CN117739473A - Intelligent central air conditioner energy-saving control method and system - Google Patents
Intelligent central air conditioner energy-saving control method and system Download PDFInfo
- Publication number
- CN117739473A CN117739473A CN202311757560.7A CN202311757560A CN117739473A CN 117739473 A CN117739473 A CN 117739473A CN 202311757560 A CN202311757560 A CN 202311757560A CN 117739473 A CN117739473 A CN 117739473A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- parameter
- central air
- environmental
- environment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000007613 environmental effect Effects 0.000 claims abstract description 135
- 238000006243 chemical reaction Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims description 18
- 230000001105 regulatory effect Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000001276 controlling effect Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 10
- 238000013210 evaluation model Methods 0.000 claims description 9
- 238000004378 air conditioning Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 230000008016 vaporization Effects 0.000 description 1
- 238000009834 vaporization Methods 0.000 description 1
Abstract
The invention discloses an intelligent central air conditioner energy-saving control method and system, which relate to the technical field of air conditioner control and comprise the following steps: determining a parameter prediction acquisition period and setting a parameter acquisition interval; collecting a plurality of parameter prediction samples; predicting environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples; determining an environmental parameter target value in a working space of a central air conditioner; predicting central air conditioner control parameters in the next parameter acquisition interval through a regulation and control reaction model; and outputting a control instruction to the central air conditioner to control the central air conditioner to operate. The invention has the advantages that: the scheme predicts future environmental parameters and builds a time regulation reaction model, reduces control delay of the central air conditioner, realizes intelligent automatic central air conditioner regulation control, and realizes optimal energy efficiency ratio.
Description
Technical Field
The invention relates to the technical field of air conditioner control, in particular to an intelligent central air conditioner energy-saving control method and system.
Background
The central air conditioning system consists of one or more cold and heat source systems and a plurality of air conditioning systems, and adopts the principle of liquid vaporization refrigeration to provide required cold energy for the air conditioning systems so as to offset the heat load of indoor environment; the heating system provides the air conditioning system with the required heat to counteract the indoor environmental cooling and heating load.
The existing central air conditioner is delayed in regulation and control, the indoor air cannot be predicted according to the current indoor air, the indoor air is adjusted in advance, the central air conditioner running scheme is lack of advanced planning, the central air conditioner is difficult to optimally regulate and control according to the environment state and the working condition state in the running process of the central air conditioner, and energy waste is easily caused.
Disclosure of Invention
In order to solve the technical problems, the technical scheme solves the problems that the control of the existing central air conditioner has postponement, the indoor air cannot be predicted according to the current indoor air, the indoor air is adjusted in advance, the running scheme of the central air conditioner is not planned in advance, the optimal control is difficult to be carried out according to the environmental state and the working condition state in the running process of the central air conditioner, and the energy waste is easy to cause.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an intelligent central air conditioner energy-saving control method comprises the following steps:
determining a parameter prediction acquisition period and setting a parameter acquisition interval;
in a parameter prediction acquisition period, acquiring a plurality of parameter prediction samples according to parameter acquisition intervals;
predicting environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples, wherein the environmental parameters at least comprise environmental temperature and environmental humidity;
determining an environmental parameter target value in a working space of a central air conditioner;
based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, predicting the central air conditioner control parameter in the next parameter acquisition interval through regulating and controlling the reaction model;
based on the central air conditioner control parameters in the next parameter acquisition interval, outputting a control instruction to the central air conditioner to control the central air conditioner to operate.
Preferably, the predicting, based on the plurality of parameter prediction samples, the environmental parameters of the central air conditioner in the next parameter acquisition interval specifically includes:
collecting at least one continuous change curve of the environmental parameter of the working space of the central air conditioner along with the time change, and summarizing all the continuous change curves into one environmental parameter curve;
uniformly dividing the environmental parameter curve to obtain at least one environmental parameter identification curve;
taking a previous parameter acquisition interval image of the environment parameter identification curve as an identification judgment curve, and taking a later parameter acquisition interval image of the environment parameter identification curve as an identification prediction curve;
equidistant taking at least one identification point on the identification judgment curve;
fitting the identification prediction curve by using a least square method to obtain a fitting function G (x) of the identification prediction curve;
at least one identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the identification point and the fitting function G (x) are called together during calling;
the plurality of groups of identification points and the fitting function G (x) form an outdoor environment parameter prediction model.
Preferably, the least square method is:
equally spaced n points on the identification prediction curve, the coordinates of the n points being (a) i ，y i ) I is 1 to n;
transversely shift n points to satisfy a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let a fitting function G (x) =kx+b identifying the prediction curve one,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and are substituted into G (x) =kx+b, G (x) is obtained, x is the time in the next parameter acquisition interval, and G (x) is the environmental parameter predicted value of the time x in the next parameter acquisition interval.
Preferably, the construction method of the regulation reaction model comprises the following steps:
determining the size of a working space of a central air conditioner;
constructing an experimental space with the same size as the working space of the central air conditioner;
determining a plurality of sample environment states based on the actual running environment state of the central air conditioner;
regulating and controlling an initial environmental state in the experimental space according to the sample environmental state;
and training a regulation and control reaction model under the environmental state of each sample by adopting an optimal model training method in the experimental space.
Preferably, the training the regulation reaction model under the environmental state of each sample by adopting the optimal model training method in the experimental space specifically includes:
setting a plurality of environmental parameter detection points in an experiment space;
setting a plurality of environmental parameter sensors at environmental parameter monitoring points;
determining a plurality of environment demand set values allowed by the central air conditioner;
constructing an operation control scheme evaluation model based on each environment demand set value respectively;
based on a neural network training model, under the limitation of an operation parameter interval of a central air conditioner, generating a plurality of operation control schemes, and recording the operation control schemes as operation control schemes to be screened;
the central air conditioner operates according to the experimental time of the operation control scheme to be screened, acquires the environmental data of each environmental parameter detection point, and substitutes the environmental data of the environmental parameter detection point into an operation control scheme evaluation model to obtain a rationality evaluation value of each operation control scheme to be screened;
screening out an operation control scheme to be screened with the minimum rationality evaluation value, and taking the operation control scheme as an optimal operation control scheme corresponding to a sample environment state-environment demand set value;
all optimal operational control schemes are combined into a regulatory response model.
Preferably, the operation control scheme evaluation model is:
wherein Q is a rationality evaluation value of an operation control scheme to be screened, m is the total number of detection points of environmental parameters, T is the duration of experimental time, and H (T) j A change curve equation of environmental data of the jth environmental parameter detection point along with time in experimental time, H 0 Set values for environmental requirements.
Preferably, the predicting the central air conditioner control parameter in the next parameter acquisition interval through the regulation and control reaction model includes:
respectively calculating the sum of the differences of all the environmental parameters between the environmental parameters of the central air conditioner in the next parameter acquisition interval and the environmental states of each sample, and screening out the sample environmental state with the minimum sum of the differences as a fitting environmental state;
and determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
Furthermore, an intelligent central air conditioner energy-saving control system is provided, which is used for realizing the intelligent central air conditioner energy-saving control method, and comprises the following steps:
the environment acquisition module is used for determining a parameter prediction acquisition period, setting a parameter acquisition interval, and acquiring a plurality of parameter prediction samples according to the parameter acquisition interval in the parameter prediction acquisition period;
the parameter prediction module is electrically connected with the environment acquisition module and is used for predicting the environment parameters of the central air conditioner in the next parameter acquisition interval based on a plurality of parameter prediction samples;
the regulation and control module is electrically connected with the parameter prediction module, and is used for determining an environmental parameter target value in the working space of the central air conditioner, predicting a central air conditioner control parameter in the next parameter acquisition interval through a regulation and control reaction model based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, and outputting a control instruction to the central air conditioner and controlling the central air conditioner to run based on the central air conditioner control parameter in the next parameter acquisition interval.
Optionally, the regulation module includes:
the reaction model building unit is used for building a regulation and control reaction model;
the environment parameter fitting unit is used for respectively calculating the sum of differences of all environment parameters between the environment parameters of the central air conditioner in the next parameter acquisition interval and the environment states of each sample, and screening out the sample environment state with the minimum sum of differences as a fitting environment state;
and the control parameter determining unit is used for determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an intelligent central air conditioner energy-saving control method, which predicts future environmental parameters, adjusts the environmental parameters according to the future environmental parameters when the regulating parameters are currently set, so that the indoor environmental parameters can keep target values, and simultaneously builds a regulating reaction model to determine the optimal central air conditioner control parameters under each environmental state, so that the real-time indoor environmental parameters are directly adjusted to the target values when central air conditioner regulation is performed, the delay is reduced, the uniformity of the regulation of the environmental parameters in a central air conditioner working space is ensured, intelligent automatic central air conditioner regulation control is realized, and the optimal energy efficiency ratio is realized.
Drawings
FIG. 1 is a flow chart of an intelligent central air conditioner energy-saving control method provided by the invention;
FIG. 2 is a flowchart of a method for predicting environmental parameters of a central air conditioner in a next parameter acquisition interval according to the present invention;
FIG. 3 is a flow chart of a method for constructing a regulatory reaction model in the present invention;
FIG. 4 is a flow chart of a method for training a model of a regulatory response in an environmental state of each sample according to the present invention;
FIG. 5 is a flowchart of a method for predicting central air conditioner control parameters in a next parameter acquisition interval according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, an intelligent central air conditioner energy-saving control method includes:
determining a parameter prediction acquisition period and setting a parameter acquisition interval;
in a parameter prediction acquisition period, acquiring a plurality of parameter prediction samples according to parameter acquisition intervals;
predicting environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples, wherein the environmental parameters at least comprise environmental temperature and environmental humidity;
determining an environmental parameter target value in a working space of a central air conditioner;
based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, predicting the central air conditioner control parameter in the next parameter acquisition interval through regulating and controlling the reaction model;
based on the central air conditioner control parameters in the next parameter acquisition interval, outputting a control instruction to the central air conditioner to control the central air conditioner to operate.
According to the scheme, future environmental parameters are predicted, and when the regulation and control parameters are set currently, the regulation and control parameters are regulated according to the future environmental parameters, so that the indoor environmental parameters can keep target values, meanwhile, a regulation and control reaction model is built to determine the optimal central air-conditioning control parameters under each environmental state, and when central air-conditioning regulation and control is conducted, the real-time indoor environmental parameters are directly regulated to the target values, and the delay is reduced.
Referring to fig. 2, predicting environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples specifically includes:
collecting at least one continuous change curve of the environmental parameter of the working space of the central air conditioner along with the time change, and summarizing all the continuous change curves into one environmental parameter curve;
uniformly dividing the environmental parameter curve to obtain at least one environmental parameter identification curve;
taking a previous parameter acquisition interval image of the environment parameter identification curve as an identification judgment curve, and taking a later parameter acquisition interval image of the environment parameter identification curve as an identification prediction curve;
equidistant taking at least one identification point on the identification judgment curve;
fitting the identification prediction curve by using a least square method to obtain a fitting function G (x) of the identification prediction curve;
at least one identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the identification point and the fitting function G (x) are called together during calling;
the plurality of groups of identification points and the fitting function G (x) form an outdoor environment parameter prediction model.
The least square method is as follows:
equally spaced n points on the identification prediction curve, the coordinates of the n points being (a) i ，y i ) I is 1 to n;
transversely shift n points to satisfy a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let a fitting function G (x) =kx+b identifying the prediction curve one,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and are substituted into G (x) =kx+b, G (x) is obtained, x is the time in the next parameter acquisition interval, and G (x) is the environmental parameter predicted value of the time x in the next parameter acquisition interval.
Because the air in the working space of the central air conditioner is directly interacted from the outside in the running process of the central air conditioner, the control of the running environment of the central air conditioner needs to predict the outdoor environment factors, wherein the central air conditioner has a key influence on the running of the central air conditioner, namely the temperature and the humidity, and therefore, at least the temperature and the humidity of the environment need to be considered when the central air conditioner is controlled.
Referring to fig. 3, the construction method of the regulation reaction model is as follows:
determining the size of a working space of a central air conditioner;
constructing an experimental space with the same size as the working space of the central air conditioner;
determining a plurality of sample environment states based on the actual running environment state of the central air conditioner;
regulating and controlling an initial environmental state in the experimental space according to the sample environmental state;
and training a regulation and control reaction model under the environmental state of each sample by adopting an optimal model training method in the experimental space.
Referring to fig. 4, training a regulation reaction model under each sample environmental state in an optimal model training method in an experimental space specifically includes:
setting a plurality of environmental parameter detection points in an experiment space;
setting a plurality of environmental parameter sensors at environmental parameter monitoring points;
determining a plurality of environment demand set values allowed by the central air conditioner;
constructing an operation control scheme evaluation model based on each environment demand set value respectively;
based on a neural network training model, under the limitation of an operation parameter interval of a central air conditioner, generating a plurality of operation control schemes, and recording the operation control schemes as operation control schemes to be screened;
the central air conditioner operates according to the experimental time of the operation control scheme to be screened, acquires the environmental data of each environmental parameter detection point, and substitutes the environmental data of the environmental parameter detection point into an operation control scheme evaluation model to obtain a rationality evaluation value of each operation control scheme to be screened;
screening out an operation control scheme to be screened with the minimum rationality evaluation value, and taking the operation control scheme as an optimal operation control scheme corresponding to a sample environment state-environment demand set value;
all optimal operational control schemes are combined into a regulatory response model.
The operation control scheme evaluation model is as follows:
wherein Q is a rationality evaluation value of an operation control scheme to be screened, m is the total number of detection points of environmental parameters, T is the duration of experimental time, and H (T) j A change curve equation of environmental data of the jth environmental parameter detection point along with time in experimental time, H 0 Set values for environmental requirements.
When the regulation and control reaction model is constructed, only a plurality of experimental spaces matched with the working space of the central air conditioner are required to be constructed, initial environmental parameters of the experimental spaces are regulated and controlled to reach a sample environmental state, then different environmental requirement set values are set, and the generated parameter regulation scheme with the minimum rationality evaluation value is iterated step by step under the limitation of the operation parameter interval of the central air conditioner, and the optimal operation control scheme with the minimum rationality evaluation value can be obtained through a plurality of iterations of the neural network.
Referring to fig. 5, predicting central air conditioner control parameters in a next parameter acquisition interval by adjusting a reaction model includes:
respectively calculating the sum of the differences of all the environmental parameters between the environmental parameters of the central air conditioner in the next parameter acquisition interval and the environmental states of each sample, and screening out the sample environmental state with the minimum sum of the differences as a fitting environmental state;
and determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
By intelligently fitting the working environment state of the central air conditioner, the optimal operation control scheme optimally adapted to the predicted environment state is called from the regulation and control reaction model as a regulation and control method of the central air conditioner, so that the regulation and control uniformity of the environment parameters in the working space of the central air conditioner can be effectively ensured, intelligent automatic central air conditioner regulation and control is realized, and the optimal energy efficiency ratio is realized.
Furthermore, based on the same inventive concept as the intelligent central air conditioner energy-saving control method, the present solution also provides an intelligent central air conditioner energy-saving control system, which includes:
the environment acquisition module is used for determining a parameter prediction acquisition period, setting a parameter acquisition interval, and acquiring a plurality of parameter prediction samples according to the parameter acquisition interval in the parameter prediction acquisition period;
the parameter prediction module is electrically connected with the environment acquisition module and is used for predicting the environment parameters of the central air conditioner in the next parameter acquisition interval based on a plurality of parameter prediction samples;
the regulation and control module is electrically connected with the parameter prediction module and is used for determining an environmental parameter target value in the working space of the central air conditioner, predicting a central air conditioner control parameter in the next parameter acquisition interval through a regulation and control reaction model based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, and outputting a control instruction to the central air conditioner to control the central air conditioner to operate based on the central air conditioner control parameter in the next parameter acquisition interval.
The regulation and control module comprises:
the reaction model building unit is used for building a regulation and control reaction model;
the environment parameter fitting unit is used for respectively calculating the sum of differences of all environment parameters between the environment parameters of the central air conditioner in the next parameter acquisition interval and the environment states of each sample, and screening the sample environment state with the minimum sum of differences as a fitting environment state;
and the control parameter determining unit is used for determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
The intelligent central air conditioner energy-saving control system comprises the following using processes:
step one: the environment acquisition module is used for determining a parameter prediction acquisition period, setting a parameter acquisition interval, and acquiring a plurality of parameter prediction samples according to the parameter acquisition interval in the parameter prediction acquisition period;
step two: the parameter prediction module predicts environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples;
step three: the reaction model construction unit constructs a regulation reaction model, which specifically comprises: determining the size of a working space of a central air conditioner; constructing an experimental space with the same size as the working space of the central air conditioner; determining a plurality of sample environment states based on the actual running environment state of the central air conditioner; regulating and controlling an initial environmental state in the experimental space according to the sample environmental state; training a regulation and control reaction model under the environmental state of each sample by adopting an optimal model training method in an experimental space;
step four: the environment parameter fitting unit is used for respectively calculating the difference sum of all environment parameters between the environment parameters of the central air conditioner in the next parameter acquisition interval and each sample environment state, and screening out the sample environment state with the minimum difference sum as a fitting environment state;
step five: the control parameter determining unit determines an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval;
step six: the regulation and control module outputs a control instruction to the central air conditioner based on the central air conditioner control parameters in the next parameter acquisition interval to control the central air conditioner to operate.
In summary, the invention has the advantages that: the scheme predicts future environmental parameters and builds a time regulation reaction model, reduces control delay of the central air conditioner, realizes intelligent automatic central air conditioner regulation control, and realizes optimal energy efficiency ratio.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. An intelligent central air conditioner energy-saving control method is characterized by comprising the following steps:
determining a parameter prediction acquisition period and setting a parameter acquisition interval;
in a parameter prediction acquisition period, acquiring a plurality of parameter prediction samples according to parameter acquisition intervals;
predicting environmental parameters of the central air conditioner in a next parameter acquisition interval based on a plurality of parameter prediction samples, wherein the environmental parameters at least comprise environmental temperature and environmental humidity;
determining an environmental parameter target value in a working space of a central air conditioner;
based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, predicting the central air conditioner control parameter in the next parameter acquisition interval through regulating and controlling the reaction model;
based on the central air conditioner control parameters in the next parameter acquisition interval, outputting a control instruction to the central air conditioner to control the central air conditioner to operate.
2. The intelligent central air conditioner energy-saving control method according to claim 1, wherein predicting the environmental parameters of the central air conditioner in the next parameter acquisition interval based on the plurality of parameter prediction samples specifically comprises:
collecting at least one continuous change curve of the environmental parameter of the working space of the central air conditioner along with the time change, and summarizing all the continuous change curves into one environmental parameter curve;
uniformly dividing the environmental parameter curve to obtain at least one environmental parameter identification curve;
taking a previous parameter acquisition interval image of the environment parameter identification curve as an identification judgment curve, and taking a later parameter acquisition interval image of the environment parameter identification curve as an identification prediction curve;
equidistant taking at least one identification point on the identification judgment curve;
fitting the identification prediction curve by using a least square method to obtain a fitting function G (x) of the identification prediction curve;
at least one identification point is arranged in sequence, a corresponding relation is established with the fitting function G (x), and the identification point and the fitting function G (x) are called together during calling;
the plurality of groups of identification points and the fitting function G (x) form an outdoor environment parameter prediction model.
3. The intelligent central air conditioner energy-saving control method according to claim 2, wherein the least square method is as follows:
equally spaced n points on the identification prediction curve, the coordinates of the n points being (a) i ，y i ) I is 1 to n;
transversely shift n points to satisfy a after translation n =1, to obtain the coordinates of new n points (x i ，y i )；
Let a fitting function G (x) =kx+b identifying the prediction curve one,
substitution into all (x i ，y i )，
Thus, the values of k and b are obtained, and are substituted into G (x) =kx+b, G (x) is obtained, x is the time in the next parameter acquisition interval, and G (x) is the environmental parameter predicted value of the time x in the next parameter acquisition interval.
4. The intelligent central air conditioner energy-saving control method according to claim 3, wherein the construction method of the regulation reaction model is as follows:
determining the size of a working space of a central air conditioner;
constructing an experimental space with the same size as the working space of the central air conditioner;
determining a plurality of sample environment states based on the actual running environment state of the central air conditioner;
regulating and controlling an initial environmental state in the experimental space according to the sample environmental state;
and training a regulation and control reaction model under the environmental state of each sample by adopting an optimal model training method in the experimental space.
5. The method for intelligent central air conditioner energy-saving control according to claim 4, wherein training the regulation reaction model under each sample environmental state by adopting the optimal model training method in the experimental space specifically comprises:
setting a plurality of environmental parameter detection points in an experiment space;
setting a plurality of environmental parameter sensors at environmental parameter monitoring points;
determining a plurality of environment demand set values allowed by the central air conditioner;
constructing an operation control scheme evaluation model based on each environment demand set value respectively;
based on a neural network training model, under the limitation of an operation parameter interval of a central air conditioner, generating a plurality of operation control schemes, and recording the operation control schemes as operation control schemes to be screened;
the central air conditioner operates according to the experimental time of the operation control scheme to be screened, acquires the environmental data of each environmental parameter detection point, and substitutes the environmental data of the environmental parameter detection point into an operation control scheme evaluation model to obtain a rationality evaluation value of each operation control scheme to be screened;
screening out an operation control scheme to be screened with the minimum rationality evaluation value, and taking the operation control scheme as an optimal operation control scheme corresponding to a sample environment state-environment demand set value;
all optimal operational control schemes are combined into a regulatory response model.
6. The intelligent central air conditioner energy-saving control method according to claim 5, wherein the operation control scheme evaluation model is as follows:
wherein Q is a rationality evaluation value of an operation control scheme to be screened, and m is an environmental parameter checkThe total number of measuring points, T is the duration of the experimental time, H (T) j A change curve equation of environmental data of the jth environmental parameter detection point along with time in experimental time, H 0 Set values for environmental requirements.
7. The intelligent central air conditioner energy saving control method according to claim 6, wherein the predicting the central air conditioner control parameter in the next parameter acquisition interval by controlling the reaction model comprises:
respectively calculating the sum of the differences of all the environmental parameters between the environmental parameters of the central air conditioner in the next parameter acquisition interval and the environmental states of each sample, and screening out the sample environmental state with the minimum sum of the differences as a fitting environmental state;
and determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
8. An intelligent central air conditioner energy-saving control system for realizing the intelligent central air conditioner energy-saving control method as set forth in any one of claims 1-7, comprising:
the environment acquisition module is used for determining a parameter prediction acquisition period, setting a parameter acquisition interval, and acquiring a plurality of parameter prediction samples according to the parameter acquisition interval in the parameter prediction acquisition period;
the parameter prediction module is electrically connected with the environment acquisition module and is used for predicting the environment parameters of the central air conditioner in the next parameter acquisition interval based on a plurality of parameter prediction samples;
the regulation and control module is electrically connected with the parameter prediction module, and is used for determining an environmental parameter target value in the working space of the central air conditioner, predicting a central air conditioner control parameter in the next parameter acquisition interval through a regulation and control reaction model based on the environmental parameter of the central air conditioner in the next parameter acquisition interval and the environmental parameter target value in the working space of the central air conditioner, and outputting a control instruction to the central air conditioner and controlling the central air conditioner to run based on the central air conditioner control parameter in the next parameter acquisition interval.
9. The intelligent central air conditioning energy saving control system according to claim 8, wherein the regulation module comprises:
the reaction model building unit is used for building a regulation and control reaction model;
the environment parameter fitting unit is used for respectively calculating the sum of differences of all environment parameters between the environment parameters of the central air conditioner in the next parameter acquisition interval and the environment states of each sample, and screening out the sample environment state with the minimum sum of differences as a fitting environment state;
and the control parameter determining unit is used for determining an optimal operation control scheme corresponding to the fitting environment state-environment parameter target value as a central air conditioner control parameter in the next parameter acquisition interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311757560.7A CN117739473A (en) | 2023-12-20 | 2023-12-20 | Intelligent central air conditioner energy-saving control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311757560.7A CN117739473A (en) | 2023-12-20 | 2023-12-20 | Intelligent central air conditioner energy-saving control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117739473A true CN117739473A (en) | 2024-03-22 |
Family
ID=90278860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311757560.7A Pending CN117739473A (en) | 2023-12-20 | 2023-12-20 | Intelligent central air conditioner energy-saving control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117739473A (en) |
-
2023
- 2023-12-20 CN CN202311757560.7A patent/CN117739473A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111237989B (en) | Building ventilation air conditioner control method and device based on load prediction | |
| CN109800066B (en) | Energy-saving scheduling method and system for data center | |
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| EP3025099B1 (en) | Control device and method for buildings | |
| CN105143781A (en) | Air-conditioning control system and method | |
| CN107632524B (en) | Communication machine room temperature model prediction control method and system | |
| CN113108432B (en) | Air conditioning system adjusting method and system based on weather forecast | |
| CN107781947A (en) | A kind of air conditioning system Cooling and Heat Source forecast Control Algorithm and device | |
| CN1224823A (en) | Room temperature control apparatus having feedforward and feedback control and method | |
| Wang et al. | Evaluation of operation performance of a multi-chiller system using a data-based chiller model | |
| CN110186156A (en) | Refrigeration plant Fuzzy control system | |
| CN111047117B (en) | Differential pressure bypass valve energy-saving optimization method based on terminal load prediction | |
| Gao et al. | Model-based space temperature cascade control for constant air volume air-conditioning system | |
| CN105091209A (en) | Control system and method based on air conditioning load prediction | |
| JP2006207929A (en) | Optimum operation control system and optimum operation control method for air conditioning system | |
| CN115685941B (en) | Machine room operation regulation and control method and device based on machine cabinet hot spot temperature prediction | |
| CN113778215A (en) | Method for realizing data center PUE prediction and consumption reduction strategy based on big data | |
| CN114154677A (en) | Air conditioner operation load model construction and prediction method, device, equipment and medium | |
| CN112113314A (en) | Real-time temperature data acquisition system and temperature adjusting method based on learning model | |
| CN115220351A (en) | Intelligent energy-saving optimization control method of building air conditioning system based on cloud side end | |
| Eini et al. | Learning-based model predictive control for smart building thermal management | |
| CN109857177B (en) | Building electrical energy-saving monitoring method | |
| CN116989432B (en) | Energy-saving operation optimization scheduling method and system for air conditioning system | |
| CN113028610B (en) | Method and device for global optimization and energy-saving control of dynamic load of central air conditioner | |
| Sha et al. | A control strategy of heating system based on adaptive model predictive control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |