CN109376795A - Air conditioner intelligent temperature control method based on Decision Tree Algorithm - Google Patents
Air conditioner intelligent temperature control method based on Decision Tree Algorithm Download PDFInfo
- Publication number
- CN109376795A CN109376795A CN201811377460.0A CN201811377460A CN109376795A CN 109376795 A CN109376795 A CN 109376795A CN 201811377460 A CN201811377460 A CN 201811377460A CN 109376795 A CN109376795 A CN 109376795A
- Authority
- CN
- China
- Prior art keywords
- data
- decision tree
- air conditioner
- temperature control
- control method
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention relates to field of air conditioning, disclose a kind of air conditioner intelligent temperature control method based on Decision Tree Algorithm, are reduced to improve the ability of automatic air conditionning, while improving user experience because uncomfortable caused by excessively blowing air-conditioning.The present invention needs earlier acquisition mass data to generate training set, and the threshold value of suitable condition is obtained by healthy system, then it is established using training set and decision tree of refining, establish decision-tree model, then in system work using generating the decision tree that finishes to the attribute value by information collecting device acquisition environmental data from root node successively test record, until reaching some leaf node, to find the class where the record, then data are judged by categorised decision tree, and the result reached under each environmental condition optimize processing and make final control operating.The present invention is controlled suitable for air conditioner intelligent temperature.
Description
Technical field
The present invention relates to field of air conditioning, in particular to the air conditioner intelligent temperature control method based on Decision Tree Algorithm.
Background technique
With popularizing for smart machine, household electrical appliance realize intelligence substantially, and more convenient and quicker is people's
Service for life.But existing air-conditioning tends not to be fitted after manually doing exercises in the case where surrounding enviroment change
The regulation of degree has caused air conditioner disease and unnecessary energy waste under the conditions of so that current environment is in optimum.
Categorised decision tree, decision tree (Decision Tree) are also known as decision tree, are a kind of tree knots for applying to classification
Structure.Each internal node (internal node) therein represents the primary test to some attribute, and each edge represents a survey
Test result, leaf node (leaf) represents the distribution (class distribution) of some class (class) or class, uppermost
Node is root node.Decision tree is divided into classification tree and two kinds of regression tree, and classification tree does decision tree to discrete variable, and regression tree is to even
Continuous variable does decision tree.Decision Tree algorithms have a benefit, that is, it can produce the rule that people can directly understand, this is shellfish
The no characteristic of Ye Si, neural network scheduling algorithm;The accuracy rate of decision tree is also relatively high, and be not required to it is to be understood that background knowledge just
It can classify, be a very effective algorithm.Decision Tree algorithms have many mutation, including ID3, C4.5, C5.0, CART
Deng, but its basis is all similar.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of air conditioner intelligent temperature control side based on Decision Tree Algorithm
Method is reduced to improve the ability of automatic air conditionning, while improving user experience because uncomfortable caused by excessively blowing air-conditioning.
To solve the above problems, the technical solution adopted by the present invention is that: the air conditioner intelligent temperature based on Decision Tree Algorithm
Prosecutor method, includes the following steps:
Step S01: the environmental information of current environment is obtained, and converts environmental information to and predefines corresponding operand
According to;
Step S02: data obtained in processing step S01 carry out data cleansing;
Step S03: data transformation is carried out to valid data obtained in step S02, is arrived more generally to change continuous data
High-level concept;
Step S04: the data after generalization are input in decision-tree model and are classified;
Step S05: optimization processing is carried out according to the classification results of step S04, and executes final result.
Further, the environmental information of step S01 acquisition is not necessarily while comprising environment temperature, ambient humidity, environment
Quality, air flowing and human surface temperature also may include environment temperature, ambient humidity, environmental quality, air flowing and people
One or more of body surface temperature information.
Further, data cleansing described in step 02 generally comprises: checking data consistency, and deletes invalid value
And missing values.
Further, in order to clearly illustrate the generation step of categorised decision tree-model of the present invention, classify in step S04 and determine
The generation step of plan tree-model may include:
Step S0401: environmental data of the statistics when people is comfortable on;
Step S0402: counting data obtained in step S0401, and carries out manual sort to data, defines
Range threshold, and training set and test data set are obtained by cleaning treatment;
Step S0403: using the training classifier of training set obtained in step S0402, and with test data set to training
Resulting classifier is tested, and a categorised decision tree is obtained;
Step S0404, beta pruning and optimization are carried out to the categorised decision tree that S0403 is obtained in conjunction with actual conditions, obtained best
Automatic temperature-controlled decision-tree model.
Further, to construct a complete categorised decision tree-model, in the case of people described in step 0401 is comfortable on
Environmental data may include: environment temperature, ambient humidity, environmental quality, air flowing and human surface temperature.
The beneficial effects of the present invention are: using the data of categorised decision tree on the basis of the existing automatic adjustment of the present invention
Analysis method more efficiently, can be carried out automatically controlling explicitly, to improve recognition accuracy to a certain extent, be improved
It is reduced while user experience because uncomfortable caused by excessively blowing air-conditioning.
Detailed description of the invention
Fig. 1 is the flow chart of embodiment.
Fig. 2 is the model schematic of categorised decision tree.
Specific embodiment
In order to make people enjoy the environment of the most comfortable to greatest extent, and improve equipment in the case where energy saving
User experience the present invention provides a kind of air conditioner intelligent temperature control system mainly include information acquisition system and control processing system
System.Before the auto temperature controlled system carries out intelligent temperature control, needs to acquire mass data in advance and generate training set, and pass through healthy system
The threshold value of suitable condition is obtained, is then established using training set and decision tree of refining, decision-tree model (this process is established
Actually one obtains knowledge from data, carries out the process of machine learning).Then it is finished in system work using generation
Decision tree obtain attribute value of the environmental data from root node successively test record to by information acquisition system, until reaching certain
A leaf node, to find the class where the record.Then data are judged by categorised decision tree, and to each environment
Under the conditions of the result that reaches carry out optimizing processing and make final control operation.
Temperature control method of the present invention from being designed into using two large divisions is divided into, determine for what is completed in system preparation by a part
Plan tree-model generating portion, a part are the implementation section of user's operation.It is specific as follows:
First part is the generation of categorised decision tree-model:
It makes thorough investigation and study, the control environment data of people is collected, obtain the number for largely being used to judge air-conditioning regulation
According to;Obtained data are counted, and manual sort is carried out to data, define threshold value, and a small number of according to most obediences
Rule carries out dirty data cleaning treatment, obtains relatively most representative training set and test data set;Utilize obtained training
Collect training classifier, and the resulting classifier of training is tested with test data set, obtains a categorised decision tree;In conjunction with
Actual conditions carry out beta pruning and optimization to categorised decision tree, obtain the decision-tree model for being suitable for air-conditioning regulation.
Second part is the application in real work:
The operation information of user is obtained by information acquisition system, and is translated into predefined corresponding operand
According to;Data cleansing is carried out to collected data, including checks data consistency, and delete invalid value and missing values;To preceding
The valid data of one step carry out data transformation, and continuous data is generally changed to higher concept, to be had one by one
The data of individually operated property;Classify the data after generalization are input in decision-tree model;According to classification results pair
Equipment carries out corresponding operation, and feeds back to user.
The present invention will be further described by the following examples.
As shown in Figure 1, embodiment provides a kind of air conditioner intelligent temperature control method based on Decision Tree Algorithm, including such as
Lower step:
Step S01: the environmental information of current environment is obtained, and converts environmental information to and predefines corresponding operand
According to;The environmental information of acquisition includes in environment temperature, ambient humidity, environmental quality, air flowing and human surface temperature's information
One or more.
Step S02: data obtained in processing step S01 carry out data cleansing, comprising: check data consistency, and
Delete invalid value and missing values.
Step S03: carrying out data transformation to valid data obtained in step S02, by stating data transformation will connect
Continue Data generalization to higher concept.
Step S04: the data after generalization are input in decision-tree model and are classified.
Wherein, the generation step of categorised decision tree-model includes:
Step S0401: environment temperature, ambient humidity, environmental quality, air flowing of the statistics when people is comfortable on
And the environmental datas such as human surface temperature;
Step S0402: counting data obtained in step S0401, and carries out manual sort to data, defines
Range threshold, and training set and test data set are obtained by cleaning treatment;
Step S0403: using the training classifier of training set obtained in step S0402, and with test data set to training
Resulting classifier is tested, and a categorised decision tree is obtained;
Step S0404, beta pruning and optimization are carried out to the categorised decision tree that S0403 is obtained in conjunction with actual conditions, obtained best
Automatic temperature-controlled decision-tree model.The model of the categorised decision tree ultimately generated is as shown in Figure 2.
Step S05: optimization processing is carried out according to the classification results of step S04, and executes final result.
Claims (5)
1. the air conditioner intelligent temperature control method based on Decision Tree Algorithm, which comprises the steps of:
Step S01: the environmental information of current environment is obtained, and converts environmental information to and predefines corresponding operation data;
Step S02: data obtained in processing step S01 carry out data cleansing;
Step S03: carrying out data transformation to valid data obtained in step S02, arrives higher generally to change continuous data
Concept;
Step S04: the data after generalization are input in decision-tree model and are classified;
Step S05: optimization processing is carried out according to the classification results of step S04, and executes final result.
2. the air conditioner intelligent temperature control method based on Decision Tree Algorithm as described in claim 1, which is characterized in that step
In S01, the environmental information of current environment includes one or more of following information: environment temperature, ambient humidity, environment matter
Amount, air flowing and human surface temperature.
3. the air conditioner intelligent temperature control method based on Decision Tree Algorithm as described in claim 1, which is characterized in that step 02
In, the data cleansing includes: inspection data consistency, and deletes invalid value and missing values.
4. the air conditioner intelligent temperature control method based on Decision Tree Algorithm as described in claim 1, which is characterized in that step
In S04, the generation step of categorised decision tree-model includes:
Step S0401: environmental data of the statistics when people is comfortable on;
Step S0402: counting data obtained in step S0401, and carries out manual sort to data, defines range
Threshold value, and training set and test data set are obtained by cleaning treatment;
Step S0403: using the training classifier of training set obtained in step S0402, and with test data set to training gained
Classifier tested, obtain a categorised decision tree;
Step S0404, the categorised decision tree obtained in conjunction with actual conditions to S0403 carries out beta pruning and optimization, obtain it is optimal from
The decision-tree model of dynamic temperature control.
5. the air conditioner intelligent temperature control method based on Decision Tree Algorithm as claimed in claim 4, which is characterized in that step
In 0401, the environmental data in the case of the people is comfortable on includes: environment temperature, ambient humidity, environmental quality, air flowing
And human surface temperature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811377460.0A CN109376795A (en) | 2018-11-19 | 2018-11-19 | Air conditioner intelligent temperature control method based on Decision Tree Algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811377460.0A CN109376795A (en) | 2018-11-19 | 2018-11-19 | Air conditioner intelligent temperature control method based on Decision Tree Algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109376795A true CN109376795A (en) | 2019-02-22 |
Family
ID=65389358
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811377460.0A Pending CN109376795A (en) | 2018-11-19 | 2018-11-19 | Air conditioner intelligent temperature control method based on Decision Tree Algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109376795A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110749958A (en) * | 2019-11-01 | 2020-02-04 | 西安光谷防务技术股份有限公司 | Heating tank of optical fiber fusion splicer and temperature control method thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103743174A (en) * | 2013-12-26 | 2014-04-23 | 柳州职业技术学院 | Vehicle air conditioner control system method based on neural network |
CN104133427A (en) * | 2013-05-03 | 2014-11-05 | 于庆广 | Intelligent household control method and system |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN104748305A (en) * | 2015-03-19 | 2015-07-01 | 智联通建筑科技(北京)有限公司 | Identification method and system of on-off state of air conditioner and estimation method and system of on-off state of air conditioner |
CN105404866A (en) * | 2015-11-17 | 2016-03-16 | 四川长虹电器股份有限公司 | Implementation method for multi-mode automatic implementation of human body state sensing |
CN107526440A (en) * | 2017-08-28 | 2017-12-29 | 四川长虹电器股份有限公司 | The intelligent electric appliance control method and system of gesture identification based on decision tree classification |
CN108224681A (en) * | 2017-12-16 | 2018-06-29 | 广西电网有限责任公司电力科学研究院 | Non-intrusion type starting of air conditioner detection method based on decision tree classifier |
-
2018
- 2018-11-19 CN CN201811377460.0A patent/CN109376795A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104133427A (en) * | 2013-05-03 | 2014-11-05 | 于庆广 | Intelligent household control method and system |
CN103743174A (en) * | 2013-12-26 | 2014-04-23 | 柳州职业技术学院 | Vehicle air conditioner control system method based on neural network |
CN104374053A (en) * | 2014-11-25 | 2015-02-25 | 珠海格力电器股份有限公司 | Intelligent control method, device and system |
CN104748305A (en) * | 2015-03-19 | 2015-07-01 | 智联通建筑科技(北京)有限公司 | Identification method and system of on-off state of air conditioner and estimation method and system of on-off state of air conditioner |
CN105404866A (en) * | 2015-11-17 | 2016-03-16 | 四川长虹电器股份有限公司 | Implementation method for multi-mode automatic implementation of human body state sensing |
CN107526440A (en) * | 2017-08-28 | 2017-12-29 | 四川长虹电器股份有限公司 | The intelligent electric appliance control method and system of gesture identification based on decision tree classification |
CN108224681A (en) * | 2017-12-16 | 2018-06-29 | 广西电网有限责任公司电力科学研究院 | Non-intrusion type starting of air conditioner detection method based on decision tree classifier |
Non-Patent Citations (1)
Title |
---|
陈焕新 等: "《数据挖掘技术在制冷空调行业的应用》", 《暖通空调》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110749958A (en) * | 2019-11-01 | 2020-02-04 | 西安光谷防务技术股份有限公司 | Heating tank of optical fiber fusion splicer and temperature control method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109357352B (en) | Air conditioner intelligent temperature control system and method based on decision tree classification algorithm | |
CN106778902B (en) | Dairy cow individual identification method based on deep convolutional neural network | |
CN104914720B (en) | Electronic nose intelligence baking control system and control method with autolearn feature | |
CN110674120B (en) | Wind farm data cleaning method and device | |
CN109461025A (en) | A kind of electric energy substitution potential customers' prediction technique based on machine learning | |
CN103996054B (en) | Electroencephalogram feature selecting and classifying method based on combined differential evaluation | |
CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
CN109489212A (en) | Intelligent sleep control method, adjustment system and equipment for air conditioner | |
CN109730818A (en) | A kind of prosthetic hand control method based on deep learning | |
CN107526440A (en) | The intelligent electric appliance control method and system of gesture identification based on decision tree classification | |
CN113177594A (en) | Air conditioner fault diagnosis method based on Bayesian optimization PCA-extreme random tree | |
CN110389663A (en) | A kind of sEMG gesture identification method based on small wave width learning system | |
CN107067022B (en) | Method, device and equipment for establishing image classification model | |
CN109903053A (en) | A kind of anti-fraud method carrying out Activity recognition based on sensing data | |
CN109325410B (en) | Electroencephalogram EEG (electroencephalogram) feature extraction method based on convolutional neural network | |
CN109342279A (en) | Mixing flexible measurement method based on grinding mechanism and neural network | |
CN109376795A (en) | Air conditioner intelligent temperature control method based on Decision Tree Algorithm | |
CN102693287A (en) | Automatic group decision-making consensus degree adjustment method based on clustering method and particle swarm optimization method | |
CN109993359A (en) | A kind of Tendency Prediction method based on sophisticated machine study | |
CN117391395A (en) | Automatic adjusting method and system for water supply system | |
CN111191510B (en) | Relation network-based remote sensing image small sample target identification method in complex scene | |
CN110458066A (en) | A kind of age bracket classification method based on tranquillization state eeg data | |
CN113673174B (en) | Super parameter determination method, device, equipment and storage medium | |
CN110059752A (en) | A kind of statistical learning querying method based on comentropy Sampling Estimation | |
CN110399656B (en) | Lower-loading waist-saving parameter design method based on fuzzy logic and neural network |
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: 20190222 |