Surface texture recognition system based on fabric tactile sensor and construction method thereof

Abstract

The present invention discloses a surface texture recognition system based on a fabric tactile sensor and a construction method thereof, which relate to the field of recognition accuracy control. The present invention weaves microstructured fabric sensing electrodes through yarn modified with conductive materials, and prepares fabric interdigitated electrodes through transfer technology, and the prepared interdigitated electrodes and sensing electrodes are stacked and assembled into a fabric tactile sensor with a bionic microstructure; the constructed microstructured sensing electrode can realize efficient perception of static force and mechanical vibration simultaneously through multi-dimensional deformation of the microstructure, so as to realize efficient recognition of fine surface texture; the constructed sensing electrode microstructure is adjustable and controllable, thereby realizing adjustable and controllable performance, avoiding the problems of device flexibility, air permeability and moisture permeability, wearing comfort, and reduced recognition accuracy caused by the commonly used template microstructure preparation method, as well as the signal collection difficulties and signal crosstalk problems caused by multi-mechanism mixed modes.

Description

Technical Field

[0001] The present invention belongs to the field of recognition accuracy control, and in particular, relates to a surface texture recognition system based on a fabric tactile sensor and a construction method thereof. Background Art

[0002] In recent years, with the rapid development of humanoid robots and human-computer interaction, higher requirements have been placed on high-performance tactile sensing devices and systems. This type of sensor can sense different tactile stimuli, such as surface texture, pressure, shape, etc., by simulating the tactile response of the skin. Especially in the field of surface texture recognition, the application of tactile sensors has great potential. Traditional surface texture recognition methods mostly rely on vision or high-precision mechanical detection, which is difficult to simulate the real tactile experience. Tactile sensors can efficiently capture subtle surface texture information by integrating flexible materials and micro-sensing units. They have good adaptability and sensitivity, and therefore have broad application prospects in smart wearable devices, robot tactile feedback, virtual reality and other fields. In order to obtain more sensitive tactile feedback information, existing technologies generally adopt multimodal sensor integration strategies to realize the perception of static force and mechanical vibration respectively (Nat. Electron. 2021, 4, 429; Matter 2022,5,1481; Adv.Sci.2023,10,2303949), for example, using piezoresistive sensors to mimic the slow adaptability of the human body to achieve the perception of static forces; using piezoelectric, capacitive or triboelectric sensors to mimic the fast adaptability of the human body to achieve the perception of high-frequency mechanical vibrations;

[0003] However, the multimodal integration strategy commonly adopted by existing surface texture recognition systems has the following problems: (1) Multimodal devices require multiple signal collection circuits, which increases the inconvenience of the use process; (2) The device is composed of multiple layers of electrodes, and shear failure is prone to occur between the electrodes, which increases the failure probability of the device during use; (3) Crosstalk between multiple signals will seriously affect the final recognition accuracy; (4) The mapping relationship between the sensing signal and the surface texture is still unclear; Therefore, how to construct a single-loop piezoresistive tactile sensor that can simultaneously achieve efficient perception of static and dynamic forces, and thus achieve accurate recognition of surface texture, has always been a key challenge. Summary of the Invention

[0004] In response to the problems in the related art, the present invention proposes a surface texture recognition system based on a fabric tactile sensor and a construction method thereof to overcome the above-mentioned technical problems existing in the existing related art.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0007] S1. Preparing a fabric sensing electrode with a honeycomb microstructure; specifically comprising the following steps:

[0008] S11, depositing a MXene aqueous dispersion and a PEDOT:PSS aqueous solution on the surface of the cotton yarn by an alternating deposition technique to obtain a MXene / PEDOT:PSS composite modified yarn;

[0009] S12, weaving the MXene / PEDOT:PSS composite modified yarn into a fabric sensing electrode having a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process;

[0010] S2. Preparing a fabric interdigital electrode; specifically comprising the following steps:

[0011] S21, printing a conductive silver paste on the surface of the non-woven fabric substrate by transfer printing technology to form a fabric interdigitated electrode;

[0012] S3. Constructing a surface texture recognition system; specifically comprising the following steps:

[0013] S31, assembling the fabric sensing electrode with the honeycomb microstructure and the fabric interdigital electrode into a fabric tactile sensor by ultrasonic bonding;

[0014] S32, constructing a surface texture recognition system according to the fabric tactile sensor, microcontroller, transimpedance amplifier, and inverter;

[0015] Microstructured fabric sensing electrodes are woven from yarns modified with conductive materials, and fabric interdigitated electrodes are prepared using transfer printing technology. The prepared interdigitated electrodes and sensing electrodes are then stacked and assembled into a fabric tactile sensor with a biomimetic microstructure. Because the fabric structure can be designed during the weaving process, the constructed microstructured sensing electrodes can simultaneously achieve efficient sensing of static forces and mechanical vibrations through multi-dimensional microstructural deformation (vertical compression deformation and shear deformation), thereby achieving efficient recognition of fine surface textures.

[0016] Preferably, the S11 includes the following steps:

[0017] S111, immersing the cotton yarn in a quaternary ammonium salt cationic modifier at a bath ratio of 1:5 to 1:30 at 20 to 80° C. for 1 to 30 minutes to make the yarn positively charged; then drying at 60° C. to obtain a cationic modified yarn;

[0018] S112, immersing the cationic modified yarn in a MXene aqueous dispersion at a bath ratio of 1:5 to 1:30 at 20 to 80° C. for 1 to 30 minutes to obtain a MXene modified yarn;

[0019] S113, repeating the S111 process with the MXene-modified yarn to obtain a positively charged MXene-modified yarn; then immersing the positively charged MXene-modified yarn in a PEDOT:PSS aqueous solution at a bath ratio of 1:5 to 1:30 at 20 to 80° C. for 1 to 30 minutes to perform PEDOT:PSS deposition, and then drying at 60° C.;

[0020] S114. Repeat S111, S112 and S113 three times to obtain MXene / PEDOT:PSS composite modified yarn.

[0021] Preferably, the mass concentration of the quaternary ammonium salt cationic modifier in S111 is 10 mg / mL.

[0022] Preferably, the mass concentration of the MXene aqueous dispersion in S112 is 10 mg / mL.

[0023] Preferably, the mass concentration of the PEDOT:PSS aqueous solution in S113 is 10 mg / mL.

[0024] Preferably, in the multi-shuttle layered weft insertion weaving process described in S12, the number of weft shuttles is 2 to 3, the number of weft layers is 2 to 6, the weft insertion angle is 15 to 90°, and the weaving density of the warp and weft yarns is 400 yarns / 10 cm.

[0025] Preferably, the solid content of the conductive silver paste in S21 is 70 wt %, and the transfer load of the conductive silver paste is 5 wt %.

[0026] Preferably, the ultrasonic bonding method in S31 has an ultrasonic power of 2000W, an ultrasonic frequency of 20 kHz and a duration of 2 minutes.

[0027] Preferably, the S32 includes the following steps:

[0028] S321. Power the fabric tactile sensor, convert the current flowing through the fabric tactile sensor into a voltage through the transimpedance amplifier, and then convert the voltage into a positive voltage through an inverter and input it into a microcontroller.

[0029] Preferably, the yarn modification active materials used in S1 for modifying the yarn with conductive active materials include carbon black, acetylene black, graphene, carbon nanotubes, silver nanoparticles, MXene, conductive polymers (polyaniline, polypyrrole, polyethylene thiophene, etc.), etc., and the transfer active materials in the transfer technology include conductive silver paste, MXene, graphene, carbon nanotubes, carbon black and other conductive pastes, etc.; the fabric substrate includes woven fabrics, knitted fabrics, non-woven fabrics, paper, polymer films, etc.; the yarn modification technology in S1 includes but is not limited to sizing, dip coating, infrared sizing, surface polymerization, etc.

[0030] A construction system for a surface texture recognition system based on a fabric tactile sensor, including a fabric sensing electrode preparation module, a fabric interdigital electrode preparation module, and a surface texture recognition system construction module;

[0031] The fabric sensing electrode preparation module is used to prepare a fabric sensing electrode having a honeycomb microstructure;

[0032] The fabric interdigital electrode preparation module is used to print conductive silver paste on the surface of a non-woven fabric substrate by transfer printing technology to form a fabric interdigital electrode;

[0033] The surface texture recognition system building module is used to form a surface texture recognition system according to the fabric tactile sensor, the microcontroller, the transimpedance amplifier and the inverter.

[0034] The present invention has the following beneficial effects:

[0035] 1. The present invention proposes a method for constructing an efficient and accurate fabric-based surface texture recognition system. Microstructured sensing electrodes are prepared using a weaving process and a fabric tactile sensor is constructed. The multi-dimensional deformation effect of the bionic microstructure on the surface of the sensing electrode under the action of external force, including vertical compression deformation and horizontal shear deformation, is utilized to simultaneously achieve efficient perception of static force and mechanical vibration, and ultimately achieve accurate perception and recognition of fine surface textures.

[0036] 2. In the present invention, a variety of microstructured sensing electrodes can be prepared through a weaving process. The constructed sensing electrode microstructure is adjustable and controllable, thereby achieving adjustable and controllable performance, avoiding the problems of device flexibility, air and moisture permeability, wearing comfort, and reduced recognition accuracy caused by the commonly used template microstructure preparation method.

[0037] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying any creative work.

[0039] Figure 1 Schematic diagram of electrode structure parameters in Examples 1, 2, 3, and 4 of the present invention;

[0040] Figure 2 Microscope images of electrodes in Examples 1, 2, 3, and 4 of the present invention;

[0041] Figure 3 This is a three-dimensional microscope image of Example 1 of the present invention;

[0042] Figure 4 This is the SEM image of Example 1 of the present invention;

[0043] Figure 5 These are tactile perception performance curves of Examples 1, 2, 3, and 4 of the present invention;

[0044] Figure 6 The finite element strain model diagrams of Examples 1, 2, 3, and 4 of the present invention are shown;

[0045] Figure 7 The tactile sensitivity curves of Examples 1, 2, 3, and 4 of the present invention are shown in FIG. In the figure, S1, S2, S3, and S4 are the sensitivities of each interval, R 2 is the fitting linearity of each interval;

[0046] Figure 8 The tactile sensitivity curves of Example 1 and Comparative Examples 1, 2, and 3 of the present invention are shown in FIG. In the figure, S1, S2, S3, and S4 are the sensitivities of each interval, R 2 is the fitting linearity of each interval;

[0047] Figure 9 This is a schematic diagram of the high-frequency mechanical vibration test of the present invention;

[0048] Figure 10 This is a schematic diagram of the high-frequency vibration sensing performance of Example 1 of the present invention. From left to right in the figure, the sensor's response current curves to dynamic forces of 1 Hz, 3 Hz, 10 Hz, 30 Hz, and 100 Hz are shown.

[0049] Figure 11 This is a graph showing the relationship between the number of response peaks and the vibration frequency in Example 1 of the present invention.

[0050] Figure 12 Schematic diagram of the structure of the surface texture recognition system of the present invention;

[0051] Figure 13 This is a real-time surface texture recognition system of the present invention;

[0052] Figure 14 Schematic diagram of the recognition results of Example 1 of the present invention at a moving speed of 200 mm / s; the horizontal axis of the sample signal line graph and the template signal line graph in the figure is the number of data points;

[0053] Figure 15 Schematic diagram of the recognition results of Example 1 of the present invention under randomly variable moving speed; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0054] Figure 16 This is a schematic diagram of the recognition results of fabric No. 12 according to Example 1 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0055] Figure 17 This is a schematic diagram of the recognition results of fabric No. 14 in Example 1 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0056] Figure 18 This is a schematic diagram of the recognition results of fabric No. 11 in Example 2 of the present invention; the horizontal axes of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0057] Figure 19 This is a schematic diagram of the recognition results of fabric No. 11 in Example 3 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0058] Figure 20 This is a schematic diagram of the recognition results of fabric No. 11 in Example 4 of the present invention; the horizontal axis of the sample signal line graph and the template signal line graph in the figure is the number of data points;

[0059] Figure 21 This is a schematic diagram of the surface texture recognition results of a complex curved surface structure according to Example 1 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0060] Figure 22 This is a schematic diagram of the surface texture recognition results of a soft substrate according to Example 1 of the present invention; the horizontal axes of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0061] Figure 23 This is a schematic diagram of the surface texture recognition results of Comparative Example 1 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0062] Figure 24This is a schematic diagram of the surface texture recognition results of Comparative Example 2 of the present invention; the horizontal coordinates of the sample signal line graph and the template signal line graph in the figure are the number of data points;

[0063] Figure 25 This is a schematic diagram of the surface texture recognition results of Comparative Example 3 of the present invention. The horizontal axes of the sample signal line graph and the template signal line graph in the figure are the number of data points.

[0064] Figure 26 Schematic diagram of the neural network structure of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0066] Example 1

[0067] This embodiment is a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0068] (1) Preparation of biomimetic microstructured fabric tactile sensor: First, the transition metal carbide / nitride aqueous dispersion (i.e., MXene aqueous dispersion) and poly (3,4-ethylenedioxythiophene) / polystyrene sulfonate aqueous solution (i.e., PEDOT:PSS aqueous solution) were deposited on the surface of cotton yarn (metric count: 120) by alternating deposition technology: the yarn was first immersed in a quaternary ammonium salt cationic modifier of dodecyldimethylbenzyl ammonium chloride (1227) (10 mg / mL aqueous solution, Sinopharm Group Co., Ltd.) at a bath ratio of 1:20 at 60°C for 5 minutes to make the yarn positively charged, and then dried at 60°C to obtain the cationic modified yarn; then the cationic modified yarn was immersed in a MXene aqueous dispersion (10 mg / mL) at 60°C at a bath ratio of 1:20 After immersion for 5 minutes, MXene modified yarn was obtained; the MXene modified yarn was subjected to the above cationic modification process again to make it positively charged again, and then immersed in a PEDOT:PSS aqueous solution (10 mg / mL) at a bath ratio of 1:20 at 60°C for 5 minutes to deposit PEDOT:PSS, and then dried at 60°C; the above steps were repeated for 3 cycles to obtain a MXene / PEDOT:PSS composite modified yarn; the composite modified yarn prepared above was then woven into a fabric sensing electrode (MPHMF) with a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process, wherein the number of weft shuttles was 3, the number of weft layers was 6, the weft insertion angle was 15°, the weaving density of the warp and weft yarns was 400 yarns / 10 cm, and the constructed sensing electrode structure was as follows: Figure 1 As shown in a; conductive silver paste is printed on non-woven fabric (pure cotton, weight 100g / m 2 ) substrate surface, wherein the conductive silver paste has a solid content of 70 wt % and a conductive silver paste transfer load of 5 wt % to form a fabric interdigital electrode; the MPHMF sensing electrode and the interdigital electrode prepared above are assembled into a fabric tactile sensor by ultrasonic bonding (ultrasonic power: 2000 W, ultrasonic frequency: 20 kHz, time: 2 minutes);

[0069] (2) Construction of surface texture recognition system: The bionic structure fabric-based tactile sensor constructed in step (1) is combined with a microcontroller, a transimpedance amplifier, and an inverter to form a surface texture recognition system. First, the system generates a 0.5V power supply to power the sensor. The transimpedance amplifier is connected between the negative electrode of the sensor and gnd. Its function is to convert the current flowing through the sensor into a voltage. The amplification factor of the transimpedance amplifier is 330. Because the gain of the transimpedance amplifier is negative, the output of the transimpedance amplifier is connected to an inverter to convert the voltage into a positive voltage that can be input by the microcontroller. The output of the inverter is connected to the pin of the built-in ADC of the microcontroller. In this way, the voltage measured by the microcontroller divided by 330 is the current flowing through the sensor. The constructed surface texture recognition system collects data on various surface textures, establishes a classification model database, and then uses machine learning technology to compare the real-time signals collected by the sensor with the classification model database established by machine learning, thereby sensing and predicting the surface texture. First, the microsensor continuously collects the sensor's response current data to the surface texture at a sampling frequency of 100Hz, and then the microcontroller sends the data to the computer through the serial port. After receiving the data, the computer will perform data noise reduction processing: when the current size data collected by the sensor reaches a certain threshold of 50×10 -6 We start collecting data. After collecting 512 data, we standardize the data and input it into the model. The model structure consists of a residual block (each residual block contains two convolutional layers, a batch normalization layer, and a ReLU activation function), a contraction layer, an RSNet main structure, a loss function, and an optimizer.

[0070] Example 2

[0071] This embodiment is a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0072] (1) Preparation of biomimetic microstructured fabric tactile sensor: First, a transition metal carbide / nitride aqueous dispersion (i.e., MXene aqueous dispersion) and a poly (3,4-ethylenedioxythiophene) / polystyrene sulfonate aqueous solution (i.e., PEDOT:PSS aqueous solution) were deposited on the surface of cotton yarn (metric count: 30) by an alternating deposition technique: the yarn was first treated with a quaternary ammonium salt cationic modifier of dodecyldimethylbenzyl ammonium chloride (1227) (10 mg / mL aqueous solution, Sinopharm Group Co., Ltd.) at a bath ratio of 1:20 at 60 °C. Immerse for 5 minutes to make the yarn positively charged, and then dry it at 60°C to obtain a cation-modified yarn; then immerse the cation-modified yarn in a MXene aqueous dispersion (10 mg / mL) at a bath ratio of 1:20 for 5 minutes at 60°C to obtain a MXene-modified yarn; the MXene-modified yarn repeats the above cationic modification process again to make it positively charged again, and then immerse it in a PEDOT:PSS aqueous solution (10 mg / mL) at 60°C for 5 minutes at a bath ratio of 1:20 to deposit PEDOT:PSS, and then dry it at 60°C. Repeat the above steps for 3 cycles to obtain a MXene / PEDOT:PSS composite modified yarn; then the composite modified yarn prepared above is woven into a fabric sensing electrode (LHMF) with a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process, wherein the number of weft shuttles is 2, the number of weft layers is 4, the weft insertion angle is 45°, the weaving density of the warp and weft yarns is 400 threads / 10 cm, and the constructed sensing electrode structure is as follows: Figure 1 As shown in b, the conductive silver paste is printed on the non-woven fabric (pure cotton, weight 100g / m 2 ) substrate surface, wherein the conductive silver paste solid content is 70wt%, and the conductive silver paste transfer load is 5wt%, to form a fabric interdigital electrode; the MPHMF sensing electrode and the interdigital electrode prepared above are assembled into a fabric tactile sensor by ultrasonic bonding (ultrasonic power: 2000W, ultrasonic frequency: 20kHZ, time: 2 minutes).

[0073] (2) Construction of surface texture recognition system: The bionic structure fabric-based tactile sensor constructed in step (1) is combined with a microcontroller, a transimpedance amplifier, and an inverter to form a surface texture recognition system. First, the system generates a 0.5V power supply to power the sensor. The transimpedance amplifier is connected between the negative electrode of the sensor and gnd. Its function is to convert the current flowing through the sensor into a voltage. The amplification factor of the transimpedance amplifier is 330. Because the gain of the transimpedance amplifier is negative, the output of the transimpedance amplifier is connected to an inverter to convert the voltage into a positive voltage that can be input by the microcontroller. The output of the inverter is connected to the pin of the built-in ADC of the microcontroller. In this way, the voltage measured by the microcontroller divided by 330 is the current flowing through the sensor. The constructed surface texture recognition system collects data on various surface textures, establishes a classification model database, and then uses machine learning technology to compare the real-time signals collected by the sensor with the classification model database established by machine learning, thereby sensing and predicting the surface texture. First, the microsensor continuously collects the sensor's response current data to the surface texture at a sampling frequency of 100Hz, and then the microcontroller sends the data to the computer through the serial port. After receiving the data, the computer will perform data noise reduction processing: when the value reaches a certain threshold of 50×10 -6 We start collecting data, and after collecting 512 data points, we standardize the data and input it into the model. The model consists of three residual blocks. Each residual block consists of convolution, residual pooling, and full connection.

[0074] Example 3

[0075] This embodiment is a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0076] (1) Preparation of biomimetic microstructured fabric tactile sensor: First, the transition metal carbide / nitride aqueous dispersion (i.e., MXene aqueous dispersion) and poly (3,4-ethylenedioxythiophene) / polystyrene sulfonate aqueous solution (i.e., PEDOT:PSS aqueous solution) were deposited on the surface of cotton yarn (metric count: 120) by alternating deposition technology: the yarn was first treated with dodecyldimethylbenzyl ammonium chloride (1227) quaternary ammonium salt cationic modifier (10 mg / mL aqueous solution, Sinopharm Group Co., Ltd.) at a bath ratio of 1:20 at 60 ℃ for 5 minutes to make the yarn positively charged, and then dried at 60℃ to obtain a cation-modified yarn; the cation-modified yarn was then immersed in a MXene aqueous dispersion (10 mg / mL) at a bath ratio of 1:20 at 60℃ for 5 minutes to obtain a MXene-modified yarn; the MXene-modified yarn was repeated with the above cationic modification process to make it positively charged again, and then immersed in a PEDOT:PSS aqueous solution (10 mg / mL) at 60℃ for 5 minutes at a bath ratio of 1:20 to deposit PEDOT:PSS, and then dried at 60℃. Repeat the above steps for 3 cycles to obtain a MXene / PEDOT:PSS composite modified yarn; the composite yarn prepared above was then woven into a fabric sensing electrode (LTHMF) with a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process, wherein the number of weft shuttles is 2, the number of weft layers is 2, the weft insertion angle is 30°, the weaving density of the warp and weft yarns is 400 pieces / 10 cm, and the constructed sensing electrode structure is as follows Figure 1 As shown in c; a conductive silver paste was printed on the surface of a non-woven fabric substrate by transfer technology, wherein the conductive silver paste had a solid content of 70 wt % and a conductive silver paste transfer load of 5 wt % to form a fabric interdigital electrode; the MPHMF sensing electrode and the interdigital electrode prepared above were assembled into a fabric tactile sensor by ultrasonic bonding (ultrasonic power: 2000 W, ultrasonic frequency: 20 kHz, time: 2 minutes);

[0077] (2) Construction of surface texture recognition system: The bionic structure fabric-based tactile sensor constructed in step (1) is combined with a microcontroller, a transimpedance amplifier, and an inverter to form a surface texture recognition system. First, the system generates a 0.5V power supply to power the sensor. The transimpedance amplifier is connected between the negative electrode of the sensor and gnd. Its function is to convert the current flowing through the sensor into a voltage. The amplification factor of the transimpedance amplifier is 330. Because the gain of the transimpedance amplifier is negative, the output of the transimpedance amplifier is connected to an inverter to convert the voltage into a positive voltage that can be input by the microcontroller. The output of the inverter is connected to the pin of the built-in ADC of the microcontroller. In this way, the voltage measured by the microcontroller divided by 330 is the current flowing through the sensor. The constructed surface texture recognition system collects data on various surface textures, establishes a classification model database, and then uses machine learning technology to compare the real-time signals collected by the sensor with the classification model database established by machine learning, thereby sensing and predicting the surface texture. First, the microsensor continuously collects the sensor's response current data to the surface texture at a sampling frequency of 100Hz, and then the microcontroller sends the data to the computer through the serial port. After receiving the data, the computer will perform data noise reduction processing: when the value reaches a certain threshold of 50×10 -6 We start collecting data, and after collecting 512 data points, we standardize the data and input it into the model. The model consists of three residual blocks. Each residual block consists of convolution, residual pooling, and full connection.

[0078] Example 4

[0079] This embodiment is a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0080] (1) Preparation of bionic microstructured fabric tactile sensors:

[0081] First, the transition metal carbide / nitride aqueous dispersion (i.e., MXene aqueous dispersion) and poly (3,4-ethylenedioxythiophene) / polystyrene sulfonate aqueous solution (i.e., PEDOT:PSS aqueous solution) were deposited on the surface of cotton yarn (metric count: 80) by alternating deposition technology: the yarn was first immersed in a quaternary ammonium salt cationic modifier of dodecyldimethylbenzyl ammonium chloride (1227) (10 mg / mL aqueous solution, Sinopharm Group Co., Ltd.) at a bath ratio of 1:20 at 60 ° C for 5 minutes to make the yarn Positively charged, dried at 60°C to obtain a cationically modified yarn; the cationically modified yarn was then immersed in a MXene aqueous dispersion (10 mg / mL) at a bath ratio of 1:20 at 60°C for 5 minutes to obtain a MXene modified yarn; the MXene modified yarn was subjected to the above cationic modification process again to make it positively charged again, and then immersed in a PEDOT:PSS aqueous solution (10 mg / mL) at 60°C for 5 minutes at a bath ratio of 1:20 to deposit PEDOT:PSS, and then dried at 60°C. Repeat the above steps for 3 cycles to obtain a MXene / PEDOT:PSS composite modified yarn; the composite yarn prepared above was then woven into a fabric sensing electrode (SSHMF) with a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process, wherein the number of weft shuttles is 2, the number of weft layers is 2, the weft insertion angle is 90°, the weaving density of the warp and weft yarns is 400 threads / 10 cm, and the constructed sensing electrode structure is as follows: Figure 1 As shown in d; a conductive silver paste was printed on the surface of a non-woven fabric substrate by transfer technology, wherein the conductive silver paste had a solid content of 70 wt % and a conductive silver paste transfer load of 5 wt % to form a fabric interdigital electrode; the MPHMF sensing electrode and the interdigital electrode prepared above were assembled into a fabric tactile sensor by ultrasonic bonding (ultrasonic power: 2000 W, ultrasonic frequency: 20 kHz, time: 2 minutes);

[0082] (2) Construction of surface texture recognition system: The bionic structure fabric-based tactile sensor constructed in step (1) is combined with a microcontroller, a transimpedance amplifier and an inverter to form a surface texture recognition system. First, the system generates a 0.5V power supply to power the sensor. The transimpedance amplifier is connected between the negative electrode of the sensor and gnd to convert the current flowing through the sensor into a voltage. The amplification factor of the transimpedance amplifier is 330. Because the gain of the transimpedance amplifier is negative, the output of the transimpedance amplifier is connected to an inverter to convert the voltage into a positive voltage that can be input by the microcontroller. The output of the inverter is connected to the pin of the built-in ADC of the microcontroller. In this way, the voltage measured by the microcontroller divided by 330 is the current flowing through the sensor. The constructed surface texture recognition system collects data on various surface textures, establishes a classification model database, and perceives and predicts surface textures through machine learning technology. First, the microsensor will continuously collect the sensor's response current data to the surface texture at a sampling frequency of 100Hz, and then the microcontroller will send the data to the computer through the serial port. After receiving the data, the computer will perform data noise reduction processing: when the value reaches a certain threshold of 50×10 -6 We start collecting data, and after collecting 512 data points, we standardize the data and input it into the model. The model consists of three residual blocks. Each residual block consists of convolution, residual pooling, and full connection.

[0083] Example 5

[0084] This embodiment discloses a system for constructing a surface texture recognition system based on a fabric tactile sensor. The system can implement the method of the above embodiment, including a fabric sensing electrode preparation module, a fabric interdigital electrode preparation module, and a surface texture recognition system construction module.

[0085] The fabric sensing electrode preparation module is used to prepare a fabric sensing electrode having a honeycomb microstructure;

[0086] The fabric interdigital electrode preparation module is used to print conductive silver paste on the surface of a non-woven fabric substrate by transfer printing technology to form a fabric interdigital electrode;

[0087] The surface texture recognition system building module is used to form a surface texture recognition system according to the fabric tactile sensor, the microcontroller, the transimpedance amplifier and the inverter.

[0088] Comparative Example 1

[0089] This comparative example discloses a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0090] (1) Preparation of biomimetic microstructured fabric tactile sensor: The specific method is the same as that in Example 1, except that the woven structure is a non-microstructured plain weave structure;

[0091] (2) Construction of surface texture recognition system: The specific method is the same as that in Example 1.

[0092] Comparative Example 2

[0093] This comparative example discloses a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0094] (1) Preparation of biomimetic microstructured fabric tactile sensor: The specific method is the same as that of Example 1, except that the weaving technology is not used in the preparation of the sensing electrode. Instead, the honeycomb structure fabric is used to directly alternately deposit MXene and PEDOT:PSS active materials to prepare the sensing electrode (MPHMF);

[0095] (2) Construction of surface texture recognition system: The specific method is the same as that in Example 1.

[0096] Comparative Example 3

[0097] This comparative example discloses a method for constructing a surface texture recognition system based on a fabric tactile sensor, comprising the following steps:

[0098] (1) Preparation of biomimetic microstructured fabric tactile sensor: The specific method is the same as that in Example 1, and the active material is a single MXene material;

[0099] (2) Construction of surface texture recognition system: The specific method is the same as that in Example 1.

[0100] The transfer technology of the present invention is an existing technology, specifically, firstly engraving an interdigitated electrode stamp, then dipping it in conductive silver paste and printing it on the fabric surface.

[0101] The commercial name of the conductive silver paste of the present invention is Repairman NANO20, and other existing technologies may also be used.

[0102] The classification model database of the present invention is established by repeatedly collecting the response signals of a sample using a prepared sensor (the sample signal comprises 512 data points at a sampling frequency of 100 Hz) to obtain a database for that sample. This process is repeated for other samples to obtain a classification model database.

[0103] The machine learning technology of the present invention preferably adopts the technology of neural network learning.

[0104] The structural models of the sensing electrodes in Examples 1 to 4 are as follows: Figure 1 As shown by Figure 1As can be seen, the surfaces of the sensor electrodes in each embodiment have a grid microstructure of a certain size. Examples 1-3 all have double-sided microstructures, while Example 4 has a single-sided microstructure. The thicknesses of the sensor electrodes in Examples 1-4 are 1.3mm, 1.6mm, 0.56mm, and 0.4mm, respectively. The higher electrode thicknesses in Examples 1 and 2 are primarily due to the greater height of the double-sided grid, while Example 4 has the smallest thickness due to the single-sided microstructure. The differences in the sensor electrode microstructure sizes in Examples 1-4 are primarily due to differences in the weaving process parameters for the multi-shuttle, layered weft insertion method used during the weaving process.

[0105] The sensing electrodes of Examples 1 to 4 were observed under an optical microscope. Figure 2 As shown. Figure 2 It can be seen that the sensing electrode of Example 1 has the smallest honeycomb size (1.5*1.5mm) (there is a scale in the lower right corner of each figure, which can be calculated based on the scale), and its three-dimensional structure diagram shows that the honeycomb microstructure is mainly due to the mesh structure formed by the yarns interwoven with each other ( Figure 3 The three-dimensional honeycomb structure of Example 1 is further confirmed in the SEM images, as shown in FIG. Figure 4 shown.

[0106] The tactile perception performance of Examples 1 to 4 is as follows Figure 5 As shown. Figure 5 It can be seen that Example 1 has the widest monitoring range (0-400 kPa) and the largest relative current response (ΔI / I0). The microstructure deformation of Examples 1-4 under the same pressure was analyzed by finite element simulation. The results are as follows Figure 6 As shown. Figure 6 It can be seen that under the same pressure, the compression deformation of the sensing electrodes of Examples 1 to 4 are 12.3%, 5.6%, 9.5%, and 7.5%, respectively. Therefore, the better tactile sensing performance of Example 1 is mainly due to its larger deformation area under the action of external force. The current response curves of Examples 1 to 4 are further linearly fitted. Figure 7 As shown by Figure 7 It can be seen that the sensitivity of Example 1, Example 2, Example 3, and Example 4 are 2486.9 kPa respectively. -1 、677.7kPa -1 , 25.1kPa -1 , 87.8kPa -1 The highest sensitivity of Example 1 is mainly due to the fact that its MPHMF surface microstructure is more easily deformed under external force, which is also Figure 6 This was confirmed by finite element model analysis

[0107] The tactile perception curves of Example 1 and Comparative Examples 1 to 3 are as follows Figure 8 As shown by Figure 8 It can be seen that the sensitivity of Example 1 is 35.5 times, 3.1 times, and 4.3 times that of Comparative Example 1, Comparative Example 2, and Comparative Example 3, respectively (all of which are compared with the highest sensitivity in the figure, for example, Example 1 is 2486.9 kPa). -1 , Comparative Example 1 is 70.1kPa -1 , Comparative Example 2 is 792.6kPa -1 , Comparative Example 3 is 573.7kPa -1 ). Example 1 has the best tactile perception performance compared to the comparative example. This is mainly because the surface of the sensing electrode of Comparative Example 1 lacks microstructures, and the deformation area of ​​the microstructure under external force stimulation is small; Comparative Example 2 is targeted at surface modification of microstructured fabrics, and it is difficult for the active material to penetrate into the yarn inside the fabric, and it is difficult to establish a complete conductive path inside the yarn, which worsens the electron transfer process during tactile perception; Comparative Example 3 uses a single MXene material, and its conductivity is lower than that of Example 1, so the electrode interface resistance is large, and therefore the tactile perception performance is poor.

[0108] For Example 1, Figure 9 The test method for high-frequency mechanical vibration is shown in the following figure. Figure 10 and Figure 11 As shown. Figure 10 It can be seen that the maximum perceptible frequency of mechanical vibration in Example 1 can reach 100 Hz; and the number of electrical signal response peaks shows an obvious linear relationship with the vibration frequency ( Figure 11 ), indicating that Example 1 of the present invention has excellent sensing capabilities for high-frequency mechanical vibrations. This is primarily due to the rich surface microstructure and fast response recovery rate of Example 1, which far exceeds the piezoresistive tactile sensors reported in other literature.

[0109] The schematic diagram of the surface texture recognition system constructed by the present invention is as follows Figure 12 As shown, it mainly includes a tactile sensor, a microcontroller, a transimpedance amplifier and an inverter. It uses machine learning methods to identify and predict surface textures. The surface texture recognition system is trained by collecting data to extract texture features, and then establishes a template signal. The sensor in the texture recognition system collects real-time current response signals of the sample texture during repeated sliding on the sample surface. The collected texture signals are compared with the template signals obtained by machine learning to achieve surface texture perception.

[0110] The surface texture recognition system constructed by the present invention is shown in the figure Figure 13 The results of surface texture recognition in Example 1 at constant sliding speed (20 cm / s) and random speed are shown in Figure 1. Figure 14 and 15As shown in the figure, whether it is a constant high-speed sliding or a random variable speed, Example 1 shows a recognition accuracy of more than 99.7%, showing excellent recognition accuracy and ultra-high recognition speed, and the recognition speed and accuracy are better than human skin. The results of Example 1 for other surface texture recognition are as follows Figure 16 and 17 As shown in the figure, it can be seen that the recognition accuracy of Example 1 for other complex surface textures is also above 99.5%, showing excellent universality.

[0111] The recognition results of Example 2, Example 3 and Example 4 for the same surface texture are as follows: Figure 18 、 19 , 20. As can be seen from the figure, the recognition accuracy of Examples 2, 3, and 4 for the same surface texture is 80.7%, 70.8%, and 60.5%, respectively, which is much lower than that of Example 1. The lower recognition accuracy of Examples 2-4 compared to Example 1 is mainly due to Example 1 having a more optimal surface microstructure size, which is more conducive to the perception of static force and high-frequency vibration, and its superior tactile perception ability.

[0112] The recognition results of Example 1 for complex curved surface texture are as follows: Figure 21 As shown. Figure 21 It can be seen that the recognition accuracy of Example 1 for the surface texture of the curved structure is 99.7%. The recognition results of Example 1 for the surface texture of the soft structure are as follows: Figure 22 As shown in the figure, the surface texture recognition accuracy of Example 1 for soft structures is 95.7%, showing excellent robustness and wide adaptability.

[0113] The recognition results of surface texture of Comparative Example 1, Comparative Example 2 and Comparative Example 3 are as follows: Figure 23 、 24 , 25. As shown in the figure, the recognition accuracy of Comparative Examples 1, 2, and 3 for the same surface texture is 40.7%, 70.7%, and 62.8%, respectively. The lowest surface texture recognition accuracy in Comparative Example 1 is primarily due to the sensor's lack of surface microstructure, making it difficult to effectively sense static forces and mechanical vibrations. The lower recognition accuracy in Comparative Example 2 is primarily due to the surface deposition technology used in its sensing electrodes, making it difficult for the active material to penetrate the electrodes, resulting in poor tactile sensing performance. The lower recognition accuracy in Comparative Example 3 is primarily due to the use of a single MXene material as the active material in the electrodes, resulting in poor tactile sensing performance.

[0114] In summary, the present invention has developed an efficient surface texture recognition system based on a fabric-based tactile sensor based on weaving technology and transfer technology, which has the following advantages:

[0115] (1) Strong technical promotion: The conductive active materials used in the present invention are more selective, and the flexible substrate can be a textile substrate or other flexible films;

[0116] (2) The process is simple and suitable for mass production;

[0117] (3) The present invention adopts a weaving process to prepare a microstructured sensing electrode, and the electrode microstructure is adjustable and controllable, the structure is diverse, and the electrode structure is stable;

[0118] (4) The present invention adopts transfer printing technology to prepare interdigitated electrodes, which have good conductivity, no penetration between electrodes, and high preparation accuracy;

[0119] (5) The multi-dimensional deformation of the bionic microstructure on the surface of the sensing electrode under the action of external force, including vertical compression deformation and horizontal shear deformation, is utilized to simultaneously achieve efficient perception of static force and mechanical vibration. The sensitivity of static force perception is as high as 2486.9kPa. -1 , the response frequency to mechanical vibration is as high as 100HZ, which is far higher than the piezoresistive tactile sensors reported in the literature;

[0120] (6) The tactile sensor constructed by the present invention has an ultra-fast response speed to static force and mechanical vibration, with response times of 10mS and 3mS respectively, which is better than the response speed of human skin;

[0121] (7) Due to the efficient sensing capabilities of the tactile sensor constructed by the present invention for static forces and mechanical vibrations, it can accurately sense and identify fine surface textures. The surface texture recognition system constructed by the present invention has extremely high recognition accuracy and speed, with an accuracy of over 98.9% for more than 21 types of textures and a recognition speed of up to 30 cm / s, far exceeding the recognition speed and accuracy of human skin.

[0122] (8) The surface texture recognition system constructed by the present invention has excellent robustness, strong adaptability to complex shapes and curved structures, and high recognition accuracy;

[0123] (9) The bionic multi-level structure flexible pressure sensor prepared by the present invention has both good air and moisture permeability and wearing comfort, and good pressure sensing performance;

[0124] (10) The performance of the tactile sensor prepared by the present invention is adjustable and controllable, and the performance of the device and the recognition accuracy of the system can be adjusted by adjusting the microstructure model of the sensing electrode;

[0125] (11) Wide range of applications: The surface texture recognition system constructed by the present invention can be used in fields such as humanoid robots and human-computer interaction.

[0126] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0127] The preferred embodiments of the invention disclosed above are intended only to help illustrate the invention. These preferred embodiments do not exhaust all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for constructing a surface texture recognition system based on a fabric tactile sensor, characterized in that: The following steps are involved: S1. Preparation of a fabric sensing electrode with a honeycomb microstructure; The specific steps include: S11, depositing a MXene aqueous dispersion and a PEDOT:PSS aqueous solution on the surface of the cotton yarn by an alternating deposition technique to obtain a MXene / PEDOT:PSS composite modified yarn; S12, weaving the MXene / PEDOT:PSS composite modified yarn into a fabric sensing electrode having a honeycomb microstructure through a multi-shuttle layered weft insertion weaving process; S2. Preparing a fabric interdigital electrode; specifically comprising the following steps: S21, printing a conductive silver paste on the surface of the non-woven fabric substrate by transfer printing technology to form a fabric interdigitated electrode; S3. Constructing a surface texture recognition system; specifically comprising the following steps: S31, assembling the fabric sensing electrode with the honeycomb microstructure and the fabric interdigital electrode into a fabric tactile sensor by ultrasonic bonding; S32, constructing a surface texture recognition system according to the fabric tactile sensor, microcontroller, transimpedance amplifier, and inverter; S11 specifically includes: The S11 includes the following steps: S111, immersing the cotton yarn in a quaternary ammonium salt cationic modifier at a bath ratio of 1:5 to 1:30 at 20 to 80° C. for 1 to 30 minutes to make the yarn positively charged; then drying at 60° C. to obtain a cationic modified yarn; S112, immersing the cationic modified yarn in a MXene aqueous dispersion at a bath ratio of 1:5 to 1:30 for 1 to 30 minutes at 20 to 80° C. to obtain a MXene modified yarn; S113, repeating the process of S111 with the MXene-modified yarn to obtain a positively charged MXene-modified yarn; then immersing the positively charged MXene-modified yarn in a PEDOT:PSS aqueous solution at a bath ratio of 1:5 to 1:30 at 20 to 80° C. for 1 to 30 minutes to perform PEDOT:PSS deposition, and then drying at 60° C.; S114. Repeat S111, S112 and S113 three times to obtain MXene / PEDOT:PSS composite modified yarn.

2. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The mass concentration of the quaternary ammonium salt cationic modifier described in S111 is 10 mg / mL.

3. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The mass concentration of the MXene aqueous dispersion in S112 is 10 mg / mL.

4. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The mass concentration of the PEDOT:PSS aqueous solution described in S113 is 10 mg / mL.

5. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: In the weaving process of multi-shuttle layered weft insertion described in S12, the number of weft shuttles is 2 to 3, the number of weft layers is 2 to 6, the weft insertion angle is 15 to 90°, and the weaving density of the warp and weft yarns is 400 yarns / 10 cm.

6. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The solid content of the conductive silver paste in S21 is 70 wt %, and the transfer load of the conductive silver paste is 5 wt %.

7. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The ultrasonic bonding method in S31 has an ultrasonic power of 2000 W, an ultrasonic frequency of 20 kHz, and a duration of 2 minutes.

8. The method for constructing a surface texture recognition system based on a fabric tactile sensor according to claim 1, characterized in that: The S32 includes the following steps: S321. Power the fabric tactile sensor, convert the current flowing through the fabric tactile sensor into a voltage through the transimpedance amplifier, and then convert the voltage into a positive voltage through an inverter and input it into a microcontroller.

9. A system for implementing the method for constructing a surface texture recognition system based on a fabric tactile sensor according to any one of claims 1 to 8.

Images