information, or in combination with the dynamic response to sense and monitor one or more dynamic parameters of the vehicle. The sensors used in these technologies are mostly conventional sensors, such as laser radar, displacement sensor, acceleration sensor, etc., which usually need to be installed on the vehicle body or suspension, and need additional power supply device for power supply. Therefore, how to reasonably design the embedded intelligent sensor without external power supply device on the vehicle with valuable space resources and realize the road grade identification has become a problem that cannot be avoided.

[0006] For vehicles, it is inevitable to encounter roads with poor road conditions during driving, and after long-time continuous driving, the temperature of each component will rise and the vibration will intensify, so that the sensors installed on the vehicle are faced with the problem of harsh working environment. This means that in order to popularize the road unevenness identification technology, the working life and reliability of the sensor under extreme harsh conditions cannot be ignored. Moreover, the cost of the sensor is also taken into account, and the use and maintenance cost is reduced while maintaining high precision, so as to promote the popularization and application of road unevenness identification technology. These are not mentioned in the prior art.

[0007] At the same time, in the manner known to the inventors, the existing research focuses mainly on the analysis and processing of the collected signals, and the design of the control system of the vehicle suspension using the identification results of the road grade. However, the collected original signals cannot be directly used as input parameters for road grade identification. And usually a series of pretreatment is carried out on the collected signals before the road grade identification, which makes the whole identification process complicated and increases the cost and threshold of actual use. SUMMARY

[0008] The purpose of the present application is to provide a road grade identification method and a suspension system embedded with a friction nanogenerator, which uses a friction nanogenerator as a self-powered sensor, and the output triboelectric signal is input to a convolutional neural network after wavelet transform for road grade identification, so as to solve the problem that the suspension dynamic stroke sensor used in the prior art needs to be equipped with a power supply device.

[0009] To achieve the above purpose, the present application provides the following scheme: the present application provides a road grade identification method, which comprises:

[0010] obtaining a triboelectric signal; the triboelectric signal is output by a friction nanogenerator acting synchronously with a suspension system;

[0011] using wavelet transform to convert the triboelectric signal into image data;

[0012] The road surface grade recognition model is constructed based on a deep learning network.

[0013] The image data is input into the road surface grade recognition model to obtain a road surface grade recognition result.

[0014] Preferably, the road surface grade recognition model is constructed based on a deep learning network, comprising:

[0015] A deep learning network and a data set are obtained.

[0016] The data set is divided into a training set and a test set; the training set and the test set each include a plurality of training sample pairs; each training sample pair is composed of historical image sample data and sample data labels; the historical image sample data is converted based on historical triboelectric signals output by a triboelectric nanogenerator;

[0017] The historical image sample data in the training set is input, and the sample data labels corresponding to the historical image sample data are output; the deep learning network is trained, and the sample pairs in the test set are used to test the trained deep learning network until the output error of the trained deep learning network reaches a set threshold; and the trained deep learning network is used as a road surface grade recognition model.

[0018] Preferably, the deep learning network is a convolutional neural network.

[0019] Also provided is a suspension system embedded with a triboelectric nanogenerator, comprising an upper shock absorber seat, a lower shock absorber seat, a shock absorber mounted between the upper shock absorber seat and the lower shock absorber seat, and a triboelectric nanogenerator matched with the shock absorber.

[0020] The triboelectric nanogenerator comprises generator bodies distributed in parallel with the shock absorber; the generator bodies comprise a first connecting portion fixed at a position above the shock absorber and a second connecting portion fixed at a position below the shock absorber; the first connecting portion and the second connecting portion move relative to each other along the shock absorbing direction of the shock absorber.

[0021] The first connecting portion is provided with interdigital electrodes that move synchronously therewith; the interdigital electrodes comprise a main body portion and a contact portion for outputting a triboelectric signal to the outside; the second connecting portion is provided with a friction portion that is in close contact with the main body portion; the friction portion moves synchronously with the second connecting portion and rubs against the main body portion.

[0022] The first connecting portion of the generator body is fixedly connected with the upper shock absorber seat, and the second connecting portion of the generator body is fixedly connected with the lower shock absorber seat.

[0023] Preferably, the friction part comprises a plurality of bosses arranged in sequence along the action direction of the second connecting part, each of the bosses synchronously acts with the second connecting part and rubs against the main body part.

[0024] Preferably, the surface of the boss rubbing against the main body part is coated with polytetrafluoroethylene.

[0025] Preferably, the width of each of the bosses is equal to the width of a single electrode on the interdigital electrode, and the groove width between the adjacent two bosses is equal to the interval between the electrodes.

[0026] Preferably, the first connecting part is an insulating hollow cylindrical sleeve, the axis of the first connecting part extends along the damping direction of the shock absorber, and the top of the first connecting part is fixed at a position above the shock absorber, and the bottom of the first connecting part is provided with an opening for the second connecting part to extend into, and the interdigital electrode is arranged on the inner wall of the first connecting part.

[0027] Preferably, the interdigital electrode comprises an interdigital electrode substrate made of a flexible circuit board, and the substrate is tightly attached to the inner wall of the first connecting part.

[0028] The present application has the following technical effects relative to the prior art:

[0029] The present application uses a friction nanogenerator as a self-powered sensor, the output triboelectric signal is input to a convolutional neural network after wavelet transform for road surface grade recognition, to solve the problem that the suspension dynamic stroke sensor used in the prior art needs to be additionally equipped with a power supply device. And the collected triboelectric signal data is preprocessed using wavelet transform, to solve the problem of complicated preprocessing. And the wavelet transform can effectively extract the time-frequency information in the triboelectric signal, and the transformed data can be directly used as the input of the convolutional neural network, without the need for additional preprocessing operation of the triboelectric signal, simplifying the operation of the preprocessing link. Further, a deep learning network is used to recognize the road surface grade, to solve the problem of complex recognition process. The deep learning network is simple to build, has strong feature extraction and generalization ability, can greatly simplify the recognition process while ensuring high recognition accuracy, effectively reduces the cost and threshold of recognition process maintenance and iteration, and is convenient for secondary development and extension. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0031] Figure 1This is a flowchart illustrating an embodiment of a road surface grade identification method provided by the present invention.

[0032] Figure 2 This is a theoretical model diagram of a linear suspension system in one embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram of the interdigitated electrode structure in one embodiment of the present invention;

[0034] Figure 4 This is a schematic diagram of the friction part structure in one embodiment of the present invention;

[0035] Figure 5 This is the basic structure of a suspension system with an embedded triboelectric nanogenerator in one embodiment of the present invention;

[0036] Figure 6 for Figure 5 Enlarged view of the triboelectric nanogenerator section;

[0037] Figure 7 This is a schematic diagram of a time-frequency image obtained by wavelet transform according to an embodiment of the present invention;

[0038] Figure 8 This is a schematic diagram of the structure of a convolutional neural network provided in an embodiment of the present invention;

[0039] Figure 9 A schematic diagram of a real triboelectric signal data array collected under different road surface excitation levels after the triboelectric nanogenerator prototype provided in an embodiment of this application was mounted on a vehicle suspension test bench;

[0040] Figure 10 This is a schematic diagram of triboelectric signal image data under different road surface excitation levels after wavelet transform preprocessing, provided in an embodiment of this application.

[0041] Figure 11 This is a schematic diagram of the confusion matrix of test results provided in an embodiment of this application.

[0042] Among them, 1-first connecting part, 2-second connecting part, 3-shock absorber, 4-main body part, 5-contact part, 6-bore, 7-mounting hole, 8-screw, 9-shock absorber upper seat, 10-shock absorber lower seat, 11-damper, 12-shock absorber spring. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] The purpose of the present application is to provide a road surface grade identification method and a suspension system embedded with a friction nanogenerator, using a friction nanogenerator as a self-powered sensor, and outputting a triboelectric signal after wavelet transform to a convolutional neural network for road surface grade identification, to solve the problem of additional power supply devices required for the suspension dynamic stroke sensor in the prior art.

[0045] In order to make the above-mentioned purposes, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below in combination with the drawings and specific embodiments.

[0046] As Figures 1 to 11 shown, in order to greatly simplify the complexity of the road surface identification process while ensuring identification accuracy, the present application provides a road surface grade identification method, which comprises:

[0047] Step 1: Obtain a triboelectric signal. Wherein, after the road surface excitation input into the vehicle suspension system, vibration is generated, and at this time the triboelectric signal is output by the friction nanogenerator acting synchronously with the suspension system.

[0048] Step 2: Convert the triboelectric signal into image data using wavelet transform.

[0049] Step 3: Construct a road surface grade identification model based on a deep learning network.

[0050] Step 4: Input the image data into the road surface grade identification model to obtain the road surface grade identification result.

[0051] In actual application process, the implementation process of the road surface grade identification method provided by the present application can be as Figure 1 shown. Wherein, the pre-trained convolutional neural network is the road surface grade identification model described above.

[0052] Further, in order to further improve the accuracy of road surface identification, the implementation process of the above step 3 can include:

[0053] Step 31: Obtain a deep learning network and a data set.

[0054] Step 32: Divide the data set into a training set and a test set. Both the training set and the test set include a plurality of training sample pairs. Each training sample pair is composed of historical image sample data and sample data labels. The historical image sample data is converted based on the historical triboelectric signal output by the friction nanogenerator.

[0055] Step 33: Train the deep learning network using historical image sample data from the training set as input and the corresponding sample data labels as output. Test the trained deep learning network using samples from the test set until the output error of the trained deep learning network reaches a set threshold. Then, use the trained deep learning network as the road surface classification model. The output error of the deep learning network is based on its prediction results and the corresponding sample data labels.

[0056] Furthermore, in order to enhance signal feature representation and facilitate road surface grade identification, the deep learning network employed in this application is as follows: Figure 8 Taking the convolutional neural network shown as an example, the implementation process of the road surface grade recognition method provided in this application will be explained.

[0057] Wavelet transform is used to preprocess the acquired triboelectric signal data to convert the one-dimensional time series into a two-dimensional time-frequency image. For example, the converted time-frequency image is as follows: Figure 7 As shown, its dimensions are 256×256×3, representing a three-channel color image.

[0058] The convolutional neural network was trained using several time-frequency image datasets. The structure and parameter settings of the convolutional neural network are as follows:

[0059] (1) Input layer: The input size is 256×256×3.

[0060] (2) Convolutional layer 1: Input channels are 3, output channels are 32, kernel size is 3, padding is 1, stride is 1, batch normalization and LeakyReLU activation function are set, and output size is 256×256×32.

[0061] (3) Pooling layer 1: The pooling kernel size is 2, the step size is 2, and the output size is 128×128×32.

[0062] (4) Convolutional layer 2: The input channel is 32, the output channel is 64, the kernel size is 3, the padding is 1, the stride is 1, and batch normalization and LeakyReLU activation functions are set. The output size is 128×128×64.

[0063] (5) Pooling layer 2: The pooling kernel size is 2, the step size is 2, and the output size is 64×64×64.

[0064] (6) Convolutional layer 3: The input channel is 64, the output channel is 128, the kernel size is 3, the padding is 1, the stride is 1, and batch normalization and LeakyReLU activation functions are set. The output size is 64×64×128.

[0065] (7) Pooling layer 3: the pooling kernel size is 2, the step is 2, and the output size is 32x32x128.

[0066] (8) Convolution layer 4: the input channel is 128, the output channel is 256, the convolution kernel size is 3, the padding is 1, the step is 1, batch normalization and LeakyReLU activation function are set, and the output size is 32x32x256.

[0067] (9) Pooling layer 4: the pooling kernel size is 2, the step is 2, and the output size is 16x16x256.

[0068] (10) Convolution layer 5: the input channel is 256, the output channel is 512, the convolution kernel size is 3, the padding is 1, the step is 1, batch normalization and LeakyReLU activation function are set, and the output size is 16x16x512.

[0069] (11) Pooling layer 5: the pooling kernel size is 2, the step is 2, and the output size is 8x8x512.

[0070] (12) Fully connected layer: the input Flatten is 8x8x512.

[0071] (13) Hidden layer 1: the input is 100, and the output is 4.

[0072] Among them, the input layer size of the convolutional neural network is determined by the image size obtained after wavelet transform preprocessing, and the final output category is determined by the number of road surface levels contained in the image data.

[0073] Based on the above description, the wavelet transform is used to preprocess the collected triboelectric signal data to solve the problem of complicated preprocessing. Moreover, the wavelet transform can effectively extract the time-frequency information in the triboelectric signal, and the transformed data can be directly used as the input of the convolutional neural network, without the need for additional preprocessing operations of the triboelectric signal, thereby simplifying the operation of the preprocessing link.

[0074] Figure 9 The application shows the real triboelectric signal data collected by the prepared triboelectric nanogenerator prototype mounted on the vehicle suspension test bench under the excitation of A, B, C and D four road surface levels, and two groups of triboelectric signals with a length of 150s are collected for each road surface level. It can be seen that as the road surface level increases, the amplitude of the triboelectric signal also increases, indicating that the output triboelectric signal of the triboelectric nanogenerator has the ability to reflect the road surface level. The collected data is divided into 150 groups of sample data for each of the four road surface levels according to the format of 4s in length and 2s in time interval. The sample data is preprocessed using wavelet transform to obtain 150 image data for each of the four road surface levels,Figure 10 The frictional electricity signal image data under different road surface level excitations after wavelet transform preprocessing is shown. The preprocessed image data is divided into training set, validation set and test set according to the ratio of 3:1:1, and input to the constructed deep learning network for training and testing, and the confusion matrix of the test result is as shown in Figure 11 It can be seen that the recognition accuracy of the trained network for road surface level reaches 98.33%, which proves the feasibility and effectiveness of the proposed road surface level recognition method.

[0075] Among them, Figure 9 A-1 and A-2 in the first column correspond to the real frictional electricity signal data collected under A-level road surface excitation, Figure 9 B-1 and B-2 in the second column correspond to the real frictional electricity signal data collected under B-level road surface excitation, Figure 9 C-1 and C-2 in the third column correspond to the real frictional electricity signal data collected under C-level road surface excitation, Figure 9 D-1 and D-2 in the fourth column correspond to the real frictional electricity signal data collected under D-level road surface excitation. Figure 10 Part (a) of FIG. 1 shows the image data of A-level road surface, Figure 10 Part (b) of FIG. 1 shows the image data of B-level road surface, Figure 10 Part (c) of FIG. 1 shows the image data of C-level road surface, Figure 10 Part (d) of FIG. 1 shows the image data of D-level road surface.

[0076] The present application uses a deep learning network to recognize the road surface level to solve the problem of complex recognition process. The deep learning network is simple to build, has strong feature extraction and generalization ability, can greatly simplify the recognition process while ensuring high recognition accuracy, effectively reduces the cost and threshold of recognition process maintenance and iteration, and is convenient for secondary development and extension.

[0077] In addition, the pre-trained convolutional deep learning network is mounted on the vehicle, which can realize real-time recognition of road surface level during vehicle driving, and can improve the response speed while saving computing resources.

[0078] As shown in Figures 2 to 6As shown, the application also provides a suspension system embedded with a friction nanogenerator, which comprises a shock absorber upper seat 9, a shock absorber lower seat 10, a shock absorber 3 mounted between the shock absorber upper seat 9 and the shock absorber lower seat 10, and a friction nanogenerator matched with the shock absorber 3. The friction nanogenerator comprises a generator body distributed in parallel with the shock absorber 3, which comprises a first connecting part 1 fixed at a position above the shock absorber 3 and a second connecting part 2 fixed at a position below the shock absorber 3. The first connecting part 1 and the second connecting part 2 move relative to each other along the shock absorbing direction of the shock absorber 3. Specifically, the first connecting part 1 and the second connecting part 2 are both fixed on the suspension system structure outside the shock absorber 3, and their mounting positions correspond to the top end and the bottom end of the shock absorber 3 respectively to realize parallel distribution with the shock absorber 3. The first connecting part 1 and the second connecting part 2 move relative to each other along the shock absorbing direction of the shock absorber 3. The first connecting part 1 is provided with interdigital electrodes that move synchronously therewith. The interdigital electrodes comprise a main body part 4 and a contact part 5 for outputting a triboelectric signal to the outside. The contact part 5 extends outside the main body part 4 so as to connect and arrange the wires. The second connecting part 2 is provided with a friction part that is attached to the main body part 4. The friction part moves synchronously with the second connecting part 2 and rubs against the main body part 4. Preferably, the second connecting part 2 has an L-shaped structure. The bottom part of the second connecting part 2 is fixedly connected to the position below the shock absorber 3 to increase the connection structure with the suspension system and improve the connection strength. The top part of the second connecting part 2 is used to connect the friction part so as to fully utilize the space of the suspension system and realize reasonable and reliable fixed connection.

[0079] The first connecting part 1 of the generator body is fixedly connected to the shock absorber upper seat 9, and the second connecting part 2 of the generator body is fixedly connected to the shock absorber lower seat 10. Specifically, the first connecting part 1 adopts an insulating hollow cylindrical sleeve which is fixed to the shock absorber upper seat by a screw 8. The bottom position of the second connecting part 2 is fixed to the shock absorber lower seat by a screw 8. The shock absorber upper seat and the shock absorber lower seat are fixed to the vehicle body and the vehicle wheel respectively. Specifically, mounting holes 7 are formed in the shock absorber upper seat 9 and the shock absorber lower seat 10 for connecting the vehicle body and the vehicle wheel respectively. The friction part of the second connecting part 2 is in close contact with the interdigital electrodes attached to the inner wall of the first connecting part 1. The triboelectric signal generated by the vibration of the suspension system is output to the outside through the contact part 5 of the interdigital electrodes.

[0080] The friction part is attached to the main body part 4 of the interdigital electrodes to ensure stable contact between them. During the vibration of the suspension system, the friction part and the main body part 4 of the interdigital electrodes can continuously rub against each other to generate a triboelectric signal for road surface grade identification and output the signal through the contact part 5. As a self-powered sensor, the generator helps to reduce the dependence on external power supply and reduce the complexity of the system. At the same time, the structure of the entire generator body is simple, which greatly reduces the processing and maintenance costs and prolongs the service life.

[0081] Further, the shock absorber 3 comprises a damper 11 and a shock spring 12, the damper 11 is connected at an intermediate position between the upper shock absorber seat 9 and the lower shock absorber seat 10, the first connecting part 1 is an insulated hollow cylindrical sleeve, the top of which is connected with the upper shock absorber seat 9, and the whole of which surrounds the outer circumferential side of the damper 11, and the first connecting part 1 and the damper 11 have an annular gap for the second connecting part 2 to extend into, and the shock spring 12 surrounds the outer circumferential side of the first connecting part 1 and has an annular gap with the first connecting part 1.

[0082] In a specific embodiment, the friction part comprises a plurality of bosses 6 arranged in sequence and spaced apart along the action direction of the second connecting part 2, each boss 6 moves synchronously with the second connecting part 2 and rubs against the main body part 4, and the distribution of each boss 6 makes the entire friction part have a grid-like structure, so as to optimize the charge distribution: the grid-like design can increase the contact area of the friction surface, so that the charge distribution is more uniform, when the main body part 4 and the friction part of the interdigital electrode rub against each other, the charge will be uniformly distributed on the surface, thereby reducing the unevenness of charge accumulation and improving the power generation efficiency. And improve the energy conversion efficiency: the grid-like design increases the number of contacts, so that mechanical movement can be more effectively converted into electrical energy, and the plurality of bosses 6 form a plurality of friction contacts, which significantly improves the power generation efficiency, and even at a lower vibration frequency, a higher energy conversion efficiency can be exhibited. Further, enhance the mechanical stability: the grid-like design not only ensures the power generation efficiency, but also enhances the stability of the mechanical structure, the grid-like structure can disperse stress and reduce stress concentration caused by mechanical movement, thereby prolonging the service life of the equipment.

[0083] In a specific embodiment, the surface of the boss 6 rubbing against the main body part 4 is coated with polytetrafluoroethylene, the surface of the boss 6 is coated with polytetrafluoroethylene to make the boss 6 have small friction resistance and high wear resistance, and the main body part 4 of the interdigital electrode is preferably made of copper material to output a frictional electric signal with more distinctive characteristics when rubbing against the boss 6.

[0084] In a specific embodiment, the width of each boss 6 is equal to the width of a single electrode on the interdigital electrode, and the groove width between the adjacent two bosses 6 is equal to the spacing between the electrodes, so that when relative displacement occurs, the area of the outer surface of different electrodes rubbing against different bosses 6 remains consistent, thereby enhancing the characteristics of the output electric signal.

[0085] In a specific embodiment, the first connecting part 1 is an insulating hollow cylindrical sleeve, the axis of the first connecting part 1 extends along the damping direction of the damper 3, and the top of the first connecting part 1 is fixed at a position above the damper 3, and the bottom of the first connecting part 1 is provided with an opening for the second connecting part 2 to extend into, and the interdigital electrode is arranged on the inner wall of the first connecting part 1, and the hollow cylindrical sleeve is arranged to protect the friction part and the interdigital electrode, so as to avoid the friction between the two being disturbed by the outside world, so as to fully guarantee the output of the electric signal.

[0086] In a specific embodiment, the interdigital electrode comprises an interdigital electrode substrate prepared by using a flexible circuit board, and the substrate is tightly attached to the inner wall of the first connecting part 1, so that the interdigital electrode can conform to the inner wall structure of the first connecting part 1, and the connection strength between the two is enhanced.

[0087] According to the actual needs, adaptive changes are within the scope of the present application.

[0088] It should be noted that for those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be regarded as limiting the claims involved.

[0089] In the present application, specific examples are applied to illustrate the principles and embodiments of the present application, and the above embodiment descriptions are only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in specific embodiments and application scope. In conclusion, the content of the present description should not be understood as a limitation of the present application.

Claims

1. A suspension system embedded with a frictional nanogenerator, characterized in that, The application is applied to a road surface grade identification method; the suspension system embedded with the friction nanometer generator comprises a shock absorber upper seat, a shock absorber lower seat, a shock absorber installed between the shock absorber upper seat and the shock absorber lower seat, and a friction nanometer generator matched with the shock absorber; The friction nanometer generator comprises generator bodies distributed in parallel with the shock absorber, the generator bodies comprising a first connecting part fixed at a position above the shock absorber and a second connecting part fixed at a position below the shock absorber, the first connecting part and the second connecting part moving relative to each other in the shock absorbing direction of the shock absorber; The first connecting part is provided with interdigital electrodes moving synchronously therewith, the interdigital electrodes comprising a main body part and a contact part for outputting a triboelectric signal to the outside, the second connecting part is provided with a friction part abutting against the main body part, the friction part moving synchronously with the second connecting part and rubbing against the main body part; The first connecting part of the generator body is fixedly connected with the shock absorber upper seat, and the second connecting part of the generator body is fixedly connected with the shock absorber lower seat; The friction part comprises a plurality of bosses arranged in sequence and at intervals in the moving direction of the second connecting part, each of the bosses moves synchronously with the second connecting part and rubs against the main body part, and the distribution of each of the bosses makes the whole friction part have a grid structure; the width of each of the bosses is equal to the width of a single electrode on the interdigital electrodes, and the groove width between the adjacent two bosses is equal to the interval between the electrodes.

2. The suspension system embedded with a frictional nanogenerator according to claim 1, wherein, The surface of the boss rubbing against the main body part is coated with polytetrafluoroethylene.

3. The suspension system embedded with a frictional nanogenerator according to claim 2, wherein, The first connecting part is an insulating hollow cylindrical sleeve, the axis of the first connecting part extends in the shock absorbing direction of the shock absorber, the top of the first connecting part is fixed at a position above the shock absorber, and the bottom of the first connecting part is provided with an opening for the second connecting part to extend into, and the interdigital electrodes are arranged on the inner wall of the first connecting part.

4. The suspension system embedded with a frictional nanogenerator according to claim 3, wherein, The interdigital electrodes comprise an interdigital electrode base prepared by using a flexible circuit board, and the base is tightly attached to the inner wall of the first connecting part.

5. The suspension system embedded with a frictional nanogenerator according to claim 1, wherein, The road surface grade identification method comprises: obtaining a triboelectric signal; the triboelectric signal is output by a friction nanometer generator moving synchronously with a suspension system; using wavelet transform to convert the triboelectric signal into image data; wherein the wavelet transform is used to pretreat the collected triboelectric signal data to convert a one-dimensional time sequence into a two-dimensional time-frequency image; the two-dimensional time-frequency image is a three-channel color image data; constructing a road surface grade identification model based on a deep learning network; inputting the image data into the road surface grade identification model to obtain a road surface grade identification result; wherein the road surface grade identification model is carried on a vehicle to realize real-time identification of the road surface grade during the driving of the vehicle.

6. The suspension system embedded with a frictional nanogenerator according to claim 5, wherein, Constructing a road surface grade identification model based on a deep learning network comprises: obtaining a deep learning network and a data set; dividing the dataset into a training set and a test set; the training set and the test set each include a plurality of training sample pairs; each training sample pair is composed of historical image sample data and sample data labels; the historical image sample data is converted based on historical triboelectric signals output by the triboelectric nanogenerator; training the deep learning network with the historical image sample data in the training set as input and the sample data labels corresponding to the historical image sample data as output, and testing the trained deep learning network with the sample pairs in the test set until the output error of the trained deep learning network reaches a set threshold, and taking the trained deep learning network as a road surface grade recognition model.

7. The suspension system embedded with a frictional nanogenerator according to claim 6, wherein, The deep learning network is a convolutional neural network.

Images