CN104374053A - Intelligent control method, device and system - Google Patents
Intelligent control method, device and system Download PDFInfo
- Publication number
- CN104374053A CN104374053A CN201410691067.4A CN201410691067A CN104374053A CN 104374053 A CN104374053 A CN 104374053A CN 201410691067 A CN201410691067 A CN 201410691067A CN 104374053 A CN104374053 A CN 104374053A
- Authority
- CN
- China
- Prior art keywords
- value
- comfort level
- running status
- neural network
- network model
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000003062 neural network model Methods 0.000 claims abstract description 101
- 238000004378 air conditioning Methods 0.000 claims abstract description 100
- 230000001276 controlling effect Effects 0.000 claims abstract description 9
- 230000001105 regulatory effect Effects 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 104
- 238000012549 training Methods 0.000 claims description 79
- 238000012545 processing Methods 0.000 claims description 20
- 230000001143 conditioned effect Effects 0.000 claims description 15
- 241001269238 Data Species 0.000 claims description 13
- 238000005286 illumination Methods 0.000 claims description 8
- 230000001537 neural effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 abstract description 6
- 238000010606 normalization Methods 0.000 description 7
- 230000004927 fusion Effects 0.000 description 6
- 238000001914 filtration Methods 0.000 description 5
- 230000007935 neutral effect Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000008921 facial expression Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
-
- 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
-
- 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
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
-
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
- F24F11/58—Remote control using Internet communication
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/10—Occupancy
- F24F2120/14—Activity of occupants
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides an intelligent control method, a device and a system, a plurality of sensors are distributed and controlled indoors and outdoors to collect indoor environment information, human body state information and outdoor environment information, multi-source information consisting of information collected by different types of sensors is input into a pre-constructed preset neural network model, and data input into the preset neural network model not only has indoor and indoor environment but also has environment and human body state measurement, so the sensor can realize diversified measurement of the surrounding environment information and the human body state information, the invention can fuse the multi-source information of the plurality of sensors, thereby accurately measuring the surrounding environment and the human body state of an air conditioner, the running state comprises human body comfort level, the air conditioning system is regulated and controlled by the human body comfort level, and the aim of regulating and controlling the air conditioner by people is realized, thereby ensuring that the indoor temperature, humidity and wind power are always kept in the most suitable living state of human bodies.
Description
Technical field
The present invention relates to technical field of automation, particularly relate to a kind of intelligent control method, Apparatus and system.
Background technology
At present, major part air-conditioning mainly gathers with the humiture of single Temperature Humidity Sensor to living environment, and using single humiture as major regulatory object, carry out cooling to control when temperature is higher, carry out intensification when the temperature is low to control, but single humidity temperature pickup accurately can not reflect the humiture situation of living environment, so the humiture of living environment can not be controlled well, often need user through repeatedly adjusting temperature, the humidity of air-conditioning and sweeping landscape condition, the indoor environment be relatively suitable for could be determined.
Such as: when user just returns in hot environment outdoor, air-conditioner temperature is adjusted to 20 degree, after a period of time, user can feel colder, need again to adjust air-conditioner temperature to 25 and spend, after a period of time may having been spent again, again air-conditioner temperature can be adjusted to 27 degree ...So airconditioning control of the prior art is main is benchmark with temperature, there is no that people-oriented.
So need a kind of method of the Based Intelligent Control indoor temperature and humidity that people-oriented, to ensure that indoor temperature, humidity and wind-force remain at the state of human body optimum inhabitation.
Summary of the invention
The invention provides a kind of intelligent control method, Apparatus and system, can ensure that indoor temperature, humidity and wind-force remain at the state of human body optimum inhabitation.
To achieve these goals, the invention provides following technological means:
A kind of intelligent control method, be applied to intelligence control system, described system comprises: be arranged at indoor at least one and gather the sensor of indoor environment state and the sensor of at least one collection body state, be arranged at the sensor that outdoor at least one gathers outdoor environment state, the processor be connected with multiple sensors of indoor and outdoor, described method comprises:
Many groups sensing data that the multiple sensors obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Neural network model is preset in the input of described many group sensing datas, and described default neural network model is in advance through at least one group of training sample training, with the model of the running status of air-conditioning for exporting, wherein running status comprises human comfort;
Current running status is exported, by described current running status adjustment air-conditioning system after described default neural network model computing.
Preferably, described human comfort comprises at least one comfort level.
Preferably, when described human comfort comprises a comfort level, using this comfort level as current comfort level, comprise by current running status adjustment air-conditioning system:
Judge whether described current comfort level is greater than predetermined level;
If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning;
If described current comfort level is less than described predetermined level, then with the gap size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level.
Preferably, when described human comfort comprises at least two comfort level, comprise by described current running status adjustment air-conditioning system:
Obtain at least two comfort level in described current running status;
The multiple basic confidence level corresponding with each comfort level is obtained respectively, the corresponding one group of sensing data of one of them sample space in different sample space;
Multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level;
When meeting pre-conditioned, obtain the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level;
Judge whether described current comfort level is greater than predetermined level;
If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning;
If described current comfort level is less than described predetermined level, then with the gap size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level.
Preferably, judge that meeting pre-conditioned process comprises:
Solve belief function and the plausibility function of each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result;
Using the difference between described plausibility function value and described belief function value as nondeterministic function value;
When described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
Preferably, the described running status presetting neural network model also comprises:
Optimum temperature value, optimal wet angle value and best wind-force value;
Preferably, comprise by described current running status adjustment air-conditioning system:
Described air-conditioning system is regulated and controled by the optimum temperature value in current running status, optimal wet angle value and best wind-force value.
Preferably, the building process of described default neural network model comprises:
The neuronal quantity of input layer, hidden layer and output layer in setting neural network model, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Obtain one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
By the raw sample data input neural network model of one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
If the error of running status undetermined and target operation state is less than threshold value, sample training terminates, otherwise restarts sample training, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations after amendment weights and threshold;
The neural network model built by current weights and threshold is as described default neural network model.
Preferably, described multiple sensing data comprises:
Be arranged at the warm and humid angle value of indoor at least one Temperature Humidity Sensor collection, the temperature value of at least one infrared temperature-test sensor collection;
Be arranged at the warm and humid angle value of outdoor at least one Temperature Humidity Sensor collection and the illumination intensity value of at least one intensity of illumination sensor collection.
A kind of intelligent controlling device, be applied to intelligence control system, described system comprises: be arranged at indoor at least one and gather the sensor of indoor environment state and the sensor of at least one collection body state, be arranged at the sensor that outdoor at least one gathers outdoor environment state, the processor be connected with multiple sensors of indoor and outdoor, described device comprises:
Obtain data cell, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Input block, for neural network model is preset in the input of described many group sensing datas, described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting;
Processing unit, for exporting current running status after described default neural network model computing, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
Preferably, described processing unit comprises:
First processing unit, during for judging that described human comfort comprises a comfort level, judges whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
Second processing unit, when comprising at least two comfort level for described running status, obtains at least two comfort level in described running status; The multiple basic confidence level corresponding with each comfort level is obtained respectively, the corresponding one group of sensing data of one of them sample space in different sample space; Multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level; When meeting pre-conditioned, obtain the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level; Judge whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
3rd processing unit, during for also comprising optimum temperature value, optimal wet angle value and best wind-force value in running status, by air-conditioning system described in the optimum temperature value in current running status, optimal wet angle value and the control of best wind-force value.
Preferably, second processing unit comprises: condition judgment unit, for solving belief function and the plausibility function of each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result; Using the difference between described plausibility function value and described belief function value as nondeterministic function value; When described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
Preferably, also comprise:
Build the construction unit presetting neural network model; Described construction unit comprises:
Initialization unit, for setting the neuronal quantity of input layer in neural network model, hidden layer and output layer, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, and the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Obtain sample unit, for obtaining one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
Integrated unit, for the raw sample data input neural network model by one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
Judging unit, if be less than threshold value for the error of running status undetermined and target operation state, sample training terminates, otherwise restart sample training after amendment weights and threshold, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations;
Complete unit, for the neural network model that built by current weights and threshold as described default neural network model.
A kind of intelligence control system, comprising:
Multiple sensor, the processor be connected with described multiple sensor, described multiple sensor comprises sensor of at least one collection indoor environment state and the sensor of at least one collection body state of being arranged at indoor, is arranged at the sensor of at least one outdoor collection outdoor environment state;
Described processor, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor; Neural network model is preset in the input of described many group sensing datas, and described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting; After described default neural network model computing, export current running status, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
Preferably, also comprise multiple sensor interface, multiple sensor interface is for connecting each sensor and processor.
The invention provides a kind of intelligent control method, the method is applied to intelligence control system, native system is used for gathering the environmental information of indoor environmental information, body state information and outdoor at indoor and outdoor multiple sensor of having deployed to ensure effective monitoring and control of illegal activities, the multi-source information of the information composition that dissimilar sensor is gathered, by the default neural network model that multi-source information input builds in advance, the current running status of air-conditioning will be exported after Multi-source Information Fusion, using the foundation of current running status as regulation and control air-conditioning system through model.
Indoor also have outdoor because the data inputing to default neural network model not only have, also having of measurement environment is not only had to measure body state, so sensor of the present invention can realize equably, diversely measure ambient condition information and body state information, the multi-source information of multiple sensor can be merged with traditional single Temperature Humidity Sensor the present invention, thus can Measurement accuracy air-conditioning surrounding environment and body state, and current running status comprises human comfort, with human comfort regulation and control air-conditioning system, thus realize people-oriented regulation and control air-conditioning object, thus guarantee indoor temperature, humidity and wind-force remain at the state that human body optimum is lived.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The structural representation of Fig. 1 a kind of intelligence control system disclosed in the embodiment of the present invention;
The flow chart of Fig. 2 a kind of intelligent control method disclosed in the embodiment of the present invention;
Fig. 3 is the flow chart of the embodiment of the present invention another intelligent control method disclosed;
Fig. 4 is the flow chart of the embodiment of the present invention another intelligent control method disclosed;
Fig. 5 is the flow chart of the embodiment of the present invention another intelligent control method disclosed;
Fig. 6 is the flow chart of the embodiment of the present invention another intelligent control method disclosed;
Fig. 7 is the structural representation of the embodiment of the present invention another intelligence control system disclosed;
The schematic diagram of neural network model is preset in Fig. 8 a kind of intelligent control method disclosed in the embodiment of the present invention;
Fig. 9 is the structural representation of the embodiment of the present invention another intelligence control system disclosed;
The structural representation of Figure 10 a kind of intelligent controlling device disclosed in the embodiment of the present invention;
Figure 11 is the structural representation of the embodiment of the present invention another intelligent controlling device disclosed;
Figure 12 is the structural representation of the embodiment of the present invention another intelligent controlling device disclosed.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, the invention provides a kind of intelligence control system, system comprises:
Be arranged at the sensor 101 that indoor at least one gathers indoor environment state, be called for short sensor group A;
Be arranged at the sensor 102 that indoor at least one gathers body state, be called for short sensor group B;
Be arranged at the sensor 103 that outdoor at least one gathers outdoor environment state, be called for short sensor group C;
The processor 100 be connected with multiple sensors of indoor and outdoor.
When specific implementation, the sensor of indoor and outdoor surroundings can be temperature sensor, humidity sensor or Temperature Humidity Sensor, be mainly used to the humiture gathering indoor and outdoor, in addition the outdoor intensity of illumination also having intensity of illumination sensor to be used for outside sensing chamber, the sensor gathering body state comprises infrared temperature-test sensor, be used for gathering the temperature of human body, sensor and/or the ccd sensor of human body humidity can be had in addition, be mainly used to gather the humidity of human body and/or the facial expression of human body, the data that all sensors collect are referred to as multiple sensing data.
All sensors are all connected with processor 100 by sensor interface, processor 100 carries out pretreatment to multiple sensing data in advance, such as AD conversion and filtering process, conveniently carry out follow-up process, generally also needs to be normalized multiple sensing data.
As shown in Figure 2, the present invention additionally provides a kind of intelligent control method on the basis of above-mentioned intelligence control system, and described method comprises:
Step S101: many groups sensing data that the multiple sensors obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Many groups sensing data comprises: characterize the sensing data of indoor environment state, characterize the sensing data of outdoor environment state and characterize the sensing data of body state.
Comprise when specific implementation: the temperature value that the warm and humid angle value that at least one indoor Temperature Humidity Sensor gathers, at least one infrared temperature-test sensor gather, the warm and humid angle value that at least one outdoor Temperature Humidity Sensor gathers and the illumination intensity value that at least one intensity of illumination sensor gathers; When being provided with the sensor of the sensor of humidity of human body and human body face expression, multiple sensing data also comprises human body humidity value and facial expression data.
Step S102: neural network model is preset in the input of described many group sensing datas, described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting;
Built in advance before the present invention performs and preset neural network model, and utilize training sample to train default neural network model, make default neural network model can export the current running status of air-conditioning according to sensing data.Wherein, training sample comprises training sensing data and the training running status under training sensing data, utilize training sample neural network training model, make neural network model after input training sensing data, the training running status of air-conditioning can be exported.
Step S103: export current running status after described default neural network model computing, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
When specifically using, multiple sensing datas of multiple sensor collections of indoor and outdoor are inputed in default neural network model, the current running status of this model prediction is exported after default neural network model calculates, then processor is according to the parameters of current running status adjustment air-conditioning system, to regulate and control air-conditioning the reaching running status that human body is comparatively suitable for.
Running status comprises human comfort, exports current human comfort, utilize the size of gap between current human comfort with default human comfort to carry out corresponding adjustment to air-conditioning system after presetting neural network model computing.
The invention provides a kind of method of Based Intelligent Control temperature, the method is applied to intelligence control system, native system is used for gathering the environmental information of indoor environmental information, body state information and outdoor at indoor and outdoor multiple sensor of having deployed to ensure effective monitoring and control of illegal activities equably, the multi-source information of the information composition that dissimilar sensor is gathered, by the default neural network model that multi-source information input builds in advance, the current running status of air-conditioning will be exported after Multi-source Information Fusion, using the foundation of current running status as regulation and control air-conditioning system through model.
Indoor also have indoor because the data inputing to default neural network model not only have, also having of measurement environment is not only had to measure body state, so sensor of the present invention can realize equably, diversely measure ambient condition information and body state information, the multi-source information of multiple sensor can be merged with traditional single Temperature Humidity Sensor the present invention, thus can Measurement accuracy air-conditioning surrounding environment and body state, and running status comprises human comfort, with human comfort regulation and control air-conditioning system, thus realize people-oriented regulation and control air-conditioning object, thus guarantee indoor temperature, humidity and wind-force remain at the state that human body optimum is lived.
Obtain human comfort in above-mentioned Fig. 2 in step S103 and comprise at least one comfort level, comfort level is for representing under multiple sensing datas of input, the degree that human body sensory is comfortable, comfort level is higher, represents that human comfort is better, wherein, the total quantity of comfort level can be set according to situation by technical staff, be understandable that, the total quantity of the comfort level of setting is more, and accuracy is higher.
Introduce the process by described running status adjustment air-conditioning system below in detail, as shown in Figure 3, comprising:
Step S201: when described human comfort comprises a comfort level, using this comfort level as current comfort level;
When only there being a comfort level in human comfort, show that this neural network model is after reception many groups sensing data, only can export a comfort level according to many group sensing datas, this comfort level can react the relation of the current running status of air-conditioning and human comfort, namely current comfort level is higher, represent that human comfort is better, current comfort level is lower, represents that human comfort is poorer.
Step S202: judge whether described current comfort level is greater than predetermined level; If be greater than, then enter step S203, if be less than, enter step S204;
Judge whether current comfort level is greater than predetermined level, predetermined level is preset a comparatively comfortable comfort level, if current comfort level is greater than predetermined level, represent that the current running status of air-conditioning is good, without the need to adjustment, if current comfort level is less than predetermined level, the running status that then expression air-conditioning is current is poor, needs to carry out adjust operation state, so that the output of air-conditioning can reach the state that comparatively human body is comparatively suitable for.
Step S203: if described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning;
Step S204: if described current comfort level is less than described predetermined level, then carry out corresponding adjust with the gap size of described predetermined level to described air-conditioning system by described current comfort level.
When adjusting, if the gap between current comfort level and predetermined level is larger, now running status is poor to represent air-conditioning, then oppositely larger adjustment is carried out to air-conditioning, if gap is less between current comfort level and predetermined level, represent air-conditioning running status elementary errors now, then oppositely less adjustment is carried out to air-conditioning.
After presetting neural network model, obtaining human comfort grade in the present invention can be set as one or more, because acting as of default neural network model predicts current running status, namely there is inaccurate process in prediction, if human comfort only has a grade in the running status of setting, then because correct comfort level may be ignored by error, thus generation error, at least two comfort level will be set in running status to reduce error, so that first neural network model dopes at least two comfort level, and then further computing is carried out again at least two comfort level, thus obtain comfort level accurately, to improve the accuracy of comfort level.
Detailed introduction is in the process of carrying out further computing at least two comfort level below, as shown in Figure 4, comprising:
Step S301: obtain at least two comfort level in described current running status;
Be the comfort level obtained after the data of all the sensors are merged in the method that Fig. 2 is corresponding, conveniently describe, the comfort level in current running status is called S, comprising S1, S2 ... Deng.
Step S302: obtain the multiple basic confidence level corresponding with each comfort level respectively in different sample space, the corresponding one group of sensing data of one of them sample space;
In order to verify that whether comfort level S is correct, by the method for Fig. 2, many experiments is carried out to each sensing data in multiple sensing data below, a corresponding sample space of sensing data, multiple comfort level M that many experiments exports are obtained in a sample space Y1, comprising M1, M2 ... Deng, to occur in M that the probability of S1 is called the basic confidence level for S1 of this sample space, to occur in M that the probability of S2 is called the basic confidence level for S2 in this sample space, the like.
Basic confidence level is the probability occurring comfort level S in sample space, and probability height higher expression comfort level is more accurate.In the same way, the basic confidence level in each sample space can be obtained.
Obtain the comfort level in different sample space as stated above, Y1S1 represents the basic confidence level that comfort level S1 is corresponding in Y1 sample, Y1S2 represents the basic confidence level of the correspondence of comfort level S2 in Y1 sample, the like, obtain the basic confidence level of each comfort level in different sample space.
Step S303: multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level;
The basic reliability function of different sample spaces is merged, tries to achieve the combined value of all sample space middle grades for a comfort level.For comfort level S1, by Y1S1, Y2S1, Y3S1 ... YNS1 merges, and obtaining comfort level is the pooled function of S1, in like manner, the pooled function that comfort level is S2 can be obtained, the like, obtain the pooled function of each comfort level.
Step S304: when meeting pre-conditioned, obtains the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level.
Pooled function corresponding for each comfort level in step S303 is sorted by size, using comfort level corresponding for the maximum of pooled function as current human's comfort level.The maximum probability of comfort level in different sample space of the maximum correspondence of pooled function, is this comfort level and can meets each sample spaces more.
Wherein, judge to meet pre-conditioned process, comprise the following steps as shown in Figure 5:
Step S401: the belief function and the plausibility function that solve each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result;
Step S402: using the difference between described plausibility function value and described belief function value as nondeterministic function value;
Step S403: when described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
Namely obtain qualitative probabilistic really for pooled function and must be greater than uncertain probability, can confirm that this comfort level is that can determine, satisfactory comfort level.
After obtaining current comfort level, perform by described current running status adjustment air-conditioning system, concrete implementation is consistent with the step shown in Fig. 3, does not repeat them here.In above-mentioned control procedure, processor is the processor of air-conditioning system, the direct pick-up transducers data of processor of air-conditioning system are gone forward side by side row relax, in addition, processor can also be the processor existed independent of air-conditioning system, after processor obtains current running status, current running status is sent to air-conditioner controller, so that air-conditioner controller controls self according to current running status, no matter which kind of mode can realize the present invention.
Above-described embodiment is the process introduced with human comfort regulation and control air-conditioning system, introduce another control mode below, the running status presetting neural network model also comprises: optimum temperature value, optimal wet angle value and best wind-force value, namely after multiple sensing data is inputed to default neural network model, neural network model can calculate according to multiple sensing data, export the optimum temperature value of now Neural Network model predictive, optimal wet angle value and best wind-force value, directly utilize optimum temperature value, optimal wet angle value and best wind-force value regulator control system can realize the object that air-conditioning is in optimum state.Introduce the building process of the default neural network model in Fig. 2 in step S102 below in detail, as shown in Figure 6, comprise the following steps:
Step S501: neural network model is initialized, initialized process comprises the neuronal quantity of input layer, hidden layer and output layer in setting neural network model, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Before carrying out the present invention, obtain the model of air-conditioning; The number of sensors that inquiry is corresponding with this model in presetting database; Using the training sample of the initial data consistent with number of sensors as this air-conditioning.Due to the quantity of sensor and the refrigerating capacity one_to_one corresponding of air-conditioning, so after model is determined, just the number of sensors that use of this product can be obtained in presetting database, after number of sensors is determined, just can in presetting database, search the raw sample data consistent with number of sensors, to carry out neural network computing for this product.
First neural network model is initialized, the neuronic quantity of setting input layer, input layer quantity is consistent with the multiple number of sensors used in the present invention, then the quantity of output layer is set, because the present invention needs output temperature value, humidity value, wind-force value and human comfort four parameters, so output layer neuronal quantity is four, middle hidden layer quantity can be determined according to the use algorithm of technical staff, resets the weights between each layer.
Such as: the weights between input layer and hidden layer are A, so hidden layer=input layer * A, the size of weights represent two-layer between relation, when inputting constant, can the Output rusults of adjustment model by adjusting weights in default neural network model.
Step S502: obtain one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
Training sample can be obtained by step S501, training sample comprises the running status of raw sample data and air-conditioning, wherein running status is judge the running status that air-conditioning should have under raw sample data according to Expert Rules, comprising the value of temperature, the value of humidity, the value of wind-force and human comfort.
Step S503: by the raw sample data input neural network model of one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
Preferably, before raw sample data inputs to neutral net, described raw sample data can be carried out pretreatment and normalized, described raw sample data is carried out pretreated process and comprise AD conversion and filtering process, after pretreatment and normalized are carried out to data, can greatly facilitate follow-up processing procedure, and can accuracy be improved.
Using the input of raw sample data as neutral net, preset neural network model by raw sample data through input layer, hidden layer and output layer, and fusion is weighted between each layer, four Output rusults of running status undetermined will be obtained after Multi-source Information Fusion, be respectively temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined.
Step S504: judge whether the error of running status undetermined and target operation state is less than threshold value, or current number of times reaches iterations, as long as meet one of them condition then enter step S505, if two conditions do not meet, after iterations adds one, enter step S503;
Step S505: training terminates.
Wherein, judge that the error of running status undetermined and target operation state is less than threshold process and comprises: judge that the error between described temperature value undetermined and described optimum temperature value is less than described threshold value; Judge that the error between described humidity value undetermined and described optimal wet angle value is less than described threshold value; Judge that the error between described wind-force value undetermined and described best wind-force value is less than described threshold value.
If the error of running status undetermined and optimal operational condition is less than described threshold value, sample training terminates, otherwise restarts sample training, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations after amendment weights and threshold; The neural network model built by current weights and threshold after training terminates is as described default neural network model.
If the error of running status undetermined and target operation state is less than threshold value, then show that error is between the two in the scope that can receive, just training process can be terminated, otherwise, think that the too large continuation of error is trained neural network model, until terminate training when error is in preset range, the object of training is to revise weights and threshold to make the error of running status undetermined and running status in preset range, after the certain number of times of training, error between running status undetermined and running status does not also reach in preset range, prove that error cannot reach in preset range by this training process, so terminate this training.
After one group of training sample terminates, also comprise: the initial data obtaining many group training samples; The initial data of described many group training samples is pressed respectively to the training method in Fig. 6, one by one described default neural network model is trained, to revise described weights and threshold.
In order to ensure that default neural network model can be applicable to different sensing datas, organize training sample so can obtain again more, and utilize training sample to train default neutral net one by one, constantly to revise weights and threshold, make this default neural network model can be more accurate, can running status corresponding to the polytype sensing data of Accurate Prediction.
The process that neural network model preset by above-mentioned structure is the process of multiple sensing data being carried out information fusion, and the default neural network model of formation can when input be determined, the running status that prediction exports.
Introduce specific embodiments of the invention below:
As shown in Figure 7, be general structure block diagram provided by the invention.
To distribute N number of sensor 104 in indoor and outdoor, some Temperature Humidity Sensors are uniformly distributed according to indoor design condition environment, in order to detect indoor temperature and humidity conditions, be uniformly distributed Temperature Humidity Sensor, in order to detect running state of air conditioner according to running state of air conditioner at air-conditioning internal machine and outer machine; Temperature Humidity Sensor and optical sensor is uniformly distributed in outdoor, for detecting outdoor temperature and humidity conditions according to outdoor situations; According to people life actual conditions at the some infrared temperature-test sensors of indoor location, in order to human body temperature regime.
Above-mentioned N number of sensor signal needs to carry out pretreatment and normalization, and wherein pretreatment comprises A/D conversion, filtering, amplification and rejects the computings such as gross error, is normalized pretreated data again.
Normalization algorithm can adopt linear normalization algorithm, that is:
wherein x, y are the value before and after normalization, x
max, x
minfor maximum and minimum of a value in the sample that all the sensors goes out to export.
Sample data after normalization carries out Algorithm Analysis and use processing by processor 100.Data can be inputted to reality by the intelligent algorithm after training and make different predictions, thus export optimum temperature, humidity and wind-force value, build the environment that optimum people lives.When processor 100 carries out decision data according to multiple sensor signals, decision-making is carried out in the suggestion that can provide in conjunction with expert system.
Primary data sample data are by testing collection, neural network model after primary data sample training may be variant with practical application, therefore intelligent air condition can carry out secondary study according to practical operation situation, continuous calibration neural network model parameter, intelligent air condition is made to be in the state not only predicted but also learn, Continual Improvement parameter, constantly needs most living environment close to people.
As shown in Figure 8, be BP neural network model in the present embodiment, training sample set obtains by experiment, according to type coupling, can the quantity of certainty annuity sensor, thus the number of input amendment of determining at every turn to sample, namely determine input layer number.
If training sample set is X=[X
1, X
2..., X
k..., X
m], a certain training sample: Xk=[x
k1, x
k2..., x
kN]
t, (k=1,2 ..., N), actual output is: Y
k=[y
k1, y
k2, y
k3, y
k4]
t, desired output is d
k=[d
k1, d
k2, d
k3, d
k4]
t.If n is iterations, weights and actual output are the functions of n.
For the weights and threshold initialize of neural network model, the random number that initial value is less than 1.Input amendment data, note iterations is n=0, calculates BP network every layer of neuronic input signal u and output signal v, if the excitation function of hidden layer and output layer is respectively f
1() and f
2(), then neutral net exports and is
q neuronic error signal is e
kq(n)=d
kq(n)-y
kq(n), wherein q=1,2,3,4.
Now choosing excitation function is S type function, namely
According to error signal e
kjn () revises the weights between hidden layer and output layer, the weights of any node on any node and hidden layer on input layer.Until error no longer carries out repetitive exercise after meeting zone of reasonableness.Modified weight amount between hidden layer and output layer is Δ w
jp(n)==η δ
j(n) v
jn (), on input layer, on any node and hidden layer, the modified weight amount of any node is Δ w
mi(n)=-η δ
i(n) x
km(n).
Neutral net output layer has four nodes, i.e. Y
k=[y
k1, y
k2, y
k3, y
k4]
t, represent temperature, humidity, wind-force and human comfort respectively.
For the D-S evidence theory algorithm flow chart in the control strategy of the intelligent air condition based on Multi-source Information Fusion and implementation method, concrete steps are as follows:
(1) be some grade S to human comfort grade classification
i(i=1,2,3 ..., N), formation hypothesis space is S={S
1, S
2, S
n, wherein N is divided rank number.
(2) by aforementioned neurological training sample data, human comfort grade S in certain sample space is obtained
i, obtain the basic confidence level m of different sample space
j(S
i), namely obtain mass function.Obtain its uncertain probability m simultaneously
j(U
i).
(3) according to Dempster-Shafer composite formula, mass function m is merged
j(S
i), namely
Its
(4) by above-mentioned merging mass function, belief function and plausibility function bel (S is solved
i) and pl (S
i).Solution formula is as follows:
(5) rule of human comfort is judged:
1. uncertain probability m
j(U
i) a certain threshold gamma must be less than;
2. belief function bel (S
i) uncertain probability m must be greater than
j(U
i);
1. and 2. 3. meet under condition, merge mass function m
j(S
i) in maximum be namely judged to be current human comfort level S
i.
(6) according to judged result, Intelligent air conditioner control system will make corresponding adjustment.Adjustment grade is determined according to human comfort grade.If when human comfort is very poor, then intelligent air-conditioning system will make larger adjustment to temperature, humidity, wind-force and wind direction; Otherwise, if human comfort is fine, then adjusts less or keep current operating conditions.
Fig. 9 is signal wiring schematic diagram provided by the invention.As shown in Figure 9, the sensor interface 105 of processor can be expanded, n expansion is carried out according to real sensor quantity and kind, each sensor interface 105 can connect i sensor, sensor signal is after A/D, filtering and the process of normalization scheduling algorithm, carry out intelligent algorithm calculating again, draw method for optimally controlling, to control the operation of air-conditioning.
The number of sensors of whole intelligent air-conditioning system and kind are different because actual application environment is different, therefore air-conditioner controller hardware and software design needs to make corresponding adjustment, design multiple sensor acquisition interface, and carry out A/D, filtering and the process of normalization scheduling algorithm.In order to without loss of generality, air-conditioner controller peripheral interface circuit can carry out hardware expanding as required, and software programming will have corresponding redundancy program.
As shown in Figure 10, present invention also offers a kind of intelligent controlling device, be applied to the intelligence control system shown in Fig. 1, comprise:
Obtain data cell 11, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Input block 12, for neural network model is preset in the input of described many group sensing datas, described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting;
Processing unit 13, for exporting current running status after described default neural network model computing, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
As shown in figure 11, described processing unit 13 comprises:
First processing unit 131, during for judging that described human comfort comprises a comfort level, judges whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
Second processing unit 132, when comprising at least two comfort level for described running status, obtains at least two comfort level in described running status; The multiple basic confidence level corresponding with each comfort level is obtained respectively, the corresponding one group of sensing data of one of them sample space in different sample space; Multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level; When meeting pre-conditioned, obtain the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level; Judge whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
3rd processing unit 133, during for also comprising optimum temperature value, optimal wet angle value and best wind-force value in running status, by air-conditioning system described in the optimum temperature value in current running status, optimal wet angle value and the control of best wind-force value.
Wherein, second processing unit 132 comprises: condition judgment unit, for solving belief function and the plausibility function of each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result; Using the difference between described plausibility function value and described belief function value as nondeterministic function value; When described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
As shown in figure 12, a kind of intelligent controlling device that the present invention also provides also comprises the construction unit 14 building and preset neural network model; Described construction unit 14 comprises:
Initialization unit 21, for setting the neuronal quantity of input layer in neural network model, hidden layer and output layer, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, and the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Obtain sample unit 22, for obtaining one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
Integrated unit 23, for the raw sample data input neural network model by one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
Judging unit 24, if be less than threshold value for the error of running status undetermined and target operation state, sample training terminates, otherwise restart sample training after amendment weights and threshold, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations;
Complete unit 25, for the neural network model that built by current weights and threshold as described default neural network model.
As shown in Figure 1, present invention also offers a kind of intelligence control system, comprising:
Multiple sensor 101 (102,103), the processor 100 be connected with described multiple sensor, described multiple sensor comprises sensor of at least one collection indoor environment state and the sensor of at least one collection body state of being arranged at indoor, is arranged at the sensor of at least one outdoor collection outdoor environment state;
Described processor 100, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor; Neural network model is preset in the input of described many group sensing datas, and described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting; After described default neural network model computing, export current running status, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
Wherein, described multiple sensor is connected by sensor interface with between described processor.Described system also comprises multiple sensor interface, and each sensor interface is connected with multiple sensor, for transmitting the sensing data that multiple sensor gathers.
If the function described in the present embodiment method using the form of SFU software functional unit realize and as independently production marketing or use time, can be stored in a computing equipment read/write memory medium.Based on such understanding, the part of the part that the embodiment of the present invention contributes to prior art or this technical scheme can embody with the form of software product, this software product is stored in a storage medium, comprising some instructions in order to make a computing equipment (can be personal computer, server, mobile computing device or the network equipment etc.) perform all or part of step of method described in each embodiment of the present invention.And aforesaid storage medium comprises: USB flash disk, portable hard drive, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. various can be program code stored medium.
In this description, each embodiment adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiment, between each embodiment same or similar part mutually see.
To the above-mentioned explanation of the disclosed embodiments, professional and technical personnel in the field are realized or uses the present invention.To be apparent for those skilled in the art to the multiple amendment of these embodiments, General Principle as defined herein can without departing from the spirit or scope of the present invention, realize in other embodiments.Therefore, the present invention can not be restricted to these embodiments shown in this article, but will meet the widest scope consistent with principle disclosed herein and features of novelty.
Claims (15)
1. an intelligent control method, it is characterized in that, be applied to intelligence control system, described system comprises: be arranged at indoor at least one and gather the sensor of indoor environment state and the sensor of at least one collection body state, be arranged at the sensor that outdoor at least one gathers outdoor environment state, the processor be connected with multiple sensors of indoor and outdoor, described method comprises:
Many groups sensing data that the multiple sensors obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Neural network model is preset in the input of described many group sensing datas, and described default neural network model is in advance through at least one group of training sample training, with the model of the running status of air-conditioning for exporting, wherein running status comprises human comfort;
Current running status is exported, by described current running status adjustment air-conditioning system after described default neural network model computing.
2. the method for claim 1, is characterized in that, described human comfort comprises at least one comfort level.
3. method as claimed in claim 2, is characterized in that, when described human comfort comprises a comfort level, using this comfort level as current comfort level, comprises by current running status adjustment air-conditioning system:
Judge whether described current comfort level is greater than predetermined level;
If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning;
If described current comfort level is less than described predetermined level, then with the gap size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level.
4. method as claimed in claim 2, is characterized in that, when described human comfort comprises at least two comfort level, comprises by described current running status adjustment air-conditioning system:
Obtain at least two comfort level in described current running status;
The multiple basic confidence level corresponding with each comfort level is obtained respectively, the corresponding one group of sensing data of one of them sample space in different sample space;
Multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level;
When meeting pre-conditioned, obtain the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level;
Judge whether described current comfort level is greater than predetermined level;
If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning;
If described current comfort level is less than described predetermined level, then with the gap size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level.
5. method as claimed in claim 4, is characterized in that, judges that meeting pre-conditioned process comprises:
Solve belief function and the plausibility function of each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result;
Using the difference between described plausibility function value and described belief function value as nondeterministic function value;
When described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
6. the method for claim 1, is characterized in that, the described running status presetting neural network model also comprises:
Optimum temperature value, optimal wet angle value and best wind-force value.
7. method as claimed in claim 6, is characterized in that, comprises by described current running status adjustment air-conditioning system:
Described air-conditioning system is regulated and controled by the optimum temperature value in current running status, optimal wet angle value and best wind-force value.
8. method as claimed in claim 6, it is characterized in that, the building process of described default neural network model comprises:
The neuronal quantity of input layer, hidden layer and output layer in setting neural network model, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Obtain one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
By the raw sample data input neural network model of one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
If the error of running status undetermined and target operation state is less than threshold value, sample training terminates, otherwise restarts sample training, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations after amendment weights and threshold;
The neural network model built by current weights and threshold is as described default neural network model.
9. the method for claim 1, is characterized in that, described multiple sensing data comprises:
Be arranged at the warm and humid angle value of indoor at least one Temperature Humidity Sensor collection, the temperature value of at least one infrared temperature-test sensor collection;
Be arranged at the warm and humid angle value of outdoor at least one Temperature Humidity Sensor collection and the illumination intensity value of at least one intensity of illumination sensor collection.
10. an intelligent controlling device, it is characterized in that, be applied to intelligence control system, described system comprises: be arranged at indoor at least one and gather the sensor of indoor environment state and the sensor of at least one collection body state, be arranged at the sensor that outdoor at least one gathers outdoor environment state, the processor be connected with multiple sensors of indoor and outdoor, described device comprises:
Obtain data cell, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor;
Input block, for neural network model is preset in the input of described many group sensing datas, described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting;
Processing unit, for exporting current running status after described default neural network model computing, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
11. devices as claimed in claim 10, it is characterized in that, described processing unit comprises:
First processing unit, during for judging that described human comfort comprises a comfort level, judges whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
Second processing unit, when comprising at least two comfort level for described running status, obtains at least two comfort level in described running status; The multiple basic confidence level corresponding with each comfort level is obtained respectively, the corresponding one group of sensing data of one of them sample space in different sample space; Multiple basic confidence level corresponding at least two comfort level merged by Dempster-Shafer formula respectively, obtain at least two pooled functions, one of them pooled function is corresponding with a comfort level; When meeting pre-conditioned, obtain the functional value of at least two pooled functions, using comfort level corresponding for pooled function maximum for functional value as current comfort level; Judge whether described current comfort level is greater than predetermined level; If described current comfort level is greater than described predetermined level, then maintain the current running status of air-conditioning; If described current comfort level is less than described predetermined level, then with the error size of described predetermined level, corresponding adjustment is carried out to described air-conditioning system by described current comfort level;
3rd processing unit, during for also comprising optimum temperature value, optimal wet angle value and best wind-force value in running status, by air-conditioning system described in the optimum temperature value in current running status, optimal wet angle value and the control of best wind-force value.
12. devices as claimed in claim 11, it is characterized in that, second processing unit comprises: condition judgment unit, for solving belief function and the plausibility function of each comfort level respectively, wherein said belief function represents that comfort level result is genuine trusting degree, and described plausibility function represents the trusting degree of the non-vacation of comfort level result; Using the difference between described plausibility function value and described belief function value as nondeterministic function value; When described nondeterministic function value is less than preset value, and when the value of belief function is greater than nondeterministic function value, judgement meets pre-conditioned.
13. devices as claimed in claim 11, is characterized in that, also comprise:
Build the construction unit presetting neural network model; Described construction unit comprises:
Initialization unit, for setting the neuronal quantity of input layer in neural network model, hidden layer and output layer, sensing data, described input layer, weights initial between described hidden layer and described output layer, initial threshold value and iterations at the end of judging training, wherein, the quantity of the input layer of described neural network model is consistent with the quantity of multiple sensor, and the neuronic quantity of output layer is four, respectively corresponding temperature value, humidity value, wind-force value and human comfort;
Obtain sample unit, for obtaining one group of training sample, described training sample comprise multiple sensor raw sample data and under this raw sample data the target operation state of air-conditioning, described target operation state comprises optimum temperature value, optimal wet angle value, best wind-force value and human comfort current under raw sample data;
Integrated unit, for the raw sample data input neural network model by one group of training sample, after the weighted calculation of described input layer, described hidden layer and described output layer, export running status undetermined, described running status undetermined comprises temperature value undetermined, humidity value undetermined, wind-force value undetermined and human comfort undetermined;
Judging unit, if be less than threshold value for the error of running status undetermined and target operation state, sample training terminates, otherwise restart sample training after amendment weights and threshold, until the error of running status undetermined and target operation state is less than threshold value or reaches iterations;
Complete unit, for the neural network model that built by current weights and threshold as described default neural network model.
14. 1 kinds of intelligence control systems, is characterized in that, comprising:
Multiple sensor, the processor be connected with described multiple sensor, described multiple sensor comprises sensor of at least one collection indoor environment state and the sensor of at least one collection body state of being arranged at indoor, is arranged at the sensor of at least one outdoor collection outdoor environment state;
Described processor, many groups sensing data that the multiple sensors for obtaining described indoor and outdoor gather, the corresponding one group of sensing data of one of them sensor; Neural network model is preset in the input of described many group sensing datas, and described default neural network model is train through at least one group of training sample in advance, with the model of the running status of air-conditioning for exporting; After described default neural network model computing, export current running status, by described current running status adjustment air-conditioning system, wherein said running status comprises human comfort.
15. systems as claimed in claim 14, it is characterized in that, also comprise multiple sensor interface, multiple sensor interface is for connecting each sensor and processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410691067.4A CN104374053B (en) | 2014-11-25 | 2014-11-25 | Intelligent control method, device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410691067.4A CN104374053B (en) | 2014-11-25 | 2014-11-25 | Intelligent control method, device and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104374053A true CN104374053A (en) | 2015-02-25 |
CN104374053B CN104374053B (en) | 2017-02-22 |
Family
ID=52553119
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410691067.4A Active CN104374053B (en) | 2014-11-25 | 2014-11-25 | Intelligent control method, device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104374053B (en) |
Cited By (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104833063A (en) * | 2015-06-04 | 2015-08-12 | 安徽建筑大学 | Air conditioner control method and system |
CN105757882A (en) * | 2016-03-01 | 2016-07-13 | 中国建筑科学研究院 | Comprehensive control method and device for thermal comfort indoor environment |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
CN106770989A (en) * | 2017-03-15 | 2017-05-31 | 深圳智达机械技术有限公司 | A kind of effective IAQ assessment system |
CN107390754A (en) * | 2017-08-29 | 2017-11-24 | 贵州省岚林阳环保能源科技有限责任公司 | Intelligent plant growth environment adjustment system and method based on Internet of Things cloud platform |
CN107390753A (en) * | 2017-08-29 | 2017-11-24 | 贵州省岚林阳环保能源科技有限责任公司 | Intelligent plant growth environment regulating device and method based on Internet of Things cloud platform |
CN107477772A (en) * | 2017-07-21 | 2017-12-15 | 天津大学 | House VMC control method based on indoor monitoring data |
CN107833573A (en) * | 2017-10-23 | 2018-03-23 | 上海百芝龙网络科技有限公司 | A kind of home scenarios semantic understanding householder method based on machine learning |
CN107826027A (en) * | 2017-09-21 | 2018-03-23 | 山东大学 | Refrigerator car temprature control method and system based on big data analysis |
CN107844073A (en) * | 2017-09-15 | 2018-03-27 | 珠海格力电器股份有限公司 | Electronic equipment control method, device and system, storage medium and processor |
CN108036473A (en) * | 2017-11-30 | 2018-05-15 | 广东芬尼克兹节能设备有限公司 | A kind of intelligent temperature and humidity control method and device |
CN108181837A (en) * | 2017-11-28 | 2018-06-19 | 珠海格力电器股份有限公司 | Control method and control device |
CN105588274B (en) * | 2015-11-06 | 2018-09-25 | 青岛海信日立空调***有限公司 | A kind of natural wind control method and device |
WO2018214002A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Comfort range determination method, and apparatus |
WO2018214000A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Method for determining comfort range of indoor environment, and terminal apparatus |
WO2018214001A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Environment conditioning method, and server |
CN108931027A (en) * | 2018-08-01 | 2018-12-04 | 北京创思工贸有限公司 | A kind of visual remote monitoring control maintenance air-conditioning system |
CN109028402A (en) * | 2018-08-04 | 2018-12-18 | 浙江国芝科技有限公司 | The water-supply control of radiation air-conditioner, device and system |
CN109028480A (en) * | 2018-06-08 | 2018-12-18 | 杭州古北电子科技有限公司 | A kind of thermostatic constant wet control system and its method |
CN109140665A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力电器股份有限公司 | Method and device for controlling air conditioner and air conditioner device |
CN109164707A (en) * | 2018-09-28 | 2019-01-08 | 苏州市建筑科学研究院集团股份有限公司 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
CN109357352A (en) * | 2018-11-05 | 2019-02-19 | 四川长虹电器股份有限公司 | Air conditioner intelligent temperature control system and method based on Decision Tree Algorithm |
CN109376795A (en) * | 2018-11-19 | 2019-02-22 | 四川长虹电器股份有限公司 | Air conditioner intelligent temperature control method based on Decision Tree Algorithm |
CN109405195A (en) * | 2018-10-31 | 2019-03-01 | 四川长虹电器股份有限公司 | Air conditioner intelligent control system and method |
CN109489212A (en) * | 2018-11-21 | 2019-03-19 | 珠海格力电器股份有限公司 | Intelligent sleep control method, adjustment system and equipment for air conditioner |
CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
CN109695943A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | The temperature and humidity control system of coating air-conditioning based on big data deep learning |
CN110230866A (en) * | 2019-06-11 | 2019-09-13 | 陕西大疆电力科技有限公司 | One kind being used for indoor temperature and humidity intelligent control system |
CN110395286A (en) * | 2019-08-02 | 2019-11-01 | 中南大学 | A kind of train air quality in vehicle monitoring and divulge information regulation method, system |
CN110726220A (en) * | 2019-10-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
CN110726214A (en) * | 2019-10-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Method and device for controlling air conditioner |
CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技(深圳)有限公司 | Environment data adjusting method and device, electronic equipment and medium |
CN110822616A (en) * | 2018-08-13 | 2020-02-21 | 格力电器(武汉)有限公司 | Automatic air conditioner adjusting method and device |
CN110837229A (en) * | 2018-08-17 | 2020-02-25 | 珠海格力电器股份有限公司 | Control method and device for household appliance |
CN112050448A (en) * | 2020-08-18 | 2020-12-08 | 吉安职业技术学院 | Indoor temperature and humidity adjusting system of low-voltage apparatus controlled by PLC circuit |
CN112212481A (en) * | 2019-07-10 | 2021-01-12 | 中华电信股份有限公司 | System and method for controlling environmental comfort by deep reinforcement learning |
CN112484259A (en) * | 2020-12-04 | 2021-03-12 | 珠海格力电器股份有限公司 | Humidity control method and device, electronic equipment and storage medium |
CN112506059A (en) * | 2020-12-07 | 2021-03-16 | 常州常工电子科技股份有限公司 | Classroom self-adaptive control system based on energy-saving model of personal sensory comfort |
CN112947637A (en) * | 2021-01-29 | 2021-06-11 | 安徽佳美瑞物联科技有限公司 | Office environment intelligent regulation system |
CN113311892A (en) * | 2021-05-27 | 2021-08-27 | 中通服咨询设计研究院有限公司 | Optimal pre-cooling control method for energy efficiency of central air conditioner of exhibition venue |
CN113327219A (en) * | 2021-06-21 | 2021-08-31 | 易成功(厦门)信息科技有限公司 | Image processing method and system based on multi-source data fusion |
CN114265458A (en) * | 2022-01-05 | 2022-04-01 | 信息产业电子第十一设计研究院科技工程股份有限公司 | Method for realizing accurate control of air pipe temperature and humidity and room temperature and humidity |
CN114370696A (en) * | 2021-12-27 | 2022-04-19 | 杭州英集动力科技有限公司 | Method for controlling outlet water temperature of cooling tower of central air conditioner based on D-S evidence theory |
CN115272675A (en) * | 2022-07-29 | 2022-11-01 | 江苏磐鼎科技有限公司 | Energy management system and method based on multi-sensor information fusion |
-
2014
- 2014-11-25 CN CN201410691067.4A patent/CN104374053B/en active Active
Non-Patent Citations (2)
Title |
---|
谢春丽 夏虹 刘永阔: "基于神经网络D-S证据理论的汽轮机转子融合诊断***研究", 《应用科技》 * |
陈明忠: "BP神经网络训练算法的分析与比较", 《科技广场》 * |
Cited By (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104833063B (en) * | 2015-06-04 | 2017-12-01 | 安徽建筑大学 | Air conditioner control method and system |
CN104833063A (en) * | 2015-06-04 | 2015-08-12 | 安徽建筑大学 | Air conditioner control method and system |
CN105588274B (en) * | 2015-11-06 | 2018-09-25 | 青岛海信日立空调***有限公司 | A kind of natural wind control method and device |
CN105757882A (en) * | 2016-03-01 | 2016-07-13 | 中国建筑科学研究院 | Comprehensive control method and device for thermal comfort indoor environment |
CN106322656A (en) * | 2016-08-23 | 2017-01-11 | 海信(山东)空调有限公司 | Air conditioner control method, server and air conditioner system |
CN106322656B (en) * | 2016-08-23 | 2019-05-14 | 海信(山东)空调有限公司 | A kind of air conditioning control method and server and air-conditioning system |
CN106770989A (en) * | 2017-03-15 | 2017-05-31 | 深圳智达机械技术有限公司 | A kind of effective IAQ assessment system |
CN106770989B (en) * | 2017-03-15 | 2019-05-10 | 江西佳信房地产资产评估有限公司 | A kind of effective indoor air quality assessment system |
WO2018214000A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Method for determining comfort range of indoor environment, and terminal apparatus |
WO2018214001A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Environment conditioning method, and server |
WO2018214002A1 (en) * | 2017-05-22 | 2018-11-29 | 深圳微自然创新科技有限公司 | Comfort range determination method, and apparatus |
CN107477772A (en) * | 2017-07-21 | 2017-12-15 | 天津大学 | House VMC control method based on indoor monitoring data |
CN107390753A (en) * | 2017-08-29 | 2017-11-24 | 贵州省岚林阳环保能源科技有限责任公司 | Intelligent plant growth environment regulating device and method based on Internet of Things cloud platform |
CN107390754A (en) * | 2017-08-29 | 2017-11-24 | 贵州省岚林阳环保能源科技有限责任公司 | Intelligent plant growth environment adjustment system and method based on Internet of Things cloud platform |
CN107390754B (en) * | 2017-08-29 | 2019-07-30 | 贵州省岚林阳环保能源科技有限责任公司 | Intelligent plant growth environment adjustment system and method based on Internet of Things cloud platform |
CN107844073B (en) * | 2017-09-15 | 2018-12-07 | 珠海格力电器股份有限公司 | Electronic equipment control method, device and system, storage medium and processor |
CN107844073A (en) * | 2017-09-15 | 2018-03-27 | 珠海格力电器股份有限公司 | Electronic equipment control method, device and system, storage medium and processor |
CN107826027B (en) * | 2017-09-21 | 2019-09-03 | 山东大学 | Refrigerator car temprature control method and system based on big data analysis |
CN107826027A (en) * | 2017-09-21 | 2018-03-23 | 山东大学 | Refrigerator car temprature control method and system based on big data analysis |
CN107833573A (en) * | 2017-10-23 | 2018-03-23 | 上海百芝龙网络科技有限公司 | A kind of home scenarios semantic understanding householder method based on machine learning |
CN107833573B (en) * | 2017-10-23 | 2021-02-09 | 上海百芝龙网络科技有限公司 | Machine learning-based family scene semantic understanding auxiliary method |
CN108181837A (en) * | 2017-11-28 | 2018-06-19 | 珠海格力电器股份有限公司 | Control method and control device |
CN108181837B (en) * | 2017-11-28 | 2020-11-27 | 珠海格力电器股份有限公司 | Control method and control device |
CN108036473B (en) * | 2017-11-30 | 2020-05-05 | 广东芬尼克兹节能设备有限公司 | Intelligent temperature and humidity control method and device |
CN108036473A (en) * | 2017-11-30 | 2018-05-15 | 广东芬尼克兹节能设备有限公司 | A kind of intelligent temperature and humidity control method and device |
CN109028480A (en) * | 2018-06-08 | 2018-12-18 | 杭州古北电子科技有限公司 | A kind of thermostatic constant wet control system and its method |
CN108931027A (en) * | 2018-08-01 | 2018-12-04 | 北京创思工贸有限公司 | A kind of visual remote monitoring control maintenance air-conditioning system |
CN109028402A (en) * | 2018-08-04 | 2018-12-18 | 浙江国芝科技有限公司 | The water-supply control of radiation air-conditioner, device and system |
CN110822616A (en) * | 2018-08-13 | 2020-02-21 | 格力电器(武汉)有限公司 | Automatic air conditioner adjusting method and device |
CN110837229A (en) * | 2018-08-17 | 2020-02-25 | 珠海格力电器股份有限公司 | Control method and device for household appliance |
CN109140665A (en) * | 2018-08-31 | 2019-01-04 | 珠海格力电器股份有限公司 | Method and device for controlling air conditioner and air conditioner device |
WO2020042417A1 (en) * | 2018-08-31 | 2020-03-05 | 珠海格力电器股份有限公司 | Air conditioner control method and device, and air conditioning device |
CN109164707A (en) * | 2018-09-28 | 2019-01-08 | 苏州市建筑科学研究院集团股份有限公司 | A kind of indoor environment negative-feedback regu- lation system based on artificial neural network algorithm |
CN109405195A (en) * | 2018-10-31 | 2019-03-01 | 四川长虹电器股份有限公司 | Air conditioner intelligent control system and method |
CN109357352B (en) * | 2018-11-05 | 2021-01-26 | 四川长虹电器股份有限公司 | Air conditioner intelligent temperature control system and method based on decision tree classification algorithm |
CN109357352A (en) * | 2018-11-05 | 2019-02-19 | 四川长虹电器股份有限公司 | Air conditioner intelligent temperature control system and method based on Decision Tree Algorithm |
CN109376795A (en) * | 2018-11-19 | 2019-02-22 | 四川长虹电器股份有限公司 | Air conditioner intelligent temperature control method based on Decision Tree Algorithm |
CN109489212B (en) * | 2018-11-21 | 2020-05-05 | 珠海格力电器股份有限公司 | Intelligent sleep control method, adjustment system and equipment for air conditioner |
CN109489212A (en) * | 2018-11-21 | 2019-03-19 | 珠海格力电器股份有限公司 | Intelligent sleep control method, adjustment system and equipment for air conditioner |
CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
CN109695943A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | The temperature and humidity control system of coating air-conditioning based on big data deep learning |
CN110230866A (en) * | 2019-06-11 | 2019-09-13 | 陕西大疆电力科技有限公司 | One kind being used for indoor temperature and humidity intelligent control system |
CN112212481A (en) * | 2019-07-10 | 2021-01-12 | 中华电信股份有限公司 | System and method for controlling environmental comfort by deep reinforcement learning |
CN110395286B (en) * | 2019-08-02 | 2020-08-07 | 中南大学 | Method and system for monitoring air quality and regulating ventilation in train |
CN110395286A (en) * | 2019-08-02 | 2019-11-01 | 中南大学 | A kind of train air quality in vehicle monitoring and divulge information regulation method, system |
WO2021023075A1 (en) * | 2019-08-02 | 2021-02-11 | 中南大学 | In-train air quality monitoring and ventilation control method and system |
US11999388B2 (en) | 2019-08-02 | 2024-06-04 | Central South University | Interior air quality monitoring and ventilation control method and system for train |
CN110738120B (en) * | 2019-09-17 | 2024-02-09 | 平安科技(深圳)有限公司 | Environment data adjustment method and device, electronic equipment and medium |
CN110738120A (en) * | 2019-09-17 | 2020-01-31 | 平安科技(深圳)有限公司 | Environment data adjusting method and device, electronic equipment and medium |
CN110726220A (en) * | 2019-10-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Control method and device of air conditioner |
CN110726214A (en) * | 2019-10-29 | 2020-01-24 | 珠海格力电器股份有限公司 | Method and device for controlling air conditioner |
CN112050448A (en) * | 2020-08-18 | 2020-12-08 | 吉安职业技术学院 | Indoor temperature and humidity adjusting system of low-voltage apparatus controlled by PLC circuit |
CN112484259A (en) * | 2020-12-04 | 2021-03-12 | 珠海格力电器股份有限公司 | Humidity control method and device, electronic equipment and storage medium |
CN112484259B (en) * | 2020-12-04 | 2021-11-16 | 珠海格力电器股份有限公司 | Humidity control method and device, electronic equipment and storage medium |
CN112506059A (en) * | 2020-12-07 | 2021-03-16 | 常州常工电子科技股份有限公司 | Classroom self-adaptive control system based on energy-saving model of personal sensory comfort |
CN112947637A (en) * | 2021-01-29 | 2021-06-11 | 安徽佳美瑞物联科技有限公司 | Office environment intelligent regulation system |
CN113311892A (en) * | 2021-05-27 | 2021-08-27 | 中通服咨询设计研究院有限公司 | Optimal pre-cooling control method for energy efficiency of central air conditioner of exhibition venue |
CN113327219A (en) * | 2021-06-21 | 2021-08-31 | 易成功(厦门)信息科技有限公司 | Image processing method and system based on multi-source data fusion |
CN113327219B (en) * | 2021-06-21 | 2022-01-28 | 易成功(厦门)信息科技有限公司 | Image processing method and system based on multi-source data fusion |
CN114370696A (en) * | 2021-12-27 | 2022-04-19 | 杭州英集动力科技有限公司 | Method for controlling outlet water temperature of cooling tower of central air conditioner based on D-S evidence theory |
CN114265458A (en) * | 2022-01-05 | 2022-04-01 | 信息产业电子第十一设计研究院科技工程股份有限公司 | Method for realizing accurate control of air pipe temperature and humidity and room temperature and humidity |
CN115272675A (en) * | 2022-07-29 | 2022-11-01 | 江苏磐鼎科技有限公司 | Energy management system and method based on multi-sensor information fusion |
Also Published As
Publication number | Publication date |
---|---|
CN104374053B (en) | 2017-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104374053A (en) | Intelligent control method, device and system | |
Farhan et al. | Predicting individual thermal comfort using machine learning algorithms | |
CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
KR102393418B1 (en) | Data learning server and method for generating and using thereof | |
CN104075402A (en) | Intelligent air conditioner control method and system | |
KR20190096311A (en) | A device for generating a temperature prediction model and a method for providing a simulation environment | |
EP3025099B1 (en) | Control device and method for buildings | |
CN114662201B (en) | Optimizing method for intelligent regulation and control of natural ventilation | |
Wang et al. | Fault detection and diagnosis for multiple faults of VAV terminals using self-adaptive model and layered random forest | |
CN106152387A (en) | A kind of detection method for indoor thermal comfort | |
CN104748305A (en) | Identification method and system of on-off state of air conditioner and estimation method and system of on-off state of air conditioner | |
CN114838470A (en) | Control method and system for heating, ventilating and air conditioning | |
CN114200839B (en) | Intelligent office building energy consumption control model for dynamic monitoring of coupling environment behaviors | |
CN110991478B (en) | Thermal comfort model establishment method and user preference temperature setting method and system | |
CN113821903B (en) | Temperature control method and equipment, modularized data center and storage medium | |
CN109435630A (en) | A kind of crew module's temprature control method based on artificial neural network algorithm | |
CN108446783A (en) | A kind of prediction of new fan operation power and monitoring method | |
CN111625030A (en) | Greenhouse environment control method, device, equipment, system and storage medium | |
CN113365222B (en) | Mobile sensor intelligent track design method based on sustainable data acquisition | |
Guillén-Navarro et al. | An LSTM deep learning scheme for prediction of low temperatures in agriculture | |
Hakim et al. | Fuzzy Mamdani performance water chiller control optimization using fuzzy adaptive neuro fuzzy inference system assisted | |
Molina-Solana et al. | Unifying fuzzy controller for indoor environment quality | |
Boicu et al. | Decision system for ensuring thermal comfort of occupants in a smart building | |
Vincent et al. | Smart building indoor temperature prediction using the IoT and machine learning | |
Thitisawat et al. | Adaptive outdoor comfort model calibrations for a semitropical region |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |