Smart home system control method and device, electronic equipment and smart home system

Abstract

The invention discloses a smart home system control method and device, electronic equipment and a smart home system, and belongs to the field of air conditioner control. Firstly, a PMV calculation formula is constructed based on target parameters, a PMV model is obtained through training, then a first PMV value is obtained through calculation according to the PMV calculation formula, and a second PMV value is obtained according to the PMV model; and integrating the first PMV value and the second PMV value to obtain a target PMV value, and controlling equipment in the smart home system based on the target PMV value and the actual target parameter. According to the scheme, the target PMV value is obtained in two modes, so that the problem that formula calculation depends on fixed parameter setting, and consequently the obtained PMV does not conform to the actual situation is solved, the obtained target PMV value is accurate, and the control effect is better.

Description

Technical Field

[0001] The present application relates to the field of air conditioning control technology, and in particular, to a smart home system control method, device, electronic device and a smart home system. Background Art

[0002] PMV (Predicted Mean Vote), the predicted mean vote, is a comprehensive evaluation index based on the basic equation of human thermal balance and the level of subjective thermal sensation in psychophysiology, and takes into account many relevant factors of human thermal comfort. The PMV index shows the average index of the group's votes for seven levels of thermal sensation (-3 to +3).

[0003] The PMV index is derived by introducing the human body heat load TL, which reflects the degree of deviation from the human body's thermal balance. Its theoretical basis is that when the human body is in a steady-state thermal environment, the greater the human body's heat load, the further the human body deviates from the state of thermal comfort. That is, the greater the positive value of the human body heat load, the hotter the person feels, and the greater the negative value, the colder the person feels;

[0004] In the prior art, some air conditioning systems are designed with PMV in mind, and the PMV value is calculated using a preset formula, and the air conditioner is controlled according to the PMV value to improve the thermal comfort of the user. However, these formula calculations rely on fixed parameter settings, resulting in the PMV obtained not being consistent with the actual situation, so that the control effect of the air conditioner is poor. Summary of the invention

[0005] In order to overcome the deficiencies of the prior art, the present application provides a smart home system control method, device, electronic device and smart home system to solve the problem that some air conditioning systems in the prior art take PMV into consideration when designing, calculate the PMV value by a preset formula, and control the air conditioner according to the PMV value to improve the thermal comfort of the user. However, these formula calculations rely on fixed parameter settings, resulting in the PMV obtained not being consistent with the actual situation, so that the control effect is poor when controlling the air conditioner.

[0006] The technical solution adopted by this application to solve its technical problem is:

[0007] In a first aspect, a smart home system control method is provided, comprising:

[0008] A PMV calculation formula is constructed based on target parameters, and a PMV model is obtained through training. The target parameters include parameters in three dimensions: environmental parameters, human body parameters, and clothing thermal resistance;

[0009] Acquire actual target parameters, and input the actual target parameters into the PMV calculation formula and the PMV model respectively to obtain a first PMV value and a second PMV value;

[0010] Obtaining a target PMV value based on the first PMV value and the second PMV value;

[0011] Devices in the smart home system are controlled based on the target PMV value and the actual target parameter.

[0012] Further, the PMV model includes an input layer, a hidden layer and an output layer;

[0013] The input layer includes n dimensions, where n=p*q, where p is the number of data categories of the actual target parameter based on time, and q is the number of sub-dimensions of the actual target parameter;

[0014] The hidden layer consists of three fully connected layers, each with 128, 64, and 32 neurons. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer.

[0015] The softmax function is used to convert the activation values ​​of the output layer neurons into a probability distribution.

[0016] Furthermore, the PMV calculation formula is as follows:

[0017] PMV1=[a*exp(-b*M)+c]{MWd[ef(MW)-Pa]-h*(MWg)-i*M(h-Pa)-j*M(v-ta)-k*fcl*[(tcl+m)-(+m)]-fcl*hc(tcl-ta)};

[0018] Among them, PMV1 is the first PMV value, a, b, d, f, h, i, j, k are preset coefficients; c, e, g, m and v are preset values, M is the human body energy metabolism rate, W is the mechanical work done by the human body, ta is the indoor air temperature, rh is the relative humidity, Pa is the atmospheric pressure, hc is the convection heat transfer coefficient, tcl is the radiation temperature, and fcl is the thermal resistance of the clothing.

[0019] Further, obtaining a target PMV value based on the first PMV value and the second PMV value includes:

[0020] Target PMV value=first weight*first PMV value+second weight*second PMV value.

[0021] Furthermore, it also includes:

[0022] Obtaining an evaluation index of the PMV model, wherein the evaluation index includes at least one of the following: accuracy, precision, and F1 value;

[0023] The value of the second weight is determined based on the evaluation index.

[0024] Furthermore, controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes:

[0025] When the absolute value of the target PMV value is greater than the preset PMV value, obtaining the indoor enthalpy value and the outdoor enthalpy value;

[0026] When the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements, the windows are closed and the device is controlled according to the actual target parameters; when the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements, the windows are opened for continuous ventilation for the preset ventilation duration.

[0027] Further, controlling the device according to the actual target parameter includes:

[0028] When the indoor temperature is not equal to the set temperature:

[0029] If the target PMV value is greater than 0, the air outlet temperature of the air conditioner outlet is increased at a first preset rate until the indoor temperature is equal to the set temperature;

[0030] If the target PMV value is less than 0, the air outlet temperature of the air-conditioning outlet is reduced at a second preset rate until the indoor temperature is equal to the set temperature.

[0031] Furthermore, it also includes:

[0032] First preset rate=first preset coefficient*(target PMV value-preset PMV value);

[0033] And / or, the second preset rate=the second preset coefficient*(-target PMV value).

[0034] Further, controlling the device according to the actual target parameter includes:

[0035] When the indoor temperature is equal to the set temperature:

[0036] If the indoor air speed is greater than the preset speed, the air outlet speed of the air conditioner is reduced at a third preset rate;

[0037] And / or, if the indoor humidity is less than a first preset humidity, the humidifier is controlled to continue humidifying for a preset humidification duration; if the indoor humidity is greater than or equal to the first preset humidity and less than or equal to a second preset humidity, the current humidity is maintained; if the indoor temperature is greater than the second preset humidity, the dehumidifier is controlled to continue dehumidifying for a preset dehumidification duration.

[0038] Furthermore, it also includes:

[0039] Preset humidification duration = preset humidification coefficient * (first preset humidity - indoor humidity);

[0040] And / or, preset dehumidification duration=preset dehumidification coefficient*(indoor humidity-second preset humidity).

[0041] Furthermore, it also includes:

[0042] Obtaining an absolute value of a difference between the indoor enthalpy value and the outdoor enthalpy value;

[0043] The product of the absolute value and the preset ventilation coefficient is taken as the preset ventilation duration time.

[0044] Furthermore, it also includes:

[0045] When the target PMV value is greater than 0, if the outdoor enthalpy value is greater than the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirement; if the outdoor enthalpy value is less than or equal to the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirement;

[0046] When the target PMV value is less than 0, if the indoor enthalpy value is greater than the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements; if the indoor enthalpy value is less than or equal to the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements.

[0047] Furthermore, controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes:

[0048] When the absolute value of the target PMV value is less than or equal to the preset PMV value, the current state is maintained unchanged.

[0049] Furthermore, the target parameters include parameters in three dimensions: environmental parameters, human body parameters and clothing thermal resistance.

[0050] Further, when the target parameter is clothing thermal resistance, obtaining the actual target parameter includes:

[0051] Obtain current season information and clothing information of target people indoors;

[0052] Obtaining a season coefficient based on the current season information, and obtaining a clothing coefficient based on the clothing information;

[0053] The thermal resistance of clothing is obtained based on the season coefficient and the clothing coefficient, and the calculation formula is as follows:

[0054] Clothing thermal resistance = season coefficient * clothing coefficient * preset basic value.

[0055] In a second aspect, a smart home system control device is provided, comprising:

[0056] A formula and model module, used to construct a PMV calculation formula based on target parameters and train a PMV model, wherein the target parameters include parameters in three dimensions: environmental parameters, human body parameters, and clothing thermal resistance;

[0057] A PMV value acquisition module, used for acquiring actual target parameters, and inputting the actual target parameters into the PMV calculation formula and the PMV model to obtain a first PMV value and a second PMV value;

[0058] a target value calculation module, configured to obtain a target PMV value based on the first PMV value and the second PMV value;

[0059] A device control module is used to control the devices in the smart home system based on the target PMV value and the actual target parameter.

[0060] According to a third aspect, an electronic device is provided, including:

[0061] at least one processor and at least one memory;

[0062] The memory stores executable instructions of the processor;

[0063] The processor is configured to execute the above-mentioned smart home system control method.

[0064] In a fourth aspect, a smart home system is provided, applying the above-mentioned smart home system control method.

[0065] Beneficial effects:

[0066] The technical solution of the present application provides a smart home system control method, device, electronic device and smart home system. First, a PMV calculation formula is constructed based on the target parameters and a PMV model is obtained through training. Then, a first PMV value is calculated according to the PMV calculation formula, and a second PMV value is obtained according to the PMV model. The target PMV value is obtained by combining the first PMV value and the second PMV value, and the equipment in the smart home system is controlled based on the target PMV value and the actual target parameters. The present application adopts two methods to obtain the target PMV value to solve the problem that the formula calculation depends on fixed parameter settings, resulting in the obtained PMV not being consistent with the actual situation. The obtained target PMV value is accurate and the control effect is better. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 is a flow chart of a smart home system control method provided by an embodiment of the present application;

[0069] Figure 2 is a schematic diagram of an initial neural network structure provided in an embodiment of the present application;

[0070] Figure 3 is a schematic diagram of a final PMV model structure provided in an embodiment of the present application;

[0071] Figure 4 is a flowchart of a specific smart home system control method provided by an embodiment of the present application;

[0072] Figure 5 It is a schematic diagram of the structure of a smart home system control device provided in an embodiment of the present application;

[0073] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0075] Reference Figure 1 , the embodiment of the present application provides a smart home system control method, comprising:

[0076] S11: constructing a PMV calculation formula based on target parameters and training to obtain a PMV model, wherein the target parameters include parameters in three dimensions: environmental parameters, human body parameters, and clothing thermal resistance;

[0077] The environmental parameter dimensions include but are not limited to the following sub-dimensions: indoor temperature, indoor humidity, outdoor temperature, outdoor humidity, air speed, and atmospheric pressure. They are obtained through sensors installed at corresponding locations or through the network.

[0078] The human body parameter dimension includes but is not limited to the following sub-dimensions: human body metabolic rate and mechanical work done by the human body. The human body metabolic rate is measured by radar, and the mechanical work done by the human body is obtained by obtaining the movement trajectory through radar or camera, and then calculated.

[0079] Wherein, the PMV model includes an input layer, a hidden layer and an output layer;

[0080] The input layer includes n dimensions, where n=p*q, where p is the number of data categories of the actual target parameter based on time, and q is the number of sub-dimensions of the actual target parameter; during data processing, the feature analysis is as comprehensive as possible for the accuracy of the prediction results and the stability of the model operation. The collected data includes the current time t, the previous time t-1... and the earlier time tm, a total of p categories, and q data sub-dimensions are collected respectively.

[0081] The hidden layer is a three-layer fully connected layer with 128, 64 and 32 neurons respectively. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer. The initial learning rate is set to 0.002, the number of training rounds is 150, and the batch size is 32. The initial network structure is as follows: Figure 1 shown.

[0082] Use the softmax function to convert the activation values ​​of the output layer neurons into probability distribution. Figure 3 shown.

[0083] The PMV calculation formula is as follows:

[0084] PMV1=[a*exp(-b*M)+c]{MWd[ef(MW)-Pa]-h*(MWg)-i*M(h-Pa)-j*M(v-ta)-k*fcl*[(tcl+m)-(+m)]-fcl*hc(tcl-ta)};

[0085] Among them, PMV1 is the first PMV value, a, b, d, f, h, i, j, k are preset coefficients; c, e, g, m and v are preset values, M is the human body energy metabolism rate, W is the mechanical work done by the human body, ta is the indoor air temperature, rh is the relative humidity, Pa is the atmospheric pressure, hc is the convection heat transfer coefficient, tcl is the radiation temperature, and fcl is the thermal resistance of the clothing.

[0086] S12: Acquire actual target parameters, and input the actual target parameters into the PMV calculation formula and the PMV model respectively to obtain a first PMV value and a second PMV value;

[0087] In one embodiment, when the target parameter is clothing thermal resistance, obtaining the actual target parameter includes:

[0088] Obtain current season information and clothing information of indoor target personnel; obtain a season coefficient based on the current season information, and obtain a clothing coefficient based on the clothing information; obtain clothing thermal resistance based on the season coefficient and the clothing coefficient, and the calculation formula is as follows: clothing thermal resistance = season coefficient * clothing coefficient * preset basic value.

[0089] Since the clothing coefficient is obtained through user input or camera acquisition (such as the user inputs the clothes he or she wears or the camera acquires the clothes worn by the user, and then the clothing coefficient is obtained based on a preset correspondence), and since the camera authority also requires user authorization, in practice, the user may not give authorization and does not input clothing. Therefore, in another embodiment, when calculating the clothing coefficient, the clothing coefficient can use the default value, or the clothing coefficient can not be used.

[0090] In another embodiment, only the clothing coefficient may be used to calculate the clothing thermal resistance.

[0091] S13: Obtaining a target PMV value based on the first PMV value and the second PMV value;

[0092] Obtaining a target PMV value based on the first PMV value and the second PMV value includes:

[0093] Target PMV value=first weight*first PMV value+second weight*second PMV value.

[0094] In one embodiment, the first weight and the second weight are preset fixed values, and illustratively, the first weight=the second weight=0.5.

[0095] In another embodiment, an evaluation index of the PMV model is obtained, and the evaluation index includes at least one of the following: accuracy, precision and F1 value; the value of the second weight is determined based on the evaluation index. Because in practice, the quality of the PMV model obtained by training is uncertain. When the quality is good, the second weight can be larger, that is, the second weight is greater than the first weight. When the quality is small, the second weight can be smaller, that is, the second weight is smaller than the first weight. The specific value of the second weight is determined according to the preset corresponding relationship with the evaluation index. After determining the second weight, the first weight is determined. The first weight = 1-second weight.

[0096] S14: Controlling devices in the smart home system based on the target PMV value and the actual target parameter.

[0097] The controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes:

[0098] When the absolute value of the target PMV value is greater than the preset PMV value, the indoor enthalpy value and the outdoor enthalpy value are obtained; when the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements, the window is closed, and the device is controlled according to the actual target parameter; preferably, when the indoor temperature is not equal to the set temperature:

[0099] If the target PMV value is greater than 0, the air outlet temperature of the air-conditioning outlet is increased at a first preset rate until the indoor temperature is equal to the set temperature; if the target PMV value is less than 0, the air outlet temperature of the air-conditioning outlet is reduced at a second preset rate until the indoor temperature is equal to the set temperature.

[0100] The first preset rate and the second preset rate may be preset fixed values, or may be calculated based on the target PMV value. For example, the first preset rate = the first preset coefficient * (target PMV value - preset PMV value); and / or the second preset rate = the second preset coefficient * (-target PMV value).

[0101] When the indoor temperature is equal to the set temperature:

[0102] If the indoor air speed is greater than the preset speed, the air outlet speed of the air conditioner is reduced at a third preset rate; and / or, if the indoor humidity is less than the first preset humidity, the humidifier is controlled to continue humidifying for the preset humidification duration; if the indoor humidity is greater than or equal to the first preset humidity and less than or equal to the second preset humidity, the current humidity is maintained; if the indoor temperature is greater than the second preset humidity, the dehumidifier is controlled to continue dehumidifying for the preset dehumidification duration.

[0103] In one embodiment, the preset humidification duration and the preset dehumidification duration are preset fixed values. In another embodiment, the preset humidification duration = preset humidification coefficient * (first preset humidity - indoor humidity;) and / or, the preset dehumidification duration = preset dehumidification coefficient * (indoor humidity - second preset humidity).

[0104] When the indoor enthalpy value and the outdoor enthalpy value meet preset requirements, the window is opened for continuous ventilation for a preset ventilation duration.

[0105] In one embodiment, the preset ventilation duration is a preset fixed value. In another embodiment, the absolute value of the difference between the indoor enthalpy value and the outdoor enthalpy value is obtained; and the product of the absolute value and the preset ventilation coefficient is used as the preset ventilation duration.

[0106] Also includes:

[0107] When the target PMV value is greater than 0, if the outdoor enthalpy value is greater than the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirement; if the outdoor enthalpy value is less than or equal to the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirement;

[0108] When the target PMV value is less than 0, if the indoor enthalpy value is greater than the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements; if the indoor enthalpy value is less than or equal to the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements.

[0109] The controlling of the devices in the smart home system based on the target PMV value and the actual target parameter includes:

[0110] When the absolute value of the target PMV value is less than or equal to the preset PMV value, the current state is maintained unchanged.

[0111] In order to more clearly illustrate the present application scheme, the present application also provides a specific implementation method, including the following steps:

[0112] 1 Data Processing

[0113] 1.1 Data Preparation

[0114] Indoor and outdoor sensor parameters: indoor temperature, indoor humidity, outdoor temperature, outdoor humidity;

[0115] WiFi obtains positioning, geographic information, weather information, and seasonal information;

[0116] Anemometer / wind speed sensor obtains air velocity;

[0117] Preferably, the season information is obtained through WIFI networking, and the thermal resistance of the clothing is calculated based on the season information. Secondarily, the thermal resistance of the clothing is obtained by an RGB camera combined with a target detection algorithm (optionally, to protect user privacy, the camera requires user authorization before it can be used, and the user can choose to turn off the camera and manually enter thermal resistance related parameters); or the thermal resistance of the clothing is determined based on both the season information and the clothing information obtained by the camera.

[0118] Radar acquires the degree of human activity and the number / density of people (usually UWB radar or millimeter wave radar);

[0119] Infrared sensor obtains human body / room area temperature;

[0120] PMV value (calculated by formula combined with neural network classification model).

[0121] Data collection can be carried out according to Table 1:

[0122] Table 1

[0123]

[0124]

[0125] 1.2 Calculation method of thermal resistance of clothing

[0126] Clothing thermal resistance RCL is an indicator of clothing insulation performance, which is used to evaluate the ability of the human body to block heat flow when wearing clothing. The following is a calculation method without a camera or without allowing the camera to obtain images, which is used to calculate the value of clothing thermal resistance based on season information and clothing information. Clothing thermal resistance calculation formula:

[0127] fcl = S*T_season

[0128] Where: S is the seasonal coefficient, which is adjusted according to different seasons and has the following values: winter: S = 1.5; spring: S = 1.0; summer: S = 0.5; autumn: S = 1.0.

[0129] S2 is the clothing coefficient, which is adjusted according to different clothing. The values ​​are as follows: Down jacket:

[0130] T_season is the seasonal temperature index, which is set based on historical climate data and has the following values:

[0131] Winter: T_season = 20 (assuming the average temperature in winter is lower)

[0132] Spring: T_season = 10 (the temperature in spring is moderate)

[0133] Summer: T_season = 5 (higher temperatures in summer)

[0134] Autumn: T_season = 10 (the temperature in autumn is moderate).

[0135] Calculation example: Assuming that it is winter now, according to the above formula and coefficient, the thermal resistance of clothing is calculated as follows: fcl = 1.5*T_season, substitute the winter value of T_season into: fcl = 1.5*20 = 30. This means that in winter, according to our formula, the thermal resistance value of clothing is 30.

[0136] 1.3 Calculation method of human energy metabolism rate

[0137] Let MetRate be the energy metabolism rate of human body (unit: W / m 2 ), REI is the radar energy index. Calculation formula:

[0138] MetRate=a1*REI*b1

[0139] Among them: a1 is the proportional coefficient, which we set to 0.1, b1 is the exponential coefficient, which we set to 1.5.

[0140] The value range of Radar Energy Index (REI): The normal monitoring range is 0 to 100.

[0141] Calculation example: Assuming that the value monitored by the radar is REI=50, the energy metabolism rate of the human body is calculated according to the above formula: MetRate=0.1*50*1.5, which means that the energy metabolism rate of the human body can be estimated based on the value monitored by the radar.

[0142] 1.4PMV calculation method

[0143] PMV (Predicted Mean Vote), predicted mean vote, is a comprehensive evaluation index based on the basic equation of human thermal balance and the level of psychophysiological subjective thermal sensation, and takes into account many relevant factors of human thermal comfort.

[0144] PMV1=[0.303exp(-0.036M)+0.0275]{MW-3.05[5.733-0.007(MW)-Pa]-0.42

[0145] (MW-58.2)-0.0173M(5.867-Pa)-0.0014M(34-ta)-

[0146] 3.9610fcl[(tcl+273)-(+273)]-fcl*hc(tcl-ta)}

[0147] Where M is the human energy metabolism rate, which is determined by the amount of human activity; W is the mechanical work done by the human body; both can be obtained by radar detection and side calculation. Indoor temperature, indoor humidity, outdoor temperature, outdoor humidity: These parameters will be used as ta (indoor air temperature) and rh (relative humidity) in the PMV formula. WiFi obtains positioning, geographic information, weather information, and seasonal information to obtain atmospheric pressure Pa, and convective heat transfer coefficient hc. Infrared sensors determine the environmental conditions around the human body, including radiation temperature tcl and clothing thermal resistance fcl. Clothing thermal resistance is usually determined by clothing material and thickness, which can be obtained by manual user input or by scanning clothing labels with a camera.

[0148] The thermal sensation corresponding to the PMV index is shown in Table 2 below:

[0149] Table 2

[0150] Thermal sensation hot warm Slightly warm Moderate Slightly cool cold cold PMV value 3 2 1 0 -1 -2 -3

[0151] In subsequent control, PMV=(PMV1 predicted by model+PMV2 calculated by formula) / 2.

[0152] 1.5 Enthalpy calculation

[0153] The enthalpy value in the air is generally used to refer to the total heat contained in the air. The enthalpy value is the capacity scale after the temperature and humidity in the unit air are combined. The symbol i is usually used to represent the enthalpy value, and the unit is kJ / kg; the symbol t is used to represent the air temperature, and the unit is ℃; the symbol d1 is used to represent the moisture content of the air, and the unit is kg. The calculation formula of the enthalpy value is as follows:

[0154] i=1.01t+(2490+1.84t)*d1

[0155] 1.6 Calculation methods of other indicators

[0156] Other indicators can be calculated in the above manner. If they cannot be calculated or are difficult to calculate in practice, specific default parameter values ​​can be set.

[0157] 2 Machine Learning Classification Algorithms

[0158] PMV is divided into two types: calculated PMV (i.e., the first PMV value) and model-predicted PMV (i.e., the second PMV value). The two are combined to output the average value, which improves the calculation and prediction stability of PMV. The above-mentioned specific PMV calculation formula is usually difficult to use for many sensors in practical applications due to cost and other issues, and most of them are default setting parameters. Therefore, the alternative PMV calculation method is the neural network classification algorithm. The average of the formula calculation result and the algorithm classification result can be used to obtain the corrected PMV value.

[0159] In the process of data processing, in order to ensure the accuracy of the prediction results and the stability of the model operation, the feature analysis is as comprehensive as possible. The collected data includes the current time t, the previous time t-1... and the earlier time tm, a total of p categories, and q data dimensions are collected respectively, as shown in Table 3:

[0160] Table 3

[0161]

[0162] The total input dimension is p*q=n-dimensional input, and the output is a one-dimensional PMV. Train the multi-layer perception mechanism and use the TensorFlow machine learning training platform for model training. Input layer: contains n inputs, set according to specific needs; output layer: contains 4 neurons, and uses the softmax function to convert the activation value of the output layer neuron into a probability distribution. There are 3 hidden layers, which have 128, 64 and 32 neurons respectively. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer. The initial learning rate is set to 0.002, the number of training rounds is 150, and the batch size is 32. The specific network structure is as follows Figure 2 shown.

[0163] The hidden layer in the middle is a three-layer fully connected layer, and the fully connected layer uses the ReLU activation function. However, in the PMV prediction task, what needs to be predicted is the specific 7 classification values ​​from -3 to 3, which is a classification problem. The network structure can be Figure 3 As shown, the specific structure is as follows:

[0164] Input layer: The input layer receives the aforementioned relevant raw data.

[0165] Fully connected layers: From the input to the output, the three fully connected layers have 128, 64, and 32 neurons respectively.

[0166] Output layer: Finally, depending on the type of prediction task, a Softmax output layer is used to generate the final prediction results.

[0167] In this task, the goal of the model is to learn the relationship between environmental parameters and input features PMV, and optimize the network weights through training data so that the PMV parameters can be accurately predicted.

[0168] Control logic diagram Figure 4 As shown:

[0169] (1) Initial settings

[0170] Initial indoor temperature setting: Set to 26℃ to ensure a comfortable environment.

[0171] (2) PMV value detection and adjustment

[0172] When the indoor temperature is not equal to 26℃, if PMV>0.5: adjust the outlet temperature, increase the temperature to reduce the PMV value. Formula: ΔT=0.1(PMV-0.5)℃.

[0173] If -0.5≤PMV≤0.5: Maintain the current outlet temperature without changing it.

[0174] If PMV<-0.5: Reduce the outlet temperature to increase the PMV value. Formula: ΔT=0.1(-PMV)℃.

[0175] (3) Wind speed monitoring and adjustment

[0176] When the indoor temperature is 26℃, if V>0.8m / s: gradually reduce the wind speed to V≤0.8m / s. Adjustment steps: V_new=V-0.1m / s.

[0177] (4) Indoor humidity adjustment

[0178] When the indoor temperature is equal to 26°C, if Phi<45%: start the humidifier to supplement humidity. Humidification duration estimation: t_humidify = 60 (45-Phi) seconds.

[0179] If 45% ≤ Phi ≤ 65%: Maintain current humidity level and do not perform any operation.

[0180] If Phi > 65%: start dehumidifier to reduce humidity. Humidification duration estimation: t_dehumidify = 60(Phi - 65) seconds.

[0181] (5) Ventilation logic

[0182] Comparison of indoor and outdoor humidity and ventilation: Judgment condition: If ioutside>iinside and PMV>0, open the window for ventilation. Ventilation time estimation: t_ventilate=30|iinside-ioutside|minutes.

[0183] The comprehensive steps are as follows: Check PMV, wind speed, humidity, and gradually adjust various parameters. Through multi-dimensional control and regulation, the dimensions that mainly affect the PMV value are regulated to ensure indoor comfort. Dynamically update settings based on real-time data to continuously optimize the indoor environment. This logic design ensures automatic adjustment and optimization of the indoor environment under different conditions to improve living comfort and air quality.

[0184] The innovation of this application lies in its comprehensive use of advanced sensor technology, machine learning algorithms and dynamic control logic to achieve more efficient and personalized environmental control. First, by integrating radar monitoring and dynamic calculation of clothing thermal resistance, this proposal can more accurately assess human thermal comfort, which is a key factor in improving system performance. Secondly, the application of neural networks to optimize PMV improves the accuracy of prediction and the level of intelligence of environmental control. Finally, the implementation of dynamic environmental control logic based on real-time data ensures that the indoor environment can be adjusted instantly according to real-time monitoring data, thereby maximizing user comfort and energy efficiency.

[0185] The advantages of this application are as follows: 1) Dynamic clothing thermal resistance calculation, through seasonal information and RGB camera or user input, real-time adjustment of clothing thermal resistance, improving the accuracy of thermal comfort assessment; 2) Comprehensive environmental monitoring, integrating multiple sensors such as indoor and outdoor temperature, humidity, wind speed, etc., to provide more detailed environmental data; 3) Accurate PMV prediction, using neural network to optimize PMV calculation, enhancing the accuracy and adaptability of prediction; 4) Intelligent control logic, dynamically adjusting environmental settings based on real-time data, achieving more flexible environmental control. These advantages are derived from the use of advanced sensor integration, machine learning algorithms and intelligent control strategies.

[0186] Based on the same inventive concept, Figure 5 As shown, the embodiment of the present application further provides a smart home system control device 50, comprising:

[0187] A formula and model module 51 is used to construct a PMV calculation formula based on target parameters and train a PMV model, wherein the target parameters include parameters in three dimensions: environmental parameters, human body parameters, and clothing thermal resistance;

[0188] Wherein, the PMV model includes an input layer, a hidden layer and an output layer;

[0189] The input layer includes n dimensions, where n=p*q, where p is the number of data categories of the actual target parameter based on time, and q is the number of sub-dimensions of the actual target parameter;

[0190] The hidden layer consists of three fully connected layers, each with 128, 64, and 32 neurons. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer.

[0191] The softmax function is used to convert the activation values ​​of the output layer neurons into a probability distribution.

[0192] The PMV calculation formula is as follows:

[0193] PMV1=[a*exp(-b*M)+c]{MWd[ef(MW)-Pa]-h*(MWg)-i*M(h-Pa)-j*M(v-ta)-k*fcl*[(tcl+m)-(+m)]-fcl*hc(tcl-ta)};

[0194] Among them, PMV1 is the first PMV value, a, b, d, f, h, i, j, k are preset coefficients; c, e, g, m and v are preset values, M is the human body energy metabolism rate, W is the mechanical work done by the human body, ta is the indoor air temperature, rh is the relative humidity, Pa is the atmospheric pressure, hc is the convection heat transfer coefficient, tcl is the radiation temperature, and fcl is the thermal resistance of the clothing.

[0195] The PMV value acquisition module 52 is used to acquire actual target parameters, and input the actual target parameters into the PMV calculation formula and the PMV model to obtain a first PMV value and a second PMV value.

[0196] When the target parameter is clothing thermal resistance, obtaining the actual target parameter includes:

[0197] Obtain current season information and clothing information of target people indoors;

[0198] Obtaining a season coefficient based on the current season information, and obtaining a clothing coefficient based on the clothing information;

[0199] The thermal resistance of clothing is obtained based on the season coefficient and the clothing coefficient, and the calculation formula is as follows:

[0200] Clothing thermal resistance = season coefficient * clothing coefficient * preset basic value.

[0201] In actual use, the preset basic value can also be determined based on only one of the current season information or clothing information, or directly input by the user. The preset basic value can be the same value for all seasons, or different values ​​can be set for different seasons.

[0202] A target value calculation module 53, configured to obtain a target PMV value based on the first PMV value and the second PMV value;

[0203] The obtaining a target PMV value based on the first PMV value and the second PMV value includes:

[0204] Target PMV value=first weight*first PMV value+second weight*second PMV value.

[0205] In one embodiment, the first weight and the second weight are preset fixed values.

[0206] In another embodiment, an evaluation index of the PMV model is obtained, and the evaluation index includes at least one of the following: accuracy, precision and F1 value;

[0207] The value of the second weight is determined based on the evaluation index. The first weight = 1 - the second weight.

[0208] The device control module 54 is used to control the devices in the smart home system based on the target PMV value and the actual target parameter.

[0209] The controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes:

[0210] When the absolute value of the target PMV value is greater than the preset PMV value, obtaining the indoor enthalpy value and the outdoor enthalpy value;

[0211] When the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements, the windows are closed and the device is controlled according to the actual target parameters; when the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements, the windows are opened for continuous ventilation for the preset ventilation duration.

[0212] Wherein, controlling the device according to the actual target parameter includes:

[0213] When the indoor temperature is not equal to the set temperature:

[0214] If the target PMV value is greater than 0, the air outlet temperature of the air conditioner outlet is increased at a first preset rate until the indoor temperature is equal to the set temperature;

[0215] If the target PMV value is less than 0, the air outlet temperature of the air-conditioning outlet is reduced at a second preset rate until the indoor temperature is equal to the set temperature.

[0216] In one embodiment, the first preset rate and the second preset rate are preset fixed values.

[0217] In another embodiment, it also includes:

[0218] First preset rate=first preset coefficient*(target PMV value-preset PMV value);

[0219] And / or, the second preset rate=the second preset coefficient*(-target PMV value).

[0220] Further, controlling the device according to the actual target parameter includes:

[0221] When the indoor temperature is equal to the set temperature:

[0222] If the indoor air speed is greater than the preset speed, the air outlet speed of the air conditioner is reduced at a third preset rate;

[0223] And / or, if the indoor humidity is less than a first preset humidity, the humidifier is controlled to continue humidifying for a preset humidification duration; if the indoor humidity is greater than or equal to the first preset humidity and less than or equal to a second preset humidity, the current humidity is maintained; if the indoor temperature is greater than the second preset humidity, the dehumidifier is controlled to continue dehumidifying for a preset dehumidification duration.

[0224] In one embodiment, the preset humidification duration and the preset dehumidification duration are preset fixed values.

[0225] In another embodiment, the preset humidification duration=preset humidification coefficient*(first preset humidity-indoor humidity);

[0226] And / or, preset dehumidification duration=preset dehumidification coefficient*(indoor humidity-second preset humidity).

[0227] In one embodiment, the preset ventilation duration is a preset fixed value.

[0228] In another embodiment, the absolute value of the difference between the indoor enthalpy value and the outdoor enthalpy value is obtained;

[0229] The product of the absolute value and the preset ventilation coefficient is taken as the preset ventilation duration time.

[0230] Also includes:

[0231] When the target PMV value is greater than 0, if the outdoor enthalpy value is greater than the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirement; if the outdoor enthalpy value is less than or equal to the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirement;

[0232] When the target PMV value is less than 0, if the indoor enthalpy value is greater than the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements; if the indoor enthalpy value is less than or equal to the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements.

[0233] When the absolute value of the target PMV value is less than or equal to the preset PMV value, the current state is maintained unchanged.

[0234] The smart home system control device provided in the embodiment of the present application first constructs a PMV calculation formula based on the target parameters and obtains a PMV model through training, then obtains a first PMV value according to the PMV calculation formula, and obtains a second PMV value according to the PMV model; obtains a target PMV value by combining the first PMV value and the second PMV value, and controls the devices in the smart home system based on the target PMV value and the actual target parameters. The present application scheme uses two methods to obtain the target PMV value to solve the problem that the formula calculation depends on fixed parameter settings, resulting in the obtained PMV not being consistent with the actual situation, and the obtained target PMV value is accurate and the control effect is better.

[0235] Based on the same inventive concept, Figure 6 As shown, the embodiment of the present application further provides an electronic device 60, including:

[0236] at least one processor 61 and at least one memory 62;

[0237] The memory stores executable instructions of the processor;

[0238] The processor is configured to execute the smart home system control method provided by the above embodiment.

[0239] The electronic device provided by the embodiment of the present application stores the executable instructions of the processor through the memory. When the executable instructions are executed, the processor can first construct a PMV calculation formula based on the target parameters and train to obtain a PMV model, then calculate a first PMV value according to the PMV calculation formula, and obtain a second PMV value according to the PMV model; the target PMV value is obtained by combining the first PMV value and the second PMV value, and the devices in the smart home system are controlled based on the target PMV value and the actual target parameters. The present application scheme adopts two methods to obtain the target PMV value to solve the problem that the formula calculation depends on fixed parameter settings, resulting in the obtained PMV not being consistent with the actual situation. The obtained target PMV value is accurate and the control effect is better.

[0240] Based on the same inventive concept, the present application also provides a smart home system, which applies the smart home system control method provided in the above embodiment.

[0241] The smart home system provided in the embodiment of the present application, by applying the smart home system control method provided in the above embodiment, can first construct a PMV calculation formula based on the target parameters and train to obtain a PMV model, then calculate a first PMV value according to the PMV calculation formula, and obtain a second PMV value according to the PMV model; combine the first PMV value and the second PMV value to obtain a target PMV value, and control the devices in the smart home system based on the target PMV value and the actual target parameters. The present application scheme adopts two methods to obtain the target PMV value to solve the problem that the formula calculation depends on fixed parameter settings, resulting in the obtained PMV not being consistent with the actual situation, and the obtained target PMV value is accurate and the control effect is better.

[0242] It should be noted that, in the description of this application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0243] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

Claims

1. A smart home system control method, It is characterized in that include: Construct a PMV calculation formula based on target parameters and train to obtain a PMV model; Acquire actual target parameters, and input the actual target parameters into the PMV calculation formula and the PMV model respectively to obtain a first PMV value and a second PMV value; Obtaining a target PMV value based on the first PMV value and the second PMV value; The devices in the smart home system are controlled based on the target PMV value and the actual target parameter.

2. The method according to claim 1, Features: The PMV model includes an input layer, a hidden layer and an output layer; The input layer includes n dimensions, where n=p*q, where p is the number of data categories of the actual target parameter based on time, and q is the number of sub-dimensions of the actual target parameter; The hidden layer consists of three fully connected layers, each with 128, 64, and 32 neurons. The hidden layer activation function uses ReLU, the loss function uses the cross entropy loss function, and the optimizer uses the Adam optimizer. The softmax function is used to convert the activation values ​​of the output layer neurons into a probability distribution.

3. The method according to claim 1, Features: The PMV calculation formula is as follows: PMV1=[a*exp(-b*M)+c]{MWd[ef(MW)-Pa]-h*(MWg)-i*M(h-Pa)-j*M(v-ta)-k*fcl*[(tcl+m)-(+m)]-fcl*hc(tcl-ta)}; Among them, PMV1 is the first PMV value, a, b, d, f, h, i, j, k are preset coefficients; c, e, g, m and v are preset values, M is the human body energy metabolism rate, W is the mechanical work done by the human body, ta is the indoor air temperature, rh is the relative humidity, Pa is the atmospheric pressure, hc is the convection heat transfer coefficient, tcl is the radiation temperature, and fcl is the thermal resistance of the clothing.

4. The method according to claim 1, Features: The obtaining a target PMV value based on the first PMV value and the second PMV value includes: Target PMV value=first weight*first PMV value+second weight*second PMV value.

5. The method according to claim 4, It is characterized in that Also includes: Obtaining an evaluation index of the PMV model, wherein the evaluation index includes at least one of the following: accuracy, precision, and F1 value; The value of the second weight is determined based on the evaluation index.

6. The method according to claim 1, Features: The controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes: When the absolute value of the target PMV value is greater than the preset PMV value, obtaining the indoor enthalpy value and the outdoor enthalpy value; When the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements, the windows are closed and the device is controlled according to the actual target parameters; when the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements, the windows are opened for continuous ventilation for the preset ventilation duration.

7. The method according to claim 6, Features: The controlling the device according to the actual target parameter comprises: When the indoor temperature is not equal to the set temperature: If the target PMV value is greater than 0, the air outlet temperature of the air conditioner outlet is increased at a first preset rate until the indoor temperature is equal to the set temperature; If the target PMV value is less than 0, the air outlet temperature of the air-conditioning outlet is reduced at a second preset rate until the indoor temperature is equal to the set temperature.

8. The method according to claim 7, It is characterized in that Also includes: First preset rate=first preset coefficient*(target PMV value-preset PMV value); And / or, the second preset rate=the second preset coefficient*(-target PMV value).

9. The method according to claim 6, Features: The controlling the device according to the actual target parameter comprises: When the indoor temperature is equal to the set temperature: If the indoor air speed is greater than the preset speed, the air outlet speed of the air conditioner is reduced at a third preset rate; And / or, if the indoor humidity is less than a first preset humidity, the humidifier is controlled to continue humidifying for a preset humidification duration; if the indoor humidity is greater than or equal to the first preset humidity and less than or equal to a second preset humidity, the current humidity is maintained; if the indoor temperature is greater than the second preset humidity, the dehumidifier is controlled to continue dehumidifying for a preset dehumidification duration.

10. The method according to claim 9, It is characterized in that Also includes: Preset humidification duration = preset humidification coefficient * (first preset humidity - indoor humidity); And / or, preset dehumidification duration=preset dehumidification coefficient*(indoor humidity-second preset humidity).

11. The method according to claim 6, It is characterized in that Also includes: Obtaining an absolute value of a difference between the indoor enthalpy value and the outdoor enthalpy value; The product of the absolute value and the preset ventilation coefficient is taken as the preset ventilation duration time.

12. The method according to claim 6, It is characterized in that Also includes: When the target PMV value is greater than 0, if the outdoor enthalpy value is greater than the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements; If the outdoor enthalpy value is less than or equal to the indoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirements; When the target PMV value is less than 0, if the indoor enthalpy value is greater than the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value meet the preset requirements; If the indoor enthalpy value is less than or equal to the outdoor enthalpy value, the indoor enthalpy value and the outdoor enthalpy value do not meet the preset requirement.

13. The method according to claim 1, It is characterized in that The controlling the devices in the smart home system based on the target PMV value and the actual target parameter includes: When the absolute value of the target PMV value is less than or equal to the preset PMV value, the current state is maintained unchanged.

14. The method according to claim 1, It is characterized in that The target parameters include parameters in three dimensions: environmental parameters, human body parameters and clothing thermal resistance.

15. The method according to claim 14, It is characterized in that When the target parameter is clothing thermal resistance, obtaining the actual target parameter includes: Obtain current season information and clothing information of target people indoors; Obtaining a season coefficient based on the current season information, and obtaining a clothing coefficient based on the clothing information; The thermal resistance of clothing is obtained based on the season coefficient and the clothing coefficient, and the calculation formula is as follows: Clothing thermal resistance = season coefficient * clothing coefficient * preset basic value.

16. A smart home system control device, It is characterized in that include: The formula and model module is used to construct the PMV calculation formula based on the target parameters and train the PMV model; A PMV value acquisition module, used for acquiring actual target parameters, and inputting the actual target parameters into the PMV calculation formula and the PMV model to obtain a first PMV value and a second PMV value; a target value calculation module, configured to obtain a target PMV value based on the first PMV value and the second PMV value; A device control module is used to control the devices in the smart home system based on the target PMV value and the actual target parameter.

17. An electronic device, It is characterized in that include: at least one processor and at least one memory; The memory stores executable instructions of the processor; The processor is configured to execute the method according to any one of claims 1-18.

18. A smart home system, It is characterized in that The method according to any one of claims 1 to 18 is used.

Images