Nothing Special   »   [go: up one dir, main page]

WO2023050814A1 - 空调器控制方法、装置和电子设备 - Google Patents

空调器控制方法、装置和电子设备 Download PDF

Info

Publication number
WO2023050814A1
WO2023050814A1 PCT/CN2022/091244 CN2022091244W WO2023050814A1 WO 2023050814 A1 WO2023050814 A1 WO 2023050814A1 CN 2022091244 W CN2022091244 W CN 2022091244W WO 2023050814 A1 WO2023050814 A1 WO 2023050814A1
Authority
WO
WIPO (PCT)
Prior art keywords
air conditioner
time
predicted
temperature
prediction
Prior art date
Application number
PCT/CN2022/091244
Other languages
English (en)
French (fr)
Inventor
方兴
李元阳
胡炯培
阎杰
孙靖
梁锐
Original Assignee
上海美控智慧建筑有限公司
广东美的暖通设备有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海美控智慧建筑有限公司, 广东美的暖通设备有限公司 filed Critical 上海美控智慧建筑有限公司
Priority to US18/564,029 priority Critical patent/US20240288191A1/en
Priority to EP22874212.8A priority patent/EP4328506A4/en
Publication of WO2023050814A1 publication Critical patent/WO2023050814A1/zh

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
    • F24F11/50—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
    • F24F11/30—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
    • F24F11/58—Remote control using Internet communication
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • 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
    • F24F11/62—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
    • F24F11/65—Electronic processing for selecting an operating mode
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F24F2110/12—Temperature of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/20—Humidity
    • F24F2110/22—Humidity of the outside air
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2221/00—Details or features not otherwise provided for
    • F24F2221/54—Heating and cooling, simultaneously or alternatively

Definitions

  • the present application relates to the technical field of air conditioners, in particular to an air conditioner control method, device and electronic equipment.
  • the start and stop of the air conditioner is generally completed manually by the property personnel, that is, the property personnel manually turn on the air conditioner before the building employees go to work, and manually turn off the air conditioner after work. This completely relies on manual control. Sometimes employees complain and complain because they fail to turn on the air conditioner in time, or they forget to turn off the air conditioner, resulting in waste of energy consumption.
  • Building Management System also known as building automatic control system
  • the above-mentioned control method of starting and stopping the air conditioner manually by unemployed people has been partially replaced by the schedule control of BMS, that is, through The start and stop time of the air conditioner is set in the BMS so that the air conditioner will automatically turn on or off according to the set start and stop time.
  • schedule control method still has certain defects, the start-stop time of the air conditioner in the schedule is set by manual experience, if open the air conditioner too early not only cause indoor temperature too low, but also produce the waste of energy consumption; Turning on the air-conditioning system can cause the indoor temperature to be too high during working hours.
  • the above two air conditioner control methods cannot adjust the start and stop time according to the change of the actual load of the building, and there are problems of high energy consumption, energy waste, and poor thermal comfort of the air conditioner.
  • the present application provides an air conditioner control method, device and electronic equipment, so as to save energy consumption of the air conditioner without causing waste of energy, and has better thermal adaptability.
  • the air conditioner control method may include: acquiring temperature data and humidity data of the air conditioner; wherein the temperature data includes indoor temperature and outdoor temperature, Humidity data includes indoor humidity and outdoor humidity; input the model of air conditioner, forecast type of air conditioner, temperature data and humidity data into the forecast model of air conditioner completed in advance, and output the forecast time of air conditioner; among them, the forecast time of air conditioner
  • the mode includes cooling mode and/or heating mode; the prediction type of the air conditioner includes the start time prediction and/or the shutdown time prediction; the parameters of the air conditioner prediction model include: indoor set temperature, indoor set temperature threshold, indoor set humidity and indoor setting humidity threshold; the predicted time includes predicted startup time and/or predicted shutdown time; based on the predicted time, the start or shutdown of the air conditioner is controlled.
  • the above-mentioned step of obtaining the temperature data and humidity data of the air conditioner may include: obtaining the first current moment; if the first current moment reaches the preset judgment time, obtaining the temperature data of the air conditioner and humidity data.
  • the air conditioner control method may further include: if the predicted time is greater than the preset upper limit of the start-up time or the turn-off time, the upper limit value As the predicted time; if the predicted time is less than the lower limit of the startup time or shutdown time, the lower limit is used as the predicted time.
  • the above-mentioned step of controlling the startup or shutdown of the air conditioner based on the predicted time may include: obtaining the second current time; calculating the time difference between the second current time and the preset on-duty or off-duty time, If the time difference is less than or equal to the predicted power-on time or the predicted power-off time, the air conditioner is controlled to start or shut down.
  • the time difference ⁇ t between the second current time and the working time is calculated in real time, and compared with the predicted start-up time ⁇ t open : if ⁇ t> ⁇ t open , then continue to wait; if ⁇ t ⁇ t open , send a power-on command to the air conditioner, and the air conditioner starts to run.
  • the air conditioner after obtaining the predicted shutdown time ⁇ t close , calculate the time difference ⁇ t between the second current time and the off-duty time in real time, and compare it with the predicted shutdown time ⁇ t close : if ⁇ t> ⁇ t close , then continue to wait; if ⁇ t ⁇ t close , send a shutdown command to the air conditioner, and the air conditioner stops running.
  • the air conditioner control method may further include: determining the temperature reaching time of the air conditioner; adjusting the parameters of the prediction model based on the temperature reaching time .
  • the above-mentioned step of determining the temperature-up time of the air conditioner may include: if the prediction type of the air conditioner is start-up time prediction, determine the start-up time of the air conditioner; The sum of the fixed temperature and the indoor set temperature threshold is used to obtain the third current moment; the difference between the third current moment and the start-up time is used as the temperature-up time; or, if the air conditioner’s prediction type is shutdown time prediction, determine the shutdown time of the air conditioner Time; if the indoor temperature is less than or equal to the sum of the indoor set temperature and the indoor set temperature threshold, obtain the fourth current moment; use the difference between the fourth current moment and the shutdown time as the temperature-up time.
  • the above-mentioned step of adjusting the parameters of the forecast model based on the warm-up time may include: if the forecast type of the air conditioner is start-up time prediction, the first step of determining the difference between the warm-up time and the predicted start-up time Absolute value; if the first absolute value is greater than the preset first error threshold, adjust the parameters of the prediction model; or, if the prediction type of the air conditioner is shutdown time prediction, determine the second absolute value of the difference between the warm-up time and the predicted shutdown time value; if the second absolute value is greater than the preset second error threshold, adjust the parameters of the prediction model.
  • the above-mentioned step of adjusting the parameters of the prediction model based on the temperature reaching time may include: acquiring historical temperature data and historical humidity data of the air conditioner within a preset time range; The humidity data adjusts the parameters of the prediction model.
  • the controller of the air conditioner may be set in the air conditioner, or the controller of the air conditioner may be set in a server communicatively connected with the air conditioner.
  • an air conditioner control device which is applied to the controller of the air conditioner, and the device may include: a data acquisition module configured to acquire temperature data and humidity data of the air conditioner; wherein, the temperature The data includes indoor temperature and outdoor temperature, and the humidity data includes indoor humidity and outdoor humidity; the time prediction module is configured to input the model of the air conditioner, the prediction type of the air conditioner, temperature data and humidity data into the air conditioner that has been trained in advance In the forecast model, the forecast time of the air conditioner is output; wherein, the mode of the air conditioner includes cooling mode and/or heating mode; the forecast type of the air conditioner includes start-up time prediction and/or shutdown time prediction; the parameters of the air-conditioner forecast model include : indoor set temperature, indoor set temperature threshold, indoor set humidity and indoor set humidity threshold; predicted time includes predicted power-on time and/or predicted power-off time; air conditioner control module configured to control the air conditioner based on the predicted time device startup or shutdown.
  • Some other embodiments of the present application also provide an electronic device, the electronic device may include a processor and a memory, the memory may store computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions In order to realize the above air conditioner control method.
  • An air conditioner control method, device and electronic equipment provided in the embodiments of the present application, input the air conditioner mode, forecast type, temperature data and humidity data into the pre-trained air conditioner forecast model, and output the air conditioner forecast time , and control the start or stop of the air conditioner based on the predicted time.
  • This method predicts the predicted startup time and predicted shutdown time of the air conditioner through the prediction model, which can save the energy consumption of the air conditioner without causing energy waste, and has good thermal adaptability.
  • FIG. 1 is a flow chart of an air conditioner control method provided in an embodiment of the present application
  • FIG. 2 is a flow chart of another air conditioner control method provided in the embodiment of the present application.
  • FIG. 3 is a schematic diagram of an air conditioner control method for predicting start-up time provided by an embodiment of the present application
  • FIG. 4 is a schematic diagram of an air conditioner control method for shutting down time prediction provided by an embodiment of the present application
  • FIG. 5 is a schematic diagram of a power-on time curve provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an air conditioner control device provided in an embodiment of the present application.
  • Fig. 7 is a schematic structural diagram of another air conditioner control device provided in the embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the control methods of air conditioners in public buildings include: manual operation by property personnel and setting schedules to control the start and stop of air conditioners. Both of the above two methods cannot adjust the start and stop time according to changes in the actual load of the building.
  • the air conditioner control method, device and electronic equipment provided in the embodiments of the present application can be applied to the start-stop controller of the air conditioner with self-learning function, and can be calculated according to the indoor and outdoor temperature, humidity and other parameters in recent days.
  • the cooling or heating temperature change rate of the air conditioner and predict the opening or closing time of the air conditioner in advance according to the temperature change rate, so as to achieve the effect of automatically optimizing the start and stop of the air conditioner without human intervention.
  • An embodiment of the present application provides a kind of air conditioner control method, is applied to the controller of air conditioner, referring to the flowchart of a kind of air conditioner control method shown in Fig. 1, this air conditioner control method may comprise the following steps:
  • Step S102 acquiring temperature data and humidity data of the air conditioner.
  • the temperature data in this embodiment may include indoor temperature and outdoor temperature
  • the humidity data may include indoor humidity and outdoor humidity.
  • the air conditioner in this embodiment may be a central air conditioner, or other air conditioners except the central air conditioner.
  • the central air conditioner is taken as an example, and details will not be described hereafter.
  • the controller of the air conditioner may be set in the air conditioner, or may be set in a server communicatively connected with the air conditioner, wherein the server may be a cloud server or a physical server, which is not limited in this embodiment.
  • the main function of the air conditioner is to ensure the temperature of the indoor environment by dealing with the cooling load or heating load in the room.
  • the main parameters affecting the cooling or heating rate of the air conditioner are indoor temperature, indoor humidity, outdoor temperature, outdoor humidity, human flow density and equipment emission. heat. Since the flow density of people and the heating value of equipment are parameters that are difficult to obtain, and for commercial office buildings, it can be considered that the flow density of people and the heating value of equipment are a fixed parameter before going to work or leaving get off work every day. Therefore, the only parameters that really affect the cooling or heating rate of the air conditioner are indoor temperature, indoor humidity, outdoor temperature and outdoor humidity. Wherein, the outdoor temperature and outdoor humidity can be directly obtained from the database of the server, and the indoor temperature and indoor humidity can be collected by a temperature sensor and a humidity sensor provided by the air conditioner itself.
  • Step S104 input the model of the air conditioner, the predicted type of the air conditioner, the temperature data and the humidity data into the pre-trained prediction model of the air conditioner, and output the predicted time of the air conditioner.
  • the mode of the air conditioner in this embodiment may include cooling mode and/or heating mode;
  • the prediction type of the air conditioner may include startup time prediction and/or shutdown time prediction;
  • the parameters of the air conditioner prediction model may include: fixed temperature, indoor set temperature threshold, indoor set humidity and indoor set humidity threshold;
  • the predicted time may include predicted power-on time and/or predicted power-off time.
  • the startup time and shutdown time of the air conditioner can be predicted, which are respectively called predicted startup time and predicted shutdown time.
  • the predicted power-on time may be output, and if the air conditioner is in the power-off time prediction, the predicted power-off time may be output.
  • the values of the parameters of the air conditioner prediction model may be the same or different, which is not limited here.
  • Step S106 controlling the start or stop of the air conditioner based on the predicted time.
  • the controller determines the predicted time, it can control the start or stop of the air conditioner according to the predicted time.
  • the predicted time output in this embodiment may be a specific moment or a duration.
  • the air conditioner can be controlled to start at 8:00; if the controller determines that the predicted shutdown time is 18:00, the air conditioner can be controlled to be turned off at 18:00.
  • the controller determines that the predicted start-up time is 1 hour, it can control the air conditioner to start at 8:00 according to the employee's work time and the predicted start-up time after 9:00 when the employee goes to work.
  • An air conditioner control method provided in an embodiment of the present application includes inputting the mode, forecast type, temperature data and humidity data of the air conditioner into the pre-trained forecast model of the air conditioner, outputting the forecast time of the air conditioner, and based on the forecast time Control the start or stop of the air conditioner. This method predicts the predicted startup time and predicted shutdown time of the air conditioner through the prediction model, which can save the energy consumption of the air conditioner without causing energy waste, and has good thermal adaptability.
  • Another embodiment of the present application provides another air conditioner control method, which is implemented on the basis of the above-mentioned embodiments, as shown in Figure 2, the flow chart of another air conditioner control method, the air conditioner in this embodiment
  • the controller control method may include the steps of:
  • Step S202 acquiring temperature data and humidity data of the air conditioner.
  • the temperature data and humidity data of the air conditioner can be obtained after the time axis reaches the preset judgment time, for example: the first current moment is obtained; if the first current moment reaches the preset judgment time, Obtain the temperature data and humidity data of the air conditioner.
  • Step S204 input the model of the air conditioner, the predicted type of the air conditioner, temperature data and humidity data into the pre-trained prediction model of the air conditioner, and output the predicted time of the air conditioner.
  • ⁇ t open f 1 (T in , RH in , T out , RH out , T set , RH set , T comp , RH comp ).
  • ⁇ t open is the predicted start-up time
  • ⁇ t open is the duration rather than the time.
  • T in is the indoor temperature
  • RH in is the indoor humidity
  • T out is the outdoor temperature
  • RH out is the outdoor humidity
  • T set is the indoor set temperature
  • RH set is the indoor set humidity
  • T comp is the indoor set temperature threshold
  • RH comp sets the humidity threshold for the room.
  • the cooling mode can be set to 1°C, and the heating mode can be set to -1°C, and the indoor set temperature T set reflects the deviation tolerance of personnel to the indoor temperature.
  • the indoor set humidity threshold RH comp the cooling mode can be set to 10%, and the heating mode can be set to -10%.
  • the indoor set humidity threshold RH comp reflects the deviation tolerance of personnel to indoor humidity.
  • the multivariate linear equation form that is, if the forecast type of the air conditioner is start-up time prediction, the predicted start-up time of the air conditioner is determined by the following formula:
  • ⁇ t open c 1 ⁇ (T in -T set -T comp )+c 2 ⁇ (T out -T set -T comp )+c 3 ⁇ (RH in -RH set -RH comp )+c 4 (RH out -RH set -RH comp );
  • c 1 -c 4 in the above formula are preset coefficients for predicting the start-up time, which can be preset in the controller.
  • the early shutdown of the air conditioner is the exact opposite of the early start-up process.
  • the air conditioner is turned off in advance, and the indoor temperature is maintained until the off-duty time by using the building's cold storage or heat storage, thereby saving the energy consumption of the air conditioner.
  • the early shutdown time of the air conditioner can be expressed by the following equation:
  • ⁇ t close f 2 (T in , RH in , T out , RH out , T set , RH set , T comp , RH comp ).
  • ⁇ t close is the predicted shutdown time of the air conditioner in advance
  • ⁇ t close is the duration rather than the time.
  • Other parameters are the same as above.
  • the above function is also expanded into a multivariate linear equation form: that is, if the forecast type of the air conditioner is shutdown time prediction, the predicted shutdown time of the air conditioner is determined by the following formula:
  • ⁇ t close d 1 ⁇ (T in -T set -T comp )+d 2 ⁇ (T out -T set -T comp )+d 3 ⁇ (RH in -RH set -RH comp )+d 4 ⁇ (RH out -RH set -RH comp );
  • ⁇ t close is the predicted shutdown time
  • d 1 -d 4 are preset shutdown time prediction coefficients, which can also be preset in the controller.
  • the controller can collect and record the current indoor temperature and humidity and outdoor temperature and humidity, and calculate the early start-up time ⁇ t open according to the early start-up time prediction equation.
  • the advance start time there is an upper limit and a lower limit for the advance start time, that is, it cannot be started too early or too late. Therefore, if the predicted time is greater than the preset upper limit of the start time or shutdown time, the upper limit value is used as the predicted time; If the predicted time is less than the lower limit value of the power-on time or the power-off time, use the lower limit value as the predicted time.
  • the predicted time Take the predicted time as the duration as an example, and take power-on as an example. If the predicted power-on time is 1 hour, however, the lower limit of the power-on time is 30 minutes, and the predicted time is less than the lower limit of the power-on time. You can set the lower limit to 30 minutes as the forecast time.
  • the situation of shutdown is similar to that of startup.
  • the calculation of early shutdown time is carried out.
  • Step S206 controlling the start or stop of the air conditioner based on the predicted time.
  • the controller when the controller controls the start or stop of the air conditioner, it may first perform the steps of judging whether the air conditioner is turned on, for example: obtain the second current moment; calculate the second 2. The time difference between the current time and the preset on-duty time or off-duty time, if the time difference is less than or equal to the predicted start-up time or predicted power-off time, the air conditioner is controlled to start or shut down.
  • the controller calculates the time difference ⁇ t between the second current time t and the on-duty time t on in real time, and compares it with the predicted start-up time ⁇ t open : if ⁇ t> ⁇ t open , it means that the current time has not yet When the start-up time is reached, the controller continues to wait; if ⁇ t ⁇ t open , it means that the current time has reached the start-up time, the controller sends a start-up command to the air conditioner, and the air conditioner starts to run.
  • the controller calculates the time difference ⁇ t between the second current time t and the off-duty time t off in real time, and compares it with ⁇ t close : if ⁇ t> ⁇ t close , it means that the current time has not yet closed When the shutdown time is reached, the controller continues to wait; if ⁇ t ⁇ t close , it means that the current time has reached the startup time, the controller sends a shutdown command to the air conditioner, and the air conditioner stops running.
  • Step S208 determining the warm-up time of the air conditioner.
  • the above steps illustrate how the controller controls the start and stop of the air conditioner.
  • the prediction model in the air conditioner can learn by itself and its parameters can be adjusted. That is, the coefficients in the air conditioner start-up time prediction equation and shutdown time prediction equation are not fixed, as shown in Figure 3 and Figure 4, it is necessary to judge whether the parameters need to be adjusted, and then adjust the parameters.
  • the temperature reaching time can be determined through the following steps: the steps of determining the temperature reaching time of the air conditioner include:
  • the prediction type of the air conditioner is start-up time prediction, determine the start-up time of the air conditioner; if the indoor temperature is greater than or equal to the sum of the indoor set temperature and the indoor set temperature threshold, obtain the third current moment; compare the third current moment with the start-up time The difference in time was taken as the reaching temperature time.
  • the up-to-temperature time calculation is shown in Figure 3.
  • the prediction type of the air conditioner is shutdown time prediction
  • determine the shutdown time of the air conditioner if the indoor temperature is less than or equal to the sum of the indoor set temperature and the indoor set temperature threshold, obtain the fourth current moment; compare the fourth current moment with the shutdown time The difference in time was taken as the reaching temperature time.
  • the up-to-temperature time calculation is shown in Figure 4.
  • Step S210 adjusting the parameters of the prediction model based on the warm-up time.
  • the air conditioner determines the first difference between the temperature reaching time and the predicted startup time. An absolute value; if the first absolute value is greater than the preset first error threshold, adjust the parameters of the prediction model; or, if the prediction type of the air conditioner is shutdown time prediction, determine the second difference between the warm-up time and the predicted shutdown time Absolute value; if the second absolute value is greater than the preset second error threshold, adjust the parameters of the prediction model.
  • the first error threshold and the second error threshold may be the same or different, which is not limited in this embodiment.
  • the coefficients of the prediction equation are updated by self-learning. Compare the error between the temperature-reaching time ⁇ t r and the predicted start-up time ⁇ t open : if
  • the coefficients of the prediction equation are updated by self-learning. Compare the error between the temperature-reaching time ⁇ t r and the predicted shutdown time ⁇ t close : if
  • adjustments can be made according to the historical temperature data and historical humidity data of the air conditioner, for example: obtaining the historical temperature data and historical humidity data of the air conditioner within a preset time range; based on the historical temperature Data and historical humidity data to adjust the parameters of the forecast model.
  • the parameters of the prediction model in the controller are not fixed, because the building load will change with the change of outdoor meteorological parameters, so the parameters of the prediction model should also be able to self-learn and adjust over time, so as to adapt to the change of load, Guaranteed the accuracy of forecast time.
  • the controller needs to record the indoor temperature and humidity and outdoor temperature and humidity values of at least 4 adjacent days, and perform adaptive update on the 4 coefficients every day.
  • the coefficients of the predictive start-up time equation are updated as follows:
  • ⁇ tr is the actual temperature-reaching time of the air conditioner (that is, the actual time taken for the indoor temperature to reach T set + T comp ), the subscript k represents today, k-1 represents yesterday, k-2 represents the day before yesterday, and k-3 It represents the day before yesterday.
  • the controller realizes the self-learning update of the coefficients of the prediction equation by collecting the indoor temperature and humidity, the outdoor temperature and humidity values and the temperature-up time of the air conditioner for 4 consecutive days.
  • the controller of the above-mentioned air conditioner may be set in the air conditioner, or the controller of the air conditioner may be set in a server communicatively connected with the air conditioner.
  • the controller of the air conditioner can be composed of a time module, a signal acquisition module, a storage module, and a prediction module.
  • the time module can be used to collect the current time. In order to ensure the accuracy of the time, the time is automatically synchronized every time it is connected to the host computer .
  • the signal acquisition module can be used to collect indoor temperature and humidity, and indoor temperature and humidity parameters.
  • the storage module can be used to record the indoor temperature and humidity, indoor temperature and humidity parameters at the preset judgment time of adjacent days, and some preset parameters of the controller, such as: cooling target temperature, heating target temperature, set temperature threshold, work Time, off-duty time, setting judgment time, earliest start time, latest start time, time error threshold, etc.
  • the prediction module can be used to calculate and predict the start-up or shutdown time according to the pre-written start-stop time prediction equation according to the temperature and humidity parameters passed in by the acquisition module.
  • the results of the air conditioner control method provided in this embodiment can be referred to a schematic diagram of a start-up time curve shown in FIG.
  • Curve 1 is the actual pre-cooling time
  • curve 2 is the predicted pre-cooling time. It can be seen from Figure 5 that through self-learning to optimize the coefficients of the prediction equation, the error between the predicted pre-cooling time and the actual pre-cooling time is close, indicating that the air conditioner The air conditioner control method can effectively ensure the indoor temperature while reducing the energy consumption of the combined air conditioner as much as possible.
  • the embodiment of this application proposes a method for predicting the optimal start and stop time of the air conditioner in different modes based on the indoor and outdoor temperature, humidity, and room setting temperature of adjacent days, so that the indoor temperature at work or after work It just does not exceed the set threshold range, and at the same time, it can save the energy consumption of the air conditioner to the greatest extent.
  • the prediction model of the air conditioner in this method will adjust the parameters by self-learning as the building load changes, so as to ensure the accuracy of the prediction time.
  • the embodiment of the present application also proposes a controller with a built-in air conditioner start-stop time prediction function.
  • the controller is composed of a time module, a signal acquisition module, a storage module, and a prediction module.
  • the local optimized start-stop control of the air conditioner can be realized.
  • the controller may not be installed in the air conditioner, and the above-mentioned functions can be realized by writing an optimized control algorithm through a host computer or a cloud platform.
  • the above-mentioned method provided in the embodiment of the present application can predict the time of starting or shutting down the air conditioner in advance in the cooling/heating scenario according to the indoor and outdoor air temperature and humidity parameters, so that the indoor temperature just reaches the set temperature range during the working hours, Turning off the air conditioner in advance before leaving work will not cause large fluctuations in temperature, thereby minimizing the energy consumption of the air conditioner.
  • the prediction model will self-learn and adjust parameters as the building load changes to ensure the accuracy of the prediction time.
  • the prediction calculation is completely completed on the local controller, without the help of a host computer or cloud platform, which is convenient for operation and use, and saves investment costs.
  • FIG. Devices can include:
  • the data acquisition module 61 can be configured to obtain temperature data and humidity data of the air conditioner; wherein, the temperature data can include indoor temperature and outdoor temperature, and the humidity data can include indoor humidity and outdoor humidity;
  • the time prediction module 62 can be configured to input the model of the air conditioner, the forecast type of the air conditioner, temperature data and humidity data into the forecast model of the air conditioner completed in advance, and output the forecast time of the air conditioner; wherein, the air conditioner
  • the mode of the air conditioner may include cooling mode and/or heating mode;
  • the prediction type of the air conditioner may include start-up time prediction and/or shutdown time prediction;
  • the parameters of the air conditioner prediction model may include: indoor set temperature, indoor set temperature threshold, The indoor set humidity and the indoor set humidity threshold;
  • the predicted time includes predicted power-on time and/or predicted power-off time;
  • the air conditioner control module 63 may be configured to control the start or stop of the air conditioner based on the predicted time.
  • An air conditioner control device provided in an embodiment of the present application can input the air conditioner mode, forecast type, temperature data, and humidity data into the pre-trained air conditioner forecast model, output the forecast time of the air conditioner, and based on the forecast The time controls the start or stop of the air conditioner.
  • This method predicts the predicted startup time and predicted shutdown time of the air conditioner through the prediction model, which can save the energy consumption of the air conditioner without causing energy waste, and has good thermal adaptability.
  • the above-mentioned data acquisition module may be configured to acquire the first current moment; if the first present moment reaches the preset judgment time, acquire the temperature data and humidity data of the air conditioner.
  • the above-mentioned time prediction module can also be configured to use the upper limit value as the predicted time if the predicted time is greater than the preset upper limit value of the startup time or shutdown time; if the predicted time is smaller than the lower limit value of the startup time or shutdown time, Let the lower limit value be the prediction time.
  • the above-mentioned air conditioner control module can be configured to obtain the second current time; calculate the time difference between the second current time and the preset on-duty or off-duty time, and if the time difference is less than or equal to the predicted start-up time or predicted power-off time, control the air conditioner On or off.
  • the air conditioner control device may also include: a model update module 64, which may be connected to the air conditioner control module 63, and the model update module 64 may be configured to determine The temperature reaching time of the air conditioner; adjust the parameters of the prediction model based on the temperature reaching time.
  • a model update module 64 which may be connected to the air conditioner control module 63, and the model update module 64 may be configured to determine The temperature reaching time of the air conditioner; adjust the parameters of the prediction model based on the temperature reaching time.
  • the above-mentioned model update module can be configured to determine the start-up time of the air conditioner if the prediction type of the air conditioner is start-up time prediction; if the indoor temperature is greater than or equal to the sum of the indoor set temperature and the indoor set temperature threshold, obtain the third The current moment; take the difference between the third current moment and the start-up time as the temperature-reaching time; or, if the prediction type of the air conditioner is shutdown time prediction, determine the shutdown time of the air conditioner; if the indoor temperature is less than or equal to the indoor set temperature and the indoor Set the sum of temperature thresholds to obtain the fourth current moment; use the difference between the fourth current moment and the shutdown time as the temperature-up time.
  • the above-mentioned model update module can be configured to determine the first absolute value of the difference between the warm-up time and the predicted start-up time if the prediction type of the air conditioner is start-up time prediction; if the first absolute value is greater than the preset first error threshold , adjust the parameters of the prediction model; or, if the prediction type of the air conditioner is shutdown time prediction, determine the second absolute value of the difference between the warm-up time and the predicted shutdown time; if the second absolute value is greater than the preset second error threshold, Adjust the parameters of the predictive model.
  • the above-mentioned model update module can be configured to obtain historical temperature data and historical humidity data of the air conditioner within a preset time range; and adjust parameters of the prediction model based on the historical temperature data and historical humidity data.
  • the controller of the air conditioner may be set in the air conditioner, or the controller of the air conditioner may be set in a server communicatively connected with the air conditioner.
  • the electronic device may include a memory 100 and a processor 101, wherein, The memory 100 may be configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor 101 to implement the above air conditioner control method.
  • the electronic device shown in FIG. 8 may further include a bus 102 and a communication interface 103 , and the processor 101 , the communication interface 103 and the memory 100 may be connected through the bus 102 .
  • the memory 100 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • RAM Random Access Memory
  • non-volatile memory such as at least one disk memory.
  • the communication connection between the system network element and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the Internet, wide area network, local network, metropolitan area network, etc. can be used.
  • the bus 102 may be an ISA bus, a PCI bus, or an EISA bus, etc.
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one double-headed arrow is used in FIG. 8 , but it does not mean that there is only one bus or one type of bus.
  • the processor 101 may be an integrated circuit chip with signal processing capability.
  • each step of the above method can be completed by an integrated logic circuit of hardware in the processor 101 or an instruction in the form of software.
  • processor 101 can be general-purpose processor, comprises central processing unit (Central Processing Unit, be called for short CPU), network processor (Network Processor, be called for short NP) etc.; Can also be Digital Signal Processor (Digital Signal Processor, be called for short DSP) ), Application Specific Integrated Circuit (ASIC for short), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.
  • CPU central processing unit
  • Network Processor Network Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the steps of the method disclosed in the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • the storage medium may be located in the memory 100, and the processor 101 may read information in the memory 100, and complete the steps of the method in the foregoing embodiments in combination with its hardware.
  • the embodiment of the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium can store computer-executable instructions. When the computer-executable instructions are invoked and executed by a processor, the computer-executable instructions can cause processing
  • the above air conditioner control method can be realized by the air conditioner, and the specific implementation can refer to the method embodiment, which will not be repeated here.
  • the computer program product of the air conditioner control method, device, and electronic equipment provided in the embodiments of the present application may include a computer-readable storage medium storing program codes, and the instructions included in the program codes may be used to execute the methods in the preceding method embodiments, For specific implementation, reference may be made to the method embodiments, which will not be repeated here.
  • connection should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrally connected; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components.
  • installation should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection , or integrally connected; it may be mechanically connected or electrically connected; it may be directly connected or indirectly connected through an intermediary, and it may be the internal communication of two components.
  • the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .
  • the present application provides an air conditioner control method, device and electronic equipment.
  • the method is applied to a controller of an air conditioner, and the method includes: obtaining temperature data and humidity data of the air conditioner; inputting the mode of the air conditioner, the prediction type of the air conditioner, the temperature data and the humidity data into the pre-trained prediction of the air conditioner
  • the model the predicted time of the air conditioner is output; the start or close of the air conditioner is controlled based on the predicted time.
  • the model, forecast type, temperature data and humidity data of the air conditioner are input into the pre-trained forecast model of the air conditioner, the forecast time of the air conditioner is output, and the start or shutdown of the air conditioner is controlled based on the forecast time.
  • This method predicts the predicted startup time and predicted shutdown time of the air conditioner through the prediction model, which can save the energy consumption of the air conditioner without causing energy waste, and has good thermal adaptability.
  • the air conditioner control method, device and electronic equipment of the present application are reproducible and can be applied in various industrial applications.
  • the air conditioner control method of the present application can be applied to the field of air conditioners.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

本申请提供了一种空调器控制方法、装置和电子设备。其中，该方法应用于空调器的控制器，该方法包括：获取空调器的温度数据和湿度数据；将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间；基于预测时间控制空调器的启动或者关闭。该方式中，将空调器的模式、预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间，并基于预测时间控制空调器的启动或者关闭。该方式通过预测模型预测空调器的预测开机时间和预测关机时间，可以节约空调器的能耗，不会造成能源的浪费，热适应性较好。

Description

空调器控制方法、装置和电子设备
相关申请的交叉引用
本申请要求于2021年9月30日提交中国国家知识产权局的申请号为202111163463.6、名称为“空调器控制方法、装置和电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及空调器技术领域，尤其是涉及一种空调器控制方法、装置和电子设备。
背景技术
在商用场景中，空调器的启停一般是通过物业人员手动操作完成的，即物业人员在楼宇的员工上班前手动打开空调器，并在下班后手动关闭空调器，这种完全依赖人工的控制方式有时会因为未能及时打开空调器遭到员工的抱怨投诉，或者忘记关闭空器调造成能耗的浪费。
随着楼宇管理系统(Building Management System，BMS，也称为楼宇自动控制系统)的推广应用，上述由无业人员手动空调器启停的控制方式已经部分被BMS的时间表控制所替代，即通过在BMS中设定好空调器的启停时间让空调器按照设定的启停时间自动开机或关机。但上述时间表控制方法仍然存在一定缺陷，时间表中空调器的启停时间是凭人工经验设定的，如果过早开启空调器不仅造成室内温度过低，而且产生能耗浪费；而过晚开启空调系统则会导致上班时间室内温度过高。
因此，上述两种空调器的控制方法，无法根据建筑实际负荷的变化调整启停时间，存在空调器的能耗大、能源浪费、热舒适性差的问题。
发明内容
有鉴于此，本申请提供了一种空调器控制方法、装置和电子设备，以节约空调器的能耗，不会造成能源的浪费，热适应性较好。
本申请一些实施例提供了一种空调器控制方法，应用于空调器的控制器，空调器控制方法可以包括：获取空调器的温度数据和湿度数据；其中，温度数据包括室内温度和室外温度，湿度数据包括室内湿度和室外湿度；将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间；其中，空调器的模式包括制冷模式和/或制热模式；空调器的预测类型包括开机时间预测和/或关机时间预测；空调器预测模型的参数包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；预测时间包括预测开机时间和/或预测关机时间；基于预测时间控制空调器的启动或者关闭。
在本申请可选的实施例中，上述获取空调器的温度数据和湿度数据的步骤，可以包括：获取第一当前时刻；如果第一当前时刻达到预设的判断时间，获取空调器的温度数据和湿度数据。
在本申请可选的实施例中，如果空调器的预测类型为开机时间预测，可以通过下述算式确定空调器的预测开机时间：Δt open＝c 1·(T in-T set-T comp)+c 2·(T out-T set-T comp)+c 3·(RH in-RH set-RH comp)+c 4(RH out-RH set-RH comp)；其中，△t open为预测开机时间，c 1-c 4为预先设定的开机时间预测的系数，T in为室内温度，RH in为室内湿度，T out为室外温度，RH out为室外湿度，T set为室内设定温度，RH set为室内设定湿度，T comp为室内设定温度阈值，RH comp为室内设定湿度阈值；如果空调器的预测类型为关机时间预测，可以通过下述算式确定空调器的预测关机时间：Δt close＝d 1·(T in-T set-T comp)+d 2·(T out-T set-T comp)+d 3·(RH in-RH set-RH comp)+d 4·(RH out-RH set-RH comp)；其中，△t close为预测关机时间，d 1-d 4为预先设定的关机时间预测的系数。
在本申请可选的实施例中，上述输出空调器的预测时间的步骤之后，空调器控制方法还可以包括：如果预测时间大于预设的开机时间或关机时间的上限值，将上限值作为预测时间；如果预测时间小于开机时间或关机时间的下限值，将下限值作为预测时间。
在本申请可选的实施例中，上述基于预测时间控制空调器的启动或者关闭的步骤，可以包括：获取第二当前时刻；计算第二当前时刻与预设的上班时刻或下班时刻的时间差，如果时间差小于或等于预测开机时间或预测关机时间，控制空调器启动或者关闭。
在本申请可选的实施例中，获取预测开机时间△t open后，实时计算第二当前时刻与上班时刻的时间差△t，并与预测开机时间△t open比较：若△t>△t open，则继续等待；若△t≤△t open，则向空调器发出开机指令，空调器开始运行。
在本申请可选的实施例中，获取预测关机时间△t close后，实时计算第二当前时刻与下班时刻的时间差△t，并与预测关机时间△t close比较：若△t>△t close，则继续等待；若△t≤△t close，则向空调器发出关机指令，空调器结束运行。
在本申请可选的实施例中，上述基于预测时间控制空调器的启动或者关闭的步骤之后，空调器控制方法还可以包括：确定空调器的达温时间；基于达温时间调整预测模型的参数。
在本申请可选的实施例中，上述确定空调器的达温时间的步骤，可以包括：如果空调器的预测类型为开机时间预测，确定空调器的开机时间；如果室内温度大于或等于室内设定温度与室内设定温度阈值的和，获取第三当前时刻；将第三当前时刻与开机时间的差作为达温时间；或者，如果空调器的预测类型为关机时间预测，确定空调器的关机时间；如果室内温度小于或等于室内设定温度与室内设定温度阈值的和，获取第四当前时刻；将第四当前时刻与关机时间的差作为达温时间。
在本申请可选的实施例中，上述基于达温时间调整预测模型的参数的步骤，可以包括：如果空调器的预测类型为开机时间预测，确定达温时间与预测开机时间的差的第一绝对值；如果第一绝对值大于预设的第一误差阈值，调整预测模型的参数；或者，如果空调器的预测类型为关机时间预测，确定达温时间与预测关机时间的差的第二绝对值；如果第二绝对值大于预设的第二误差阈值，调整预测模型的参数。
在本申请可选的实施例中，上述基于达温时间调整预测模型的参数的步骤，可以包括：获取预设时间范围内的空调器的历史温度数据和历史湿度数据；基于历史温度数据和历史湿度数据调整预测模型的参数。
在本申请可选的实施例中，上述空调器的控制器可以设置于空调器中，或者，空调器的控制器可以设置于与空调器通信连接的服务器中。
本申请另一些实施例还提供了一种空调器控制装置，应用于空调器的控制器，该装置可以包括：数据获取模块，配置成用于获取空调器的温度数据和湿度数据；其中，温度数据包括室内温度和室外温度，湿度数据包括室内湿度和室外湿度；时间预测模块，配置成用于将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间；其中，空调器的模式包括制冷模式和/或制热模式；空调器的预测类型包括开机时间预测和/或关机时间预测；空调器预测模型的参数包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；预测时间包括预测开机时间和/或预测关机时间；空调器控制模块，配置成用于基于预测时间控制空调器的启动或者关闭。
本申请又一些实施例还提供了一种电子设备，该电子设备可以包括处理器和存储器，该存储器可以存储有能够被该处理器执行的计算机可执行指令，该处理器执行该计算机可执行指令以实现上述空调器控制方法。
本申请再一些实施例还提供了一种计算机可读存储介质，该计算机可读存储介质可以存储有计算机可执行指令，该计算机可执行指令在被处理器调用和执行时，计算机可执行指令促使处理器实现上述空调器控制方法。
本申请实施例可以带来至少以下有益效果：
本申请实施例提供的一种空调器控制方法、装置和电子设备，将空调器的模式、预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间，并基于预测时间控制空调器的启动或者关闭。该方式通过预测模型预测空调器的预测开机时间和预测关机时间，可以节约空调器的能耗，不会造成能源的浪费，热适应性较好。
本申请的其他特征和优点将在随后的说明书中阐述，或者，部分特征和优点可以从说 明书推知或毫无疑义地确定，或者通过实施本申请的上述技术即可得知。
为使本申请的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本申请具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种空调器控制方法的流程图；
图2为本申请实施例提供的另一种空调器控制方法的流程图；
图3为本申请实施例提供的一种开机时间预测的空调器控制方法的示意图；
图4为本申请实施例提供的一种关机时间预测的空调器控制方法的示意图；
图5为本申请实施例提供的一种开机时间的曲线示意图；
图6为本申请实施例提供的一种空调器控制装置的结构示意图；
图7为本申请实施例提供的另一种空调器控制装置的结构示意图；
图8为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
目前，公共建筑中空调器的控制方法包括：物业人员手动操作和设置时间表两种控制空调器启停的方式，上述两种方式均无法根据建筑实际负荷的变化调整启停时间，存在空调器的能耗大、能源浪费、热舒适性差的问题。基于此，本申请实施例提供的一种空调器控制方法、装置和电子设备，可以应用于带自学习功能的空调的启停控制器，可以根据最近几天的室内外温度、湿度等参数计算空调器的制冷或制热温度变化率，并根据温度变化率预测空调器的提前开启或关闭的时间，做到不需要人为干预、自动优化空调器启停的效果。
为便于对本实施例进行理解，首先对本申请实施例所公开的一种空调器控制方法进行详细介绍。
本申请一实施例提供了一种空调器控制方法，应用于空调器的控制器，参见图1所示 的一种空调器控制方法的流程图，该空调器控制方法可以包括如下步骤：
步骤S102，获取空调器的温度数据和湿度数据。
其中，本实施例中的温度数据可以包括室内温度和室外温度，湿度数据可以包括室内湿度和室外湿度。本实施例中的空调器可以为中央空调器，也可以为除了中央空调器之外的其他空调器，本实施例中以中央空调器为例，此后不再赘述。空调器的控制器可以设置在空调器中，也可以设置在与空调器通信连接的服务器中，其中，上述服务器可以是云服务器，也可以是物理服务器，本实施例对此不做限定。
空调器的主要功能是通过处理室内的冷负荷或热负荷保证室内环境的温度，影响空调器制冷或制热速率的主要参数为室内温度、室内湿度、室外温度、室外湿度、人流密度及设备发热量。由于人流密度与设备发热量是较难获取的参数，且对于商业办公建筑，可以认为每天上班前或下班前，人流密度和设备发热量是一个固定的参数。因此，真正影响空调器制冷或制热速率的参数只剩下室内温度、室内湿度、室外温度和室外湿度。其中，室外温度和室外湿度可以直接从服务器的数据库中获取，室内温度和室内湿度可以由空调器自身设置的温度传感器和湿度传感器采集。
步骤S104，将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间。
其中，本实施例中的空调器的模式可以包括制冷模式和/或制热模式；空调器的预测类型可以包括开机时间预测和/或关机时间预测；空调器预测模型的参数可以包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；预测时间可以包括预测开机时间和/或预测关机时间。
本实施例可以预测空调器的开机时间和关机时间，分别称为预测开机时间和预测关机时间。其中，如果空调器处于开机时间预测则可以输出预测开机时间，如果空调器处于关机时间预测则可以输出预测关机时间。此外，空调器的模式不同，则空调器预测模型的参数的数值可能相同，也可以不同，这里对此不做限定。
步骤S106，基于预测时间控制空调器的启动或者关闭。
因此，控制器在确定预测时间之后，可以根据预测时间控制空调器的启动或者关闭。本实施例中输出的预测时间可以是具体的时刻，也可以是时长。
例如：如果控制器确定预测开机时间是具体的时刻8点，则可以控制空调器在8点启动；如果控制器确定预测关闭时间为18点，则可以控制空调器在18点关闭。
又例如：如果控制器确定预测开机时间是时长1小时，则可以在预先确定员工上班的时刻9点之后，根据员工上班的时刻和预测开机时间，控制空调器在8点启动。
本申请实施例提供的一种空调器控制方法，将空调器的模式、预测类型、温度数据和 湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间，并基于预测时间控制空调器的启动或者关闭。该方式通过预测模型预测空调器的预测开机时间和预测关机时间，可以节约空调器的能耗，不会造成能源的浪费，热适应性较好。
本申请另一实施例提供了另一种空调器控制方法，该方法在上述实施例的基础上实现，如图2所示的另一种空调器控制方法的流程图，本实施例中的空调器控制方法可以包括如下步骤：
步骤S202，获取空调器的温度数据和湿度数据。
对于预测类型为开机时间预测和关机时间预测的空调器控制方法，可以分别参见图3所示的一种开机时间预测的空调器控制方法的示意图和图4所示的一种关机时间预测的空调器控制方法的示意图。在本实施例中先以图3为例进行解释，后以图4为例进行解释，此后不再赘述。
如图3和图4所示，在时间轴进行到预设判断时间之后可以获取空调器的温度数据和湿度数据，例如：获取第一当前时刻；如果第一当前时刻达到预设的判断时间，获取空调器的温度数据和湿度数据。
如图3所示，控制器中的时间模块可以获取第一当前时刻t，实时比较第一当前时刻t与预设判断时间t 0的大小，如果第一当前时刻t<预设判断时间t 0，则继续等待；如果第一当前时刻＝预设判断时间t 0(即述第一当前时刻达到预设的判断时间)，则触发提前开机控制。
如图4所示，控制器中的时间模块可以获取第一当前时刻t，实时比较第一当前时刻t与预设判断时间t 0的大小，如果第一当前时刻t<预设判断时间t 0，则继续等待；如果第一当前时刻＝预设判断时间t 0(即述第一当前时刻达到预设的判断时间)，则触发提前关机控制。
步骤S204，将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间。
上文已经提到，对于商业办公建筑，可以认为每天上班前或下班前，人流密度和设备发热量是一个固定的参数，真正影响空调器制冷或制热速率的参数只剩下室内温度、室内湿度、室外温度、室外湿度。对于制冷场景，显然室内温度、室外温度越高，空调器所要处理的显热负荷越大，需要的制冷时间也就越长；室内湿度、室外湿度越高，空调器所要处理的潜热负荷越大，需要的制冷时间同样越长。对于制热场景则相反。
因此，空调器预测开机时间可以用下述方程表示：
Δt open＝f 1(T in,RH in,T out,RH out,T set,RH set,T comp,RH comp)。
其中，△t open为预测开机时间，△t open为时长而非时刻。T in为室内温度，RH in为室内湿度，T out为室外温度，RH out为室外湿度，T set为室内设定温度，RH set为室内设定湿度，T comp为室内设定温度阈值，RH comp为室内设定湿度阈值。
这里需要说明的是，对于室内设定温度T set，制冷模式可以设置为1℃，制热模式可以设置为-1℃，室内设定温度T set反映人员对室内温度的偏差容忍度。对于室内设定湿度阈值RH comp，制冷模式可以设置为10％，制热模式可以设置为-10％，室内设定湿度阈值RH comp反映人员对室内湿度的偏差容忍度。
上述函数可以表示为多种方程形式，考虑到控制器芯片的计算能力有限，多元线形方程形式：即如果空调器的预测类型为开机时间预测，通过下述算式确定空调器的预测开机时间：
Δt open＝c 1·(T in-T set-T comp)+c 2·(T out-T set-T comp)+c 3·(RH in-RH set-RH comp)+c 4(RH out-RH set-RH comp)；
上式中的c 1-c 4为预先设定的开机时间预测的系数，可以在控制器中进行预设置。
空调器提前关机是与提前开机完全相反的过程，通过利用室内允许的温度偏差和湿度偏差，提前关闭空调器，利用建筑蓄冷或蓄热将室内温度维持到下班时刻，从而节约空调器的能耗，空调器提前关机时间可以用下述方程表示：
Δt close＝f 2(T in,RH in,T out,RH out,T set,RH set,T comp,RH comp)。式中，△t close为空调器预测提前关机时间，△t close为时长而非时刻。其他参数同上。
将上述函数也展开为多元线形方程形式：即，如果空调器的预测类型为关机时间预测，通过下述算式确定空调器的预测关机时间：
Δt close＝d 1·(T in-T set-T comp)+d 2·(T out-T set-T comp)+d 3·(RH in-RH set-RH comp)+d 4·(RH out-RH set-RH comp)；
其中，△t close为预测关机时间，d 1-d 4为预先设定的关机时间预测的系数，也可以在控制器中进行预设置。
如图3所示，进行提前开机时间的计算，控制器可以采集并记录当前时刻的室内温湿度、室外温湿度，根据提前开机时间预测方程计算提前开机时间△t open。然而，提前开机时间是存在一个上限和下限的，即不能过早或过晚才开机，因此，如果预测时间大于预设的开机时间或关机时间的上限值，将上限值作为预测时间；如果预测时间小于开机时间或关机时间的下限值，将下限值作为预测时间。
以预测时间是时长为例，以开机为例，如果预测开机时间为1小时，然而，开机时间的下限值为30分钟，则预测时间小于开机时间的下限值，可以将下限值30分钟作为预测时间。
对于关机的情况则与开机类似，如图4所示，进行提前关机时间的计算，控制器采集并记录当前时刻的室内温湿度、室外温湿度，根据提前开机时间预测方程计算提前开机时间△t close。若△t close超过关机时间的上限值△t max，则△t close＝△t max；若△t close小于关机时间的下限值△t min，则△t close＝△t min。
步骤S206，基于预测时间控制空调器的启动或者关闭。
以预测时间是时长为例，如图3和图4所示，控制器在控制空调器的启动或者关闭时，可以首先进行判断空调器是否开机的步骤，例如：获取第二当前时刻；计算第二当前时刻与预设的上班时刻或下班时刻的时间差，如果时间差小于或等于预测开机时间或预测关机时间，控制空调器启动或者关闭。
如图3所示的判断空调器是否开机。当获取预测开机时间后，控制器实时计算第二当前时刻t与上班时刻t on的时间差△t，并与预测开机时间△t open比较：若△t>△t open，则说明当前时刻还未到达开机时刻，控制器继续等待；若△t≤△t open，则说明当前时刻已到达开机时刻，控制器向空调器发出开机指令，空调器开始运行。
如图4所示的判断空调器是否开机。当获取预测关机时间△t close后，控制器实时计算第二当前时刻t与下班时刻t off的时间差△t，并与△t close比较：若△t>△t close，则说明当前时刻还未到达关机时刻，控制器继续等待；若△t≤△t close，则说明当前时刻已到达开机时刻，控制器向空调器发出关机指令，空调器结束运行。
步骤S208，确定空调器的达温时间。
上述步骤说明了控制器如何控制空调器的开机和关机，然而，空调器中的预测模型是可以自学习，并对其参数进行调整的。即，空调器开机时间预测方程与关机时间预测方程中的系数不是固定不变的，如图3和图4所示，需要先判断是否需要调整参数，之后再对参数进行调整。可以通过下述步骤确定达温时间：确定空调器的达温时间的步骤，包括：
如果空调器的预测类型为开机时间预测，确定空调器的开机时间；如果室内温度大于或等于室内设定温度与室内设定温度阈值的和，获取第三当前时刻；将第三当前时刻与开机时间的差作为达温时间。
如图3所示的达温时间计算。控制器可以实时采集室内温度，判断室内温度大于或等于室内设定温度与室内设定温度阈值的和：室内温度T in＝室内设定温度T set+室内设定温度阈值T comp；若是，记录第三当前时刻t 2，达温时间△t r＝第三当前时刻t 2-开机时间t 1；否则，继续等待。
如果空调器的预测类型为关机时间预测，确定空调器的关机时间；如果室内温度小于或等于室内设定温度与室内设定温度阈值的和，获取第四当前时刻；将第四当前时刻与关机时间的差作为达温时间。
如图4所示的达温时间计算。控制器可以实时采集室内温度，判断室内温度小于或等于室内设定温度与室内设定温度阈值的和：室内温度T in＝室内设定温度T set+室内设定温度阈值T comp；若是，记录第三当前时刻t 2，达温时间△t r＝第三当前时刻t 2-关机时间t 1；否则，继续等待。
步骤S210，基于达温时间调整预测模型的参数。
如果达温时间与预测开机时间或预测关机时间的误差较大，则可以调整预测模型的参数，例如：如果空调器的预测类型为开机时间预测，确定达温时间与预测开机时间的差的第一绝对值；如果第一绝对值大于预设的第一误差阈值，调整预测模型的参数；或者，如果空调器的预测类型为关机时间预测，确定达温时间与预测关机时间的差的第二绝对值；如果第二绝对值大于预设的第二误差阈值，调整预测模型的参数。
其中，上述第一误差阈值和第二误差阈可以相同，也可以不同，本实施例对此不作限定。
如图3所示的预测方程系数自学习更新。比较达温时间△t r与预测开机时间△t open的误差：若|△t r-△t open|≤第一误差阈值，则不对预测方程系数进行更新；否则结合历史的室内温湿度、室外温湿度、实际达温时间预测方程系数进行更新。
如图4所示的预测方程系数自学习更新。比较达温时间△t r与预测关机时间△t close的误差：若|△t r-△t close|≤第二误差阈值，则不对预测方程系数进行更新；否则结合历史的室内温湿度、室外温湿度、实际达温时间预测方程系数进行更新。
在进行预测模型的参数的调整的步骤时，可以根据空调器的历史温度数据和历史湿度数据进行调整，例如：获取预设时间范围内的空调器的历史温度数据和历史湿度数据；基于历史温度数据和历史湿度数据调整预测模型的参数。
控制器中预测模型的参数不是固定不变的，因为建筑负荷会随着室外气象参数的变化而变化，因此预测模型的参数也应能随着时间的推移自学习调整，从而适应负荷的变化，保证预测时间的精度。以空调器提前启动为例，要对预测模型的参数进行更新，则可以联立4个方程求解。因此，控制器需要至少记录相邻4天的室内温湿度与室外温湿度值，并且每天对4个系数进行自适应更新，预测开机时间方程系数更新如下：
Figure PCTCN2022091244-appb-000001
上述方程中，△tr为空调器实际达温时间(即室内温度达到T set+T comp实际所用的时间)，下标k代表今天，k-1代表昨天，k-2代表前天，k-3代表大前天。控制器通过采集连续4天的室内温湿度、室外温湿度值及空调器达温时间，实现对预测方程系数的自学习更新。
此外还需要说明的是，上述空调器的控制器可以设置于空调器中，或者，空调器的控制器可以设置于与空调器通信连接的服务器中。空调器的控制器可以由时间模块、信号采集模块、存储模块、预测模块组成，其中，时间模块可以用于采集当前的时间，为保证时间的准确性，每次与上位机联网时自动同步时间。信号采集模块可以用于采集室内温湿度、室内温湿度参数。存储模块可以用于记录相邻几天预设判断时刻的室内温湿度、室内温湿度参数，以及控制器的一些预设参数，例如：制冷目标温度、制热目标温度、设定温度阈值、上班时刻、下班时刻、设判断时刻、最早开机时间、最晚开机时间、时间误差阈值等。预测模块可以用于根据采集模块传入的温湿度参数，依据预先编写的启停时间预测方程计算预测开机或关机的时间。
此外，本实施例提供的空调器控制方法的结果，可以参见图5所示的一种开机时间的曲线示意图，图5为某大楼组合式空调器采用本实施例提供的空调器控制方法的开机时间，曲线1为实际预冷时间，曲线2为预测预冷时间，从图5中可以看出，通过自学习优化预测方程系数，预测预冷时间与实际预冷时间的误差接近，说明该空调器控制方法可以在有效保证室内温度的同时，尽可能减少组合式空调器的能耗。
综上，本申请实施例提出一种根据相邻几天的室内外温度、湿度以及房间设定温度，预测空调器在不同模式下优化启停时间的方法，使得室内在上班或下班时刻室内温度刚好不超过设定阈值范围，同时能最大程度节约空调器的能耗。该方式中的空调器的预测模型会随着建筑负荷的变化自学习调整参数，保证预测时间的精度。本申请实施例还提出一种内置空调器启停时间预测功能的控制器，该控制器由时间模块、信号采集模块、存储模块、预测模块组成，无需人员操作也无需接入BMS群控系统，可实现空调器的本地优化启停控制。当然，该控制器也可以不设置在空调器中，通过上位机或云平台编写优化控制算法可实现上述功能。
本申请实施例提供的上述方法，可以根据室内外空气温湿度参数预测在制冷/制热场景下的空调器提前开机或关机的时间，使得室内温度在上班时刻刚好达到设定温度的范围内，在下班前提前关闭空调器不会引起温度的较大波动，从而尽量减少空调器的运行能耗。同时，预测模型会随着建筑负荷的变化自学习调整参数，保证预测时间的精度。该预测计算完全在本地控制器完成，不需要借助上位机或云平台，方便操作使用，节约投资成本。
对应于上述方法实施例，本申请又一实施例提供了一种空调器控制装置，应用于空调器的控制器，参见图6所示的一种空调器控制装置的结构示意图，该空调器控制装置可以包括：
数据获取模块61，可以配置成用于获取空调器的温度数据和湿度数据；其中，温度数 据可以包括室内温度和室外温度，湿度数据可以包括室内湿度和室外湿度；
时间预测模块62，可以配置成用于将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间；其中，空调器的模式可以包括制冷模式和/或制热模式；空调器的预测类型可以包括开机时间预测和/或关机时间预测；空调器预测模型的参数可以包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；预测时间包括预测开机时间和/或预测关机时间；
空调器控制模块63，可以配置成用于基于预测时间控制空调器的启动或者关闭。
本申请实施例提供的一种空调器控制装置，可以将空调器的模式、预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间，并基于预测时间控制空调器的启动或者关闭。该方式通过预测模型预测空调器的预测开机时间和预测关机时间，可以节约空调器的能耗，不会造成能源的浪费，热适应性较好。
上述数据获取模块，可以配置成用于获取第一当前时刻；如果第一当前时刻达到预设的判断时间，获取空调器的温度数据和湿度数据。
上述时间预测模块，可以配置成用于如果空调器的预测类型为开机时间预测，通过下述算式确定空调器的预测开机时间：Δt open＝c 1·(T in-T set-T comp)+c 2·(T out-T set-T comp)+c 3·(RH in-RH set-RH comp)+c 4(RH out-RH set-RH comp)；其中，△t open为预测开机时间，c 1-c 4为预先设定的开机时间预测的系数，T in为室内温度，RH in为室内湿度，T out为室外温度，RH out为室外湿度，T set为室内设定温度，RH set为室内设定湿度，T comp为室内设定温度阈值，RH comp为室内设定湿度阈值；
上述时间预测模块，可以配置成用于如果空调器的预测类型为关机时间预测，通过下述算式确定空调器的预测关机时间：Δt close＝d 1·(T in-T set-T comp)+d 2·(T out-T set-T comp)+d 3·(RH in-RH set-RH comp)+d 4·(RH out-RH set-RH comp)；其中，△t close为预测关机时间，d 1-d 4为预先设定的关机时间预测的系数。
上述时间预测模块，还可以配置成用于如果预测时间大于预设的开机时间或关机时间的上限值，将上限值作为预测时间；如果预测时间小于开机时间或关机时间的下限值，将下限值作为预测时间。
上述空调器控制模块，可以配置成用于获取第二当前时刻；计算第二当前时刻与预设的上班时刻或下班时刻的时间差，如果时间差小于或等于预测开机时间或预测关机时间，控制空调器启动或者关闭。
参见图7所示的另一种空调器控制装置的结构示意图，该空调器控制装置还可以包括：模型更新模块64，可以与空调器控制模块63连接，模型更新模块64可以配置成用于确定空调器的达温时间；基于达温时间调整预测模型的参数。
上述模型更新模块，可以配置成用于如果空调器的预测类型为开机时间预测，确定空调器的开机时间；如果室内温度大于或等于室内设定温度与室内设定温度阈值的和，获取第三当前时刻；将第三当前时刻与开机时间的差作为达温时间；或者，如果空调器的预测类型为关机时间预测，确定空调器的关机时间；如果室内温度小于或等于室内设定温度与室内设定温度阈值的和，获取第四当前时刻；将第四当前时刻与关机时间的差作为达温时间。
上述模型更新模块，可以配置成用于如果空调器的预测类型为开机时间预测，确定达温时间与预测开机时间的差的第一绝对值；如果第一绝对值大于预设的第一误差阈值，调整预测模型的参数；或者，如果空调器的预测类型为关机时间预测，确定达温时间与预测关机时间的差的第二绝对值；如果第二绝对值大于预设的第二误差阈值，调整预测模型的参数。
上述模型更新模块，可以配置成用于获取预设时间范围内的空调器的历史温度数据和历史湿度数据；基于历史温度数据和历史湿度数据调整预测模型的参数。
上述空调器的控制器可以设置于空调器中，或者，上述空调器的控制器可以设置于与空调器通信连接的服务器中。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的空调器控制装置的具体工作过程，可以参考前述的空调器控制方法的实施例中的对应过程，在此不再赘述。
本申请再一实施例提供了一种电子设备，用于运行上述空调器控制方法；参见图8所示的一种电子设备的结构示意图，该电子设备可以包括存储器100和处理器101，其中，存储器100可以配置成用于存储一条或多条计算机指令，一条或多条计算机指令被处理器101执行，以实现上述空调器控制方法。
可选地，图8所示的电子设备还可以包括总线102和通信接口103，处理器101、通信接口103和存储器100可以通过总线102连接。
其中，存储器100可能包含高速随机存取存储器(RAM，Random Access Memory)，也可能还包括非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。通过至少一个通信接口103(可以是有线或者无线)实现该系统网元与至少一个其他网元之间的通信连接，可以使用互联网，广域网，本地网，城域网等。总线102可以是ISA总线、PCI总线或EISA总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图8中仅用一个双向箭头表示，但并不表示仅有一根总线或一种类型的总线。
处理器101可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方 法的各步骤可以通过处理器101中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器101可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(Digital Signal Processor，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、现场可编程门阵列(Field-Programmable Gate Array，简称FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质可以位于存储器100，处理器101可以读取存储器100中的信息，结合其硬件完成前述实施例的方法的步骤。
本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质可以存储有计算机可执行指令，该计算机可执行指令在被处理器调用和执行时，计算机可执行指令可以促使处理器实现上述空调器控制方法，具体实现可参见方法实施例，在此不再赘述。
本申请实施例所提供的空调器控制方法、装置和电子设备的计算机程序产品，可以包括存储了程序代码的计算机可读存储介质，程序代码包括的指令可用于执行前面方法实施例中的方法，具体实现可参见方法实施例，在此不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统和/或装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
另外，在本申请实施例的描述中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本申请中的具体含义。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的 介质。
在本申请的描述中，需要说明的是，术语“中心”、“上”、“下”、“左”、“右”、“竖直”、“水平”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。此外，术语“第一”、“第二”、“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性。
最后应说明的是：以上所述实施例，仅为本申请的具体实施方式，用以说明本申请的技术方案，而非对其限制，本申请的保护范围并不局限于此，尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本申请实施例技术方案的精神和范围，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。
工业实用性
本申请提供了一种空调器控制方法、装置和电子设备。该方法应用于空调器的控制器，该方法包括：获取空调器的温度数据和湿度数据；将空调器的模式、空调器的预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间；基于预测时间控制空调器的启动或者关闭。该方式中，将空调器的模式、预测类型、温度数据和湿度数据输入预先训练完成的空调器的预测模型中，输出空调器的预测时间，并基于预测时间控制空调器的启动或者关闭。该方式通过预测模型预测空调器的预测开机时间和预测关机时间，可以节约空调器的能耗，不会造成能源的浪费，热适应性较好。
此外，可以理解的是，本申请的空调器控制方法、装置和电子设备是可以重现的，并且可以应用在多种工业应用中。例如，本申请的空调器控制方法可以应用于空调器领域。

Claims (15)

  1. 一种空调器控制方法，其特征在于，应用于空调器的控制器，所述空调器控制方法包括：
    获取所述空调器的温度数据和湿度数据；其中，所述温度数据包括室内温度和室外温度，所述湿度数据包括室内湿度和室外湿度；
    将所述空调器的模式、所述空调器的预测类型、所述温度数据和所述湿度数据输入预先训练完成的空调器的预测模型中，输出所述空调器的预测时间；其中，所述空调器的模式包括制冷模式和/或制热模式；所述空调器的预测类型包括开机时间预测和/或关机时间预测；所述预测模型的参数包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；所述预测时间包括预测开机时间和/或预测关机时间；
    基于所述预测时间控制所述空调器的启动或者关闭。
  2. 根据权利要求1所述的空调器控制方法，其特征在于，获取所述空调器的温度数据和湿度数据的步骤，包括：
    获取第一当前时刻；
    如果所述第一当前时刻达到预设的判断时间，获取所述空调器的温度数据和湿度数据。
  3. 根据权利要求1或2所述的空调器控制方法，其特征在于，如果所述空调器的预测类型为所述开机时间预测，通过下述算式确定所述空调器的预测开机时间：
    Δt open＝c 1·(T in-T set-T comp)+c 2·(T out-T set-T comp)+c 3·(RH in-RH set-RH comp)+c 4(RH out-RH set-RH comp)；
    其中，△t open为所述预测开机时间，c 1-c 4为预先设定的所述开机时间预测的系数，T in为所述室内温度，RH in为所述室内湿度，T out为所述室外温度，RH out为所述室外湿度，T set为所述室内设定温度，RH set为所述室内设定湿度，T comp为所述室内设定温度阈值，RH comp为所述室内设定湿度阈值；
    如果所述空调器的预测类型为所述关机时间预测，通过下述算式确定所述空调器的预测关机时间：
    Δt close＝d 1·(T in-T set-T comp)+d 2·(T out-T set-T comp)+d 3·(RH in-RH set-RH comp)+d 4·(RH out-RH set-RH comp)；
    其中，△t close为所述预测关机时间，d 1-d 4为预先设定的所述关机时间预测的系数。
  4. 根据权利要求1至3中的任一项所述的空调器控制方法，其特征在于，输出所述空调器的预测时间的步骤之后，所述空调器控制方法还包括：
    如果所述预测时间大于预设的开机时间或关机时间的上限值，将所述上限值作为所述预测时间；
    如果所述预测时间小于所述开机时间或所述关机时间的下限值，将所述下限值作为所 述预测时间。
  5. 根据权利要求1至4中的任一项所述的空调器控制方法，其特征在于，基于所述预测时间控制所述空调器的启动或者关闭的步骤，包括：
    获取第二当前时刻；
    计算所述第二当前时刻与预设的上班时刻或下班时刻的时间差，如果所述时间差小于或等于所述预测开机时间或所述预测关机时间，控制所述空调器启动或者关闭。
  6. 根据权利要求5所述的空调器控制方法，其特征在于，
    获取所述预测开机时间△t open后，实时计算所述第二当前时刻与所述上班时刻的时间差△t，并与所述预测开机时间△t open比较：若△t>△t open，则继续等待；若△t≤△t open，则向所述空调器发出开机指令，所述空调器开始运行。
  7. 根据权利要求5所述的空调器控制方法，其特征在于，
    获取所述预测关机时间△t close后，实时计算所述第二当前时刻与所述下班时刻的时间差△t，并与所述预测关机时间△t close比较：若△t>△t close，则继续等待；若△t≤△t close，则向所述空调器发出关机指令，所述空调器结束运行。
  8. 根据权利要求1至7中的任一项所述的空调器控制方法，其特征在于，基于所述预测时间控制所述空调器的启动或者关闭的步骤之后，所述空调器控制方法还包括：
    确定所述空调器的达温时间；
    基于所述达温时间调整所述预测模型的参数。
  9. 根据权利要求8所述的空调器控制方法，其特征在于，确定所述空调器的达温时间的步骤，包括：
    如果所述空调器的预测类型为所述开机时间预测，确定所述空调器的开机时间；如果所述室内温度大于或等于所述室内设定温度与所述室内设定温度阈值的和，获取第三当前时刻；将所述第三当前时刻与所述开机时间的差作为所述达温时间；
    或者，如果所述空调器的预测类型为所述关机时间预测，确定所述空调器的关机时间；如果所述室内温度小于或等于所述室内设定温度与所述室内设定温度阈值的和，获取第四当前时刻；将所述第四当前时刻与所述关机时间的差作为所述达温时间。
  10. 根据权利要求8或9所述的空调器控制方法，其特征在于，基于所述达温时间调整所述预测模型的参数的步骤，包括：
    如果所述空调器的预测类型为所述开机时间预测，确定所述达温时间与所述预测开机时间的差的第一绝对值；如果所述第一绝对值大于预设的第一误差阈值，调整所述预测模型的参数；
    或者，如果所述空调器的预测类型为所述关机时间预测，确定所述达温时间与所述预 测关机时间的差的第二绝对值；如果所述第二绝对值大于预设的第二误差阈值，调整所述预测模型的参数。
  11. 根据权利要求8或9所述的空调器控制方法，其特征在于，基于所述达温时间调整所述预测模型的参数的步骤，包括：
    获取预设时间范围内的所述空调器的历史温度数据和历史湿度数据；
    基于所述历史温度数据和所述历史湿度数据调整所述预测模型的参数。
  12. 根据权利要求1至11中的任一项所述的空调器控制方法，其特征在于，所述空调器的控制器设置于所述空调器中，或者，所述空调器的控制器设置于与所述空调器通信连接的服务器中。
  13. 一种空调器控制装置，其特征在于，应用于空调器的控制器，所述空调器控制装置包括：
    数据获取模块，配置成用于获取所述空调器的温度数据和湿度数据；其中，所述温度数据包括室内温度和室外温度，所述湿度数据包括室内湿度和室外湿度；
    时间预测模块，配置成用于将所述空调器的模式、所述空调器的预测类型、所述温度数据和所述湿度数据输入预先训练完成的空调器的预测模型中，输出所述空调器的预测时间；其中，所述空调器的模式包括制冷模式和/或制热模式；所述空调器的预测类型包括开机时间预测和/或关机时间预测；所述预测模型的参数包括：室内设定温度、室内设定温度阈值、室内设定湿度和室内设定湿度阈值；所述预测时间包括预测开机时间和/或预测关机时间；
    空调器控制模块，配置成用于基于所述预测时间控制所述空调器的启动或者关闭。
  14. 一种电子设备，其特征在于，包括处理器和存储器，所述存储器存储有能够被所述处理器执行的计算机可执行指令，所述处理器执行所述计算机可执行指令以实现权利要求1至12中的任一项所述的空调器控制方法。
  15. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令在被处理器调用和执行时，计算机可执行指令促使处理器实现权利要求1至12中的任一项所述的空调器控制方法。
PCT/CN2022/091244 2021-09-30 2022-05-06 空调器控制方法、装置和电子设备 WO2023050814A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US18/564,029 US20240288191A1 (en) 2021-09-30 2022-05-06 Method for controlling air conditioner, and electronic device and computer-readable storage medium
EP22874212.8A EP4328506A4 (en) 2021-09-30 2022-05-06 AIR CONDITIONER CONTROL METHOD AND APPARATUS AND ELECTRONIC DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111163463.6A CN113739390B (zh) 2021-09-30 2021-09-30 空调器控制方法、装置和电子设备
CN202111163463.6 2021-09-30

Publications (1)

Publication Number Publication Date
WO2023050814A1 true WO2023050814A1 (zh) 2023-04-06

Family

ID=78725937

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/091244 WO2023050814A1 (zh) 2021-09-30 2022-05-06 空调器控制方法、装置和电子设备

Country Status (4)

Country Link
US (1) US20240288191A1 (zh)
EP (1) EP4328506A4 (zh)
CN (1) CN113739390B (zh)
WO (1) WO2023050814A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113739390B (zh) * 2021-09-30 2023-01-24 上海美控智慧建筑有限公司 空调器控制方法、装置和电子设备
CN114526537B (zh) * 2021-12-31 2023-12-26 新奥数能科技有限公司 一种设备节能控制方法和装置
CN114543303B (zh) * 2022-01-26 2023-07-14 深圳达实智能股份有限公司 基于运行大数据的中央空调制冷站运行优化方法和系统
CN115289602B (zh) * 2022-10-09 2022-12-16 蘑菇物联技术（深圳）有限公司 确定中央空调系统目标操作时刻的方法、计算设备和介质
CN117308288B (zh) * 2023-09-21 2024-04-19 中国工业互联网研究院 一种制丝空调启停预测控制方法以及装置

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107504656A (zh) * 2017-09-15 2017-12-22 珠海格力电器股份有限公司 一种空调器自学习控制方法及系统
CN109373539A (zh) * 2018-11-07 2019-02-22 珠海格力电器股份有限公司 空调及其控制方法和装置
CN110686382A (zh) * 2019-10-16 2020-01-14 广东美的暖通设备有限公司 空调控制方法、装置及计算机可读存储介质
CN112050384A (zh) * 2019-06-06 2020-12-08 青岛海尔空调器有限总公司 制冷工况下空调器的控制方法
US20210018205A1 (en) * 2019-07-16 2021-01-21 Johnson Controls Technology Company Systems and methods for automated system identification
CN112283889A (zh) * 2020-10-10 2021-01-29 广东美的暖通设备有限公司 空调的预启动时间控制方法、装置、设备及存储介质
CN112762576A (zh) * 2020-12-29 2021-05-07 广东美的白色家电技术创新中心有限公司 空调系统控制方法、达温时间预测模型训练方法及设备
CN113739390A (zh) * 2021-09-30 2021-12-03 上海美控智慧建筑有限公司 空调器控制方法、装置和电子设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7152118B2 (ja) * 2018-10-31 2022-10-12 アズビル株式会社 空調システムの最適起動制御装置
EP3885664B1 (en) * 2018-12-12 2023-04-26 Mitsubishi Electric Corporation Air conditioning control device and air conditioning control method

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107504656A (zh) * 2017-09-15 2017-12-22 珠海格力电器股份有限公司 一种空调器自学习控制方法及系统
CN109373539A (zh) * 2018-11-07 2019-02-22 珠海格力电器股份有限公司 空调及其控制方法和装置
CN112050384A (zh) * 2019-06-06 2020-12-08 青岛海尔空调器有限总公司 制冷工况下空调器的控制方法
US20210018205A1 (en) * 2019-07-16 2021-01-21 Johnson Controls Technology Company Systems and methods for automated system identification
CN110686382A (zh) * 2019-10-16 2020-01-14 广东美的暖通设备有限公司 空调控制方法、装置及计算机可读存储介质
CN112283889A (zh) * 2020-10-10 2021-01-29 广东美的暖通设备有限公司 空调的预启动时间控制方法、装置、设备及存储介质
CN112762576A (zh) * 2020-12-29 2021-05-07 广东美的白色家电技术创新中心有限公司 空调系统控制方法、达温时间预测模型训练方法及设备
CN113739390A (zh) * 2021-09-30 2021-12-03 上海美控智慧建筑有限公司 空调器控制方法、装置和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4328506A4 *

Also Published As

Publication number Publication date
US20240288191A1 (en) 2024-08-29
CN113739390A (zh) 2021-12-03
CN113739390B (zh) 2023-01-24
EP4328506A4 (en) 2024-09-11
EP4328506A1 (en) 2024-02-28

Similar Documents

Publication Publication Date Title
WO2023050814A1 (zh) 空调器控制方法、装置和电子设备
WO2021063033A1 (zh) 空调能耗模型训练方法与空调系统控制方法
CN106817909B (zh) 空调控制方法、空调控制装置以及计算机可读记录介质
JP2020067270A (ja) 空調制御プログラム、空調制御方法および空調制御装置
US11353232B2 (en) Control method, control apparatus, and non-transitory computer-readable storage medium for storing program
WO2023040694A1 (zh) 制冷机房能效计算方法、装置和电子设备
KR101929195B1 (ko) 건물 에너지 효율 등급과 연계한 부하 예측 기반 빌딩 제어 장치
WO2018188522A1 (zh) 一种空调器制热运行控制方法
CN112050446B (zh) 新风空调的控制方法
US20200124304A1 (en) Control method, control apparatus, and non-transitory computer-readable storage medium for storing program
CN114526537B (zh) 一种设备节能控制方法和装置
CN112050440A (zh) 新风空调的控制方法
CN112050441A (zh) 新风空调的净化控制方法
CN116045560A (zh) 一种制冷系统远程管理方法、系统及计算机可读存储介质
CN112050392B (zh) 制冷工况下空调器的控制方法
JP2023027827A (ja) 運転管理装置、運転管理方法、及びプログラム
CN112050396B (zh) 制冷工况下空调器的控制方法
CN112050447B (zh) 新风空调的控制方法
CN112050386B (zh) 制冷工况下空调器的控制方法
CN112050384B (zh) 制冷工况下空调器的控制方法
CN112050393B (zh) 制冷工况下空调器的控制方法
JP5705316B2 (ja) 空調管理装置、空調管理方法、プログラム、及び、空調システム
CN112050439A (zh) 新风空调的控制方法
CN112050394A (zh) 制冷工况下空调器的控制方法
CN112050383A (zh) 制冷工况下空调器的控制方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22874212

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022874212

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 18564029

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2022874212

Country of ref document: EP

Effective date: 20231122

NENP Non-entry into the national phase

Ref country code: DE