CN115523943A - Flexible multi-modal touch sensing system based on non-grid sensing plane - Google Patents
Flexible multi-modal touch sensing system based on non-grid sensing plane Download PDFInfo
- Publication number
- CN115523943A CN115523943A CN202211336024.5A CN202211336024A CN115523943A CN 115523943 A CN115523943 A CN 115523943A CN 202211336024 A CN202211336024 A CN 202211336024A CN 115523943 A CN115523943 A CN 115523943A
- Authority
- CN
- China
- Prior art keywords
- resistance
- module
- grid
- sensing
- flexible
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D5/00—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable
- G01D5/12—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable using electric or magnetic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The invention discloses a flexible multi-mode touch sensing system based on a non-grid sensing plane, wherein a non-grid flexible plane sensing module is used for sensing multi-mode touch information and converting the multi-mode touch information into resistance information, an edge electrode module comprises N electrodes which are embedded into the edge of the non-grid flexible plane sensing module, the N electrodes are distributed and arranged and are not in contact with each other, any two electrodes form a resistance channel, and a resistance measuring circuit module is used for recording resistance change information of multiple channels in the edge electrode module and inputting the resistance change information into a neural network module; the neural network module is used for outputting multi-modal tactile information. According to the technical scheme, a plurality of edge electrodes are adopted to form the resistance measurement channel, the number of the resistance measurement channels affects the sensing precision of the multi-mode tactile information, the number of the electrodes can be obviously reduced under the condition of keeping the precision, the complex wire interconnection is avoided, and the multi-mode tactile information can be accurately sensed in real time.
Description
Technical Field
The invention belongs to the field of sensing and perception, and particularly relates to a flexible multi-modal touch perception system based on a non-grid sensing plane.
Background
In order to realize high-precision tactile perception, a large number of dense sensor units are distributed in a traditional flexible tactile sensing system, and each sensor unit individually responds to tactile information applied to the sensor unit and then transmits a perception signal. Due to the limitations of array design, the number of electrodes and the arrangement of the electrodes, the conventional flexible tactile sensing system often has problems in terms of precision, area, cost and the like. Therefore, how to realize large-area high-precision touch sensing in a low-cost and efficient manner is a very critical technical problem in the development of sensing technology.
In addition, human touch sense can also realize real-time accurate sensing on external physical information in various modes such as temperature, humidity, sliding, vibration and the like besides sensing pressure, and because the traditional flexible touch sense sensing system is limited by the density of units in an array and the complexity of a circuit, each sensing unit can only respond to physical signals in a single mode generally, so that the synchronous sensing of the multi-mode touch sense information is difficult to realize by simulating the real touch sense of a human, and meanwhile, the complicated decoupling process in the signal analysis process cannot be avoided, and the system is not beneficial to wide application.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a flexible multi-modal haptic sensing system based on a mesh-free sensing plane.
The specific technical scheme for realizing the purpose of the invention is as follows: a flexible multi-modal touch perception system based on a non-grid sensing plane comprises a non-grid flexible plane sensing module, an edge electrode module, a resistance measuring circuit module and a neural network module;
the non-grid flexible plane sensing module is used for sensing multi-modal tactile information and converting the multi-modal tactile information into resistance information;
the edge electrode module comprises N electrodes which are all embedded into the edge of the non-grid flexible plane sensing module, the N electrodes are distributed and arranged, are not in contact with each other, and any two electrodes are connectedThe electrodes form a resistance channel, and the N electrodes form
A plurality of resistive channels;
the number of the resistance channels is more than or equal to the dimension of multi-modal tactile information to be sensed;
the resistance measurement circuit module is used in the recording edge electrode module
The road channel resistance change information is input into the neural network module;
the neural network module is used for outputting multi-modal tactile information, and the input number of the neural network module is
And (4) respectively.
Furthermore, the non-grid flexible planar sensing module is a microstructure, the substrate material is an insulating material, and the substrate material is doped with conductive filler; and the non-grid flexible plane sensing unit is externally encapsulated with a flexible material.
Further, the multi-modal tactile information includes, but is not limited to, single or multi-point pressure magnitude, pressure action location, pressure action shape, pressure action area, pressure action direction, temperature, humidity;
the pressure action shape comprises a triangle, a quadrangle, a hexagon, a dodecagon or other polygons.
Furthermore, the edge electrode module is embedded in the edge of the non-grid flexible plane sensing module;
one end of each electrode is embedded into the non-grid flexible plane sensing module, the other end of each electrode extends out of the non-grid flexible plane sensing module, and the electrodes are not crossed.
Further, the microstructure comprises a porous structure, a skeleton-containing structure and a surface convex structure;
the substrate material comprises one or more of rubber, PI, PVDF, PDMS and PEDOT, PSS; the conductive filler includes one or more of carbon black, carbon nanotubes, graphene, and nano-metal particles.
Furthermore, the resistance measuring circuit module is a time division multiplexing multi-path resistance measuring circuit, measures the resistance between different electrode combinations in the edge electrode module, and comprises a control unit, a path selection unit, a resistance measuring and calculating unit and a data transmission unit;
the channel selection unit is composed of a plurality of multi-path selection switches, the switching of resistance channels among different edge electrode combinations is completed by matching with time sequence levels, the resistance measurement and calculation unit comprises an operational amplifier and a proportional amplifier composed of resistors, different potentials are output according to different channel resistors, the control unit is used for providing corresponding time sequence levels for the channel selection unit and measuring and calculating the potentials output by the resistance measurement and calculation unit to obtain the channel resistance, and the data transmission unit transmits resistance data of each channel to the neural network module.
Further, a PI film is further arranged on the grid-free flexible plane sensing module, and the PI film obtains different capacitances under different humidities based on the saturated salt humidity generating device.
Furthermore, a conductive silver wire grid is drawn on the PI film, and the external temperature is obtained according to the resistance of the silver wire grid based on a corresponding curve of the silver wire resistance to the temperature.
Further, the neural network module trains based on the data set pair;
the data set is multi-modal tactile information and corresponding multi-channel resistance value change information thereof;
the trained neural network module outputs multi-mode touch information based on multi-channel resistance information output by the resistance measurement circuit module, wherein the multi-mode touch information comprises a pressure action shape, a pressure action abscissa, a pressure action ordinate, a pressure action area, a pressure action size, a temperature and a humidity.
Compared with the prior art, the invention has the beneficial effects that:
(1) The technical scheme of the invention is based on a sensing module without a grid, can accurately sense multi-modal touch information in real time, and the sensing module has simple structure and process and low cost;
(2) According to the technical scheme, a plurality of edge electrodes are adopted to form a resistance measurement channel, the number of the resistance measurement channels affects the sensing precision of multi-mode tactile information, the number of the electrodes can be obviously reduced under the condition that the same precision as that of the prior art is kept, and complicated wire interconnection is avoided;
(3) According to the technical scheme, the multichannel resistor is predicted based on the trained neural network, and accurate multi-mode tactile information including pressure, action position, action shape, action area, action direction, temperature and humidity can be output;
drawings
Fig. 1 is a schematic structural diagram of a flexible multi-mode tactile perception system based on a meshless sensing plane according to the invention.
Fig. 2 is a schematic structural diagram of a meshless flexible planar sensing module and an edge electrode module in one embodiment of the invention.
FIG. 3 is a schematic circuit diagram of a resistance measurement circuit module according to an embodiment of the invention.
FIG. 4 is a logic diagram of the operation of the resistance measurement circuit module in one embodiment of the invention.
Fig. 5 is a graph of the change in sensed temperature in a meshless flexible planar sensing module in an embodiment of the invention.
Fig. 6 is a graph of humidity sensing in a meshless flexible planar sensor module in an embodiment of the invention.
Fig. 7 and 8 are schematic diagrams illustrating the pressure sensing result in the flexible multi-mode tactile perception system based on the meshless sensing plane according to the invention.
Detailed Description
A flexible multi-modal touch perception system based on a non-grid sensing plane comprises a non-grid flexible plane sensing module, an edge electrode module, a resistance measuring circuit module and a neural network module;
the non-grid flexible plane sensing module is used for sensing multi-modal tactile information and converting the multi-modal tactile information into resistance information;
the edge electrode module comprises N electrodes which are all embedded into the edge of the grid-free flexible plane sensing module, the N electrodes are distributed and arranged and are not in contact with each other, any two electrodes form a resistance channel, and the N electrodes form a resistance channel
A plurality of resistive channels;
the number of the resistance channels is more than or equal to the dimension of multi-modal tactile information to be sensed, and the number of the electrodes in the edge electrode module can be flexibly set according to the number of the multi-modal tactile information to be sensed.
The resistance measurement circuit module is used in the recording edge electrode module
The road channel resistance change information is input into the neural network module;
the neural network module is used for outputting multi-modal tactile information, and the input number of the neural network module is
When the number N of the electrodes is increased, the input number of the neural network module is also increased rapidly, and thus the output accuracy of the neural network module is also increased rapidly.
Through the system, multi-mode physical action is applied to the non-grid flexible planar sensing module through contact surfaces with different shapes, so that a plurality of channel resistors formed by combining edge electrodes in pairs are changed, the resistance measuring circuit module synchronously reads resistance value change information of each group of channels at high speed, the resistance value information is used as input of the neural network module, simultaneously, multi-mode physical information during testing is synchronously recorded and comprises single-point or multi-point pressure, pressure action position, pressure action shape, pressure action area, pressure action direction, temperature, humidity and the like which are used as output information of the neural network module to jointly construct a training database of the neural network module, and the trained neural network module can synchronously and accurately predict the multi-mode physical information to be sensed through the channel change information of each group generated by the multi-mode physical information to be sensed acting on the non-grid flexible planar sensing module.
Furthermore, the non-grid flexible planar sensing module is a microstructure, the substrate material is an insulating material, and the substrate material is doped with conductive filler; the non-grid flexible plane sensing unit is externally packaged with flexible materials, and the packaging method includes but is not limited to plastic hot pressing, plastic packaging machine packaging, thin film bonding packaging and the like.
The multi-modal tactile information includes but is not limited to single-point or multi-point pressure magnitude, pressure action position, pressure action shape, pressure action area, pressure action direction, temperature and humidity;
the pressure action shape comprises a triangle, a quadrangle, a hexagon, a dodecagon or other polygons.
Furthermore, the edge electrode module is embedded at the edge of the non-grid flexible plane sensing module, and the tail end of the edge electrode module is of a fractal structure consisting of a plurality of wires;
the edge electrode module is provided with N electrodes, each electrode contains a plurality of strands of thin wires, the tail end of each electrode is of a spiral fractal structure, and any two electrodes are taken to realize one channel to realize the same
And a resistance measurement channel. The higher output resistance dimension is realized, and the prediction precision is improved; in the multi-mode touch sensing field, the sensing accuracy is influenced by the number of sensing channels, and compared with an electrode setting mode in which resistance measuring points are formed by intersection points of electrode intersections in the traditional technology, the number of electrodes adopted in the method is small, and the sensing accuracy still keeps a high level.
Further, the microstructure comprises a porous structure, a skeleton-containing structure and a surface convex structure; the substrate material comprises one or more of rubber, PI, PVDF, PDMS, PEDOT, PSS and the like; the conductive filler includes one or more of carbon black, carbon nanotubes, graphene, and nano-metal particles, and different combinations may exhibit different properties.
Generally, rubber has better elasticity than materials such as PDMS; rubber doped with 10% carbon black, showing insulation and best flexibility; the rubber doped with 20% of carbon black has a resistance value of 600 omega and a resistance value strain of more than 20%; 23% doped carbon black has a resistance of 310 Ω and a resistance strain of about 20%; the combination of 20% carbon black with 3% carbon nanotubes exhibits 200 Ω and very high hardness with only less than 10% resistance strain.
Furthermore, the resistance measuring circuit module is a time division multiplexing multi-path resistance measuring circuit and is used for measuring the resistance between different electrode combinations in the edge electrode module, and the resistance measuring circuit module comprises a control unit, a path selection unit, a resistance measuring and calculating unit and a data transmission unit;
the channel selection unit consists of a plurality of multi-path selection switches, the switching of resistance channels among different edge electrode combinations is completed by matching with time sequence levels, the resistance measurement and calculation unit comprises an operational amplifier and a proportional amplifier consisting of resistors, different potentials are output according to different channel resistances, the control unit is used for providing corresponding time sequence levels for the channel selection unit and measuring and calculating the potentials output by the resistance measurement and calculation unit to obtain the channel resistance, and the data transmission unit transmits the resistance data of each channel to the neural network module;
the control unit of the resistance measurement circuit module is an MCU chip and is used for providing a corresponding time sequence level for the channel selection unit; the path selection unit consists of a plurality of multi-path selection switches and is matched with a time sequence level to complete the switching of resistance channels among different electrode combinations; the resistance measuring and calculating unit is an operational amplifier and a proportional amplifier consisting of resistors, outputs different potentials according to different connected loads, namely channel resistors, and measures and calculates the channel resistance through an ADC (analog to digital converter) channel of the MCU to obtain the channel resistance;
the data transmission unit consists of data transmission chips, including but not limited to chips corresponding to transmission schemes such as serial port communication, bluetooth communication and Zigbee communication, and transmits signals obtained by ADC conversion to the neural network module;
further, a PI film is further arranged on the grid-free flexible planar sensing module, the PI film obtains different capacitances under different humidities based on the saturated salt humidity generating device, and the environment humidity is obtained according to the capacitance of the PI film.
Furthermore, a conductive silver wire grid is drawn on the PI film, and the external temperature is obtained according to the resistance of the silver wire grid based on a corresponding curve of the silver wire resistance to the temperature.
Further, the multi-modal tactile information includes, but is not limited to, single or multi-point pressure magnitude, pressure action location, pressure action shape, pressure action area, pressure action direction, temperature, humidity;
the pressure action shape comprises a triangle, a quadrangle, a hexagon, a dodecagon or other polygons.
Further, the neural network module trains based on the data set, and the neural network is selected from the neural network types including but not limited to RBF NN, DNN, CNN, RNN, LSTM, etc.
The data set is multi-modal tactile information and corresponding multi-channel resistance value change information thereof;
the trained neural network module outputs multi-mode tactile information based on multi-channel resistance information output by the resistance measurement circuit module, wherein the multi-mode tactile information comprises a pressure action shape, a pressure action abscissa, a pressure action ordinate, a pressure action area, a pressure action size, temperature and humidity.
The present invention will be further described with reference to the following examples.
Examples
With reference to fig. 1, a flexible multi-mode tactile sensing system based on a mesh-free sensing plane includes a mesh-free flexible plane sensing module, an edge electrode module, a resistance measurement circuit module, and a neural network module;
the non-grid flexible plane sensing module is used for sensing multi-modal tactile information and converting the multi-modal tactile information into resistance information;
the edge electrode module comprises N electrodes which are all embedded in the electrodeAt the edge of the grid flexible plane sensing module, N electrodes are distributed and arranged and are not in contact with each other, any two electrodes form a resistance channel, and the N electrodes form
A resistor channel;
the number of the resistance channels is more than or equal to the dimension of multi-modal tactile information to be sensed;
the resistance measurement circuit module is used in the recording edge electrode module
The road channel resistance change information is input into the neural network module;
the neural network module is used for outputting multi-modal tactile information, and the input number of the neural network module is
And (4) respectively.
Furthermore, the non-grid flexible planar sensing module is a microstructure, the substrate material is an insulating material, and the substrate material is doped with conductive filler; the non-grid flexible plane sensing unit is externally packaged with flexible materials, and the packaging method includes but is not limited to plastic hot pressing, plastic packaging machine packaging, thin film bonding packaging and the like.
Further, the microstructure comprises a porous structure, a skeleton-containing structure and a surface convex structure;
the substrate material comprises one or more of rubber, PI, PVDF, PDMS, PEDOT, PSS and other materials; the conductive filler includes one or more of carbon black, carbon nanotubes, graphene, and nano-metal particles, and different combinations may exhibit different properties.
In the embodiment, the substrate material of the non-grid flexible planar sensing module adopts silicon sulfide rubber, dimethyl silicone oil, ethyl orthosilicate and dibutyltin dilaurate, the conductive filler material adopts conductive carbon black powder, and the doping proportion of the conductive carbon black powder is 20%.
The multi-modal tactile information includes but is not limited to single-point or multi-point pressure magnitude, pressure action position, pressure action shape, pressure action area, pressure action direction, temperature and humidity;
the pressure action shape comprises a triangle, a quadrangle, a hexagon, a dodecagon or other polygons.
Further, a PI film is further arranged on the grid-free flexible planar sensing module, the PI film obtains different capacitances under different humidities based on the saturated salt humidity generating device, and the environment humidity is obtained according to the capacitance of the PI film.
Furthermore, a conductive silver wire grid is drawn on the PI film, and the external temperature is obtained according to the resistance of the silver wire grid based on a corresponding curve of the silver wire resistance to the temperature.
Furthermore, the edge electrode modules are provided with N electrodes, each electrode comprises a plurality of fine wires, the tail end of each electrode is of a spiral fractal structure, one end of each electrode is embedded into the non-grid flexible planar sensing module, the other end of each electrode extends out of the non-grid flexible planar sensing module, and the electrodes are not crossed;
two electrodes are arbitrarily taken to realize one channel, and the realization is realized together
The resistance measuring channels are used for realizing higher output resistance dimensionality and improving prediction precision, and the number and the position of edge electrodes in the edge electrode module can be flexibly set according to requirements.
In this embodiment, 8 edge electrodes uniformly arranged are adopted, and three schemes are available for selecting the number of channels:
one is that 8 electrodes are divided into two groups to realize 4 channels; the second type is also divided into two groups, and each group respectively takes one electrode to be combined one by one to realize 16 channels; the third is that 2 electrodes are selected from 8 electrodes optionally to be combined, and 28 channels can be realized;
in this embodiment, the second scheme is adopted, that is, 4 electrodes on the left side of the sensor are marked as A1, A2, A3, and A4, and 4 electrodes on the right side are marked as B1, B2, B3, and B4. A total of 16 resistance channels A1B1, A1B2, 8230A 4B4 are realized.
Furthermore, the resistance measuring circuit module is a time division multiplexing multi-path resistance measuring circuit and is used for measuring the resistance between different electrode combinations in the edge electrode module, and the resistance measuring circuit module comprises a control unit, a path selection unit, a resistance measuring and calculating unit and a data transmission unit;
the channel selection unit consists of a plurality of multi-path selection switches, the switching of resistance channels among different edge electrode combinations is completed by matching with time sequence levels, the resistance measurement and calculation unit comprises an operational amplifier and a proportional amplifier consisting of resistors, different potentials are output according to different channel resistances, the control unit is used for providing corresponding time sequence levels for the channel selection unit and measuring and calculating the potentials output by the resistance measurement and calculation unit to obtain the channel resistance, and the data transmission unit transmits the resistance data of each channel to the neural network module;
the control unit of the resistance measuring circuit module is an MCU chip and is used for providing a corresponding time sequence level for the access selection unit; the path selection unit consists of a plurality of multi-path selection switches and is matched with a time sequence level to complete the switching of resistance channels among different electrode combinations; the resistance measuring and calculating unit is an operational amplifier and a proportional amplifier consisting of resistors, outputs different potentials according to different connected loads, namely channel resistors, and measures and calculates the channel resistance through an ADC (analog to digital converter) channel of the MCU to obtain the channel resistance;
the data transmission unit is composed of data transmission chips, including but not limited to chips corresponding to transmission schemes such as serial port communication, bluetooth communication and Zigbee communication, and transmits signals obtained through ADC conversion to the neural network module;
as shown in fig. 3 and 4, the time division multiplexing circuit can rapidly switch channels according to the flow in fig. 4, so as to implement real-time measurement of the resistance and data transmission. The specific logic is that from the A1B1 channel, the MCU chip reads the channel resistance at the moment and transmits the channel resistance to the upper computer, and then the right connected electrode is switched, namely the channel is replaced by the A1B2 channel to repeat the steps of reading and transmitting, and the A1B4 channel is a small cycle period; and switching the left connected electrode once after the small cycle is finished, and returning the right connected electrode to the beginning, namely starting A2B1, wherein A1-A4 are a large cycle period.
Further, the neural network module trains based on the data set pair;
the data set is multi-modal tactile information and corresponding multi-channel resistance value change information thereof;
the trained neural network module outputs multi-mode tactile information based on multi-channel resistance information output by the resistance measurement circuit module, wherein the multi-mode tactile information comprises a pressure action shape, a pressure action abscissa, a pressure action ordinate, a pressure action area, a pressure action size, temperature and humidity.
For the neural network module, a resistance set composed of 16 resistances as parameters is input, and the shape of pressure action, the abscissa of pressure action, the ordinate of pressure action, the area of pressure action, the size of pressure action, the temperature and the humidity are output to be 7 parameters in total;
the pressure shape that wherein the training process experiment arrived is designed 16, including circular, pentagon, regular triangle, right angled triangle, square, regular pentagon, regular hexagon, regular octagon, regular decagon, regular dodecagon, fan-shaped, the hexagram shape, the four corners star, the cross, the ring shape, lightning shape. A square area with the pressure action position range of 10cm × 10cm, the pressure action area is from 1cm < 2 > to 5cm < 2 >, and the pressure action size is 0-100N. The temperature test range is 20 ℃ to 150 ℃. The humidity range is 10% RH to 97% RH.
The training set of the neural network contains more than 6000 pieces of data, and the prediction set contains 300 pieces of data different from the training set.
As shown in fig. 5 and 6, the flexible multi-mode tactile perception system based on the meshless sensing plane can show different resistance and capacitance values in different temperature and humidity environments.
As shown in fig. 7, the neural network after training predicts 300 pieces of data composed of channel resistance sets, and the pressure-sensitive prediction shows that the neural network accurately predicts the 293 pieces of pressure action shapes therein, with an accuracy rate of 97.6%.
As shown in fig. 8, the x-axis and y-axis are pressure acting positions, the z-axis is pressure acting magnitude, the trained neural network predicts 300 pieces of data composed of channel resistance sets, and the pressure sensation prediction is expressed as:
the pressure action has 56.6% of the prediction result deviation less than 5%, and 11% of the prediction result deviation less than 1%; the horizontal coordinate of the pressure action position has 60% of prediction result deviation within 0.36cm, and the vertical coordinate is 64% within 0.35 cm; the pressure-acting area has a predicted result deviation of 57.5% which is less than 0.304cm2.
The foregoing embodiments illustrate and describe the general principles and principal features of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed.
Claims (9)
1. A flexible multi-modal touch perception system based on a non-grid sensing plane is characterized by comprising a non-grid flexible plane sensing module, an edge electrode module, a resistance measuring circuit module and a neural network module;
the non-grid flexible plane sensing module is used for sensing multi-modal tactile information and converting the multi-modal tactile information into resistance information;
the edge electrode module comprises N electrodes which are all embedded into the edge of the grid-free flexible plane sensing module, the N electrodes are distributed and arranged and are not in contact with each other, any two electrodes form a resistance channel, and the N electrodes form
A resistor channel;
the number of the resistance channels is more than or equal to the dimension of multi-modal tactile information to be sensed;
the resistance measurement circuit module is used in the recording edge electrode module
Road channel resistance change information is input into neural netA winding module;
the neural network module is used for outputting multi-modal tactile information, and the input number of the neural network module is
And (4) respectively.
2. The grid-free sensing plane-based flexible multi-modal haptic perception system according to claim 1, wherein the grid-free flexible plane sensing module is a microstructure, the base material is an insulating material, and the base material is doped with a conductive filler; and the non-grid flexible plane sensing unit is externally encapsulated with a flexible material.
3. The grid-free sensing plane based flexible multi-modal haptic perception system according to claim 1, wherein the multi-modal haptic information includes but is not limited to single or multi-point pressure magnitude, pressure action position, pressure action shape, pressure action area, pressure action direction, temperature, humidity;
the pressure action shape comprises a triangle, a quadrangle, a hexagon, a dodecagon or other polygons.
4. The mesh-free sensing plane based flexible multi-modal haptic perception system according to claim 1, wherein the edge electrode module is embedded at the edge of the mesh-free flexible plane sensing module;
one end of each electrode is embedded into the non-grid flexible plane sensing module, the other end of each electrode extends out of the non-grid flexible plane sensing module, and the electrodes are not crossed.
5. The grid-free sensing plane based flexible multi-modal haptic perception system according to claim 2, wherein the micro-structure comprises a porous structure, a skeleton-containing structure, and a surface convex structure;
the substrate material comprises one or more of rubber, PI, PVDF, PDMS and PEDOT; the conductive filler includes one or more of carbon black, carbon nanotubes, graphene, and nano-metal particles.
6. The grid-free sensing plane-based flexible multi-modal touch sensing system according to claim 4, wherein the resistance measurement circuit module is a time division multiplexing resistance measurement circuit, measures the resistance between different electrode combinations in the edge electrode module, and comprises a control unit, a channel selection unit, a resistance measurement unit and a data transmission unit;
the channel selection unit is composed of a plurality of multi-path selection switches, switching of resistance channels among different edge electrode combinations is completed by matching with time sequence levels, the resistance measurement and calculation unit comprises an operational amplifier and a proportional amplifier composed of resistors, different potentials are output according to different channel resistances, the control unit is used for providing corresponding time sequence levels for the channel selection unit and measuring and calculating the potentials output by the resistance measurement and calculation unit to obtain the channel resistance, and the data transmission unit transmits resistance data of each channel to the neural network module.
7. The grid-free sensing plane-based flexible multi-modal haptic perception system according to claim 2, wherein a PI film is further arranged on the grid-free flexible plane sensing module, and the PI film obtains different capacitances at different humidities based on a saturated salt humidity generating device.
8. The grid-free sensing plane-based flexible multi-modal haptic perception system according to claim 7, wherein a conductive silver wire grid is drawn on the PI film, and the conductive silver wire grid obtains external temperature according to resistance of the silver wire grid based on a corresponding curve of silver wire resistance to temperature.
9. The mesh-free sensing plane based flexible multi-modal haptic perception system according to claim 1, wherein the neural network module is trained based on a data set pair;
the data set is multi-modal tactile information and corresponding multi-channel resistance value change information thereof;
the trained neural network module outputs multi-mode tactile information based on multi-channel resistance information output by the resistance measurement circuit module, wherein the multi-mode tactile information comprises a pressure action shape, a pressure action abscissa, a pressure action ordinate, a pressure action area, a pressure action size, temperature and humidity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211336024.5A CN115523943A (en) | 2022-10-28 | 2022-10-28 | Flexible multi-modal touch sensing system based on non-grid sensing plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211336024.5A CN115523943A (en) | 2022-10-28 | 2022-10-28 | Flexible multi-modal touch sensing system based on non-grid sensing plane |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115523943A true CN115523943A (en) | 2022-12-27 |
Family
ID=84702705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211336024.5A Pending CN115523943A (en) | 2022-10-28 | 2022-10-28 | Flexible multi-modal touch sensing system based on non-grid sensing plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115523943A (en) |
-
2022
- 2022-10-28 CN CN202211336024.5A patent/CN115523943A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11965755B2 (en) | Triboelectric sensor and control system | |
| CN102770742B (en) | Flexible pressure sensor and flexible pressure sensing array | |
| CN103983382B (en) | A kind of Grazing condition capacitance type touch sensor | |
| CN101512311B (en) | Tactile sensor for curved surfaces and manufacturing method thereof | |
| CN111289158B (en) | Flexible pressure sensor and flexible pressure sensing array | |
| CN109708785B (en) | Flexible capacitive touch sensor, electronic skin, wearable device and method | |
| WO2012050938A2 (en) | Wearable tactile keypad with stretchable artificial skin | |
| TW201329815A (en) | Force sensitive interface device and methods of using same | |
| CN104995587A (en) | Pressure measurement structure and touch control device | |
| CN101201277A (en) | Array type ultra-thin submissive force sensor and preparation method thereof | |
| CN104406627A (en) | Wearable flexible touch sensor of artificial hand and touch detection system thereof | |
| CN103323152A (en) | Bionic skin three-dimensional force touch perception device and measuring method thereof | |
| Wang et al. | A flexible tactile sensor with dual-interlocked structure for broad range force sensing and gaming applications | |
| US11248967B2 (en) | Dual-use strain sensor to detect environmental information | |
| CN201993187U (en) | Multifunctional flexible tactile sensor | |
| CN111473904A (en) | Integrated flexible three-dimensional force touch sensor and manufacturing method thereof | |
| CN109141696A (en) | A kind of flexible touch sensation sensor and its signal processing system based on piezoelectric membrane | |
| CN107368222B (en) | Array substrate, touch display panel and display device thereof | |
| CN113386158A (en) | Full-printing bionic super-sensing flexible robot skin | |
| CN204154423U (en) | A kind of flexible tactile and slip sense composite sensing array based on pressure-sensitive conductive rubber | |
| CN115523943A (en) | Flexible multi-modal touch sensing system based on non-grid sensing plane | |
| Xu et al. | The design of a novel flexible tactile sensor based on pressure-conductive rubber | |
| CN115479704A (en) | Capacitive pressure sensor | |
| CN114689220A (en) | Force sensitive array sensor and array type multi-point force measuring system | |
| CN112362201A (en) | Positive octagonal frustum piezoresistive flexible touch sensor array and working method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |