CN104091045B - Predicting method for long-term performance of air conditioner based on BP neural network - Google Patents
Predicting method for long-term performance of air conditioner based on BP neural network Download PDFInfo
- Publication number
- CN104091045B CN104091045B CN201410267716.8A CN201410267716A CN104091045B CN 104091045 B CN104091045 B CN 104091045B CN 201410267716 A CN201410267716 A CN 201410267716A CN 104091045 B CN104091045 B CN 104091045B
- Authority
- CN
- China
- Prior art keywords
- neural network
- air
- long
- conditioning
- input
- 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.)
- Active
Links
Abstract
The invention discloses a predicting method for the long-term performance of an air conditioner based on a BP neural network. The method comprises the following steps: determining the evaluation index of the long-term performance of the air conditioner; obtaining parameter amounts affecting the long-term performance of the air conditioner; preprocessing the data of the parameter amounts; calculating the cooling and heating generation time of the preprocessed parameter amounts in a weighted manner, using the weighted parameters as the input parameters of structure of the BP neural network, namely the input parameters of the prediction of the long-term performance of the air conditioner; determining the structure of the BP neural network; training the BP neural network; inputting the input parameters of the structure of the BP neural network, calculating the output results, namely the predicting values of the long-efficiency performance of the air conditioner, through the trained BP neural network. For the method, the condition that the performance is reduced during the actual usage of the air conditioner is comprehensively considered, the performance of the air conditioner after being used for a long time is accurately predicted, and a reference is also supplied to the development of the energy efficiency standards of the air conditioner.
Description
Technical field
The present invention relates to air-conditioning technical field, the long-acting performance prediction side of the more particularly to a kind of air-conditioning based on BP neural network
Method.
Background technology
At present, two Energy Efficiency Standard GB12021.3-2011 of China's domestic air conditioner《Room air conditioner energy efficiency market
And efficiency grade》And GB21455-2008《Rotating speed controllable type room air conditioner energy efficiency market and efficiency grade》In,
It is EER (Energy Efficiency Ratio) and SEER (seasonal energy efficiency ratio (seer)) respectively for the Energy efficiency evaluation index of such product.But the two standards are only
It is that the power consumption and refrigerating capacity for being determined is evaluated for new product under the operating mode that standard specifies.Some Enterprises are to chase after
High energy efficiency ratio is sought, with space and the state revenue and expenditure subsidy of gaining high profits, is not stinted and is thought highly of using increase heat exchanger area and heat exchange
The mode of amount, although due technical requirement so can be reached in the test process of new product, according to《Household electrical appliance
Safe service life detailed rules and regulations》Regulation, the service life of room air conditioner is 8-10, therefore, product after longtime running, by
Different degrees of decay occurs in the performance of compressor, dispatches from the factory so as to cause to reach in the actual performance with air-conditioner
The performance of state.
In addition, the vaporizer and condenser of air-conditioner, due to there is different degrees of black dirt accumulation, can also reduce product
Performance.And examined according to working standard, it is runnability of the prescribed product under standard condition, but actually used
During, the operating condition of air-conditioner product often deviates the operating mode that standard specifies, or even will also be in exceedingly odious ring
Run under border, so that properties of product deviate the runnability that standard specifies under operating mode, the above can all make produced with air-conditioning
Moral character can be unable to reach test result of the new product under standard condition.
To sum up, the air-conditioner product of prior art does not account for the air-conditioner feelings that performance can decline in actual use
Condition, therefore people need one kind to carrying out more reasonable, more fully evaluation methodology, the method with the lasting energy-conservation of air-conditioner product
Can be to being predicted with the long-acting performance of air-conditioning.
The content of the invention
It is an object of the invention to overcome the shortcoming and deficiency of prior art, there is provided a kind of air-conditioning based on BP neural network
Long-acting performance prediction method.
The purpose of the present invention is realized by following technical scheme：
The long-acting performance prediction method of a kind of air-conditioning based on BP neural network, the step of comprising following order：
S1. the long-acting Performance Evaluating Indexes of air-conditioning are determined；
S2. obtain the parameter amount for affecting the long-acting performance of air-conditioning；
S3. pretreatment is carried out to the ginseng incremental data；
S4. refrigerating/heating time of origin weighted calculation is carried out to the parameter amount through pretreatment, the ginseng after weighted calculation
|input paramete of the number as BP neural network structure, the i.e. long-lasting foreseeable |input paramete of air-conditioning；
S5. determine BP neural network structure；
S6. BP neural network is trained；
S7. the |input paramete of BP neural network structure is input into, output result is calculated by the BP neural network for training, it is defeated
Go out the predictive value that result is the long-acting performance of air-conditioning.
In step S1, the long-acting Performance Evaluating Indexes of described air-conditioningWherein APFoIt is after life-time service
The annual energy resource consumption rate of air-conditioning, APF are the annual energy resource consumption rates of air-conditioning when dispatching from the factory.
Described step S2, the parameter amount for affecting the long-acting performance of air-conditioning are high-temperature refrigeration efficiency attenuation rate, low-temperature heating energy
Effect attenuation rate, specified heat attenuation rate, specified refrigeration attenuation rate；
Described step S3, high-temperature refrigeration efficiency attenuation rate, low-temperature heating efficiency attenuation rate, specified heats attenuation rate, volume
Customize cold attenuation rate high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio are obtained after pretreatment, specified energy is heated
Effect retention ratio, specified refrigeration efficiency retention ratio；
Described step S4, high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio, specified heat efficiency are retained
Rate, specified refrigeration efficiency retention ratio obtain revised 4 after each being corresponded to warm area refrigerating/heating time of origin weighted calculation
Individual new parameter：High-temperature refrigeration influence factor W, low-temperature heating influence factor T, it is specified heat influence factor D, specified refrigeration affect because
Plain A；|input paramete of 4 new parameters as BP neural network structure, the i.e. long-lasting foreseeable |input paramete of air-conditioning.
In step S5, described BP neural network is made up of input layer, hidden layer and output layer, and wherein input layer is by generation
The neuron composition of table input variable, hidden layer is made up of the neuron for representing intermediate variable, and output layer is by representing output result
Neuron composition.
Described input layer, hidden layer, wherein output layer composition three-layer neural network, the letter between input layer and hidden layer
Breath is transmitted by hyperbolic tangent S transmission functions, and the information between hidden layer and output layer is transmitted by linear transmission function.
Described hidden layer, the nodes of its neuron areInput neuron sections of the wherein n for input layer
Points, output neuron nodes of the m for output layer, a is constant.
Described n=4, m=1, a are the constant between 1-10.
Described step S6, specifically comprising following order the step of：
(1) the 80% of total sample air-conditioning number is randomly selected as training sample, remaining 20% used as detection sample；
(2) the BP neural network model that detection sample input training sample is trained, and obtain the detection sample
Corresponding output valve；
(3) judge the output valve with the error of standard output value whether less than preset error value；
(4) if so, then the corresponding node in hidden layer of current BP neural network model, weights and threshold value training are completed
The corresponding node in hidden layer of neutral net, weights and threshold value；
(5) if it is not, then changing node in hidden layer, with training sample re -training BP neural network execution step (2).
The present invention compared with prior art, has the advantage that and beneficial effect：
1st, use comprehensive evaluation value method proposed by the present invention evaluates the performance of air-conditioner, it is contemplated that air-conditioner is actually used
During performance degradation situation, more conform to the actually used situation of air-conditioner.
2nd, the long-acting performance prediction method of BP neural network air-conditioning proposed by the present invention is outstanding self-adaptation nonlinear dynamic
System, improves the long-lasting foreseeable accuracy rate of air-conditioning.
3rd, the present invention considers the different of national different cities cooling and warming time of origin curve and its to household air-conditioner
The impact of decay, improves air-conditioner actual performance to the sensitivity using geographical position.
4th, the present invention on the basis of considering in terms of the above 3 more conforms to the actually used situation of air-conditioner, improves
The long-lasting foreseeable accuracy rate of air-conditioning, to the long-acting performance evaluation of air-conditioner and prediction there is provided effective and feasible method, also for
Future, the formulation of air-conditioning Energy Efficiency Standard was referred to there is provided one.
Description of the drawings
Fig. 1 is the flow chart of the long-acting performance prediction method of the air-conditioning based on BP neural network of the present invention；
It is that, under 4, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 2 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is that, under 5, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 3 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is that, under 6, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 4 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is that, under 7, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 5 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is that, under 8, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 6 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is that, under 9, the actual comprehensive evaluation value of detection sample is comprehensive with prediction in hidden layer node number P that Fig. 7 is Fig. 1 methods describeds
Close evaluation of estimate comparison diagram；
It is, under 10, to detect the actual comprehensive evaluation value of sample and prediction in hidden layer node number P that Fig. 8 is Fig. 1 methods describeds
Comprehensive evaluation value comparison diagram；
It is, under 11, to detect the actual comprehensive evaluation value of sample and prediction in hidden layer node number P that Fig. 9 is Fig. 1 methods describeds
Comprehensive evaluation value comparison diagram；
It is, under 12, to detect the actual comprehensive evaluation value of sample and prediction in hidden layer node number P that Figure 10 is Fig. 1 methods describeds
Comprehensive evaluation value comparison diagram.
Specific embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited
In this.
The long-acting performance prediction method of a kind of air-conditioning based on BP neural network, the step of comprising following order：
S1. determine the long-acting Performance Evaluating Indexes comprehensive evaluation value mathematical model of air-conditioning, the long-acting Performance Evaluating Indexes of air-conditioning are comprehensive
Close evaluation of estimate mathematical model beη is the long-acting Performance Evaluating Indexes comprehensive evaluation value of air-conditioning, APFoBe through
The annual energy resource consumption rate of life-time service (more than 5 years) air-conditioning afterwards, APF is the annual energy resource consumption rate of air-conditioning when dispatching from the factory.Specifically
APF and APFoComputational methods refer to GB/T 21455-2013, will not be described here；
S2. the parameter amount for affecting the long-acting performance of air-conditioning is obtained, taking affects the parameter amount of the long-acting performance of air-conditioning to be respectively high temperature
Refrigeration efficiency attenuation rate, low-temperature heating efficiency attenuation rate, specified heat efficiency attenuation rate, specified refrigeration efficiency attenuation rate；Specifically
Measurement condition is as shown in table 1：
Table 1：Air-conditioner measurement condition
Wherein
High-temperature refrigeration efficiency attenuation rate：When air-conditioner is run under high-temperature load, actual measurement refrigeration efficiency compares EERgWith air-conditioning
The refrigeration efficiency that device is surveyed under specified cooling condition than EER difference with actual measurement refrigeration efficiency than EER ratio；
Low-temperature heating efficiency attenuation rate：When air-conditioner is run under low temperature environment load, heating energy efficiency ratio COP is surveyeddWith
The difference of the heating energy efficiency ratio COP that air-conditioner is surveyed under specified heat pump heating condition with actual measurement heating energy efficiency ratio COP ratio；
Specified heat efficiency attenuation rate：Air-conditioner surveys heating energy efficiency ratio COP Jing after long time runningsIt is real with before operating
Survey the ratio of the difference actual measurement heating energy efficiency ratio COP front with operating of heating energy efficiency ratio COP；
Specified refrigeration efficiency attenuation rate：Jing after long time running, actual measurement refrigeration efficiency compares EER to air-conditionersIt is real with before operating
Survey difference and operate front actual measurement refrigeration efficiency ratio than EER of the refrigeration efficiency than EER；
S3. to affecting the long-acting performance factor of air-conditioning to carry out pretreatment, obtain：P=1-EERg, H=1-COPd, B=1-COPs、F
=1-EERs；Wherein：
P, H, B, F are respectively high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio, specified heat efficiency and retain
Rate, specified refrigeration efficiency retention ratio；
S4. to high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio, specified heat efficiency retention ratio, specified system
Cold energy effect retention ratio carry out refrigerating/heating time of origin weighting, obtain high-temperature refrigeration influence factor W, low-temperature heating influence factor T,
It is specified to heat influence factor D, specified refrigeration influence factor A.Wherein：
W=a1*P (1)
T=a2*H (2)
D=a3*B (3)
A=a4*F (4)
In formula：a1、a2、a3、a4Respectively high-temperature refrigeration, low-temperature heating, it is specified heat, specified refrigeration refrigerating/heating occur
Time weight coefficient,
In formula：It is higher than 35 DEG C of refrigeration time of origin sum for temperature,
It is that temperature heats time of origin sum less than 7 DEG C,
Time of origin sum is heated less than 20 DEG C higher than 7 DEG C for temperature,
For refrigeration time of origin sum of the temperature higher than 27 DEG C less than 35 DEG C；The each temperature of concrete air-conditioner refrigerating/heating
Degree time of origin is shown in GB/T7725-2004；
S5. determine BP neural network structure：BP neural network is made up of input layer, hidden layer and output layer, and input layer has
The neuron composition of input variable is represented, hidden layer is made up of the neuron for representing intermediate variable, and output layer is tied by output is represented
The neuron composition of fruit；
1) choosing input variable includes：High-temperature refrigeration influence factor W, low-temperature heating influence factor T, it is specified heat impact because
Plain D and specified refrigeration influence factor A；
2) it is the comprehensive evaluation value η that can represent the long-acting performance indications of air-conditioning to choose output layer；
3) BP neural network uses the three-layer neural network that hyperbolic tangent S transmission functions and linear transmission function are constituted；
S6.BP neutral nets node in hidden layer determines：
1) in hidden layer, the nodes of neuron existIn the range of choose；N, m and a are input neuron respectively
Nodes, output neuron nodes and constant, in this example, n=4, m=1, a are the constant between 1-10；
2) the 80% of total sample air-conditioner (being shown in Table 2) number is randomly selected as training sample, remaining 20% used as inspection
Test sample sheet；This example total number of samples is 22, and it is training sample to choose 18 samples, and remaining 4 are detection sample；
Table 2：The data tested before all sample cleaning air conditioners
Note：Testing time is 2014
3) the BP neural network model that detection sample input training sample is trained, and obtain the detection sample pair
The output valve answered；
4) judge the output valve with the error of standard output value whether less than preset error value；
5) if so, then the corresponding node in hidden layer of current BP neural network model is the neutral net correspondence that training is completed
Node in hidden layer；
6) if it is not, then changing node in hidden layer, with training sample re -training BP neural network and perform the 3) step；
7), under Fig. 2～Figure 10 is for different hidden layer node number P, detect that the actual comprehensive evaluation value of sample and prediction are comprehensive
Evaluation of estimate comparison diagram, from Fig. 2～Figure 10 it will be seen that when node in hidden layer is 4, predictive value and actual value error
Minimum, so node in hidden layer is defined as 4；
S7.BP neural metwork trainings：With whole sample air-conditioning data to determining the BP nerve net of structure and nodes
Network is trained, and weights and threshold value are preserved at the end of training；
S8. the |input paramete amount of input prediction air-conditioning, calculates output integrated evaluation of estimate by the BP neural network for training,
Prediction terminates.
Above-described embodiment is the present invention preferably embodiment, but embodiments of the present invention not by above-described embodiment
Limit, other any spirit without departing from the present invention and the change, modification, replacement made under principle, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (7)
1. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network, it is characterised in that the step of comprising following order：
S1. the long-acting Performance Evaluating Indexes of air-conditioning are determined；
The long-acting Performance Evaluating Indexes of described air-conditioningWherein APFoIt is the annual energy of the air-conditioning after life-time service
Consumption rate, APF are the annual energy resource consumption rates of air-conditioning when dispatching from the factory；
S2. obtain the parameter amount for affecting the long-acting performance of air-conditioning；
S3. pretreatment is carried out to the ginseng incremental data；
S4. refrigerating/heating time of origin weighted calculation is carried out to the parameter amount through pretreatment, the parameter after weighted calculation is made
For the long-lasting foreseeable |input paramete of the |input paramete of BP neural network structure, i.e. air-conditioning；
S5. determine BP neural network structure；
S6. BP neural network is trained；
S7. the |input paramete of BP neural network structure is input into, output result, output knot is calculated by the BP neural network for training
Fruit is the predictive value of the long-acting performance of air-conditioning.
2. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 1, it is characterised in that：
Described step S2, the parameter amount for affecting the long-acting performance of air-conditioning be high-temperature refrigeration efficiency attenuation rate, low-temperature heating efficiency attenuation rate,
It is specified to heat attenuation rate, specified refrigeration attenuation rate；
Described step S3, high-temperature refrigeration efficiency attenuation rate, low-temperature heating efficiency attenuation rate, specified heats attenuation rate, specified system
Cold attenuation rate obtains high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio, specified heat efficiency after pretreatment and stays
Deposit rate, specified refrigeration efficiency retention ratio；
Described step S4, high-temperature refrigeration efficiency retention ratio, low-temperature heating efficiency retention ratio, specified heat efficiency retention ratio, volume
Determine to obtain revised 4 after refrigeration efficiency retention ratio is each corresponded to warm area refrigerating/heating time of origin weighted calculation newly
Parameter：High-temperature refrigeration influence factor W, low-temperature heating influence factor T, specified heat influence factor D, specified refrigeration influence factor A；
|input paramete of 4 new parameters as BP neural network structure, the i.e. long-lasting foreseeable |input paramete of air-conditioning.
3. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 1, it is characterised in that：
In step S5, described BP neural network is made up of input layer, hidden layer and output layer, and wherein input layer is become by input is represented
The neuron composition of amount, hidden layer are made up of the neuron for representing intermediate variable, and output layer is by the neuron for representing output result
Composition.
4. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 3, it is characterised in that：
Described input layer, hidden layer, output layer composition three-layer neural network, wherein the information between input layer and hidden layer is by hyperbolic
Line tangent S transmission functions are transmitted, and the information between hidden layer and output layer is transmitted by linear transmission function.
5. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 3, it is characterised in that：
Described hidden layer, the nodes of its neuron areInput neuron node numbers of the wherein n for input layer, m is
The output neuron nodes of output layer, a is constant.
6. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 5, it is characterised in that：
Described n=4, m=1, a are the constant between 1-10.
7. the long-acting performance prediction method of a kind of air-conditioning based on BP neural network according to claim 1, it is characterised in that：
Described step S6, specifically comprising following order the step of：
(1) the 80% of total sample air-conditioning number is randomly selected as training sample, remaining 20% used as detection sample；
(2) the BP neural network model that detection sample input training sample is trained, and obtain the detection sample correspondence
Output valve；
(3) judge the output valve with the error of standard output value whether less than preset error value；
(4) if so, then the corresponding node in hidden layer of current BP neural network model, weights and threshold value are the nerve that training is completed
The corresponding node in hidden layer of network, weights and threshold value；
(5) if it is not, then changing node in hidden layer, with training sample re -training BP neural network execution step (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410267716.8A CN104091045B (en) | 2014-06-16 | 2014-06-16 | Predicting method for long-term performance of air conditioner based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410267716.8A CN104091045B (en) | 2014-06-16 | 2014-06-16 | Predicting method for long-term performance of air conditioner based on BP neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104091045A CN104091045A (en) | 2014-10-08 |
| CN104091045B true CN104091045B (en) | 2017-04-19 |
Family
ID=51638761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410267716.8A Active CN104091045B (en) | 2014-06-16 | 2014-06-16 | Predicting method for long-term performance of air conditioner based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104091045B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104501370B (en) * | 2014-12-02 | 2017-05-24 | 广东美的制冷设备有限公司 | Air conditioner and control method for same |
| CN105890109B (en) * | 2016-03-31 | 2018-09-14 | 华南理工大学 | A kind of room air conditioner long-acting performance detection and optimizing operation method online |
| CN106288157A (en) * | 2016-08-05 | 2017-01-04 | 珠海格力电器股份有限公司 | The evaluation methodology of a kind of unit using effect and device |
| CN106352475A (en) * | 2016-08-23 | 2017-01-25 | 海信（山东）空调有限公司 | Training sample collection method and device of air conditioner neutral network and air conditioning system |
| CN106874581B (en) * | 2016-12-30 | 2021-03-30 | 浙江大学 | Building air conditioner energy consumption prediction method based on BP neural network model |
| CN107273974B (en) * | 2017-05-22 | 2021-06-01 | 浙江鹏信信息科技股份有限公司 | Method and system for constructing safety emergency disposal evaluation system |
| CN108234195B (en) * | 2017-12-08 | 2021-08-31 | 北京市商汤科技开发有限公司 | Method, apparatus, device, medium for predicting network performance |
| CN109323425B (en) * | 2018-11-15 | 2021-05-25 | 广东美的制冷设备有限公司 | Control method and device of air conditioner and readable storage medium |
| WO2020098405A1 (en) * | 2018-11-15 | 2020-05-22 | 广东美的制冷设备有限公司 | Control method for air conditioner, air conditioner and storage medium |
| CN109781447B (en) * | 2019-02-01 | 2021-04-30 | 上海理工大学 | Method for obtaining evolution characteristic of air-conditioning box energy efficiency along with operation age in subway station |
| CN109886448A (en) * | 2019-03-14 | 2019-06-14 | 浙江工业大学 | Using learning rate changing BP neural network and the heat pump multiobjective optimization control method of NSGA-II algorithm |
| CN110656385B (en) * | 2019-10-28 | 2021-01-12 | 季华实验室 | Neural network-based electrostatic spinning fiber average diameter prediction method |
| CN111431184B (en) * | 2020-04-10 | 2021-07-16 | 华南理工大学 | Optimal virtual harmonic resistance control method based on BP neural network algorithm |
| CN111928430A (en) * | 2020-07-27 | 2020-11-13 | 珠海格力电器股份有限公司 | Air conditioner energy efficiency grade determining method and device, computer equipment and storage medium |
| CN113124623B (en) * | 2021-04-26 | 2022-05-10 | 珠海格力电器股份有限公司 | Defrosting control method and device for refrigeration equipment and condensing unit |
| JP2023074821A (en) * | 2021-11-18 | 2023-05-30 | アズビル株式会社 | Information processing apparatus, information processing method, and information processing program |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0835706A (en) * | 1994-07-21 | 1996-02-06 | Hitachi Plant Eng & Constr Co Ltd | Air conditioning heat load predicting system |
| JPH0916555A (en) * | 1995-06-30 | 1997-01-17 | Nec Corp | Demand amount predicting device |
| CN102831478A (en) * | 2012-08-05 | 2012-12-19 | 珠海派诺科技股份有限公司 | Metro energy consumption comprehensive prediction method based on BP neural network |
| CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制系统有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7502768B2 (en) * | 2004-02-27 | 2009-03-10 | Siemens Building Technologies, Inc. | System and method for predicting building thermal loads |
-
2014
- 2014-06-16 CN CN201410267716.8A patent/CN104091045B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0835706A (en) * | 1994-07-21 | 1996-02-06 | Hitachi Plant Eng & Constr Co Ltd | Air conditioning heat load predicting system |
| JPH0916555A (en) * | 1995-06-30 | 1997-01-17 | Nec Corp | Demand amount predicting device |
| CN102831478A (en) * | 2012-08-05 | 2012-12-19 | 珠海派诺科技股份有限公司 | Metro energy consumption comprehensive prediction method based on BP neural network |
| CN102997374A (en) * | 2012-12-31 | 2013-03-27 | 深圳市奥宇控制系统有限公司 | Method and device for forecasting air-conditioning load and air-conditioner |
Non-Patent Citations (5)
| Title |
|---|
| Li Yang et al..The impact of evaporator fouling and fi * |
| ltration on the performance of packaged air conditioners.《International Journal of Refrigeration》.2006,第30卷 * |
| Performance degradation of a vapor compression refrigeration system under fouled conditions;Bilal Ahmed Qureshi et al.;《International Journal of Refrigeration》;20110226;第34卷;1016-1027 * |
| 使用焓差法测试空调APF不确定度计算方法研究;祁伟等;《家电科技》;20140101(第01期);48-50 * |
| 在用空调器持续节能评价方法研究;袁雅青等;《家电科技》;20121001(第10期);40-41 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104091045A (en) | 2014-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104091045B (en) | Predicting method for long-term performance of air conditioner based on BP neural network | |
| Lin et al. | China's building energy efficiency and urbanization | |
| Wang et al. | Multi-criteria building energy performance benchmarking through variable clustering based compromise TOPSIS with objective entropy weighting | |
| CN102818337B (en) | Device for monitoring ground source heat pump system based on internet of things | |
| Gassar et al. | Data-driven approach to prediction of residential energy consumption at urban scales in London | |
| Yu et al. | A systematic procedure to study the influence of occupant behavior on building energy consumption | |
| CN105357691A (en) | LTE (Long Term Evolution) wireless network user sensitive monitoring method and system | |
| Cheung et al. | Simulation of fault impacts for vapor compression systems by inverse modeling. Part I: Component modeling and validation | |
| Kordjamshidi et al. | House rating schemes | |
| CN105973626A (en) | Evaluation and prediction method and apparatus for operation energy efficiency of host of central air-conditioning system | |
| CN110111024A (en) | Scientific and technological achievement market valuation method based on AHP model of fuzzy synthetic evaluation | |
| Vučićević et al. | Assessing the sustainability of the energy use of residential buildings in Belgrade through multi-criteria analysis | |
| CN103617371A (en) | Method for comprehensively evaluating electric energy quality based on grey theory | |
| CN113175700B (en) | Intelligent equipment management and big data early warning analysis system and method for heat supply network | |
| CN110310031A (en) | A kind of power distribution network multidimensional methods of risk assessment | |
| CN105242155A (en) | Transformer fault diagnosis method based on entropy weight method and grey correlation analysis | |
| CN107368940A (en) | Count and respond uncertain temperature control Load aggregation response potential evaluation method and system | |
| CN111046536A (en) | Thermal comfort modeling method based on variable adaptive factors and predicted average voting value | |
| CN104091076B (en) | User electric equipment energy efficiency assessment method based on interval entropy weight method | |
| Wang et al. | Multicriteria decision-making approach for selecting ventilation heat recovery devices based on the attributes of buildings and the preferences of decision makers | |
| Lei et al. | Prediction method of energy consumption for high building based on LMBP neural network | |
| Karatasou et al. | Detection of low-dimensional chaos in buildings energy consumption time series | |
| Kim et al. | Development of flow rate and equipment simulation model for commercial building HVAC&R system by data-driven method | |
| CN109657967A (en) | A kind of confirmation method and system of Transmission Expansion Planning in Electric evaluating indexesto scheme weight | |
| Du et al. | Development and application of hardware-in-the-loop simulation for the HVAC systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |