CN108954680A - A kind of air-conditioning energy consumption prediction technique based on operation data - Google Patents
A kind of air-conditioning energy consumption prediction technique based on operation data Download PDFInfo
- Publication number
- CN108954680A CN108954680A CN201810768210.3A CN201810768210A CN108954680A CN 108954680 A CN108954680 A CN 108954680A CN 201810768210 A CN201810768210 A CN 201810768210A CN 108954680 A CN108954680 A CN 108954680A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- operation data
- subset
- conditioning
- air
- 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
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/20—Heat-exchange fluid temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/50—Load
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/60—Energy consumption
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Combustion & Propulsion (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Mechanical Engineering (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The air-conditioning energy consumption prediction technique based on operation data that the present invention provides a kind of, belongs to central air-conditioning Modeling Research field.The present invention is directed to traditional insoluble nonlinearity central air-conditioning modeling problem of mechanism analysis method and identification method, and the method combined using Boruta feature selecting algorithm and BP neural network predicts air-conditioning energy consumption.Boruta feature selecting algorithm carries out energy consumption characters selection to operation data first, obtains energy consumption characters subset, reduces the energy consumption characters dimension in operation data, and the redundancy of energy consumption characters subset is then reduced using pearson correlation coefficient process;Finally using energy consumption character subset as the input of BP neural network energy consumption model, for central air conditioner system general power as its output, the BP neural network energy consumption prediction model trained is reliable and pervasive, significant to energy saving in running strategy.
Description
Technical field
The invention belongs in central air-conditioning Modeling Research field, in particular to a kind of central air-conditioning energy based on operation data
Consume prediction technique.
Background technique
In central air-conditioning Modeling Research field, passing research work is often from the number for establishing central air conditioner system operational energy efficiency
It learns model to set out, is recognized according to the data model parameters that system operation data carries out each equipment, finally determine central air-conditioning system
System optimization Simulation control strategy, is known as conventional method for this method here.Since central air conditioner system is the mutual pass that intercouples
The operation of connection is whole, its efficiency mathematical model and identification model structure is complicated, and model parameter is difficult to obtain, the machine of conventional method
Reason modeling is difficult.
As the development of cloud database technology has accumulated a large amount of higher-dimensions in the metering of central air conditioner system operation energy consumption
Real time energy consumption data, conventional method are difficult to find and summarize the knowledge that these data contain.Boruta feature in data mining
Selection algorithm is a kind of packaging algorithm of random forest, is that the original energy consumption characters of air-conditioning extract energy consumption characters subset, then uses
Pearson correlation coefficient process reduces the redundancy of energy consumption characters subset, and last this feature subset is as heuristic BP neural network
Input parameter, can effectively predict air-conditioning energy consumption, therefore be of great importance to air-conditioning energy consumption modeling.
Currently, being directed to the difference of each central air conditioner system, central air conditioner system energy consumption characters are also different, lack a set of general
Suitable air-conditioning energy consumption prediction technique.
Summary of the invention
In order to solve the problems, such as to lack in the prior art a set of pervasive air-conditioning energy consumption prediction technique, the present invention is proposed
A kind of air-conditioning energy consumption prediction technique based on operation data.Energy consumption spy is extracted in operation data using boruta algorithm
Subset is levied, the redundancy of energy consumption characters subset is then reduced using pearson correlation coefficient process, it is finally pre- using BP neural network
Survey air-conditioning energy consumption.
A kind of air-conditioning energy consumption prediction technique based on operation data, comprising the following steps:
Step 1, the operation data of central air conditioner system is acquired;
Step 2, collected operation data is pre-processed, obtains energy consumption characters collection;
Step 3, according to the energy consumption characters collection obtained after pretreatment, energy consumption characters subset is extracted;
Step 4, correlation analysis is carried out to energy consumption characters subset, reduces energy consumption characters subset redundancy;
Step 5, described using the energy consumption characters subset after progress correlation analysis as the input parameter of BP neural network
The output parameter of BP neural network is central air conditioner system general power, and the training BP neural network obtains energy consumption prediction model.
Further, the operation data include bypass valve opening, chilled-water flow, rate of load condensate, chilled water discharge pressure,
Chilled water pressure of return water, chilled water leaving water temperature, cooling range, chilled water return water temperature, the chilled water temperature difference, cooling water return water
Temperature, cooling water leaving water temperature, cooling pump frequency, freezing pump frequency and system total power.
Further, the step 2 envelope following below scheme:
Based on collected operation data, is filled up the vacancy value using Lagrange's interpolation, obtain energy consumption characters collection.
Further, the step 3 includes following below scheme:
According to the energy consumption characters collection, energy consumption characters subset is extracted using boruta feature extraction algorithm.
Further, boruta feature extraction algorithm is using the boruta packet in language.
Further, the step 4 includes following below scheme:
The correlation of stochastic variable is measured using pearson related coefficient, solves the multicollinearity of energy consumption characters subset,
Reduce energy consumption characters subset redundancy.
Beneficial effects of the present invention: the air-conditioning energy consumption prediction technique based on operation data that the present invention provides a kind of,
For traditional insoluble nonlinearity central air-conditioning modeling problem of mechanism analysis method and identification method, use
Boruta feature selecting algorithm carries out energy consumption characters selection to original higher-dimension operation data, obtains energy consumption characters subset, reduces
Energy consumption characters dimension in operation data;Then the redundancy of energy consumption characters subset is reduced using pearson correlation coefficient process;Most
Afterwards using energy consumption character subset as the input of BP neural network energy consumption model, air-conditioning system general power should as its output, training
BP neural network model, obtained air conditioning energy consumption model is reliable and pervasive, significant to energy saving in running strategy.
Detailed description of the invention
Fig. 1 is the flow chart of the embodiment of the present invention.
Fig. 2 is boruta feature extraction algorithm importance sorting figure.
Fig. 3 is characterized variable box diagram description figure.
Fig. 4 is BP neural network structure chart.
Fig. 5 is the effect picture of BP neural network air-conditioning energy consumption model prediction model.
Specific embodiment
The embodiment of the present invention is described further with reference to the accompanying drawing.
Referring to Fig. 1, a kind of air-conditioning energy consumption prediction technique based on operation data proposed by the present invention, by following
Step is realized:
Step 1, the operation data of central air conditioner system is acquired.
In the present embodiment, as shown in following table (one), the operation data of acquisition includes bypass valve opening, chilled-water flow, bears
Lotus rate, chilled water discharge pressure, chilled water pressure of return water, chilled water leaving water temperature, cooling range, chilled water return water temperature,
The chilled water temperature difference, cooling water return water temperature, cooling water leaving water temperature, cooling pump frequency, freezing pump frequency and system total power.
Table (one) central air conditioner system operation data characteristic parameter
Step 2, collected operation data is pre-processed, obtains energy consumption characters collection.
In the present embodiment, database is connected in MATLAB, using collected data, is mended using Lagrange's interpolation
Vacancy value is filled, energy consumption characters collection is obtained.
Step 3, according to the energy consumption characters collection obtained after pretreatment, energy consumption characters subset is extracted.
In the preferred embodiment of the present embodiment, energy consumption characters subset, boruta are extracted using boruta feature extraction algorithm
Feature extraction algorithm can be provided by the boruta packet in R language, and the principle is as follows:
Assuming that former feature set is x, mixing copy attribute is created to former feature set x and is gone forward side by side rearrangement, obtain shadow feature set with
The set x of former feature set1.In x1On the basis of training characteristics collection d, the conduct not being drawn into extracted using bootstrap mode
Test feature collection d1It is based on x1The Random Forest model containing m decision tree is constructed, each decision tree is calculated and corresponds to test feature
Collect d1Mean square sesidual MSE (0-M) be based on MSE (0-M) calculate character pair z value, screen the maximum shadow feature of z value, together
When mark the feature bigger than its value, as important feature, and the corresponding feature smaller than its z value is then labeled as insignificant feature simultaneously
It is deleted from former feature set.Finally delete all copy features and inessential feature.
Repeat it is above thus the step of, until reaching the termination condition of setting.
Please refer to Fig. 2 and Fig. 3, boruta characteristic selection result as shown, in figure ShadowMax be shadow feature most
Big different degree, ShadowMean are the average different degree of shadow feature, and ShadowMin is the minimum different degree of shadow feature, cold
Freeze water flow and be slightly above averagely shadow feature scores, labeled as inessential;The ascending sequence of remaining characteristic variable is important
Characteristic variable, i.e. energy consumption character subset are bypass valve opening, rate of load condensate, chilled water discharge pressure, chilled water pressure of return water, freezing
Water leaving water temperature, cooling range, chilled water return water temperature, the chilled water temperature difference, cooling water return water temperature, cooling water go out water temperature
Degree, cooling pump frequency, freezing pump frequency.
Step 4, correlation analysis is carried out to energy consumption characters subset, reduces energy consumption characters subset redundancy.
In the present embodiment, the correlation of energy consumption characters subset is measured using pearson related coefficient, solves energy consumption characters
The multicollinearity of collection reduces energy consumption characters subset redundancy.Pearson related coefficient, that is, Pearson correlation coefficient, it is main to use
Data on two vectors are described whether on one wire, value range is between 0~1.Its expression formula is
In formula: X, Y are the long vectors such as two, and N is vector element number.R is the degree of correlation, it is covariance and two variable marks
The ratio of quasi- difference product is not dimension, standardized covariance.
It obtains shown in correlation matrix such as following table (two), in strong a pair of of the characteristic variable of correlation, in conjunction with boruta
The importance sorting that feature selecting algorithm obtains, different degree is high to be retained, and different degree is low to be removed.Such as: take the degree of correlation
Threshold values is 0.8, and freezing leaving water temperature and the freezing return water temperature degree of correlation are 0.97, and water outlet is freezed in boruta arithmetic result figure
Temperature different degree is higher than freezing return water temperature, therefore deletes freezing return water temperature;Similarly, cooling water outlet temperature and water temperature is cooled back
Spending the degree of correlation is 0.89, and cooling backwater temperature different degree is higher than cooling water outlet temperature in boruta arithmetic result figure, therefore deletes
Except cooling water outlet temperature;Energy consumption characters subset is finally obtained as bypass valve opening, rate of load condensate, chilled water discharge pressure, chilled water
Pressure of return water, chilled water leaving water temperature, cooling range, the chilled water temperature difference, cooling water return water temperature, cooling pump frequency, freezing
Pump frequency.
Table (two) central air conditioner system energy consumption characters subset correlation matrix
Step 5, described using the energy consumption characters subset after progress correlation analysis as the input parameter of BP neural network
The output parameter of BP neural network is central air conditioner system general power, and the training BP neural network obtains energy consumption prediction model.
In the present embodiment, in the input layer of BP neural network, input parameter is sub using the energy consumption characters that feature selecting obtains
Collection, i.e. bypass valve opening, rate of load condensate, chilled water discharge pressure, chilled water pressure of return water, chilled water leaving water temperature, coolant water temperature
Difference, the chilled water temperature difference, cooling water return water temperature, cooling pump frequency, freezing pump frequency;In output layer, output parameter is that system is total
Power;In hidden layer, according to Kolmogorov theorem, intermediate hidden layer neuron number generally takes 2n+1, and wherein n is input layer
Number.Its principle are as follows:
Referring to Fig. 4, input signal XiOutput node is acted on by intermediate node (hidden layer point), by non-thread deformation
It changes, generates output signal Y, each sample of network training includes input vector X and desired throughput t.Network output valve Y and phase
The deviation between output valve t is hoped, by adjusting the linking intensity value W of input node and hidden nodeijWith hidden node with it is defeated
Linking intensity T between egressjAnd threshold value, make error along gradient direction decline, by repetition learning training, determine with most
The corresponding network parameter (weight and threshold value) of small error, training stop stopping.Trained BP neural network can at this time
To the input information of similar sample, the smallest information by non-linear conversion of output error is voluntarily handled.In BP neural network
In, hidden layer node output is Oj=∫ (∑ Wij×Xi-qj), output node layer output is Y=∫ (∑ Tj×Oj), ∫ () in formula
For non-linear action function, reflect lower layer's input to the function of upper layer node boost pulse intensity, also known as stimulation function, q is mind
Through cell threshode.
Referring to Fig. 5, the result of BP neural network air-conditioning energy consumption model prediction model is as shown in the figure.According to having set
Trained maximum frequency of training is set as 100 by the central air conditioner system energy consumption prediction model counted, and the target error of grid is set
It is set to 0.01, non-linear action function selects sigmoid function.3000 groups of training (training) data carry out BP nerve in figure
Network training obtains regression coefficient R=0.99908, (validation) regression coefficient R=after 3000 groups of data cross verifyings
0.99576,90 group of test (test) data is verified to obtain regression coefficient R=0.99119, the trained values of whole samples
It (output) is R=0.99765 with the regression coefficient of target value (target), training effect is ideal.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such specific embodiments and embodiments.This field
Those of ordinary skill disclosed the technical disclosures can make according to the present invention and various not depart from the other each of essence of the invention
The specific variations and combinations of kind, these variations and combinations are still within the scope of the present invention.
Claims (6)
1. a kind of air-conditioning energy consumption prediction technique based on operation data, which comprises the following steps:
Step 1, the operation data of central air conditioner system is acquired;
Step 2, collected operation data is pre-processed, obtains energy consumption characters collection;
Step 3, according to the energy consumption characters collection obtained after pretreatment, energy consumption characters subset is extracted;
Step 4, correlation analysis is carried out to energy consumption characters subset, reduces energy consumption characters subset redundancy;
Step 5, using the energy consumption characters subset after progress correlation analysis as the input parameter of BP neural network, the BP mind
Output parameter through network is central air conditioner system general power, and the training BP neural network obtains energy consumption prediction model.
2. the air-conditioning energy consumption prediction technique based on operation data as described in claim 1, which is characterized in that the operation
Data include by-passing valve aperture, chilled-water flow, rate of load condensate, chilled water discharge pressure, chilled water pressure of return water, chilled water water outlet
Temperature, cooling range, chilled water return water temperature, the chilled water temperature difference, cooling water return water temperature, cooling water leaving water temperature, cooling
Pump frequency, freezing pump frequency and system total power.
3. the air-conditioning energy consumption prediction technique based on operation data as described in claim 1, which is characterized in that the step
2 envelope following below scheme:
Based on collected operation data, is filled up the vacancy value using Lagrange's interpolation, obtain energy consumption characters collection.
4. the air-conditioning energy consumption prediction technique based on operation data as described in claim 1, which is characterized in that the step
3 include following below scheme:
According to the energy consumption characters collection, energy consumption characters subset is obtained using boruta feature selecting algorithm.
5. the air-conditioning energy consumption prediction technique based on operation data as claimed in claim 4, which is characterized in that boruta is special
Extraction algorithm is levied using the boruta packet in R language.
6. the air-conditioning energy consumption prediction technique based on operation data as described in claim 1, which is characterized in that the step
4 include following below scheme:
The correlation of energy consumption characters subset is measured using pearson related coefficient, solves the multicollinearity of energy consumption characters subset,
Reduce energy consumption characters subset redundancy.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810768210.3A CN108954680A (en) | 2018-07-13 | 2018-07-13 | A kind of air-conditioning energy consumption prediction technique based on operation data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810768210.3A CN108954680A (en) | 2018-07-13 | 2018-07-13 | A kind of air-conditioning energy consumption prediction technique based on operation data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108954680A true CN108954680A (en) | 2018-12-07 |
Family
ID=64483295
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810768210.3A Pending CN108954680A (en) | 2018-07-13 | 2018-07-13 | A kind of air-conditioning energy consumption prediction technique based on operation data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108954680A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109855238A (en) * | 2019-02-27 | 2019-06-07 | 四川泰立智汇科技有限公司 | A kind of modeling of central air-conditioning and efficiency optimization method and device |
CN109961177A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | A kind of general water cooled central air conditioner energy consumption prediction technique based on shot and long term memory Recognition with Recurrent Neural Network |
CN109973355A (en) * | 2019-03-29 | 2019-07-05 | 江苏极熵物联科技有限公司 | A kind of energy-saving method towards air compressor |
CN110188143A (en) * | 2019-04-04 | 2019-08-30 | 上海发电设备成套设计研究院有限责任公司 | A kind of power plant Vibration Trouble of Induced Draft Fan diagnostic method |
CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
CN110762768A (en) * | 2019-10-30 | 2020-02-07 | 南京亚派软件技术有限公司 | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system |
CN111859625A (en) * | 2020-06-28 | 2020-10-30 | 五邑大学 | Energy-saving control method and device based on big data and storage medium |
CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
CN112329813A (en) * | 2020-09-29 | 2021-02-05 | 中南大学 | Energy consumption prediction feature extraction method and system |
CN112393390A (en) * | 2020-07-15 | 2021-02-23 | 上海有孚智数云创数字科技有限公司 | Cloud computing data center precision air conditioner energy-saving control method based on data analysis |
CN112747416A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Energy consumption prediction method and device for air conditioning system |
CN113129054A (en) * | 2021-03-30 | 2021-07-16 | 广州博冠信息科技有限公司 | User identification method and device |
CN114165854A (en) * | 2021-11-10 | 2022-03-11 | 武汉理工大学 | Intelligent optimization control method based on dynamic simulation platform of central air conditioning system |
CN114383299A (en) * | 2021-12-22 | 2022-04-22 | 武汉理工大学 | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation |
CN114791160A (en) * | 2022-01-27 | 2022-07-26 | 王艳茜 | Central air conditioner control method and device based on neural network model |
CN115355580A (en) * | 2022-08-16 | 2022-11-18 | 浙江大冲能源科技股份有限公司 | Cold storage system for balance pipe of secondary pump of central air conditioner |
CN115730228A (en) * | 2022-12-05 | 2023-03-03 | 成都迅宏自控设备有限公司 | Central air conditioner energy consumption analysis method based on BP neural network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015155978A1 (en) * | 2014-04-11 | 2015-10-15 | 日本電気株式会社 | Environment control system |
CN105627504A (en) * | 2015-05-28 | 2016-06-01 | 重庆大学 | Energy consumption estimation method for water chilling unit of variable-air-volume central air conditioning system based on support vector machine |
CN106384308A (en) * | 2016-11-16 | 2017-02-08 | 南方电网科学研究院有限责任公司 | Power consumption load data processing method and apparatus for power system |
CN106765932A (en) * | 2016-12-14 | 2017-05-31 | 深圳达实智能股份有限公司 | The Energy Efficiency Ratio Forecasting Methodology and device of central air conditioner system refrigeration host computer |
CN107044710A (en) * | 2016-12-26 | 2017-08-15 | 深圳达实智能股份有限公司 | Energy-saving control method for central air conditioner and system based on joint intelligent algorithm |
-
2018
- 2018-07-13 CN CN201810768210.3A patent/CN108954680A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015155978A1 (en) * | 2014-04-11 | 2015-10-15 | 日本電気株式会社 | Environment control system |
CN105627504A (en) * | 2015-05-28 | 2016-06-01 | 重庆大学 | Energy consumption estimation method for water chilling unit of variable-air-volume central air conditioning system based on support vector machine |
CN106384308A (en) * | 2016-11-16 | 2017-02-08 | 南方电网科学研究院有限责任公司 | Power consumption load data processing method and apparatus for power system |
CN106765932A (en) * | 2016-12-14 | 2017-05-31 | 深圳达实智能股份有限公司 | The Energy Efficiency Ratio Forecasting Methodology and device of central air conditioner system refrigeration host computer |
CN107044710A (en) * | 2016-12-26 | 2017-08-15 | 深圳达实智能股份有限公司 | Energy-saving control method for central air conditioner and system based on joint intelligent algorithm |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109855238A (en) * | 2019-02-27 | 2019-06-07 | 四川泰立智汇科技有限公司 | A kind of modeling of central air-conditioning and efficiency optimization method and device |
CN109961177A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | A kind of general water cooled central air conditioner energy consumption prediction technique based on shot and long term memory Recognition with Recurrent Neural Network |
CN109973355A (en) * | 2019-03-29 | 2019-07-05 | 江苏极熵物联科技有限公司 | A kind of energy-saving method towards air compressor |
CN109973355B (en) * | 2019-03-29 | 2020-05-19 | 江苏极熵物联科技有限公司 | Energy saving and consumption reducing method for air compressor |
CN110188143A (en) * | 2019-04-04 | 2019-08-30 | 上海发电设备成套设计研究院有限责任公司 | A kind of power plant Vibration Trouble of Induced Draft Fan diagnostic method |
CN110674842A (en) * | 2019-08-26 | 2020-01-10 | 明阳智慧能源集团股份公司 | Wind turbine generator main shaft bearing fault prediction method |
CN110762768A (en) * | 2019-10-30 | 2020-02-07 | 南京亚派软件技术有限公司 | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system |
CN112747416A (en) * | 2019-10-31 | 2021-05-04 | 北京国双科技有限公司 | Energy consumption prediction method and device for air conditioning system |
CN112747416B (en) * | 2019-10-31 | 2022-04-05 | 北京国双科技有限公司 | Energy consumption prediction method and device for air conditioning system |
CN111859625A (en) * | 2020-06-28 | 2020-10-30 | 五邑大学 | Energy-saving control method and device based on big data and storage medium |
CN112393390A (en) * | 2020-07-15 | 2021-02-23 | 上海有孚智数云创数字科技有限公司 | Cloud computing data center precision air conditioner energy-saving control method based on data analysis |
CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
CN112329813A (en) * | 2020-09-29 | 2021-02-05 | 中南大学 | Energy consumption prediction feature extraction method and system |
CN113129054A (en) * | 2021-03-30 | 2021-07-16 | 广州博冠信息科技有限公司 | User identification method and device |
CN114165854A (en) * | 2021-11-10 | 2022-03-11 | 武汉理工大学 | Intelligent optimization control method based on dynamic simulation platform of central air conditioning system |
CN114383299A (en) * | 2021-12-22 | 2022-04-22 | 武汉理工大学 | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation |
CN114791160A (en) * | 2022-01-27 | 2022-07-26 | 王艳茜 | Central air conditioner control method and device based on neural network model |
CN115355580A (en) * | 2022-08-16 | 2022-11-18 | 浙江大冲能源科技股份有限公司 | Cold storage system for balance pipe of secondary pump of central air conditioner |
CN115730228A (en) * | 2022-12-05 | 2023-03-03 | 成都迅宏自控设备有限公司 | Central air conditioner energy consumption analysis method based on BP neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108954680A (en) | A kind of air-conditioning energy consumption prediction technique based on operation data | |
CN111476713B (en) | Intelligent weather image identification method and system based on multi-depth convolution neural network fusion | |
CN102323972B (en) | Method for managing phased array radar resource | |
CN104809658B (en) | A kind of rapid analysis method of low-voltage distribution network taiwan area line loss | |
CN109272146A (en) | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network | |
CN105701596A (en) | Method for lean distribution network emergency maintenance and management system based on big data technology | |
CN109598451A (en) | A kind of non-intrusion type load discrimination method based on PCA Yu LSTM neural network | |
CN108446794A (en) | One kind being based on multiple convolutional neural networks combination framework deep learning prediction techniques | |
CN105260738A (en) | Method and system for detecting change of high-resolution remote sensing image based on active learning | |
CN104523264B (en) | Electrocardiosignal processing method | |
CN103914705B (en) | Hyperspectral image classification and wave band selection method based on multi-target immune cloning | |
CN103488869A (en) | Wind power generation short-term load forecast method of least squares support vector machine | |
CN109165819B (en) | Active power distribution network reliability rapid evaluation method based on improved AdaBoost. M1-SVM | |
CN104881735A (en) | System and method of smart power grid big data mining for supporting smart city operation management | |
CN105046326A (en) | Oil pumping unit parameter optimization method based on indicator diagram principal component analysis | |
CN108133225A (en) | A kind of icing flashover fault early warning method based on support vector machines | |
CN109543939A (en) | A kind of method of green building productions certification risk evaluation model building | |
CN101178703A (en) | Failure diagnosis chart clustering method based on network dividing | |
CN105320967A (en) | Multi-label AdaBoost integration method based on label correlation | |
CN109558897A (en) | A kind of more situation extracting methods of Electric Power Network Planning based on data mining | |
CN114484731A (en) | Method and device for diagnosing faults of central air conditioner based on stacking fusion algorithm | |
CN105630458B (en) | The Forecasting Methodology of average throughput under a kind of out-of order processor stable state based on artificial neural network | |
CN102867183A (en) | Method and device for detecting littered objects of vehicle and intelligent traffic monitoring system | |
CN106991049A (en) | A kind of Software Defects Predict Methods and forecasting system | |
CN110008853A (en) | Pedestrian detection network and model training method, detection method, medium, equipment |
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: 20181207 |