CN113485498B - Indoor environment comfort level adjusting method and system based on deep learning - Google Patents
Indoor environment comfort level adjusting method and system based on deep learning Download PDFInfo
- Publication number
- CN113485498B CN113485498B CN202110811142.6A CN202110811142A CN113485498B CN 113485498 B CN113485498 B CN 113485498B CN 202110811142 A CN202110811142 A CN 202110811142A CN 113485498 B CN113485498 B CN 113485498B
- Authority
- CN
- China
- Prior art keywords
- data
- indoor environment
- environment
- module
- indoor
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a deep learning-based indoor environment comfort level adjusting method and system, wherein a data acquisition module acquires environment data by using sensor equipment and sends the environment state data to an edge preprocessing and control module; predicting the change of indoor environment in a certain time period in the future based on a deep learning LSTM neural network construction model; the multisource heterogeneous environment data uploaded by the sensor at the current moment are used as the input of an indoor environment prediction model; the indoor environment prediction model completes prediction according to the transmitted indoor multi-source heterogeneous environment data and sends the result to the next thermal comfort level control model; and constructing a thermal comfort level control model, setting initial environmental parameters and an environmental parameter adjusting range, and providing an indoor environment adjusting scheme for improving the comfort level of the human body under the constraint of different scene modes. The invention provides comfortable indoor environment for users through dynamic prediction, and simultaneously effectively reduces energy consumption.
Description
Technical Field
The invention relates to the field of indoor environment control, in particular to an indoor environment comfort level adjusting method and system based on deep learning.
Background
When most of the next families or office areas adopt a single constant-temperature control indoor temperature regulation mode, the comfort level of human bodies is improved only by means of regulating the indoor temperature, and other controllable environmental factors influencing the indoor comfort level are not considered; and the control of temperature is accomplished through setting for air conditioning system of people's subjective consciousness also, and temperature variation has the characteristics of nonlinearity and non-real-time nature in the indoor environment in addition, and this kind of control mode can not satisfy people to the real needs of indoor environment travelling comfort, and the operating process that relapses simultaneously can make people's indoor environment experience feel relatively poor. Therefore, the establishment of a reasonable control strategy for the indoor environment thermal comfort has practical requirements and application values.
In order to avoid guidance and adjustment without practical significance caused by the defects of indexes in the comfort control of the indoor environment, various environmental factors influencing the comfort of the human body are comprehensively considered, an environmental comfort prediction model based on deep learning is established on the basis, and the environmental comfort control model is further established according to the predicted value of the model. The comfort level of the indoor environment is quantitatively evaluated by means of the American Society of heating, refrigeration and Air-Conditioning Engineers (ASHRAE) standard, and meanwhile, the comfort level of the indoor environment can be used as a control variable of an indoor comfort control system to achieve effective regulation of the comfort level of the indoor environment through indirect control of indexes. Meanwhile, considering the influence of indoor working scenes and operation modes on the indoor environment, the invention further provides an environment comfort level control model limited by the indoor operation mode, so that the environment comfort level control is more in line with the actual requirements.
Disclosure of Invention
The invention aims to provide an indoor environment comfort level adjusting method and system based on deep learning. From the two angles of considering the evaluation index (PMV) for expressing the human body thermal response and saving energy consumption, a relatively comfortable indoor environment is provided for a user, excessive change and non-real-time adjustment of the indoor environment are avoided through adjustment of the indoor environment, the comfort degree of the user is improved, and meanwhile, energy consumption saving of indoor environment adjusting equipment is achieved.
The invention provides an indoor environment comfort level adjusting system based on deep learning. The system is divided into 4 modules according to functional attributes, and the modules are a data collection module, an edge preprocessing and control module, an indoor environment prediction module based on deep learning and a thermal comfort control module based on mode feature constraint from bottom to top.
The data collection module is mainly responsible for collecting multisource heterogeneous environment data under the current scene, including temperature, humidity and wind speed, and the multisource heterogeneous environment data are converged and fused to the edge preprocessing and control module through the data collection module. The edge preprocessing and control module applies noise reduction, abnormal value removal and other means to the data to improve the data availability, ensure the accuracy of the input data of the prediction model and improve the precision of the prediction model. The indoor environment prediction module is based on a deep learning neural network and is responsible for completing prediction of indoor environment changes in a certain time period in the future. The thermal comfort control module based on mode feature constraint realizes reasonable adjustment of indoor environment under different mode constraints, thereby achieving the purpose of improving the thermal comfort of the indoor environment.
The invention provides an indoor environment comfort level adjusting method based on deep learning, which comprises the following steps:
s1, a data collection module collects indoor real-time multi-source heterogeneous environment data and sends the environment data to an edge preprocessing and control module;
s2, performing data preprocessing on the multi-source heterogeneous environment data uploaded by the sensor in an edge preprocessing and control module;
s3, predicting the change of the indoor environment within a certain period of time in the future based on a deep learning LSTM neural network construction model;
s4, the multi-source heterogeneous environment data processed by the edge preprocessing and control module is used as the input of an indoor environment prediction model;
s5, the indoor environment prediction model completes prediction of indoor environment change according to the transmitted indoor multi-source heterogeneous environment data, and sends the result to a thermal comfort level control model based on different mode feature constraints in the next step;
s6, constructing a thermal comfort level control model based on different mode characteristic constraints, and providing an indoor environment adjusting scheme for improving the comfort level of a human body under different scene mode constraints;
s7, the data center is directly connected with the edge preprocessing and control module, if the regulation and control result cannot meet the self requirement of a user, the instruction can be adjusted through an application program, the application program sends the system instruction to the edge preprocessing and control module, and then the edge preprocessing and control module sends the instruction to the related environment control equipment;
step S2 described as the present invention includes a preprocessing operation on the multi-source heterogeneous environment deployment, including:
s21, deleting abnormal values or setting missing bits aiming at multi-source heterogeneous environment data uploaded by sensors influenced by environment fluctuation and faults in the venue, wherein the missing values are processed by interpolation or elimination;
s22, processing multisource heterogeneous environment data based on a Kalman filtering algorithm, calculating Kalman gain, continuously correcting and updating to realize noise reduction of the environment data, and transmitting the preprocessed data to an indoor environment prediction model;
in step S3 described in the present invention, building and training a deep learning model includes:
s31, carrying out normalization and other processing on the preprocessed multi-source heterogeneous historical environment data set containing temperature, humidity and wind speed, and dividing the data set into training and verification data sets;
s32, setting the number of layers of a neural network, input dimensions, time step length of input data, LSTM input data reading batch size, a window length LSTM model optimizer, a learning rate and model iteration times;
s33, continuously adjusting parameters, checking the convergence degree of the model according to the model loss, and preferentially selecting high-convergence-degree parameters to form an indoor environment prediction model based on the LSTM;
step S6, described as the present invention, includes the regulation of the indoor environment, including:
s61, setting an environment parameter adjusting range according to different scene modes;
s62, receiving the result of the indoor environment prediction model in the previous step, calculating comfort level and fuzzy algorithm by utilizing a PMV formula in combination with the indoor environment parameter change range set under the constraint of the scene mode to obtain target temperatures of the indoor environment for different modes, and generating an environment control signal according to the target temperatures
S63, finally feeding back the adjustment result to the indoor environment prediction model for training and updating the model, and improving the system efficiency;
compared with the prior art, the invention has the beneficial effects that: according to the indoor environment comfort level adjusting method and system based on deep learning, environmental data uploaded by the sensor are analyzed through the prediction model, future changes of indoor environment are predicted and fed back to the indoor thermal comfort level control model, the control model provides a human body thermal comfort level optimization scheme based on current scene mode constraints, results are fed back to the prediction model, meanwhile, relevant equipment is controlled to adjust the indoor environment to a proper state, repeated adjustment of the environment is effectively avoided, energy consumption is reduced, and a reasonable scheme for indoor environment adjustment can be provided according to different scenes and operation modes.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of the indoor environment comfort level adjusting method and system based on deep learning according to the present invention.
Fig. 2 is a schematic structural diagram of an indoor environment comfort level adjustment system according to embodiment 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The invention is described in further detail below with reference to the attached drawing figures:
example 1
As shown in fig. 1, the present invention provides a method and a system for adjusting comfort level of indoor environment based on deep learning. Fig. 2 is a schematic structural diagram of an indoor environment comfort level adjustment system provided in embodiment 1 of the present invention, which takes an indoor environment as an example, and specifically includes the following steps:
s1, acquiring environmental data by using sensor equipment in a data acquisition module, and sending the environmental state data to an edge preprocessing and control module;
the method comprises the steps that sensors such as temperature, humidity and wind speed are deployed to detect current indoor temperature, humidity and wind speed and other environmental conditions, and the devices such as the temperature, humidity and wind speed sensors are communicated with an edge preprocessing and control module through network protocols such as Zigbee or echo Lite.
S2, after the indoor environment data are collected by the edge preprocessing and control module, caching and preprocessing the data through the miniature server, and then sending the data to the data center through the gateway;
the edge preprocessing and control module is responsible for collecting data from sensors of temperature, humidity, wind speed and the like, and sending the data to an indoor environment prediction model and a data center after data cleaning and noise reduction processing.
Wherein, the data cleaning uses Statistical Product and Service Solutions software (SPSS) to delete abnormal values or set missing bits, and the missing values are processed by interpolation or elimination;
denoising the environmental data based on the principle of a Kalman filter; the state variable y at the next moment is predicted based on the optimal estimation x at a certain past moment, the state is observed to obtain an observed variable z, and then analysis is performed between prediction and observation, or the predicted quantity is corrected by the observed quantity, so that the optimal estimation at the next moment is obtained.
S3, storing the environmental state data in the edge preprocessing and control module, inputting the real-time environmental data into a deep learning LSTM prediction model which is trained in advance, and obtaining the change condition of the environment within a period of time in the future;
the core of the LSTM is the control unit state c, the control includes a forgetting gate f t And input gate i t And an output gate o t . At the current time t, forget the door f t Responsible for controlling the last moment c t-1 How much to save to the current moment c t (ii) a Input door i t Is responsible for controlling how much the instant state at the current moment is input into the current unit state c t (ii) a Output gate o t Is responsible for controlling the current cell state c t How many hidden layer outputs h as the current time t . The calculation formulas are respectively as follows:
(1)f t ＝σ(w f ·[x t ,h t-1 ]+b f )
(2)i t ＝σ(w i ·[x t ,h t-1 ]+b i )
(3)o t ＝σ(w o ·[x t ,h t-1 ]+b o )
wherein, w f 、w i 、w o Weight matrices for forgetting gate, input gate and output gate, respectively, b f 、b i 、b o Are respectively offset terms of a forgetting gate, an input gate and an output gate, and sigma is a sigmoid function.
The inputs to the LSTM include: cell state at last moment c t-1 Last time LSTM hidden layer output value h t-1 Input value x of network at current time t t (ii) a The output of the LSTM includes: cell state c at the present time t Hidden layer output value h of LSTM at current time t 。
Wherein the current input unit state is input by the network x at the current time t t Last time LSTM hidden layer output value h t-1 Jointly determining, the calculation formula is as follows:
wherein, w c Is a weight of the state of the input unitMatrix, b c Is a bias term of the state of the input cell, tanh is a hyperbolic tangent function
Current cell state c t By forgetting door f t Last time cell state c t-1 And an input gate i t Is determined together with the current input unit state and has the calculation formula of
Wherein symbol |, indicates multiplication by element. Hidden layer output value h of LSTM at current moment t From an output gate o t And the current cell state c t Jointly determining, the calculation formula is as follows: h is t ＝o t ⊙tanh(c t )
And LSTM neural network output
The calculation formula is as follows:
the invention adopts Mean Square Error (MSE) as loss function (loss), and the calculation formula is as follows:
wherein N is the number of samples, x is the observed value, and x' is the predicted value.
In the data preprocessing stage of the model, when the environmental data is predicted by using the sequence data composed of a plurality of variable sequences, the dimensions of different variables are different, and the numerical value difference is also large. Considering the input and output range of the nonlinear activation function in the model, in order to avoid neuron saturation, normalization processing needs to be performed on the variable time series.
The prediction model is based on a Keras deep learning framework, an LSTM network related module in the Keras framework is used, and the input dimensionality and the time step length of input data of the LSTM are set; LSTM input data reads batch size and window length LSTM model optimizer and learning rate; the number of the cryptomelanic ganglion points; the number of model iterations; and continuously adjusting parameters, checking the convergence degree of the model according to the model loss, and preferentially selecting high-convergence parameters to form an indoor environment prediction model based on the LSTM.
And S4, based on the result of the indoor environment prediction model in the previous step, the thermal comfort control model under the constraint of different mode characteristics is used for receiving the result of the indoor environment prediction model in the previous step, and based on the indoor environment parameter change range and the PMV thermal sensing scale (shown in the table 1) set under the constraint of the scene mode, the comfort and fuzzy algorithm are calculated by utilizing a PMV formula (shown in the following) to obtain the target temperature of the indoor environment aiming at different modes, and the environment control signal is generated according to the target temperature.
TABLE 1
PMV＝[0.303e-0.036M+0.028]{M-W-3.0* 10-3 [5.733-6.99(M-W)-p a ]-0.42[(M-W)-58.15]-1.7*10 -5 M(5867-p a )-0.0014M(34-t a )-3.96*10 -8 f cl [(t cl +273) 4 -(t s +273) 4 -f cl h c (t cl -t a )]}
Wherein M is the metabolic rate and the unit is W/M2; w is human body power, and the unit is W/s; t is t a Is the indoor air temperature in units of; t is t s Is the mean radiant temperature in deg.C, t cl The average temperature of the outer surface of the human body is the unit;
p a the unit is Pa for the water vapor partial pressure in the ambient air, and the specific calculation formula is shown as follows;
p a ＝6107.8×RH a ×exp[t a /(t a +238.2)×17.2694]
f cl the specific calculation formula is shown as follows;
h c the convective heat exchange coefficient was calculated in units of W/(s.m 2 ℃), and its specific calculation formula was as follows.
8 variables in the formula: m (metabolism rate), W (power of human body), p a (partial pressure of water vapor in ambient air), t a (indoor air temperature), f cl (ratio of the surface area of the body to the surface area of the bare body, and t) s (mean radiant temperature), t cl (average temperature of outer surface of human body wearing clothes), h c (convective heat transfer coefficient). In fact, M (metabolic rate), p a (partial pressure of water vapor in ambient air), t a (temperature of indoor air), f cl (ratio of the surface area of the body to be dressed), t s (mean radiation temperature), t cl The (average temperature of the outer surface of the dressed body) can be replaced by the average of the statistics over a period of time, W (power of the body) we consider here as 0.
From the above formula, it can be seen that there are 6 factors affecting human comfort: air temperature, air velocity (wind speed), relative humidity, average radiation temperature, human body metabolic rate and clothing thermal resistance. The human body metabolic rate and the clothing thermal resistance are fixed values and are adjusted according to different seasons and different weather. Secondly, as can be known from the analysis of the PMV formula, the influence of the relative humidity on the comfort level is small, so in the comfort level adjustment model, the adjustment of the indoor comfort level is realized mainly by adjusting two environmental variables, namely the temperature and the air flow rate (wind speed).
The thermal comfort adjustment adopts a fuzzy control algorithm, T up Is the upper temperature limit, T, of the target temperature region down Is temperatureA lower limit; w up Is the upper temperature limit of the target temperature region, W down Is a lower limit of temperature T up Is the upper temperature limit, T, of the target temperature region down The lower temperature limit. Firstly, an indoor temperature value T and a wind speed value W at the next moment are obtained from an indoor environment prediction model. And according to the difference of indoor thermal comfort degree corresponding to the PMV thermal sensing ruler, different adjusting amplitudes are adopted according to a fuzzy control algorithm to give a target temperature. The specific fuzzy control algorithm is shown in Table 2
TABLE 2
x represents a preset indoor temperature control return difference which can be set independently and is usually 0.5 ℃ or 1 ℃. y represents the preset indoor wind speed control return difference and is usually 0.05m/s.
And meanwhile, limiting the fuzzy algorithm according to the set range of the system mode parameters in the thermal comfort level adjusting module, and terminating the current adjusting operation of the environmental parameter when the adjusting range of a certain parameter exceeds the set range of the system mode parameter, so as to keep the previous value unchanged. And the final regulation result is fed back to the indoor prediction model, and the effect of the model is optimized to realize the regulation of the indoor environment.
In the embodiments provided by the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling, direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in an electrical, mechanical or other form.
The integrated unit implemented in the form of a software functional unit may be stored in a computer-readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solutions of the present invention, and are not meant to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made to the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. An indoor environment comfort level adjusting method based on deep learning is characterized by comprising the following steps:
s1, acquiring environmental data by using sensor equipment in a data acquisition module, and sending the environmental state data to an edge preprocessing and control module;
s2, after the environment state data are collected by the edge preprocessing and control module, preprocessing the data through a miniature server, and then sending the data to an indoor environment prediction module through a gateway;
s3, storing the environmental state data in an indoor environment prediction module, inputting the real-time environmental state data into a deep learning LSTM model which is trained in advance, and obtaining the change of the indoor environment at the next moment;
s4, the indoor environment prediction module sends a signal of indoor environment change at the next moment output by the prediction model to the thermal comfort regulation module, the regulation module sends regulation and control information of the system to the edge preprocessing and control module through an algorithm, and the edge preprocessing and control module sends an instruction to related environment control equipment;
s5, the data center is directly connected with the edge preprocessing and control module, if the regulation and control result of the thermal comfort degree regulation module does not meet the self requirement of a user enough, the instruction can be adjusted through an application program, the application program sends a system instruction to the edge preprocessing and control module, and then the edge preprocessing and control module sends the instruction to related environment control equipment;
the S1 step comprises:
the method comprises the following steps that temperature, humidity and wind speed sensors are deployed to detect current indoor temperature, humidity and wind speed environmental conditions, and the temperature, humidity and wind speed sensors are communicated with an edge preprocessing and control module through Zigbee or an echo Lite network protocol;
and the S3 step comprises:
s31, in the data preprocessing stage of the model, when sequence data consisting of a plurality of variable sequences are used for predicting environment data, dimensions of different variables are different, and numerical value difference is large; considering the input and output range of the nonlinear activation function in the model, in order to avoid neuron saturation, normalization processing needs to be carried out on the variable time sequence;
s32, setting the input dimension of the LSTM and the time step length of input data by using an LSTM network related module in the Keras framework on the basis of the Keras deep learning framework by using a prediction model;
s33, reading batch size and window length LSTM model optimizer and learning rate by LSTM input data;
s34, counting the number of the cryptomelanic ganglia; the number of model iterations; continuously adjusting parameters, checking the convergence degree of the model according to the model loss, and preferentially selecting high-convergence parameters to form an indoor environment prediction model based on the LSTM;
the S4 step comprises:
the thermal comfort adjustment adopts a fuzzy control algorithm, T up Is the upper temperature limit, T, of the target temperature region down Is the lower temperature limit; w up At wind speed of target temperature regionLimit, W down Is the lower limit of wind speed; firstly, acquiring an indoor temperature value T and a wind speed value W at the next moment from an indoor environment prediction model; and according to the difference of indoor thermal comfort degree corresponding to the PMV thermal sensing ruler, different adjusting amplitudes are adopted according to a fuzzy control algorithm to give a target temperature.
2. The deep learning-based indoor environment comfort level adjustment method according to claim 1, wherein the S2 step includes:
the edge preprocessing and control module is responsible for collecting data from the sensors and sending the data to the indoor environment prediction module through the MQTT protocol.
3. The deep learning-based indoor environment comfort level adjustment method of claim 1, wherein in a system for implementing the method,
the indoor environment comfort level adjusting system is divided into 4 modules according to the functional attributes, and the modules are a data acquisition module, an edge preprocessing and control module, an indoor environment prediction module and a thermal comfort level adjusting module based on mode characteristic constraint from bottom to top respectively;
the data acquisition module is mainly responsible for acquiring environmental data and comprises a temperature and humidity sensor, a wind speed sensor and an equipment controller;
the edge preprocessing and control module is mainly used for preprocessing data of multi-source heterogeneous environment data uploaded by the sensor, the data preprocessing module is used for reducing noise and removing abnormal values from the data to improve the usability of the data, the accuracy of data input by a prediction model is ensured, the precision of the prediction model is improved, and the preprocessed data are uploaded to an indoor environment prediction module;
the indoor environment prediction module is a core layer of the indoor environment comfort level regulation system and is responsible for completing prediction of environment changes in the stadium within a certain time period in the future based on the deep learning neural network;
the thermal comfort degree adjusting module based on mode feature constraint is responsible for interaction between an indoor environment control system and a user, and analyzes environment data through an algorithm to regulate and control indoor environment equipment, so that reasonable adjustment of the environment in a venue under different mode constraints is realized, and the purpose of improving the thermal comfort degree of the indoor environment is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811142.6A CN113485498B (en) | 2021-07-19 | 2021-07-19 | Indoor environment comfort level adjusting method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811142.6A CN113485498B (en) | 2021-07-19 | 2021-07-19 | Indoor environment comfort level adjusting method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113485498A CN113485498A (en) | 2021-10-08 |
| CN113485498B true CN113485498B (en) | 2022-10-18 |
Family
ID=77942172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110811142.6A Active CN113485498B (en) | 2021-07-19 | 2021-07-19 | Indoor environment comfort level adjusting method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113485498B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114048537B (en) * | 2021-11-22 | 2022-11-25 | 盈嘉互联（北京）科技有限公司 | Indoor environment state prediction method based on BIM and cross sample learning |
| CN113971376B (en) * | 2021-12-22 | 2022-04-19 | 云丁网络技术(北京)有限公司 | Intelligent control method and system for environmental parameters |
| CN114234384B (en) * | 2021-12-27 | 2023-08-29 | 中铁第四勘察设计院集团有限公司 | Air conditioning optimization control method and system for railway passenger station |
| CN116839185B (en) * | 2023-07-04 | 2024-04-05 | 重庆大学 | Air conditioner temperature regulation and control method and system |
| CN117570512B (en) * | 2024-01-16 | 2024-03-19 | 成都航空职业技术学院 | Building temperature control system based on temperature self-adaptive control model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102563808A (en) * | 2012-01-11 | 2012-07-11 | 华南理工大学 | Automatic control method of indoor environment comfort level |
| CN102589092A (en) * | 2012-03-12 | 2012-07-18 | 山东建筑大学 | Indoor-environment thermal comfort control method based on novel fuzzy controller |
| CN104359192A (en) * | 2014-11-19 | 2015-02-18 | 山东建筑大学 | Data-based personalized control system and method for energy conservation and comfort of indoor environment |
| CN205481574U (en) * | 2016-03-01 | 2016-08-17 | 中国建筑科学研究院 | Indoor environment comfort level control system based on fuzzy controller |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3188048B2 (en) * | 1993-05-28 | 2001-07-16 | 東芝キヤリア株式会社 | Air conditioner |
| TWI546506B (en) * | 2014-12-04 | 2016-08-21 | 台達電子工業股份有限公司 | Controlling system for environmental comfort value and controlling method of the controlling system |
| US20190187635A1 (en) * | 2017-12-15 | 2019-06-20 | Midea Group Co., Ltd | Machine learning control of environmental systems |
| CN109899937A (en) * | 2019-03-12 | 2019-06-18 | 王馨仪 | Comfort level and the foreseeable air conditioning system of section and method based on LSTM model |
| CN109931678B (en) * | 2019-03-13 | 2020-09-25 | 中国计量大学 | Air conditioner fault diagnosis method based on deep learning LSTM |
| CN110298487B (en) * | 2019-05-30 | 2023-05-16 | 同济大学 | Indoor temperature prediction method for meeting personalized demands of users |
| CN110186170B (en) * | 2019-06-20 | 2020-11-27 | 北京石油化工学院 | Thermal comfort index PMV control method and equipment |
| CN110689075A (en) * | 2019-09-26 | 2020-01-14 | 北京工业大学 | Fault prediction method of self-adaptive threshold of refrigeration equipment based on multi-algorithm fusion |
| CN111126658A (en) * | 2019-11-15 | 2020-05-08 | 太原理工大学 | Coal mine gas prediction method based on deep learning |
| CN111639462B (en) * | 2020-05-29 | 2023-04-18 | 桂林电子科技大学 | Building indoor thermal comfort prediction method in natural ventilation environment based on deep belief neural network |
| CN111795484B (en) * | 2020-07-24 | 2021-11-23 | 北京大学深圳研究生院 | Intelligent air conditioner control method and system |
| CN111928429A (en) * | 2020-08-25 | 2020-11-13 | 北京大学深圳研究生院 | Energy-saving control method and device for data center refrigerating system |
| CN112113317B (en) * | 2020-10-14 | 2024-05-24 | 清华大学 | Indoor thermal environment control system and method |
| CN112613232B (en) * | 2020-12-18 | 2023-05-26 | 大连海事大学 | Indoor human body thermal comfort prediction and evaluation method under winter heating condition |
| CN113112077B (en) * | 2021-04-14 | 2022-06-10 | 太原理工大学 | HVAC control system based on multi-step prediction deep reinforcement learning algorithm |
-
2021
- 2021-07-19 CN CN202110811142.6A patent/CN113485498B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102563808A (en) * | 2012-01-11 | 2012-07-11 | 华南理工大学 | Automatic control method of indoor environment comfort level |
| CN102589092A (en) * | 2012-03-12 | 2012-07-18 | 山东建筑大学 | Indoor-environment thermal comfort control method based on novel fuzzy controller |
| CN104359192A (en) * | 2014-11-19 | 2015-02-18 | 山东建筑大学 | Data-based personalized control system and method for energy conservation and comfort of indoor environment |
| CN205481574U (en) * | 2016-03-01 | 2016-08-17 | 中国建筑科学研究院 | Indoor environment comfort level control system based on fuzzy controller |
Non-Patent Citations (3)
| Title |
|---|
| 一种基于数据的夏季居住环境热舒适度控制方法;段培永等;《山东建筑大学学报》;20110228;第26卷(第01期);1-7 * |
| 基于神经网络和遗传算法优化室内热舒适控制参数;徐巍等;《北京理工大学学报》;20100228;第30卷(第02期);240-244 * |
| 基于神经网络的室内环境热舒适度融合算法;张方方等;《重庆工学院学报(自然科学版)》;20091031;第23卷(第10期);114-118 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113485498A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113485498B (en) | Indoor environment comfort level adjusting method and system based on deep learning | |
| Gao et al. | DeepComfort: Energy-efficient thermal comfort control in buildings via reinforcement learning | |
| CN108413588B (en) | Personalized air conditioner control system and method based on thermal imaging and BP neural network | |
| CN113112077B (en) | HVAC control system based on multi-step prediction deep reinforcement learning algorithm | |
| CN111609534B (en) | Temperature control method and device and central temperature control system | |
| CN108613332B (en) | Interactive thermal comfort level adjusting method for personnel in micro-area of energy-saving building | |
| AU2021105951A4 (en) | Method and System for Adjusting Indoor Environment Comfort Based on Deep Learning | |
| CN111486554B (en) | Air conditioner temperature non-sensitive control method based on online learning | |
| CN102589092A (en) | Indoor-environment thermal comfort control method based on novel fuzzy controller | |
| TW201323793A (en) | Air conditioning control device and method thereof | |
| CN110377084B (en) | Building indoor environment regulation and control method based on intelligent control strategy | |
| CN112613232B (en) | Indoor human body thermal comfort prediction and evaluation method under winter heating condition | |
| CN114370698A (en) | Indoor thermal environment learning efficiency improvement optimization control method based on reinforcement learning | |
| CN112577159B (en) | Air conditioner energy-saving intelligent control method and device based on human body thermal comfort | |
| CN110097929A (en) | A kind of blast furnace molten iron silicon content on-line prediction method | |
| CN112634083A (en) | Building energy-saving monitoring method | |
| CN113240184A (en) | Building space unit cold load prediction method and system based on federal learning | |
| CN116045443A (en) | Building air conditioner energy consumption prediction method based on indoor temperature optimization control | |
| CN117195747B (en) | Uniform heat distribution optimization method for magnetic material drying | |
| CN113418286B (en) | Self-adaptive thermal sensing robot and air conditioner temperature adjusting method | |
| Ding et al. | Multi-zone hvac control with model-based deep reinforcement learning | |
| Duan et al. | A novel data-based control strategy of dynamic thermal comfort for inhabited environment | |
| CN111271810B (en) | Air conditioner control method, control system, air conditioner and computer storage medium | |
| CN113719974A (en) | Air conditioner wind direction intelligent control method and system based on flow field information prediction | |
| CN113177675A (en) | Air conditioner cold load prediction method based on optimization neural network of longicorn group algorithm |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |