CN107296427A - A kind of cushion and sitting posture analysis method - Google Patents
A kind of cushion and sitting posture analysis method Download PDFInfo
- Publication number
- CN107296427A CN107296427A CN201710733760.7A CN201710733760A CN107296427A CN 107296427 A CN107296427 A CN 107296427A CN 201710733760 A CN201710733760 A CN 201710733760A CN 107296427 A CN107296427 A CN 107296427A
- Authority
- CN
- China
- Prior art keywords
- layer
- sitting posture
- row conductor
- cushion
- column wire
- 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.)
- Withdrawn
Links
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47C—CHAIRS; SOFAS; BEDS
- A47C27/00—Spring, stuffed or fluid mattresses or cushions specially adapted for chairs, beds or sofas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The present invention discloses a kind of cushion and sitting posture analysis method.The cushion includes:M × N array of pressure sensors, the array of pressure sensors includes column wire layer, conductive fiber layer and row conductor layer, and the conductive fiber layer is between column wire layer and row conductor layer;The column wire layer is laid with the parallel column wire of M bars;The row conductor layer is laid with the parallel row conductor of N bars;The row conductor is intersected with the column wire, and each row conductor is connected by the conductive fiber layer with each column wire, constitutes a pressure sensor.Using the cushion and sitting posture analysis method of the present invention, sensing point is relatively more, and higher resolution ratio can be realized by adding to be combined with algorithm, not influenceed in measurement process by extraneous other factors, and the degree of accuracy of measurement result is not stressed influence, therefore degree of accuracy height.
Description
Technical field
The present invention relates to intellectual analysis field, more particularly to a kind of cushion and sitting posture analysis method.
Background technology
The most common posture of human body has three kinds:Stand, lie, sit.In daily life, the time of sitting posture is generally remained
Relatively long, sitting posture is one of most natural posture of human body.For worker, family of office for computer workstation,
They keep sitting posture ordinary working hours for a long time, cause body to there is different degrees of discomfort, if things go on like this, also result in
Disease.Sitting posture decides our health to a certain extent, in the case where that can not avoid keeping sitting posture, improves our seat
Appearance, can effectively improve our health states, mitigate the symptom of some diseases.
The cushion of existing measurement sitting posture generally uses capacitive sensing techniques, and electricity is constituted by the use of two electrical bodies as electrode
Container, the relevant parameter of cushion stress is obtained by measuring the capacitance variation in cushion.Due to the electric capacity of human contact's cushion
Pole plate in device, it will usually produce corresponding parasitic capacitance, cause measurement result inaccurate.And for parasitic capacitance can be avoided
Cushion, typically cost is very high.
The content of the invention
It is an object of the invention to provide a kind of cushion and sitting posture analysis method, to solve sitting posture measurement result in the prior art
Inaccurate the problem of.
To achieve the above object, the invention provides following scheme:
A kind of cushion, the cushion includes:M × N array of pressure sensors, the array of pressure sensors is led including row
Line layer, conductive fiber layer and row conductor layer, the conductive fiber layer is between column wire layer and row conductor layer;Institute
State column wire layer and be laid with the parallel column wire of M bars;The row conductor layer is laid with the parallel row conductor of N bars;The row conductor
Intersect with the column wire, and each row conductor is connected by the conductive fiber layer with each column wire,
Constitute a pressure sensor.
Optionally, the conductive fiber is the fiber base yarn polymers for being coated with piezoelectricity.
Optionally, the row conductor is mutually perpendicular to the column wire.
A kind of sitting posture analytical equipment, described device include cushion, the first analog switch, the second analog switch, single-chip microcomputer, on
Position machine;
The cushion includes:M × N array of pressure sensors, the array of pressure sensors includes column wire layer, conduction
Fibrous layer and row conductor layer, the conductive fiber layer is between column wire layer and row conductor layer;The column wire
Layer is laid with the parallel column wire of M bars;The row conductor layer is laid with the parallel row conductor of N bars;The row conductor and the row
Wires cross, and each row conductor connected by the conductive fiber layer with each column wire, constitutes one
Pressure sensor;
First output end of the single-chip microcomputer connects the column wire layer by the control end of first analog switch
The parallel column wire of bar;Second output end of the single-chip microcomputer connects the row by the control end of second analog switch and led
The parallel row conductor of bar of line layer;The input of the single-chip microcomputer connects the output end of second analog switch, for gathering
The voltage value data of described pressure sensor;3rd output end of the single-chip microcomputer is connected with the host computer, for institute
State the voltage value data of host computer transmission collection;
The host computer is used for the sitting posture that cushion user is analyzed according to the voltage value data.
Optionally, described device also includes:Analog-digital converter, the input of the single-chip microcomputer passes through the analog-digital converter
The output end of second analog switch is connected, the analog-digital converter is used to carry out modulus turn to the voltage value data of collection
Change, generate data signal.
Optionally, the conductive fiber is the fiber base yarn polymers for being coated with piezoelectricity.
A kind of sitting posture analysis method, methods described includes:
The voltage value data of a pressure sensor in cushion is gathered, the cushion includes:M × N array of pressure sensors,
The array of pressure sensors includes column wire layer, conductive fiber layer and row conductor layer, and the conductive fiber layer is located at the row
Between conductor layer and row conductor layer;The column wire layer is laid with the parallel column wire of M bars;The row conductor layer is laid with
The parallel row conductor of N bars;The row conductor is intersected with the column wire, and each row conductor passes through the conductive fiber
Layer is connected with each column wire, constitutes a pressure sensor;
The voltage value data is converted into data signal;
Cushion force diagram picture is obtained according to the data signal;
Wavelet decomposition is carried out to the data signal, feature, the data after being decomposed is extracted;
Sitting posture analysis is carried out to the data after the decomposition using BP neural network, the sitting posture class of cushion user is obtained
Type, the sitting posture type includes:The inclined appearance of right part, the inclined appearance of left part, anterior appearance, the inclined appearance in rear portion and uniform sitting posture partially.
Optionally, it is described that cushion force diagram picture is obtained according to the data signal, specifically include:
Seat cushion stress initial pictures are generated according to the data signal;
With the corresponding pressure sensor position of different stress values in initial pictures described in different colour codes;
To not there is no the area filling color of pressure sensor in the initial pictures using interpolation algorithm;
Obtain the final cushion force diagram picture.
Optionally, it is described that sitting posture analysis is carried out to the data after the decomposition using BP neural network, obtain cushion and use
The sitting posture type of person, is specifically included:
Build BP neural network sitting posture identification model;
Determined according to the data after the decomposition and sitting posture type number hidden in the BP neural network sitting posture identification model
Number containing layer;
By the input layer of BP neural network sitting posture identification model described in the data input after the decomposition;
The sitting posture type of the sitting posture user is determined according to the BP neural network sitting posture identification model.
Optionally, the structure BP neural network sitting posture identification model, is specifically included:
Using the data after decomposition as BP neural network input, sitting posture type be used as output end, build BP nerve nets
Network rudimentary model;
The BP neural network rudimentary model is trained using Q sample;
Calculate the training error of the Q sample;
Judge whether the training error is less than setting error threshold, obtain the first judged result;
When first judged result represents that the training error is less than setting error threshold, the BP nerve nets are determined
Network rudimentary model is BP neural network sitting posture identification model.
The specific embodiment provided according to the present invention, the invention discloses following technique effect:
The degree of accuracy is high:The present invention measures cushion pressure information using array of pressure sensors, and sensing point is relatively more, plus
Upper be combined with algorithm can realize higher resolution ratio, and the change of cushion pressure directly affects conductive fiber in pressure sensor
The internal pressure of layer, conductive fiber layer internal pressure is bigger, and resistance is smaller, so that the output of pressure sensor is changed,
Do not influenceed in measurement process by extraneous other factors, the degree of accuracy of measurement result is not stressed influence, therefore the degree of accuracy is high.
Technique is simple:This cushion need to be only made up of the part of upper, middle and lower three, and upper strata is that the common fabric for being covered with longitudinal wire is applied
Cloth, lower floor be covered with horizontal wire common fabric coating, intermediate layer be resistance can with pressure change conductive fiber, make work
Skill is relatively easy, and this three parts are all easier to make processing.
It is simple in construction:Although this system has M × N number of sensor points, but required signal wire only has M+N roots, compared to
Other sensors, such as piezoresistance sensor, if with M × N number of sensor, each sensor has two signal wires, therefore needs 2M altogether
× N root signal wires.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is the structure chart of cushion of the present invention;
Fig. 2 is the structure chart of sitting posture analytical equipment of the present invention;
Fig. 3 is connected circuit diagram for sensor in sitting posture analytical equipment of the present invention with analog switch;
Fig. 4 is the flow chart of sitting posture analysis method of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
In order to facilitate the understanding of the purposes, features and advantages of the present invention, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is further detailed explanation.
Fig. 1 is the structure chart of cushion of the present invention.As shown in figure 1, the cushion includes:M × N array of pressure sensors, M
It is the integer more than zero with N, for example, M=5, N=6, now composition 5 × 6 array of pressure sensors;M=8, N=8, this
When constitute 8 × 8 array of pressure sensors;M=10, N=10, now composition 10 × 10 array of pressure sensors.Specific pressure
The size of force sensor array, can make adjustments according to the actual requirements.The array of pressure sensors includes column wire layer 101, led
Electric fibrous layer 102 and row conductor layer 103;
The conductive fiber layer 102 is between column wire layer 101 and row conductor layer 103;Conductive fiber layer
102 be the material based on conductive fiber, and it is the fiber base yarn polymers for being coated with piezoelectricity, in the presence of no external force,
Resistance inside conductive fiber is very big, when there is external force to be applied to cushion surface, and the inside of conductive fiber is extruded, its electricity
Resistance will become very little.It is unlimited that its resistance between any two points of the same side can be counted as.Therefore, we can be with
This feature is taken to design high density and low cost pressure sensor array.
The column wire layer 101 is to be laid with the parallel column wire 1011 of M bars on common fabric even spread;The row is led
Line layer 103 is to be laid with the parallel row conductor 1013 of N bars on common fabric even spread;The row conductor is handed over the column wire
Pitch, and each row conductor is connected by the conductive fiber layer 102 with each column wire, constitutes a pressure
Sensor.Now, the conductive interlayer fibrous layer between row conductor and column wire is resistance, each friendship of row conductor and column wire
Point is changed into presser sensor resistance, forms pressure sensor.In the specific implementation, row conductor is vertical with column wire, now M on cushion
× N number of pressure sensor is evenly distributed.
Fig. 2 is the structure chart of sitting posture analytical equipment of the present invention.As shown in Fig. 2 shown device includes:Cushion 201, the first mould
Intend the 202, second analog switch 203 of switch, single-chip microcomputer 204, host computer 205;
Cushion 201 includes M × N array of pressure sensors, the pressure sensor using the cushion structure shown in Fig. 1
Array is three-ply sandwich structure, including column wire layer 2011, conductive fiber layer 2012 and row conductor layer 2013.
First output end of the single-chip microcomputer 204 connects the row by the control end of first analog switch 202 and led
The parallel column wire of M bars of line layer 2011;
Second output end of the single-chip microcomputer 204 connects the row by the control end of second analog switch 203 and led
The parallel row conductor of N bars of line layer 2013;
The input of the single-chip microcomputer 204 connects the output end of second analog switch 203, for gathering the M × N
The voltage value data of individual pressure sensor;
3rd output end of the single-chip microcomputer 204 is connected with the host computer 205, for being transmitted to the host computer 205
The voltage value data of collection;The effect of single-chip microcomputer 204 be the pressure signal measured is acquired and carried out it is certain corresponding
Processing, then by the serial communication interface of single-chip microcomputer 204 and host computer 205 with certain method by the pressure after acquisition process
Data transfer is on host computer 205.
The host computer 205 is used for the sitting posture that cushion user is analyzed according to the voltage value data.Mainly find out specific
Several typical sitting postures pressure distribution situation corresponding thereto, specific sitting posture is differentiated, the human body collected is sat
Appearance pressure distribution data realizes visualization.
Described device also includes:Analog-digital converter, the input of the single-chip microcomputer 204 is connected by the analog-digital converter
The output end of second analog switch 203, the analog-digital converter is used to carry out analog-to-digital conversion to the voltage value data of collection,
Generate data signal.
The sitting posture analytical equipment of the present invention has advantages below:
Technique is simple:Cushion need to be only made up of the part of upper, middle and lower three, upper strata be covered with longitudinal wire polypropylene plastics flitch (or
Person's common fabric even spread), lower floor is to be covered with horizontal wire polypropylene plastics flitch (or common fabric even spread), middle
One layer of resistance can with pressure change conductive fiber layer, manufacture craft is relatively easy, and this three parts are all to be easier to make
Processing.The country carry out sitting posture identification using it is more be PVDF pressure sensors, the domestic Technical comparing of this sensor into
It is ripe, because the producer that can be done is less, so price is more relatively expensive.The cushion of the present invention uses distributed sensor array
Row, relative inexpensiveness is a lot of.
It is simple in construction:Although this system has M × N number of sensor points, but required signal wire only has M+N roots, compared to
Other sensors, such as piezoresistance sensor, if with M × N number of sensor, each sensor has two signal wires, therefore needs 2M altogether
× N root signal wires.
Fig. 3 is connected circuit diagram for sensor in sitting posture analytical equipment of the present invention with analog switch.As shown in figure 3, top layer is arranged
Each conductive bus of conductor layer are connected to power supply VCC by analog switch S1.Each conductive bus of bottom line conductor layer lead to
Cross analog switch S2 and be connected to analog-digital converter (Analog to Digital Converter, ADC) and by offset resistance R0
Ground connection, R0 also has certain partial pressure effect.S1 and S2 are by microprocessor control.When control S1 is alternatively coupled to one of top
Passage j reading is sensor Vij in voltage supply during bus i, S2.By peripheral circuit, microcontroller (single-chip microcomputer) can be with
Access the magnitude of voltage of any sensor in this array.
Single-chip microcomputer controls multi-channel analog switch circuit first, is responsible for selection switching M × N roads sitting posture pressure distribution signal.It is single
Piece machine control S1 once adds 3.3V voltages to each wire in turn, and when S1 is alternatively coupled to a bus i at top, voltage is supplied
Should, passage j reading is sensor Vij in S1, by peripheral circuit, and microcontroller can access each in this array and sense
The magnitude of voltage of device.Progress A/D conversions are needed just to be sent on computer, the system selection single-chip microcomputer for the data collected
The A/D modular converters carried can meet needs, and single A/D converter can also be selected to carry out analog-to-digital conversion.
Fig. 4 is the flow chart of sitting posture analysis method of the present invention.As shown in figure 4, methods described includes:
Step 401:Gather pressure sensor data in cushion.Pressure sensor data is voltage value data.Cushion is to adopt
With the cushion structure shown in Fig. 1, cushion includes M × N array of pressure sensors, and the array of pressure sensors is three layer interlayers
Structure, including column wire layer, conductive fiber layer and row conductor layer.
Step 402:Voltage value data is converted into data signal.Due to step 401 gather be pressure distribution simulation
Signal, therefore analog-to-digital conversion is carried out, and the data signal after analog-to-digital conversion is preserved to wait a series of follow-up processing
Work.
Step 403:Obtain cushion force diagram picture.According to the data signal, cushion force diagram is obtained according to pressure distribution
Picture.Because the data signal of reception is the data signal that represents different pressures size, with matching somebody with somebody that developing instrument Matlab is carried
The position for the representative different pressures size that color scheme collects different pressure sensors represents its with different colors
Size, takes with its color of interpolation algorithm reasonable supplement for the position without pressure sensor.In this way, will on gui interface
There is the pressure-plotting that a width represents sitting posture pressure distribution, different colours represent different pressure sizes.Detailed process is:
Pressure distribution information generation seat cushion stress initial pictures in the data signal;
With the corresponding pressure sensor position of different stress values in initial pictures described in different colour codes;
To not there is no the area filling color of pressure sensor in the initial pictures using interpolation algorithm;
Obtain the final cushion force diagram picture.
Step 404:Data after being decomposed.Wavelet decomposition is carried out to the data signal, feature is extracted, is decomposed
Data afterwards.Wavelet decomposition is a kind of letter being segmented to pressure signal by a series of wavelet basis functions under time-frequency domain
Number processing means.It can go to complete the decomposition and reconstruct of different frequency segment signal by the selection to different wavelet basis functions,
Finally give by it is after careful analysis, eliminate the waveform of partial noise.From the point of view of mathematics, that is, pass through time domain one-dimensional signal
To the conversion of time-frequency domain two-dimensional space, the purpose of multiresolution analysis is finally reached.
Step 405:Sitting posture analysis is carried out using BP neural network, sitting posture type is obtained.Using BP neural network to described
Data after decomposition carry out sitting posture analysis, obtain the sitting posture type of cushion user, the sitting posture type includes:The inclined appearance of right part,
The inclined appearance of left part, anterior appearance, the inclined appearance in rear portion and uniform sitting posture partially.Detailed process is:
Build BP neural network sitting posture identification model.With reference to sitting posture pressure distribution information to the structures of BP networks, input it is defeated
Go out and various parameters are designed, build the sitting posture identification model based on BP neural network;
Determined according to the data after the decomposition and sitting posture type number hidden in the BP neural network sitting posture identification model
Number containing layer.Hidden layer neuron number is larger to the performance impact of BP neural network.If the number of hidden layer neuron compared with
Few, then network can not fully describe the relation between input and output variable;If the number of opposite hidden layer neuron is more,
The problem of learning time of network can be caused elongated, or even over-fitting occur.There is presently no determine hidden layer neuron number
Unified approach, typically may be referred to empirical equationWherein p is hidden layer neuron number, and n is input
Layer neuron number (n=M × N in the present invention), q is output layer neuron number (i.e. the quantity of sitting posture classification), and a is taken as 0 and arrived
Constant between 10.In order to obtain optimal hidden layer neuron number, it can choose different on the basis of above-mentioned empirical equation
Hidden layer neuron number tested respectively, respectively record each case under train after network reality output with expectation it is defeated
The mean square error size and train epochs gone out, considers the network that error is smaller and train epochs are less, so that it is determined that more
For suitable hidden layer neuron number.In present networks, it is 12 to choose hidden layer neuron.
By the input layer of BP neural network sitting posture identification model described in the data input after the decomposition.By M in the present invention
The pressure sensor signal of × N-dimensional inputs the number of neuron for M × N number of as the input of BP neural network.
The sitting posture type of the sitting posture user is determined according to the BP neural network sitting posture identification model.It will sit accordingly
Appearance type is used as output result.Output layer is sitting posture classification, respectively the inclined appearance of right part, the inclined appearance of left part, anterior appearance, the inclined appearance in rear portion partially
With uniform sitting posture, 1,2,3,4,5 are respectively defined as, output layer nodes are 1.
Wherein, the process of structure BP neural network sitting posture identification model is:
Using the data after decomposition as BP neural network input, sitting posture type be used as output end, build BP nerve nets
Network rudimentary model;
The BP neural network rudimentary model is trained using Q sample;
Calculate the training error of the Q sample;
Judge whether the training error is less than setting error threshold, obtain the first judged result;
When first judged result represents that the training error is less than setting error threshold, the BP nerve nets are determined
Network rudimentary model is BP neural network sitting posture identification model.
For example:Using pressure sensor signal as the input of neutral net, corresponding sitting posture classification is regard as output end, structure
7*12*1 BP networks are built, and network is trained, 260 samples of selection are as training sample, and a sample is used as test
Sample builds BP neural network sitting posture identification model.Neural Network Toolbox is carried by MATLAB to be trained it, is set
Frequency of training be 1000 times, training error target be 0.0001, learning rate is 0.05, when training error be less than training error mesh
When marking (setting error threshold), then meet the requirements, BP neural network sitting posture identification model is successfully constructed.
This method is substantially that can reflect the pressure distribution situation of human body sitting posture and can determine five kinds of sitting postures
Type.The different colours of pressure-plotting according to visualization interface out, can qualitatively determine each sensing point
The pressure size at place, and then it is estimated that the distribution situation of human body sitting posture pressure.Pass through instruction of the neutral net to training data
Practice the sitting posture type that may determine that test data.All tests above demonstrate the feasibility of the system design scheme.
Specific implementation process:
Pressure distribution measurement is carried out with the present invention by five aspiration testers of selection and sitting posture differentiates.Five tests are arranged altogether
Person does two groups of tests, and first group is to allow them arbitrarily to sit down, and takes the posture being usually accustomed to take a seat, tester is not arranged specially
Sitting posture.Second group is the sitting posture for providing five people, allows them to train five involved sitting postures before taking respectively, i.e., after
The inclined appearance in portion (LB), the inclined appearance of left part (ROL), the inclined appearance of right part (LOR), anterior appearance (SFE), uniform sitting posture (UPRIGHT) partially.Five surveys
The information of examination person is as follows:
Tester A:25 years old, women, height 162cm was usually accustomed to the earlier position of seat.First group of test
When be in normal sitting position SFE states, provided when second group of test he be in lift up cross-legged ROL states.
Tester B:26 years old, women, height 160cm usually liked lifting up cross-legged seat.It is in when doing first group of test
Cross-legged LOR posture is lifted up, provides that she is in UPRIGHT sitting posture state when doing second group of test.
Tester C:24 years old, male, height 172cm, sitting posture custom was good.In normal when first group of test
UPRIGHT postures, provide that he is in LOR sitting posture state when doing second group of test.
Tester D:23 years old, women, height 167cm usually liked being seated against chair back.At when first group of test
In LB state, provide that she is in SFE sitting posture state when doing second group of test.
Tester E:29 years old, male, height 176cm usually liked lifting up cross-legged.ROL is in when first group of test
State, provided when doing second group of test his be in LB sitting posture state.
The result of two groups of tests is as follows:
In the first set, tester A customs are sitting in the forward position of chair, and sensor array only has anterior stress, behind
Do not acted on by power, such sitting posture is still very healthy.Tester B is to lift up cross-legged seat due to custom usually
, be that left leg has been placed on right leg and lifts up cross-legged among test, cause on the right side of lifting surface area substantially than the stress surface in left side
Product is much bigger, and sitting posture pressure distribution is uneven.Tester C is normal upright sitting posture custom, sitting posture pressure due to custom
The ratio of power distribution is more uniform, healthier.Tester D is sat due to liking against the chair back, so causes his center rearward, is sensed
Device rear portion stress is larger, and anterior stress is smaller, and the paralysed seated posture of hypsokinesis is presented in body.Tester D also likes lifting up cross-legged when flat
Sit, be that right leg has been placed on left leg and lifts up cross-legged in test, cause the lifting surface area in left side substantially than the lifting surface area on right side
It is big.
Pressure-plotting obtained by second group of test also complies with advance setting.The pressure-plotting for summarizing the above can be with
Find out, the result of pressure-plotting meets the cognition directly perceived of true and people.
LB type sitting postures cause centre of pressure rearward, and the pressure at sensor rear portion is far longer than the pressure of front portion,
LOR type sitting postures cause the pressure on the left of sensor substantially larger than right side,
ROL type sitting postures cause the pressure on the right side of sensor substantially larger than left side,
SFE type sitting postures cause that pressure is all distributed in the front portion of sensor and rear portion does not have a stress, and in front portion distribution
It is more uniform,
UPRIGHT type sitting postures pressure distribution just than more uniform, be substantially exactly all around four regions be uniformly distributed.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other
Between the difference of embodiment, each embodiment identical similar portion mutually referring to.For system disclosed in embodiment
For, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is said referring to method part
It is bright.
Specific case used herein is set forth to the principle and embodiment of the present invention, and above example is said
The bright method and its core concept for being only intended to help to understand the present invention;Simultaneously for those of ordinary skill in the art, foundation
The thought of the present invention, will change in specific embodiments and applications.In summary, this specification content is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of cushion, it is characterised in that the cushion includes:M × N array of pressure sensors, the pressure sensor battle array
Row include column wire layer, conductive fiber layer and row conductor layer, and the conductive fiber layer is led located at column wire layer with the row
Between line layer;The column wire layer is laid with the parallel column wire of M bars;The row conductor layer is laid with the parallel row conductor of N bars;
The row conductor is intersected with the column wire, and each row conductor passes through the conductive fiber layer and each row
Wire is connected, and constitutes a pressure sensor.
2. cushion according to claim 1, it is characterised in that the conductive fiber is the fiber based yarn for being coated with piezoelectricity
Polymer.
3. cushion according to claim 1, it is characterised in that the row conductor is mutually perpendicular to the column wire.
4. a kind of sitting posture analytical equipment, it is characterised in that described device include cushion, the first analog switch, the second analog switch,
Single-chip microcomputer, host computer;
The cushion includes:M × N array of pressure sensors, the array of pressure sensors includes column wire layer, conductive fiber
Layer and row conductor layer, the conductive fiber layer is between column wire layer and row conductor layer;The column wire layer cloth
Provided with the parallel column wire of M bars;The row conductor layer is laid with the parallel row conductor of N bars;The row conductor and the column wire
Intersect, and each row conductor is connected by the conductive fiber layer with each column wire, constitutes a pressure
Sensor;
The M bars that first output end of the single-chip microcomputer connects the column wire layer by the control end of first analog switch are put down
Capable column wire;Second output end of the single-chip microcomputer connects the row conductor layer by the control end of second analog switch
The parallel row conductor of N bars;The input of the single-chip microcomputer connects the output end of second analog switch, described for gathering
The voltage value data of M × N number of pressure sensor;3rd output end of the single-chip microcomputer is connected with the host computer, for institute
State the voltage value data of host computer transmission collection;
The host computer is used for the sitting posture that cushion user is analyzed according to the voltage value data.
5. device according to claim 4, it is characterised in that described device also includes:Analog-digital converter, the single-chip microcomputer
Input the output end of second analog switch is connected by the analog-digital converter, the analog-digital converter is used for adopting
The voltage value data of collection carries out analog-to-digital conversion, generates data signal.
6. device according to claim 4, it is characterised in that the conductive fiber is the fiber based yarn for being coated with piezoelectricity
Polymer.
7. a kind of sitting posture analysis method, it is characterised in that methods described includes:
The voltage value data of M × N number of pressure sensor in cushion is gathered, the cushion includes:M × N array of pressure sensors,
The array of pressure sensors includes column wire layer, conductive fiber layer and row conductor layer, and the conductive fiber layer is located at the row
Between conductor layer and row conductor layer;The column wire layer is laid with the parallel column wire of M bars;The row conductor layer is laid with
The parallel row conductor of N bars;The row conductor is intersected with the column wire, and each row conductor passes through the conductive fiber
Layer is connected with each column wire, constitutes a pressure sensor;
The voltage value data is converted into data signal;
Cushion force diagram picture is obtained according to the data signal;
Wavelet decomposition is carried out to the data signal, feature, the data after being decomposed is extracted;
Sitting posture analysis is carried out to the data after the decomposition using BP neural network, the sitting posture type of cushion user, institute is obtained
Stating sitting posture type includes:The inclined appearance of right part, the inclined appearance of left part, anterior appearance, the inclined appearance in rear portion and uniform sitting posture partially.
8. method according to claim 7, it is characterised in that described that cushion force diagram is obtained according to the data signal
Picture, is specifically included:
Seat cushion stress initial pictures are generated according to the data signal;
With the corresponding pressure sensor position of different stress values in initial pictures described in different colour codes;
To not there is no the area filling color of pressure sensor in the initial pictures using interpolation algorithm;
Obtain the final cushion force diagram picture.
9. method according to claim 7, it is characterised in that the utilization BP neural network is to the data after the decomposition
Sitting posture analysis is carried out, the sitting posture type of cushion user is obtained, specifically includes:
Build BP neural network sitting posture identification model;
Hidden layer in the BP neural network sitting posture identification model is determined according to the data after the decomposition and sitting posture type number
Number;
By the input layer of BP neural network sitting posture identification model described in the data input after the decomposition;
The sitting posture type of the sitting posture user is determined according to the BP neural network sitting posture identification model.
10. method according to claim 9, it is characterised in that the structure BP neural network sitting posture identification model, specifically
Including:
Using the data after decomposition as the input of BP neural network, sitting posture type is as output end, at the beginning of building BP neural network
Walk model;
The BP neural network rudimentary model is trained using Q sample;
Calculate the training error of the Q sample;
Judge whether the training error is less than setting error threshold, obtain the first judged result;
When first judged result represents that the training error is less than setting error threshold, at the beginning of determining the BP neural network
Step model is BP neural network sitting posture identification model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710733760.7A CN107296427A (en) | 2017-08-24 | 2017-08-24 | A kind of cushion and sitting posture analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710733760.7A CN107296427A (en) | 2017-08-24 | 2017-08-24 | A kind of cushion and sitting posture analysis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107296427A true CN107296427A (en) | 2017-10-27 |
Family
ID=60132554
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710733760.7A Withdrawn CN107296427A (en) | 2017-08-24 | 2017-08-24 | A kind of cushion and sitting posture analysis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107296427A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107945467A (en) * | 2017-12-20 | 2018-04-20 | 中国科学院合肥物质科学研究院 | A kind of Portable sitting monitoring and system for prompting based on buttocks Pressure Distribution |
CN108549834A (en) * | 2018-03-08 | 2018-09-18 | 佛山市顺德区中山大学研究院 | A kind of human body sitting posture recognition methods and its system based on flexible sensor |
CN108814616A (en) * | 2018-04-12 | 2018-11-16 | 深圳和而泰数据资源与云技术有限公司 | A kind of sitting posture knows method for distinguishing and Intelligent seat |
CN109512188A (en) * | 2019-01-04 | 2019-03-26 | 北京环境特性研究所 | A kind of sitting posture detecting method and device and seat |
CN110897425A (en) * | 2019-11-18 | 2020-03-24 | 中国地质大学(武汉) | Child sitting posture detection cushion, device interacting with cushion and sitting posture monitoring method |
CN112617817A (en) * | 2020-12-17 | 2021-04-09 | 深圳数联天下智能科技有限公司 | Sitting posture detection method and device, computer equipment and storage medium |
CN112773356A (en) * | 2020-11-16 | 2021-05-11 | 深圳数联天下智能科技有限公司 | Sitting posture detection method, system, terminal and storage medium |
CN113080941A (en) * | 2021-03-15 | 2021-07-09 | 深圳数联天下智能科技有限公司 | Sitting posture assessment method and related device |
CN113627236A (en) * | 2021-06-24 | 2021-11-09 | 广东技术师范大学 | Sitting posture identification method, device, equipment and storage medium |
CN114323368A (en) * | 2021-12-09 | 2022-04-12 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on hip pressure |
CN117288355A (en) * | 2023-09-21 | 2023-12-26 | 北京软体机器人科技股份有限公司 | Pressure sensor and flexible finger clamp |
-
2017
- 2017-08-24 CN CN201710733760.7A patent/CN107296427A/en not_active Withdrawn
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107945467A (en) * | 2017-12-20 | 2018-04-20 | 中国科学院合肥物质科学研究院 | A kind of Portable sitting monitoring and system for prompting based on buttocks Pressure Distribution |
CN108549834A (en) * | 2018-03-08 | 2018-09-18 | 佛山市顺德区中山大学研究院 | A kind of human body sitting posture recognition methods and its system based on flexible sensor |
CN108814616B (en) * | 2018-04-12 | 2021-11-05 | 深圳和而泰数据资源与云技术有限公司 | Sitting posture identification method and intelligent seat |
CN108814616A (en) * | 2018-04-12 | 2018-11-16 | 深圳和而泰数据资源与云技术有限公司 | A kind of sitting posture knows method for distinguishing and Intelligent seat |
CN109512188A (en) * | 2019-01-04 | 2019-03-26 | 北京环境特性研究所 | A kind of sitting posture detecting method and device and seat |
CN109512188B (en) * | 2019-01-04 | 2021-11-16 | 北京环境特性研究所 | Sitting posture detection method and device and seat |
CN110897425A (en) * | 2019-11-18 | 2020-03-24 | 中国地质大学(武汉) | Child sitting posture detection cushion, device interacting with cushion and sitting posture monitoring method |
CN112773356A (en) * | 2020-11-16 | 2021-05-11 | 深圳数联天下智能科技有限公司 | Sitting posture detection method, system, terminal and storage medium |
CN112617817A (en) * | 2020-12-17 | 2021-04-09 | 深圳数联天下智能科技有限公司 | Sitting posture detection method and device, computer equipment and storage medium |
CN113080941A (en) * | 2021-03-15 | 2021-07-09 | 深圳数联天下智能科技有限公司 | Sitting posture assessment method and related device |
CN113080941B (en) * | 2021-03-15 | 2024-02-02 | 深圳数联天下智能科技有限公司 | Sitting posture assessment method and related device |
CN113627236A (en) * | 2021-06-24 | 2021-11-09 | 广东技术师范大学 | Sitting posture identification method, device, equipment and storage medium |
CN114323368A (en) * | 2021-12-09 | 2022-04-12 | 深圳先进技术研究院 | Flexible intelligent sitting posture monitoring system based on hip pressure |
CN117288355A (en) * | 2023-09-21 | 2023-12-26 | 北京软体机器人科技股份有限公司 | Pressure sensor and flexible finger clamp |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107296427A (en) | A kind of cushion and sitting posture analysis method | |
CN102793542B (en) | Device for acquiring sole pressure and three-dimensional data of foot appearance | |
CN104463326B (en) | Standard 12-lead ecg signal reconstruction method | |
CN104545912B (en) | The measuring method and device of a kind of cardiopulmonary impedance | |
CN106419893A (en) | Sleep state detection method and device | |
CN109760691B (en) | It is a kind of consider electromyography signal driver comfort drive posture under the matched method of man-machine arrangement parameter | |
CN103605832B (en) | The method that prediction human calf is distributed for garment pressure | |
CN109875565A (en) | A kind of cerebral apoplexy upper extremity exercise function method for automatically evaluating based on deep learning | |
CN106980367A (en) | A kind of gesture identification method based on myoelectricity topographic map | |
CN106980746A (en) | A kind of general Woundless blood sugar Forecasting Methodology based on Time-Series analysis | |
CN107330949A (en) | A kind of artifact correction method and system | |
CN102138860A (en) | Intelligentized rehabilitation training equipment for hand functions of patients suffering from cerebral injury | |
CN100577097C (en) | Method for masuring metabolism of human for one day and heat quantity valve needed by human for biologic action | |
CN206641449U (en) | A kind of pressure sensitivity Intelligent insole and Intelligent sole pressure monitor system | |
CN106037650A (en) | Hybrid variation bioelectrical impedance imaging method | |
CN208371375U (en) | A kind of cushion and sitting posture detection device | |
CN107374780A (en) | A kind of artificial intelligence skin and its method for detection humiture and pressure | |
CN103815905B (en) | A kind of bioelectrical impedance analysis instrument realizing any areal survey of human body | |
CN114847980A (en) | Swallowing test system | |
CN111938642A (en) | System and method for measuring parameters of plantar pressure surface based on electrical impedance imaging technology | |
CN107595433A (en) | A kind of artificial intelligence skin and its method for detection humidity and temperature | |
DUBUISSON | Systematic relationships within the genus Trichomanes sensu lato (Hymenophyllaceae, Filicopsida): cladistic analysis based on anatomical and morphological data | |
Fu et al. | Electrical equivalent network modeling of forearm tissue bioimpedance | |
Yang et al. | An image reconstruction algorithm for electrical impedance tomography using measurement estimation of virtual electrodes | |
CN110207865B (en) | Plantar pressure sensor for correcting temperature influence and corresponding correction method |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171027 |
|
WW01 | Invention patent application withdrawn after publication |