Central air conditioner control system

Abstract

The invention discloses a central air conditioner control system which comprises at least one outdoor unit and at least one indoor unit in communication connection with the outdoor units through communication buses. The controllers can communicate with one another and are respectively connected with the communication bus; the temperature and humidity sensor is used for collecting indoor temperature data and humidity data; wherein the controller is used for storing current regional information, weather information and equipment operation records; the controller is also used for establishing a thermal comfort evaluation / recommendation model and an intelligent prediction schedule model by using a machine learning algorithm; the controller is further used for forming recommended control parameters according to the set requirements of the user and sending the recommended control parameters to the outdoor unit or the indoor unit. According to the invention, based on the information of the area where the user is located, the weather information, the indoor environment information and the user information, a machine learning algorithm is utilized to establish a thermal comfort evaluation recommendation model and an intelligent prediction schedule model, the models are combined to form a recommendation control strategy according to a scene set by the user, and optimal control parameters are provided for the user. And in cooperation with the energy-saving effect of the central air conditioning equipment, the purpose of efficient and energy-saving operation is achieved on the premise that the comfort level of a user is met.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical appliances, and more particularly to a central air-conditioning control system Background Art

[0002] Currently, the leading air-conditioning control technologies in the industry are still limited to voice control, APP timing, scene control, and linkage control with other devices (smart speakers, air detectors), etc. There is no realization of non-intrusive intelligent control, and the goal of energy-saving air-conditioning control has not been achieved yet

[0003] The above information disclosed in this background art is only used to increase the understanding of the background art of this application. Therefore, it may include prior art that is not known to those of ordinary skill in the art Summary of the Invention

[0004] In view of the problems pointed out in the background art, the present invention proposes a central air-conditioning control system to facilitate non-intrusive intelligent operation

[0005] To achieve the above-mentioned invention objectives, the present invention is implemented by the following technical solutions

[0006] In some embodiments of the present application, a central air-conditioning control system is provided, including

[0007] At least one outdoor unit

[0008] At least one indoor unit, which is communicatively connected to each outdoor unit through a communication bus

[0009] At least one controller, each controller can communicate with each other and is respectively connected to the communication bus

[0010] A temperature and humidity sensor for collecting indoor temperature data and humidity data

[0011] Wherein, the controller is used to store the current area information, weather information, and equipment operation records

[0012] The controller is also used to establish a thermal comfort evaluation / recommendation model and an intelligent prediction schedule model using machine learning algorithms

[0013] The controller is also used to form recommended control parameters according to the user's set requirements and send them to the outdoor unit or the indoor unit

[0014] In some embodiments of the present application, the controller is used to trigger the intelligent prediction schedule model according to the instruction of the schedule request and predict the service status of the central air-conditioning control system; the controller is also used to correct the predicted service status according to the stored information to obtain an intelligent schedule

[0015] In some embodiments of the present application, the prediction of the service status of the central air-conditioning control system after triggering the intelligent prediction schedule model includes:

[0016] The controller queries the device operation records at least N days ago, processes the device operation records to construct an LSTM grid, and then conducts model training. The output value of the model is the n-hour prediction service status of the central air-conditioning control system.

[0017] In some embodiments of the present application, the controller is further configured to query whether there are holidays and the home status in the user profile within the previous N days and decide the device on / off time periods when the device operation records are less than N days.

[0018] In some embodiments of the present application, the controller is further configured to query whether there are holidays and the home status in the user profile within the previous N days and decide the device on / off time periods when the accuracy of the intelligent prediction schedule model is poor.

[0019] In some embodiments of the present application, the intelligent schedule obtained after correcting the predicted service status according to the stored information includes:

[0020] Query the weather information for the next n hours, calculate the optimal temperature demand for each moment within the next n hours using the relationship between the indoor thermal neutral temperature and the outdoor temperature; then calculate the humidity, wind speed value, and PMV according to the thermal comfort model, and further generate an intelligent schedule.

[0021] In some embodiments of the present application, the querying of the weather information for the next n hours includes:

[0022] Query the outdoor temperature for the next n hours and the records with the difference between the outdoor temperature and the humidity not greater than the threshold in the same season.

[0023] In some embodiments of the present application, the calculation of the humidity, wind speed value, and PMV according to the thermal comfort model includes:

[0024] Query the temperature, humidity, and wind preferences in the user profile and obtain the corresponding temperature, humidity, and wind speed values using the thermal comfort model.

[0025] In some embodiments of the present application, when the number of days of the query records is not less than M days, the controller filters out invalid data and calculates the average values of the set temperature, humidity, and wind speed during the corresponding time when the service status is on.

[0026] In some embodiments of the present application, a central air-conditioning control system includes:

[0027] At least one outdoor unit,

[0028] At least one indoor unit, which is communicatively connected to each outdoor unit through a communication bus;

[0029] At least one controller, each controller being capable of communicating with each other and being respectively connected to the communication bus;

[0030] A temperature and humidity sensor for collecting indoor temperature data and humidity data;

[0031] Wherein, the controller is used to update the intelligent schedule. When the controller receives a new intelligent schedule request, the controller first determines whether the previous intelligent schedule has expired. After the previous intelligent schedule has expired, the controller slices the new intelligent schedule and writes it into the database;

[0032] When both the air service and the schedule switch are in the on state, the controller obtains the schedule status at the current moment from the slice library and pushes the schedule at this moment to multi-dimensional decision-making; the controller pushes the schedule information to the schedule executor to realize the update of the intelligent schedule.

[0033] Compared with the prior art, the advantages and positive effects of the present invention are:

[0034] Based on the user's location information, weather information, indoor environment information and user information, the present invention uses machine learning algorithms to establish a thermal comfort evaluation / recommendation model and an intelligent prediction schedule model. According to the user-set scenarios, the models are combined to form a recommended control strategy, and optimal control parameters are provided to the user. Combining with the energy-saving effect of the central air-conditioning equipment itself, the purpose of efficient energy-saving operation is achieved while meeting the user's comfort.

[0035] After reading the specific embodiments of the present invention in conjunction with the accompanying drawings, other features and advantages of the present invention will become clearer. Brief Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 It is a connection schematic diagram of a central air-conditioning control system according to an embodiment;

[0038] Figure 2 It is a control flowchart of a central air-conditioning control system according to an embodiment;

[0039] Figure 3 It is a flowchart for predicting the service state of the device according to an embodiment;

[0040] Figure 4Flow chart of device service status when the device running record time is short according to an embodiment; Figure 5 Flow chart of the intelligent schedule generation according to an embodiment;

[0041] Figure 6 Flow chart of the intelligent schedule generation when the record time is short according to an embodiment;

[0042] Figure 7 Flow chart of the recommended parameters according to an embodiment;

[0043] Figure 8 Flow chart of the generation of the recommended parameter set according to an embodiment;

[0044] Figure 9 Flow chart of the intelligent schedule prediction update according to an embodiment;

[0045] Figure 10 Flow chart of the execution of the intelligent schedule model according to an embodiment.

[0046] Reference numerals:

[0047] 100, outdoor unit; 200, indoor unit; 300, controller; 400, temperature and humidity sensor. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0049] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0050] The terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0051] In the description of the present application, it should be noted that, unless otherwise clearly specified or limited, the terms "install", "connect", and "couple" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0052] In the present invention, unless otherwise clearly specified or limited, the first feature being "on" or "under" the second feature may include the direct contact between the first and second features, or may include the case where the first and second features are not in direct contact but in contact through additional features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes that the first feature is directly above and obliquely above the second feature, or merely means that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "below" and "beneath" the second feature includes that the first feature is directly below and obliquely below the second feature, or merely means that the horizontal height of the first feature is lower than that of the second feature.

[0053] The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, components and arrangements of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numerals and / or reference letters in different examples. Such repetition is for the purpose of simplification and clarity, and does not in itself indicate the relationship between the various embodiments and / or arrangements discussed. In addition, the present invention provides examples of various specific processes and materials, but those of ordinary skill in the art may be aware of the application of other processes and / or the use of other materials.

[0054] In this application, the air conditioner performs a refrigeration cycle by using a compressor, a condenser, an expansion valve, and an evaporator. The refrigeration cycle includes a series of processes involving compression, condensation, expansion, and evaporation to cool or heat the indoor space.

[0055] The low-temperature and low-pressure refrigerant enters the compressor, and the compressor compresses it into a refrigerant gas in a high-temperature and high-pressure state and discharges the compressed refrigerant gas. The discharged refrigerant gas flows into the condenser. The condenser condenses the compressed refrigerant into a liquid phase, and the heat is released to the surrounding environment through the condensation process.

[0056] The expansion valve expands the liquid-phase refrigerant in a high-temperature and high-pressure state formed by condensation in the condenser into a low-pressure liquid-phase refrigerant. The evaporator evaporates the refrigerant expanded in the expansion valve and returns the refrigerant gas in a low-temperature and low-pressure state to the compressor. The evaporator can achieve a refrigeration effect by using the latent heat of evaporation of the refrigerant for heat exchange with the material to be cooled. Throughout the cycle, the air conditioner can adjust the temperature of the indoor space.

[0057] The outdoor unit of the air conditioner refers to the part of the refrigeration cycle including the compressor and the outdoor heat exchanger. The indoor unit of the air conditioner includes the indoor heat exchanger, and the expansion valve can be provided in the indoor unit or the outdoor unit.

[0058] The indoor heat exchanger and the outdoor heat exchanger serve as condensers or evaporators. When the indoor heat exchanger serves as a condenser, the air conditioner serves as a heater in the heating mode. When the indoor heat exchanger serves as an evaporator, the air conditioner serves as a cooler in the cooling mode.

[0059] Refer to Figure 1 As shown, a central air-conditioning control system includes:

[0060] At least one outdoor unit 100,

[0061] At least one indoor unit 200, which is communicatively connected to each outdoor unit 100 through a communication bus;

[0062] At least one controller 300, each of the controllers 300 can communicate with each other and is respectively connected to the communication bus;

[0063] A temperature and humidity sensor 400 for collecting indoor temperature data and humidity data;

[0064] Wherein, the controller 300 is used to store the current area information, weather information and equipment operation records;

[0065] The controller 300 is further used to establish a thermal comfort evaluation / recommendation model and an intelligent prediction schedule model by using machine learning algorithms;

[0066] The controller 300 is further used to form recommended control parameters according to the user's set requirements and send them to the outdoor unit 100 or the indoor unit 200.

[0067] In some embodiments of the present application, the area information included in the controller 300 of the central air-conditioning control system is the geographical location where the current device is located, and the controller 300 can query the climate information of the current area according to the current area information.

[0068] The weather information in the controller 300 includes historical weather information and predicted weather information. Among them, the historical weather information is used as training data for the thermal comfort evaluation / recommendation model; the predicted weather information is used as the basis for updating the device service status.

[0069] In some embodiments of the present application, referring to Figure 2 as shown, the controller 300 is used to trigger the intelligent prediction schedule model according to the instruction of the schedule request, and then predict the service status of the central air-conditioning control system; the controller 300 is also used to correct the predicted service status according to the stored information to obtain an intelligent schedule.

[0070] In some embodiments of the application, the controller 300 is used to receive an instruction for generating an intelligent schedule request from the user, and this instruction can be input through a mobile terminal, and the mobile terminal includes but is not limited to a wireless remote control, an APP terminal, etc.

[0071] In some embodiments of the present application, referring to Figure 2 as shown, the predicting the service status of the central air-conditioning control system after triggering the intelligent prediction schedule model includes:

[0072] The controller 300 queries the device operation records at least N days ago, processes the device operation records to construct an LSTM grid, and then performs model training, and the output value of this model is the n-hour predicted service status of the central air-conditioning control system.

[0073] In some embodiments of the present application, after receiving the intelligent schedule request, the controller 300 triggers the query function.

[0074] The query scope of the controller 300 includes but is not limited to: device operation records at least N days ago, and the query time can be at certain intervals, including homelD (i.e., user information), air device combination ID, service status, outdoor temperature value, outdoor humidity value, outdoor air quality, and whether it is a holiday (i.e., whether there was a holiday N days ago).

[0075] The start time of the controller 300 during the holiday is different from that during the non-holiday. Therefore, it is necessary to confirm whether there is a holiday in the operation record N days ago.

[0076] In some embodiments of the present application, the controller 300 normalizes the queried data, then specifies the time step of the LSTM, and converts the data into the LSTM format.

[0077] The controller 300 divides the input and output, and converts the data in the LSTM format into the 3D format [n_samples, timesteps, features].

[0078] The controller 300 constructs an LSTM network for model training.

[0079] The LSTM network is established using the sklearn library in the Python language. By calling the LSTM network library function, the dataset (including parameters such as home ID, air combination ID, service status, outdoor humidity, outdoor temperature, and outdoor air quality) is classified, with 80% as the training set and 20% as the validation set.

[0080] Continue to refer to Figure 3 As shown, the training set is input into the created LSTM library function for training. The root mean square error (RMSE) is used as the criterion for judging the model, and the parameter adjustment number is α. The value of α is adjusted according to the actual usage. When α is closer to 1, the effect is the best, but the training time is long. The smaller α is, the worse the model accuracy.

[0081] When the training accuracy of the model is relatively high, the model directly outputs the predicted service status of the device for n hours. Then, the thermal comfort evaluation / recommendation model is used to correct the predicted service status to obtain the final intelligent schedule.

[0082] In some embodiments of the present application, referring to Figure 4 As shown, the controller 300 is further configured to query whether there are holidays, the home status in the user profile, and the decision-making device on / off time period within the previous N days when the device operation record is less than N days.

[0083] In some embodiments of the application, when the controller 300 receives a request for generating an intelligent schedule, it starts to query the device operation record at least 21 days ago.

[0084] When the operation record stored in the controller 300 is less than 21 days, that is, insufficient historical data support cannot be obtained, the controller 300 first queries whether there are holidays and the home status in the user profile to determine the on / off time period of the air conditioner. Then, the thermal comfort evaluation / recommendation model is used to determine the operation data during the air conditioner on time period to obtain the final intelligent schedule.

[0085] In some embodiments of the present application, the root mean square error (RMSE) is used as the criterion for judging the model, and the parameter adjustment number is α. When RMSE is not less than α, it indicates that the model accuracy is poor. When the model accuracy is poor, the controller 300 first queries whether there are holidays and the home status in the user profile to determine the on / off time period of the air conditioner. Then, the thermal comfort evaluation / recommendation model is used to determine the operation data during the air conditioner on time period to obtain the final intelligent schedule.

[0086] In some embodiments of the present application, referring to Figure 5As shown, the intelligent schedule obtained after correcting the predicted service status according to the stored information includes:

[0087] Query the weather information for the next n hours, calculate the optimal temperature demand for each moment within the next n hours using the relationship between the indoor thermal neutral temperature and the outdoor temperature; then calculate the humidity, wind speed value, and PMV according to the thermal comfort model, and further generate an intelligent schedule.

[0088] In some embodiments of the present application, continue to refer to Figure 5 As shown, the querying of the weather information for the next n hours includes:

[0089] Query the outdoor temperature for the next n hours and query the records with the difference between the outdoor temperature and the humidity not greater than the threshold in the same season.

[0090] The intelligent schedule generally executes the service status of the central air-conditioning control system for the next 24 hours, and these 24 hours can be limited by a natural day or within 24 hours after the current moment.

[0091] For the records with the difference between the outdoor temperature and the humidity not greater than the threshold in the same season, that is, it is possible to query the records with the difference in the outdoor temperature value within 1°C and the humidity difference within 5% compared with the current outdoor temperature value in the same season. The controller 300 can calculate the set value of the indoor temperature based on this temperature and humidity data.

[0092] In some embodiments of the present application, continue to refer to Figure 5 As shown, if the records queried by the controller 300 span a short number of days, the controller 300 can query the region in the portrait, and then calculate the optimal temperature demand for each moment within the next n hours according to the relationship between the indoor thermal neutral temperature and the outdoor temperature.

[0093] In some embodiments of the present application, the controller 300 queries the temperature, humidity, and wind preferences in the user portrait, that is, the usual set values of the temperature, humidity, and wind speed.

[0094] The controller 300 can make a judgment according to the temperature preference. If the user's temperature preference is warm, the temperature takes the median value in the interval of [thermal neutral temperature, warm temperature]; if the user's temperature preference is cool, the temperature takes the median value in the interval of [cool temperature, thermal neutral temperature].

[0095] In some embodiments of the present application, the calculation of the humidity, wind speed value, and PMV according to the thermal comfort model includes:

[0096] Query the temperature, humidity, and wind preferences in the user portrait, and obtain the corresponding temperature, humidity, and wind speed values using the thermal comfort model.

[0097] In some embodiments of the present application, refer to Figure 6As shown, when the number of days of query records is not less than M days, the controller 300 filters out invalid data and calculates the average values of the set temperature, humidity, and wind speed within the corresponding time when the service status is on.

[0098] In some embodiments of the present application, during the process of correcting the service status, if the query record time is not less than 20 days, the controller 300 filters out invalid data and then calculates the average values of the set temperature, humidity, and wind speed within the corresponding time when the service status is on.

[0099] In some embodiments of the present application, refer to Figure 7 As shown, when it is necessary to correct the predicted service status, a comfort recommendation request is triggered. The controller 300 first determines whether the records of similar outdoor weather in the same season reach the limit.

[0100] When the records of similar outdoor weather in the same season reach the limit, the controller 300 filters out invalid data and then calculates the temperature, humidity, and wind speed values, and then performs comfort level / recommendation parameters.

[0101] When the records of similar outdoor weather in the same season do not reach the limit, the controller 300 provides comfort parameter guidance according to the geographical information; obtains special control requirements such as temperature and wind speed.

[0102] The controller 300 can select temperature as the first requirement or select wind speed / ventilation as the first requirement, and then screen according to temperature and wind speed preferences.

[0103] The controller 300 can screen according to the value closest to the current indoor temperature and then return to perform comfort level / recommendation parameters.

[0104] In some embodiments of the present application, the controller 300 determines whether to select temperature as the first requirement or select wind speed / ventilation as the first requirement according to the health warning.

[0105] The health warning refers to the special requirements of the user for the environment (temperature, air volume), allowing the user to provide an explanation and incorporating it into the judgment conditions for subsequent control.

[0106] In some embodiments of the present application, for the thermal comfort evaluation / recommendation model, refer to Figure 8 As shown, first, data set support is performed, including geographical information and its corresponding climate specific; then feature engineering is performed, that is, features are selected after preprocessing the data.

[0107] The controller 300 performs AI model training on it, with input features: regional climate, season, indoor temperature, indoor humidity, indoor wind speed, outdoor temperature, and user age (specifically, the user's metabolic rate is judged according to age); the AI evaluation model uses random forest training to obtain an algorithm model and compares the effect with the conventional PMV calculation model.

[0108] The thermal comfort evaluation / recommendation model can achieve AI parameter recommendation. By solving the range combinations of indoor temperature, indoor humidity, indoor wind speed, and outdoor temperature parameters corresponding to different comfort levels, a set of recommended parameters is formed.

[0109] In some embodiments of the present application, the temperature recommendation ranges are sorted according to the regional climate zone:

[0110] According to the thermal comfort literature, the 80% and 90% thermal comfort temperature ranges in different climate zones and different seasons are sorted out. The 80% comfort temperature range is used as the upper and lower limits of the temperature in the cool, comfortable, and warm levels, and the 90% comfort temperature range is used as the upper and lower limits of the temperature in the comfortable level; then, in combination with the GB50736-2016 standard, ensure that the deviation of each temperature upper and lower limit does not exceed the standard regulation (within 3°C). At the same time, in combination with the air-conditioning controllable temperature range, the adjustment range corresponding to each comfort level is generated, as shown in the following table:

[0111]

[0112] In some embodiments of the present application, for the comfort tables of different parameter combinations:

[0113] According to the PMV theoretical calculation formula proposed by ISO-7730:

[0114] PMV = [0.303exp(-0.036M) + 0.028]{M(1 - η) - 3.054×10 -3 [5733 - 6.99H - p a - 0.42[H - 58.15] - 1.7×10 -5 M×(5867 - p a ) - 0.001M(34 - T a ) - Q}

[0115] In the formula: Q = 3.96×10 -8 f c1 (T c1 4 - T r 4 ) - f c1 h c (T c1 - T a )

[0116] Q——Sensible heat dissipation

[0117] M——Human energy metabolic rate (depending on the level of activity) (met or W / m2)

[0118] η——Mechanical efficiency of the human body

[0119] p a ——Vapor pressure of the air around the human body (related to the relative humidity of the air)

[0120] H——Net heat gain of the human body

[0121] T a ——Temperature of the air around the human body

[0122] T c1 and T r ——Kelvin temperature and Celsius temperature on the outer surface of the clothing

[0123] For the central air-conditioning control system and various tests, the above variables are optimized as follows:

[0124] M——Central air-conditioning is commonly used in office buildings, offices and other places, and people are often engaged in light physical work. According to the standard "Determination of PMV and PPD Indices in Moderate Thermal Environments and Regulations for Thermal Comfort Conditions" (GB / T 18049-2000), relevant parameters can be found. Here, the human energy metabolic rate takes a fixed value of 1.2 met, that is, 69.6 W / m2.

[0125] η——The mechanical efficiency of people can be ignored here.

[0126] p a ——Taking a relative humidity of 60%, pa = 0.6×(2.9311t 2 + 21.233t + 686.36), where t is the temperature.

[0127] Analysis of the theoretical calculation formula of PMV shows that when

[0128] Q = M(1 - η) - 3.054×10 -3 [5733 - 6.99M - p a - 0.42[M - 58.15] - 1.7×10 -5 M×(5867 - p a ) - 0.001M(34 - T a )

[0129] PMV = 0, that is, the indoor environment is in the most comfortable state. Substituting the values of M and pa into the above formula and simplifying, Q can be simplified as a function of the indoor temperature t. That is, Q = f(t)

[0130] According to the PMV theoretical calculation formula,

[0131] Q = 3.96×10 -8 f c1 (T c1 4 -T r 4 ) - f c1 h c (T c1 -T a )

[0132] where f CL = 1 + 0.25I CL After substitution and further simplification and arrangement, the relationship between temperature and wind speed can be obtained as:

[0133]

[0134] In the software of the actual air-conditioning system, the relationship between wind speed and temperature is programmed into a table according to the above formula. When the air-conditioning system needs to read the wind speed V (temperature T) during operation, the corresponding temperature T (wind speed V) can be quickly and accurately obtained by looking up the table, so as to realize the thermal comfort index in the control of the air-conditioning system.

[0135] In some embodiments of the present application, for the thermal comfort random forest model, different climates, different seasons (different clothing thermal resistances), different populations (different metabolic rates), different indoor temperatures, different indoor wind speeds, different indoor temperatures, and different outdoor temperatures are cyclically traversed to obtain a thermal comfort parameter combination table.

[0136] In some embodiments of the present application, the controller 300 is further configured to update the intelligent schedule. Referring to Figure 9 as shown, when the controller 300 receives a new intelligent schedule request, the controller 300 first determines whether the previous intelligent schedule has expired. When the previous intelligent schedule expires, the controller 300 slices the new intelligent schedule and writes it into the database.

[0137] When both the air service and the schedule switch are in the on state, the controller 300 obtains the schedule status at the current moment from the slice library and pushes the schedule at that moment to multi-dimensional decision-making; the controller 300 pushes the schedule information to the schedule executor to realize the update of the intelligent schedule.

[0138] In some embodiments of the present application, when the intelligent schedule is updated due to the user modifying the portrait, the controller 300 omits the judgment of whether the previous intelligent schedule has expired. The controller 300 slices the new intelligent schedule and writes it into the database.

[0139] When both the air service and the schedule switch are in the on state, the controller 300 obtains the schedule status at the current moment from the slice library and pushes the schedule at that moment to the multi-dimensional decision-making; the controller 300 pushes the schedule information to the schedule executor to update the intelligent schedule.

[0140] In some embodiments of the present application, referring to Figure 10 As shown, the controller 300 is further configured to execute the timing task of the intelligent schedule. The controller 300 generates a schedule request:

[0141] Trigger the timing task (triggered at 20:00 every day, with an interval of 24 hours), and request to generate the room intelligent schedule;

[0142] In some embodiments of the present application, the controller 300 queries and obtains data support including:

[0143] A. Holiday (divided into working days, weekends, and specified public holidays) information;

[0144] B. The time periods when the air conditioners are turned on for 80% of the people in the existing dataset on working days and weekends;

[0145] C. The outdoor temperature in the next 24 hours;

[0146] D. The relationship between the indoor neutral temperature and the outdoor temperature;

[0147] E. The indoor temperature for turning on / off air conditioning for cooling and the indoor temperature for turning on / off air conditioning for heating in different regions and seasons;

[0148] In some embodiments of the present application, the controller 300 forms a schedule generation rule (LSTM):

[0149] A. Determine the time periods for turning on and off the service according to the user settings and the historical records of device operation;

[0150] B. Search for historical records with similar outdoor environments;

[0151] C. Statistically analyze the temperature, humidity, and wind speed parameters according to the historical records;

[0152] D. Calculate the optimal temperature requirements for each moment within 24 hours according to the relationship between the neutral temperature and the outdoor temperature;

[0153] E. Calculate the temperature, humidity, wind speed, and comfort requirements for each moment within 24 hours according to the user preferences;

[0154] In some embodiments of the present application, the controller 300 outputs the intelligent schedule:

[0155] A. A new room schedule, which is pushed to the schedule management module, and the schedule timing update needs to be marked during the push;

[0156] B.Execution schedule.

[0157] Compared with the prior art, the advantages and positive effects of the present invention are:

[0158] The present invention realizes the grading of comfort through modeling, and utilizes the coordinated use of thermal comfort evaluation / recommendation model and intelligent prediction schedule model to generate an intelligent schedule based on various factors, thereby realizing intelligent and senseless control of users and achieving the goal of efficient and energy-saving operation.

[0159] That is to say, based on the user's area information, weather information, indoor environment information and user information, machine learning algorithms are used to establish thermal comfort evaluation\recommendation models and intelligent prediction schedule models. According to the user-set scenarios, the models are combined to form recommended control strategies, provide users with optimal control parameters, and cooperate with the energy-saving effects of the central air-conditioning equipment itself to achieve the goal of efficient and energy-saving operation while meeting the user's comfort.

[0160] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0161] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A central air conditioning control system, characterized in that, Comprising: At least one outdoor unit, At least one indoor unit, which is communicatively connected to each outdoor unit via a communication bus; At least one controller, each controller being able to communicate with each other and being respectively connected to the communication bus; A temperature and humidity sensor for collecting indoor temperature data and humidity data; Wherein, the controller is used for storing the current area information, weather information and equipment operation records; The controller is also used for establishing a thermal comfort evaluation / recommendation model and an intelligent prediction schedule model by using machine learning algorithms; The controller is also used for forming recommended control parameters according to the user's set requirements and sending them to the outdoor unit or the indoor unit.

2. The central air-conditioning control system according to claim 1, wherein The controller is used for triggering the intelligent prediction schedule model according to the instruction of the schedule request and predicting the service state of the central air-conditioning control system; the controller is also used for correcting the predicted service state according to the stored information to obtain an intelligent schedule.

3. The central air-conditioning control system according to claim 2, wherein The predicting the service state of the central air-conditioning control system after triggering the intelligent prediction schedule model includes: The controller queries the equipment operation records at least N days ago, processes the equipment operation records to construct an LSTM grid, and then performs model training, and the output value of the model is the n-hour predicted service state of the central air-conditioning control system.

4. The central air-conditioning control system according to claim 1, wherein The controller is also used for querying whether there are holidays, the home state in the user portrait, and the decision-making equipment on / off time period within the previous N days when the equipment operation records are less than N days.

5. The central air-conditioning control system according to claim 1, wherein The controller is also used for querying whether there are holidays, the home state in the user portrait, and the decision-making equipment on / off time period within the previous N days when the accuracy of the intelligent prediction schedule model is poor.

6. The central air-conditioning control system according to claim 2, wherein The obtaining the intelligent schedule after correcting the predicted service state according to the stored information includes: Querying the weather information for the next n hours, calculating the optimal temperature requirement for each moment within the next n hours by using the relationship between the indoor thermal neutral temperature and the outdoor temperature; then calculating the humidity, wind speed value and PMV according to the thermal comfort model, and further generating an intelligent schedule.

7. The central air-conditioning control system according to claim 6, wherein The querying the weather information for the next n hours includes: Querying the outdoor temperature for the next n hours and querying the records with the difference between the outdoor temperature and the humidity not greater than the threshold value in the same season.

8. The central air-conditioning control system according to claim 6, wherein The calculating the humidity, wind speed value and PMV according to the thermal comfort model includes: Querying the temperature, humidity and wind preferences in the user portrait and obtaining the corresponding temperature, humidity and wind speed values by using the thermal comfort model.

9. The central air-conditioning control system according to claim 1, wherein When the number of days of query records is not less than M days, the controller filters out invalid data and calculates the average values of the set temperature, humidity, and wind speed within the corresponding time when the service status is on.

10. A central air-conditioning control system, characterized in that, Including: At least one outdoor unit, At least one indoor unit, which is communicatively connected to each outdoor unit via a communication bus; At least one controller, each controller can communicate with each other and is respectively connected to the communication bus; A temperature and humidity sensor for collecting indoor temperature data and humidity data; Wherein, the controller is used to update the intelligent schedule. When the controller receives a new intelligent schedule request, the controller first determines whether the last intelligent schedule has expired. After the last intelligent schedule has expired, the controller slices the new intelligent schedule and writes it into the database; When both the air service and the schedule switch are in the on state, the controller obtains the schedule status at the current moment from the slice library and pushes the schedule at that moment after multi-dimensional decision-making; the controller pushes the schedule information to the schedule executor to realize the update of the intelligent schedule.

Images