CN116592462A - Central air conditioner chilled water backwater temperature prediction method and system - Google Patents
Central air conditioner chilled water backwater temperature prediction method and system Download PDFInfo
- Publication number
- CN116592462A CN116592462A CN202310679692.6A CN202310679692A CN116592462A CN 116592462 A CN116592462 A CN 116592462A CN 202310679692 A CN202310679692 A CN 202310679692A CN 116592462 A CN116592462 A CN 116592462A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- central air
- sample
- module
- parameters
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004927 fusion Effects 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 239000013598 vector Substances 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 239000000498 cooling water Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 abstract description 3
- 238000013486 operation strategy Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction 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
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/56—Remote control
-
- 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
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
- F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
-
- 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
- F24F11/88—Electrical aspects, e.g. circuits
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/20—Heat-exchange fluid temperature
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a method and a system for predicting return water temperature of chilled water of a central air conditioner, and relates to the technical field of prediction of return water temperature of air conditioners. The method comprises the following steps: recording real-time operation parameters of the central air conditioner; carrying out standardization treatment on the acquired parameters; dividing data into sample characteristics and sample labels; performing attention calculation on the feature set between time sequence and different parameters; performing depth fusion again; performing model training; the model is used for predicting the return water temperature of the central air conditioner in the future period. The nonlinear relation between the chilled water return temperature value of the central air conditioner and other operation parameters is excavated mainly by collecting the real-time operation parameters of the central air conditioner and setting a correlation model between the chilled water return temperature value and the other operation parameters. In addition, on the basis of the predicted value, whether surplus or loss exists in the refrigerating or heating quantity of the central air conditioner is reasonably judged. Provides powerful guarantee for the operation strategy of the central air conditioner.
Description
Technical Field
The invention relates to the technical field of air conditioner backwater temperature prediction, in particular to a method and a system for predicting the backwater temperature of chilled water of a central air conditioner.
Background
The chilled water backwater temperature of the central air conditioner is influenced by multiple factors, including the ambient temperature, the outdoor temperature, the unit power and the like. The change of the temperature of the backwater is mainly used for providing refrigeration for the environment. And the temperature of the backwater reflects whether the refrigerating capacity of the unit is sufficient. For example, in the case of refrigeration in summer, the return water temperature of the chilled water is lower, compared with the situation that the outlet water temperature difference is small, the refrigerating capacity of the unit is redundant to a large extent, and the refrigerating capacity produced by the unit cannot be used in the environment. Under such a condition, the machine set can do idle work by manufacturing redundant cold energy, so that the electric power is wasted. Therefore, the return water temperature of the chilled water of the central air conditioner at the future moment is predicted, whether the ambient cold quantity is enough or not can be predicted in advance, and the energy-saving planning of the air conditioner can be formulated in advance.
The patent number CN201310236529.9 is a cooling water backwater temperature prediction control method of a central air conditioner, which can also predict the backwater temperature of chilled water, but only adopts a two-layer BP neural network model to perform conventional training and optimization, and does not perform feature attention calculation and feature fusion, so that the phenomenon of insufficient feature discrimination can easily occur, and finally the trained model can be influenced.
In view of this, there is a need for a method and system for predicting return water temperature of chilled water of a central air conditioner.
Disclosure of Invention
Aiming at the problems that the phenomenon of insufficient feature discrimination is easy to occur and finally the trained model is influenced when feature attention calculation and feature fusion are not performed in the prior art, the invention provides a central air conditioner chilled water return water temperature prediction method and system, which can perform attention calculation on feature sets between time sequence and different parameters, fully excavate association relations between the parameters and time, and then perform deep fusion again, thereby improving feature discrimination and further improving the performance of the trained model. The specific technical scheme is as follows:
the central air conditioner chilled water backwater temperature prediction method is characterized by comprising the following steps of:
s1: effectively recording real-time operation parameters of the central air conditioner to form a real-time operation parameter data set of the central air conditioner;
s2: carrying out standardization treatment on the acquired parameters;
s3: dividing the data into sample features and sample labels so as to facilitate training of a machine learning model;
s4: performing attention calculation on the feature set between time sequence and different parameters, and mining association relations between the parameters and over time;
s5: for each of the samples x obtained in step S4 i Two new features of calculated attention are obtainedAnd->Deep fusion is carried out again to obtain final fusion characteristics +.>
S6: the new fusion characteristics are sent into a three-layer BP neural network again, and a predicted value y 'of each sample for the return water temperature of the cooling water is obtained' i Will predict the value y' i True tag value y of sample i The mean square error calculation is performed according to the following formula to obtain the loss value l of each sample i The mean square error formula is as follows:
l i ＝E(y′ i -y i ) 2
after obtaining the loss value of each sample, updating the parameters of the model through the back propagation of the neural network, and obtaining the optimal parameters by the model after multiple rounds of training;
s7: and the trained neural network model is used for predicting the return water temperature of the central air conditioner in the future period.
Preferably, the step S1 specifically includes: when the central air conditioner operates, temperature and humidity sensors are arranged at the motor, the chilled water outlet and return port, the indoor multi-temperature area and the outdoor, data of all the sensors are recorded according to the frequency of one time of the set interval time and are transmitted to the data acquisition system, and a data set is formed.
Preferably, the interval is 30 seconds.
Preferably, the step S2 specifically includes: firstly, calculating the mean value mu and the standard deviation sigma of all parameters, and obtaining a standardized data set through the following formula:
wherein T is a parameter data set, mu is a mean value, and sigma is a standard deviation.
Preferably, the step S3 specifically includes: n pieces of data are used as one sample X according to 60 continuous records, 1 record is arranged between two samples, after the data X is divided, n-60 samples can be obtained, each sample is divided into characteristics and labels, all parameters of the first 59 records are arranged according to time sequence to be used as characteristic values X1 of the sample 1, the chilled water return temperature value in the last 1 record is used as label values Y1 of the sample 1, and according to the mode, all samples are divided into characteristics and labels to obtain all characteristic values X and all label values Y.
Preferably, the step S4 specifically includes the following steps:
for any one sample x in the feature set i ∈R 59*d Firstly, converting the dimension of the air conditioner into 8*d by a layer of BP neural network, wherein d represents the number of parameters recorded in the running process of the central air conditioner;
x after dimension conversion i Dividing the vector into 8 vectors 1*d according to the time dimension, and inputting the vectors into an attention calculating module to obtain new characteristics
X after dimension conversion i The vector divided into d 8*1 according to different parameter directions is input into an attention calculating module to obtain new characteristics
The saidAnd->Are all equal to x i Is the same.
Preferably, the step S5 specifically includes: will beAnd->The elements of each position are added in pairs. And then, the added features pass through a BP neural network to obtain new features. And carrying out pooling operation on the new features to obtain a score vector. Then multiplying the obtained score vector with the new feature to obtain the final fusion feature +.>
The central air conditioner adjustable electricity demand prediction system is applied to the central air conditioner adjustable electricity demand prediction method, and comprises a parameter recording module, a parameter standardization module, a training sample dividing module, a characteristic attention calculating module, a characteristic fusion module, a model learning module and a cooling water return water temperature prediction module; the parameter recording module is used for effectively recording real-time operation parameters of the central air conditioner and transmitting the real-time operation parameters to the data acquisition system, the parameter standardization module is used for carrying out standardization processing on the acquired parameters, and the training sample dividing module is used for dividing data into sample characteristics and sample labels so as to facilitate training of a machine learning model; the feature attention calculation module is used for carrying out attention calculation on the feature set between time sequence and different parameters, the feature fusion module is used for carrying out deep fusion on new features of attention again, the model learning module is used for obtaining a trained model, and the cooling water return water temperature prediction module is used for predicting cooling water return water temperature.
A computer readable storage medium comprising a stored program, wherein the program when run controls a device in which the computer readable storage medium resides to perform a method for predicting chilled water return temperature of a central air conditioner as described above.
A processor for running a program, wherein the program executes a central air conditioner chilled water return water temperature prediction method as described above.
Compared with the prior art, the invention has the beneficial effects that:
the nonlinear relation between the chilled water return temperature value of the central air conditioner and other operation parameters is excavated mainly by collecting the real-time operation parameters of the central air conditioner and setting a correlation model between the chilled water return temperature value and the other operation parameters. Feature attention calculation and feature fusion are introduced in the model training process, feature discrimination is improved, and the chilled water return temperature at the future moment can be effectively predicted during the running of the central air conditioner under the analysis of the trained correlation model. And on the basis of the predicted value, whether surplus or loss exists in the refrigerating or heating quantity of the central air conditioner is reasonably judged. Provides powerful guarantee for the operation strategy of the central air conditioner.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of an attention computing module of the present invention;
FIG. 2 is a schematic diagram of a feature fusion module according to the present invention;
FIG. 3 is a diagram showing the storage format of the operation parameters of the central air conditioner and the division of the training set;
fig. 4 is a schematic diagram of sample feature and sample tag partitioning.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
With reference to fig. 1-4, this embodiment provides a method for predicting return water temperature of chilled water of a central air conditioner, which is characterized by comprising the following steps:
s1: effectively recording real-time operation parameters of the central air conditioner to form a real-time operation parameter data set of the central air conditioner;
the step is mainly used for effectively recording the real-time operation parameters of the central air conditioner to form a real-time operation parameter data set of the central air conditioner. Temperature and humidity sensors are arranged in a motor, a chilled water outlet, an indoor multi-temperature area and an outdoor when the central air conditioner is in operation, data of all the sensors are recorded according to the frequency of 30 seconds, and the data are transmitted to a data acquisition system to form a data set.
S2: carrying out standardization treatment on the acquired parameters;
by passing throughStep S1 can effectively collect real-time operation parameters of the central air conditioner and form a parameter data set T epsilon R n×d Representing a total of n samples, each sample containing d features. The step is mainly to perform standardization processing on the acquired parameters, so as to ensure the best performance in the subsequent machine learning step. First, the mean μ and standard deviation σ of all parameters are calculated, and the normalized data set is obtained by the formula (1).
S3: dividing the data into sample features and sample labels so as to facilitate training of a machine learning model;
through the operation of step S2, all values in the data X are normalized to data with a mean value of 0 and a standard deviation of 1. The data X is then partitioned into sample features and sample labels to facilitate training of the machine learning model. N pieces of data were recorded as one sample x in 60 consecutive pieces. As shown in fig. 3, sample 1 and sample 2 are two samples recorded 1 strip apart. After the division of the data X, n-60 samples can be obtained. Each sample is then subdivided into features and labels. As shown in fig. 4, taking sample 1 as an example, 60 records are included. All parameters of the first 59 records are arranged according to time sequence to be used as characteristic values x1 of a sample 1, and the chilled water return water temperature value in the last 1 records is used as a label value y1 of the sample 1. And dividing the characteristics and the labels of all the samples in the mode to obtain all the characteristic values X and all the label values Y.
S4: performing attention calculation on the feature set between time sequence and different parameters, and mining association relations between the parameters and over time;
the feature set X and the tag set Y can be obtained through step S3. And then, carrying out attention calculation on the feature set between time sequence and different parameters, and fully mining the association relation between the parameters and the time. For any one sample x in the feature set i ∈R 59*d It is first passed through a layer-by-layer BP nerveThe network converts its dimensions to 8*d. Wherein d represents the number of parameters recorded in the running process of the central air conditioner. Then, the dimension-transformed x is used for i The vector is divided into 8 vectors 1*d according to the time dimension, and the vectors are input into an attention calculating module shown in the figure (2) to obtain new characteristicsIn addition, the dimension-transformed x i The vector divided into d 8*1 according to different parameter directions is also input into an attention calculating module shown in the figure (2) to obtain new characteristic +.> And->Are all equal to x i Is the same.
S5: for each of the samples x obtained in step S4 i Two new features of calculated attention are obtainedAnd->Deep fusion is carried out again to obtain final fusion characteristics +.>
After processing all sample features of the feature set in step S4, each sample x i Both new features of calculated attention can be obtainedAnd->Next, will->And->Depth fusion is performed again, as shown in FIG. 3, by +.>And (3) withThe elements of each position are added in pairs. And then, the added features pass through a BP neural network to obtain new features. And carrying out pooling operation on the new features to obtain a score vector. Then multiplying the obtained score vector with the new feature to obtain the final fusion feature +.>
S6: the new fusion characteristics are sent into a three-layer BP neural network again, and a predicted value y 'of each sample for the return water temperature of the cooling water is obtained' i Will predict the value y' i True tag value y of sample i The mean square error calculation is performed according to the following formula to obtain the loss value l of each sample i The mean square error formula is as follows:
l i ＝E(y′ i -y i ) 2
after obtaining the loss value of each sample, updating the parameters of the model through the back propagation of the neural network, and obtaining the optimal parameters by the model after multiple rounds of training;
s7: and the trained neural network model is used for predicting the return water temperature of the central air conditioner in the future period.
After the step six, the BP neural network with the optimal parameters can be obtained through training. The time sequence correlation between the chilled water backwater temperature of the central air conditioner and other operation parameters is effectively mined. And then the trained neural network model is used for a central air conditioner future period backwater temperature prediction module. And (3) recording the current running time of the central air conditioner as t, and calling 59 running parameter records from the current running time to the front from the database to form the feature xt to be predicted at the current running time. And (5) carrying out normalization operation on each column of xt according to a formula (1). Next, xt is fed as input into the trained neural network, resulting in a predicted value yt of d 1. yt is the predicted return water temperature value of 30 seconds in the future at the current time.
The embodiment also provides a central air conditioner adjustable electricity demand prediction system which is applied to the central air conditioner adjustable electricity demand prediction method, and comprises a parameter recording module, a parameter standardization module, a training sample dividing module, a characteristic attention calculating module, a characteristic fusion module, a model learning module and a cooling water backwater temperature prediction module; the parameter recording module is used for effectively recording real-time operation parameters of the central air conditioner and transmitting the real-time operation parameters to the data acquisition system, the parameter standardization module is used for carrying out standardization processing on the acquired parameters, and the training sample dividing module is used for dividing data into sample characteristics and sample labels so as to facilitate training of a machine learning model; the feature attention calculation module is used for carrying out attention calculation on the feature set between time sequence and different parameters, the feature fusion module is used for carrying out deep fusion on new features of attention again, the model learning module is used for obtaining a trained model, and the cooling water return water temperature prediction module is used for predicting cooling water return water temperature.
In summary, the nonlinear relation between the chilled water return temperature value and other operation parameters of the central air conditioner is excavated mainly by collecting the real-time operation parameters of the central air conditioner and setting the correlation model between the chilled water return temperature value and other operation parameters. Feature attention calculation and feature fusion are introduced in the model training process, feature discrimination is improved, and the chilled water return temperature at the future moment can be effectively predicted during the running of the central air conditioner under the analysis of the trained correlation model. And on the basis of the predicted value, whether surplus or loss exists in the refrigerating or heating quantity of the central air conditioner is reasonably judged. The method provides powerful guarantee for the operation strategy of the central air conditioner, and solves the problems in the background technology.
Those of ordinary skill in the art will appreciate that the modules of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components of the examples have been described generally in terms of functionality in the foregoing description to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiment provided in the present invention, it should be understood that the division of the modules is merely a logic function division, and other division manners may be implemented in practice, for example, multiple modules may be combined into one module, one module may be split into multiple modules, or some features may be omitted.
In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules.
The integrated modules, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-0nlyMemory (ROM), a random access memory (RAM, randomAccessMemory), a removable hard disk, a magnetic disk, or an optical disk, or the like, which can store program codes.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (10)
1. The central air conditioner chilled water backwater temperature prediction method is characterized by comprising the following steps of:
s1: effectively recording real-time operation parameters of the central air conditioner to form a real-time operation parameter data set of the central air conditioner;
s2: carrying out standardization treatment on the acquired parameters;
s3: dividing the data into sample features and sample labels so as to facilitate training of a machine learning model;
s4: performing attention calculation on the feature set between time sequence and different parameters, and mining association relations between the parameters and over time;
s5: for each of the samples x obtained in step S4 i Two new features of calculated attention are obtainedAnd (3) withDeep fusion is carried out again to obtain final fusion characteristics +.>
S6: the new fusion characteristics are sent into a three-layer BP neural network again, and a predicted value y 'of each sample for the return water temperature of the cooling water is obtained' i Will predict the value y' i True tag value y of sample i The mean square error calculation is performed according to the following formula to obtain the loss value l of each sample i The mean square error formula is as follows:
l i ＝E(y′ i -y i ) 2
after obtaining the loss value of each sample, updating the parameters of the model through the back propagation of the neural network, and obtaining the optimal parameters by the model after multiple rounds of training;
s7: and the trained neural network model is used for predicting the return water temperature of the central air conditioner in the future period.
2. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 1, wherein the step S1 is specifically: when the central air conditioner operates, temperature and humidity sensors are arranged at the motor, the chilled water outlet and return port, the indoor multi-temperature area and the outdoor, data of all the sensors are recorded according to the frequency of one time of the set interval time and are transmitted to the data acquisition system, and a data set is formed.
3. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 2, wherein the interval time is 30 seconds.
4. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 1, wherein the step S2 is specifically: firstly, calculating the mean value mu and the standard deviation sigma of all parameters, and obtaining a standardized data set through the following formula:
wherein T is a parameter data set, mu is a mean value, and sigma is a standard deviation.
5. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 1, wherein the step S3 is specifically: n pieces of data are used as one sample X according to 60 continuous records, 1 record is arranged between two samples, after the data X is divided, n-60 samples can be obtained, each sample is divided into characteristics and labels, all parameters of the first 59 records are arranged according to time sequence to be used as characteristic values X1 of the sample 1, the chilled water return temperature value in the last 1 record is used as label values Y1 of the sample 1, and according to the mode, all samples are divided into characteristics and labels to obtain all characteristic values X and all label values Y.
6. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 1, wherein the step S4 is specifically as follows:
for any one sample x in the feature set i ∈R 59*d Firstly, converting the dimension of the air conditioner into 8*d by a layer of BP neural network, wherein d represents the number of parameters recorded in the running process of the central air conditioner;
x after dimension conversion i Dividing the vector into 8 vectors 1*d according to the time dimension, and inputting the vectors into an attention calculating module to obtain new characteristics
X after dimension conversion i The vector divided into d 8*1 according to different parameter directions is input into an attention calculating module to obtain new characteristics
The saidAnd->Are all equal to x i Is the same.
7. The method for predicting the return water temperature of chilled water of a central air conditioner according to claim 1, wherein the step S5 is specifically: will beAnd->Adding the elements at each position in pairs, obtaining new features by a BP neural network, pooling the new features to obtain a score vector, multiplying the score vector with the new features to obtain final fusion features>
8. The central air conditioner adjustable electricity demand prediction system is characterized by being applied to the central air conditioner adjustable electricity demand prediction method according to any one of claims 1 to 7, and comprises a parameter recording module, a parameter standardization module, a training sample dividing module, a characteristic attention calculating module, a characteristic fusion module, a model learning module and a cooling water return water temperature prediction module; the parameter recording module is used for effectively recording real-time operation parameters of the central air conditioner and transmitting the real-time operation parameters to the data acquisition system, the parameter standardization module is used for carrying out standardization processing on the acquired parameters, and the training sample dividing module is used for dividing data into sample characteristics and sample labels so as to facilitate training of a machine learning model; the feature attention calculation module is used for carrying out attention calculation on the feature set between time sequence and different parameters, the feature fusion module is used for carrying out deep fusion on new features of attention again, the model learning module is used for obtaining a trained model, and the cooling water return water temperature prediction module is used for predicting cooling water return water temperature.
9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program when run controls a device in which the computer readable storage medium is located to execute a chilled water return temperature prediction method of a central air conditioner according to any one of claims 1 to 7.
10. A processor, wherein the processor is configured to run a program, and wherein the program executes a method for predicting a chilled water return temperature of a central air conditioner according to any one of claims 1 to 7 when run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310679692.6A CN116592462A (en) | 2023-06-09 | 2023-06-09 | Central air conditioner chilled water backwater temperature prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310679692.6A CN116592462A (en) | 2023-06-09 | 2023-06-09 | Central air conditioner chilled water backwater temperature prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116592462A true CN116592462A (en) | 2023-08-15 |
Family
ID=87608226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310679692.6A Pending CN116592462A (en) | 2023-06-09 | 2023-06-09 | Central air conditioner chilled water backwater temperature prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116592462A (en) |
-
2023
- 2023-06-09 CN CN202310679692.6A patent/CN116592462A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458340B (en) | Building air conditioner cold load autoregressive prediction method based on mode classification | |
| CN114484731B (en) | Central air conditioner fault diagnosis method and device based on stacking fusion algorithm | |
| CN101021914A (en) | Heating ventilating and air conditioner load predicting method and system | |
| CN112415924A (en) | Energy-saving optimization method and system for air conditioning system | |
| CN115220351B (en) | Intelligent energy-saving optimization control method for building air conditioning system based on cloud side end | |
| CN111442489A (en) | Control method and system of air conditioner, air conditioner and readable storage medium | |
| CN111539845B (en) | Enterprise environment-friendly management and control response studying and judging method based on power consumption mode membership grade | |
| CN113657660A (en) | Heat source load prediction method based on substation load and heat supply network hysteresis model | |
| CN114997044A (en) | Energy consumption optimization method and data acquisition system for central air conditioner | |
| CN107220514A (en) | Air-conditioning load prediction method and system based on big data | |
| CN108491580A (en) | A kind of equipment fault diagnosis apparatus and system | |
| CN112283876A (en) | Air conditioner fault prediction method and air conditioner | |
| CN116266253A (en) | Optimization control method, system and computer readable storage medium for air conditioner parameters | |
| CN107036238A (en) | Intelligent energy-saving control method for dynamically predicting external air and load | |
| CN111723085B (en) | Method and system for cleaning electric energy consumption data of public building air conditioner | |
| CN116384700A (en) | Energy efficiency optimization method for central air conditioning system based on data mining | |
| CN117234301A (en) | Server thermal management method based on artificial intelligence | |
| CN116558038A (en) | Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium | |
| CN116928984B (en) | Internal and external double-circulation temperature and humidity regulation and control system and regulation and control method for constant temperature and humidity refrigeration house | |
| CN116592462A (en) | Central air conditioner chilled water backwater temperature prediction method and system | |
| JP4434905B2 (en) | Process management device | |
| CN113108643B (en) | Heat exchange system based on micro-channel heat exchanger and computer readable storage medium | |
| CN116562111A (en) | Data center energy saving method, device, system and storage medium | |
| CN116499084A (en) | Peak clipping method and system for electric power system based on chilled water outlet and return water temperature difference | |
| CN116663617A (en) | Method and system for predicting adjustable power consumption requirement of central air conditioner |
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 |