CN111067493A - Human body thermal comfort prediction method - Google Patents
Human body thermal comfort prediction method Download PDFInfo
- Publication number
- CN111067493A CN111067493A CN201911318703.8A CN201911318703A CN111067493A CN 111067493 A CN111067493 A CN 111067493A CN 201911318703 A CN201911318703 A CN 201911318703A CN 111067493 A CN111067493 A CN 111067493A
- Authority
- CN
- China
- Prior art keywords
- model
- thermal comfort
- comfort prediction
- output
- human body
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
Abstract
The invention discloses a human body thermal comfort prediction method, which comprises the following specific steps: acquiring the change conditions of various physiological parameters and different working condition perception data of a normal person under the control of different metabolism levels and different environmental temperatures; establishing a neural network thermal comfort prediction model; and verifying the neural network thermal comfort prediction model. A method for predicting human body thermal comfort based on heart rate, blood pressure, skin temperature, respiratory frequency, oxygen consumption rate, and CO2Partial pressure and other information of a series of related physiological parameters are fused, and evaluation and analysis are carried out on thermal comfort of different metabolism levels and different environmental temperatures of a human body.
Description
Technical Field
The invention relates to the technical field of human body thermal comfort, in particular to a human body thermal comfort prediction method.
Background
The human body has self-regulation function and can adapt to different thermal environments. For example, when a person enters a cold environment from a warm environment, the body adapts to the new environment through a series of complex physiological processes, including vasoconstriction, chills, and the like. At the same time, heat transfer between the human body and the hot environment is a complex process involving radiation, convection, conduction, evaporation and respiration. Since the 60's of the 20 th century, the study of thermal comfort models for specific work environments has been developed, and the study of thermal comfort models for the human body has been in the past 50 years. The thermal interaction of the human body with the environment includes physiological and psychological reactions, and thus the thermal comfort model is further classified into a physiological or psychological model.
A complete thermal equilibrium thermal comfort model typically includes three parts: a detailed multi-segmented, multi-layer physical heat exchange model and garment model involving thermal interaction between the human body and the environment; a thermo-physiological regulation model, which simulates the passive and active thermal systems of the human body, and a psychological thermal sensation model, which predicts local and systemic thermal sensations. Most previous studies focused on heat and mass transfer mechanisms or thermoregulation models, while less concerned with thermal sensation and the subjective human response to the thermal environment. The response of people to an asymmetric environment is more complex than a homogeneous environment, since it depends not only on the overall comfort level but also on the comfort level of the local body part. The primary application at this stage is multi-element thermal comfort models, including multi-layer and multi-node structures. The current information technology and computing technology are developed at a high speed, the research and establishment of the thermal comfort model are not only stopped at the stage of linear solving, and a large number of complex nonlinear computing methods, such as a fuzzy neural network, are relatively suitable for establishing a complex model like human body thermal regulation and realizing automatic temperature control of special clothes. In the research of human thermal comfort, a thermal comfort model plays a crucial role.
Disclosure of Invention
In view of the above, the present invention provides a human thermal comfort prediction method, which includes a neural network metabolic rate prediction model and a thermal comfort prediction model, and is based on heart rate, blood pressure, skin temperature, respiratory frequency, oxygen consumption rate, and CO2Partial pressure and other information of a series of related physiological parameters are fused, and evaluation analysis is carried out on thermal comfort of different metabolic levels and different temperatures of a human body. Meanwhile, the method has better expansibility and also has an important reference function for dynamic evaluation of other human subjective systems.
In order to achieve the above purpose, the invention provides the following technical scheme:
a human body thermal comfort prediction method comprises the following specific steps:
acquiring the change conditions of various physiological parameters of a human body and different working condition perception data of a plurality of normal people at different metabolism levels and different temperatures;
calculating an actual metabolic rate according to the measured physiological parameters;
taking the metabolic rate and the physiological parameters as model input, taking the thermal comfort value as model output, substituting the model output into a model for training, and establishing a neural network thermal comfort prediction model;
carrying out simulation verification on the neural network thermal comfort prediction model;
analyzing the steady-state relation between human body metabolic parameters, metabolic rate and an environment control system, and establishing a thermal comfort prediction model;
and (5) verifying a thermal comfort prediction model.
Preferably, in the above method for predicting human thermal comfort, the physiological parameters include but are not limited to: heart rate, blood pressure, skin temperature, respiratory frequency, oxygen consumption rate, CO2Partial pressure, CO2The rate of formation.
Preferably, in the above method for predicting human thermal comfort, the method for acquiring the change of the perception data is to score and record thermal comfort perception under different working conditions.
Preferably, in one of the above-mentioned human thermal comfort prediction methods, the measured oxygen consumption rate and CO are used as a basis2Calculating an actual metabolic rate by using the generation rate as a metabolic prediction verification standard of the model, wherein the actual metabolic rate is calculated by using a formula as follows:
in the above formula, the first and second carbon atoms are,
is the oxygen consumption rate;
is CO2Generating a rate; wbIs body weight in kg; hbHeight is given in m.
Preferably, in the above method for predicting human thermal comfort, the heart rate, blood pressure, skin temperature, respiratory frequency and CO are measured2The method comprises the following steps of taking physiological parameters such as partial pressure and the like as model input, taking a thermal comfort value as model output, and establishing a neural network thermal comfort prediction model, wherein the neural network thermal comfort prediction model comprises a node output model, an action function model, an error calculation model and a self-learning model, and each model function is as follows:
① node output model:
hidden node output model: o isj＝f(∑Wij×Xi-qj)；
Output node output model: y isk＝f(∑Tjk×Oj-qk)；
② model of function:
a Sigmoid function defined with a function value continuous within (0, 1):
③ error calculation model:
④ self-learning model of Δ Wij(n+1)＝h×φi×Oj+a×ΔWij(n)。
Preferably, in the above method for predicting human thermal comfort, after training in the training set is completed, the simulation verification is performed by taking the remaining half of the data as a test set to perform simulation calculation verification, and setting an input matrix of the test set as Q, an output matrix as W, and an output matrix obtained after network simulation as R; the specific simulation verification method comprises the following steps: and (3) comparing the simulation result R with the original output result W of the test set after the simulation calculation is finished.
Preferably, in the method for predicting human thermal comfort, the subjects are subjected to load tests at different environmental temperatures and under different working conditions, and the thermal comfort perception of each working condition stage is scored and recorded; and the thermal comfort prediction model verification compares the thermal comfort prediction score calculated by the thermal comfort prediction model with the actual score of the tested object in the actual working condition process.
According to the technical scheme, compared with the prior art, the invention discloses a human body thermal comfort prediction method based on heart rate, blood pressure, skin temperature, breathing frequency, oxygen consumption and CO2Partial pressure and other information of a series of related physiological parameters are fused, and evaluation analysis is carried out on thermal comfort of different metabolic levels and different temperatures of a human body. During the operation of the model, the dynamic loss of physiological parameters does not influence the prediction of thermal comfort by the model, such as incapability of testing oxygen consumption and CO2Partial pressure and skin temperature, and the model can keep high prediction precision only by single heart rate input parameters. Meanwhile, the method has better expansibility and also has an important reference function for dynamic evaluation of other human subjective systems.
Due to the adoption of the technical scheme, the invention has the following advantages:
1. the invention establishes a thermal comfort prediction model based on the neural network, and can predict the thermal comfort of the human body directly based on physiological parameters.
2. The parameters included in the model are the most basic physiological parameters of the human body, the acquisition is convenient, the signals are stable, and the simplicity and the accuracy of the prediction model are ensured.
3. The algorithm adopted by the invention has stronger stability, and can still keep good accuracy under the condition of missing parameters and missing input parameters.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of error convergence in BP neural network training according to the present invention;
FIG. 3 is a diagram of heat collection comfort prediction results of BP neural network test according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a human body thermal comfort prediction method based on heart rate, blood pressure, skin temperature, breathing frequency, oxygen consumption rate and CO2Partial pressure and other information of a series of related physiological parameters are fused, and evaluation and analysis are carried out on thermal comfort of different metabolism levels and different environmental temperatures of a human body. Meanwhile, the method has better expansibility and also has an important reference function for dynamic evaluation of other human subjective systems.
The invention provides a human body thermal comfort prediction model, which comprises the following steps:
1) continuously monitoring physiological parameters and perception data of a human body under different workloads and different environmental control systems by using a portable pulmonary function instrument, and randomly selecting half of the data as a training set and the other half of the data as a test set;
2) creating and training a neural network thermal comfort prediction model: mixing heart rate, blood pressure, skin temperature, respiratory frequency and CO2A series of physiological parameters such as partial pressure and the like are used as model input, and the thermal comfort score is used as model output and is substituted into the model for training;
3) and (5) verifying a neural network thermal comfort prediction model.
In the step 1), the human physiological parameters refer to the experimental environment and the various temperature environments of the testeeHeart rate, blood pressure, skin temperature, breathing frequency, oxygen consumption rate, CO under various workloads2Partial pressure, etc. The physiological parameters are acquired and stored in real time through a portable pulmonary function instrument, and more than 1000 groups of effective data need to be acquired by a subject.
In the step 1), the different working loads refer to a plurality of different test working conditions and are a plurality of upper limb movement loads established based on the metabolism simulation apparatus.
In the step 2), the neural network prediction model comprises a node output model, an action function model, an error calculation model and a self-learning model, and each model function is as follows:
① node output model:
hidden node output model: o isj＝f(∑Wij×Xi-qj)；
Output node output model: y isk＝f(∑Tjk×Oj-qk)；
② model of function:
a Sigmoid function defined with a function value continuous within (0, 1):
③ error calculation model:
④ self-learning model of Δ Wij(n+1)＝h×φi×Oj+a×ΔWij(n)。
In the step 2), the neural network parameters are as shown in fig. 1.
In the step 3), the verification of the thermal comfort prediction model specifically refers to comparing the thermal comfort prediction score calculated by the model with the actual score of 8 tested subjects in the actual working condition process, and the result is shown in table 1:
TABLE 1 thermal comfort actual score and prediction model prediction values
As can be seen from the score comparison in Table 1, the average absolute error of the predicted score of the thermal comfort model and the tested actual score is +/-0.12, which is less than the minimum index value of 0.5 of the subjective thermal comfort score, so that the thermal comfort score prediction is basically realized by the thermal comfort model.
Further, the thermal comfort prediction model is not capable of inputting skin temperature, blood pressure and CO2Under the condition of physiological parameters such as partial pressure and the like, only heart rate and breathing frequency can be input as model input parameters, the thermal comfort value is output as a model, a neural network thermal comfort prediction model is established, the tested thermal comfort value is predicted, the thermal comfort prediction score calculated by the thermal comfort prediction model is compared with the actual subjective score of the tested in the actual working condition process, and the prediction precision of the table 1 can also be achieved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A human body thermal comfort prediction method is characterized by comprising the following specific steps:
acquiring the change conditions of various physiological parameters and different working condition perception data of a normal person under the control of different metabolism levels and different environmental temperatures;
calculating an actual metabolic rate according to the measured physiological parameters;
taking the metabolic rate and the physiological parameters as model input, taking the thermal comfort value as model output, substituting the model output into a model for training, and establishing a neural network thermal comfort prediction model;
and (5) verifying a thermal comfort prediction model.
2. The method of claim 1, wherein the physiological parameters include but are not limited to: heart rate, blood pressure, skin temperature, respiratory frequency, oxygen consumption rate, CO2Partial pressure, CO2The rate of formation.
3. The method according to claim 1, wherein the change of the perception data is obtained by scoring and recording the thermal comfort feelings under different environments.
4. The method of claim 1, wherein the heart rate, blood pressure, skin temperature, respiratory frequency and CO are measured2The method comprises the following steps of taking physiological parameters such as partial pressure and the like as model input, taking a thermal comfort value as model output, and establishing a neural network thermal comfort prediction model, wherein the neural network thermal comfort prediction model comprises a node output model, an action function model, an error calculation model and a self-learning model, and each model function is as follows:
① node output model:
hidden node output model: o isj＝f(∑Wij×Xi-qj)；
Output node output model: y isk＝f(∑Tjk×Oj-qk)；
② model of function:
defined as a function value within (0,1)Successive Sigmoid functions:
③ error calculation model:
④ self-learning model of Δ Wij(n+1)＝h×φi×Oj+a×ΔWij(n)。
5. The human thermal comfort prediction method according to claim 1, wherein after training of the training set is completed, simulation calculation verification is performed on the neural network thermal comfort prediction model, i.e. the remaining half of data is used as a test set, and an input matrix of the test set is set to be Q, an output matrix is set to be W, and an output matrix obtained after network simulation is set to be R; the specific simulation verification method comprises the following steps: and (3) comparing the simulation result R with the original output result W of the test set after the simulation calculation is finished.
6. The human thermal comfort prediction method according to claim 1, wherein the thermal comfort prediction model verification compares the thermal comfort prediction score calculated by the thermal comfort prediction model with the actual score of the human body during the actual working condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318703.8A CN111067493A (en) | 2019-12-19 | 2019-12-19 | Human body thermal comfort prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318703.8A CN111067493A (en) | 2019-12-19 | 2019-12-19 | Human body thermal comfort prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111067493A true CN111067493A (en) | 2020-04-28 |
Family
ID=70315875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911318703.8A Pending CN111067493A (en) | 2019-12-19 | 2019-12-19 | Human body thermal comfort prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111067493A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124007A (en) * | 2019-12-19 | 2020-05-08 | 中国人民解放军63919部队 | Special individual protective clothing self-adaptation liquid temperature adjusting device |
| CN113808743A (en) * | 2021-09-13 | 2021-12-17 | 中国矿业大学(北京) | Power grid outdoor operator heat stress early warning method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680025A (en) * | 2012-06-06 | 2012-09-19 | 安徽农业大学 | Indoor thermal comfort evaluation system |
| CN104490371A (en) * | 2014-12-30 | 2015-04-08 | 天津大学 | Heat comfort detection method based on physiological parameters of human body |
| CN110298487A (en) * | 2019-05-30 | 2019-10-01 | 同济大学 | It is a kind of for meeting the room temperature prediction technique of users ' individualized requirement |
| CN110377936A (en) * | 2019-06-06 | 2019-10-25 | 西安交通大学 | A kind of system and method for intelligent building personnel personalization hot comfort dynamic sensing |
-
2019
- 2019-12-19 CN CN201911318703.8A patent/CN111067493A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680025A (en) * | 2012-06-06 | 2012-09-19 | 安徽农业大学 | Indoor thermal comfort evaluation system |
| CN104490371A (en) * | 2014-12-30 | 2015-04-08 | 天津大学 | Heat comfort detection method based on physiological parameters of human body |
| CN110298487A (en) * | 2019-05-30 | 2019-10-01 | 同济大学 | It is a kind of for meeting the room temperature prediction technique of users ' individualized requirement |
| CN110377936A (en) * | 2019-06-06 | 2019-10-25 | 西安交通大学 | A kind of system and method for intelligent building personnel personalization hot comfort dynamic sensing |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111124007A (en) * | 2019-12-19 | 2020-05-08 | 中国人民解放军63919部队 | Special individual protective clothing self-adaptation liquid temperature adjusting device |
| CN113808743A (en) * | 2021-09-13 | 2021-12-17 | 中国矿业大学(北京) | Power grid outdoor operator heat stress early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104490371B (en) | A kind of thermal comfort detection method based on human body physiological parameter | |
| Li et al. | Experimental research of online monitoring and evaluation method of human thermal sensation in different active states based on wristband device | |
| Yeom et al. | Local body skin temperature-driven thermal sensation predictive model for the occupant's optimum productivity | |
| CN111067493A (en) | Human body thermal comfort prediction method | |
| Burzo et al. | Using infrared thermography and biosensors to detect thermal discomfort in a building’s inhabitants | |
| Zhao et al. | State-of-the-art, challenges and new perspectives of thermal comfort demand law for on-demand intelligent control of heating, ventilation, and air conditioning systems | |
| Li et al. | Correlation analysis and modeling of human thermal sensation with multiple physiological markers: An experimental study | |
| Chen et al. | Personal thermal comfort models based on physiological measurements–A design of experiments based review | |
| Na et al. | Metabolic rate estimation method using image deep learning | |
| Li et al. | A comprehensive review of impact assessment of indoor thermal environment on work and cognitive performance-Combined physiological measurements and machine learning | |
| Cao et al. | A review of research on dynamic thermal comfort | |
| Bogatu et al. | Human physiology for personal thermal comfort-based HVAC control–A review | |
| Omidvar et al. | A novel theoretical model for predicting the individuals’ thermal sensations based on air temperature and biomarkers measured by wearable devices | |
| Liu et al. | Non-invasive measurements of thermal discomfort for thermal preference prediction based on occupants' adaptive behavior recognition | |
| Wang et al. | Intrusive and non-intrusive early warning systems for thermal discomfort by analysis of body surface temperature | |
| Fan et al. | Real-time machine learning-based recognition of human thermal comfort-related activities using inertial measurement unit data | |
| CN111124007A (en) | Special individual protective clothing self-adaptation liquid temperature adjusting device | |
| Pei et al. | Biofeedback in the Dynamic VR Environments: A Method to Evaluate the Influence of Architectural Elements on Human Spatial Perception | |
| Liu et al. | Artificial neural network-based adaptive fluid temperature regulation of extravehicular activity suit | |
| Li et al. | Development and validation of mobile app and data management system for intelligent control of indoor thermal environment | |
| Chen et al. | Improved grey principal component analysis neural network based adaptive thermal comfort model: Application in the enclosed cabin with microclimatic conditions | |
| Zhao et al. | On-line adaptive personalized dynamic thermal comfort (PDTC) model using recursive least square estimation | |
| Barone et al. | Modelling the thermal response of the human body for thermal comfort assessment in indoor spaces: an experimental validation | |
| Wu et al. | Subjective environmental evaluation based on combination method of VR and EEG | |
| Yeom et al. | Thermal preferences and cognitive performance estimation via user's physiological responses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |