CN107203662A - Method and device for establishing temperature prediction model of electronic equipment cabin - Google Patents
Method and device for establishing temperature prediction model of electronic equipment cabin Download PDFInfo
- Publication number
- CN107203662A CN107203662A CN201710330777.8A CN201710330777A CN107203662A CN 107203662 A CN107203662 A CN 107203662A CN 201710330777 A CN201710330777 A CN 201710330777A CN 107203662 A CN107203662 A CN 107203662A
- Authority
- CN
- China
- Prior art keywords
- temperature
- model
- mrow
- electronic equipment
- equipment cabin
- 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 38
- 238000003062 neural network model Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 24
- 239000002184 metal Substances 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
Abstract
The invention provides a method and a device for establishing a temperature prediction model of an electronic equipment cabin. Wherein the method comprises the following steps: determining a temperature parameter that affects a temperature of a compartment of the electronic device; acquiring temperature data corresponding to the temperature parameters; inputting the temperature data into a neural network model for training to obtain target parameters of the neural network model, and establishing a temperature prediction model of the electronic equipment cabin according to the target parameters. The device comprises: the device comprises a temperature parameter determining module, a temperature data acquiring module and a temperature prediction model establishing module. The method and the device for establishing the temperature prediction model of the electronic equipment cabin can effectively predict the temperature of each measuring point in the electronic equipment cabin, and have the advantages of small error and high accuracy.
Description
Technical field
The present invention relates to technical field of electronic equipment, and in particular to the temperature prediction model in a kind of electronic equipment cabin is set up
Method and device.
Background technology
With the development of modern science and technology, increasing electronic equipment is used, such as laser, infrared, radar
Electronic equipment.The Performance And Reliability of these electronic equipments has strong dependence to environmental conditions such as temperature, humidity.To protect
Demonstrate,prove these electronic equipments reliably working in drying, cleaning, the environment of proper temperature, it is necessary to the mounting ring in electronic equipment cabin
Border control system, so as to obtain the prediction in electronics bay room about temperature change.
For heat transfer situation in electronics bay room, whether conduction process or Convective Heat Transfer, its governing equation
All it is the nonlinear differential equation, heat transfer relation can be studied using distributed parameter model research method, its feature is:Border
The parameters such as condition, physical parameter, heat transfer and drag evaluation criterion all realize localization, can obtain in electronics bay room more
Plus accurately conduct heat and thermal characteristic, but calculating cost is too high, application surface is narrow.In actual applications, can be by appropriate
Assuming that and simplify, reduce the application difficulty of nonlinear equation, pass through lumped parameter model method and node thermo network and simplify heat transfer
Process, is established for analyzing the linear equation calculated by the heat transfer relation between analysis node, but now will necessarily band
Carry out larger error.
The subject matter that existing research is present is that calculating cost is too high and calculation error is too big.
The content of the invention
To solve problems of the prior art, the temperature prediction model that the present invention provides a kind of electronic equipment cabin is built
Cube method and device.
On the one hand, the embodiments of the invention provide the temperature prediction model method for building up in a kind of electronic equipment cabin, including:
It is determined that the temperature parameter of influence electronic equipment cabin temperature;
Obtain the corresponding temperature data of the temperature parameter;
Temperature data input neural network model is trained, the target ginseng of the neural network model is obtained
Number, and set up according to the target component temperature prediction model in the electronic equipment cabin.
On the other hand, the embodiments of the invention provide the temperature prediction device in a kind of electronic equipment cabin, including:
Temperature parameter determining module, the temperature parameter for determining influence electronic equipment cabin temperature;
Temperature data acquisition module, for obtaining the corresponding temperature data of the temperature parameter;
Temperature prediction model sets up module, for temperature data input neural network model to be trained, obtains
The target component of the neural network model, and set up according to the target component temperature prediction mould in the electronic equipment cabin
Type.
The method for building up and fitting device of the temperature prediction model in the electronic equipment cabin that the present invention is provided can be effectively
The temperature of each measuring point in electronics bay room is predicted, error is smaller, and accuracy is higher.
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 embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 illustrates for the temperature prediction model method for building up flow in a kind of electronic equipment cabin provided in an embodiment of the present invention
Figure;
Fig. 2 is a kind of electronic equipment cabin provided in an embodiment of the present invention heat transfer schematic diagram;
Fig. 3 is a kind of electronic equipment cabin internal thermal resistance network provided in an embodiment of the present invention;
Target component training and temperature prediction model of the Fig. 4 for neural network model provided in an embodiment of the present invention are set up
Schematic flow sheet;
Fig. 5 is Artificial Neural Network Structures schematic diagram provided in an embodiment of the present invention;
Fig. 6 shows for the temperature prediction model method for building up flow in another electronic equipment cabin provided in an embodiment of the present invention
It is intended to;
Fig. 7 is a kind of temperature data handling process schematic diagram provided in an embodiment of the present invention;
Fig. 8 shows for the temperature prediction model method for building up flow in another electronic equipment cabin provided in an embodiment of the present invention
It is intended to;
Fig. 9 is the temperature prediction schematic device in a kind of electronic equipment cabin provided in an embodiment of the present invention;
Figure 10 is the temperature prediction schematic device in another electronic equipment cabin provided in an embodiment of the present invention;
Figure 11 is the temperature prediction schematic device in another electronic equipment cabin provided in an embodiment of the present invention;
Figure 12 is the temperature prediction schematic device in another electronic equipment cabin provided in an embodiment of the present invention;
Figure 13 is the temperature prediction schematic device in another electronic equipment cabin provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 illustrates for the temperature prediction model method for building up flow in a kind of electronic equipment cabin provided in an embodiment of the present invention
Figure, as shown in figure 1, the temperature prediction model method for building up in a kind of electronic equipment cabin, including:
Step 11, the temperature parameter for determining influence electronic equipment cabin temperature;
Step 12, the corresponding temperature data of the acquisition temperature parameter;
Step 13, by the temperature data input neural network model be trained, obtain the neural network model
Target component, and set up according to the target component temperature prediction model in the electronic equipment cabin.
This implementation is further illustrated below by the temperature prediction model method for building up flow in specific electronic equipment cabin
The technical scheme of example.In an experiment, equipment is all upper electric, the electron when keeping electronic equipment cabin local environment temperature-resistant
Equipment cabin leads to cold wind, determines to influence the temperature of electronic equipment cabin temperature respectively for five equipment in electronics bay room
Parameter, then measures the corresponding temperature data of the temperature parameter, and the temperature data for afterwards obtaining measurement is input to nerve net
Network model is trained, and obtains the target component of the neural network model, and setting up the electronics according to the target component sets
The temperature prediction model in standby cabin.
The method for building up of the temperature prediction model in the electronic equipment cabin that the present invention is provided, can effectively predict that electronics is set
The temperature of each measuring point in standby cabin, error is smaller, and accuracy is higher.
Further, on the basis of above-described embodiment, when meeting the first preparatory condition, the determination influence electronics is set
The temperature parameter of standby cabin temperature is specifically included:
Determined to influence the first inner wall temperature parameter in the electronic equipment cabin according to the first inner wall temperature model;
Or,
Determined to influence the first air themperature parameter in the electronic equipment cabin according to the first air themperature model;
Or,
Determined to influence the first device temperature parameter in the electronic equipment cabin according to the first device temperature model;
Wherein, the first inner wall temperature model is:
Tw(n+1)=f1[Ta(n),Tw(n),Te(n),Tf(n)]
Tw(n+1) be the inwall n+1 moment the first temperature, Tw(n) be the inwall n moment second temperature, Tf(n) it is outer wall
3rd temperature at current time, Ta(n) be the air n moment the 4th temperature, Te(n) be the equipment n moment the 5th temperature, f1For
First inner wall temperature function;
The first air themperature model is:
Ta(n+1)=f2[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n)]
Tecs,in(n) for metal box air inlet n moment cold airs the 6th temperature, T1,out(n) it is metal box outlet
7th temperature at the n moment of mouth, f2For the first air themperature function;
The first device temperature model is:
Te(n+1)=f3[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n),Q]
Q is equipment itself heat production, f3For the first device temperature function;
The first inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature and described
5th temperature;
The first air themperature parameter includes the second temperature, the 4th temperature, the 5th temperature, described the
Six temperature and the 7th temperature;
The first device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature, described the
Six temperature, the 7th temperature and the equipment itself heat production.
First preparatory condition is that control volume is placed in a metal box, and metal box has an air inlet, one
Gas outlet.
Specifically, Fig. 2 is a kind of electronic equipment cabin provided in an embodiment of the present invention heat transfer schematic diagram, as shown in Fig. 2 with
Exemplified by equipment 1, control volume is placed in a metal box, and metal box has an air inlet, a gas outlet.In this condition
Under, first have to determine the temperature parameter of influence electronic equipment cabin temperature:Wherein, according to the first inner wall temperature model Tw(n+1)
=f1[Ta(n),Tw(n),Te(n),Tf(n) the inner wall temperature parameter for] determining the influence electronic equipment cabin is respectively Tw(n)、
Tf(n)、Ta(n)、Te(n);Tw(n) be the inwall n moment second temperature, Tf(n) be outer wall current time the 3rd temperature, Ta
(n) it is the temperature of air n moment the 4th, Te(n) it is the temperature of equipment n moment the 5th.According to the first air themperature model Ta(n+1)=
f2[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n) the air themperature parameter point in the influence electronic equipment cabin] is determined
Wei not Tw(n)、Tf(n)、Ta(n)、Te(n)Tecs,inAnd T (n)1,out(n);Tecs,in(n) it is the n moment of metal box air inlet
6th temperature of cold air, T1,out(n) for metal box gas outlet the n moment the 7th temperature.According to the first device temperature mould
Type Te(n+1)=f3[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n), Q], it is determined that influenceing the electronic equipment cabin
The device temperature parameter of device temperature is respectively Tw(n)、Tf(n)、Ta(n)、Te(n)、T1,out(n)、Tecs,inAnd Q, Q are (n)
Itself heat production of equipment 1, can be obtained by Fig. 3 internal thermal resistance networks in a kind of electronic equipment cabin provided in an embodiment of the present invention.
On the basis of above-mentioned steps, the T of equipment 1 in the same time is then measured notw(n)、Tf(n)、Ta(n)、Te(n)、T1,out(n)、Tecs,in
(n) and the corresponding actual temperature datas of Q, obtained T will actually be measured afterwardsw(n)、Tf(n)、Ta(n)、Te(n)、T1,out
(n)、Tecs,in(n) and the corresponding temperature datas of Q are input to neural network model and are trained, the neutral net mould is obtained
The target component of type, the temperature prediction model in the electronic equipment cabin is set up according to the target component.
Further, on the basis of above-described embodiment, when meeting the second preparatory condition, the determination influence electronics is set
The temperature parameter of standby cabin temperature is specifically included:
Determined to influence the second inner wall temperature parameter in the electronic equipment cabin according to the second inner wall temperature model;
Or,
Determined to influence the second air themperature parameter in the electronic equipment cabin according to the second air themperature model;
Or,
Determined to influence the second device temperature parameter in the electronic equipment cabin according to the second device temperature model;
Wherein, the second inner wall temperature model is:
Tw(n+1)=f4[Tw(n),Tf(n),Ta(n),Te(n)]
The second air themperature model is:
Ta(n+1)=f5[Ta(n),Tw(n),Te(n)]
The second device temperature model is:
Te(n+1)=f6[Ta(n),Tw(n),Te(n),Q]
f4For the second inner wall temperature function, f5For the second air themperature function, f6For the second device temperature function;
The second inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature, described the
Five temperature;
The second air themperature parameter includes the second temperature, the 4th temperature and the 5th temperature;
The second device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature and set
Itself standby heat production.
Second preparatory condition is without metal box, the direct contacting electronic equipments cabin of control volume outside control volume.
Specifically, by taking equipment in Fig. 24 as an example, there is no metal box outside control volume, control volume directly contacts electronics and set
In the case of standby cabin, it is first determined the temperature parameter of influence electronic equipment cabin temperature:Wherein, according to the second inner wall temperature mould
Type Tw(n+1)=f4[Tw(n),Tf(n),Ta(n),Te(n)], it is determined that influenceing the inner wall temperature parameter point in the electronic equipment cabin
Wei not Tw(n)、Tf(n)、Ta(n)、Te(n), Tw(n) be the inwall n moment second temperature, Tf(n) it is the of outer wall current time
Three temperature, Ta(n) it is the temperature of air n moment the 4th, Te(n) it is the temperature of equipment n moment the 5th;According to the second air themperature model
Ta(n+1)=f5[Ta(n),Tw(n),Te(n) the air themperature parameter for] determining the influence electronic equipment cabin is respectively Tw
(n)、Ta(n)、Te(n);According to the 3rd device temperature model Te(n+1)=f [Ta(n),Tw(n),Te(n), Q], it is determined that influence institute
State the device temperature parameter respectively T in electronic equipment cabinw(n)、Ta(n)、Te(n) and Q, Q are equipment 4 itself heat production, can be with
Obtained by Fig. 3 internal thermal resistance networks in a kind of electronic equipment cabin provided in an embodiment of the present invention.On the basis of above-mentioned steps, so
After measure not the corresponding T of equipment 4 in the same timew(n)、Tf(n)、Ta(n)、Te(n) and Q actual temperature data, afterwards will be actual
Measure obtained Tw(n)、Tf(n)、Ta(n)、Te(n)、T1,out(n)、Tecs,inAnd the corresponding temperature datas of Q are input to god (n)
It is trained through network model, obtains the target component of the neural network model, the electricity is set up according to the target component
The temperature prediction model in sub- equipment cabin.
The method for building up of the temperature prediction model in the electronic equipment cabin that the present invention is provided, passes through the specific feelings according to equipment
Condition is different, selects corresponding temperature model, can effectively predict the temperature of each measuring point in electronics bay room, error is smaller,
Accuracy is higher.
Target component training and temperature prediction model of the Fig. 4 for neural network model provided in an embodiment of the present invention are set up
Schematic flow sheet, it is as described in Figure 4, further, described that the temperature data is inputted into nerve on the basis of above-described embodiment
Network model is trained, and obtains the target component of the neural network model, and set up the electricity according to the target component
The temperature prediction model in sub- equipment cabin, is specifically included:
The output function φ (x) of step 31, the hidden layer of the calculating neural network model:
Wherein, φ (x) is activation primitive, and x is the temperature data, and w is input layer in network to the weights of hidden layer, b
For the biasing of input layer in network to hidden layer, w and b are with the stochastic variable being distributed;
Step 32, the hidden layer of the neural network model is obtained to the weight beta of output layer:
β=(δTδ+λI)-1δTY
Wherein, λ is a constant amount, and I is unit diagonal matrix, and Y is the label Y=[y of different temperatures1,y2,…yN]T, δ is hidden
Output parameter matrix containing layer, L is that hidden layer number is dimension, and N is data amount check;
The target component is inputted including hidden layer into the weight of output layer, the output parameter matrix of hidden layer, network
The layer biasing of input layer to hidden layer into the weights and network of hidden layer.
Step 33, the temperature prediction model for setting up according to the target component electronic equipment cabin, the temperature are pre-
Surveying model G (x) is:
Wherein, βmFor the weight of the hidden layer to output layer, m is m-th of hidden layer.
Fig. 5 is the schematic diagram of neural network model, as shown in Figure 5.
Specifically, first, environment according to residing for equipment is different, i.e., preparatory condition is different, sets up different temperature models,
The temperature parameter of influence electronic equipment cabin temperature is determined according to different temperatures model;Then the temperature parameter is measured corresponding
True temperature data;Afterwards, by the true temperature data input of acquisition into neural network model, calculate in neural network model
Hidden layer output function φ (x), the weight beta of hidden layer to output layer and the temperature prediction model G in electronic equipment cabin
(x).Wherein, imply the number of plies and 2000 are selected after screening, the weight w and bigoted b of input layer to hidden layer are with the random of distribution
Variable, the random assignment between (- 2,2).These parameters are updated toIn calculate φ (x);Then, it is sharp
With formula β=(δTδ+λI)-1δTY calculates hidden layer to the weight beta of output layer, wherein, λ is a constant amount, value 0.0005, I
For unit diagonal matrix, Y is the label Y=[y of different temperatures1,y2,…yN]T, L is that hidden layer number is dimension, and N is data
Number, δ is the output parameter matrix of hidden layer, is calculated according to the following equation:
Finally, according to hidden layer to the weights of output layer and other target components, including input layer is to the power of hidden layer
Heavy, bigoted and hidden layer output parameter matrix, sets up the temperature prediction model G (x) in the electronic equipment cabin, wherein:
βmFor the weight of the hidden layer to output layer, m is m-th of hidden layer.
The method for building up of the temperature prediction model in the electronic equipment cabin that the present invention is provided, can effectively predict that electronics is set
The temperature of each measuring point in standby cabin, error is smaller, and accuracy is higher.
Fig. 6 shows for the temperature prediction model method for building up flow in another electronic equipment cabin provided in an embodiment of the present invention
It is intended to, as shown in fig. 6, further, it is described to enter temperature data input neural network model on the basis of above-described embodiment
Row training, obtains the target component of the neural network model, and set up the electronic equipment cabin according to the target component
Temperature prediction model before, in addition to:
Step 14, to the temperature data carry out data processing;
The idiographic flow of data processing that carried out to the temperature data is as shown in fig. 7, specifically include:
Step 41, the temperature data to the acquisition carry out wavelet decomposition;
Step 42, to by the small echo processing after temperature data carry out FIR LPFs;
Step 43, down-sampled processing is carried out to the temperature data after the FIR LPFs;
Step 44, to by it is described it is down-sampled after temperature data be normalized;
The normalized is:
Wherein, T is the temperature data, and T_min is the minimum value in the temperature data, and T_max is the temperature number
Maximum in.
Specifically, the temperature prediction model method for building up in another electronic equipment cabin provided in an embodiment of the present invention, such as
Shown in Fig. 6, wherein step 11,12 and step 13 are same as the previously described embodiments, and step is also included between step 12 and step 13
Rapid 14, i.e., data processing is carried out to the temperature data.
In order to clearly explain the embodiment of the present invention, an example is set forth below.First, according to the preparatory condition not
Together, different temperature models are set up, are determined to influence the temperature parameter of electronic equipment cabin temperature by different temperatures model;Measurement is obtained
Take the corresponding temperature data of the temperature parameter;Then the temperature data acquired is carried out at data processing, the data
Reason includes:According to theory of wavelet transformation, 12 layers of wavelet de-noising filtering process are carried out to initial data, wavelet de-noising is filtered
Data reconstruction takes low-limit frequency section, as valid data section;Then 20*16* is used to the temperature data after small echo processing
40 ranks, cut-off frequency carries out FIR low-pass filtering treatments for 0.0001Hz FIR low pass filter;Afterwards to passing through FIR low pass filtereds
The temperature data of ripple processing carries out down-sampled processing, and down-sampled rate is 1:16*60, and intercept the data of appropriate length;It is finally right
Temperature data after down-sampled processing is normalized, that is, utilizes formulaTemperature data is carried out
Normalized.Finally the temperature data input neural network model Jing Guo data processing is trained, the nerve is obtained
The target component of network model, the temperature prediction model in the electronic equipment cabin is set up according to the target component.
The method for building up of the temperature prediction model in the electronic equipment cabin that the present invention is provided, passes through the temperature data to obtaining
Wavelet decomposition, FIR LPFs, down-sampled processing and normalized are carried out, the temperature data can be effectively removed
In noise effect, enabling effectively predict the temperature of each measuring point in electronics bay room, error is smaller, accuracy compared with
It is high.
Fig. 8 shows for the temperature prediction model method for building up flow in another electronic equipment cabin provided in an embodiment of the present invention
It is intended to, as shown in figure 8, further, it is described that the temperature data is inputted into neutral net mould on the basis of above-described embodiment
Type is trained, and obtains the target component of the neural network model, and set up the electronic equipment according to the target component
After the temperature prediction model in cabin, in addition to:
Step 15, the pending temperature data of acquisition, input the temperature prediction model by the pending temperature data, obtain
To temperature prediction value;Calculate the difference of the temperature prediction value and the temperature actual value;If the difference is less than threshold value, really
The fixed temperature prediction model is target temperature forecast model.
Specifically, step 11 described in Fig. 8,12, it is 13 same as the previously described embodiments.The step 15 is specially:Acquisition is treated
Treatment temperature data, that is, obtain actual temperature data, and actual temperature data then is input into the temperature prediction model G
(x) in, the temperature prediction value of subsequent time is obtained, then, the temperature prediction value is contrasted with the temperature actual value,
Calculate the difference of the two;If the difference is less than default threshold value, it is determined that the temperature prediction model G (x) is target temperature
Spend forecast model.
The method for building up of the temperature prediction model in the electronic equipment cabin that the present invention is provided, by by temperature prediction value with temperature
Degree actual value is contrasted, and obtained temperature prediction model is verified, can effectively be predicted each in electronics bay room
The temperature of measuring point, error is smaller, and accuracy is higher.
Fig. 9 is the temperature prediction schematic device in a kind of electronic equipment cabin provided in an embodiment of the present invention, such as Fig. 9 institutes
Show, the temperature prediction device in a kind of electronic equipment cabin, including temperature parameter determining module 91, the and of temperature data acquisition module 92
Temperature prediction model sets up module 93, wherein:
Temperature parameter determining module 91, the temperature parameter for determining influence electronic equipment cabin temperature;
Temperature data acquisition module 92, for obtaining the corresponding temperature data of the temperature parameter;
Temperature prediction model sets up module 93, for temperature data input neural network model to be trained, obtains
To the target component of the neural network model, and set up according to the target component temperature prediction in the electronic equipment cabin
Model.
Specifically, in an experiment, equipment is all upper electric, when keeping electronic equipment cabin local environment temperature-resistant to electricity
Sub- equipment cabin leads to cold wind, for five equipment in electronics bay room, and temperature parameter determining module 91 determines influence respectively
The temperature parameter of each electronic equipment cabin temperature, then, it is corresponding that temperature data acquisition module 92 measures the temperature parameter
Temperature data, afterwards temperature prediction model set up module 93 by measure obtain temperature data input neural network model instructed
Practice, obtain the target component of the neural network model, the temperature in the electronic equipment cabin is set up according to the target component
Forecast model.
The temperature prediction device in the electronic equipment cabin that the present invention is provided, can effectively be predicted each in electronics bay room
The temperature of measuring point, error is smaller, and accuracy is higher.
Figure 10 illustrates for the temperature prediction model fitting device in another electronic equipment cabin provided in an embodiment of the present invention
Figure, as shown in Figure 10, further, on the basis of above-described embodiment, when meeting the first preparatory condition, the temperature parameter
Determining module 91 is specifically included:
First inner wall temperature parameter determination submodule 911, for being determined to influence the electricity according to the first inner wall temperature model
The inner wall temperature parameter in sub- equipment cabin;
First air themperature parameter determination module 912, for being determined to influence the electricity according to the first air themperature model
The air themperature parameter in sub- equipment cabin;
First device temperature parameter determination module 913, for being determined to influence the electricity according to the first device temperature model
The device temperature parameter in sub- equipment cabin;
Wherein, the first inner wall temperature model is:
Tw(n+1)=f1[Ta(n),Tw(n),Te(n),Tf(n)]
Tw(n+1) be the inwall n+1 moment the first temperature, Tw(n) be the inwall n moment second temperature, Tf(n) it is outer wall
3rd temperature at current time, Ta(n) be the air n moment the 4th temperature, Te(n) be the equipment n moment the 5th temperature, f1For
First inner wall temperature function;
The first air themperature model is:
Ta(n+1)=f2[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n)]
Tecs,in(n) for metal box air inlet n moment cold airs the 6th temperature, T1,out(n) it is metal box outlet
7th temperature at the n moment of mouth, f2For the first air themperature function;
The first device temperature model is:
Te(n+1)=f3[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n),Q]
Q is equipment itself heat production, f3For the first device temperature function;
The first inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature and described
5th temperature;
The first air themperature parameter includes the second temperature, the 4th temperature, the 5th temperature, described the
Six temperature and the 7th temperature;
The first device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature, described the
Six temperature, the 7th temperature and the equipment itself heat production;
First preparatory condition is that control volume is placed in a metal box, and metal box has an air inlet, one
Gas outlet.
Further, on the basis of above-described embodiment, when meeting the second preparatory condition, the temperature parameter determining module
Specifically include:Second inner wall temperature parameter determination submodule, the second air themperature parameter determination submodule and the second equipment temperature
Parameter determination submodule is spent, wherein:
Second inner wall temperature parameter determination module, for being determined to influence the electronic equipment according to the second inner wall temperature model
The inner wall temperature parameter in cabin;
Second air themperature parameter determination module, for being determined to influence the electronic equipment according to the second air themperature model
The air themperature parameter in cabin;
Second device temperature parameter determination module, for being determined to influence the electronic equipment according to the second device temperature model
The device temperature parameter in cabin;
Wherein, the second inner wall temperature model is:
Tw(n+1)=f4[Tw(n),Tf(n),Ta(n),Te(n)]
The second air themperature model is:
Ta(n+1)=f5[Ta(n),Tw(n),Te(n)]
The second device temperature model is:
Te(n+1)=f6[Ta(n),Tw(n),Te(n),Q]
f4For the second inner wall temperature function, f5For the second air themperature function, f6For the second device temperature function;
The second inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature, described the
Five temperature;
The second air themperature parameter includes the second temperature, the 4th temperature and the 5th temperature;
The second device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature and set
Itself standby heat production.
Second preparatory condition is without metal box, the direct contacting electronic equipments cabin of control volume outside control volume.
Device provided in an embodiment of the present invention, its function is referring in particular to above method embodiment, and here is omitted.
The temperature prediction device in the electronic equipment cabin that the present invention is provided, choosing different by the concrete condition according to equipment
Select corresponding temperature model, can effectively predict the temperature of each measuring point in electronics bay room, error is smaller, accuracy compared with
It is high.
Figure 11 is the temperature prediction model fitting device in another electronic equipment cabin provided in an embodiment of the present invention, is such as schemed
Shown in 11, on the basis of above-described embodiment, the temperature prediction model, which sets up module 93, includes output function calculating sub module
931st, Weight Acquisition submodule 932 and temperature prediction model setting up submodule 933, wherein:
Output function computing module 931, the output function φ of the hidden layer for calculating the neural network model
(x):
Wherein, φ (x) is activation primitive, and x is the temperature data, and w is input layer in network to the weights of hidden layer, b
For the biasing of input layer in network to hidden layer, w and b are with the stochastic variable being distributed;
Weight Acquisition submodule 932, for obtaining the hidden layer of the neural network model to the weight beta of output layer:
β=(δTδ+λI)-1δTY
Wherein, λ is a constant amount, and I is unit diagonal matrix, and Y is the label Y=[y of different temperatures1,y2,…yN]T, δ is hidden
Output parameter matrix containing layer, L is that hidden layer number is dimension, and N is data amount check.
Temperature prediction model setting up submodule 933, for setting up temperature prediction model G (x):
Wherein, βmFor the weight of the hidden layer to output layer, m is m-th of hidden layer.
The temperature prediction device in the electronic equipment cabin that the present invention is provided, can effectively be predicted each in electronics bay room
The temperature of measuring point, error is smaller, and accuracy is higher.
Figure 12 is the temperature prediction model fitting device in another electronic equipment cabin provided in an embodiment of the present invention, is such as schemed
Shown in 12, on the basis of above-described embodiment, the temperature data acquisition module 92 sets up module with the temperature prediction model
Between 93, in addition to temperature data processing module 94;
Temperature data processing module 94, data processing is carried out for the temperature data to the acquisition;Wherein, the temperature
Data processing module 94 is specifically included:
Small echo handles submodule 941, and wavelet decomposition is carried out for the temperature data to the acquisition;
FIR LPFs submodule 942, for carrying out FIR to the temperature data handled by the small echo processing module
LPF;
Down-sampled processing module 943, for being dropped to the temperature data handled by the FIR low-pass filtering modules
Sampling processing;
Normalized module 944, for returning to the temperature data by the down-sampled processing module processing
One change is handled;
The normalized is:
Wherein, T is the temperature data, and T_min is the minimum value in the temperature data, and T_max is the temperature number
Maximum in.
The temperature prediction device in the electronic equipment cabin that the present invention is provided, by setting temperature data processing module to acquisition
Temperature data carry out wavelet decomposition, FIR LPFs, down-sampled processing and normalized so that temperature data is made an uproar
Sound is reduced so that the temperature error of each measuring point is smaller in prediction electronics bay room, and accuracy is higher.
Figure 13 is fitted schematic device for the temperature prediction model in a kind of electronic equipment cabin provided in an embodiment of the present invention,
As shown in figure 13, on the basis of above-described embodiment, described device also includes temperature comparisons' module 95;
Temperature comparisons' module 95, for obtaining pending temperature data, the temperature is inputted by the pending temperature data
Forecast model is spent, temperature prediction value is obtained;Calculate the difference of the temperature prediction value and the temperature actual value;If the difference
Less than threshold value, it is determined that the temperature prediction model is target temperature forecast model;
Device provided in an embodiment of the present invention, its function is referring in particular to above method embodiment, and here is omitted.
The temperature prediction device in the electronic equipment cabin that the present invention is provided, by the way that temperature prediction value is entered with temperature actual value
Row contrast, verifies to obtained temperature prediction model, can effectively predict the temperature of each measuring point in electronics bay room,
Error is smaller, and accuracy is higher.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that:It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic;
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. the method for building up of the temperature prediction model in a kind of electronic equipment cabin, it is characterised in that including:
It is determined that the temperature parameter of influence electronic equipment cabin temperature;
Obtain the corresponding temperature data of the temperature parameter;
Temperature data input neural network model is trained, the target component of the neural network model is obtained, and
The temperature prediction model in the electronic equipment cabin is set up according to the target component.
2. method according to claim 1, it is characterised in that described to be instructed temperature data input neural network model
Practice, obtain the target component of the neural network model, specifically include:
Calculate the output function φ (x) of the hidden layer of the neural network model:
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mi>x</mi>
<mo>+</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
</mrow>
</msup>
</mrow>
</mfrac>
</mrow>
Wherein, φ (x) be activation primitive, x be the temperature data, w be network in input layer to the weights of hidden layer, b is net
Input layer is to the biasing of hidden layer in network, and w and b are with the stochastic variable being distributed;
The hidden layer of the neural network model is obtained to the weight beta of output layer:
β=(δTδ+λI)-1δTY
Wherein, λ is a constant amount, and I is unit diagonal matrix, and Y is the label Y=[y of different temperatures1,y2,…yN]T, δ is hidden layer
Output parameter matrix, L be hidden layer number be dimension, N is data amount check;
The target component is arrived including hidden layer input layer into the weight of output layer, the output parameter matrix of hidden layer, network
Biasing of the input layer to hidden layer in the weights and network of hidden layer.
3. method according to claim 2, it is characterised in that described that the electronic equipment is set up according to the target component
The temperature prediction model in cabin, is specifically included:
The temperature prediction model G (x) is:
<mrow>
<mi>G</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>m</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>L</mi>
</munderover>
<msub>
<mi>&beta;</mi>
<mi>m</mi>
</msub>
<mi>&delta;</mi>
<mrow>
<mo>(</mo>
<msubsup>
<mi>w</mi>
<mi>m</mi>
<mi>T</mi>
</msubsup>
<mi>x</mi>
<mo>+</mo>
<msub>
<mi>b</mi>
<mi>m</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein, βmFor the weight of the hidden layer to output layer, m is m-th of hidden layer.
4. according to the method described in claim 1, it is characterised in that the temperature ginseng for determining influence electronic equipment cabin temperature
Number, is specifically included:
Determined to influence the first inner wall temperature parameter in the electronic equipment cabin according to the first inner wall temperature model;
Or,
Determined to influence the first air themperature parameter in the electronic equipment cabin according to the first air themperature model;
Or,
Determined to influence the first device temperature parameter in the electronic equipment cabin according to the first device temperature model;
Wherein, the first inner wall temperature model is:
Tw(n+1)=f1[Ta(n),Tw(n),Te(n),Tf(n)]
Tw(n+1) be the inwall n+1 moment the first temperature, Tw(n) be the inwall n moment second temperature, Tf(n) it is that outer wall is current
3rd temperature at moment, Ta(n) be the air n moment the 4th temperature, Te(n) be the equipment n moment the 5th temperature, f1For first
Inner wall temperature function;
The first air themperature model is:
Ta(n+1)=f2[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n)]
Tecs,in(n) for metal box air inlet n moment cold airs the 6th temperature, T1,out(n) it is metal box gas outlet
7th temperature at n moment, f2For the first air themperature function;
The first device temperature model is:
Te(n+1)=f3[Ta(n),Tw(n),Te(n),Tecs,in(n),T1,out(n),Q]
Q is equipment itself heat production, f3For the first device temperature function;
The first inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature and the described 5th
Temperature;
The first air themperature parameter includes the second temperature, the 4th temperature, the 5th temperature, the 6th temperature
Degree and the 7th temperature;
The first device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature, the 6th temperature
Degree, the 7th temperature and the equipment itself heat production.
5. method according to claim 4, it is characterised in that the temperature ginseng of the determination influence electronic equipment cabin temperature
Number, is specifically included:
Determined to influence the second inner wall temperature parameter in the electronic equipment cabin according to the second inner wall temperature model;
Or,
Determined to influence the second air themperature parameter in the electronic equipment cabin according to the second air themperature model;
Or,
Determined to influence the second device temperature parameter in the electronic equipment cabin according to the second device temperature model;
Wherein, the second inner wall temperature model is:
Tw(n+1)=f4[Tw(n),Tf(n),Ta(n),Te(n)]
The second air themperature model is:
Ta(n+1)=f5[Ta(n),Tw(n),Te(n)]
The second device temperature model is:
Te(n+1)=f6[Ta(n),Tw(n),Te(n),Q]
f4For the second inner wall temperature function, f5For the second air themperature function, f6For the second device temperature function;
The second inner wall temperature parameter includes the second temperature, the 3rd temperature, the 4th temperature, the 5th temperature
Degree;
The second air themperature parameter includes the second temperature, the 4th temperature and the 5th temperature;
The second device temperature parameter includes the second temperature, the 4th temperature, the 5th temperature and equipment certainly
Body heat production.
6. method according to claim 1, it is characterised in that described to be instructed temperature data input neural network model
Practice, obtain the target component of the neural network model, and set up according to the target component temperature in the electronic equipment cabin
Spend before forecast model, in addition to:
Wavelet decomposition, LPF, down-sampled processing and normalized are carried out to the temperature data successively;
The normalized is:
<mrow>
<mi>n</mi>
<mi>o</mi>
<mi>r</mi>
<mi>m</mi>
<mo>=</mo>
<mfrac>
<mrow>
<mi>T</mi>
<mo>-</mo>
<mi>T</mi>
<mo>_</mo>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
<mrow>
<mi>T</mi>
<mo>_</mo>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
<mo>-</mo>
<mi>T</mi>
<mo>_</mo>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</mfrac>
</mrow>
Wherein, T is the temperature data, and T_min is the minimum value in the temperature data, and T_max is in the temperature data
Maximum.
7. according to the method described in claim 1, it is characterised in that described to enter temperature data input neural network model
Row training, obtains the target component of the neural network model, and set up the electronic equipment cabin according to the target component
Temperature prediction model after, in addition to:
Pending temperature data is obtained, the pending temperature data is inputted into the temperature prediction model, temperature prediction is obtained
Value;Calculate the difference of the temperature prediction value and the temperature actual value;If the difference is less than threshold value, it is determined that the temperature
Forecast model is target temperature forecast model.
8. the temperature prediction device in a kind of electronic equipment cabin, it is characterised in that including:
Temperature parameter determining module, the temperature parameter for determining influence electronic equipment cabin temperature;
Temperature data acquisition module, for obtaining the corresponding temperature data of the temperature parameter;
Temperature prediction model sets up module, for temperature data input neural network model to be trained, obtains described
The target component of neural network model, and set up according to the target component temperature prediction model in the electronic equipment cabin.
9. device according to claim 8, it is characterised in that the temperature prediction model, which sets up module, to be included:
Output function calculating sub module, the output function φ (x) of the hidden layer for calculating the neural network model:
<mrow>
<mi>&phi;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mi>w</mi>
<mi>x</mi>
<mo>+</mo>
<mi>b</mi>
<mo>)</mo>
</mrow>
</mrow>
</msup>
</mrow>
</mfrac>
</mrow>
Wherein, φ (x) be activation primitive, x be the temperature data, w be network in input layer to the weights of hidden layer, b is net
Input layer is to the biasing of hidden layer in network, and w and b are with the stochastic variable being distributed;
Weight Acquisition submodule, for obtaining the hidden layer of the neural network model to the weight beta of output layer:
β=(δTδ+λI)-1δTY
Wherein, λ is a constant amount, and I is unit diagonal matrix, and Y is the label Y=[y of different temperatures1,y2,…yN]T, δ is hidden layer
Output parameter matrix, L be hidden layer number be dimension, N is data amount check.
10. device according to claim 8, it is characterised in that described device also includes:
Temperature comparisons' module, for obtaining pending temperature data, the temperature prediction is inputted by the pending temperature data
Model, obtains temperature prediction value;Calculate the difference of the temperature prediction value and the temperature actual value;If the difference is less than threshold
Value, it is determined that the temperature prediction model is target temperature forecast model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710330777.8A CN107203662A (en) | 2017-05-11 | 2017-05-11 | Method and device for establishing temperature prediction model of electronic equipment cabin |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710330777.8A CN107203662A (en) | 2017-05-11 | 2017-05-11 | Method and device for establishing temperature prediction model of electronic equipment cabin |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107203662A true CN107203662A (en) | 2017-09-26 |
Family
ID=59905630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710330777.8A Pending CN107203662A (en) | 2017-05-11 | 2017-05-11 | Method and device for establishing temperature prediction model of electronic equipment cabin |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107203662A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108133085A (en) * | 2017-12-08 | 2018-06-08 | 北方工业大学 | Method and system for predicting equipment temperature in electronic equipment cabin |
CN109583585A (en) * | 2018-11-22 | 2019-04-05 | 西安热工研究院有限公司 | A kind of station boiler wall temperature prediction neural network model |
CN109598371A (en) * | 2018-11-21 | 2019-04-09 | 北京航空航天大学 | A kind of aircraft carries the temperature predicting method and system of electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1132562A (en) * | 1993-10-04 | 1996-10-02 | 乔冶亚技术研究公司 | Learning neural network and method thereof |
CN103322646A (en) * | 2013-06-13 | 2013-09-25 | 浙江工业大学 | Return cooling water temperature predictive control method for central air conditioner |
-
2017
- 2017-05-11 CN CN201710330777.8A patent/CN107203662A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1132562A (en) * | 1993-10-04 | 1996-10-02 | 乔冶亚技术研究公司 | Learning neural network and method thereof |
CN103322646A (en) * | 2013-06-13 | 2013-09-25 | 浙江工业大学 | Return cooling water temperature predictive control method for central air conditioner |
Non-Patent Citations (7)
Title |
---|
DIRK HUSMEIER等: "《Neural Networks for Predicting Conditional Probability Densities:Improved Training Scheme Combining EM and RVFL》", 《NEURAL NETWORKS》 * |
SIMONE SCARDAPANE 等: ""Distributed learning for Random Vector Functional-Link"", 《INFORMATION SCIENCES》 * |
WEIDAI等: ""Particle size estimate of grinding processes using random vector functional link networks with improved robustness"", 《NEUROCOMPUTING》 * |
YASMINE KORTEBY等: "《Implementation of an artificial neural network as a PAT tool for the prediction of temperature distribution within a pharmaceutical fluidized bed granulator》", 《EUROPEAN JOURNAL OF PHAMACEUTICAL SCIENCES》 * |
赵晋明: "《一种基于随机映射的网络状态评估方法》", 《电信科学》 * |
陈立平 等: "《基于BP神经网络模型的温度预测方法》", 《沙洲职业工学院学报》 * |
马占龙 等: ""基于有限元及神经网络的磨削温度仿真预测"", 《电子测量与仪器学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108133085A (en) * | 2017-12-08 | 2018-06-08 | 北方工业大学 | Method and system for predicting equipment temperature in electronic equipment cabin |
CN108133085B (en) * | 2017-12-08 | 2021-12-07 | 北方工业大学 | Method and system for predicting equipment temperature in electronic equipment cabin |
CN109598371A (en) * | 2018-11-21 | 2019-04-09 | 北京航空航天大学 | A kind of aircraft carries the temperature predicting method and system of electronic equipment |
CN109598371B (en) * | 2018-11-21 | 2021-02-02 | 北京航空航天大学 | Temperature prediction method and system for electronic equipment on aircraft |
CN109583585A (en) * | 2018-11-22 | 2019-04-05 | 西安热工研究院有限公司 | A kind of station boiler wall temperature prediction neural network model |
CN109583585B (en) * | 2018-11-22 | 2023-04-18 | 西安热工研究院有限公司 | Construction method of power station boiler wall temperature prediction neural network model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107016236B (en) | Power grid false data injection attack detection method based on nonlinear measurement equation | |
CN104977545B (en) | The state-of-charge method of estimation and system of a kind of electrokinetic cell | |
CN107203662A (en) | Method and device for establishing temperature prediction model of electronic equipment cabin | |
CN106872904A (en) | Lithium battery interior temperature estimation method based on discrete sliding mode observer | |
Kumar et al. | Fuzzy classifier for fault diagnosis in analog electronic circuits | |
CN103808426B (en) | The indirect measurement method of cable core temperature | |
CN109755683A (en) | A kind of battery pack internal temperature method of real-time based on compressive sensing theory | |
Mohammad et al. | Artificial neural network analysis of liquid desiccant dehumidifier performance in a solar hybrid air-conditioning system | |
US20230022649A1 (en) | Method, apparatus and program product for predicting multiaxial fatigue life | |
CN106126783A (en) | A kind of lithium ion battery becomes time scale model parameter estimation method | |
CN105182141A (en) | Transformer fault detection method and system | |
CN106980044A (en) | A kind of Harmonious Waves in Power Systems current estimation method for adapting to wind power integration | |
CN108133085A (en) | Method and system for predicting equipment temperature in electronic equipment cabin | |
CN108717505A (en) | A kind of solidification thermal process space-time modeling method based on K-RVFL | |
CN104833852A (en) | Power system harmonic signal estimation and measurement method based on artificial neural network | |
CN109040084A (en) | A kind of network flow abnormal detecting method, device, equipment and storage medium | |
CN111781244A (en) | Infrared thermal imaging type coating detection method based on long-term and short-term memory network | |
Astray et al. | Esters flash point prediction using artificial neural networks | |
CN106650060B (en) | Photovoltaic cell internal resistance attenuation coefficient prediction method | |
CN107462836B (en) | Battery parameter online identification method based on randls model | |
Wang et al. | A baseline correction algorithm for Raman spectroscopy by adaptive knots B-spline | |
Mehrabi et al. | A fuzzy virtual temperature sensor for an irradiative enclosure | |
CN106706559B (en) | Measurement method, system and the server of fallen leaves moisture content | |
CN115183884A (en) | Infrared temperature measurement compensation method and device of electric heating cooperative system | |
Galvão et al. | Identification of fractional-order transfer functions using exponentially modulated signals with arbitrary excitation waveforms |
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: 20170926 |