Individual comfort model optimization method and system based on warm manikin

Abstract

The invention discloses an individual comfort model optimization method and system based on a thermal manikin. The method comprises the following steps: measuring clothing thermal resistance in an individual comfort system (PCS) use scene; different parameters (including but not limited to temperature, humidity and the like) are set in the artificial environment climate chamber, a test without turning on a PCS and a test with turning on the PCS are carried out respectively, and the heating power and the surface temperature of each part of the thermal manikin under different PCS operation conditions are recorded; calculating a power change value and a power change percentage after the PCS is started through the heating power of each part, calculating an equivalent temperature of each part and a difference value between the equivalent temperature and the environment temperature according to the thermal resistance of the clothes and the surface temperature of the thermal dummy, and calculating a thermal sensitivity temperature difference value according to the thermal sensitivity of each part of the human body; and generating parameters of the individual comfort model PCM. According to the method, the PCS performance is evaluated by applying the warm manikin, and the prediction performance of PCM on personnel thermal evaluation is improved in combination with theories of human body thermal sensitivity and the like.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to an optimization method and system for an individual comfort model based on a thermal manikin. Background Art

[0002] People spend 80% of their lives indoors. Therefore, creating a healthy and comfortable indoor environment and improving the thermal satisfaction rate of indoor occupants is of great significance. Existing indoor thermal environment creation strategies and technical means target the overall environment and cannot penetrate the local space at the individual level. As a result, there is a mismatch between the environmental supply and the actual needs of people in terms of time and space, and this problem is particularly evident in multi-person office scenarios. To make up for this shortcoming, it is necessary to develop accurate individual thermal demand identification methods and microenvironment control devices for individuals centered around individual users to provide accurate thermal services.

[0003] The accurate individual thermal demand identification method is the individual comfort model (Personal comfort model, abbreviated as PCM). Such models usually use environmental parameters (temperature, humidity, air velocity, etc.), individual physiological data (skin temperature, heart rate, brain waves), and individual adjustment behaviors (air conditioner control behaviors, clothing adjustment behaviors, etc.) as input parameters, generate operation logic through physical process abstraction or machine learning algorithms, and the output object is the predicted value of individual thermal evaluation (cold / hot feeling, comfort level, temperature preference, etc.) for guiding the control of environmental creation equipment. The individual microenvironment control device is the individual comfort system (Personal comfort system, abbreviated as PCS). Such devices include but are not limited to workplace air supply outlets, desktop fans, table fans, adjustable temperature seats, small electric heaters, etc. The PCS has the characteristics of independent control, strong flexibility, and low energy consumption.

[0004] The invention patent CN118035932A proposes an individual thermal comfort prediction method. Based on the obtained individual thermal comfort data set, an individual thermal comfort prediction model is constructed using a variety of different machine learning algorithms, and the accuracy of the model is evaluated. The prediction performance and generalization performance of the model are improved through the complementary advantages of multiple algorithms. The utility model patent CN215571095U introduces the physiological parameter of skin temperature into the air conditioning system, and a PCM is established based on the relationship between skin temperature and TSV and used for the control of the temperature adjustment of the air conditioning system.

[0005] Although the prior art provides a method for constructing a PCM based on individual thermal comfort data and the PCM has a relatively preliminary application in current high-end air conditioners, the applicable scenarios cannot cover the cases where PCS is used, resulting in large prediction errors when people use PCS. To avoid this problem, it is necessary to focus on how the use of PCS is reflected in the PCM and optimize the structure of the PCM based on an effective evaluation of the performance of PCS. Summary of the Invention

[0006] The present invention aims to solve at least one of the technical problems in the related art to some extent.

[0007] The present invention proposes an optimization method for an individual comfort model based on a thermal manikin, which optimizes the performance of the individual comfort model (PCM) in the usage scenario of the individual comfort system (PCS), and proposes an optimization method for an individual comfort model based on a thermal manikin. The present invention uses a thermal manikin to uniformly evaluate the PCS, and combines theories such as human thermal sensitivity to generate input parameters applicable to the PCM.

[0008] Another object of the present invention is to propose an optimization system for an individual comfort model based on a thermal manikin.

[0009] To achieve the above object, on the one hand, the present invention proposes an optimization method for an individual comfort model based on a thermal manikin, including:

[0010] Measuring the clothing thermal resistance in the usage scenario of the individual comfort system PCS;

[0011] Arranging an artificial environmental climate chamber and setting different environmental conditions. Under each environmental condition, start the thermal manikin in a preset operation mode, and conduct tests without turning on the PCS and tests with the PCS turned on respectively. After the thermal manikin reaches a stable state, record the heat generation power and surface temperature of each part of the thermal manikin;

[0012] Calculating the power change value and power change percentage after turning on the PCS through the heat generation power of each part, calculating the equivalent temperature of each part, the difference between the equivalent temperature and the environmental temperature, and calculating the thermal sensitivity temperature difference according to the thermal sensitivity of each part of the human body to generate the parameters of the individual comfort model PCM.

[0013] The optimization method for an individual comfort model based on a thermal manikin according to the embodiments of the present invention may further have the following additional technical features:

[0014] In one embodiment of the present invention, the operating mode of the thermal manikin is a constant surface temperature mode or a comfort mode. In the constant surface temperature mode, the surface temperature of each region is set individually, and the surface temperature is set according to the human skin temperature. The control logic of the comfort mode is to maintain the core temperature of the thermal manikin unchanged.

[0015] In one embodiment of the present invention, if the selected actual ambient temperature value is within the ambient temperature setting range value of the artificial environmental climate chamber, the power change value corresponding to the air temperature is directly selected as the generated parameter value. The calculation formula for the power change value is:

[0016] Δw = w_on – w_off

[0017] where w_on is the measured value of the heating power when the PCS is turned on; w_off is the measured value of the heating power when the PCS is turned off; and Δw is the power change value.

[0018] In one embodiment of the present invention, if the selected actual ambient temperature value is not within the ambient temperature setting range value of the artificial environmental climate chamber, a linear regression is performed on the heating power and the air temperature, and the relationship between the two is obtained. The parameter value is calculated according to the fitting formula, and the fitting formula is as follows:

[0019] w = a × Ta + b

[0020] where w is the heating power; Ta is the air temperature; a is the slope; and b is the intercept.

[0021] In one embodiment of the present invention, the fitting formulas for the heating power under different PCS operating conditions are obtained: the PCS off condition is w = a1 × Ta + b1, and the PCS on condition is w = a2 × Ta + b2. In actual applications, w is calculated according to the PCS usage method to obtain the parameter value required for the PCM;

[0022] For the power change percentage, the calculation formula is as follows:

[0023] w% = Δw / w_off

[0024] where w% is the power change percentage.

[0025] In one embodiment of the present invention, the equivalent temperature of each part and the difference between the equivalent temperature and the ambient temperature are calculated according to the clothing thermal resistance and the surface temperature of the thermal manikin. The calculation formula for the equivalent temperature is as follows:

[0026] Teq = Tsurf – 0.155 × I × w

[0027] where Teq is the equivalent temperature; Tsurf is the surface temperature; and I is the clothing thermal resistance.

[0028] In one embodiment of the present invention, the calculation formula for the difference between the equivalent temperature and the ambient temperature is as follows:

[0029] ΔT = Teq – Ta

[0030] where ΔT is the difference between the equivalent temperature and the ambient temperature; Teq is the equivalent temperature.

[0031] In one embodiment of the present invention, the calculation formula for the difference in thermal sensitivity temperature is as follows:

[0032] ΔTS = ΔT × S

[0033] where ΔTS is the difference in thermal sensitivity temperature; ΔT is the difference between the equivalent temperature and the ambient temperature; S is the thermal sensitivity.

[0034] To achieve the above object, on the other hand, the present invention provides an individual comfort model optimization system based on a thermal manikin, including:

[0035] A clothing thermal resistance measurement module for measuring the clothing thermal resistance in the usage scenario of the individual comfort system PCS;

[0036] A relevant parameter measurement module for arranging an artificial environmental climate chamber and setting different environmental conditions, starting the thermal manikin in a preset operation mode under each environmental condition, and respectively conducting tests without turning on the PCS and tests with the PCS turned on. After the thermal manikin reaches a stable state, record the heating power and surface temperature of each part of the thermal manikin;

[0037] A parameter optimization and generation module for calculating the power change value and power change percentage after turning on the PCS through the heating power of each part, calculating the equivalent temperature of each part, the difference between the equivalent temperature and the ambient temperature according to the clothing thermal resistance and the surface temperature of the thermal manikin, and calculating the difference in thermal sensitivity temperature according to the thermal sensitivity of each part of the human body, so as to generate the parameters of the individual comfort model PCM.

[0038] The parameters generated by the individual comfort model optimization method and system based on the thermal manikin according to the embodiments of the present invention correspond to different human body parts, characterize the effect of the PCS on these parts, and can be directly used to expand the input parameters of the PCM.

[0039] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. Description of the Drawings

[0040] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where:

[0041] Figure 1 is a flowchart of an individual comfort model optimization method based on a thermal manikin according to an embodiment of the present invention;

[0042] Figure 2 is another flowchart of an individual comfort model optimization method based on a thermal manikin according to an embodiment of the present invention;

[0043] Figure 3 is a parameter relationship diagram of an individual comfort model optimization method based on a thermal manikin according to an embodiment of the present invention;

[0044] Figure 4 is an experimental scenario diagram of an individual comfort model optimization method based on a thermal manikin according to an embodiment of the present invention;

[0045] Figure 5 is a structural diagram of an individual comfort model optimization system based on a thermal manikin according to an embodiment of the present invention. Detailed implementation manners

[0046] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0047] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] The individual comfort model optimization method and system based on a thermal manikin proposed according to an embodiment of the present invention will be described below with reference to the drawings.

[0049] Figure 1 is a flowchart of an individual comfort model optimization method based on a thermal manikin according to an embodiment of the present invention. As Figure 1 shown, the method includes:

[0050] S1, measuring the clothing thermal resistance under the usage scenario of the individual comfort system PCS;

[0051] S2, arranging an artificial environmental climate chamber and setting different environmental conditions, starting the thermal manikin in a preset operation mode under each environmental condition, and respectively conducting tests without turning on the PCS and tests with turning on the PCS. After the thermal manikin reaches a stable state, record the heating power and surface temperature of each part of the thermal manikin;

[0052] S3. Calculate the power change value and power change percentage after turning on the PCS based on the heating power of each part, calculate the equivalent temperature of each part, the difference between the equivalent temperature and the ambient temperature, and the temperature difference of thermal sensitivity based on the clothing thermal resistance and the surface temperature of the warm manikin, so as to generate the parameters of the individual comfort model PCM.

[0053] It can be understood that the present invention proposes an optimization method for an individual comfort model based on a warm manikin. The necessary hardware facilities include an artificial environmental climate chamber, a warm manikin, and a PCS to be tested. The method proposed by the present invention includes the implementation of multiple sub-test experiments. First, it is the selection of common clothing in the PCS usage scenario and the measurement of clothing thermal resistance. The selection of clothing needs to comprehensively consider the places where the PCS is applied (such as offices, classrooms, etc.), seasons, etc. The method for measuring clothing thermal resistance refers to "GB / T18398-2001 Test Method for Clothing Thermal Resistance - Warm Manikin Method". In this experiment, the clothing thermal resistance of each part of the warm manikin needs to be recorded instead of the weighted clothing thermal resistance.

[0054] On this basis, arrange the artificial environmental climate chamber according to the common PCS usage scenario, and set different environmental conditions respectively. Turn on the warm manikin under each environmental condition and use it as the object of action of the PCS. Conduct tests without turning on the PCS. After the warm manikin reaches a stable state (the stable standard can be defined in the warm manikin control program), record the heating power and surface temperature parameters of each part of the warm manikin. After the recording is completed, turn on the PCS. Similarly, after the warm manikin reaches a stable state, record the relevant parameters of each part of the warm manikin. If the same PCS has different usage methods (such as a desktop fan can adjust the blowing part), then conduct the same experimental operations under another usage method.

[0055] After the experiment is completed, parameter generation can be carried out. The dimension of the parameters involved depends on the warm manikin and is theoretically no more than the number of adjustable parts of the warm manikin. Taking the case of turning off the PCS as the benchmark, the power change value and power change percentage after turning on the PCS can be directly calculated through the heating power of each part; combining the clothing thermal resistance and the surface temperature of the warm manikin, the equivalent temperature of each part and the difference between the equivalent temperature and the ambient temperature can be calculated; further, combining the research results of the thermal sensitivity of each part of the human body, the temperature (equivalent temperature and ambient temperature) difference considering thermal sensitivity can be calculated. The generated parameters correspond to different human body parts and characterize the effect of the PCS on these parts, and can be directly used to expand the input parameters of the PCM.

[0056] Specifically, the purpose of the present invention is to optimize the performance of the individual comfort model (PCM) in the PCS usage scenario. The implementation process, the relationship between the measured parameters and the generated parameters, and the experimental scenario examples involved are shown in Figure 2 andFigure 3 and Figure 4 . The hardware facilities necessary for implementing this method include an artificial climate chamber 301, a warm-body manikin 302, and a PCS 303 to be tested. The artificial climate chamber 301 needs to have the function of adjusting the ambient temperature and humidity, and the typical control accuracy is (±0.3°C, ±5%). In order to reduce the impact of unstable airflow, it is necessary to control the airflow velocity in the artificial climate chamber during the experiment to be lower than 0.1m / s. The warm-body manikin 302 can simulate the heat and moisture exchange process between the human body and the environment, and evaluate the impact of clothing, environment or equipment on human thermal comfort. Its applications cover clothing, architectural environment, medical health, transportation design and other fields. Taking the warm-body manikin produced by PTTEKNIK of Denmark as an example, this type of warm-body manikin can achieve independent control of the temperature / heating power of 22 areas of the whole body, and has three modes: constant power mode, constant surface temperature mode and comfort mode. In the sub-experiments involved in the present invention, it is recommended to operate in the latter two modes. The PCS 303 to be tested may be any micro-environment control device around personnel, including but not limited to workstation air outlets, desktop fans, table fans, temperature-adjustable chairs, small electric heaters, etc.

[0057] like Figure 2 As shown, the method proposed in the present invention includes the implementation of multiple sub-test experiments.

[0058] Step 101, selection of common clothing for PCS usage scenarios and determination of clothing thermal resistance. The selection of clothing needs to comprehensively consider the location (office, classroom, etc.) and season of PCS application. For example, a desktop fan is a common device in summer offices, and the clothing in this scenario is a short-sleeved shirt, thin trousers, shoes and socks, and underwear. The test method for clothing thermal resistance is not original to the present invention. The determination of clothing thermal resistance is only a necessary step to implement the method proposed by the present invention. Therefore, the method for determining clothing thermal resistance is not further elaborated. For more test information, please refer to "GB / T 18398-2001 Clothing Thermal Resistance Test Method Warm Manikin Method". The experiment needs to record the thermal resistance of the clothing of the warm manikin 201, which is the value of each part rather than the weighted value of each part.

[0059] Step 102: Arrange an artificial environmental climate chamber according to common PCS usage scenarios, and set different environmental conditions (mainly temperature, such as 23, 26, 29, 32 °C, relative humidity 50%). Turn on the thermal manikin under each environmental condition and use it as the object of action of the PCS. The operation mode of the thermal manikin 302 can be selected as the constant surface temperature mode or the comfort mode. In the constant surface temperature mode, the surface temperature of each area can be set individually. According to the human skin temperature, the surface temperature can be set to 34 °C. The control logic of the comfort mode is to maintain the core temperature of the thermal manikin 302 unchanged. This mode is more in line with human physiological characteristics, but it takes a longer time to reach the stability of the surface temperature 203. In the experiment, first conduct a test without turning on the PCS as a benchmark. After the thermal manikin 302 reaches a stable state (the stability standard can be defined in the thermal manikin control program, for example, the surface temperature changes no more than 0.1 °C within 15 minutes), record the heating power 202 and surface temperature 203 of each part of the thermal manikin. After the recording is completed, conduct a test with the PCS turned on. Similarly, after the thermal manikin reaches a stable state, record the relevant parameters of each part of the thermal manikin. If the same PCS includes different usage methods (such as a desktop fan can adjust the blowing part), then conduct the same experimental operation in another usage method.

[0060] Step 103: Generate parameters based on the data obtained in Step 101 and Step 102. The dimension of the parameters involved depends on the thermal manikin 302. Theoretically, it is no more than the number of adjustable parts of the thermal manikin 302. For example, if the thermal manikin has 22 areas, at most 22 input parameters can be introduced, or different parts can be combined according to actual needs. Taking the case of turning off the PCS as a benchmark, the power change value 205 and power change percentage 206 after turning on the PCS can be directly calculated through the heating power 202 of each part. Since each measured value involved is related to the ambient air temperature, the generation of parameters first requires preliminary processing of the data under different working conditions. For the heating power 202, if there are enough environmental conditions in the artificial environmental climate chamber 301, such as the set values of the air temperature are 22, 23, 24, 25,... 32 °C, then the change value 205 of the heating power measurement value corresponding to the air temperature can be directly selected as the generated parameter value. The calculation formula for the power change value 205 is:

[0061] Δw = w_on – w_off

[0062] where w_on is the measured value of the heating power 202 when the PCS is turned on, with the unit W; w_off is the measured value of the heating power 202 when the PCS is turned off, with the unit W; Δw is the power change value 205, with the unit W.

[0063] However, if the set value of the air temperature in the artificial environmental climate chamber 301 is relatively low, such as 22, 26, 30, 34 °C, since the air temperature in actual applications may be values outside the experimental test range, such as 23, 28 °C, etc., the corresponding heating power 202 cannot be obtained. In this case, it is necessary to first perform a linear regression on the heating power 202 and the air temperature to obtain the relationship between the two, and calculate the parameter values according to the fitting formula in the application. An example of the fitting formula is as follows:

[0064] w = a × Ta + b

[0065] where w is the heating power 202, in units of W; Ta is the air temperature, in units of °C; a is the slope; b is the intercept.

[0066] According to this method, the fitting formulas for different PCS operating conditions can be obtained. For example, the PCS off condition is w = a1 × Ta + b1, and the PCS on condition is w = a2 × Ta + b2. In actual applications, calculate w (corresponding to w_off and w_on for PCS off and PCS on respectively) according to the PCS usage method to obtain the parameter values required for the PCM. Furthermore, the corresponding power change value 205 can be obtained through the above calculation method of Δw. It should be clear that when the PCS is off, the power change value 205 is always 0.

[0067] For the power change percentage, the calculation formula is as follows:

[0068] w% = Δw / w_off

[0069] where w% is the power change percentage 206; Δw is the power change value 205, in units of W; w_off is the measured value of the heating power 202 when the PCS is off, in units of W.

[0070] Furthermore, by combining the clothing thermal resistance 201 and the surface temperature 203 of the warm manikin, the equivalent temperature 207 of each part and the difference 208 between the equivalent temperature and the ambient temperature (air temperature) can be calculated. The equivalent temperature 207 can be understood as the temperature of the microenvironment on the surface of the manikin. When the PCS is off, theoretically the equivalent temperature value is equal to the ambient air temperature; when the PCS is on, the equivalent temperature 207 value will be lower than the air temperature. The calculation formula for the equivalent temperature 207 is as follows:

[0071] Teq = Tsurf – 0.155 × I × w

[0072] where Teq is the equivalent temperature 207, in units of °C; Tsurf is the surface temperature 203, in units of °C; I is the clothing thermal resistance 201, in units of clo; w is the heating power 202, in units of W.

[0073] The calculation formula for the difference 208 between the equivalent temperature and the ambient temperature is as follows:

[0074] ΔT = Teq – Ta

[0075] Where ΔT is the difference between the equivalent temperature and the ambient temperature 208, in °C; Teq is the equivalent temperature 207, in °C; Ta is the air temperature, in °C.

[0076] Furthermore, combining the research results on the thermal sensitivity of various parts of the human body, the temperature difference of thermal sensitivity (equivalent temperature and ambient temperature) 209 can be calculated. The calculation formula for the temperature difference of thermal sensitivity 209 is as follows:

[0077] ΔTS = ΔT × S

[0078] Where ΔTS is the temperature difference of thermal sensitivity 209; ΔT is the difference between the equivalent temperature and the ambient temperature 208, in °C; S is the thermal sensitivity 204, in °C -1 .

[0079] The value of the thermal sensitivity 204 needs to be obtained through experiments on real people. Here, based on the research results of Luo et al [1] , taking the thermal manikin produced by PT TEKNIK of Denmark as an example, the reference values of the thermal sensitivity 204 in 22 regions are provided in Table 1. Among them, the selection of thermal sensitivity (cold stimulus) and thermal sensitivity (heat stimulus) is determined according to the PCS type. If it is a PCS such as a heater, then select thermal sensitivity (heat stimulus); otherwise, select thermal sensitivity (cold stimulus).

[0080] Table 1

[0081]

[0082]

[0083] The above content describes the parameter calculation methods involved in generating the parameters of the individual comfort model in step 103. These parameters can be directly used as the input parameters of the PCM for predicting the thermal evaluation of personnel. Now, taking a typical PCM as an example, the thermal evaluation accuracy rates of personnel are calculated respectively in the cases of not adding the parameters generated in step 103 and not adding the generated parameters.

[0084] The PCM here is a model for predicting human thermal sensation based on measuring the skin temperature of the human face using an infrared sensor. The original input parameters include the skin temperatures of the human forehead, glasses, nose, and cheeks, the overall average facial temperature, and the air temperature. The output parameter is the predicted value of human thermal sensation (classified into three categories: cold, hot, and neutral). This model is established based on the machine learning algorithm support vector machine using 1148 pieces of data obtained through subject experiments. Among them, the data without turning on the desktop fan, with the desktop fan blowing towards the face, and with the desktop fan blowing towards the hand each account for one-third. Test experiments are carried out on the desktop fan according to the method proposed in the present invention to generate various parameters. Then, the generated parameters are applied to the PCM respectively, and the final prediction effect is shown in Table 2.

[0085] Table 2

[0086]

[0087]

[0088] It can be seen from the results in Table 2 that after adding the parameters generated by the method proposed in the present invention, the prediction accuracy of the PCM has increased by 4% to 5%. In summary, the method proposed in the present invention can fully consider the use of the PCS, and the generated parameters can effectively improve the prediction performance of the PCM in the scenario of using the PCS.

[0089] The above are only the preferred embodiments of the present invention, and do not limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are all included in the protection scope of the present invention.

[0090] According to the individual comfort model optimization method based on a warm manikin in the embodiment of the present invention, it is possible to achieve a unified description of different types of PCSs and different usage methods of the same PCS, effectively reducing the cost of structural adjustment of the PCM in different PCS usage scenarios; fully considering the thermal evaluation of the human body under local thermal exposure by combining the thermal sensitivity information of each part, making the predicted value of the PCM closer to the actual thermal evaluation of the person at the physiological level and improving the prediction accuracy; an efficient and easy-to-implement test method, suitable for PCS R & D institutions to directly carry out tests and generate input parameters that meet the requirements of the PCM; in a new PCS usage scenario, the prediction performance of the PCM containing the parameters generated by this method has good reliability and does not require a large amount of new data to be supplemented for retraining (this item mainly aims at the PCM based on machine learning).

[0091] To implement the above embodiment, as Figure 5 shown, the present embodiment also provides an individual comfort model optimization system 10 based on a warm manikin, including:

[0092] A clothing thermal resistance measurement module for measuring the clothing thermal resistance in the usage scenarios of the Personal Comfort System (PCS).

[0093] A relevant parameter measurement module for arranging an artificial environmental climate chamber and setting different environmental conditions, starting the thermal manikin in a preset operation mode under each environmental condition, and respectively conducting tests without turning on the PCS and with turning on the PCS. After the thermal manikin reaches a stable state, record the heating power and surface temperature of each part of the thermal manikin.

[0094] A parameter optimization and generation module for calculating the power change value and power change percentage after turning on the PCS through the heating power of each part, calculating the equivalent temperature of each part, the difference between the equivalent temperature and the environmental temperature, and the thermal sensitivity temperature difference according to the clothing thermal resistance and the surface temperature of the thermal manikin, so as to generate the parameters of the Personal Comfort Model (PCM).

[0095] The individual comfort model optimization system based on the thermal manikin according to the embodiments of the present invention can achieve a unified description of different types of PCS and different usage methods of the same PCS, effectively reducing the cost of structural adjustment of the PCM in different PCS usage scenarios; fully considering the thermal evaluation of the human body under local heat exposure by combining the thermal sensitivity information of each part, making the predicted value of the PCM closer to the actual thermal evaluation of personnel at the physiological level and improving the prediction accuracy; an efficient and easy-to-implement test method, suitable for PCS R & D institutions to directly conduct tests and generate input parameters that meet the requirements of the PCM; in a new PCS usage scenario, the prediction performance of the PCM containing the parameters generated by this method has good reliability and does not require a large amount of new data to be supplemented for retraining (this item mainly aims at the PCM based on machine learning).

[0096] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

Claims

1. An individual comfort model optimization method based on a warm manikin, characterized in that: include: Determine the thermal resistance of clothing in the PCS usage scenario; Arrange an artificial climate chamber and set different environmental conditions. Start the thermal manikin in the preset operation mode under each environmental condition, and conduct tests without and with the PCS turned on. After the thermal manikin reaches a stable state, record the heating power and surface temperature of each part of the thermal manikin. The power change value and power change percentage after PCS is turned on are calculated based on the heating power of each part, and the equivalent temperature of each part, the difference between the equivalent temperature and the ambient temperature are calculated based on the thermal resistance of the clothing and the surface temperature of the thermal manikin. In addition, the thermal sensitivity temperature difference is calculated based on the thermal sensitivity of each part of the human body to generate the parameters of the individual comfort model PCM.

2. The method according to claim 1, characterized in that The operation mode of the thermal manikin is set to a constant surface temperature mode or a comfort mode, wherein the constant surface temperature mode sets the surface temperature of each area individually and sets the surface temperature according to the human skin temperature; the control logic of the comfort mode is to maintain the core temperature of the thermal manikin unchanged.

3. The method according to claim 1, characterized in that If the actual ambient temperature value selected is within the ambient temperature setting range of the artificial climate chamber, the power change value at the corresponding air temperature is directly selected as the generated parameter value. The calculation formula of the power change value is: Δw=w_on–w_off Among them, w_on is the measured value of the heating power when the PCS is turned on; w_off is the measured value of the heating power when the PCS is turned off; Δw is the power change value.

4. The method according to claim 1, characterized in that If the actual ambient temperature value selected is not within the ambient temperature setting range of the artificial climate chamber, perform linear regression on the heating power and air temperature, and obtain the relationship between the two. Calculate the parameter value according to the fitting formula. The fitting formula is as follows: w=a×Ta+b Where w is the heating power; Ta is the air temperature; a is the slope; and b is the intercept.

5. The method according to claim 4, characterized in that Get the fitting formula for heating power under different PCS operating conditions: PCS off condition is w = a1 × Ta + b1, PCS on condition is w = a2 × Ta + b2. In actual application, calculate w according to the PCS usage mode to obtain the parameter value required by PCM. For the percentage of power change, the calculation formula is as follows: w%=Δw / w_off Wherein, w% is the power change percentage.

6. The method according to claim 5, characterized in that The equivalent temperature of each part and the difference between the equivalent temperature and the ambient temperature are calculated based on the thermal resistance of the clothing and the surface temperature of the thermal manikin. The calculation formula of the equivalent temperature is as follows: Teq=Tsurf–0.155×I×w Among them, Teq is the equivalent temperature; Tsurf is the surface temperature; I is the thermal resistance of clothing.

7. The method according to claim 6, characterized in that The difference between the equivalent temperature and the ambient temperature is calculated as follows: ΔT=Teq–Ta Where ΔT is the difference between the equivalent temperature and the ambient temperature; Teq is the equivalent temperature.

8. The method according to claim 7, characterized in that The calculation formula of thermal sensitivity temperature difference is as follows: ΔTS=ΔT×S Among them, ΔTS is the thermal sensitivity temperature difference; ΔT is the difference between the equivalent temperature and the ambient temperature; S is the thermal sensitivity.

9. An individual comfort model optimization system based on a warm manikin, characterized in that: include: Clothing thermal resistance measurement module, used to measure clothing thermal resistance in the use scenario of the personal comfort system PCS; The relevant parameter measurement module is used to arrange the artificial environment climate chamber and set different environmental conditions. Under each environmental condition, the thermal manikin in the preset operation mode is started, and the test without opening the PCS and the test with opening the PCS are respectively performed. After the thermal manikin reaches a stable state, the heating power and surface temperature of each part of the thermal manikin are recorded; The parameter optimization generation module is used to calculate the power change value and power change percentage after PCS is turned on through the heating power of each part, and calculate the equivalent temperature of each part, the difference between the equivalent temperature and the ambient temperature according to the thermal resistance of the clothing and the surface temperature of the thermal manikin, and calculate the thermal sensitivity temperature difference according to the thermal sensitivity of each part of the human body, so as to generate the parameters of the individual comfort model PCM.

Images