CN109905487A - A kind of intelligent health management system and method based on cloud computing - Google Patents
A kind of intelligent health management system and method based on cloud computing Download PDFInfo
- Publication number
- CN109905487A CN109905487A CN201910212870.8A CN201910212870A CN109905487A CN 109905487 A CN109905487 A CN 109905487A CN 201910212870 A CN201910212870 A CN 201910212870A CN 109905487 A CN109905487 A CN 109905487A
- Authority
- CN
- China
- Prior art keywords
- unit
- monitoring
- air
- conditioning
- cloud computing
- 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- Withdrawn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
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The intelligent health management system based on cloud computing that the invention discloses a kind of, comprising: monitoring unit；Processing system is electrically connected with the output end of the monitoring unit；Storage unit, and the processing system is two-way is electrically connected；Control unit, input terminal are electrically connected with the output end of the processing system；Output unit, input terminal are electrically connected with the output end of described control unit；Alarm unit, input terminal are electrically connected with the output end of described control unit；Unit is adjusted, input terminal is electrically connected with the output end of described control unit.It is monitored by temperature, humidity, PM2.5 concentration, combustable gas concentration of the monitoring unit to living environment either region to be monitored, it notifies and adjusts in time when changing, improve living environment, occupant is allowed to know environmental change in advance, counter-measure is carried out, health control efficiency is improved.The intelligent health management system based on cloud computing that the present invention also provides a kind of.
Description
Technical field
The intelligent health management system based on cloud computing that the present invention relates to a kind of, belongs to health management arts.
Background technique
With the progress and expanding economy in epoch, people increasingly pay attention to health and maintenance, and health control is exactly to use
Modern information technologies and medical technology, in health care, medical scientific basic, a set of perfect, careful and individual character of foundation
The service routine of change, its object is to help healthy population, sub-health population and disease by modes such as maintaining healthy, promotion health
Patient group establishes the life style of Ordered and Healthy, reduces risk status, far from disease.
It is Healthy People there are about 15% in China, 15% non-health people, 70% sub-healty adults, and it is actively engaged in health
Management less than 5%, relatively weak due to health perception, the disbursement that many families are applied to medical treatment every year accounts for family's receipts
30% or more entered, What is more because medical expense returns to poverty but also can not save life one by one.
Health control is to reduce medical expense to prevent and control disease and occur and develop, for the purpose of improving quality of life,
Health education is carried out for individual and group, improves self-management consciousness and level, and endanger to the relevant health of its life style
The life style that dangerous factor health control can rest on a scientific basis carries out comprehensive monitoring to personal or crowd health risk factors,
The process for the Whole Course Management analyzed, assess, predict and intervened instructs people actively effectively to safeguard and hold and is good for
Health, become passive treatment for actively prevention, by passively treat disease promote it is healthy towards actively preventing disease, holding and maintaining healthy
Concept Change.
Modern medicine study shows that many disease causes of disease are primarily not caused by biological factor, but due to undesirable life
Caused by the mode of living, environmental factor etc., therefore, reinforce the monitoring to living environment, is the hand for realizing that health control is indispensable
Section.
Summary of the invention
The present invention has designed and developed a kind of intelligent health management system based on cloud computing, by monitoring unit to inhabitation ring
Border is monitored, and is adjusted and is alarmed in environmental change.
The present invention has also designed and developed a kind of control method of intelligent health management system based on cloud computing, can be to residence
Firmly environment is monitored and adjusts, and can not classify to governing stage, in case of emergency alarms, and control precision is high,
Effect is good.
Another goal of the invention of the invention: the rate of discharge by adjusting air-conditioning regulating valve improves degree of regulation.
Technical solution provided by the invention are as follows:
A kind of intelligent health management system based on cloud computing, comprising:
Monitoring unit；
Processing system is electrically connected with the output end of the monitoring unit,；
Storage unit, and the processing system is two-way is electrically connected；
Control unit, input terminal are electrically connected with the output end of the processing system；
Output unit, input terminal are electrically connected with the output end of described control unit；
Alarm unit, input terminal are electrically connected with the output end of described control unit；
Unit is adjusted, input terminal is electrically connected with the output end of described control unit.
Preferably, the monitoring unit includes: that Temperature Humidity Sensor, PM2.5 concentration detection sensor, fuel gas are dense
Spend sensor.
Preferably, the adjusting unit includes: air-conditioning and air purifier.
A kind of control method of the intelligent health management system based on cloud computing, comprising:
Monitoring unit is monitored the temperature in monitored region, humidity, PM2.5 concentration and combustable gas concentration；
Processing system receives the monitoring signals transmitted from monitoring unit, and will be in monitoring signals and the storage unit
Normal monitoring state signal is compared the monitoring state identifier for obtaining representing monitored region after classification；According to institute monitoring section
The monitoring state identifier in domain determines the monitored matched operating condition in region；
In the absence of monitoring state identifier, then according to neural network model, the operation for institute's monitoring signals is provided
Classification, comprising:
The coding layer for monitoring obtained multiple monitoring signals is configured to neural network model, in the neural network
Institute's monitoring signals are parsed and exported；
Output result is input in fuzzy controller, the output vector group for indicating to adjust classification is obtained, as tune
Save answer output.
Preferably, the neural network model is three layers of BP neural network model, and the neural network specifically monitored
Journey includes:
Step 1, the temperature T in the monitored region of acquisition, humidity RH, PM2.5 concentration CP, combustable gas concentration CK, and by parameter
It is successively normalized, determines that the input layer vector of three layers of BP neural network is x={ x1,x2,x3,x4}；Wherein, x1For temperature system
Number, x2For humidity coefficient, x3For PM2.5 concentration factor, x4For combustable gas concentration coefficient；
Step 2, the input layer DUAL PROBLEMS OF VECTOR MAPPING to middle layer, the middle layer vector y={ y1,y2,…,ym}；During m is
Interbed node number；
Step 3 obtains output layer vector o={ o1,o2,o3}；o1For air-conditioning adjustment factor, o2It is adjusted for air purifier and is
Number, o3For alarm index.
Preferably, the formula that the input layer vector is normalized are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter: T, RH, CPAnd CK, j=1,2,3,4；
XjmaxAnd XjminMaximum value and minimum value in respectively corresponding measurement parameter.
Preferably, the middle layer node number m meets:Wherein, n is input layer
Number, p are output layer node number；The excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/
(1+e-x)。
Preferably, the course of work of the fuzzy controller includes:
Air-conditioning adjustment factor is obtained into air-conditioning adjusting deviation signal compared with preset air-conditioning adjustment factor, by air cleaning
Device adjustment factor obtains air purifier adjusting deviation signal compared with preset air purifier adjustment factor, by alarm index
Alarm deviation signal is obtained compared with preset air-conditioning alarm index；
Air-conditioning adjusting deviation signal is obtained into air-conditioning by differential calculation and adjusts change rate signal, air purifier adjusts inclined
Difference signal obtains air purifier by differential calculation and adjusts change rate signal, and alarm deviation signal is obtained by differential calculation
Air-conditioning adjusts change rate signal；
Air-conditioning is adjusted into change rate signal, air purifier adjusts change rate signal and alarm change rate signal passes through jointly
Fuzzy controller is inputted after crossing amplification, output adjusts grade.
Preferably, the rate of discharge of the air-conditioning regulating valve meets:
Wherein, QvFor the setting flow velocity for adjusting valve outlet, π is pi, and r is the pipeline radius that refrigerant flows through pipeline,
L is the flow distance of refrigerant, and V is the volume of refrigerant fluid reservoir, v0The volume of refrigerant, v when being initialiFor refrigerant
Measure volume, piFor channel interior pressure, p0For tube outlet pressure, kcFor constriction coefficient, A1For fluid reservoir inlet cross section
Product, A2For fluid reservoir liquid outlet cross-sectional area, IWThe steady-state current of compressor, I when to work0The initial electricity of compressor when work
Stream, η are the working efficiency of compressor.
It is of the present invention the utility model has the advantages that by monitoring unit to the temperature, wet in living environment either region to be monitored
Degree, PM2.5 concentration, combustable gas concentration are monitored, and are notified and are adjusted in time when changing, and are improved living environment, are allowed
Occupant knows environmental change in advance, carries out counter-measure, improves health control efficiency.
The present invention analyze to the monitoring data that monitoring unit transmits by BP neural network to be compared and exports, in environment
It is adjusted, and can classify when change to grade is adjusted, alarm when urgent, regulating effect is good, and precision is high.
The present invention is adjusted by adjusting valve air gate flow to air-conditioning, prevents living environment from changing to living
The influence of health status, enhancing health control consciousness, improves health control efficiency.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the intelligent health management system of the present invention based on cloud computing.
Fig. 2 is the working strategies figure of the intelligent health management system of the present invention based on cloud computing.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, the present invention provides a kind of intelligent health management system based on cloud computing, monitoring region can be treated
Daily living environment be monitored and adjust, alarm in danger, improve people's health management awareness and health pipe
Manage efficiency.Specifically include: monitoring unit, storage unit, control unit, alarm unit, adjusts unit and output at processing system
Unit.
Monitoring unit includes Temperature Humidity Sensor, PM2.5 concentration detection sensor and combustable gas concentration detection sensing
Device, the input terminal of the output end electrical connection processing system of monitoring unit, processing system with storage unit is two-way is electrically connected, processing system
The input terminal that the output end of system is electrically connected control unit, adjusts unit and alarm unit, the output end of control unit are electrically connected
Connect the input terminal of output unit.It is monitored by the living environment that monitoring unit treats monitoring region, and become in environment
It is adjusted when change by adjusting unit, early warning is carried out when dangerous situation, personnel are evacuated in advance, pass through output unit
Output adjusts grade, and the management effect for keeping this health management system arranged is good, and precision is high.
In the present embodiment, as a preference, adjusting Unit selection control and air purifier.
The control method for the intelligent health management system based on cloud computing that the present invention also provides a kind of, BP neural network is to prison
The monitoring data for surveying unit transmitting carry out analysis and compare and export, and alarm when there is dangerous situation, when environment changes
It is adjusted, specifically includes as follows:
Monitoring unit is monitored the temperature in monitored region, humidity, PM2.5 concentration and combustable gas concentration；
Processing system receives the monitoring signals transmitted from monitoring unit, and by monitoring signals with it is normal in storage unit
Monitoring state signal obtains representing the monitoring state identifier in monitored region after being compared classification；According to monitored region
Monitoring state identifier determines the monitored matched operating condition in region；
In the absence of monitoring state identifier, then according to neural network model, the operation for institute's monitoring signals is provided
Classification, comprising:
The coding layer for multiple monitoring signals that monitoring unit monitors is configured to neural network model, in neural network
In institute's monitoring signals are parsed and are exported；
When the operating condition in monitored region needs to be adjusted, output result is input in fuzzy controller, is obtained
The output vector group that must indicate adjusting classification exports as answer is adjusted.
Step 1, Step 1: establishing BP mind for network model；
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding
Indicate that n detection signal of equipment working state, these signal parameters are provided by data preprocessing module.The second layer is hidden layer,
Total m node is determined in an adaptive way by the training process of network.Third layer is output layer, total p node, by system
Actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input layer vector: x=(x1,x2,…,xn)T
Middle layer vector: y=(y1,y2,…,ym)T
Output layer vector: z=(z1,z2,…,zp)T
In the present invention, input layer number is n=4, and output layer number of nodes is p=3.Hidden layer number of nodes m is estimated by following formula
It obtains:
4 parameters of input signal respectively indicate are as follows: x1For temperature coefficient, x2For humidity coefficient, x3For PM2.5 concentration factor,
x4For combustable gas concentration coefficient；
Since the data that sensor obtains belong to different physical quantitys, dimension is different.Therefore, people is inputted in data
Before artificial neural networks, need to turn to data requirement into the numerical value between 0-1.
By the temperature T in region to be monitored, humidity RH, PM2.5 concentration CP, combustable gas concentration CKPlace is normalized respectively
Reason normalizes formula are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter: T, RH, CPAnd CK, j=1,2,3,4；
XjmaxAnd XjminMaximum value and minimum value in respectively corresponding measurement parameter
Specifically, after being normalized, obtaining temperature coefficient x for the temperature T in region to be monitored1:
Wherein, TminAnd TmaxThe temperature minimum value and maximum value in region respectively to be monitored.
Likewise, after being normalized, obtaining humidity coefficient x for the humidity RH in region to be monitored2
Likewise, for the PM2.5 concentration C in region to be monitoredPAfter being normalized, PM2.5 concentration factor x is obtained3；
Likewise, for the combustable gas concentration C in region to be monitoredKIt is normalized, obtains combustable gas concentration coefficient
x4；
Output layer vector is expressed as: o={ o1,o2,o3}；Wherein, o1For air-conditioning adjustment factor, o2For air purifier adjusting
Coefficient, o3For emergency alarm
Step 2 carries out BP neural network training.
The sample of training, and the connection between given input node i and hidden layer node j are obtained according to historical empirical data
Weight Wij, hidden node j and output node layer k between connection weight Wjk, the threshold θ of hidden node jj, output node layer k's
Threshold θk、Wij、Wjk、θj、θkIt is the random number between -1 to 1.
In the training process, W is constantly correctedij、WjkValue, until systematic error be less than or equal to anticipation error when, complete mind
Training process through network.
(1) training method
Each subnet is using individually trained method；When training, first have to provide one group of training sample, each of these sample
This, to forming, when all reality outputs of network and its consistent ideal output, is shown to train by input sample and ideal output
Terminate；Otherwise, by correcting weight, keep the ideal output of network consistent with reality output；
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can be concluded
It is as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum when being calculated for n-th,For l layers of j units with it is previous
Connection weight between the unit i of layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) unit i send
Working signal；When i=0, enableFor the threshold value of l layers of j unit.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
And ej(n)=xj(n)-oj(n)；
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training
Input sequence is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow etc.
Problem.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time shorter,
Network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe；
Wherein, J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector,
Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using
The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and
In the case where quantity, system can carry out self study, to constantly improve network performance；
As shown in table 1, given the value of each node in one group of training sample and training process
Each nodal value of 1 training process of table
Step 3: obtained output layer vector is input in fuzzy controller, the vector group for indicating to adjust classification is obtained,
It is specific as follows:
By air-conditioning adjustment factor o1With preset air-conditioning adjustment factorCompare to obtain air-conditioning adjusting deviation signal,
By air purifier adjustment factor o2With preset air purifier adjustment factorCompare to obtain air purifier adjusting
Deviation signal, by alarm index o3With preset air-conditioning alarm indexCompare to obtain alarm deviation signal；
Air-conditioning adjustment factor deviation signal is obtained into air-conditioning by differential calculation and adjusts change rate signal e1, air purifier
Adjustment factor deviation signal e2Air purifier adjustment factor change rate signal is obtained by differential calculation, by deviation signal of alarming
Alarm index change rate signal e is obtained by differential calculation3；
Air-conditioning is adjusted into change rate signal e1, air purifier adjust change rate signal e2And alarm index change rate letter
Number e3Fuzzy controller is inputted after amplification jointly, output adjusts grade I={ I0,I1,I2,I3, wherein I0Normally to transport
Row, I1For level-one adjusting, I2For second level adjusting, I3It for alarm signal, needs to arouse attention, emergency escape is carried out when necessary.
Wherein, e1、e2、e3Actual change range be respectively [- 1,1], [- 1,1], [- 1,1]；Discrete domain be-
6, -5, -4, -3, -2, -1,0,1,2,3,4,5,6 }, the discrete domain of I is { 0,1,2,3 },
Then quantizing factor, then k1=6/1, k2=6/1, k3=6/1；
Ambiguity in definition subset and membership function:
Air-conditioning is adjusted change rate signal and is divided into 7 fringes: PB (honest), PM (center), PS (just small), ZR
(zero), NS (bearing small), NM (in negative), NB (negative big), show that air-conditioning adjusts change rate signal e in conjunction with experience1Subordinating degree function
Table, as shown in table 2
2 air-conditioning of table adjusts change rate signal e1Subordinating degree function table
| e1 | -6 | -5 | -4 | -3 | -2 | -1 | 0 | +1 | +2 | +3 | +4 | +5 | +6 |
| PB | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.4 | 0.8 | 1.0 |
| PM | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.2 | 0.7 | 1.0 | 0.5 | 0.1 |
| PS | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.4 | 1.0 | 0.8 | 0.7 | 0 | 0 |
| ZR | 0 | 0 | 0 | 0 | 0.2 | 0.7 | 1.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| NB | 0 | 0 | 0.3 | 0.6 | 1.0 | 0.8 | 0.5 | 0 | 0 | 0 | 0 | 0 | 0 |
| NM | 0.2 | 0.4 | 1.0 | 0.6 | 0.1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| NS | 1.0 | 0.6 | 0.4 | 0.2 | 0 | 0 | 0 | 0.2 | 0 | 0 | 0 | 0 | 0 |
Air purifier is adjusted change rate signal and is divided into 7 fringes: PB (honest), PM (center), PS (just small),
ZR (zero), NS (are born small), and NM (in negative), NB (negative big) show that air purifier adjusts change rate signal e in conjunction with experience2Person in servitude
Category degree function table, as shown in table 3.
3 air purifier of table adjusts change rate signal e2Subordinating degree function table
| e2 | -6 | -5 | -4 | -3 | -2 | -1 | 0 | +1 | +2 | +3 | +4 | +5 | +6 |
| PB | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.4 | 0.8 | 1.0 |
| PM | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.2 | 0.7 | 1.0 | 0.5 | 0.1 |
| PS | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.4 | 1.0 | 0.8 | 0.7 | 0 | 0 |
| ZR | 0 | 0 | 0 | 0 | 0.2 | 0.7 | 1.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| NB | 0 | 0 | 0.3 | 0.6 | 1.0 | 0.8 | 0.5 | 0 | 0 | 0 | 0 | 0 | 0 |
| NM | 0.2 | 0.4 | 1.0 | 0.6 | 0.1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| NS | 1.0 | 0.6 | 0.4 | 0.2 | 0 | 0 | 0 | 0.2 | 0 | 0 | 0 | 0 | 0 |
Alarm deviation variation rate e3It is divided into three fringes: PB (honest), ZR (zero), NB (negative big), in conjunction with experience mistake
Thermal deviation change rate e3The function table being subordinate to, as shown in table 4
| e3 | -6 | -5 | -4 | -3 | -2 | -1 | 0 | +1 | +2 | +3 | +4 | +5 | +6 |
| PB | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.4 | 0.8 | 1.0 |
| ZR | 0 | 0 | 0 | 0 | 0.2 | 0.7 | 1.0 | 0 | 0 | 0 | 0 | 0 | 0 |
| NS | 1.0 | 0.6 | 0.4 | 0.2 | 0 | 0 | 0 | 0.2 | 0 | 0 | 0 | 0 | 0 |
Fuzzy reasoning process has to carry out complicated matrix operation, and calculation amount is very big, and on-line implement reasoning is difficult to meet
The requirement of control system real-time, the present invention carry out fuzzy reasoning operation using look-up table, and Fuzzy inferential decision is using three inputs
The mode singly exported can sum up the preliminary control rule of fuzzy controller by experience, and fuzzy controller is according to the mould obtained
Paste value carries out defuzzification to output signal, obtains fault level I, seeks fuzzy polling list, since domain is discrete, mould
Paste control is regular and can be expressed as a fuzzy matrix, using single-point fuzzification, show that I control rule is shown in Table 5.
Table 5 is fuzzy control rule table
In another embodiment, the rate of discharge of air-conditioning regulating valve meets:
Wherein, QvFor the setting flow m for adjusting valve outlet3/ h, π are pi, and r is the pipeline half that refrigerant flows through pipeline
Diameter, unit mm, L are refrigerant flow distance, and unit mm, V are the volume of refrigerant fluid reservoir, v0Refrigerant when being initial
Volume, viFor the measurement volume of refrigerant, unit mm3, piFor channel interior pressure, unit Pa, p0For tube outlet pressure
Power, unit Pa, kcFor constriction coefficient, A1For fluid reservoir inlet cross-sectional area, mm2, A2For fluid reservoir liquid outlet cross section
Product, unit mm2, IWThe steady-state current of compressor, unit A, I when to work0The initial current of compressor, unit when work
For A.η is the working efficiency of compressor.
The monitoring data that monitoring unit transmits analyze by BP neural network and compares and exports, when environment changes
It is adjusted, and is classified by fuzzy control to grade is adjusted, alarmed when urgent, regulating effect is good, and precision is high.
It is adjusted by adjusting valve air gate flow to air-conditioning, prevents living environment from changing to healthy shape of living
The influence of condition, enhancing health control consciousness, improves health control efficiency.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (9)
1. a kind of intelligent health management system based on cloud computing characterized by comprising
Monitoring unit；
Processing system is electrically connected with the output end of the monitoring unit；
Storage unit, and the processing system is two-way is electrically connected；
Control unit, input terminal are electrically connected with the output end of the processing system；
Output unit, input terminal are electrically connected with the output end of described control unit；
Alarm unit, input terminal are electrically connected with the output end of described control unit；
Unit is adjusted, input terminal is electrically connected with the output end of described control unit.
2. the intelligent health management system according to claim 1 based on cloud computing, which is characterized in that the monitoring unit
It include: Temperature Humidity Sensor, PM2.5 concentration detection sensor, combustable gas concentration sensor.
3. the intelligent health management system according to claim 2 based on cloud computing, which is characterized in that the adjusting unit
It include: air-conditioning and air purifier.
4. a kind of control method of the intelligent health management system based on cloud computing characterized by comprising
Monitoring unit is monitored the temperature in monitored region, humidity, PM2.5 concentration and combustable gas concentration；
Processing system receives monitoring signals transmit from monitoring unit, and by the normal monitoring in monitoring signals and storage unit
Status signal obtains representing the monitoring state identifier in monitored region after being compared classification；According to the monitoring in monitored region
Status identifier determines the monitored matched operating condition in region；
In the absence of monitoring state identifier, then according to neural network model, the operation classification for institute's monitoring signals is provided,
Include:
The coding layer for monitoring obtained multiple monitoring signals is configured to neural network model, to institute in the neural network
Monitoring signals are parsed and are exported；
Output result is input in fuzzy controller, the output vector group for indicating to adjust classification is obtained, is answered as adjusting
Case output.
5. the control method of the intelligent health management system according to claim 4 based on cloud computing, which is characterized in that institute
Stating neural network model is three layers of BP neural network model, and the specific monitoring process of neural network includes:
Step 1, the temperature T in the monitored region of acquisition, humidity RH, PM2.5 concentration CP, combustable gas concentration CK, and successively by parameter
It is normalized, determines that the input layer vector of three layers of BP neural network is x={ x1,x2,x3,x4}；Wherein, x1For temperature coefficient,
x2For humidity coefficient, x3For PM2.5 concentration factor, x4For combustable gas concentration coefficient；
Step 2, the input layer DUAL PROBLEMS OF VECTOR MAPPING to middle layer, the middle layer vector y={ y1,y2,…,ym}；M is middle layer
Node number；
Step 3 obtains output layer vector o={ o1,o2,o3}；o1For air-conditioning adjustment factor, o2For air purifier adjustment factor,
o3For alarm index.
6. the control method of the intelligent health management system according to claim 5 based on cloud computing, which is characterized in that institute
State the formula that input layer vector is normalized are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter: T, RH, CPAnd CK, j=1,2,3,4；XjmaxWith
XjminMaximum value and minimum value in respectively corresponding measurement parameter.
7. the control method of the intelligent health management system according to claim 6 based on cloud computing, which is characterized in that institute
State middle layer node number m satisfaction:Wherein, n is input layer number, and p is output node layer
Number；The excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
8. the control method of the intelligent health management system according to claim 6 based on cloud computing, which is characterized in that institute
The course of work for stating fuzzy controller includes:
Air-conditioning adjustment factor is obtained into air-conditioning adjusting deviation signal compared with preset air-conditioning adjustment factor, by air purifier tune
Section coefficient obtains air purifier adjusting deviation signal compared with preset air purifier adjustment factor, by alarm index and in advance
If air-conditioning alarm index relatively obtain alarm deviation signal；
Air-conditioning adjusting deviation signal is obtained into air-conditioning by differential calculation and adjusts change rate signal, air purifier adjusting deviation letter
Number obtaining air purifier by differential calculation adjusts change rate signal, and alarm deviation signal is obtained air-conditioning by differential calculation
Adjust change rate signal；
Air-conditioning is adjusted into change rate signal, air purifier adjusts change rate signal and alarm change rate signal is jointly through over-discharge
Fuzzy controller is inputted after big, output adjusts grade.
9. the control method of the intelligent health management system according to claim 8 based on cloud computing, which is characterized in that institute
The rate of discharge for stating air-conditioning regulating valve meets:
Wherein, QvFor the setting flow velocity for adjusting valve outlet, π is pi, and r is the pipeline radius that refrigerant flows through pipeline, and L is system
The flow distance of cryogen, V are the volume of refrigerant fluid reservoir, v0The volume of refrigerant, v when being initialiFor the measurement body of refrigerant
Product, piFor channel interior pressure, p0For tube outlet pressure, kcFor constriction coefficient, A1For fluid reservoir inlet cross-sectional area, A2For
Fluid reservoir liquid outlet cross-sectional area, IWThe steady-state current of compressor, I when to work0The initial current of compressor when work, η are pressure
The working efficiency of contracting machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212870.8A CN109905487A (en) | 2019-03-20 | 2019-03-20 | A kind of intelligent health management system and method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910212870.8A CN109905487A (en) | 2019-03-20 | 2019-03-20 | A kind of intelligent health management system and method based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109905487A true CN109905487A (en) | 2019-06-18 |
Family
ID=66952418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910212870.8A Withdrawn CN109905487A (en) | 2019-03-20 | 2019-03-20 | A kind of intelligent health management system and method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109905487A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110306008A (en) * | 2019-07-23 | 2019-10-08 | 辽宁工业大学 | A kind of on-line monitoring method stage by stage for refining furnace steel-making |
| CN110560948A (en) * | 2019-09-06 | 2019-12-13 | 中国化学工程第六建设有限公司 | High-pressure pipeline welding device and welding method |
| CN110733493A (en) * | 2019-11-22 | 2020-01-31 | 辽宁工业大学 | Power distribution method for hybrid electric vehicles |
| CN113156822A (en) * | 2021-04-22 | 2021-07-23 | 重庆大学 | Thermal error prediction system and thermal error compensation system based on Mist-edge-fog-cloud computing |
| CN113515155A (en) * | 2021-07-12 | 2021-10-19 | 昆明理工大学 | Multi-path intelligent indoor safety detection system and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0477908A (en) * | 1990-07-20 | 1992-03-12 | Mitsubishi Atom Power Ind Inc | Fuzzy control method for temperature control system |
| WO1995011106A1 (en) * | 1993-10-22 | 1995-04-27 | Powerlasers Ltd. | Method and apparatus for real-time control of laser processing of materials |
| CN102589092A (en) * | 2012-03-12 | 2012-07-18 | 山东建筑大学 | Indoor-environment thermal comfort control method based on novel fuzzy controller |
| CN102856910A (en) * | 2012-07-31 | 2013-01-02 | 上海交通大学 | Static compensator (STATCOM) control method based on multi-model fuzzy neural network PI |
| CN103309370A (en) * | 2013-06-01 | 2013-09-18 | 中南林业科技大学 | Incubating room humidity control method based on BP (back-propagation) neural network |
| CN104833154A (en) * | 2015-05-28 | 2015-08-12 | 河海大学常州校区 | Chilled water loop control method based on fuzzy PID and neural internal model |
| CN104999061A (en) * | 2015-07-06 | 2015-10-28 | 湖南红宇耐磨新材料股份有限公司 | Constant-volume casting control method and system for tilting type casting machine |
| CN106406394A (en) * | 2016-08-26 | 2017-02-15 | 张振堂 | Indoor environment monitoring and adjusting system of low-voltage power distribution cabinet |
| CN108519781A (en) * | 2018-03-21 | 2018-09-11 | 北矿机电科技有限责任公司 | A kind of cleaning table intelligent control method |
| CN108922104A (en) * | 2018-09-12 | 2018-11-30 | 吉林建筑大学 | A kind of factory's fire safety monitoring system and its control method |
| CN109186670A (en) * | 2018-09-10 | 2019-01-11 | 湖北众锐智能技术股份有限公司 | A kind of building intellectualization environmental monitoring system |
-
2019
- 2019-03-20 CN CN201910212870.8A patent/CN109905487A/en not_active Withdrawn
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0477908A (en) * | 1990-07-20 | 1992-03-12 | Mitsubishi Atom Power Ind Inc | Fuzzy control method for temperature control system |
| WO1995011106A1 (en) * | 1993-10-22 | 1995-04-27 | Powerlasers Ltd. | Method and apparatus for real-time control of laser processing of materials |
| CN102589092A (en) * | 2012-03-12 | 2012-07-18 | 山东建筑大学 | Indoor-environment thermal comfort control method based on novel fuzzy controller |
| CN102856910A (en) * | 2012-07-31 | 2013-01-02 | 上海交通大学 | Static compensator (STATCOM) control method based on multi-model fuzzy neural network PI |
| CN103309370A (en) * | 2013-06-01 | 2013-09-18 | 中南林业科技大学 | Incubating room humidity control method based on BP (back-propagation) neural network |
| CN104833154A (en) * | 2015-05-28 | 2015-08-12 | 河海大学常州校区 | Chilled water loop control method based on fuzzy PID and neural internal model |
| CN104999061A (en) * | 2015-07-06 | 2015-10-28 | 湖南红宇耐磨新材料股份有限公司 | Constant-volume casting control method and system for tilting type casting machine |
| CN106406394A (en) * | 2016-08-26 | 2017-02-15 | 张振堂 | Indoor environment monitoring and adjusting system of low-voltage power distribution cabinet |
| CN108519781A (en) * | 2018-03-21 | 2018-09-11 | 北矿机电科技有限责任公司 | A kind of cleaning table intelligent control method |
| CN109186670A (en) * | 2018-09-10 | 2019-01-11 | 湖北众锐智能技术股份有限公司 | A kind of building intellectualization environmental monitoring system |
| CN108922104A (en) * | 2018-09-12 | 2018-11-30 | 吉林建筑大学 | A kind of factory's fire safety monitoring system and its control method |
Non-Patent Citations (1)
| Title |
|---|
| 董海鹰: "《智能控制理论及应用》", 30 September 2016 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110306008A (en) * | 2019-07-23 | 2019-10-08 | 辽宁工业大学 | A kind of on-line monitoring method stage by stage for refining furnace steel-making |
| CN110560948A (en) * | 2019-09-06 | 2019-12-13 | 中国化学工程第六建设有限公司 | High-pressure pipeline welding device and welding method |
| CN110733493A (en) * | 2019-11-22 | 2020-01-31 | 辽宁工业大学 | Power distribution method for hybrid electric vehicles |
| CN113156822A (en) * | 2021-04-22 | 2021-07-23 | 重庆大学 | Thermal error prediction system and thermal error compensation system based on Mist-edge-fog-cloud computing |
| CN113515155A (en) * | 2021-07-12 | 2021-10-19 | 昆明理工大学 | Multi-path intelligent indoor safety detection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109905487A (en) | A kind of intelligent health management system and method based on cloud computing | |
| CN109946987A (en) | A kind of life of elderly person environment optimization monitoring method Internet-based | |
| Sun et al. | A Mamdani fuzzy inference approach for assessing ecological security in the Pearl River Delta urban agglomeration, China | |
| Ali et al. | The theory of neutrosophic cubic sets and their applications in pattern recognition | |
| Zhou et al. | A sequential learning algorithm for online constructing belief-rule-based systems | |
| Hamdan et al. | Adaptive neuro-fuzzy inference system (ANFIS) in modelling breast cancer survival | |
| Gehrke et al. | Lifted dynamic junction tree algorithm | |
| Cheng et al. | A new distance for intuitionistic fuzzy sets based on similarity matrix | |
| Aramesh et al. | A general neural and fuzzy-neural algorithm for natural gas flow prediction in city gate stations | |
| Chen et al. | Study on center-of-sets type-reduction of interval type-2 fuzzy logic systems with noniterative algorithms | |
| Hu et al. | Multi-objective deep reinforcement learning for emergency scheduling in a water distribution network | |
| Mayilvaganan et al. | Risk factor analysis to patient based on fuzzy logic control system | |
| Dincer et al. | Fuzzy modeling of performance of counterflow Ranque-Hilsch vortex tubes with different geometric constructions | |
| Toth-Laufer et al. | Conjunction and disjunction operators in neuro-fuzzy risk calculation model simplification | |
| Ma et al. | Traffic flow forecasting research based on Bayesian normalized Elman neural network | |
| CN110109005A (en) | A kind of analog circuit fault test method based on sequential test | |
| Agogino et al. | Integrating neural networks with influence diagrams for power plant monitoring and diagnostics | |
| CN110594187B (en) | Installation and debugging method for large compressor set instrument system | |
| Ahilan et al. | Performance assessment of heat exchanger using intelligent decision making tools | |
| Tóth-Laufer et al. | Interactions handling between the input factors in risk level calculation | |
| Zhao et al. | Fuzzy neural network based scenario features extraction and mapping model for crowd evacuation stability analysis | |
| Castro et al. | Hybrid learning algorithm for interval type-2 fuzzy neural networks | |
| Yang et al. | Application of mamdani fuzzy system amendment on load forecasting model | |
| Ballini et al. | A seasonal streamflow forecasting model using neurofuzzy network | |
| Sharma et al. | Tuberculosis recognition &-it's analysis using adaptive neuro fuzzy inference system-ANFIS |
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: 20190618 |
|
| WW01 | Invention patent application withdrawn after publication |