CN112710415A - High-precision planar piezoresistive sensor system and application method thereof - Google Patents
High-precision planar piezoresistive sensor system and application method thereof Download PDFInfo
- Publication number
- CN112710415A CN112710415A CN202011386307.1A CN202011386307A CN112710415A CN 112710415 A CN112710415 A CN 112710415A CN 202011386307 A CN202011386307 A CN 202011386307A CN 112710415 A CN112710415 A CN 112710415A
- Authority
- CN
- China
- Prior art keywords
- piezoresistive sensor
- planar
- electrodes
- planar piezoresistive
- pressure
- 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
- 238000000034 method Methods 0.000 title claims abstract description 14
- 230000010365 information processing Effects 0.000 claims abstract description 19
- 238000005259 measurement Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 239000011540 sensing material Substances 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 7
- 238000003825 pressing Methods 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 239000000463 material Substances 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
Images
Classifications
-
- 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
- G01L1/18—Measuring force or stress, in general using properties of piezo-resistive materials, i.e. materials of which the ohmic resistance varies according to changes in magnitude or direction of force applied to the material
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The invention provides a high-precision plane piezoresistive sensor system, which comprises a plane piezoresistive sensor, external electrodes arranged on the edge of the piezoresistive sensor, an information processing chip and/or an external computer, wherein pressure intensities with different sizes are applied to different positions of the plane piezoresistive sensor, the resistance between each group of electrodes changes correspondingly, the information processing chip and/or the external computer receive the pressure intensity action position and the pressure intensity of each measurement and the corresponding resistance between each group of electrodes, and train a neural network model for predicting the position and the size of the subsequent pressure intensity. The invention adopts the form of electrode edge arrangement, avoids the complex latticed electrode arrangement form of the traditional plane sensor, has no limitation on the shape of the sensor, has simple process, easy operation and low cost, establishes a training data set through multiple data acquisition for model training, reduces the number of required electrodes, improves the positioning precision and reduces the requirement on the sensitivity of sensitive materials.
Description
Technical Field
The invention relates to the technical field of sensors, in particular to a high-precision planar piezoresistive sensor system and a using method thereof.
Background
Piezoresistive sensors have gained more and more attention in the fields of electronic skin, wearable medical detection, motion monitoring and the like by virtue of their characteristics of low cost, high sensitivity and the like. Although conventional planar piezoresistive sensors have been designed with an array of electrodes to reduce the number of leads, their test accuracy is limited by the array grid density. Meanwhile, the array arrangement of the electrodes and the alignment between the multiple layers of electrodes require that the shape of the sensor is relatively regular and flat, the process difficulty is high, and the production efficiency is reduced. Many researches have been carried out to optimize the grid planar sensor by adopting artificial intelligence algorithms such as a neural network algorithm and the like, but the artificial intelligence algorithms are mainly used for pattern recognition and the like, are still limited by grid arrangement, and can not realize the detection of the pressure intensity at any position.
The number of leads can be further reduced by adopting a grid-free structure with electrodes arranged at the edge, and the reconstruction of the pressure intensity and the positioning can be realized by combining a bioelectrical impedance tomography (EIT) algorithm, but the algorithm has high requirements on hardware processing performance and a manual debugging process. In addition, the algorithm is still limited by the shape, the measuring range and the number of electrodes of the sensor, the system is difficult to design, the setting and debugging are complicated, and the cost is high.
Disclosure of Invention
The invention aims to provide a high-precision planar piezoresistive sensor system and a using method thereof.
The technical solution for realizing the purpose of the invention is as follows: a high-precision planar piezoresistive sensor system comprises a planar piezoresistive sensor, external electrodes arranged on the edge of the piezoresistive sensor, an information processing chip and/or an external computer, wherein pressure intensities with different sizes are applied to different positions of the planar piezoresistive sensor, the resistance size between each group of electrodes can be changed correspondingly, the information processing chip and/or the external computer receive the pressure intensity action position and the pressure intensity of each measurement and the corresponding resistance between each group of electrodes, a test data set is constructed, and a neural network model is trained for predicting the position and the size of the subsequent pressure intensity.
Further, the planar piezoresistive sensor is a rigid planar piezoresistive sensor or a flexible planar piezoresistive sensor.
Further, the shape of the planar piezoresistive sensor is any regular or irregular shape.
Furthermore, the sensing material of the planar piezoresistive sensor is a uniform sensing material or a non-uniform sensing material.
Furthermore, the external electrodes do not form a staggered grid dividing structure, but are distributed at the edge of the planar piezoresistive sensor. The specific connection mode can be embedded inside the sensing material edge part of the planar piezoresistive sensor, and can also be directly connected with the surface of the sensing material edge part.
Furthermore, the external electrode is embedded inside the edge of the sensing material of the planar piezoresistive sensor, or is directly connected to the outer side of the edge of the sensing material of the planar piezoresistive sensor.
The use method of the high-precision planar piezoresistive sensor comprises the following steps:
applying pressure intensities with different sizes at different positions of the planar piezoresistive sensor, recording the pressure intensity action position and the pressure intensity of each measurement and the corresponding resistance between each group of electrodes, and transmitting the pressure intensities to an information processing chip and/or an external computer;
and the information processing chip and/or the external computer receives the pressure action position and the pressure size of each measurement and the resistance between the corresponding groups of electrodes to construct a test data set, and trains a neural network model for predicting the position and the size of the subsequent pressure.
Further, the information processing chip and/or the external computer adopt a neural network which is a BP neural network.
Further, the external computer simultaneously trains and predicts a plurality of data sets.
Furthermore, the information processing chip and/or the external computer integrates a mode recognition function, including multi-point contact simultaneous recognition, gesture recognition, pressing mode recognition, contact point size and movement direction and speed recognition.
Compared with the prior art, the invention has the following remarkable advantages: 1) the invention adopts the form of electrode edge arrangement, avoids the complex latticed electrode arrangement form of the traditional plane sensor, has no limitation on the shape of the sensor, and has simple process, easy operation and low cost. 2) The invention adopts a neural network algorithm, establishes a training data set through multiple data acquisition and carries out model training, reduces the number of required electrodes, improves the positioning precision and reduces the requirement on the sensitivity of sensitive materials.
Drawings
FIG. 1 is a schematic diagram of a system for externally connecting an information processing chip according to the present invention.
FIG. 2 is a schematic diagram of the arrangement of external electrodes of the sensor according to the present invention.
FIG. 3 is a flow chart of a method for using the external information processing chip according to the present invention.
FIG. 4 is a diagram of a system configured to connect to a computer according to the present invention.
FIG. 5 is a graph of the accuracy of the predicted pressure magnitude and position for an input signal having an accuracy of 0.1 Ω in accordance with the present invention.
FIG. 6 is a graph comparing the predicted results of the homogeneous sample (a) and the heterogeneous sample (b) according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
As shown in fig. 1, a high-precision planar piezoresistive sensor system includes a planar piezoresistive sensor 1, an external electrode 2 arranged at the edge of the piezoresistive sensor 1, and an information processing chip 3.
As shown in fig. 2, the external electrodes 2 of the planar piezoresistive sensor 1 do not form a staggered grid structure, but are distributed at the edge of the planar piezoresistive sensor 1. The specific connection mode can be embedded inside the sensing material edge of the planar piezoresistive sensor 1, or can be directly connected with the outer side of the sensing material edge.
Further, the planar piezoresistive sensor 1 may be rigid or flexible. Meanwhile, the planar shape of the planar piezoresistive sensor 1 may be arbitrary, and the sensing material may not be uniform. The above factors do not affect the overall measurement accuracy of the system.
As shown in fig. 3, the high-precision planar piezoresistive sensor system is used by numbering electrodes 2, applying different pressures at different positions of the planar piezoresistive sensor 1, and changing the resistance between each group of electrodes accordingly. And recording the pressure acting position and the pressure intensity, and recording the resistance between the corresponding groups of electrodes. And changing the acting position and size of the pressure intensity, and performing multiple measurements to obtain a test data set. The test data set is input into the information processing chip 3 to train the neural network. The pressure intensity of any position and size can be predicted by utilizing the trained model, the high-precision pressure intensity and position sensing function is realized, the measurement precision is not limited by the position and the density of the electrode, and the measurement precision mainly depends on the quantity and the quality of the training sample.
As a specific implementation mode, the external computer 4 can be used for training the neural network model instead of or in cooperation with the information processing chip 3. Further preferably, the neural network model is a BP neural network model. As shown in fig. 4, the computer 4 may also complete data acquisition and training at the cloud end, and may process data set training and prediction of multiple sensing units at the same time.
Examples
To verify the validity of the inventive scheme, the following simulation experiment was performed.
A high-precision planar piezoresistive sensor system comprises a planar piezoresistive sensor 1, electrodes 2 arranged on the edge of the piezoresistive sensor 1 and an external computer 4. In this embodiment, the sensing material of the planar piezoresistive sensor 1 is conductive rubber, the electrodes 2 arranged at the edge have 4 groups, resistance changes under different positions and pressures of the 4 groups of electrodes and corresponding pressure action positions and size information are measured and recorded to obtain a data set, and the data set is input into the external computer 4. The external computer 4 performs BP neural network training and then predicts the pressure action position and size.
As shown in fig. 5, under the condition that the input signal precision is 0.1 Ω, the prediction precision of the positioning after training the BP neural network is less than 0.006cm in both the X direction and the Y direction, and the prediction deviation of the pressure P is less than 1.6 kPa. The BP neural network model has stable prediction accuracy at different positions and different pressure ranges, and has good uniformity and linear characteristics.
As shown in FIG. 6, the average predicted deviations in the X-direction, Y-direction and pressure P of the uniform sample used in graph (a) were 0.098cm, 0.119cm and 7.45kPa, respectively, while the average deviations in the X-direction, Y-direction and pressure of the non-uniform sample used in graph (b) were 0.078cm, 0.089cm and 7.2kPa, respectively. The prediction deviation of the uniform sample is not obviously different from that of the non-uniform sample, and the measurement deviation of the planar piezoresistive sensor caused by the non-uniformity can be compensated by means of the neural network, so that the requirement on the uniformity in the manufacturing process is greatly reduced, the process complexity is simplified, and the device cost is reduced.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A high-precision plane piezoresistive sensor system is characterized by comprising a plane piezoresistive sensor (1), external electrodes (2) and an information processing chip (3) which are arranged on the edge of the piezoresistive sensor (1) and/or an external computer (4), pressure intensities with different sizes are applied to different positions of the plane piezoresistive sensor (1), the resistance size between each group of electrodes can be changed correspondingly, the information processing chip (3) and/or the external computer (4) receive the pressure intensity action position and the pressure intensity of each measurement and the corresponding resistance between each group of electrodes, a test data set is constructed, and a neural network model is trained for predicting the position and the size of the subsequent pressure intensity.
2. High precision planar piezoresistive sensor system according to claim 1, characterized in that the planar piezoresistive sensor (1) is a rigid planar piezoresistive sensor, or a flexible planar piezoresistive sensor.
3. The high precision planar piezoresistive sensor system according to claim 1, wherein the shape of the planar piezoresistive sensor (1) is any regular or irregular shape.
4. The high precision planar piezoresistive sensor system according to claim 1, wherein the sensing material of the planar piezoresistive sensor (1) is a homogeneous sensing material, or a heterogeneous sensing material.
5. The high precision planar piezoresistive sensor system according to claim 1, wherein the circumscribed electrodes (2) do not form a staggered grid structure, but are distributed at the edges of the planar piezoresistive sensor (1). The specific connection mode can be embedded inside the edge part of the sensing material of the planar piezoresistive sensor (1) or can be directly connected with the surface of the edge part of the sensing material.
6. The high precision planar piezoresistive sensor system according to claim 1, wherein the external electrodes (2) are embedded inside the sensing material edges of the planar piezoresistive sensor (1) or directly attached outside the sensing material edges of the planar piezoresistive sensor (1).
7. Use of a high precision planar piezoresistive sensor according to any of the claims 1-6, comprising the following steps:
applying pressure intensities with different sizes at different positions of the planar piezoresistive sensor (1), recording the pressure intensity action position and the pressure intensity of each measurement and the corresponding resistance between each group of electrodes, and transmitting the pressure intensities to the information processing chip (3) and/or the external computer (4);
the information processing chip (3) and/or the external computer (4) receives the pressure action position and the pressure size of each measurement and the resistance between the corresponding groups of electrodes to construct a test data set, and trains a neural network model for predicting the position and the size of the subsequent pressure.
8. The use method of the high-precision planar piezoresistive sensor system according to claim 6, wherein the neural network adopted by the information processing chip (3) and/or the external computer (4) is a BP neural network.
9. Use of a high precision planar piezoresistive sensor system according to claim 6, characterized in that the off-board computer (4) is training and predicting multiple data sets simultaneously.
10. Use method of high precision planar piezoresistive sensor system according to claim 6, characterized in that the information processing chip (3) and/or external computer (4) integrates pattern recognition functions including multi-point contact simultaneous recognition, gesture recognition, pressing pattern recognition, contact point size and movement direction and speed recognition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011386307.1A CN112710415A (en) | 2020-12-01 | 2020-12-01 | High-precision planar piezoresistive sensor system and application method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011386307.1A CN112710415A (en) | 2020-12-01 | 2020-12-01 | High-precision planar piezoresistive sensor system and application method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112710415A true CN112710415A (en) | 2021-04-27 |
Family
ID=75542268
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011386307.1A Pending CN112710415A (en) | 2020-12-01 | 2020-12-01 | High-precision planar piezoresistive sensor system and application method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112710415A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114923607A (en) * | 2022-05-19 | 2022-08-19 | 浙江大学 | Intelligent pressure sensor based on porous material |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102410894A (en) * | 2011-08-02 | 2012-04-11 | 中国矿业大学 | Interface pressure distribution testing sensing element |
CN103267597A (en) * | 2013-01-09 | 2013-08-28 | 中国科学院电工研究所 | Piezoresistive-material-based resistivity imaging flexible pressure detection system and detection method |
US20190321643A1 (en) * | 2017-01-09 | 2019-10-24 | Industry-Academia Cooperation Group Of Sejong University | Sensing system and sensing method using machine learning |
CN110414366A (en) * | 2019-07-04 | 2019-11-05 | 东南大学 | A kind of pressure drag array and pressure distribution matching process based on Dynamic Signal |
CN111964821A (en) * | 2020-08-05 | 2020-11-20 | 清华大学深圳国际研究生院 | Pressure touch prediction method and pressure touch prediction model for electronic skin |
-
2020
- 2020-12-01 CN CN202011386307.1A patent/CN112710415A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102410894A (en) * | 2011-08-02 | 2012-04-11 | 中国矿业大学 | Interface pressure distribution testing sensing element |
CN103267597A (en) * | 2013-01-09 | 2013-08-28 | 中国科学院电工研究所 | Piezoresistive-material-based resistivity imaging flexible pressure detection system and detection method |
US20190321643A1 (en) * | 2017-01-09 | 2019-10-24 | Industry-Academia Cooperation Group Of Sejong University | Sensing system and sensing method using machine learning |
CN110414366A (en) * | 2019-07-04 | 2019-11-05 | 东南大学 | A kind of pressure drag array and pressure distribution matching process based on Dynamic Signal |
CN111964821A (en) * | 2020-08-05 | 2020-11-20 | 清华大学深圳国际研究生院 | Pressure touch prediction method and pressure touch prediction model for electronic skin |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114923607A (en) * | 2022-05-19 | 2022-08-19 | 浙江大学 | Intelligent pressure sensor based on porous material |
CN114923607B (en) * | 2022-05-19 | 2023-10-31 | 浙江大学 | Intelligent pressure sensor based on porous material |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104729769B (en) | Distributed flexible pressure sensor based on electroactive polymer | |
CN109700451B (en) | Flexible temperature-sensitive pressure sensor based on nano particle lattice quantum conductance and assembling method and application thereof | |
CN209841248U (en) | Flexible array pressure sensor | |
WO2017044617A1 (en) | Tactile sensors and methods of fabricating tactile sensors | |
CN110375636B (en) | High-tensile flexible strain sensor based on porous flexible material | |
CN103743787A (en) | Tri-axial testing device for testing water content distribution of soil sample | |
CN107582215B (en) | Artificial intelligence skin and its detection method with temperature and humidity and pressure detecting function | |
CN109745046B (en) | Electrical impedance imaging electrode and system suitable for motion state | |
CN214149645U (en) | Flexible wearable pressure sensor based on elastic cloth | |
CN1965755A (en) | Impedance tomography apparatus based on microneedle electrodes and micro-traumatic measuring method thereof | |
CN113203504A (en) | Flexible wearable pressure sensor with ultrahigh capacitance and pressure sensor array | |
CN112710415A (en) | High-precision planar piezoresistive sensor system and application method thereof | |
CN105547138B (en) | The preparation method of flexible strain transducer made of macro mesh structure carbon nanocoil | |
KR102016208B1 (en) | Method for using materials having no regular pattern as sensor and sensing system | |
Chowdhury et al. | Monitoring and analysis of cardiovascular pulse waveforms using flexible capacitive and piezoresistive pressure sensors and machine learning perspective | |
CN102599907B (en) | Electrical impedance tomography method based on gridding displacement model | |
CN102178509B (en) | Method and system for noninvasive detection of soft tissue neoplasms/nodes | |
CN111938642A (en) | System and method for measuring parameters of plantar pressure surface based on electrical impedance imaging technology | |
CN210833938U (en) | Skin touch sensor | |
CN105509937A (en) | Pressure sensor, pressure detection method and manufacturing process | |
CN112754456A (en) | Three-dimensional electrical impedance imaging system based on deep learning | |
Liu et al. | Fabrication of a tactile sensor for artificial skin based on electrical impedance tomography | |
CN103054577A (en) | Sparse reconstruction method for electrical impedance tomography | |
CN102599908A (en) | Electrical impedance tomography method based on gridding displacement model with balance factor | |
CN110200633A (en) | The sensor and detection method of vola direct stress and shearing force when accurate detection walking |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210427 |