WO2020056811A1 - Comprehensive index calculation method for characterizing comprehensive quality of indoor environment - Google Patents

Comprehensive index calculation method for characterizing comprehensive quality of indoor environment Download PDF

Info

Publication number
WO2020056811A1
WO2020056811A1 PCT/CN2018/109857 CN2018109857W WO2020056811A1 WO 2020056811 A1 WO2020056811 A1 WO 2020056811A1 CN 2018109857 W CN2018109857 W CN 2018109857W WO 2020056811 A1 WO2020056811 A1 WO 2020056811A1
Authority
WO
WIPO (PCT)
Prior art keywords
environmental
indoor environment
quality
comprehensive
weight
Prior art date
Application number
PCT/CN2018/109857
Other languages
French (fr)
Chinese (zh)
Inventor
卞春
孙宝石
曹石
Original Assignee
苏州数言信息技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 苏州数言信息技术有限公司 filed Critical 苏州数言信息技术有限公司
Publication of WO2020056811A1 publication Critical patent/WO2020056811A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Definitions

  • the invention belongs to the technical field of indoor environmental quality monitoring, and relates to a comprehensive index calculation method that characterizes the comprehensive quality of indoor environment.
  • the quality of the indoor environment is directly related to the physical and mental health of the user, especially the indoor environment of the classroom.
  • the classroom is an important place for children to learn and live every day.
  • the quality of the indoor environment in the classroom is directly related to the physical and mental health of the child.
  • the current indoor environmental quality of classrooms in elementary and middle schools in China is not optimistic. For example, an article published by Dongfang.com on "How to Control Air Pollution in Primary and Middle School classrooms?" The article of the People's Congress Deputies Advising Shanghai to Make Local Regulations pointed out the status quo.
  • a survey report on the visual health and visual environment of elementary and middle school students caused concern among parents.
  • the technical problem to be solved by the present invention is to provide a comprehensive index calculation method that characterizes the comprehensive quality of the indoor environment, quantifies the quality index of the indoor environment, simplifies the quality of the complex indoor environment to a quantity, and then calculates the indoor environment characteristic from the quantity analysis.
  • the comprehensive quality data index can be used to evaluate both the qualitative and quantitative indoor environment comprehensive quality.
  • the present invention provides a comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment, including:
  • the weight w i represents the degree of influence of the environmental parameter u i on the environmental quality
  • n the number of environmental parameters.
  • X [x 1 x 2 x 3 ... x i ... x n ] , And satisfy x i ⁇ ⁇ 0,1 ⁇ ;
  • u min u i a predetermined minimum value in the national standard of environmental parameters
  • u max u i predetermined maximum value in the national standard of environmental parameters
  • the environment contribution function f i ⁇ ⁇ f1 i , f2 i , f3 i ⁇ is further determined according to the fuzzy comprehensive evaluation method
  • Equation 3-1 a i is the value of the environmental parameter when the environmental contribution function reaches the optimum, and b i is the value of the environmental parameter when the environmental contribution function reaches the worst;
  • Equation 3-2 a i is the value of the environmental parameter when the environmental contribution function reaches the worst, and b i is the value of the environmental parameter when the environmental contribution function reaches the optimal;
  • a i, d i is the value of an environmental parameter when the function reaches the worst environmental contribution, a i ⁇ d i; b i, c i is a function of environmental contribution optimal environment parameter values, b i ⁇ c i .
  • the environmental parameters further include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide, and noise.
  • the quality of the indoor environment is further divided into several levels, including but not limited to excellent, good, medium, poor, and inferior;
  • the method further includes using a machine deep learning method or / and a factor analysis method in statistics to determine the weight of the environmental parameter; when the target data sample used to calculate the comprehensive index is less than or equal to a set value, Use the factor analysis method to determine the weight of the environmental parameters; when it exceeds the set value, use the machine deep learning method to determine the weight of the environmental parameters.
  • the process of further determining the weight of the environment parameter by using the machine deep learning method is:
  • Environmental parameter data including but not limited to temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide and noise;
  • a weight model obtained by training is used to perform a weight analysis on the characteristics of the environment parameter to obtain a weight of the environment parameter.
  • the method further includes obtaining the weight model through model training.
  • the training process is:
  • the weighted model is obtained by training the characterized data samples based on a related algorithm.
  • the training process that further includes the weight model further includes:
  • the optimal weight model is used to perform weight analysis on the characteristics of the environmental parameters to obtain the weight of the environmental parameters.
  • further related algorithms for training to obtain weight models include, but are not limited to, machine learning algorithms, convolutional neural network algorithms, recurrent neural network algorithms, decision trees, and Bayesian decision theory-based Classification algorithms and deep learning algorithms.
  • the invention calculates a comprehensive index for characterizing the comprehensive quality of the indoor environment, quantifies the quality index of the indoor environment, simplifies the quality of the complex indoor environment into a quantity, and then calculates a data indicator representing the comprehensive quality of the indoor environment from the quantity analysis, thereby obtaining
  • the comprehensive index can evaluate the comprehensive quality of indoor environment both qualitatively and quantitatively.
  • the present invention has the following technical advantages:
  • FIG. 1 is a flowchart of a comprehensive index calculation method in a preferred embodiment of the present invention
  • FIG. 2 is a flowchart of determining the weight of an environmental parameter when a data sample exceeds a set value in a preferred embodiment of the present invention
  • FIG. 3 is a flowchart of training a weight model
  • FIG. 6 is a functional relationship diagram of f3 i .
  • temperature (° C), humidity (%), illuminance (Lux), color temperature (K), PM2.5 (mg / m 3 ), PM10 (mg / m 3 ), carbon dioxide (mg / m 3 ), formaldehyde ( mg / m 3 ), TVOC (mg / m 3 ), noise (dB).
  • this embodiment discloses a comprehensive index calculation method that characterizes the comprehensive quality of the indoor environment.
  • the comprehensive index for the indoor environment in Table 1 is calculated, including:
  • X [x 1 x 2 x 3 ... x i ... x n ], and satisfy x i ⁇ ⁇ 0, 1 ⁇ ;
  • u min u i a predetermined minimum value in the national standard of environmental parameters
  • u max u i predetermined maximum value in the national standard of environmental parameters
  • the weight w i represents the degree of influence of the environmental parameter u i on environmental quality.
  • W [0.1 0.1 0.2 0.2 0 0 0.1 0 0 0.3].
  • the environmental parameter data samples in Table 1 are imported into the SPSS software, and on the SPSS interface, click "Select Analysis-> Dimension Reduction-> Factor Analysis Method" to directly obtain the weight corresponding to each environmental parameter u i , thereby The above weight matrix.
  • n the number of environmental parameters.
  • the environmental contribution function f i ⁇ ⁇ f1 i , f2 i , f3 i ⁇ of the environmental parameters is determined according to the fuzzy comprehensive evaluation method; f1 i is small, f2 i is large, and f3 i is intermediate.
  • a small value means that the value of the environmental parameter index is as small as possible, for example, a smaller carbon dioxide concentration is better;
  • a large value means that the value of the environmental parameter index is larger and better;
  • the middle type is the value of the environmental parameter index
  • the middle section is the best. For example, the value of the middle section is the best for illumination, color temperature and temperature.
  • Equation 3-1 a i is the value of the environmental parameter when the environmental contribution function reaches the optimum, and b i is the value of the environmental parameter when the environmental contribution function reaches the worst;
  • Equation 3-2 a i is the value of the environmental parameter when the environmental contribution function reaches the worst, and b i is the value of the environmental parameter when the environmental contribution function reaches the optimal;
  • a i, d i is the value of an environmental parameter when the function reaches the worst environmental contribution, a i ⁇ d i; b i, c i is a function of environmental contribution optimal environment parameter values, b i ⁇ c i .
  • A2 Determine the value of the environmental contribution function of carbon dioxide:
  • the contribution function of carbon dioxide to the environment conforms to a small-scale function form, that is, when it exceeds the limit set by the state, it will become worse or worse, and it will not meet people's activities.
  • the calculated environmental contribution function for temperature is 1.
  • the comprehensive indicators of indoor environmental quality are divided into several levels, including but not limited to excellent, good, medium, poor, and inferior;
  • the indoor environment in Table 1 can be determined by the calculation method of the present invention to have an excellent environmental level.
  • trapezoidal or semi-ladder function form is a typical example of determining the value of the environmental contribution function. According to the actual situation, other function forms can also be used, such as: quadratic function, power function, logarithmic function, Sigmoid Wait.
  • environmental parameter data include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide, and noise.
  • environmental parameter data include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide, and noise.
  • Collect various environmental parameter data in the current state through various sensors distributed in the environment, for example, the temperature sensor collects the current temperature of 28 ° C, the humidity sensor collects 47% of humidity, etc. Data of various environmental parameters in the current state.
  • the foregoing weight model is obtained through training.
  • the training process is as follows:
  • Environmental parameters include, but are not limited to, temperature, humidity, illumination, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide and noise.
  • Collect various environmental parameter data in the current state through various sensors distributed in the environment, for example, the temperature sensor collects the current temperature of 28 ° C, the humidity sensor collects 47% of humidity, etc. Data samples of various environmental parameters in the current state.
  • the feature parameters of the environmental parameter data samples are extracted in combination with the use scenarios of the indoor environment to obtain the characterized data samples.
  • the use scenario of the indoor environment except for normal data samples and non-working time data samples.
  • the collected data is abnormal (far greater than or far less than the normal value), or when the power-off state is output, "-" is output, and such abnormal data samples are eliminated by the feature extraction unit.
  • the time of the indoor environment is normally from 9:00 to 17:00, and data samples other than this working time are eliminated by the feature extraction unit.
  • the characterized data samples are randomly divided into training data groups and test data groups. Specifically, 80% of all characterized data samples are classified as training data groups and 20% are classified as test data groups.
  • the characteristic data samples are trained based on the correlation algorithm to obtain a weight model.
  • related algorithms include, but are not limited to, machine learning algorithms, convolutional neural network algorithms, recurrent neural network algorithms, decision trees, classification algorithms based on Bayesian decision theory, and deep learning algorithms.
  • the model training unit uses the above several related algorithms to separately train data samples to obtain several weight models.
  • the data samples in the test data set are used to test and verify the performance of several weight models. Among the several weight models, the one with the highest matching degree is selected as the optimal weight model. For example, the data samples in the test data set are imported into each weight model to see whether the weights output by each weight model match the actual situation, and the weight model with the highest matching degree is selected as the optimal weight model.
  • the matching degree of the optimal weight model is not less than 95%. After testing and verification, if the matching degree of all weight models is less than 95%, the weighting model with the highest matching degree is iteratively optimized until the matching degree is not less than 95%.

Abstract

A comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment, comprising determining an environment parameter matrix U＝[u 1 u2 u3 ... ui ... un] in view of the usage scenario of an indoor environment; determining a weight matrix of environment parameters in view of the usage scenario of the indoor environment: W＝[w1 w2 w3 ... wi ... wn], wherein w1+w2+w3+...+wi+...+wn＝1; and the weight wi of the environment parameters characterizes the degree of influence of the environment parameters ui on the quality of the environment; determining an environment contribution function value matrix of the environment parameters in view of the usage scenario of the indoor environment: F＝[f1 f2 f3 ... fi ... fn], wherein fi∈[0, 1]; the environment contribution function fi of the environment parameters characterizes the function relationship of the degree of influence of the environment parameters ui on the environment quality index, i.e., fi＝f(ui); and calculating the comprehensive index of the indoor environment quality according to the following formula. The comprehensive index calculation method quantifies the quality index of the indoor environment and simplifies complex indoor environment quality into numbers to calculate a data index characterizing the comprehensive quality of the indoor environment from the analysis of numbers, and thus the obtained comprehensive index may qualitatively and quantitatively evaluate the comprehensive quality of the indoor environment.

Description

表征室内环境综合质量的综合指标计算方法Calculation method of comprehensive index characterizing comprehensive quality of indoor environment 技术领域Technical field
本发明属于室内环境质量监测技术领域，涉及一种表征室内环境综合质量的综合指标计算方法。The invention belongs to the technical field of indoor environmental quality monitoring, and relates to a comprehensive index calculation method that characterizes the comprehensive quality of indoor environment.
背景技术Background technique
室内环境质量的好坏直接关系到使用者的身心健康，尤其是教室室内环境，教室是孩子每天学习生活的重要场所，教室室内环境质量的好坏直接关系到孩子的身心健康。然而，目前国内中小学教室室内环境质量却很不容乐观，如2017-02-09 14：21东方网发布的一篇关于《中小学教室空气污染如何治理？人大代表建议上海制定地方法规》的文章指出了现状。2016年6月初，在全国爱眼日前夕，一份和中小学生视觉健康、视觉环境有关的调查报告引起了家长的担忧，报告显示，广州中小学教室环境不良问题较为严重，教室的黑板照度达到要求的仅占8.8％，桌面照度达到国家要求的仅占34.2％，据悉，这份调查报告具有较高代表性，是依据国家颁布的教室照明新标准进行的。测量室内环境质量的客观物理指标有很多，包括照度、色温、温度、湿度、PM2.5浓度、二氧化碳浓度等等。目前可以通过各种传感器测量这些物理指标，然后将各项指标的数值报告给相关信息使用者。这样做的问题在于相关信息使用者通常无法直观地理解这些物理指标与身心健康的关系。目前的室内环境质量指标缺少对环境质量的综合量化评价，缺少易于理解的指标。此外，目前对室内环境质量的评价也没有考虑某些室内环境参数的最优配置与教学场景和学生活动内容的关 系。The quality of the indoor environment is directly related to the physical and mental health of the user, especially the indoor environment of the classroom. The classroom is an important place for children to learn and live every day. The quality of the indoor environment in the classroom is directly related to the physical and mental health of the child. However, the current indoor environmental quality of classrooms in elementary and middle schools in China is not optimistic. For example, an article published by Dongfang.com on "How to Control Air Pollution in Primary and Middle School Classrooms?" The article of the People's Congress Deputies Advising Shanghai to Make Local Regulations pointed out the status quo. At the beginning of June 2016, on the eve of National Eye Love Day, a survey report on the visual health and visual environment of elementary and middle school students caused concern among parents. The report showed that the classroom environment in Guangzhou's primary and secondary schools was more serious, and the blackboard illumination in the classroom reached Only 8.8% of the requirements are met, and only 34.2% of the desktop illumination meets the national requirements. It is reported that this survey report is highly representative and is based on the new classroom lighting standards issued by the state. There are many objective physical indicators for measuring indoor environmental quality, including illumination, color temperature, temperature, humidity, PM2.5 concentration, carbon dioxide concentration, and so on. At present, these physical indicators can be measured by various sensors, and then the values of each indicator are reported to relevant information users. The problem with this is that users of related information often cannot intuitively understand the relationship between these physical indicators and physical and mental health. The current indoor environmental quality indicators lack a comprehensive quantitative assessment of environmental quality and lack easy-to-understand indicators. In addition, the current assessment of indoor environmental quality does not take into account the relationship between the optimal configuration of certain indoor environmental parameters and teaching scenarios and student activities.
发明内容Summary of the Invention
本发明要解决的技术问题是提供一种表征室内环境综合质量的综合指标计算方法，量化室内环境的质量指标，把复杂的室内环境质量简化为数量，进而从数量的分析中计算出表征室内环境综合质量的数据指标，以此获得的综合指标既能定性又能定量的评价室内环境综合质量。The technical problem to be solved by the present invention is to provide a comprehensive index calculation method that characterizes the comprehensive quality of the indoor environment, quantifies the quality index of the indoor environment, simplifies the quality of the complex indoor environment to a quantity, and then calculates the indoor environment characteristic from the quantity analysis. The comprehensive quality data index can be used to evaluate both the qualitative and quantitative indoor environment comprehensive quality.
为了解决上述技术问题，本发明提供了一种表征室内环境综合质量的综合指标计算方法，包括：In order to solve the above technical problems, the present invention provides a comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment, including:
结合室内环境的使用场景确定环境参数矩阵U＝[u 1 u 2 u 3 ... u i ... u n]； Determine the environmental parameter matrix U = [u 1 u 2 u 3 ... u i ... u n ] in combination with the use scenario of the indoor environment;
结合室内环境的使用场景确定环境参数的权重矩阵：Determine the weight matrix of environmental parameters based on the indoor environment's use scenario:
W＝[w 1 w 2 w 3 ... w i ... w n]，且满足w 1+w 2+w 3+...+w i+...+w n＝1；环境参数的权重w i表征环境参数u i对环境质量的影响程度； W = [w 1 w 2 w 3 ... w i ... w n ], and satisfy w 1 + w 2 + w 3 + ... + w i + ... + w n = 1; environmental parameter The weight w i represents the degree of influence of the environmental parameter u i on the environmental quality;
结合室内环境的使用场景确定环境参数的环境贡献函数值矩阵：Determine the environmental contribution function value matrix of the environmental parameters in combination with the use environment of the indoor environment:
F＝[f 1 f 2 f 3 ... f i ... f n]，且满足f i∈[0，1]；环境参数的环境贡献函数f i表征环境参数u i对环境质量指标影响程度的函数关系，即f i＝f(u i)； F = [f 1 f 2 f 3 ... f i ... f n ] and satisfies f i ∈ [0, 1]; the environmental contribution function f i of the environmental parameter represents the influence of the environmental parameter u i on the environmental quality index A functional relationship of degree, that is, f i = f (u i );
根据公式一计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index E-IEQ of indoor environmental quality according to formula 1:
Figure PCTCN2018109857-appb-000001
Figure PCTCN2018109857-appb-000001
其中，n表示环境参数的数量。Among them, n represents the number of environmental parameters.
本发明一个较佳实施例中，进一步包括其还包括结合室内环境的使用场景确定环境参数的一票否决权矩阵：X＝[x 1 x 2 x 3 ... x i ... x n]，且满足x i∈{0，1}； In a preferred embodiment of the present invention, it further includes a one-vote veto matrix for determining environmental parameters in combination with an indoor environment usage scenario: X = [x 1 x 2 x 3 ... x i ... x n ] , And satisfy x i ∈ {0,1};
当u i≥u max或者u i≤u min时，x i＝0； When u i ≥ u max or u i ≤ u min , x i = 0;
当u min＜u i＜u max时，x i＝1； When u min <u i <u max , x i = 1;
其中，u min为环境参数u i在国标中规定的最小值，u max为环境参数u i在国标中规定的最大值； Wherein, u min u i a predetermined minimum value in the national standard of environmental parameters, u max u i predetermined maximum value in the national standard of environmental parameters;
根据公式二计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index of indoor environmental quality E-IEQ according to formula 2:
Figure PCTCN2018109857-appb-000002
Figure PCTCN2018109857-appb-000002
本发明一个较佳实施例中，进一步包括根据模糊综合评价法确定环境参数的环境贡献函数f i∈{f1 i，f2 i，f3 i}； In a preferred embodiment of the present invention, the environment contribution function f i ∈ {f1 i , f2 i , f3 i } is further determined according to the fuzzy comprehensive evaluation method;
Figure PCTCN2018109857-appb-000003
Figure PCTCN2018109857-appb-000003
Figure PCTCN2018109857-appb-000004
Figure PCTCN2018109857-appb-000004
Figure PCTCN2018109857-appb-000005
Figure PCTCN2018109857-appb-000005
其中，式3-1中：a i为环境贡献函数达到最优时环境参数的取值，b i为环境贡献函数达到最差时环境参数的取值； Among them, in Equation 3-1: a i is the value of the environmental parameter when the environmental contribution function reaches the optimum, and b i is the value of the environmental parameter when the environmental contribution function reaches the worst;
式3-2中：a i为环境贡献函数达到最差时环境参数的取值，b i为环境贡献函数达到最优时环境参数的取值； In Equation 3-2: a i is the value of the environmental parameter when the environmental contribution function reaches the worst, and b i is the value of the environmental parameter when the environmental contribution function reaches the optimal;
式3-3中：a i、d i为环境贡献函数达到最差时环境参数的取值，a i＜d i；b i、 c i为环境贡献函数达到最优时环境参数的取值，b i＜c i。 3-3 formula: a i, d i is the value of an environmental parameter when the function reaches the worst environmental contribution, a i <d i; b i, c i is a function of environmental contribution optimal environment parameter values, b i <c i .
本发明一个较佳实施例中，进一步包括所述环境参数包括但不局限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音。In a preferred embodiment of the present invention, the environmental parameters further include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide, and noise.
本发明一个较佳实施例中，进一步包括将所述室内环境质量分为若干个等级，包括但不局限于优秀、良好、中等、差、劣；In a preferred embodiment of the present invention, the quality of the indoor environment is further divided into several levels, including but not limited to excellent, good, medium, poor, and inferior;
综合指标E-IEQ∈[0.9，1]时，所述室内环境质量为优秀；When the comprehensive index E-IEQ ∈ [0.9, 1], the indoor environment quality is excellent;
综合指标E-IEQ∈[0.8，0.9)时，所述室内环境质量为良好；When the comprehensive index E-IEQ ∈ [0.8, 0.9), the indoor environment quality is good;
综合指标E-IEQ∈[0.7，0.8)时，所述室内环境质量为中等；When the comprehensive index E-IEQ ∈ [0.7, 0.8), the indoor environment quality is medium;
综合指标E-IEQ∈[0.6，0.7)时，所述室内环境质量为差；When the comprehensive index E-IEQ ∈ [0.6, 0.7), the indoor environment quality is poor;
综合指标E-IEQ∈[0，0.6)时，所述室内环境质量为良好。When the comprehensive index E-IEQ ∈ [0, 0.6), the indoor environment quality is good.
本发明一个较佳实施例中，进一步包括使用机器深度学习法或/和统计学中的因子分析法确定所述环境参数的权重；用于计算综合指的标数据样本小于等于设定值时，使用因子分析法确定环境参数的权重；超过设定值时，使用机器深度学习法确定环境参数的权重。In a preferred embodiment of the present invention, the method further includes using a machine deep learning method or / and a factor analysis method in statistics to determine the weight of the environmental parameter; when the target data sample used to calculate the comprehensive index is less than or equal to a set value, Use the factor analysis method to determine the weight of the environmental parameters; when it exceeds the set value, use the machine deep learning method to determine the weight of the environmental parameters.
本发明一个较佳实施例中，进一步包括使用机器深度学习法确定环境参数权重的过程为，In a preferred embodiment of the present invention, the process of further determining the weight of the environment parameter by using the machine deep learning method is:
采集环境参数数据，所述环境参数包括但不限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音；Collect environmental parameter data, including but not limited to temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide and noise;
结合室内环境的使用场景对所述环境参数数据进行特征提取，获得环境参数特征；Performing feature extraction on the environmental parameter data in combination with an indoor environment use scenario to obtain environmental parameter characteristics;
使用经训练获得的权重模型对所述环境参数特征做权重分析，获得环境参 数的权重。A weight model obtained by training is used to perform a weight analysis on the characteristics of the environment parameter to obtain a weight of the environment parameter.
本发明一个较佳实施例中，进一步包括通过模型训练获得所述权重模型，其训练过程为，In a preferred embodiment of the present invention, the method further includes obtaining the weight model through model training. The training process is:
获取用作样本的环境参数数据样本；Obtain a sample of environmental parameter data used as a sample;
结合室内环境的使用场景对环境参数数据样本进行特征提取，获得特征化后的数据样本；Feature extraction of environmental parameter data samples in combination with indoor environment usage scenarios to obtain characterized data samples;
基于相关算法训练特征化后的数据样本，获得所述权重模型。The weighted model is obtained by training the characterized data samples based on a related algorithm.
本发明一个较佳实施例中，进一步包括所述权重模型的训练过程还包括，In a preferred embodiment of the present invention, the training process that further includes the weight model further includes:
对特征后的数据样本进行随机分组，分为训练数据组和测试数据组，使用训练数据组中的数据样本进行模型训练获得所述权重模型；Randomly grouping the characteristic data samples into training data groups and test data groups, and using the data samples in the training data group to perform model training to obtain the weight model;
使用若干个相关算法分别训练所述训练数据组中的数据样本，获得若干个权重模型；Using several related algorithms to separately train data samples in the training data set to obtain several weight models;
使用所述测试数据组中的数据样本分别测试验证所述若干个权重模型的性能，在所述若干个权重模型中选取匹配度最高的一个为最优权重模型；Use the data samples in the test data set to test and verify the performance of the several weight models, and select the one with the highest matching degree among the several weight models as the optimal weight model;
使用最优权重模型对环境参数特征做权重分析，获得环境参数的权重。The optimal weight model is used to perform weight analysis on the characteristics of the environmental parameters to obtain the weight of the environmental parameters.
本发明一个较佳实施例中，进一步包括用于训练获得权重模型的相关算法包括但不局限于机器学习算法、卷积神经网络算法、循环神经网络算法、决策树、基于贝叶斯决策理论的分类算法和深度学习算法。In a preferred embodiment of the present invention, further related algorithms for training to obtain weight models include, but are not limited to, machine learning algorithms, convolutional neural network algorithms, recurrent neural network algorithms, decision trees, and Bayesian decision theory-based Classification algorithms and deep learning algorithms.
本发明表征室内环境综合质量的综合指标计算方法，量化室内环境的质量指标，把复杂的室内环境质量简化为数量，进而从数量的分析中计算出表征室内环境综合质量的数据指标，以此获得的综合指标既能定性又能定量的评价室 内环境综合质量。The invention calculates a comprehensive index for characterizing the comprehensive quality of the indoor environment, quantifies the quality index of the indoor environment, simplifies the quality of the complex indoor environment into a quantity, and then calculates a data indicator representing the comprehensive quality of the indoor environment from the quantity analysis, thereby obtaining The comprehensive index can evaluate the comprehensive quality of indoor environment both qualitatively and quantitatively.
相较于现有技术，本发明具有以下技术优势：Compared with the prior art, the present invention has the following technical advantages:
其一、结合室内环境的实际使用场景为本发明整个计算方法的基础，重视不同使用场景下环境参数指标的差异性，以此获得的综合指标更科学、更合理、更准确。First, combining the actual usage scenarios of the indoor environment is the basis of the entire calculation method of the present invention. The difference in environmental parameter indicators under different usage scenarios is valued, and the comprehensive indicators obtained through this are more scientific, more reasonable, and more accurate.
其二、综合室内环境的多项环境参数、并结合实际使用场景，通过分析建立模型来支管的表示不同市场长江下的室内环境质量，分值越高说明说明室内环境越适合当前的使用场景。Secondly, by integrating multiple environmental parameters of the indoor environment and combining with actual use scenarios, the analysis and establishment of a model to represent the indoor environment quality under the Yangtze River in different markets is indicated. A higher score indicates that the indoor environment is more suitable for the current use scenario.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是本发明优选实施例中综合指标计算方法的流程图；1 is a flowchart of a comprehensive index calculation method in a preferred embodiment of the present invention;
图2是本发明优选实施例中数据样本超过设定值时确定环境参数权重的流程图；2 is a flowchart of determining the weight of an environmental parameter when a data sample exceeds a set value in a preferred embodiment of the present invention;
图3是训练获得权重模型的流程图；FIG. 3 is a flowchart of training a weight model;
图4是f1 i的函数关系图； 4 is a functional relationship diagram of f1 i ;
图5是f2 i的函数关系图； 5 is a functional relationship diagram of f2 i ;
图6是f3 i的函数关系图。 FIG. 6 is a functional relationship diagram of f3 i .
具体实施方式detailed description
下面结合附图和具体实施例对本发明作进一步说明，以使本领域的技术人员可以更好地理解本发明并能予以实施，但所举实施例不作为对本发明的限定。The present invention will be further described below with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.
实施例Examples
s＝夏季、S＝考试场景下采集教室内的环境参数如表1所示。表1s = summer, S = environmental parameters collected in the classroom under the test scene are shown in Table 1. Table 1
Figure PCTCN2018109857-appb-000006
Figure PCTCN2018109857-appb-000006
其中，温度(℃)、湿度(％)、照度(Lux)、色温(K)、PM2.5(mg/m 3)、PM10(mg/m 3)、二氧化碳(mg/m 3)、甲醛(mg/m 3)、TVOC(mg/m 3)、噪音(dB)。 Among them, temperature (° C), humidity (%), illuminance (Lux), color temperature (K), PM2.5 (mg / m 3 ), PM10 (mg / m 3 ), carbon dioxide (mg / m 3 ), formaldehyde ( mg / m 3 ), TVOC (mg / m 3 ), noise (dB).
如图1所示，本实施例公开了一种表征室内环境综合质量的综合指标计算方法，计算表1中室内环境下的综合指标，包括：As shown in FIG. 1, this embodiment discloses a comprehensive index calculation method that characterizes the comprehensive quality of the indoor environment. The comprehensive index for the indoor environment in Table 1 is calculated, including:
(1)结合室内环境的使用场景确定环境参数矩阵U＝[u 1 u 2 u 3 ... u i ... u n]； (1) Determine the environmental parameter matrix U = [u 1 u 2 u 3 ... u i ... u n ] in combination with the use scenario of the indoor environment;
对应表1确定环境参数矩阵U，Correspond to Table 1 to determine the environmental parameter matrix U,
U＝[温度，湿度，照度，色温，PM2.5，PM10，二氧化碳，甲醛，TVOC，噪音]。U = [temperature, humidity, illuminance, color temperature, PM2.5, PM10, carbon dioxide, formaldehyde, TVOC, noise].
(2)结合室内环境的使用场景确定环境参数的一票否决权矩阵：(2) A one-vote veto matrix for determining environmental parameters in combination with the use scenario of the indoor environment:
X＝[x 1 x 2 x 3 ... x i ... x n]，且满足x i∈{0，1}； X = [x 1 x 2 x 3 ... x i ... x n ], and satisfy x i ∈ {0, 1};
当u i≥u max或者u i≤u min时，x i＝0； When u i ≥ u max or u i ≤ u min , x i = 0;
当u min＜u i＜u max时，x i＝1； When u min <u i <u max , x i = 1;
其中，u min为环境参数u i在国标中规定的最小值，u max为环境参数u i在国标中规定的最大值。 Wherein, u min u i a predetermined minimum value in the national standard of environmental parameters, u max u i predetermined maximum value in the national standard of environmental parameters.
对应S＝考试场景，s＝夏季，照度和噪音对考试影响较大，对应表1确定环境参数的一票否决权矩阵X：X＝[1 1 0 1 1 1 1 1 1 0]。Corresponds to S = exam scene, s = summer season, illumination and noise have a great impact on the exam. Correspond to Table 1 to determine the one-vote veto matrix X of the environmental parameters: X = [1,1,1,1,1,0].
(3)结合室内环境的使用场景确定环境参数的权重矩阵：(3) Determine the weight matrix of environmental parameters in combination with the use scenario of the indoor environment:
W＝[w 1 w 2 w 3 ... w i ... w n]，且满足w 1+w 2+w 3+...+w i+...+w n＝1；环境参数的权重w i表征环境参数u i对环境质量的影响程度。 W = [w 1 w 2 w 3 ... w i ... w n ], and satisfy w 1 + w 2 + w 3 + ... + w i + ... + w n = 1; environmental parameter The weight w i represents the degree of influence of the environmental parameter u i on environmental quality.
由于数据样本比较小，本实施例技术方案中优选使用统计学工具SPSS中的因子分析法确定权重矩阵W：W＝[0.1 0.1 0.2 0.2 0 0 0.1 0 0 0.3]。此处，将表1中的环境参数数据样本导入SPSS软件，在SPSS界面上点击″选择分析-＞降维-＞因子分析法″，直接获得对应每个环境参数u i的权重，由此获得以上权重矩阵。 Because the data sample is relatively small, in the technical solution of this embodiment, it is preferable to use a factor analysis method in the statistical tool SPSS to determine the weight matrix W: W = [0.1 0.1 0.2 0.2 0 0 0.1 0 0 0.3]. Here, the environmental parameter data samples in Table 1 are imported into the SPSS software, and on the SPSS interface, click "Select Analysis-> Dimension Reduction-> Factor Analysis Method" to directly obtain the weight corresponding to each environmental parameter u i , thereby The above weight matrix.
(4)结合室内环境的使用场景确定环境参数的环境贡献函数值矩阵：F＝[f 1 f 2 f 3 ... f i ... f n]，且满足f i∈[0，1]；环境参数的环境贡献函数f i表征环境参数u i对环境质量指标影响程度的函数关系，即f i＝f(u i)； (4) Determine the environmental contribution function value matrix of the environmental parameters in combination with the use scenario of the indoor environment: F = [f 1 f 2 f 3 ... f i ... f n ], and satisfy f i ∈ [0, 1] ; The environmental contribution function f i of the environmental parameters characterizes the functional relationship between the environmental parameter u i and the environmental quality index, ie, f i = f (u i );
根据公式二计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index of indoor environmental quality E-IEQ according to formula 2:
Figure PCTCN2018109857-appb-000007
Figure PCTCN2018109857-appb-000007
其中，n表示环境参数的数量。Among them, n represents the number of environmental parameters.
本发明优选技术方案中，根据模糊综合评价法确定环境参数的环境贡献函数f i∈{f1 i，f2 i，f3 i}；f1 i为偏小型，f2 i为偏大型，f3 i为中间型，此处的偏小型意为环境参数指标的取值越小越好，比如二氧化碳的浓度越小越好；偏大型为环境参数指标的取值越大越好；中间型为环境参数指标的取值在中间段最好，比如照度、色温、温度等取中间段的值最好。 In the preferred technical solution of the present invention, the environmental contribution function f i ∈ {f1 i , f2 i , f3 i } of the environmental parameters is determined according to the fuzzy comprehensive evaluation method; f1 i is small, f2 i is large, and f3 i is intermediate. Here, a small value means that the value of the environmental parameter index is as small as possible, for example, a smaller carbon dioxide concentration is better; a large value means that the value of the environmental parameter index is larger and better; the middle type is the value of the environmental parameter index The middle section is the best. For example, the value of the middle section is the best for illumination, color temperature and temperature.
Figure PCTCN2018109857-appb-000008
Figure PCTCN2018109857-appb-000008
Figure PCTCN2018109857-appb-000009
Figure PCTCN2018109857-appb-000009
Figure PCTCN2018109857-appb-000010
Figure PCTCN2018109857-appb-000010
其中，式3-1中：a i为环境贡献函数达到最优时环境参数的取值，b i为环境贡献函数达到最差时环境参数的取值； Among them, in Equation 3-1: a i is the value of the environmental parameter when the environmental contribution function reaches the optimum, and b i is the value of the environmental parameter when the environmental contribution function reaches the worst;
式3-2中：a i为环境贡献函数达到最差时环境参数的取值，b i为环境贡献函数达到最优时环境参数的取值； In Equation 3-2: a i is the value of the environmental parameter when the environmental contribution function reaches the worst, and b i is the value of the environmental parameter when the environmental contribution function reaches the optimal;
式3-3中：a i、d i为环境贡献函数达到最差时环境参数的取值，a i＜d i；b i、c i为环境贡献函数达到最优时环境参数的取值，b i＜c i。 3-3 formula: a i, d i is the value of an environmental parameter when the function reaches the worst environmental contribution, a i <d i; b i, c i is a function of environmental contribution optimal environment parameter values, b i <c i .
根据以上环境贡献函数的确定方法确定表1中各个环境参数的环境贡献函数值的过程如下：According to the above method for determining the environmental contribution function, the process of determining the environmental contribution function value of each environmental parameter in Table 1 is as follows:
A→确定二氧化碳的环境贡献函数值：A → Determine the value of the environmental contribution function of carbon dioxide:
A1：根据各个国家的相关标准，确定u 二氧化碳取值的各个节点： A1: According to the relevant standards of each country, determine each node of u carbon dioxide value:
已知澳大利亚、加拿大、日本、韩国、新加坡、瑞典等地二氧化碳浓度上限为1000ppm，美国的二氧化碳浓度上限为2000ppm，中国的二氧化碳浓度上限为1800ppm。It is known that the upper limit of carbon dioxide concentration in Australia, Canada, Japan, South Korea, Singapore, Sweden and other places is 1000 ppm, the upper limit of carbon dioxide concentration in the United States is 2000 ppm, and the upper limit of carbon dioxide concentration in China is 1800 ppm.
A2：确定二氧化碳的环境贡献函数值：二氧化碳对环境的贡献函数符合偏小型的函数形式，即当超过国家规定的限制之后是会越来越差或者是不符合人从事活动的，以此，确定二氧化碳的环境贡献函数值适应于f1 i。根据各个国家 的相关标准，确定式3-1中的a i＝1000，b i＝1800。 A2: Determine the value of the environmental contribution function of carbon dioxide: The contribution function of carbon dioxide to the environment conforms to a small-scale function form, that is, when it exceeds the limit set by the state, it will become worse or worse, and it will not meet people's activities. The value of the environmental contribution function of carbon dioxide is adapted to f1 i . According to the relevant standards of each country, a i = 1000 and b i = 1800 in Equation 3-1 are determined.
将表1中二氧化碳的500代入公式3-1中，Substitute 500 of carbon dioxide in Table 1 into Formula 3-1,
Figure PCTCN2018109857-appb-000011
Figure PCTCN2018109857-appb-000011
得出二氧化碳的环境贡献函数值为1。The value of the environmental contribution function of carbon dioxide is 1.
B→确定温度的环境贡献函数值：B → Determine the value of the environmental contribution function of temperature:
B1：确定u 温度取值的各个节点： B1: Determine each node of u temperature value:
国标规定夏季的舒适温度为22-28℃，两边区间适当放宽2℃，即20-30℃。The national standard stipulates that the comfortable temperature in summer is 22-28 ° C, and the interval on both sides is appropriately relaxed by 2 ° C, that is, 20-30 ° C.
B2：确定温度的环境贡献函数值：温度对环境的贡献函数符合中间型的函数形式，根据国标的规定，确定式三中的a i＝20，b i＝22，c i＝28，d i＝30。 B2: determining the environmental contribution function values of temperature: the temperature of the environment contribution functions meet the functional form intermediate, according to the national standard specified, determines three-a i = 20, b i = 22, c i = 28, d i = 30.
将表1中温度25℃代入公式三：Substitute the temperature of 25 ° C in Table 1 into Formula 3:
Figure PCTCN2018109857-appb-000012
Figure PCTCN2018109857-appb-000012
计算得出温度的环境贡献函数值为1。The calculated environmental contribution function for temperature is 1.
以此类推，根据以上方法分别求得表1中各个环境参数对应的环境贡献函数值，确定矩阵F，F＝[1 1 1 1 1 1 1 1 1 1]。By analogy, according to the above method, the environmental contribution function values corresponding to each environmental parameter in Table 1 are obtained, and the matrix F is determined, and F = [1,1,1,1,1,1,1].
根据公式二计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index of indoor environmental quality E-IEQ according to formula 2:
E-IEQ＝0.1*1+0.1*1+0.2*1+0.2*1+0*1+0*1+0.1*1+0*1+0*1+0.3*1＝1。E-IEQ = 0.1 * 1 + 0.1 * 1 + 0.2 * 1 + 0.2 * 1 + 0 * 1 + 0 * 1 + 0.1 * 1 + 0 * 1 + 0 * 1 + 0.3 * 1 = 1.
为了便于人们理解，将室内环境质量的综合指标分为若干个等级，包括但不局限于优秀、良好、中等、差、劣；In order to facilitate people's understanding, the comprehensive indicators of indoor environmental quality are divided into several levels, including but not limited to excellent, good, medium, poor, and inferior;
综合指标E-IEQ∈[0.9，1]时，所述室内环境质量为优秀；When the comprehensive index E-IEQ ∈ [0.9, 1], the indoor environment quality is excellent;
综合指标E-IEQ∈[0.8，0.9)时，所述室内环境质量为良好；When the comprehensive index E-IEQ ∈ [0.8, 0.9), the indoor environment quality is good;
综合指标E-IEQ∈[0.7，0.8)时，所述室内环境质量为中等；When the comprehensive index E-IEQ ∈ [0.7, 0.8), the indoor environment quality is medium;
综合指标E-IEQ∈[0.6，0.7)时，所述室内环境质量为差；When the comprehensive index E-IEQ ∈ [0.6, 0.7), the indoor environment quality is poor;
综合指标E-IEQ∈[0，0.6)时，所述室内环境质量为良好。When the comprehensive index E-IEQ ∈ [0, 0.6), the indoor environment quality is good.
鉴于此，表1中的室内环境，通过本发明计算方法能够确定其环境等级为优。In view of this, the indoor environment in Table 1 can be determined by the calculation method of the present invention to have an excellent environmental level.
另，需要注意的是，以上梯形或半梯形函数形式是一个确定环境贡献函数值一个典型实例，根据实际情况，还可以使用其它函数形式，比如：二次函数、幂函数、对数函数、Sigmoid等。In addition, it should be noted that the above trapezoidal or semi-ladder function form is a typical example of determining the value of the environmental contribution function. According to the actual situation, other function forms can also be used, such as: quadratic function, power function, logarithmic function, Sigmoid Wait.
当样本数据达到500以上的时候，使用机器深度学习法确定环境参数的权重，如图2所述，其具体确定过程如下：When the sample data reaches 500 or more, use machine deep learning to determine the weight of the environmental parameters, as shown in Figure 2. The specific determination process is as follows:
(1)获取环境参数数据；环境参数包括但不限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音。通过分布在环境中的各种传感器采集当前状态下的各个环境参数数据，比如，温度传感器采集当前状态下的温度为28℃、湿度传感器采集的湿度为47％等等，以此来获取环境中当前状态下各个环境参数的数据。(1) Obtaining environmental parameter data; environmental parameters include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide, and noise. Collect various environmental parameter data in the current state through various sensors distributed in the environment, for example, the temperature sensor collects the current temperature of 28 ° C, the humidity sensor collects 47% of humidity, etc. Data of various environmental parameters in the current state.
(2)结合室内环境的使用场景对环境参数数据进行特征提取，获得环境参数特征。具体的，结合室内环境的使用场景，剔除非正常的环境参数数据和非 工作时间的环境参数数据。比如，传感器处于故障或者断电状态时，采集的数据异常(远大于或者远小于正常值)、或者断电状态时输出″--″，通过特征提取模块剔除这种非正常的环境参数数据。另一种情况下，比如，正常情况下室内环境的时间是9：00-17：00，通过特征提取模块剔除这一工作时间以外的环境参数数据。(2) Feature extraction of environmental parameter data in combination with the use scenario of the indoor environment to obtain environmental parameter characteristics. Specifically, in combination with the indoor environment usage scenario, except for normal environmental parameter data and non-working time environmental parameter data. For example, when the sensor is in the fault or power-off state, the collected data is abnormal (far greater than or far less than the normal value), or "-" is output when the sensor is in the power-off state, and this abnormal environmental parameter data is eliminated by the feature extraction module. In another case, for example, the time of the indoor environment is normally 9: 00-17: 00, and the environmental parameter data other than this working time is eliminated by the feature extraction module.
(3)使用经训练获得的权重模型对环境参数特征做权重分析，获得环境参数的权重。(3) Use the trained weight model to perform weight analysis on the characteristics of the environmental parameters to obtain the weight of the environmental parameters.
本实施例技术方案中，上述权重模型通过训练获得，如图3所示，其训练过程为：In the technical solution of this embodiment, the foregoing weight model is obtained through training. As shown in FIG. 3, the training process is as follows:
(3.1)获取用作样本的环境参数数据样本。环境参数包括但不限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音。通过分布在环境中的各种传感器采集当前状态下的各个环境参数数据，比如，温度传感器采集当前状态下的温度为28℃、湿度传感器采集的湿度为47％等等，以此来获取环境中当前状态下各个环境参数的数据样本。(3.1) Acquire a sample of environmental parameter data used as a sample. Environmental parameters include, but are not limited to, temperature, humidity, illumination, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide and noise. Collect various environmental parameter data in the current state through various sensors distributed in the environment, for example, the temperature sensor collects the current temperature of 28 ° C, the humidity sensor collects 47% of humidity, etc. Data samples of various environmental parameters in the current state.
(3.2)结合室内环境的使用场景对环境参数数据样本进行特征提取，获得特征化后的数据样本。具体的，结合室内环境的使用场景，剔除非正常的数据样本和非工作时间的数据样本。比如，传感器处于故障或者断电状态时，采集的数据异常(远大于或者远小于正常值)、或者断电状态时输出″--″，通过特征提取单元剔除这种非正常的数据样本。另一种情况下，比如，正常情况下室内环境的时间是9：00-17：00，通过特征提取单元剔除这一工作时间以外的数据样本。(3.2) The feature parameters of the environmental parameter data samples are extracted in combination with the use scenarios of the indoor environment to obtain the characterized data samples. Specifically, in combination with the use scenario of the indoor environment, except for normal data samples and non-working time data samples. For example, when the sensor is in the fault or power-off state, the collected data is abnormal (far greater than or far less than the normal value), or when the power-off state is output, "-" is output, and such abnormal data samples are eliminated by the feature extraction unit. In another case, for example, the time of the indoor environment is normally from 9:00 to 17:00, and data samples other than this working time are eliminated by the feature extraction unit.
(3.3将特征化后的数据样本随机分为训练数据组和测试数据组。具体的， 将特征化后的所有数据样本中的80％归为训练数据组，20％归为测试数据组。(3.3 The characterized data samples are randomly divided into training data groups and test data groups. Specifically, 80% of all characterized data samples are classified as training data groups and 20% are classified as test data groups.
(3.4)基于相关算法训练特征化后的数据样本，获得权重模型。具体的，相关算法包括但不局限于机器学习算法、卷积神经网络算法、循环神经网络算法、决策树、基于贝叶斯决策理论的分类算法和深度学习算法。模型训练单元使用以上的若干个相关算法分别训练数据样本，获得若干个权重模型。并使用测试数据组中的数据样本分别测试验证若干个权重模型的性能，在若干个权重模型中选取匹配度最高的一个为最优权重模型。比如，将测试数据组中的数据样本导入各个权重模型中，看各个权重模型输出的权重是否与实际情况相匹配，选取匹配度最高的的权重模型为最优权重模型，本实施例技术方案中，限定最优权重模型的匹配度不低于95％。测试验证后，如果所有的权重模型的匹配度都低于95％，则对匹配度最高的权重模型进行迭代优化，直至其匹配度不低于95％。(3.4) The characteristic data samples are trained based on the correlation algorithm to obtain a weight model. Specifically, related algorithms include, but are not limited to, machine learning algorithms, convolutional neural network algorithms, recurrent neural network algorithms, decision trees, classification algorithms based on Bayesian decision theory, and deep learning algorithms. The model training unit uses the above several related algorithms to separately train data samples to obtain several weight models. The data samples in the test data set are used to test and verify the performance of several weight models. Among the several weight models, the one with the highest matching degree is selected as the optimal weight model. For example, the data samples in the test data set are imported into each weight model to see whether the weights output by each weight model match the actual situation, and the weight model with the highest matching degree is selected as the optimal weight model. In the technical solution of this embodiment, The matching degree of the optimal weight model is not less than 95%. After testing and verification, if the matching degree of all weight models is less than 95%, the weighting model with the highest matching degree is iteratively optimized until the matching degree is not less than 95%.
需要注意的是，在有新的数据样本导入时，当前测试数据组内的数据样本合并至训练数据组中，新的数据样本进入测试数据组，以此不断优化权重模型。It should be noted that when new data samples are imported, the data samples in the current test data group are merged into the training data group, and the new data samples enter the test data group to continuously optimize the weight model.
(4)使用经训练、筛选获得的最优权重模型对环境参数特征做权重分析，获得环境参数的权重。具体的，将特征化后的环境参数数据导入最优权重模型中，最优权重模型对环境参数数据做权重分析直接输出各个环境参数的权重。(4) Use the optimal weight model obtained by training and screening to perform weight analysis on the characteristics of the environmental parameters to obtain the weight of the environmental parameters. Specifically, the characteristic environmental parameter data is imported into the optimal weight model, and the optimal weight model performs weight analysis on the environmental parameter data to directly output the weight of each environmental parameter.
以上所述实施例仅是为充分说明本发明而所举的较佳的实施例，本发明的保护范围不限于此。本技术领域的技术人员在本发明基础上所作的等同替代或变换，均在本发明的保护范围之内。本发明的保护范围以权利要求书为准。The embodiments described above are merely preferred embodiments for fully explaining the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art on the basis of the present invention are all within the protection scope of the present invention. The protection scope of the present invention is subject to the claims.

Claims (10)

  1. 一种表征室内环境综合质量的综合指标计算方法，其特征在于：包括，A comprehensive index calculation method characterizing the comprehensive quality of indoor environment, which is characterized by:
    结合室内环境的使用场景确定环境参数矩阵U＝[u 1 u 2 u 3 ... u i ... u n]； Determine the environmental parameter matrix U = [u 1 u 2 u 3 ... u i ... u n ] in combination with the use scenario of the indoor environment;
    结合室内环境的使用场景确定环境参数的权重矩阵：Determine the weight matrix of environmental parameters based on the indoor environment's use scenario:
    W＝[w 1 w 2 w 3 ... w i ... w n]，且满足w 1+w 2+w 3+...+w i+...+w n＝1；环境参数的权重w i表征环境参数u i对环境质量的影响程度； W = [w 1 w 2 w 3 ... w i ... w n ], and satisfy w 1 + w 2 + w 3 + ... + w i + ... + w n = 1; environmental parameter The weight w i represents the degree of influence of the environmental parameter u i on the environmental quality;
    结合室内环境的使用场景确定环境参数的环境贡献函数值矩阵：Determine the environmental contribution function value matrix of the environmental parameters in combination with the use environment of the indoor environment:
    F＝[f 1 f 2 f 3 ... f i ... f n]，且满足f i∈[0，1]；环境参数的环境贡献函数f i表征环境参数u i对环境质量指标影响程度的函数关系，即f i＝f(u i)； F = [f 1 f 2 f 3 ... f i ... f n ] and satisfies f i ∈ [0, 1]; the environmental contribution function f i of the environmental parameter represents the influence of the environmental parameter u i on the environmental quality index A functional relationship of degree, that is, f i = f (u i );
    根据公式一计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index E-IEQ of indoor environmental quality according to formula 1:
    Figure PCTCN2018109857-appb-100001
    Figure PCTCN2018109857-appb-100001
  2. 如权利要求1所述的表征室内环境综合质量的综合指标计算方法，其特征在于：其还包括结合室内环境的使用场景确定环境参数的一票否决权矩阵：X＝[x 1 x 2 x 3 ... x i ... x n]，且满足x i∈{0，1}； The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 1, further comprising a one-vote veto matrix for determining environmental parameters in combination with an indoor environment use scenario: X = [x 1 x 2 x 3 ... x i ... x n ], and satisfy x i ∈ {0, 1};
    当u i≥u max或者u i≤u min时，x i＝0； When u i ≥ u max or u i ≤ u min , x i = 0;
    当u min＜u i＜u max时，x i＝1； When u min <u i <u max , x i = 1;
    其中，u min为环境参数u i在国标中规定的最小值，u max为环境参数u i在国标中规定的最大值； Wherein, u min u i a predetermined minimum value in the national standard of environmental parameters, u max u i predetermined maximum value in the national standard of environmental parameters;
    根据公式二计算室内环境质量的综合指标E-IEQ：Calculate the comprehensive index of indoor environmental quality E-IEQ according to formula 2:
    Figure PCTCN2018109857-appb-100002
    Figure PCTCN2018109857-appb-100002
  3. 如权利要求1所述的表征室内环境综合质量的综合指标计算方法，其特征在于：根据模糊综合评价法确定环境参数的环境贡献函数f i∈{f1 i，f2 i，f3 i}； The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 1, characterized in that an environmental contribution function f i ∈ {f1 i , f2 i , f3 i } of an environmental parameter is determined according to a fuzzy comprehensive evaluation method;
    Figure PCTCN2018109857-appb-100003
    Figure PCTCN2018109857-appb-100003
    Figure PCTCN2018109857-appb-100004
    Figure PCTCN2018109857-appb-100004
    Figure PCTCN2018109857-appb-100005
    Figure PCTCN2018109857-appb-100005
    其中，式3-1中：a i为环境贡献函数达到最优时环境参数的取值，b i为环境贡献函数达到最差时环境参数的取值； Among them, in Equation 3-1: a i is the value of the environmental parameter when the environmental contribution function reaches the optimum, and b i is the value of the environmental parameter when the environmental contribution function reaches the worst;
    式3-2中：a i为环境贡献函数达到最差时环境参数的取值，b i为环境贡献函数达到最优时环境参数的取值； In Equation 3-2: a i is the value of the environmental parameter when the environmental contribution function reaches the worst, and b i is the value of the environmental parameter when the environmental contribution function reaches the optimal;
    式3-3中：a i、d i为环境贡献函数达到最差时环境参数的取值，a i＜d i；b i、c i为环境贡献函数达到最优时环境参数的取值，b i＜c i。 3-3 formula: a i, d i is the value of an environmental parameter when the function reaches the worst environmental contribution, a i <d i; b i, c i is a function of environmental contribution optimal environment parameter values, b i <c i .
  4. 如权利要求1所述的表征室内环境综合质量的综合指标计算方法，其特征在于：所述环境参数包括但不局限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音。The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 1, wherein the environmental parameters include, but are not limited to, temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide And noise.
  5. 如权利要求1所述的表征室内环境综合质量的综合指标计算方法，其特征在于：将所述室内环境质量分为若干个等级，包括但不局限于优秀、良好、 中等、差、劣；The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 1, characterized in that the indoor environment quality is divided into several grades, including but not limited to excellent, good, medium, poor, and inferior;
    综合指标E-IEQ∈[0.9，1]时，所述室内环境质量为优秀；When the comprehensive index E-IEQ ∈ [0.9, 1], the indoor environment quality is excellent;
    综合指标E-IEQ∈[0.8，0.9)时，所述室内环境质量为良好；When the comprehensive index E-IEQ ∈ [0.8, 0.9), the indoor environment quality is good;
    综合指标E-IEQ∈[0.7，0.8)时，所述室内环境质量为中等；When the comprehensive index E-IEQ ∈ [0.7, 0.8), the indoor environment quality is medium;
    综合指标E-IEQ∈[0.6，0.7)时，所述室内环境质量为差；When the comprehensive index E-IEQ ∈ [0.6, 0.7), the indoor environment quality is poor;
    综合指标E-IEQ∈[0，0.6)时，所述室内环境质量为良好。When the comprehensive index E-IEQ ∈ [0, 0.6), the indoor environment quality is good.
  6. 如权利要求1所述的表征室内环境综合质量的综合指标计算方法，其特征在于：使用机器深度学习法或/和统计学中的因子分析法确定所述环境参数的权重；用于计算综合指的标数据样本小于等于设定值时，使用因子分析法确定环境参数的权重；超过设定值时，使用机器深度学习法确定环境参数的权重。The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 1, characterized in that: using machine deep learning method or / and factor analysis method in statistics to determine the weight of the environmental parameter; When the target data sample is less than or equal to the set value, the weight of the environmental parameter is determined using the factor analysis method; when it exceeds the set value, the weight of the environmental parameter is determined using the machine deep learning method.
  7. 如权利要求6所述的表征室内环境综合质量的综合指标计算方法，其特征在于：使用机器深度学习法确定环境参数权重的过程为，The comprehensive index calculation method for characterizing the comprehensive quality of an indoor environment according to claim 6, characterized in that the process of determining the weight of the environmental parameters using the machine deep learning method is:
    采集环境参数数据，所述环境参数包括但不限于温度、湿度、照度、色温、PM2.5、PM10、甲醛、TVOC、二氧化碳和噪音；Collect environmental parameter data, including but not limited to temperature, humidity, illuminance, color temperature, PM2.5, PM10, formaldehyde, TVOC, carbon dioxide and noise;
    结合室内环境的使用场景对所述环境参数数据进行特征提取，获得环境参数特征；Performing feature extraction on the environmental parameter data in combination with an indoor environment use scenario to obtain environmental parameter characteristics;
    使用经训练获得的权重模型对所述环境参数特征做权重分析，获得环境参数的权重。Perform weight analysis on the characteristics of the environmental parameters using the trained weight model to obtain the weight of the environmental parameters.
  8. 如权利要求7所述的表征室内环境综合质量的综合指标计算方法，其特征在于：通过模型训练获得所述权重模型，其训练过程为，The comprehensive index calculation method for representing the comprehensive quality of an indoor environment according to claim 7, wherein the weight model is obtained through model training, and the training process is:
    获取用作样本的环境参数数据样本；Obtain a sample of environmental parameter data used as a sample;
    结合室内环境的使用场景对环境参数数据样本进行特征提取，获得特征化后的数据样本；Feature extraction of environmental parameter data samples in combination with indoor environment usage scenarios to obtain characterized data samples;
    基于相关算法训练特征化后的数据样本，获得所述权重模型。The weighted model is obtained by training the characterized data samples based on a related algorithm.
  9. 如权利要求8所述的表征室内环境综合质量的综合指标计算方法，其特征在于：所述权重模型的训练过程还包括，The comprehensive index calculation method for representing the comprehensive quality of an indoor environment according to claim 8, wherein the training process of the weight model further comprises:
    对特征后的数据样本进行随机分组，分为训练数据组和测试数据组，使用训练数据组中的数据样本进行模型训练获得所述权重模型；Randomly grouping the characteristic data samples into training data groups and test data groups, and using the data samples in the training data group to perform model training to obtain the weight model;
    使用若干个相关算法分别训练所述训练数据组中的数据样本，获得若干个权重模型；Using several related algorithms to separately train data samples in the training data set to obtain several weight models;
    使用所述测试数据组中的数据样本分别测试验证所述若干个权重模型的性能，在所述若干个权重模型中选取匹配度最高的一个为最优权重模型；Use the data samples in the test data set to test and verify the performance of the several weight models, and select the one with the highest matching degree among the several weight models as the optimal weight model;
    使用最优权重模型对环境参数特征做权重分析，获得环境参数的权重。The optimal weight model is used to perform weight analysis on the characteristics of the environmental parameters to obtain the weight of the environmental parameters.
  10. 如权利要求9所述的表征室内环境综合质量的综合指标计算方法，其特征在于：用于训练获得权重模型的相关算法包括但不局限于机器学习算法、卷积神经网络算法、循环神经网络算法、决策树、基于贝叶斯决策理论的分类算法和深度学习算法。The comprehensive index calculation method for representing the comprehensive quality of an indoor environment according to claim 9, characterized in that the relevant algorithms for training to obtain the weight model include, but are not limited to, machine learning algorithms, convolutional neural network algorithms, and recurrent neural network algorithms , Decision tree, classification algorithm and deep learning algorithm based on Bayes decision theory.
PCT/CN2018/109857 2018-09-21 2018-10-11 Comprehensive index calculation method for characterizing comprehensive quality of indoor environment WO2020056811A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811108366.5 2018-09-21
CN201811108366.5A CN109242329A (en) 2018-09-21 2018-09-21 Characterize the overall target calculation method of indoor environment comprehensive quality

Publications (1)

Publication Number Publication Date
WO2020056811A1 true WO2020056811A1 (en) 2020-03-26

Family

ID=65057153

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/109857 WO2020056811A1 (en) 2018-09-21 2018-10-11 Comprehensive index calculation method for characterizing comprehensive quality of indoor environment

Country Status (2)

Country Link
CN (1) CN109242329A (en)
WO (1) WO2020056811A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112557585A (en) * 2019-09-25 2021-03-26 上海迪勤智能科技有限公司 Learning environment quality evaluation system and method based on Weber-Feishlnut law
CN113379284B (en) * 2021-06-24 2022-03-08 哈尔滨工业大学 Indoor environment condition equivalence determination method and determination system based on environment experience probability quality function
CN115096357A (en) * 2022-06-07 2022-09-23 大连理工大学 Indoor environment quality prediction method based on CEEMDAN-PCA-LSTM

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105550515A (en) * 2015-12-10 2016-05-04 山东科技大学 Multi-level comprehensive judgment method for air quality data
CN106021858A (en) * 2016-05-06 2016-10-12 中科同德（北京）生态科技有限公司 A calculating method for index evaluation data representing indoor air environment quality
CN106546323A (en) * 2016-11-08 2017-03-29 浙江工业大学 A kind of Interior Illumination Environment health degree appraisal procedure

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108363294A (en) * 2017-01-26 2018-08-03 安徽东方果园生物科技有限公司 A kind of the environmental monitoring method for early warning and environmental monitoring early warning system of agricultural product transport closing and semiclosed carriage body

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105550515A (en) * 2015-12-10 2016-05-04 山东科技大学 Multi-level comprehensive judgment method for air quality data
CN106021858A (en) * 2016-05-06 2016-10-12 中科同德（北京）生态科技有限公司 A calculating method for index evaluation data representing indoor air environment quality
CN106546323A (en) * 2016-11-08 2017-03-29 浙江工业大学 A kind of Interior Illumination Environment health degree appraisal procedure

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
FAN, YU: "Application Research of Fuzzy Comprehensive Evaluation in Green Building Evaluation", SCIENCE -ENGINEERING (II), CHINA MASTER'S THESES FULL-TEXT DATABASE, 15 July 2012 (2012-07-15), pages 9 - 16 *

Also Published As

Publication number Publication date
CN109242329A (en) 2019-01-18

Similar Documents

Publication Publication Date Title
WO2019233189A1 (en) Method for detecting sensor network abnormal data
WO2020056811A1 (en) Comprehensive index calculation method for characterizing comprehensive quality of indoor environment
WO2021073462A1 (en) 10 kv static load model parameter identification method based on similar daily load curves
CN106549813A (en) A kind of appraisal procedure and system of network performance
CN110196814B (en) Software quality evaluation method
CN109087277B (en) Method for measuring PM2.5 of fine air particles
CN110929918A (en) 10kV feeder line fault prediction method based on CNN and LightGBM
CN105590283A (en) Examination data analysis method on the basis of fuzzy synthetic evaluation model
Chon et al. A comparison of item fit statistics for mixed IRT models
CN109767074A (en) Effect comprehensive estimation method is planned in a kind of distribution of high reliability service area
WO2020056812A1 (en) Environmental parameter weight determining method and system for evaluating indoor environmental quality
CN113378473A (en) Underground water arsenic risk prediction method based on machine learning model
Viana Statistical methods for summarizing independent correlational results
CN111861038A (en) College entrance examination score prediction method and system based on machine learning algorithm
CN108133296B (en) Event attendance prediction method combining environmental data under social network based on events
CN116011871A (en) Method for quantifying space update probability of traditional villages based on space update sensitivity
Liu et al. Comprehensive evaluation of urban livability
Haddad et al. Relationship between children’s comfort temperature and outdoor climate: some methodological issues
Huang et al. RESEARCH ON INDEPENDENT COLLEGE TEACHERS’TEACHING ABILITY BASED ON FACTOR ANALYSIS IN SPSS
Liumei et al. Analysis of system implementation effect based on Bayes analysis of imbalanced measures
CN113780833B (en) Typhoon login influence area wind field risk assessment method and device
CN104575522B (en) A kind of music-listener&#39;s Classified Protection for voice quality networks subjective audiometry
CN108459948A (en) The determination method of fail data distribution pattern in Reliability evaluation
Maricic et al. Ranking European universities based on their level of collaboration with the Industry: The University-Industry Research Connections Index
CN112903928B (en) Indoor air quality evaluation method based on improved analytic hierarchy process

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18934334

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18934334

Country of ref document: EP

Kind code of ref document: A1