CN112762576A - Air conditioning system control method, temperature reaching time prediction model training method and equipment - Google Patents
Air conditioning system control method, temperature reaching time prediction model training method and equipment Download PDFInfo
- Publication number
- CN112762576A CN112762576A CN202011593392.9A CN202011593392A CN112762576A CN 112762576 A CN112762576 A CN 112762576A CN 202011593392 A CN202011593392 A CN 202011593392A CN 112762576 A CN112762576 A CN 112762576A
- Authority
- CN
- China
- Prior art keywords
- temperature
- time
- conditioning system
- air
- air conditioning
- 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
Images
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
- F24F11/62—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
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/12—Timing analysis or timing optimisation
Abstract
The application discloses an air conditioning system control method, a temperature reaching time prediction model training method and equipment, wherein the air conditioning system control method comprises the following steps: the method comprises the steps that outdoor environmental parameters and indoor environmental parameters before an air conditioning system is started are obtained, the indoor environmental parameters at least comprise first temperature of an air handling unit of the air conditioning system, and the first temperature is the temperature in an air return pipe of the air handling unit; inputting the outdoor environment parameters and the indoor environment parameters into a temperature reaching time prediction model to obtain the time of reaching the temperature, wherein the temperature reaching time prediction model is obtained by training by utilizing historical operation data of an air conditioning system; and controlling the starting of the air conditioner according to the temperature reaching time. Through the mode, the method and the device can accurately predict the time reaching the temperature, accurately control the starting time and reduce the energy consumption.
Description
Technical Field
The application relates to the technical field of air conditioners, in particular to an air conditioner system control method, a temperature reaching time prediction model training method and equipment.
Background
With the popularization of Air conditioners, the energy consumption of the Air conditioners becomes a major part of the energy consumption of life, especially large Heating, Ventilation and Air Conditioning (HVAC), and the energy consumption of the system is huge. Large buildings such as offices and malls generally stop cooling or heating at night, but require that the indoor temperature reaches a set value (e.g., 26 degrees for cooling and 22 degrees for heating) when the buildings are actually operated (e.g., 8:30am) in the morning. Therefore, the HVAC system is generally started up in advance, and how long the HVAC system needs to be started up in advance is generally set empirically, and excess time is generally reserved to ensure that the indoor temperature reaches the set value when the building is in formal operation (for example, only 1 hour is actually used, but the HVAC system is started up 1 half hour in advance). Reserving excess pre-refrigeration/heating time can result in wasted energy. Therefore, it is necessary to optimize through reasonable control so as to effectively reduce energy consumption.
Disclosure of Invention
The technical problem mainly solved by the application is to provide an air conditioning system control method, a temperature reaching time prediction model training method and equipment, which can accurately predict the temperature reaching time, accurately control the starting time and reduce the energy consumption.
In order to solve the technical problem, the application adopts a technical scheme that: provided is an air conditioning system control method including: the method comprises the steps that outdoor environmental parameters and indoor environmental parameters before an air conditioning system is started are obtained, the indoor environmental parameters at least comprise first temperature of an air handling unit of the air conditioning system, and the first temperature is the temperature in an air return pipe of the air handling unit; inputting the outdoor environment parameters and the indoor environment parameters into a temperature reaching time prediction model to obtain the time of reaching the temperature, wherein the temperature reaching time prediction model is obtained by training by utilizing historical operation data of an air conditioning system; and controlling the starting of the air conditioner according to the temperature reaching time.
Wherein the outdoor environment parameters at least comprise outdoor dry bulb temperature and outdoor wet bulb temperature.
Wherein, the indoor environmental parameter still includes indoor dry bulb temperature, and indoor dry bulb temperature is the average value of the indoor dry bulb temperature in at least two spaces.
Wherein, obtaining the indoor environment parameters before the air conditioning system is started comprises: predicting the number of starting air handling units; selecting m air handling units as air handling units to be started, wherein m is the predicted number of the started air handling units, calculating the average value of the first temperatures of all the air handling units to be started, and taking the average value of the first temperatures as an indoor environment parameter.
Wherein, m air handling units can be selected from all air handling units as the air handling units to be started up. Or m air handling units with specific identifications can be selected as the air handling units to be started according to preset rules.
The air conditioning system control method further comprises the following steps: acquiring a startup operation period identifier of the air conditioning system, wherein the operation period identifier is used for identifying a node of a startup day in an operation period; and inputting the operation period identifier as a prediction parameter into the temperature-reaching time prediction model.
Wherein, obtaining the outdoor environmental parameter and the indoor environmental parameter before the air conditioning system is started comprises: the method comprises the steps of obtaining outdoor environment parameters and indoor environment parameters of an air conditioning system at a first moment before the air conditioning system is started, wherein the first moment is obtained by calculation according to a target temperature reaching moment and a first time length, and the first time length refers to the maximum allowable advanced starting time length of the air conditioning system.
Wherein, calculating the first time according to the target temperature reaching time and the first time length comprises: and calculating a first duration forward by taking the target temperature reaching moment as a node, wherein the calculated moment is the first moment.
In order to solve the above technical problem, another technical solution adopted by the present application is: an air conditioning system is provided, the air conditioner comprising an air handling unit and a controller for executing instructions to implement any of the air conditioning system control methods described above.
In order to solve the above technical problem, another technical solution adopted by the present application is: a training method of a temperature-reaching time prediction model is provided, and comprises the following steps: acquiring a plurality of groups of first historical operating data, wherein the first historical operating data comprises outdoor environmental parameters before the air conditioning system is started, indoor environmental parameters and the temperature reaching duration of the air conditioning system, the indoor environmental parameters at least comprise a first temperature of an air handling unit of the air conditioning system, and the first temperature is the temperature in an air return pipe of the air handling unit; and taking the outdoor environment parameters and the indoor environment parameters of a plurality of groups of first historical operating data as inputs, and taking the time of reaching the temperature as an output to carry out model training to obtain a temperature and time predicting model.
Wherein missing values in the sets of first historical operating data may be filled in using linear interpolation.
And removing outlier data in the first historical operating data of the groups by utilizing the box type graph.
Wherein, 75-85% of a plurality of groups of first historical operating data can be used as training sample data to be input into the initial model, and a temperature reaching time prediction model is obtained after training; inputting the remaining 15-25% of the first historical operating data of a plurality of groups as training sample data into a temperature reaching time prediction model, and verifying the temperature reaching time prediction model; responding to the temperature and time reaching prediction model reaching the standard, and performing model deployment application work; and responding to the situation that the temperature-reaching time prediction model does not reach the standard, and executing the work of obtaining historical operation data, model training and model verification again until the temperature-reaching time prediction model reaches the standard.
The training method of the temperature-reaching time prediction model further comprises the following steps: acquiring second historical operating data, wherein the generation time of the second historical operating data is later than that of the first historical operating data; and updating the temperature-reaching time prediction model by using the second historical operation data.
Wherein, the temperature-reaching time prediction model is an XgBoost model, an SVM model or a Random Forest model.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a time-to-temperature prediction apparatus comprising a processor for executing instructions to implement a method of training a time-to-temperature prediction model of any one of the above.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a computer readable storage medium for storing instructions/program data executable to implement the method of any one of the above.
The beneficial effect of this application is: the method is different from the situation of the prior art, the temperature reaching time prediction model is provided, necessary parameters are obtained, the time required by the air conditioner to reach the target temperature from the starting up can be accurately predicted by the temperature reaching time prediction model, the starting up time of the air conditioner can be accurately controlled, the extra early starting up time is shortened, and the energy consumption can be reduced.
Drawings
FIG. 1 is a schematic flow chart of a method for training a time-to-temperature prediction model according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating another method for training a time-to-temperature prediction model according to an embodiment of the present disclosure;
FIG. 3 is a flow chart illustrating a control method of an air conditioning system according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a temperature-reaching time prediction apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural view of an air conditioning system in an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer-readable storage medium in an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solution and effect of the present application clearer and clearer, the present application is further described in detail below with reference to the accompanying drawings and examples.
The application provides an air conditioner control method, which can train a temperature reaching time prediction model by using historical operating data of an air conditioner, predict the time required by pre-cooling/heating by using the temperature reaching time prediction model, and further control the time for starting the air conditioner in advance. In this way, the predicted time to reach the temperature is more accurate than the manual prediction, so that the startup time is more accurately controlled; the target temperature can be achieved on time, extra starting time cannot be increased, and energy consumption can be effectively reduced. Meanwhile, the control method can realize equipment automation, automatically control the operation of the air conditioning unit, reduce manual participation and save labor cost.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a temperature-reaching time prediction model training method according to an embodiment of the present disclosure. In the embodiment, the temperature-reaching time prediction model can be trained by using historical operating data of the air conditioner. It should be noted that, if the result is substantially the same, the flow sequence shown in fig. 1 is not limited in this embodiment. As shown in fig. 1, the present embodiment includes:
s110: several sets of historical operating data are obtained.
The plurality of groups of historical operating data comprise outdoor environmental parameters and indoor environmental parameters before the air conditioning system is started, and the temperature reaching time of the air conditioning system.
Wherein the outdoor environment parameters at least comprise outdoor dry bulb temperature and outdoor wet bulb temperature. The dry bulb temperature is a value read by a dry bulb thermometer exposed to the air without being directly irradiated by the sun, and can reflect the real temperature of the air to a certain extent. The wet bulb temperature is a value read on the wet bulb thermometer, the temperature sensing part of the thermometer is wrapped by wet cotton cloth, and the cotton cloth is kept in a wet state all the time, so that the wet bulb thermometer can be formed. And meanwhile, the dry bulb temperature and the wet bulb temperature of the outdoor environment are obtained, the outdoor environment information can be more accurately evaluated and judged, and the time length required by preheating/refrigerating is calculated.
The indoor environmental parameter includes at least a first temperature of an Air Handling Unit (AHU) of the Air conditioning system. The first temperature is the temperature in the return air duct of the air handling unit, and a temperature sensor can be arranged in the return air duct of the air handling unit to detect and acquire the first temperature. When the air handling unit operates, the return air in the return air pipe is the air drawn back from the indoor space, and the temperature of the return air in the return air pipe can reflect the indoor environment temperature to a certain extent. Before starting up, the return air pipe is communicated with the indoor space, and the indoor environment temperature before starting up can be reflected by the temperature in the return air pipe; after the machine is started, the return air flows in the return air pipe, and the temperature of indoor air at the moment of returning the return air can be reflected. HVAC system generally is applied to large-scale building, and the air conditioner air outlet distributes widely in the building, and the dispersion is in different spaces, if every space all detects space temperature, detects the degree of difficulty great. The indoor environment temperature is reflected by the first temperature of the air handling unit, and whether the temperature is reached is judged, so that the air handling unit is relatively more convenient, simple and stable.
The time length of reaching the temperature is the time length required by the air conditioner to reach the target temperature from starting.
S120: and taking outdoor environment parameters and indoor environment parameters of a plurality of groups of historical operating data as input, and taking the time of reaching the temperature as output to carry out model training to obtain a model for predicting the time of reaching the temperature.
In the embodiment, the temperature-reaching time prediction model can be trained by using historical operating data of the air conditioning system, and when the model is trained, various influence factors are considered, so that the model can be constrained, and a more accurate prediction result can be obtained.
Referring to fig. 2, fig. 2 is a schematic flow chart illustrating another temperature-reaching time prediction model training method according to an embodiment of the present disclosure. In the embodiment, the temperature-reaching time prediction model can be trained by using historical operating data of the air conditioner. It should be noted that, if the result is substantially the same, the flow sequence shown in fig. 2 is not limited in this embodiment. As shown in fig. 2, the present embodiment includes:
s210: several sets of historical operating data are obtained.
The historical operation data of the air conditioner at least comprises outdoor environment parameters, indoor environment parameters, operation cycle identification and temperature reaching duration of the current day of operation. During the period of collecting sample data, the advanced start-up time length can be manually controlled, a fixed advanced start-up time length can also be preset, and the advanced start-up time length can be designed to be equal to the maximum allowable advanced start-up time length in advance so as to ensure that the target temperature can be reached at the target moment. In the operation period, the air conditioner is generally started once a day, and can be started in the morning every day, and after the air conditioner is started, the air conditioner operates for a whole day, and a set of sample data can be acquired every day. The more training samples the better, the more accurate the trained model will be. For example, outdoor environmental parameters, indoor environmental parameters and running period identification during starting up within one month and corresponding temperature reaching time can be collected in advance to be used as training samples, and the model is trained.
In one embodiment, more parameters may be obtained as input to the temperature-reaching time prediction model to obtain a more accurate prediction result.
Optionally, the number of the air handling units to be started can be predicted, and the time for reaching the temperature can be shortened to a certain extent as more air handling units are started, so that the number of the air handling units to be started can be used as a prediction parameter of the time for reaching the temperature. The obtained first temperature of the air handling unit may be an average of the first temperatures of the plurality of air handling units when the plurality of air handling units are operating. Or, when the first temperature of most of the air handling units reaches the target temperature at the target moment, the temperature is considered to be reached; if 80% of the first temperature of the air handling unit reaches the temperature, the indoor temperature is determined to have reached the temperature. And meanwhile, the running data of all air handling units can be recorded, and the air handling units which cannot reach the temperature for a long time can be removed. The number of air handling units that are turned on may be determined by a load prediction algorithm. Specifically, load prediction variables are obtained, wherein the load prediction variables can comprise outdoor average temperature, indoor average temperature, terminal opening number and the like, and the load prediction variables are used for predicting the number of the air processing units which are started. If it is predicted that m air handling units are needed to be started, m air handling units can be selected from all the air handling units as air handling units to be started, and when the starting time is up, the m air handling units to be started are started to operate. Or m air handling units with specific identifications can be selected as the air handling units to be started according to preset rules. If the number of the air handling units can be numbered, the air handling units to be started are selected in a circulating mode according to the operation period. For example, there are 10 air handling units in total; starting the air treatment units with the numbers of 1-4 on the first day, starting 3 air treatment units on the second day, selecting the air treatment units with the numbers of 5-7, starting 5 air treatment units on the third day, selecting the air treatment units with the numbers of 8-10 and 1-2, and circulating sequentially. Through the mode, the air treatment units can be reasonably and fully utilized, and particularly when a plurality of groups of air treatment units are arranged, the air treatment units can be stopped in turn to maintain and prolong the service life. Of course, the selection rule of the air handling unit is not limited in the application, and the selection rule can be set according to needs.
Optionally, the dry bulb temperature in each room can be obtained, and whether the indoor environment reaches the temperature or not can be fed back more accurately. The temperature of each indoor air conditioner control panel can be read as the indoor dry bulb temperature. In this way, the cost of laying out the thermometer indoors can be reduced. Similarly, the average of the dry bulb temperatures of at least two spaces can be used to determine whether the indoor environment is warm.
Optionally, more input data can be added as the prediction parameters, for example, weather forecast data, wind data, solar radiation data, HVAC operation setting data, etc. can also be acquired, and the prediction accuracy of the prediction model can be further improved.
In one embodiment, for management, the HVAC system typically pre-designs an operation period to control the air conditioner to operate according to a certain rule. For the air conditioner of office buildings, the air conditioner can be set to operate only in working days and not in holidays; for the air conditioner of the market building, a specific rest day can be set, and the air conditioner does not operate in the rest day. In the operation period, when the air conditioner is started every time, the time interval between the air conditioner and the previous shutdown has a certain rule. The length of the shutdown interval can have a certain influence on the time to reach the temperature. If the air conditioner is set to operate on Monday to Friday, and not to operate on Saturday and Sunday. When the air conditioner is started on monday, the time interval between the air conditioner and the last shutdown is two days on weekend, and the indoor and outdoor environment is basically not influenced by the last air conditioner operation any more; when the air conditioner is started on a tuesday, the time interval between the air conditioner and the last shutdown is only one night, and the indoor and outdoor environment may also have the influence of the residual temperature of the air conditioner; especially, the indoor environment is influenced by the previous air conditioner operation to a certain extent if the air conditioner is closed after being turned off, and by analogy, when the air conditioner is turned on in five weeks, the influence factor may be accumulated to be obviously different from that when the air conditioner is turned on in monday. Or, in the same external environment, the time duration of reaching the temperature during the Monday startup and the time duration of reaching the temperature during the Friday startup may be different. Furthermore, the shutdown interval may also have an effect on the operating efficiency of the air handling unit to a certain extent; therefore, the shutdown interval will have an effect on the length of time to reach temperature to some extent. The influence factor is considered, and the parameter of the operation period is incorporated into the temperature-reaching time prediction model, so that the accuracy of prediction of the temperature-reaching time prediction model is improved. The operation cycle identifier is used for identifying a node of the startup day in the operation cycle. If the operation cycle design has a rest of one day every ten days of operation, the operation cycle identifier may be … … for the first and second days of operation; the operation cycle designs Monday to Friday operation and weekend rest, and the operation cycle identifier can be Monday, Tuesday … …, etc. The method and the device do not limit the form of the operation period identification, and the operation period identification is displayed in a mode of showing the operation time length and the interval time length.
S220: and processing the historical operating data.
Wherein, abnormal data can be cleaned.
And counting the operation data collected every day, and filling a missing value if certain data is missing. If the initial first temperature of a certain air handling unit is absent or the first temperature when reaching the temperature is absent, interpolation can be used to fill the missing value. The missing values can be filled in using linear interpolation, for example.
And counting the operation data collected every day, and if certain data is obviously abnormal, rejecting the data. If the first temperature of one air handling unit is obviously different from the first temperatures of other air handling units, the accuracy of the average first temperature is influenced, and the data can be rejected. The boxed graph may be used to cull out anomalous data.
And counting and recording the operating data of all the air handling units, and if the air handling units cannot reach the temperature for a long time or cannot reach the temperature for multiple times, considering that the air handling units are abnormal or damaged, reporting to repair and processing the air handling units, and removing the air handling units from the sample data to improve the accuracy of the model.
S230: inputting the processed historical operating data into an initial model for training.
The regression prediction model can be selected as a model framework of the temperature-reaching time prediction model, such as XgBoost, ANN, SVM, RandomForest model and the like. The model has simple structure and small size, and can be applied to various air conditioner processors.
80-90% of the collected sample data can be used as training sample data, a loss function of the model is calculated, and a temperature-reaching time prediction model is obtained through training; and taking the remaining sample data as verification sample data, verifying the obtained temperature-reaching time prediction model, and determining whether the model reaches the standard or not. The mean absolute value error may be used as an evaluation criterion. If the model reaches the standard, the method can be popularized and applied, and if the model does not reach the standard, the training sample can be increased, and the training is continued until the model reaches the standard.
In the above embodiment, the trained temperature reaching time prediction model can be applied to a large heating, ventilating and cooling air conditioner, and is used for accurately predicting the temperature reaching time so as to accurately control the early starting time and reduce the energy consumption.
In one embodiment, the temperature-reaching time prediction model can be carried in an air conditioner processor, and parameter data can be obtained locally to predict the temperature-reaching time, control the startup time and realize self-control. In other embodiments, the temperature-reaching time prediction model may be mounted in a cloud server, the air conditioner obtains parameter data and sends the parameter data to the cloud server, and the cloud server performs prediction by using the model and sends the prediction data to the air conditioner, or sends a control instruction to the air conditioner, so as to realize remote control of the air conditioner. The temperature reaching time prediction model is carried in the server, so that the operation is faster, and meanwhile, a plurality of air conditioners can be simultaneously controlled, the comprehensive control is realized, and the model management is convenient.
Referring to fig. 3, fig. 3 is a flowchart illustrating an air conditioner control method according to an embodiment of the present disclosure. In this embodiment, the time to reach temperature can be predicted by using the time to reach temperature prediction model, so as to accurately control the boot time. It should be noted that, if the result is substantially the same, the flow sequence shown in fig. 3 is not limited in this embodiment. As shown in fig. 3, the present embodiment includes:
s310: and acquiring outdoor environment parameters and indoor environment parameters before the air conditioning system is started.
The outdoor environmental parameters and the indoor environmental parameters at a first moment before the air-conditioning system is started can be obtained, the first moment is obtained by calculation according to the target temperature reaching moment and a first time length, and the first time length refers to the maximum allowable advanced starting time length of the air-conditioning system. Specifically, the target temperature reaching time may be used as a node to estimate the first time length forward, and the estimated time may be the first time. The target temperature reaching time can be a certain time which is set in 12 hours or 24 hours, and can be set in advance according to needs. The first time may be a certain time in the 12-hour system or the 24-hour system. The first time is calculated according to the target temperature reaching time and the first time length, and may be calculated by pushing the target temperature reaching time forward by the first time length, and in a normal case, the first time length may be obtained by subtracting the first time length from the target temperature reaching time, for example, the target temperature reaching time is 8 am, the first time length is 1 hour, and the first time length is 7 am (8 pm minus 1 hour). In some cases, the conversion may be required, for example, the target time to reach temperature is 1 am, the first time period is 2 hours, and the first time period is 23 am. For example, an outdoor environment parameter and an indoor environment parameter at a certain time in the morning may be acquired. This time may be derived from the maximum allowed advanced boot time. If the target time to temperature (e.g., 8:30) is 2 hours and 30 minutes, then 6 o' clock outdoor environment parameters and indoor environment parameters need to be obtained. The maximum allowable advanced starting time duration can be set according to the performance of the air conditioner, application scenes and the like, and can be two and a half hours, two hours and the like.
The outdoor environment parameter and the indoor environment parameter may be one or more of the parameters used in any of the embodiments described above.
S320: and inputting the outdoor environment parameters and the indoor environment parameters into the temperature reaching time prediction model to obtain the temperature reaching time.
Besides the parameters, the corresponding parameters can be adaptively selected and input into the model according to the parameters used in the training of the temperature-reaching time prediction model, so as to obtain a more accurate prediction result.
Such as the number of air handling units that are turned on. The number of air handling units that are turned on may be determined by a load prediction algorithm. Specifically, load prediction variables are obtained, wherein the load prediction variables can comprise outdoor average temperature, indoor average temperature, terminal opening number and the like, and the load prediction variables are used for predicting the number of the air processing units which are started. The air treatment units can be reasonably and fully utilized, and particularly when a plurality of groups of air treatment units are arranged, the air treatment units can be shut down in turn to maintain and prolong the service life.
S330: and controlling the starting of the air conditioning system according to the temperature reaching time.
The air conditioning system can be controlled to be started up in advance when the temperature reaches the duration so as to reach the target temperature at the moment when the temperature reaches the target temperature.
For example, if the predicted temperature reaching time is 1 hour, and the target temperature reaching time is 8:30, the unit operation can be started at 7 points 30. The actual startup time point after prediction may be different from the time point of acquiring parameter data during prediction, for example, 6 o 'clock is used for prediction, and 7 o' clock half startup is required after prediction. Although the parameter data for the two time instants may deviate by a small amount, this error may be within an allowable range. In other words, this error factor is taken into account during model training, and therefore, the error does not have a substantial effect on the final prediction result.
In the embodiment, the time required for pre-cooling/heating is predicted by using the temperature reaching time prediction model, so that the time for starting the air conditioner in advance is controlled. In this way, the predicted time to reach the temperature is more accurate than the manual prediction, so that the startup time is more accurately controlled; the target temperature can be achieved on time, extra starting time cannot be increased, and energy consumption can be effectively reduced. Meanwhile, the control method can realize equipment automation, automatically control the operation of the air conditioning unit, reduce manual participation and save labor cost.
In one embodiment, the prediction effect may be monitored periodically and the prediction model may be updated in time. In particular, the model prediction effect may change over time, thus requiring constant monitoring of the model prediction effect and retraining of the model using newly acquired operational data. The prediction model can be set to be updated regularly; an error threshold may also be set and the model update performed when the prediction error is greater than the threshold.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a temperature-reaching time prediction apparatus according to an embodiment of the present disclosure. In this embodiment, the time-to-temperature prediction apparatus 10 includes a processor 11.
The processor 11 may also be referred to as a CPU (Central Processing Unit). The processor 11 may be an integrated circuit chip having signal processing capabilities. The processor 11 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor 11 may be any conventional processor or the like.
The warm-time prediction model training 10 may further include a memory (not shown) for storing instructions and data required for the processor 11 to operate.
The processor 11 is configured to execute instructions to implement the methods provided by any of the embodiments of the time-to-temperature prediction model training methods of the present application and any non-conflicting combinations thereof.
The temperature-reached time prediction device may be a computer device such as a server, may be a single server, may be a server cluster, or the like.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an air conditioning system according to an embodiment of the present disclosure. In this embodiment, the air conditioning system 20 includes a controller 21 and an air handling unit 22.
The controller 21 may also be referred to as a CPU (Central Processing Unit). The controller 21 may be an integrated circuit chip having signal processing capabilities. The controller 21 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the controller 21 may be any conventional processor or the like.
The controller 21 is configured to execute instructions to implement the methods provided by any of the embodiments of the air conditioning control method of the present application and any non-conflicting combinations.
The air conditioning system 20 may be a large heating, ventilating, and cooling air conditioner, which may be used in large buildings.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present disclosure. The computer readable storage medium 30 of the present embodiment stores instructions/program data 31, and when executed, the instructions/program data 31 implement the method provided by any embodiment of the above-mentioned temperature-reaching prediction model training method, air-conditioning control method, and any non-conflicting combination of the above-mentioned embodiments of the present invention. The instructions/program data 31 may form a program file stored in the storage medium 30 in the form of a software product, so as to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods according to the embodiments of the present application. And the aforementioned storage medium 30 includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (15)
1. An air conditioning system control method, comprising:
acquiring outdoor environmental parameters and indoor environmental parameters before the air conditioning system is started, wherein the indoor environmental parameters at least comprise a first temperature of an air handling unit of the air conditioning system, and the first temperature is the temperature in an air return pipe of the air handling unit;
inputting the outdoor environment parameters and the indoor environment parameters into a temperature reaching time prediction model to obtain temperature reaching time, wherein the temperature reaching time prediction model is obtained by utilizing historical operation data of the air conditioning system in a training mode;
and controlling the start of the air conditioner according to the temperature reaching time.
2. The method as claimed in claim 1, wherein the obtaining the indoor environment parameter before the air conditioning system is turned on comprises:
predicting the number of starting air handling units;
selecting m air handling units as air handling units to be started, wherein m is the predicted number of started air handling units;
and calculating the average value of the first temperatures of all the air handling units to be started, and taking the average value of the first temperatures as the indoor environment parameter.
3. The air conditioning system control method according to claim 2, wherein the selecting m air handling units as the air handling units to be started comprises:
randomly selecting m air treatment units from all the air treatment units as the air treatment units to be started; or
And according to a preset rule, selecting m air handling units with specific identifications as the air handling units to be started.
4. The air conditioning system control method according to claim 1, characterized by further comprising:
acquiring a startup operation period identifier of the air conditioning system, wherein the operation period identifier is used for identifying a node of a startup day in an operation period;
and inputting the operation cycle identifier as a prediction parameter into the temperature-reaching time prediction model.
5. The method as claimed in claim 1, wherein the obtaining of the outdoor environment parameter and the indoor environment parameter before the air conditioning system is turned on comprises:
the method comprises the steps of obtaining outdoor environment parameters and indoor environment parameters of the air conditioning system at a first moment before the air conditioning system is started, wherein the first moment is obtained by calculation according to a target temperature reaching moment and a first time length, and the first time length refers to the maximum allowable advanced starting time length of the air conditioning system.
6. The air conditioning system control method according to claim 5, wherein the calculating the first time according to the target temperature reaching time and the first time period comprises:
and calculating the first duration forward by taking the target temperature reaching moment as a node, wherein the calculated moment is the first moment.
7. The air conditioning system control method according to claim 1,
the outdoor environment parameters at least comprise outdoor dry bulb temperature and outdoor wet bulb temperature; and/or
The indoor environmental parameters at least include indoor dry bulb temperature, which is an average of indoor dry bulb temperatures of at least two spaces.
8. An air conditioning system, comprising:
an air handling unit and a controller for executing instructions to implement the air conditioning system control method of any of claims 1-7.
9. A method for training a temperature-reaching time prediction model is characterized by comprising the following steps:
acquiring a plurality of groups of first historical operating data, wherein the first historical operating data comprises outdoor environmental parameters before an air conditioning system is started, indoor environmental parameters and the temperature reaching duration of the air conditioning system, the indoor environmental parameters at least comprise a first temperature of an air handling unit of the air conditioning system, and the first temperature is the temperature in an air return pipe of the air handling unit;
and taking the outdoor environment parameters and the indoor environment parameters of the plurality of groups of first historical operating data as inputs, and taking the time of reaching the temperature as an output to carry out model training to obtain a temperature and time predicting model.
10. A method of training a time-to-temperature prediction model according to claim 9, wherein the obtaining a plurality of sets of first historical operating data comprises:
filling missing values in the plurality of groups of first historical operating data by using a linear interpolation method; and/or
And removing outlier data in the plurality of groups of first historical operating data by using the box type graph.
11. The method of training of a time-to-temperature prediction model according to claim 9,
inputting 75-85% of the plurality of groups of first historical operating data as training sample data into an initial model, and obtaining a temperature-reaching time prediction model after training;
inputting the remaining 15-25% of the plurality of groups of first historical operating data as training sample data into the temperature reaching time prediction model, and verifying the temperature reaching time prediction model;
responding to the temperature and time reaching prediction model reaching the standard, and performing model deployment application work; and responding to the fact that the temperature-reaching time prediction model does not reach the standard, and executing the work of obtaining historical operation data, model training and model verification again until the temperature-reaching time prediction model reaches the standard.
12. The method of training of a time-to-temperature prediction model according to claim 9,
acquiring second historical operating data, wherein the generation time of the second historical operating data is later than that of the first historical operating data;
and updating the temperature-reaching time prediction model by using the second historical operation data.
13. The method of training of a time-to-temperature prediction model according to claim 9,
the temperature-reaching time prediction model is an XgBoost model, an SVM model or a Random Forest model.
14. An arrival time prediction apparatus characterized in that,
the time-to-temperature prediction apparatus comprises a processor for executing instructions to implement a method of training a time-to-temperature prediction model as claimed in any one of claims 9 to 13.
15. A computer-readable storage medium for storing instructions/program data executable to implement a method of training a time-to-temperature prediction model according to any one of claims 9-13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011593392.9A CN112762576A (en) | 2020-12-29 | 2020-12-29 | Air conditioning system control method, temperature reaching time prediction model training method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011593392.9A CN112762576A (en) | 2020-12-29 | 2020-12-29 | Air conditioning system control method, temperature reaching time prediction model training method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112762576A true CN112762576A (en) | 2021-05-07 |
Family
ID=75696302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011593392.9A Pending CN112762576A (en) | 2020-12-29 | 2020-12-29 | Air conditioning system control method, temperature reaching time prediction model training method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112762576A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113339113A (en) * | 2021-07-15 | 2021-09-03 | 中国能源建设集团江苏省电力设计院有限公司 | Method and system for predicting NOx generation and ammonia demand of SCR system and storage medium |
| CN113375318A (en) * | 2021-06-04 | 2021-09-10 | 日立楼宇技术（广州）有限公司 | Control method, system and device for air conditioner pre-starting and storage medium |
| CN113739390A (en) * | 2021-09-30 | 2021-12-03 | 上海美控智慧建筑有限公司 | Air conditioner control method and device and electronic equipment |
| CN113847712A (en) * | 2021-09-15 | 2021-12-28 | 珠海格力电器股份有限公司 | Control method and control device of air conditioner and air conditioning system |
| CN113865046A (en) * | 2021-09-23 | 2021-12-31 | 宁波奥克斯电气股份有限公司 | Multi-air-conditioner control method and device and electronic equipment |
| CN114017904A (en) * | 2021-11-04 | 2022-02-08 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114279075A (en) * | 2021-12-29 | 2022-04-05 | 博锐尚格科技股份有限公司 | Cold station startup control method and device |
| CN114353273A (en) * | 2022-01-13 | 2022-04-15 | 北京小米移动软件有限公司 | Device control method, device, electronic device and storage medium |
| CN114383289A (en) * | 2021-12-13 | 2022-04-22 | 启北公司 | Method, device and equipment for calculating temperature adjustment duration and storage medium |
| CN116085937A (en) * | 2023-04-11 | 2023-05-09 | 湖南禾自能源科技有限公司 | Intelligent central air conditioner energy-saving control method and system |
| CN117606109A (en) * | 2024-01-22 | 2024-02-27 | 南京群顶科技股份有限公司 | Method and system for judging optimal temperature of air conditioner in machine room |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3029389A2 (en) * | 2014-12-04 | 2016-06-08 | Delta Electronics, Inc. | Controlling system for environmental comfort degree and controlling method of the controlling system |
| CN108009941A (en) * | 2017-11-23 | 2018-05-08 | 武汉大学 | Solve the nested optimization method of water light complementation power station Optimization of Unit Commitment By Improved |
| CN109373539A (en) * | 2018-11-07 | 2019-02-22 | 珠海格力电器股份有限公司 | Air-conditioning and its control method and device |
| CN111623497A (en) * | 2020-02-20 | 2020-09-04 | 上海朗绿建筑科技股份有限公司 | Radiation air conditioner precooling and preheating method and system, storage medium and radiation air conditioner |
-
2020
- 2020-12-29 CN CN202011593392.9A patent/CN112762576A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3029389A2 (en) * | 2014-12-04 | 2016-06-08 | Delta Electronics, Inc. | Controlling system for environmental comfort degree and controlling method of the controlling system |
| CN108009941A (en) * | 2017-11-23 | 2018-05-08 | 武汉大学 | Solve the nested optimization method of water light complementation power station Optimization of Unit Commitment By Improved |
| CN109373539A (en) * | 2018-11-07 | 2019-02-22 | 珠海格力电器股份有限公司 | Air-conditioning and its control method and device |
| CN111623497A (en) * | 2020-02-20 | 2020-09-04 | 上海朗绿建筑科技股份有限公司 | Radiation air conditioner precooling and preheating method and system, storage medium and radiation air conditioner |
Non-Patent Citations (1)
| Title |
|---|
| 赵哲身编著: "《智能建筑控制与节能》", 30 September 2007 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113375318A (en) * | 2021-06-04 | 2021-09-10 | 日立楼宇技术（广州）有限公司 | Control method, system and device for air conditioner pre-starting and storage medium |
| CN113339113A (en) * | 2021-07-15 | 2021-09-03 | 中国能源建设集团江苏省电力设计院有限公司 | Method and system for predicting NOx generation and ammonia demand of SCR system and storage medium |
| CN113339113B (en) * | 2021-07-15 | 2022-08-19 | 中国能源建设集团江苏省电力设计院有限公司 | Method and system for predicting NOx generation and ammonia demand of SCR system and storage medium |
| CN113847712A (en) * | 2021-09-15 | 2021-12-28 | 珠海格力电器股份有限公司 | Control method and control device of air conditioner and air conditioning system |
| CN113865046A (en) * | 2021-09-23 | 2021-12-31 | 宁波奥克斯电气股份有限公司 | Multi-air-conditioner control method and device and electronic equipment |
| CN113739390A (en) * | 2021-09-30 | 2021-12-03 | 上海美控智慧建筑有限公司 | Air conditioner control method and device and electronic equipment |
| WO2023050814A1 (en) * | 2021-09-30 | 2023-04-06 | 上海美控智慧建筑有限公司 | Method and apparatus for controlling air conditioner, and electronic device |
| CN113739390B (en) * | 2021-09-30 | 2023-01-24 | 上海美控智慧建筑有限公司 | Air conditioner control method and device and electronic equipment |
| CN114017904B (en) * | 2021-11-04 | 2023-01-20 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114017904A (en) * | 2021-11-04 | 2022-02-08 | 广东电网有限责任公司 | Operation control method and device for building HVAC system |
| CN114383289A (en) * | 2021-12-13 | 2022-04-22 | 启北公司 | Method, device and equipment for calculating temperature adjustment duration and storage medium |
| CN114383289B (en) * | 2021-12-13 | 2023-09-01 | 启北公司 | Temperature adjustment duration calculation method and device, equipment and storage medium |
| CN114279075B (en) * | 2021-12-29 | 2023-02-10 | 博锐尚格科技股份有限公司 | Cold station startup control method and device |
| CN114279075A (en) * | 2021-12-29 | 2022-04-05 | 博锐尚格科技股份有限公司 | Cold station startup control method and device |
| CN114353273A (en) * | 2022-01-13 | 2022-04-15 | 北京小米移动软件有限公司 | Device control method, device, electronic device and storage medium |
| CN116085937A (en) * | 2023-04-11 | 2023-05-09 | 湖南禾自能源科技有限公司 | Intelligent central air conditioner energy-saving control method and system |
| CN117606109A (en) * | 2024-01-22 | 2024-02-27 | 南京群顶科技股份有限公司 | Method and system for judging optimal temperature of air conditioner in machine room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112762576A (en) | Air conditioning system control method, temperature reaching time prediction model training method and equipment | |
| US11796205B2 (en) | Systems and methods of optimizing HVAC control in a building or network of buildings | |
| WO2018217251A1 (en) | Model predictive maintenance system for building equipment | |
| US20150167996A1 (en) | Thermodynamic modeling for enclosures | |
| CN110749053B (en) | Control method and device of air conditioner | |
| US11320165B2 (en) | Predictive temperature scheduling for a thermostat using machine learning | |
| CN102252400B (en) | Setting value controlling method and device | |
| US20120130924A1 (en) | System and method for analyzing energy use | |
| US11598542B2 (en) | Thermostat scheduling using user devices and machine learning | |
| CN111928429A (en) | Energy-saving control method and device for data center refrigerating system | |
| US11609014B2 (en) | Predictive presence scheduling for a thermostat using machine learning | |
| US20220042696A1 (en) | Error correction for predictive schedules for a thermostat | |
| CN114820227A (en) | Energy storage method and device | |
| US20220282882A1 (en) | Optimization engine for energy sustainability | |
| TWI678504B (en) | Ice storage amount adjusting system and adjusting method for the same | |
| CN113280474B (en) | Self-cleaning control method and device of multi-split air conditioner and storage medium | |
| CN112781177B (en) | Method and device for predicting air conditioner operating power, electronic equipment and storage medium | |
| CN113847715B (en) | Method and device for regulating and controlling air conditioner of base station, electronic equipment and medium | |
| WO2023164768A1 (en) | System and method for dynamic control of hvac components of a building | |
| US10503192B2 (en) | Energy consumption modeling | |
| Spencer et al. | Forecasting internal temperature in a home with a sensor network | |
| JP5751742B2 (en) | Air conditioning equipment remote management system, remote management device, control device | |
| CN114484773A (en) | Air conditioning unit and equipment mapping relation updating method and device thereof | |
| Salsbury et al. | Smarter building start–A distributed solution | |
| Korkas et al. | Adaptive optimization for smart operation of cyber-physical systems: A thermostatic zoning test case |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210507 |