CN113639767A - Intelligent electronic target identification method for skin - Google Patents
Intelligent electronic target identification method for skin Download PDFInfo
- Publication number
- CN113639767A CN113639767A CN202111185107.4A CN202111185107A CN113639767A CN 113639767 A CN113639767 A CN 113639767A CN 202111185107 A CN202111185107 A CN 202111185107A CN 113639767 A CN113639767 A CN 113639767A
- Authority
- CN
- China
- Prior art keywords
- intelligent electronic
- electronic skin
- value
- test
- standard
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012360 testing method Methods 0.000 claims abstract description 69
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 239000010410 layer Substances 0.000 claims description 68
- 239000002184 metal Substances 0.000 claims description 33
- 239000000758 substrate Substances 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 239000002082 metal nanoparticle Substances 0.000 claims description 8
- 239000003989 dielectric material Substances 0.000 claims description 4
- 239000002346 layers by function Substances 0.000 claims description 3
- 239000003990 capacitor Substances 0.000 description 26
- 230000000638 stimulation Effects 0.000 description 20
- 238000004364 calculation method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006386 memory function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000012782 phase change material Substances 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- 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
- G01D5/14—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 influencing the magnitude of a current or voltage
-
- 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
- G01D5/14—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 influencing the magnitude of a current or voltage
- G01D5/24—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 influencing the magnitude of a current or voltage by varying capacitance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/14—Measuring force or stress, in general by measuring variations in capacitance or inductance of electrical elements, e.g. by measuring variations of frequency of electrical oscillators
- G01L1/142—Measuring force or stress, in general by measuring variations in capacitance or inductance of electrical elements, e.g. by measuring variations of frequency of electrical oscillators using capacitors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/16—Measuring force or stress, in general using properties of piezoelectric devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/20—Measuring force or stress, in general by measuring variations in ohmic resistance of solid materials or of electrically-conductive fluids; by making use of electrokinetic cells, i.e. liquid-containing cells wherein an electrical potential is produced or varied upon the application of stress
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/02—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with propagation of electric current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- Remote Sensing (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Power Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a method for intelligently identifying a target by electronic skin, which comprises the following steps: configuring adjustable constants of all sensitive elements in the intelligent electronic skin when an object to be identified is in a detection area on the intelligent electronic skin so as to obtain a standard value of the object to be identified, wherein the adjustable constants at least comprise one of dielectric constant, resistivity, conductivity and deformation coefficient, and the standard value at least comprises one of standard capacitance value, standard resistance value and standard current value; when an object is matched with the intelligent electronic skin, a test value detected by the intelligent electronic skin is obtained, wherein the test value comprises a test capacitance value, a test resistance value or a test current value; and determining whether the object is the target to be recognized and determining the position corresponding to the target to be recognized according to the comparison result of the standard value and the test value.
Description
Technical Field
The invention relates to electronic skin, in particular to a method for identifying a target by intelligent electronic skin.
Background
With the development of artificial intelligence technology, the demand for intelligent hardware is increasingly strong. The pressure sensor array constitutes an electronic skin, which is a way for the manipulator to obtain a tactile sensation. The e-skin cannot directly recognize the shape of the contacted object. At the present stage, the manipulator identifies the shape of the contacted object, pressure data of the pressure sensor array is required to be acquired, then the pressure data is transmitted to a processor and/or a memory connected with the electronic skin, the pressure data is calculated and compared with the stored object shape data one by one, and therefore the shape of the object is determined, wherein the electronic skin is only used as a sensing device and cannot participate in calculation, and the intelligent degree is low.
Therefore, there is a need to provide an intelligent electronic skin identification target method to solve the above problems.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention aims to provide an intelligent electronic skin target identification method, which can improve the identification speed of electronic skin and enable the electronic skin to have certain calculation capacity.
To achieve the above object, an embodiment of the present invention provides a method for intelligent electronic skin identification target, including: configuring adjustable constants of all sensitive elements in the intelligent electronic skin when an object to be identified is in a detection area on the intelligent electronic skin so as to obtain a standard value of the object to be identified, wherein the adjustable constants at least comprise one of dielectric constant, resistivity, conductivity and deformation coefficient, and the standard value at least comprises one of standard capacitance value, standard resistance value and standard current value; when the object is matched with the intelligent electronic skin, a test value detected by the intelligent electronic skin is obtained, wherein the test value comprises a standard capacitance value, a standard resistance value or a standard current value; and determining whether the object is a target to be recognized and determining the position corresponding to the target to be recognized according to the comparison result of the standard value and the test value.
In one or more embodiments of the invention, the step of configuring the adjustable constant of each sensitive element in the intelligent electronic skin when the target to be identified is in the detection area on the intelligent electronic skin comprises the following steps: when the target to be recognized is in the detection area on the intelligent electronic skin, the adjustable constant of each sensitive element in the intelligent electronic skin is calculated by using the algorithm of the artificial neural network.
The invention also provides a method for intelligently identifying the target by the electronic skin, which comprises the following steps: configuring adjustable constants of all sensitive elements in the intelligent electronic skin when a plurality of targets to be identified are in a detection area on the intelligent electronic skin so as to obtain a plurality of standard values corresponding to the plurality of targets to be identified, wherein the adjustable constants at least comprise one of dielectric constant, resistivity, conductivity and deformation coefficient, and the standard values at least comprise one of standard capacitance value, standard resistance value and standard current value; when one or more objects are matched with the intelligent electronic skin, the intelligent electronic skin detects a test value, wherein the test value comprises a test capacitance value, a test resistance value or a test current value; and determining the target to be recognized and the corresponding position corresponding to the object according to the comparison result of the plurality of standard values and the plurality of test values.
In one or more embodiments of the invention, the step of configuring the adjustable constant of each sensitive element in the intelligent electronic skin when a plurality of objects to be identified are in the detection area on the intelligent electronic skin comprises the following steps: when a plurality of targets to be identified are in a detection area on the intelligent electronic skin, calculating the adjustable constant of each sensitive element in the intelligent electronic skin by using an algorithm of an artificial neural network.
In one or more embodiments of the present invention, the intelligent electronic skin includes: the top electrode layer comprises a plurality of top electrode metal strips which are arranged at intervals; the bottom electrode layer is arranged below the top electrode layer and comprises a plurality of bottom electrode metal strips arranged at intervals; and the dielectric layer is arranged between the top electrode metal strip and the bottom electrode metal strip, and the dielectric constant of the dielectric layer is nonvolatile and adjustable.
The top electrode metal strip, the dielectric layer and the bottom electrode metal strip form a plurality of memory containers distributed in an array.
In one or more embodiments of the invention, the bottom electrode layer is further provided with a substrate layer at a side remote from the top electrode layer.
In one or more embodiments of the invention, the substrate layer is a flexible substrate.
In one or more embodiments of the present invention, a projection of the top electrode metal strip on the substrate is perpendicular to a projection of the bottom electrode metal strip on the substrate.
In one or more embodiments of the invention, the dielectric layer is made of a flexible dielectric material.
In one or more embodiments of the present invention, the intelligent electronic skin includes: the first electrode layer comprises a plurality of first electrode strips which are arranged at intervals; the second electrode layer comprises a plurality of second electrode strips which are arranged at intervals; and the functional part is arranged between the first electrode strip and the second electrode strip and comprises an insulating layer, metal nano particles filled in the insulating layer and a phase change layer coated on the surfaces of the metal nano particles.
A plurality of memristors distributed in an array form among the first electrode strips, the second electrode strips and the functional layer, and the resistivity of each memristor is nonvolatile and adjustable.
Compared with the prior art, according to the method for identifying the target by the intelligent electronic skin, which is disclosed by the embodiment of the invention, the standard value corresponding to the target to be identified is obtained by configuring the adjustable constant of each sensitive element in the intelligent electronic skin, then the test value obtained by the detection of the intelligent electronic skin is obtained when the object is matched with the intelligent electronic skin, and the standard value is compared with the test value on the equipment (which can be a memory and/or a processor) connected with the intelligent electronic skin, so that the effect of identifying the target can be achieved. Therefore, the intelligent electronic skin has certain calculation capacity, the calculation pressure of equipment (which can be a memory and/or a processor) connected with the intelligent electronic skin is reduced, and the method has the advantages of reducing the power consumption of the electronic skin, improving the identification speed of the electronic skin and enabling the electronic skin to have certain calculation and memory capacity.
Drawings
FIG. 1 is a schematic diagram of a capacitive structure in smart electronic skin according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an intelligent electronic skin site according to an embodiment of the present invention;
FIG. 3 is a graph of dielectric constant versus number of stimuli in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of the distribution of capacitive structures in intelligent electronic skin, according to an embodiment of the invention;
FIG. 5 is a schematic diagram of the distribution of capacitive structures in smart electronic skin according to another embodiment of the present invention;
FIG. 6 is a schematic diagram of the distribution of capacitive structures in smart electronic skin according to yet another embodiment of the present invention;
fig. 7 is a schematic diagram of the distribution of capacitance structures in smart electronic skin according to yet another embodiment of the present invention.
Description of the main reference numerals:
1. a top electrode layer; 11. a top electrode metal strip; 2. a bottom electrode layer; 21. a bottom electrode metal strip; 3. a dielectric layer; 4. a substrate layer; 5. and (3) a capacitor structure.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
As shown in fig. 1, the method for intelligent electronic skin identification of a target according to a preferred embodiment of the present invention comprises:
s1, configuring the adjustable constant of each sensitive element in the intelligent electronic skin when the target to be recognized is in the detection area on the intelligent electronic skin, so as to obtain the standard value of the target to be recognized.
The adjustable constant can be one of dielectric constant, resistivity, conductivity or deformation coefficient, and the standard value packet can be a standard capacitance value, a standard resistance value and a standard current value corresponding to the adjustable constant.
In a specific embodiment, the corresponding value of the adjustable constant of each sensitive element in the intelligent electronic skin can be calculated through an algorithm of the artificial neural network, and then the adjustable constant of each sensitive element is adjusted to reach the calculated value. Wherein, different sensitive elements and adjusting modes are different. For example, when the sensitive element is a memristor or, the standard value corresponding to the memristor may be a dielectric constant, and the adjustable constant corresponding to the memristor may be a resistivity or a conductivity. The adjustable constant can be changed by stimulation, and the stimulation can be thermal stimulation, optical stimulation or electric stimulation, etc.
In step S1, obtaining a standard value of the target to be recognized, namely a corresponding standard value when the target to be recognized contacts the detection area on the intelligent electronic skin; and records the normalized values to a memory and/or processor connected to the intelligent electronic skin. This process can be understood as the process of intelligent e-skin learning, so in order for an intelligent e-skin to identify a target, the intelligent e-skin must first "learn" over the target.
And S2, obtaining a test value obtained by the detection of the intelligent electronic skin when the object is matched with the intelligent electronic skin, wherein the test value comprises a test capacitance value, a test resistance value or a test current value.
In the above process, when the object, i.e. the target needing intelligent electronic skin identification, is matched with the intelligent electronic skin, the intelligent electronic skin outputs a test value outwards (outwards can be understood as being towards a memory and/or a processor connected with the intelligent electronic skin).
And S3, determining whether the object is the target to be recognized and determining the position corresponding to the target to be recognized according to the comparison result of the standard value and the test value.
In the above process, through the comparison result of the standard value and the test value in the memory and/or the processor, it can be determined whether the object is the object to be identified, and if the object is the object to be identified, the contact position of the object and the intelligent electronic skin can be determined.
As shown in fig. 2, an embodiment of the present invention further provides a method for intelligent electronic skin identification of a target, including:
s1, configuring adjustable constants of all sensitive elements in the intelligent electronic skin when a plurality of targets to be recognized are in the detection area on the intelligent electronic skin, and obtaining a plurality of standard values corresponding to the targets to be recognized.
The adjustable constant can be one of dielectric constant, resistivity, conductivity or deformation coefficient, and the standard value packet can be a standard capacitance value, a standard resistance value and a standard current value corresponding to the adjustable constant.
In a specific embodiment, the corresponding value of the adjustable constant of each sensitive element in the intelligent electronic skin can be calculated through an algorithm of the artificial neural network, and then the adjustable constant of each sensitive element is adjusted to reach the calculated value. Wherein, different sensitive elements and adjusting modes are different. For example, when the sensitive element is a memristor or, the standard value corresponding to the memristor may be a dielectric constant, and the adjustable constant corresponding to the memristor may be a resistivity or a conductivity. The adjustable constant can be changed by stimulation, and the stimulation can be thermal stimulation, optical stimulation or electric stimulation, etc.
And S2, obtaining a test value detected by the intelligent electronic skin when one or more objects are matched with the intelligent electronic skin, wherein the test value comprises a test capacitance value, a test resistance value or a test current value.
In the above process, when the object, i.e. the target needing intelligent electronic skin identification, is matched with the intelligent electronic skin, the intelligent electronic skin outputs a test value outwards (outwards can be understood as being towards a memory and/or a processor connected with the intelligent electronic skin).
And S3, determining the target to be recognized and the corresponding position corresponding to the object according to the comparison result of the plurality of standard values and the test values.
In the above process, through the comparison result of the standard value and the test value in the memory and/or the processor, it can be determined whether the object is the object to be identified, and if the object is the object to be identified, the contact position of the object and the intelligent electronic skin can be determined. Meanwhile, in the method, one object can be placed on the intelligent electronic skin at one time for identification, and a plurality of objects can also be placed on the intelligent electronic skin at one time for identification.
As shown in fig. 1 and 2, the intelligent electronic skin according to the preferred embodiment of the present invention comprises a top electrode layer 1, a bottom electrode layer 2, a dielectric layer 3 and a substrate layer 4. This embodiment is one of the possible solutions for intelligent electronic skins.
As shown in fig. 2, in one embodiment, the top electrode layer 1 may include a plurality of top electrode metal strips 11 disposed at intervals; the bottom electrode layer 2 is arranged below the top electrode layer 1, and the bottom electrode layer 2 comprises a plurality of bottom electrode metal strips 21 arranged at intervals; the dielectric layer 3 is arranged between the top electrode metal strip 11 and the bottom electrode metal strip 21, and the dielectric constant of the dielectric layer 3 is nonvolatile and adjustable.
In a specific embodiment, the dielectric layer 3 is made of a flexible dielectric material. The flexible dielectric material may provide the dielectric layer 3 with a certain flexibility.
In a specific embodiment, a substrate layer 4 is further disposed on a side of the bottom electrode layer 2 away from the top electrode layer 1, and the substrate layer 4 is a flexible substrate. The flexible substrate has the advantage of acting as the skin of the terminal, which may be irregular in shape, for example when the terminal is a robot, the surface of the robot is uneven, and the flexible substrate provides the substrate layer 4 with a certain flexibility, and can better adhere to the surface of the robot, acting as the "skin" of the robot.
As shown in fig. 2, in the above embodiment, a plurality of overlapping areas distributed in an array are formed in the projection direction of the plurality of top electrode metal strips 11 and the plurality of bottom electrode metal strips 21 on the substrate layer 4, and the dielectric layer 3 is disposed between the top electrode metal strips 11 and the bottom electrode metal strips 21 in each overlapping area, so as to form a capacitor structure 5 as shown in fig. 1.
Wherein the projection of the top electrode metal strip 11 on the substrate is perpendicular to the projection of the bottom electrode metal strip 21 on the substrate layer 4. The metal strips 11 and 21 are arranged vertically to each other, so that the overlapping area of the top electrode metal strips 11 and the bottom electrode metal strips 21 is regular, and in general, the projection of the overlapping area on the substrate layer 4 is rectangular, which is convenient for adjusting the dielectric constant of the capacitor structure 5.
In the above embodiment, since the dielectric constant of the dielectric layer 3 is non-volatile and adjustable, the capacitor structure 5 can be regarded as a memcapacitor, which can be understood as a capacitor having a certain memory function. The dielectric constant of the memcapacitor can be changed by stimulation, as shown by a line represented by 3a in fig. 3, under the action of positive stimulation, the dielectric constant of the memcapacitor is increased along with the increase of stimulation times; as shown by the line 3b in fig. 3, the dielectric constant of the negative stimulation decreases as the stimulation frequency increases. The dielectric constant of the memcapacitor can be adjusted to a desired value by the stimulus, and after the stimulus disappears, the dielectric constant of the memcapacitor is kept at the desired value until the next stimulus comes.
In one embodiment, the stimulus may be an electrical stimulus, a thermal stimulus, an optical stimulus, or a magnetic stimulus.
By utilizing the principle of the memory capacitor, the dielectric constant of each capacitor structure 5 in the array-type plurality of capacitor structures 5 can be set to be the required dielectric constant, so that the capacitance value change generated when each object to be identified is placed on the intelligent electronic skin is different, and the capacitance value change generated when each object to be identified is placed on the intelligent electronic skin is input into a memory and/or a processor connected with the intelligent electronic skin;
how to determine the dielectric constant of each capacitor structure 5, the dielectric constant of each capacitor structure 5 to be achieved can be calculated through an algorithm of an artificial neural network according to the number and the shape of objects to be identified and the contact position of the intelligent electronic skin, and the dielectric constant of each capacitor structure 5 can be achieved through corresponding stimulation.
When a target object is in contact with the intelligent electronic skin, certain pressure is generated at the intelligent electronic skin in contact with the target object, the pressure changes the distance between the top electrode metal strip 11 and the bottom electrode metal strip 21 inside one or more capacitor structures 5 at the intelligent electronic skin in contact part, so that the total capacitance value of the intelligent electronic skin is changed, the capacitance value is transmitted to a memory and/or a processor connected with the intelligent electronic skin through an A/D converter, and the capacitance value can correspond to the capacitance value change quantity preset by the memory and/or the processor, so that the shape and the position of the object in contact with the intelligent electronic skin can be rapidly identified. Therefore, a large amount of calculation is not needed in the memory and/or the processor, and only simple corresponding calculation is needed, so that the speed of the identification process is increased, and the calculation amount and the energy consumption of the memory and/or the processor are reduced.
An embodiment of the present invention also provides an intelligent electronic skin, including: the first electrode layer comprises a plurality of first electrode strips which are arranged at intervals; the second electrode layer comprises a plurality of second electrode strips which are arranged at intervals; and the functional part is arranged between the first electrode strip and the second electrode strip and comprises an insulating layer, metal nano particles filled in the insulating layer and a phase change layer coated on the surfaces of the metal nano particles.
A plurality of memristors distributed in an array form among the first electrode strips, the second electrode strips and the functional layer, and the resistivity of each memristor is nonvolatile and adjustable.
In the above embodiments, the memristor may be understood as a resistor having a certain memory function. The resistivity of the memristor may be altered by a stimulus, which may be a thermal stimulus or other stimulus. The state of the phase change material in the phase change layer, i.e., the degree of crystalline and amorphous states, in the memristor may thereby be altered. In the crystalline state, the resistivity of the memristor is low, the change of the resistivity is large when pressure is applied, and the sensitivity is high; in an amorphous state, the resistivity of the memristor is high, the change of the resistivity is small when pressure is applied, and the sensitivity is low. When an object is in contact with the intelligent electronic skin, even if the distance between the first electrode layer and the second electrode layer is reduced, the metal nanoparticles located between the first electrode layer and the second electrode layer can be in contact with each other, namely, the metal nanoparticles apply pressure on the memristor, so that the resistivity of the memristor is changed, and the resistance can be changed.
The method for intelligent electronic skin identification target of the invention will be described in detail below in some scenarios with reference to different embodiments.
In the case of the example 1, the following examples are given,
as shown in fig. 4, the corresponding in fig. 4 is a detection area on the intelligent electronic skin, each grid in the figure is a capacitor structure 5 on the intelligent electronic skin, the intelligent electronic skin only needs to learn one kind of object to be identified (when the contact with the intelligent electronic skin is a square of 4 grids multiplied by 4 grids), and the identified position is fixed (the shaded area in the figure).
Firstly, calculating by using an algorithm of an artificial neural network, when an object to be identified is placed in a shadow area in fig. 4, the output standard capacitance value (the variation of the capacitance value) is 1, and when the object is placed at other positions, the output standard capacitance value is not equal to 1; in this case, the dielectric constant of the capacitor structure 5 corresponding to 16 lattices in the hatched portion in the figure should be ∈ 1, and the dielectric constant of the capacitor structure 5 corresponding to the remaining lattices should be ∈ 2. Then, the dielectric constants of the capacitor structures 5 corresponding to the 16 lattices in the shaded part in the figure are adjusted to epsilon 1 by means of thermal stimulation, and the dielectric constants of the capacitor structures 5 corresponding to the remaining lattices are adjusted to epsilon 2.
Then within the memory and/or processor connected to the intelligent electronic skin, a "1" = "square" is recorded. And then removing the target to be identified.
Then when putting different objects into the detection area in proper order, and can make every object's center coincide with the detection area as far as possible, intelligent electronic skin can obtain a plurality of test capacitance values (the variable quantity of capacitance value) in proper order to in proper order transmit a plurality of test capacitance values in the memory and/or the treater.
The memory and/or the processor can sequentially compare the plurality of test capacitance values with the previously recorded standard capacitance values, if the plurality of test capacitance values are equal, the plurality of test capacitance values are displayed as squares, and if the plurality of test capacitance values are not equal, the target to be identified or the non-squares can be prompted. The object and the target to be recognized are the same, but the variation of the capacitance value output by the intelligent electronic skin is different due to the fact that the position of the object placed in the detection area is different from the position of the target to be recognized in the detection area, and therefore the target to be recognized cannot be recognized.
The detection area of the present embodiment may be enlarged or reduced depending on the detection object.
Therefore, the embodiment can recognize the contact shape of the specified object and the intelligent electronic skin at the specified position on the intelligent electronic skin, and recognize whether the object is the target to be recognized which is learned by the intelligent electronic skin at the specified position of the intelligent electronic skin.
In the case of the example 2, the following examples are given,
as shown in fig. 5, fig. 5 corresponds to a detection area on the intelligent electronic skin, each cell in the figure is a capacitor structure 5 on the intelligent electronic skin, and the intelligent electronic skin only needs to learn one kind of object to be identified (when the contact with the intelligent electronic skin is a square of 2 cells by 2 cells). Wherein the content of the first and second substances,
first, when the target to be recognized is placed at any position in the detection area in the graph, which is calculated by using an algorithm of an artificial neural network (since 12 grids are provided in total and the contact position of the target to be recognized and the intelligent electronic skin is a square of 2 grids multiplied by 2 grids, only 6 different placement positions are provided) and the output standard capacitance value (the variation of the capacitance value) is 1, 2, 3, 4, 5 or 6, the dielectric constant value of the capacitor structure 5 corresponding to 12 grids in the graph should be respectively epsilon 1, epsilon 2, epsilon 3 · epsilon 12. Then, the dielectric constant values of the capacitor structures 5 corresponding to the 12 lattices are sequentially adjusted to epsilon 1, epsilon 2, epsilon 3-epsilon 12 by adopting a thermal stimulation mode.
Then, in a memory and/or a processor connected to the intelligent electronic skin, "1" = "square is recorded, and placed in a first position," 2 "=" square, and placed in a second position, ", ·," 6 "=" square, and placed in a sixth position "; and then removing the target to be identified.
Then when putting into the detection area with different objects in proper order, and every object can place arbitrary position in the detection area at random, intelligent electronic skin can obtain a plurality of test capacitance values (the change of capacitance value) in proper order to in passing a plurality of test capacitance values in proper order and transmitting memory and/or treater.
The memory and/or the processor can compare the plurality of test capacitance values with the previously recorded standard capacitance values in sequence, if the plurality of test capacitance values are equal, the plurality of test capacitance values are displayed as squares and placed at the Xth position, and if the plurality of test capacitance values are not equal, the target to be identified or the non-squares can be prompted.
The detection area of the present embodiment may be enlarged or reduced depending on the detection object.
The embodiment can identify the contact shape and the corresponding position of the specified object with the intelligent electronic skin in any area of the intelligent electronic skin. And whether the object is the target to be recognized and the corresponding position thereof which are learned by the intelligent electronic skin can be detected.
In the case of the example 3, the following examples are given,
as shown in fig. 6, fig. 6 corresponds to a detection area on the intelligent electronic skin, each cell in the figure is a capacitor structure 5 on the intelligent electronic skin, and the intelligent electronic skin only needs to learn four objects to be identified (the contact position with the intelligent electronic skin is in a shape of triangle (occupying 9 cells), circle (occupying 12 cells), square (occupying 4 cells) or rectangle (occupying 6 cells)). In fig. 6, a diagram of the number of occupied lattices (i.e., the shape of the border + the number of lattices in the border) for each target to be identified when placed on the intelligent electronic skin is shown.
Firstly, calculating by using an algorithm of an artificial neural network, and outputting standard capacitance values of a1, a2, · -an when each target to be identified is placed at any position in a detection area in a graph, namely when the shape of a contact part with the intelligent electronic skin is a triangle; when the contact part of the intelligent electronic skin is circular, the output standard capacitance values are b1, b2, · · bn; when the contact part with the intelligent electronic skin is square, the output standard capacitance values are c1, c2, · · cn; when the contact part with the intelligent electronic skin is rectangular, the output standard capacitance values are d1, d2,. cndot.. dn, and the dielectric constant values of the capacitor structure 5 corresponding to 64 lattices in the figure are respectively epsilon 1, epsilon 2 and epsilon 3. cndot.. epsilon.64. Then, the dielectric constant values of the capacitor structures 5 corresponding to the 64 lattices are sequentially adjusted to epsilon 1, epsilon 2, epsilon 3-epsilon 64 by adopting a thermal stimulation mode.
Then, within a memory and/or processor connected to the intelligent electronic skin, "a 1" = "triangle, and placed in a first location," "a 2" = "square, and placed in a second location,", · · ·, "an" = "square, and placed in an nth location"; and then removing the target to be recognized, replacing the target to be recognized, and recording the content according to the above mode until all records are finished.
Then when putting into the detection area with different objects in proper order, and every object can place arbitrary position in the detection area at random, intelligent electronic skin can obtain a plurality of test capacitance values (the change of capacitance value) in proper order to in passing a plurality of test capacitance values in proper order and transmitting memory and/or treater.
The memory and/or the processor can compare the plurality of test capacitance values with the previously recorded standard capacitance values in sequence, if the plurality of test capacitance values are equal, the corresponding graph is displayed and placed at the Xth position, and if the plurality of test capacitance values are not equal, a non-target to be identified or a non-square shape can be prompted.
The detection area of the present embodiment may be enlarged or reduced depending on the detection object.
The embodiment can identify the contact shape and the corresponding position of the specified object with the intelligent electronic skin in any area of the intelligent electronic skin. And whether the object is one of a plurality of objects to be identified which are learned by the intelligent electronic skin and the corresponding position of the object can be detected.
In the case of the example 4, the following examples are given,
as shown in fig. 7, fig. 7 corresponds to a detection area on the intelligent electronic skin, each cell in the figure is a capacitor structure 5 on the intelligent electronic skin, and the intelligent electronic skin only needs to learn three objects to be identified (the contact position with the intelligent electronic skin is in a shape of a circle (occupying 12 cells), a square (occupying 4 cells) or a rectangle (occupying 6 cells)). Fig. 7 is a situation when three targets to be identified are placed together on the intelligent electronic skin, and each target to be identified occupies the number of lattices (namely the number of the lattices in the shape frame and the lattices in the shape frame).
Firstly, calculating by using an algorithm of an artificial neural network, and outputting standard capacitance values of a1, a2, a.cndot.an when each target to be recognized is placed at any position in a detection area in a graph, namely when the position in contact with the intelligent electronic skin is rectangular; when the contact part of the intelligent electronic skin is circular, the output standard capacitance values are b1, b2, · · bn; when the contact part with the intelligent electronic skin is square, the output standard capacitance values are c1, c2, · · cn; and when every two objects to be identified are simultaneously placed at any position in the detection area in the graph (placed without overlapping), namely the contact part with the intelligent electronic skin is rectangular or square, the output standard capacitance values are d1, d2, · · dn; namely, when the contact part with the intelligent electronic skin is rectangular or circular, the output standard capacitance values are e1, e2, · · e n; namely, when the contact part with the intelligent electronic skin is in a circular or square shape, the output standard capacitance values are f1, f2, · · fn; and when every three targets to be identified are simultaneously placed at any position in the detection area in the graph (placed without overlapping), namely the shape of the contact part with the intelligent electronic skin is rectangular, circular or square, the output standard capacitance values are g1, g2, · · gn; the values of the dielectric constants of the capacitor structures 5 corresponding to 64 cells in the figure are ε 1, ε 2, ε 3 · ε 64, respectively. Then, the dielectric constant values of the capacitor structures 5 corresponding to the 64 lattices are sequentially adjusted to epsilon 1, epsilon 2, epsilon 3-epsilon 64 by adopting a thermal stimulation mode.
Then, in a memory and/or a processor connected to the intelligent electronic skin, it is recorded that "a 1" = "triangle and placed in the first position", "a 2" = "square and placed in the second position",. · · ·, "an" = "square and placed in the nth position" when only one identification object is placed; and then removing the target to be recognized, replacing the target to be recognized, and recording the content according to the above mode until all records are finished.
Record that only two recognition objects are placed, "d 1" = "square, and placed at a first location; and a rectangle, and placed in a first position "," d2 "=" square, and placed in a second position; and a rectangle, and placed at the second position ", ·" dn "=" square, and placed at the nth position; and rectangular and placed in the nth position ". (wherein the first positions for the different shapes are different from each other); and then removing the target to be recognized, replacing the target to be recognized, and recording the content according to the above mode until all records are finished.
Recording that "g 1" = "square when only three recognition objects are placed, and placing at a first position; rectangular and placed at a first position; circular and placed in a first position "," g2 "=" square and placed in a second position; rectangular and placed in a second position; circular and placed in the first position ", · ·," gn "=" square and placed in the nth position; rectangular and placed at the Nth position; circular and placed in the first position ". (wherein the first positions for the different shapes are different from each other); and then removing the target to be identified.
Then when putting different objects into the detection area (can put into one or more objects at a time), and every object can place arbitrary position in the detection area at random, intelligent electronic skin can obtain a plurality of test capacitance values (the change of capacitance value) in proper order to in proper order with a plurality of test capacitance values transfer in memory and/or treater.
The memory and/or the processor will compare the plurality of test capacitance values with the previously recorded standard capacitance values in sequence, if the plurality of test capacitance values are equal, the corresponding pattern is displayed and placed at the xth position (the result may be one pattern and its position, or a plurality of patterns and their positions), and if the plurality of test capacitance values are not equal, the target not to be recognized or the non-square shape is prompted.
The detection area of the present embodiment may be enlarged or reduced depending on the detection object.
The embodiment can identify the contact shapes and the corresponding positions of a plurality of specified objects with the intelligent electronic skin in any area of the intelligent electronic skin. And detecting whether the object is one or more of a plurality of objects to be identified which are learned by the intelligent electronic skin and the corresponding positions of the objects.
In summary, the method for identifying the target by the intelligent electronic skin has the beneficial effects that:
the method comprises the steps of obtaining a standard value corresponding to a target to be identified by configuring adjustable constants of all sensitive elements in the intelligent electronic skin, obtaining a test value obtained by detection of the intelligent electronic skin when a subject is matched with the intelligent electronic skin, and comparing the standard value with the test value on equipment (which can be a memory and/or a processor) connected with the intelligent electronic skin, so that the target identification effect can be achieved. Therefore, the intelligent electronic skin has certain calculation capacity, the calculation pressure of equipment (which can be a memory and/or a processor) connected with the intelligent electronic skin is reduced, and the method has the advantages of reducing the power consumption of the electronic skin, improving the identification speed of the electronic skin and enabling the electronic skin to have certain calculation and memory capacity.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (10)
1. A method of intelligent electronic skin identification of a target, comprising: configuring adjustable constants of all sensitive elements in the intelligent electronic skin when an object to be identified is in a detection area on the intelligent electronic skin so as to obtain a standard value of the object to be identified, wherein the adjustable constants at least comprise one of dielectric constant, resistivity, conductivity and deformation coefficient, and the standard value at least comprises one of standard capacitance value, standard resistance value and standard current value;
when an object is matched with the intelligent electronic skin, a test value detected by the intelligent electronic skin is obtained, wherein the test value comprises a test capacitance value, a test resistance value or a test current value; and
and determining whether the object is a target to be recognized and determining the position corresponding to the target to be recognized according to the comparison result of the standard value and the test value.
2. The method of intelligent electronic skin identification targets according to claim 1, wherein said step of configuring tunable constants of sensitive elements in intelligent electronic skin for detection of areas of the target to be identified on the intelligent electronic skin comprises: when the target to be recognized is in the detection area on the intelligent electronic skin, the adjustable constant of each sensitive element in the intelligent electronic skin is calculated by using the algorithm of the artificial neural network.
3. A method of intelligent electronic skin identification of a target, comprising: configuring adjustable constants of all sensitive elements in the intelligent electronic skin when a plurality of targets to be identified are in a detection area on the intelligent electronic skin so as to obtain a plurality of standard values corresponding to the plurality of targets to be identified, wherein the adjustable constants at least comprise one of dielectric constant, resistivity, conductivity and deformation coefficient, and the standard values at least comprise one of standard capacitance value, standard resistance value and standard current value;
when one or more objects are matched with the intelligent electronic skin, the intelligent electronic skin detects a test value, wherein the test value comprises a test capacitance value, a test resistance value or a test current value; and
and determining the target to be recognized and the corresponding position corresponding to the object according to the comparison result of the plurality of standard values and the plurality of test values.
4. The method of intelligent electronic skin identification targets according to claim 3, wherein said step of configuring tunable constants for sensitive elements in intelligent electronic skin for a plurality of targets to be identified in a detection area on intelligent electronic skin comprises: when a plurality of targets to be identified are in a detection area on the intelligent electronic skin, calculating the adjustable constant of each sensitive element in the intelligent electronic skin by using an algorithm of an artificial neural network.
5. The intelligent electronic skin target identification method of any one of claims 1 to 4, wherein the intelligent electronic skin comprises:
the top electrode layer comprises a plurality of top electrode metal strips which are arranged at intervals;
the bottom electrode layer is arranged below the top electrode layer and comprises a plurality of bottom electrode metal strips arranged at intervals; and
the dielectric layer is arranged between the top electrode metal strip and the bottom electrode metal strip, and the dielectric constant of the dielectric layer is nonvolatile and adjustable;
the top electrode metal strip, the dielectric layer and the bottom electrode metal strip form a plurality of memory containers distributed in an array.
6. An intelligent electronic skin identification target method according to claim 5, wherein said bottom electrode layer is further provided with a substrate layer at a side remote from the top electrode layer.
7. The method of intelligent electronic skin identification targets of claim 6 wherein said substrate layer is a flexible substrate.
8. The method of intelligent electronic skin identification targets of claim 7 wherein the projections of the top electrode metal strips on the substrate are orthogonal to the projections of the bottom electrode metal strips on the substrate.
9. The method of intelligent electronic skin identification goals of claim 5, wherein said dielectric layer is made of a flexible dielectric material.
10. The intelligent electronic skin target identification method of any one of claims 1 to 4, wherein the intelligent electronic skin comprises:
the first electrode layer comprises a plurality of first electrode strips which are arranged at intervals;
the second electrode layer comprises a plurality of second electrode strips which are arranged at intervals; and
the functional part is arranged between the first electrode strip and the second electrode strip and comprises an insulating layer, metal nano particles filled in the insulating layer and a phase change layer coated on the surfaces of the metal nano particles;
a plurality of memristors distributed in an array form among the first electrode strips, the second electrode strips and the functional layer, and the resistivity of each memristor is nonvolatile and adjustable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111185107.4A CN113639767B (en) | 2021-10-12 | 2021-10-12 | Intelligent electronic target identification method for skin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111185107.4A CN113639767B (en) | 2021-10-12 | 2021-10-12 | Intelligent electronic target identification method for skin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113639767A true CN113639767A (en) | 2021-11-12 |
| CN113639767B CN113639767B (en) | 2022-02-08 |
Family
ID=78426514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111185107.4A Active CN113639767B (en) | 2021-10-12 | 2021-10-12 | Intelligent electronic target identification method for skin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113639767B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105606291A (en) * | 2016-01-21 | 2016-05-25 | 清华大学 | Thermal type pressure sensor and flexible electronic skin |
| CN106382997A (en) * | 2016-09-18 | 2017-02-08 | 北京科技大学 | Electronic skin of friction electrostatic induction type |
| CN109163824A (en) * | 2018-10-10 | 2019-01-08 | 北京理工大学 | A kind of flexible electronic skin with tactile and close feel bimodulus perceptional function |
| CN110320241A (en) * | 2019-07-28 | 2019-10-11 | 北京怡成生物电子技术股份有限公司 | The recognition methods of target strip and system |
| CN211855191U (en) * | 2019-08-02 | 2020-11-03 | 深圳市越疆科技有限公司 | Non-contact electronic skin sensing circuit and device |
-
2021
- 2021-10-12 CN CN202111185107.4A patent/CN113639767B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105606291A (en) * | 2016-01-21 | 2016-05-25 | 清华大学 | Thermal type pressure sensor and flexible electronic skin |
| CN106382997A (en) * | 2016-09-18 | 2017-02-08 | 北京科技大学 | Electronic skin of friction electrostatic induction type |
| CN109163824A (en) * | 2018-10-10 | 2019-01-08 | 北京理工大学 | A kind of flexible electronic skin with tactile and close feel bimodulus perceptional function |
| CN110320241A (en) * | 2019-07-28 | 2019-10-11 | 北京怡成生物电子技术股份有限公司 | The recognition methods of target strip and system |
| CN211855191U (en) * | 2019-08-02 | 2020-11-03 | 深圳市越疆科技有限公司 | Non-contact electronic skin sensing circuit and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113639767B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0457398B1 (en) | Fingerprint sensing | |
| Lee et al. | Artificially intelligent tactile ferroelectric skin | |
| US5973623A (en) | Solid state capacitive switch | |
| TWI390452B (en) | Fingerprint detection device and method and associated touch control device with fingerprint detection | |
| JP2000514227A (en) | Fingerprint sensing device and system incorporating the same | |
| US10955301B2 (en) | Two-dimensional center of pressure sensor systems, devices, and methods | |
| EP2819065B1 (en) | Powerless time reference | |
| WO2009067293A1 (en) | Pointing and data entry input device | |
| CN104813260A (en) | Printed piezoelectric pressure sensing foil | |
| Pincella et al. | Electrical properties of an organic memristive system | |
| TW201523413A (en) | Control-point sensing panel and design method of control-point sensing panel | |
| US20190384451A1 (en) | Position sensor, position sensing method, and associated state-switching method | |
| CN113639767B (en) | Intelligent electronic target identification method for skin | |
| CN111982379B (en) | Continuous elastic touch sensor and detection method thereof | |
| US8754869B2 (en) | Surface capacitance with area gestures | |
| US20190272406A1 (en) | Fingerprint sensing circuit, electronic device and method for processing fingerprint image | |
| CN110346837A (en) | A kind of flexible capacitive proximity sensor and method for sensing based on capacitor fringing field effect | |
| CN108709585B (en) | Artificial skin and method for detecting pressure, temperature and humidity and adjusting temperature of artificial skin | |
| CN107256106B (en) | Array substrate, liquid crystal display panel, touch display device and touch driving method | |
| CN111337152B (en) | Electronic skin and electronic equipment | |
| Hoffstadt et al. | Modeling approach for the electrodynamics of multilayer de stack-transducers | |
| WO2018145255A1 (en) | Smart terminal, capacitive fingerprint sensor, and sensing module thereof | |
| CN111985633A (en) | Method and circuit for simulating artificial perception neuron | |
| Abbey et al. | Emulating homoeostatic effects with metal-oxide memristors T-dependence | |
| EP2404229A1 (en) | Surface capacitance with area gestures |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |