A thermal comfort prediction method, device, equipment and storage medium
Calculate the thermal comfort prediction value through BP neural network, and solve the problems of PMV calculation complexity and time delay of thermal comfort index in the prior art, improve the efficiency and accuracy of thermal comfort prediction, and satisfy people's thermal comfort Demand.
Patent Information
- Application Number
- CN202111315089.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-11-08
AI Technical Summary
In the prior art, the calculation complexity and time delay of the thermal comfort index PMV lead to the inability to accurately evaluate and control, and cannot meet people's thermal comfort needs.
Using a pre-trained BP neural network, the comfort prediction evaluation value corresponding to each factor is calculated by obtaining multiple factors that affect thermal comfort, and combining these evaluation values to obtain thermal comfort prediction value, which improves prediction efficiency and accuracy. .
By deeply studying the impact of multiple influencing factors on the human body's thermal comfort level, the use of BP neural network improves the efficiency and accuracy of thermal comfort level prediction, and better meets people's thermal comfort needs.
Smart Images

Figure CN113919588B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the field of thermal comfort technology, and in particular to a thermal comfort prediction method, device, equipment and storage medium. Background Art
[0002] Indoor thermal and humid environment refers to the physical environment formed by indoor temperature and relative humidity that people feel most intuitively. People's feeling about indoor thermal and humid environment is called indoor thermal comfort (abbreviated as thermal comfort), and the quantitative standard of thermal comfort is called thermal comfort index.
[0003] In the related art, the PMV value is calculated by the thermal comfort index PMV equation. However, due to the complexity, nonlinearity and time lag of the thermal comfort index PMV equation calculation itself, it is impossible to make an accurate assessment, and thus it is impossible to accurately control the thermal comfort index PMV and reasonably meet people's thermal comfort needs. Summary of the invention
[0004] The present invention provides a thermal comfort prediction method, device, equipment and storage medium to improve the thermal comfort prediction efficiency and accuracy to better meet people's thermal comfort needs.
[0005] In a first aspect, an embodiment of the present invention provides a thermal comfort prediction method, comprising:
[0006] Obtain multiple factors affecting thermal comfort;
[0007] Inputting the plurality of influencing factors into a pre-trained BP neural network for processing, and calculating the predicted evaluation value of comfort corresponding to each of the influencing factors;
[0008] The predicted value of thermal comfort is obtained by combining the predicted evaluation values of comfort corresponding to the influencing factors.
[0009] Optionally, the influencing factors include: environmental factors and human factors;
[0010] The environmental factors include: operating temperature, humidity, wind speed, light, mean radiant temperature and color temperature;
[0011] The human factors include: human metabolic rate, clothing thermal resistance and external mechanical work.
[0012] Optionally, the operating temperature is calculated by the following formula:
[0013]
[0014] Among them, t o is the operating temperature, t a is the temperature of the ambient air, hc is the convective heat transfer coefficient, h r is the radiation heat transfer coefficient, is the average radiant temperature of a human body in a sitting position;
[0015] Among them, the average radiation temperature of the human body in a sitting position is calculated by the following formula:
[0016]
[0017] Among them, t up ,t down ,t right ,t left ,t front ,t back They are the surface temperatures of the upper, lower, right, left, front and rear walls of the human body respectively.
[0018] Optionally, the plurality of influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of comfort corresponding to each of the influencing factors is calculated, including:
[0019] The predicted evaluation value of comfort corresponding to the operating temperature is calculated using the following formula:
[0020] y 1A =-18.004+1.642t o -0.038t o 2
[0021] y 1B =-84.130+6.834t o -0.139t o 2
[0022] Among them, y 1A ,y 1B are the predicted evaluation values of comfort corresponding to the operating temperature under winter and summer conditions, t o is the operating temperature.
[0023] Optionally, the plurality of influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of comfort corresponding to each of the influencing factors is calculated, including:
[0024] The predicted evaluation value of comfort corresponding to humidity is calculated using the following formula:
[0025]
[0026] Among them, y 2 is the predicted evaluation value of comfort corresponding to humidity, h uis the relative humidity.
[0027] Optionally, the plurality of influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of comfort corresponding to each of the influencing factors is calculated, including:
[0028] The predicted evaluation value of comfort corresponding to lighting is calculated using the following formula:
[0029] y 3 =-4.573+0.012E-9.206×10 -6 E 2
[0030] Among them, y 3 is the predicted evaluation value of comfort corresponding to the lighting, and E is the illumination.
[0031] Optionally, the plurality of influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of comfort corresponding to each of the influencing factors is calculated, including:
[0032] The predicted evaluation value of comfort corresponding to color temperature is calculated using the following formula:
[0033] y 4 =-2.662e-7X 2 +0.002048X-4.86
[0034] Among them, y 4 is the predicted evaluation value of comfort corresponding to color temperature, e is a natural number, and X is the color temperature value.
[0035] Optionally, the predicted value of thermal comfort is obtained by combining the predicted evaluation values of comfort corresponding to the influencing factors, including:
[0036] The utility function comprehensive evaluation method is used to comprehensively evaluate the predicted evaluation values of comfort corresponding to the influencing factors to obtain the predicted value of thermal comfort. The utility function formula is as follows:
[0037] C = ξ(y i ,ω i )
[0038] Among them, C is the predicted value of thermal comfort, y i is the predicted evaluation value of comfort corresponding to each of the influencing factors, ω i is the weight value of the predicted evaluation value of comfort corresponding to each of the influencing factors, ξ is y i and ω i The comprehensive function model.
[0039] In a second aspect, an embodiment of the present invention further provides a thermal comfort prediction device, comprising:
[0040] An influencing factor acquisition module is used to obtain multiple influencing factors affecting thermal comfort;
[0041] A calculation module, used for inputting the plurality of influencing factors into a pre-trained BP neural network for processing, and calculating a predicted evaluation value of comfort corresponding to each of the influencing factors;
[0042] The comprehensive prediction module is used to obtain a thermal comfort prediction value by comprehensively analyzing the predicted evaluation values of comfort corresponding to the influencing factors.
[0043] In a third aspect, an embodiment of the present invention further provides a computer device, including:
[0044] one or more processors;
[0045] A storage device for storing one or more programs;
[0046] When the one or more programs are executed by the one or more processors, the one or more processors implement the thermal comfort prediction method provided in the first aspect of the present invention.
[0047] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the thermal comfort prediction method provided in the first aspect of the present invention.
[0048] The thermal comfort prediction method provided by the embodiment of the present invention includes: obtaining multiple influencing factors affecting thermal comfort, inputting the multiple influencing factors into a pre-trained BP neural network for processing, calculating the predicted evaluation value of comfort corresponding to each influencing factor, and synthesizing the predicted evaluation value of comfort corresponding to each influencing factor to obtain a predicted value of thermal comfort. The BP neural network is used to deeply study the influence of multiple influencing factors on human thermal comfort, and the predicted evaluation value of comfort corresponding to each influencing factor is synthesized to obtain a predicted value of thermal comfort, thereby improving the efficiency and accuracy of thermal comfort prediction to better meet people's thermal comfort needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] Figure 1A A flowchart of a thermal comfort prediction method provided in Embodiment 1 of the present invention;
[0050] Figure 1B A schematic diagram of the structure of a BP neural network provided by an embodiment of the present invention;
[0051] Figure 1C Schematic diagram of the change of average wet sensation of human body under different humidity environments;
[0052] Figure 1D This is the composition diagram of the indoor light environment;
[0053] Figure 1E A relationship diagram of illumination, color temperature and comfort provided by an embodiment of the present invention;
[0054] Figure 2 A schematic diagram of the structure of a thermal comfort prediction device provided in Embodiment 2 of the present invention;
[0055] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0056] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0057] Embodiment 1
[0058] Figure 1A This is a flow chart of a thermal comfort prediction method provided in the first embodiment of the present invention. This embodiment is applicable to thermal comfort prediction in a space. The method can be executed by a thermal comfort prediction device provided in the embodiment of the present invention. The device can be implemented in software and / or hardware, and is usually configured in a computer device, such as Figure 1A As shown, the method specifically comprises the following steps:
[0059] S101. Obtain multiple influencing factors affecting thermal comfort.
[0060] Professor Fanger collected data from 1,393 American and Danish subjects, and comprehensively considered the impact of indoor environmental factors (air temperature, relative humidity, indoor wind speed, indoor average radiant temperature) and two non-environmental factors (human metabolic rate, clothing thermal resistance) on human comfort, and obtained the predicted mean voting index PMV, which represents the comfort feeling of most people in the environment. Under normal circumstances, the human body needs to satisfy the relationship of maintaining thermal balance:
[0061] S=MWCRE
[0062] In the formula, S represents the heat requirement of the human body, in W / m2; M represents the metabolic rate of the human body, in W / m2; W represents the external mechanical work of the human body, in W / m2; C represents the convective heat transfer, in W / m2; R represents the radiation heat dissipation, in W / m2; E represents the evaporative heat dissipation, in W / m2.
[0063] The metabolic rate of the human body usually changes with the amount of activity, age, environment, etc. The indirect method is often used to calculate the formula:
[0064]
[0065] RQ is the respiratory entropy of a person; is the volume of oxygen inhaled by the human body, in ml / s; A D Refers to the skin surface area of the human body, measured in m 2 .
[0066] The convective heat transfer C can be expressed by Newton's heat transfer formula:
[0067] C = f cl h c (t cl -t cl )
[0068] In the formula, f cl Refers to the area coefficient of human clothing.
[0069]
[0070] In the formula, I cl is the thermal resistance of human clothing, in m 2 K / W; h c is the convective heat transfer coefficient, W / (m 2 ·K).
[0071]
[0072] In the formula, v ar is the indoor wind speed, m / s; t cl It is the outer surface temperature of human clothing.
[0073] t cl =35.7-0.028(MW)-I c {(3.96×10 -8 )f cl [(t cl +273) 4 -(t r +273) 4 ]+f cl h c (t cl -t a )}
[0074] Where, t a The temperature of the environment surrounding the human body.
[0075] Radiation heat transfer can be expressed by the following formula:
[0076] R=ξf cl f eff σ[(t cl+273.15) 4 -(t r +273.15) 4 ]
[0077] Where ξ is the emissivity of the radiating surface, f eff is the effective area correction coefficient; t r It is the average radiant temperature of the room where the human body is located.
[0078] The calculation formula for evaporative heat dissipation is:
[0079] E=C res +E res +E df +E rsw
[0080] In the formula, C res It indicates the dampness and heat of human body breathing.
[0081] C res =0.0014M(34-t a )
[0082] E res Indicates the heat of human breathing, in W / m 2 ;P a The partial pressure of water vapor around the human body.
[0083] E res =0.00173M(5.867-P a )
[0084] E dif Indicates the evaporative heat loss from the skin surface, in W / m 2 .
[0085] E dif =3.05(0.25t sk -3.335-P a )
[0086] Where, t sk Indicates the average skin temperature of the human body, in W / m 2 .
[0087] t sk =35.7-0.0275(MW)
[0088] E rsw Indicates the heat generated by sweat on the skin surface, unit is W / m 2 .
[0089] E rsw =0.42(MW-58.2)
[0090] Based on the above formulas, when the human body reaches a steady-state condition, the derivation formula of PMV is as follows:
[0091] PMV=(0.303e (-0.036M) +0.028){(MW)-3.05×10 -3 ×[5733-6.99(MW)-P a ]-0.42×[(MW)-58.15]-1.73×10 -5 M(5876-P a )-0.0014M(34-t a )-3.96×10 -8 f cl [(t cl +273) 4 -(t r +273) 4 ]-f d h c (t cl -t a )}
[0092] To sum up, Professor Fanger divides the factors that affect the comfort of the indoor environment into the results of the joint action of the following 6 variables. It can be clearly seen that as long as these data are obtained, the thermal comfort PMV can be calculated through the formula.
[0093] In existing research, most methods for calculating PMV indicators use simplified calculation methods, but such simplified methods will lose some information. There are also other simplified methods that will affect the calculation of PMV values.
[0094] Exemplarily, in the embodiment of the present invention, the influencing factors include: environmental factors and human factors. The environmental factors include: operating temperature, humidity, wind speed, light, average radiation temperature and color temperature; the human factors include: human metabolic rate, clothing thermal resistance and external mechanical work.
[0095] In order to simplify the description of thermal comfort, the operating temperature to is used to describe the thermal comfort of the indoor environment under most indoor conditions. The operating temperature to is used as the main parameter to describe the thermal environment, which can reflect the combined effect of convection and radiation on the subject in the thermal environment. The expression of the operating temperature is as follows:
[0096]
[0097] Among them, t o is the operating temperature, t a is the temperature of the ambient air, h c is the convective heat transfer coefficient, h ris the radiation heat transfer coefficient, is the average radiant temperature of a human body in a sitting position.
[0098] Among them, the average radiation temperature of the human body in a sitting position is calculated by the following formula:
[0099]
[0100] Among them, t up ,t down ,t right ,t left ,t front ,t back They are the surface temperatures of the upper, lower, right, left, front and rear walls of the human body respectively.
[0101] In the expression of operating temperature, the convective heat transfer coefficient h c The value reflects the influence of air flow speed. When the relative humidity is in the range of 20% to 70%, the human body can hardly feel the change of relative humidity. At the same time, when the pressure is not too low, the change of water vapor partial pressure is not obvious. Therefore, it is accurate to describe thermal comfort with operating temperature.
[0102] S102: Input multiple influencing factors into a pre-trained BP neural network for processing, and calculate the predicted evaluation value of comfort corresponding to each influencing factor.
[0103] The basic structure of the nervous system is the neuron (nerve cell), which is the basic unit for processing information transmission between various parts of the human body. It is composed of many interconnected processing units. These processing units are usually arranged linearly in groups, called layers. Each processing unit has many input quantities, and each input quantity has an associated weight. The processing unit sums the input quantity through weighted summation, and obtains the output quantity through the action of the transfer function, and then transmits it to the neurons in the next layer.
[0104] The basic BP algorithm includes two aspects: forward propagation of signals and backward propagation of errors. That is, the actual output is calculated from input to output, while the weights and thresholds are corrected from output to input.
[0105] Figure 1B A schematic diagram of the structure of a BP neural network provided by an embodiment of the present invention is shown in FIG. Figure 1B As shown, x j represents the input (i.e., influencing factor) of the jth node in the input layer, j = 1,…,M; w ij represents the weight between the i-th node in the hidden layer and the j-th node in the input layer; θ i represents the threshold of the i-th node in the hidden layer; φ(x) represents the activation function of the hidden layer; w kirepresents the weight between the kth node in the output layer and the ith node in the hidden layer, i = 1,…,q; a k represents the threshold of the kth node in the output layer, k = 1,…,L; ψ(x) represents the activation function of the output layer; o k Represents the output of the kth node in the output layer.
[0106] (1) Signal forward propagation process
[0107] The input net of the i-th node in the hidden layer i :
[0108]
[0109] The output y of the i-th node in the hidden layer i :
[0110]
[0111] The input net of the kth node in the output layer k :
[0112]
[0113] The output o of the kth node in the output layer k :
[0114]
[0115] (2) Error back propagation process
[0116] The back propagation of the error, that is, first starting from the output layer, calculates the output error of each layer of neurons layer by layer, and then adjusts the weights and thresholds of each layer according to the error gradient descent method, so that the final output of the modified network can be close to the expected value.
[0117] For each sample p, the quadratic error criterion function is E p :
[0118]
[0119] The total error criterion function of the system for P training samples is:
[0120]
[0121] According to the error gradient descent method, the correction value Δw of the output layer weight is corrected in sequence ki , the correction amount Δa of the output layer threshold k , the correction value Δw of the hidden layer weight ij , the correction value Δθ of the hidden layer threshold i .
[0122]
[0123] Output layer weight adjustment formula:
[0124]
[0125] Output layer threshold adjustment formula:
[0126]
[0127] Hidden layer weight adjustment formula:
[0128]
[0129] Hidden layer threshold adjustment formula:
[0130]
[0131] And because:
[0132]
[0133]
[0134]
[0135]
[0136]
[0137] So we finally get the following formula:
[0138]
[0139]
[0140]
[0141]
[0142] In an embodiment of the present invention, the dimensionless function of the thermal environment index is discussed. In the comfort zone diagram of the latest ASHRAE indoor thermal environment standard 55-2013, there is a significant difference from the comfort zones of the effective temperature, standard effective temperature and new effective temperature given by ASHRAE before, that is, the comfort zone is divided into two parts, namely the winter working condition comfort zone and the summer working condition comfort zone. It shows that there are differences in temperature and humidity parameters and clothing thermal resistance in the comfort zones of winter and summer. There are also different provisions for the comfort zones of winter and summer in the current standards of our country. Based on this, the dimensionless functions of the thermal environment under winter and summer working conditions should be discussed separately in the comprehensive comfort evaluation process. According to the results of the thermal comfort experiment, the quadratic curve functions of winter working conditions and summer working conditions are selected as the dimensionless functions of the thermal environment. Exemplarily, in an embodiment of the present invention, multiple influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of the comfort corresponding to each influencing factor is calculated, including:
[0143] The predicted evaluation value of comfort corresponding to the operating temperature is calculated using the following formula:
[0144] y 1A =-18.004+1.642t o -0.038t o 2
[0145] y 1B =-84.130+6.834t o -0.139t o 2
[0146] Among them, y 1A ,y 1B are the predicted evaluation values of comfort corresponding to the operating temperature under winter and summer conditions, t o is the operating temperature.
[0147] Koch, Nevins, Faner, McIntyre and others believe that when the metabolic rate is low (1met) and the temperature is below 28°C, humidity has little effect on human comfort (10% = 0.3°C), and only has an effect at a high metabolic level. Research by Berglund, Tanabe, Hayakawa, Tian Yuanyuan and others shows that when the temperature is in a hot environment (greater than 28°C) and the human body is in a low metabolic rate (sitting), 70% is usually the threshold for relative humidity to affect human comfort, and as the air temperature and metabolic level increase, the impact of relative humidity will increase. This shows that there are certain requirements for temperature for humidity to take effect, and at the same time, the effect of humidity on human comfort has a threshold characteristic. When it is above a certain humidity, humidity will have a significant effect. This study intends to create a stuffy environment, so the temperature needs to be set above 28°C, the maximum relative humidity should be above 70%, and the relative humidity should be increased as much as possible. According to the feedback from the pre-experiment, Figure 1C Schematic diagram of the change of average humidity sensation of human body under different humidity environments, such as Figure 1C As shown in the figure, from the average value, there is almost no change between low humidity and normal humidity (the difference is 0.14), and the indoor humidity feeling level is within the good level of 0-0.5. It can be considered that from the perspective of humidity feeling, there is a good humidity comfort. For high humidity, the humidity feeling deviates slightly from the comfort range, but the deviation value is very large. And from the deviation point of view, its value also tends to increase with the increase of humidity, and this increase is more obvious at high humidity.
[0148] The T test was used to study the differences in average wet sensations at different humidity levels, with a significance level of α = 0.05. It can be seen that there is no significant difference in indoor wet sensations at the three humidity levels. However, in terms of the difference, high humidity has a more objective difference value compared to low humidity and normal humidity, which can also be seen from the mean scatter plot. However, due to the large humidity deviation, especially in high humidity, this difference is not significant.
[0149] Therefore, the wetness sensation tends to increase slightly with humidity, but this increase is not significant, that is, humidity has no significant effect on wetness sensation. At the same time, under high humidity, the deviation is larger than the previous two, and the significance level of the difference in wetness sensation between high humidity and normal humidity is relatively low (0.21), which suggests that there is still a weak difference under high humidity. At the same time, compared with thermal sensation, the deviation of wetness sensation under full humidity is also much higher than that of thermal sensation, and even exceeds 100% under high humidity. This shows that the human body's perception sensitivity to wetness sensation is far less than that of thermal sensation, and at the same time, individual differences are more obvious than thermal sensation.
[0150] According to the results of the wet sensation experiment, combined with the human comfort empirical formula comprehensively expressed by the China Meteorological Observatory, a dimensionless function of wet comfort with a temperature of 26 degrees Celsius and a wind speed of 0.1 m / s is selected. In an embodiment of the present invention, a plurality of the influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of the comfort corresponding to each of the influencing factors is calculated, including:
[0151] The predicted evaluation value of comfort corresponding to humidity is calculated using the following formula:
[0152]
[0153] Among them, y 2 is the predicted evaluation value of comfort corresponding to humidity, h u is the relative humidity.
[0154] Figure 1D is the composition diagram of the indoor light environment, such as Figure 1D As shown in Figure 1, the main function of indoor light environment is to meet people's needs in terms of physiology, psychology, visual ergonomics and aesthetics. It is an environment formed by the illumination of light in the interior space. The sources of indoor light mainly include natural light and artificial light.
[0155] A good artificial light environment should have a suitable illumination, so that the human visual system can adapt well to the entire environmental lighting. To see the static or moving targets in the space clearly, if the illumination is too high, glare will be generated. Glare will cause the local brightness of the target object to be too high, and the shadow of the object will not be obvious. Excessive light will illuminate the human eyeball, making it impossible to see the target object clearly, and also causing harm to people's visual system. In addition to illumination, functional lighting must also have brightness contrast. Objects of the same brightness will have different clarity under different illumination backgrounds.
[0156] Illuminance refers to the size of the light flux received by the light source per unit area. It is an objective physical quantity. Illuminance is a major parameter factor affecting the comfort of personnel. It not only affects the brightness of personnel's vision, but also has a certain impact on personnel's physiological and psychological aspects. Therefore, the illumination conditions of each area should be considered. Its definition is as follows:
[0157]
[0158] Wherein, E is the symbol of illumination, the unit is lux (lx), 1lx = 1lm / m2.
[0159] If multiple light sources illuminate a certain point on the work surface at the same time, the illuminance at that point should be the superposition of the illuminances produced by each light source at that point. The calculation formula is as follows:
[0160] E=E1+E2+…+En
[0161] For ease of understanding and calculation, it is further abbreviated as:
[0162]
[0163] Through long-term practical research, my country has also had a clear definition of the comfort evaluation of the light environment in line with national conditions. In recent years, relevant organizations and departments as well as experts and scholars in related fields have successively formulated and issued the CIE "Indoor Workplace Lighting" standard, "Architectural Lighting Design Standard GB50034-2013" and "Architectural Lighting Design Standard GB50034-2013". The standards stipulate the basic evaluation index standards for designing various types of building light environments.
[0164] Different workplaces and different areas have different illumination requirements. The higher the better is not necessarily the case. Appropriate illumination refers to the illumination value that most people can feel comfortable with under a certain lighting environment.
[0165] There is a certain difference between the comfort of the light environment and the comfort of the thermal environment, that is, there is no obvious difference in light comfort under the two working conditions of winter and summer. Therefore, this study carried out experiments under two color temperature working conditions of 3300K and 6400K. However, in most current standards, only the illumination is clearly stipulated in the standard value of lighting. Relevant experimental studies have shown that when the illumination is the same under different color temperature light sources, there is no difference in the ability to visually recognize details. However, the subjective effect of different color temperatures is still related to the illumination. In general, medium lighting is used for life, office and school, corresponding to medium color temperature (3300K~5300K). Only high-illuminance industrial production workshops and other occasions require high color temperature (>5300K) light sources. The indoor environment studied in this paper is mainly based on low color temperature 3300K.
[0166] According to the results of the light comfort experiment, the quadratic curve function under the color temperature of 3300K is selected as the dimensionless function of the light environment, as shown below:
[0167] y 3 =-4.573+0.012E-9.206×10 -6 E 2
[0168] Among them, y 3 is the predicted evaluation value of comfort corresponding to the lighting, and E is the illumination.
[0169] The color table of a light source is often expressed in terms of color temperature. When the spectrum of a light source is the same or similar to the spectrum emitted by a black body at a certain temperature, the thermodynamic temperature of the black body is called the color temperature of the light source. According to experiments conducted by Kruithoff, people's preference for light color has a certain correlation with the illuminance value. Figure 1E The relationship diagram of illumination, color temperature and comfort provided by the embodiment of the present invention is as follows: Figure 1E As shown, with the increase of the color temperature of the light source, the comfortable illumination required by people also increases. That is, under a light source with warm tones, a lower illumination can achieve a sense of comfort, while under a light source with cool tones and high color temperature, a higher illumination is required to achieve comfort.
[0170] In the embodiment of the present invention, multiple influencing factors are input into a pre-trained BP neural network for processing, and the predicted evaluation value of comfort corresponding to each influencing factor is calculated, including:
[0171] The predicted evaluation value of comfort corresponding to color temperature is calculated using the following formula:
[0172] y 4 =-2.662e-7X 2 +0.002048X-4.86
[0173] Among them, y 4 is the predicted evaluation value of comfort corresponding to color temperature, e is a natural number, and X is the color temperature value.
[0174] S103. The predicted value of thermal comfort is obtained by combining the predicted evaluation values of comfort corresponding to various influencing factors.
[0175] In the embodiment of the present invention, the predicted value of thermal comfort may be obtained by combining the predicted evaluation values of comfort corresponding to various influencing factors in a weighted manner, etc., and the present invention is not limited thereto.
[0176] In recent years, the application of utility function comprehensive evaluation method at home and abroad is not limited to the whole process from dimensionless index to weighted synthesis. For example, Chen Zhilin et al. used the utility function method to construct dimensionless function of single evaluation value; Jiao Yonglan et al. used generalized utility function method to conduct comprehensive evaluation of multiple indicators on the basis of determining the index content and the weight of evaluation index; Zhao Liang et al. used the utility additivity theory to establish total utility evaluation function in the evaluation model process; SankerKumar Roy et al. introduced utility function to select the objective function in the mathematical model for solving multi-objective transportation problems. It can be seen that the utility function evaluation method is widely used in the engineering field.
[0177] Exemplarily, in a specific embodiment of the present invention, a utility function comprehensive evaluation method is used to comprehensively influence the predicted evaluation value of comfort corresponding to the factors to obtain a predicted value of thermal comfort. The utility function formula is as follows:
[0178] C = ξ(y i ,ω i )
[0179] Among them, C is the predicted value of thermal comfort, y i is the predicted evaluation value of comfort corresponding to each of the influencing factors, ω i is the weight value of the predicted evaluation value of comfort corresponding to each influencing factor, ξ is y i and ω i The comprehensive function model.
[0180] Among them, y i For x i The utility function evaluation value, y i =f i (x i ), i.e., dimensionless value; f i For x i The utility function, i.e., dimensionless function; x i It is an evaluation index of a single factor.
[0181] Therefore, the utility function method in the comprehensive evaluation of human comfort in indoor environment is about the utility function f i , the weight value ωi and the synthetic model ξ, the specific procedure includes three aspects:
[0182] The first is to construct the evaluation index system and make the single factor dimensionless. Based on the accurate and direct reflection of a certain aspect of the human comfort of the indoor environment, the value that depicts a certain feature of the human comfort of the indoor environment from different aspects is selected as the evaluation index. In order to avoid the influence of the selected evaluation index due to different units or large differences in the order of magnitude of the values, the evaluation index needs to be dimensionless.
[0183] The second is to determine the weight coefficient. Among multiple evaluation indicators, the importance of each indicator on the comprehensive comfort of the human body is different, and it is necessary to determine the value of the importance of the evaluation indicator based on a certain weighting method.
[0184] The third is the synthesis of evaluation indicators, that is, using a mathematical function to synthesize multiple evaluation indicators into a total evaluation index value. The evaluation concept of the evaluation function should be scientific and reasonable, and the physical meaning of the single evaluation indicator should be consistent with the physical meaning of the total evaluation value.
[0185] Since there is no unified evaluation standard for comfort that combines factors such as temperature, humidity, light, and color temperature, nor is there an internationally accepted grading index, it is necessary to establish certain multi-factor comprehensive indicators for factors such as temperature, humidity, light, and color temperature to quantify and unify them.
[0186] After the main parameters of a single environmental factor are determined, a quantitative and unified standard for the evaluation index is formulated. However, the units of multiple evaluation indexes of human comprehensive comfort are different, and the order of magnitude is inconsistent. Therefore, it is necessary to make the relationship between the value level of a single factor and comfort dimensionless.
[0187] The subjective response of the human body is converted into quantitative indicators. On the one hand, the units and magnitudes of the evaluation indicators are quantified and unified; on the other hand, the quantitative results also need to reflect the role and importance of multiple factors (temperature, humidity, light, color temperature) in the entire comprehensive evaluation system. Therefore, after each factor system is determined, it is necessary to assign different weight coefficients to the evaluation indicators (temperature, humidity, light, color temperature). Determining the rationality of the weights is also of great significance to the comprehensive evaluation.
[0188] This experiment uses the AHP evaluation scale, applies the idea of scale-free limit, introduces the binary weight distribution value, and statistically calculates the binary distribution value between any two elements from 109 survey results, taking the average and median respectively. The AHP method is used to judge the matrix, and the sum-product method is used for approximate solution. The elements in the judgment matrix are normalized by column, and then the columns of the same row of the normalized matrix are added, and finally the weight ratio is calculated.
[0189] The thermal comfort prediction method provided by the embodiment of the present invention includes: obtaining multiple influencing factors affecting thermal comfort, inputting the multiple influencing factors into a pre-trained BP neural network for processing, calculating the predicted evaluation value of comfort corresponding to each influencing factor, and synthesizing the predicted evaluation value of comfort corresponding to each influencing factor to obtain a predicted value of thermal comfort. The BP neural network is used to deeply study the influence of multiple influencing factors on human thermal comfort, and the predicted evaluation value of comfort corresponding to each influencing factor is synthesized to obtain a predicted value of thermal comfort, thereby improving the efficiency and accuracy of thermal comfort prediction to better meet people's thermal comfort needs.
[0190] Embodiment 2
[0191] Figure 2 A schematic diagram of the structure of a thermal comfort prediction device provided in the second embodiment of the present invention is shown in FIG. Figure 2 As shown, the device comprises:
[0192] An influencing factor acquisition module 201 is used to acquire multiple influencing factors that affect thermal comfort;
[0193] A calculation module 202 is used to input the plurality of influencing factors into a pre-trained BP neural network for processing, and calculate the predicted evaluation value of comfort corresponding to each of the influencing factors;
[0194] The comprehensive prediction module 203 is used to obtain a thermal comfort prediction value by comprehensively analyzing the predicted evaluation values of comfort corresponding to the influencing factors.
[0195] In some embodiments of the present invention, the influencing factors include: environmental factors and human factors;
[0196] The environmental factors include: operating temperature, humidity, wind speed, light, mean radiant temperature and color temperature;
[0197] The human factors include: human metabolic rate, clothing thermal resistance and external mechanical work.
[0198] In some embodiments of the present invention, the operating temperature is calculated by the following formula:
[0199]
[0200] Among them, t o is the operating temperature, t a is the temperature of the ambient air, h c is the convective heat transfer coefficient, h r is the radiation heat transfer coefficient, is the average radiant temperature of a human body in a sitting position;
[0201] Among them, the average radiation temperature of the human body in a sitting position is calculated by the following formula:
[0202]
[0203] Among them, t up ,t down ,t right ,t left ,t front ,t back They are the surface temperatures of the upper, lower, right, left, front and rear walls of the human body respectively.
[0204] In some embodiments of the present invention, the calculation module 202 calculates the predicted evaluation value of the comfort corresponding to the operating temperature using the following formula:
[0205] y 1A =-18.004+1.642t o -0.038t o 2
[0206] y 1B =-84.130+6.834t o -0.139t o 2
[0207] Among them, y 1A,y 1B are the predicted evaluation values of comfort corresponding to the operating temperature under winter and summer conditions, t o is the operating temperature.
[0208] In some embodiments of the present invention, the calculation module 202 calculates the predicted evaluation value of the comfort corresponding to the humidity using the following formula:
[0209]
[0210] Among them, y 2 is the predicted evaluation value of comfort corresponding to humidity, h u is the relative humidity.
[0211] In some embodiments of the present invention, the calculation module 202 calculates the predicted evaluation value of the comfort corresponding to the illumination using the following formula:
[0212] y 3 =-4.573+0.012E-9.206×10 -6 E 2
[0213] Among them, y 3 is the predicted evaluation value of comfort corresponding to the lighting, and E is the illumination.
[0214] In some embodiments of the present invention, the calculation module 202 calculates the predicted evaluation value of the comfort level corresponding to the color temperature using the following formula:
[0215] y 4 =-2.662e-7X 2 +0.002048X-4.86
[0216] Among them, y 4 is the predicted evaluation value of comfort corresponding to color temperature, e is a natural number, and X is the color temperature value.
[0217] In some embodiments of the present invention, the comprehensive prediction module 203 includes:
[0218] The comprehensive prediction unit adopts the utility function comprehensive evaluation method to comprehensively calculate the predicted evaluation value of the comfort corresponding to the influencing factors to obtain the predicted value of thermal comfort. The utility function formula is as follows:
[0219] C = ξ(y i ,ω i )
[0220] Among them, C is the predicted value of thermal comfort, y i is the predicted evaluation value of comfort corresponding to each of the influencing factors, ω iis the weight value of the predicted evaluation value of comfort corresponding to each of the influencing factors, ξ is y i and ω i The comprehensive function model.
[0221] The above-mentioned thermal comfort prediction device can execute the thermal comfort prediction method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the thermal comfort prediction method.
[0222] Embodiment 3
[0223] Embodiment 3 of the present invention provides a computer device, Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the computer device includes:
[0224] Processor 301, memory 302, communication module 303, input device 304 and output device 305; the number of processors 301 in the mobile terminal can be one or more, Figure 3 A processor 301 is taken as an example; the processor 301, the memory 302, the communication module 303, the input device 304 and the output device 305 in the mobile terminal can be connected by a bus or other means, Figure 3 The above processor 301, memory 302, communication module 303, input device 304 and output device 305 can be integrated in a computer device.
[0225] The memory 302 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as the module corresponding to the thermal comfort prediction method in the above embodiment. The processor 301 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 302, that is, implements the above thermal comfort prediction method.
[0226] The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the microcomputer, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0227] The communication module 303 is used to establish a connection with an external device (such as a smart terminal) and realize data interaction with the external device. The input device 304 can be used to receive input digital or character information and generate key signal input related to user settings and function control of the computer device.
[0228] The computer device provided in this embodiment can execute the thermal comfort prediction method provided in any of the above embodiments of the present invention, and has corresponding functions and beneficial effects.
[0229] Embodiment 4
[0230] Embodiment 4 of the present invention provides a storage medium containing computer executable instructions, on which a computer program is stored. When the program is executed by a processor, a thermal comfort prediction method as provided in any of the above embodiments of the present invention is implemented. The method includes:
[0231] Obtain multiple factors affecting thermal comfort;
[0232] Inputting the plurality of influencing factors into a pre-trained BP neural network for processing, and calculating the predicted evaluation value of comfort corresponding to each of the influencing factors;
[0233] The predicted value of thermal comfort is obtained by combining the predicted evaluation values of comfort corresponding to the influencing factors.
[0234] It should be noted that, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0235] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a robot, a personal computer, a server, or a network device, etc.) to execute the thermal comfort prediction method described in any embodiment of the present invention.
[0236] It is worth noting that in the above-mentioned device, the various modules and units included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0237] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0238] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0239] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A thermal comfort prediction method, It is characterized in that include: Acquire multiple influencing factors affecting thermal comfort, wherein the influencing factors are dimensionless values; Inputting the plurality of influencing factors into a pre-trained BP neural network for processing, and calculating the predicted evaluation value of comfort corresponding to each of the influencing factors; The predicted value of thermal comfort is obtained by combining the predicted evaluation values of comfort corresponding to the influencing factors; The influencing factors include: environmental factors and human factors; The environmental factors include: operating temperature, humidity, wind speed, light, mean radiant temperature and color temperature; The human factors include: human metabolic rate, clothing thermal resistance and external mechanical work; The operating temperature is calculated by the following formula: Among them, t o is the operating temperature, t a is the temperature of the ambient air, h c is the convective heat transfer coefficient, h r is the radiation heat transfer coefficient, is the average radiant temperature of a human body in a sitting position; Among them, the average radiation temperature of the human body in a sitting position is calculated by the following formula: Among them, t up ,t down ,t right ,t left ,t front ,t back are the surface temperatures of the upper, lower, right, left, front and rear walls of the human body respectively; The inputting of the plurality of influencing factors into a pre-trained BP neural network for processing and calculating the predicted evaluation value of the comfort corresponding to each of the influencing factors comprises: The predicted evaluation value of comfort corresponding to the operating temperature is calculated using the following formula: and 1A -18.004+1.642t o -0.038t o 2 <h2 style=";text-align:left;direction:ltr">y<h2 style=";text-align:left;direction:ltr"> 1B <h2 style=";text-align:left;direction:ltr"> =-84.130+6.834t<h2 style=";text-align:left;direction:ltr"> o <h2 style=";text-align:left;direction:ltr"> -0.139t<h2 style=";text-align:left;direction:ltr"> o <h2 style=";text-align:left;direction:ltr"> 2 Among them, y 1A ,y 1B are the predicted evaluation values of comfort corresponding to the operating temperature under winter and summer conditions, t o is the operating temperature; The predicted evaluation value of comfort corresponding to humidity is calculated using the following formula: Among them, y 2 is the predicted evaluation value of comfort corresponding to humidity, h u is the relative humidity; The predicted evaluation value of comfort corresponding to lighting is calculated using the following formula: yes 3 =-4.573+0.012E-9.206×10 -6 From 2 Among them, y 3 is the predicted evaluation value of comfort corresponding to the lighting, and E is the illumination; The predicted evaluation value of comfort corresponding to color temperature is calculated using the following formula: y 4 =-2.662e-7X 2 +0.002048X-4.86 Among them, y 4 is the predicted evaluation value of comfort corresponding to color temperature, e is a natural number, and X is the color temperature value; The predicted value of thermal comfort is obtained by synthesizing the predicted evaluation values of comfort corresponding to the influencing factors, including: The utility function comprehensive evaluation method is used to comprehensively evaluate the predicted evaluation values of comfort corresponding to the influencing factors to obtain the predicted value of thermal comfort. The utility function formula is as follows: C=ξ(y i ,oh i ) Among them, C is the predicted value of thermal comfort, y i is the predicted evaluation value of comfort corresponding to each of the influencing factors, ω i is the weight value of the predicted evaluation value of comfort corresponding to each of the influencing factors, ξ is y i and ω i The comprehensive function model.
2. A thermal comfort prediction device, It is characterized in that include: An influencing factor acquisition module, used to acquire a plurality of influencing factors affecting thermal comfort, wherein the influencing factors are dimensionless values; A calculation module, used for inputting the plurality of influencing factors into a pre-trained BP neural network for processing, and calculating a predicted evaluation value of comfort corresponding to each of the influencing factors; A comprehensive prediction module, used to obtain a thermal comfort prediction value by comprehensively analyzing the predicted evaluation values of comfort corresponding to the influencing factors; The influencing factors include: environmental factors and human factors; The environmental factors include: operating temperature, humidity, wind speed, light, mean radiant temperature and color temperature; The human factors include: human metabolic rate, clothing thermal resistance and external mechanical work; The operating temperature is calculated by the following formula: Among them, t o is the operating temperature, t a is the temperature of the ambient air, h c is the convective heat transfer coefficient, h r is the radiation heat transfer coefficient, is the average radiant temperature of a human body in a sitting position; Among them, the average radiation temperature of the human body in a sitting position is calculated by the following formula: Among them, t up ,t down ,t right ,t left ,t front ,t back are the surface temperatures of the upper, lower, right, left, front and rear walls of the human body respectively; The inputting of the plurality of influencing factors into a pre-trained BP neural network for processing and calculating the predicted evaluation value of the comfort corresponding to each of the influencing factors comprises: The predicted evaluation value of comfort corresponding to the operating temperature is calculated using the following formula: and 1A -18.004+1.642t o -0.038t o 2 <h2 style=";text-align:left;direction:ltr">y<h2 style=";text-align:left;direction:ltr"> 1B <h2 style=";text-align:left;direction:ltr"> =-84.130+6.834t<h2 style=";text-align:left;direction:ltr"> o <h2 style=";text-align:left;direction:ltr"> -0.139t<h2 style=";text-align:left;direction:ltr"> o <h2 style=";text-align:left;direction:ltr"> 2 Among them, y 1A ,y 1B are the predicted evaluation values of comfort corresponding to the operating temperature under winter and summer conditions, t o is the operating temperature; The predicted evaluation value of comfort corresponding to humidity is calculated using the following formula: Among them, y 2 is the predicted evaluation value of comfort corresponding to humidity, h u is the relative humidity; The predicted evaluation value of comfort corresponding to lighting is calculated using the following formula: yes 3 =-4.573+0.012E-9.206×10 -6 From 2 Among them, y 3 is the predicted evaluation value of comfort corresponding to the lighting, and E is the illumination; The predicted evaluation value of comfort corresponding to color temperature is calculated using the following formula: y 4 =-2.662e-7X 2 +0.002048X-4.86 Among them, y 4 is the predicted evaluation value of comfort corresponding to color temperature, e is a natural number, and X is the color temperature value; The predicted value of thermal comfort is obtained by synthesizing the predicted evaluation values of comfort corresponding to the influencing factors, including: The utility function comprehensive evaluation method is used to comprehensively evaluate the predicted evaluation values of comfort corresponding to the influencing factors to obtain the predicted value of thermal comfort. The utility function formula is as follows: C=ξ(y i ,oh i ) Among them, C is the predicted value of thermal comfort, y i is the predicted evaluation value of comfort corresponding to each of the influencing factors, ω i is the weight value of the predicted evaluation value of comfort corresponding to each of the influencing factors, ξ is y i and ω i The comprehensive function model.
3. A computer device, It is characterized in that include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the thermal comfort prediction method according to claim 1.
4. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the thermal comfort prediction method as claimed in claim 1 is implemented.
