WO2022142569A1 - 列车车厢空气调控方法、装置、存储介质及程序产品 - Google Patents

列车车厢空气调控方法、装置、存储介质及程序产品 Download PDF

Info

Publication number
WO2022142569A1
WO2022142569A1 PCT/CN2021/122732 CN2021122732W WO2022142569A1 WO 2022142569 A1 WO2022142569 A1 WO 2022142569A1 CN 2021122732 W CN2021122732 W CN 2021122732W WO 2022142569 A1 WO2022142569 A1 WO 2022142569A1
Authority
WO
WIPO (PCT)
Prior art keywords
total number
bacterial colonies
concentration
air
exhaust
Prior art date
Application number
PCT/CN2021/122732
Other languages
English (en)
French (fr)
Inventor
刘辉
李燕飞
谢佳豪
张洁
陈曦睿
Original Assignee
中南大学
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 中南大学 filed Critical 中南大学
Priority to JP2022527144A priority Critical patent/JP7360218B2/ja
Priority to US18/267,450 priority patent/US20230366004A1/en
Publication of WO2022142569A1 publication Critical patent/WO2022142569A1/zh

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
    • C12Q1/04—Determining presence or kind of microorganism; Use of selective media for testing antibiotics or bacteriocides; Compositions containing a chemical indicator therefor
    • C12Q1/06—Quantitative determination
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00—Heating, cooling or ventilating [HVAC] devices
    • B60H1/00357—Air-conditioning arrangements specially adapted for particular vehicles
    • B60H1/00371—Air-conditioning arrangements specially adapted for particular vehicles for vehicles carrying large numbers of passengers, e.g. buses
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00—Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/0073—Control systems or circuits characterised by particular algorithms or computational models, e.g. fuzzy logic or dynamic models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00—Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
    • B60H1/008—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models the input being air quality
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61D—BODY DETAILS OR KINDS OF RAILWAY VEHICLES
    • B61D27/00—Heating, cooling, ventilating, or air-conditioning
    • B61D27/009—Means for ventilating only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/06—Investigating concentration of particle suspensions
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/01—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials specially adapted for biological cells, e.g. blood cells
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/02—Investigating particle size or size distribution
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
    • Y02A50/20—Air quality improvement or preservation, e.g. vehicle emission control or emission reduction by using catalytic converters

Definitions

  • the invention relates to the field of train environment monitoring, in particular to a method, device, storage medium and program product for air conditioning in a train compartment.
  • the patent application with the publication number CN101885338A proposes an intelligent sampling detection and air purification device for a train air conditioning and ventilation system, including a frequency conversion cyclone dust catcher and a high-efficiency filter.
  • the patent application with publication number CN105172818A proposes a special air purifier for trains, which includes an upper box body and a lower box body that cooperates with the upper box body.
  • a vehicle environment adjustment method based on the detection of air pollutants proposes a health protection system and method for train occupants in a polluted environment inside the vehicle, including a basic data acquisition module, a train external air quality prediction module, a train internal air quality prediction module and a ventilation strategy formulation module.
  • Patent application with publication number CN104608785A proposes an intelligent control method for an air conditioning system of a high-speed train.
  • the above methods mainly use the air pollutants such as PM2.5 inside the train as the basis for air quality assessment.
  • the existing technology does not pay attention to the harm of biological pollution in the air environment to human health, and there is no relevant research at this stage that pays attention to the airtightness of the train compartment.
  • Environmental biological pollutants because the microbial measurement mechanism is different from that of pollutants such as PM2.5, microbial measurement must be carried out through long-term colony culture, and it is difficult to directly detect and take real-time control measures.
  • the technical problem to be solved by the present invention is to provide a method, device, storage medium and program product for air conditioning in a train compartment in view of the deficiencies of the prior art, so as to make optimal protection measures for the health of passengers according to the distribution of microorganisms in the compartment .
  • the technical scheme adopted in the present invention is: a method, system and storage medium for air conditioning in a train compartment, comprising the following steps:
  • the invention learns the mapping relationship between microbial pollution and air pollutant concentration in the compartment, and makes optimal protection measures for the health of passengers in real time according to the distribution of microorganisms in the compartment.
  • the invention detects and analyzes the microorganisms in the train compartment, and adjusts the ventilation system according to the distribution of microorganisms among the measuring points, thereby reducing the microbial contamination in the area where the passengers are located.
  • This method has a guiding role in the regulation of air quality of railway trains.
  • step 2) the specific implementation process of establishing the mapping relationship between the total number of bacterial colonies D and the concentration d of air pollutants in each microenvironmental unit includes:
  • A. Read the air pollutant concentration and total bacterial colony index data set of the current microenvironmental unit in M consecutive historical moments, and divide the data set into a training set and a test set;
  • B. Construct a microorganism-air pollutant model by using a deep belief network, take the air pollutant concentration as the input of the deep belief network, and the total number of bacterial colonies at the same time as the output of the deep belief network, and train the deep belief network;
  • test set is used as the input of the deep belief network after training, and a set of parameters with the highest description accuracy on the test set is selected as the microorganism-air pollutant mapping model of the micro-environmental unit;
  • the invention studies the mapping relationship between microbial pollution and air pollutant concentration, can effectively solve the real-time problem of microbial detection, and ensure the real-time regulation of microbial pollution in the train compartment.
  • test result (which is and ) takes the value 0 or 1.
  • the method of the invention performs causal relationship test on the microbial time series data between different measuring points, and further selects the measuring points closely related to the seat where the passenger is located for subsequent modeling, realizes the compression of the spatial dimension of the measuring points, and makes the provided
  • the data features should have strong representation ability.
  • step 4) includes:
  • the present invention uses a deep neural network to describe the non-linear mapping relationship of microorganism-air pollutant concentration and seat-air supply port/air exhaust port microorganism, which ensures the accuracy of the description.
  • step 5 the specific realization process of calculating the fitting result of the total number of bacterial colonies at the air supply port/air exhaust port under different ventilation rates includes:
  • step iii) Repeat step i) and step ii), traverse to all air supply and exhaust ports, and obtain the polynomial fitting result of the total number of bacterial colonies in all air supply and exhaust ports as a function of ventilation rate m, n are the number of detection points of the air supply port and the air exhaust port, respectively.
  • step 5 the optimization objective is set to minimize the fitting result of the total number of bacterial colonies at each seat at the same time, and the optimization function is:
  • the invention adopts a multi-objective optimization method to minimize the total number of bacterial colonies at each seat, so that the microbial contamination in the area where the passenger is located achieves the overall optimum, and avoids secondary pollution in some areas caused by the adjustment process of the ventilation system.
  • step 5 select the evaluation index
  • the minimum non-dominated solution NS * arg min E is reached to determine the ventilation rate NS * for all supply and exhaust outlets; where, is the variance of the total number of bacterial colonies in all seats in the test set; uk and lk are the upper and lower limits of the ventilation rate vk of the kth air supply/exhaust vent, respectively.
  • the evaluation index is the combination of the cumulative fitting result and variance of the total number of bacterial colonies on all seats, where the cumulative fitting result of the total bacterial colony on all seats represents the degree of microbial contamination after ventilation regulation, and the variance represents the difference between each seat.
  • the discrete degree of microbial contamination Selecting the non-dominated solution that minimizes this evaluation index can ensure that: (1) the overall level of microbial contamination in the cabin is minimized; (2) the difference in microbial contamination between seats is minimized, avoiding extreme contamination in individual areas.
  • the present invention also provides a computer device including a memory, a processor and a computer program stored on the memory; it is characterized in that the processor executes the computer program to implement the steps of the air conditioning method for a train compartment of the present invention.
  • the present invention also provides a computer-readable storage medium on which computer programs/instructions are stored; when the computer programs/instructions are executed by a processor, the steps of the method for air conditioning in a train compartment of the present invention are implemented.
  • the present invention also provides a computer program product, comprising a computer program/instruction; when the computer program/instruction is executed by a processor, the steps of the air conditioning method for a train compartment of the present invention are implemented.
  • the present invention has the following beneficial effects:
  • the present invention detects and analyzes the microorganisms in the train compartment.
  • the ventilation system is adjusted according to the diffusion of microorganisms between the measuring points, thereby reducing the microbial contamination index in the area where passengers are located. This method has a guiding role in the regulation of air quality of railway trains.
  • the present invention studies the mapping relationship between microbial pollution and atmospheric pollutant concentration, which can effectively solve the real-time problem of microbial detection and ensure the real-time regulation of microbial pollution in the train compartment.
  • the present invention adopts the comprehensive detection method of air supply vents, exhaust vents and seats, which can effectively describe the distribution of atmospheric pollutants and microorganisms in the interior environment of the vehicle, and ensure the authenticity of the detection results to the actual spatial distribution.
  • the method of the present invention performs causal relationship test on the microbial time series data between different measuring points, and further selects the measuring points closely related to the seat where the passenger is located for subsequent modeling, and realizes the compression of the spatial dimension of the measuring points, so that the The data features provided should have strong representational ability.
  • the present invention uses a deep neural network to describe the nonlinear mapping relationship between microorganisms-atmospheric pollutant concentration and seat-air supply/exhaust microorganisms, which ensures the accuracy of the description.
  • the present invention adopts a multi-objective optimization method to minimize the total number of bacterial colonies at each seat, so that the microbial contamination in the area where the passenger is located achieves the overall optimum, and avoids secondary pollution in some areas caused by the adjustment process of the ventilation system.
  • Fig. 1 is the flow chart of the method of the present invention.
  • Step 1 Multi-point collection of pollution data
  • the interior of the train compartment includes six air pollutants such as PM 2.5 , PM 10 , CO, NO 2 , SO 2 and O 3 as well as microbial contamination such as bacteria, fungi and viruses.
  • Microorganisms are closely related to air quality. Generally, the total number of bacterial colonies in the air is positively correlated with the existence probability of pathogenic microorganisms (bacteria, fungi, viruses). Therefore, this patent measures the pathogenicity of microorganisms by the total number of bacterial colonies. .
  • TS WES-C air pollutant detectors measure PM 2.5 concentration, PM 10 concentration, CO concentration, NO 2 concentration, SO 2 concentration, O 3 concentration , real-time detection
  • Anderson impact air microbial sampler to measure the total number of bacterial colonies, after 48h of microbial culture.
  • the obtained data include PM 2.5 concentration, PM 10 concentration, CO concentration, NO 2 concentration, SO 2 concentration, O 3 concentration, and total bacterial colony at the air supply vents, exhaust vents, and seats, which can be expressed as and in the formula represents the concentration of air pollutants at the mth air outlet, represents the concentration of air pollutants at the nth exhaust outlet, represents the concentration of air pollutants at the p-th seat, where represents the total number of bacterial colonies at the mth air outlet, represents the total number of bacterial colonies at the nth exhaust outlet, Represents the total number of bacterial colonies at the p-th seat, i represents the six air pollutants of PM2.5, PM10, CO, NO2, SO2 and O3, m, n, p are the air supply, exhaust and seat respectively Number of measuring points. Each detection point is regarded as a small environmental unit, the detection data is corresponding to the number of the carriage, and the time stamp of the detection data is recorded, and the interval between adjacent data is 5 minutes.
  • the collected data is transmitted to the data storage platform through
  • Step 2 Microbiology-Air Pollutant Mapping Learning
  • A1 Select a micro-environmental unit, and read the data set of the air pollutant concentration and total bacterial colony index of the micro-environmental unit in 200 consecutive historical moments.
  • A2 Dataset partitioning. The above data set contains 200 consecutive historical moments, the data from time 1 to 160 is used as the training set, and the data from time 161 to 200 is used as the test set.
  • a microbe-air pollutant model is constructed using a deep belief network, and the concentration of air pollutants is used as the input of the deep belief network, and the total number of bacterial colonies at the same time is used as the output of the deep belief network.
  • the number of layers of the deep belief network is determined by 5-fold cross-validation, and the selection range is [1, 2, 3, 4, 5].
  • A4 Test the model on the test set with the well-trained deep belief network, and select a set of parameters with the highest description accuracy on the test set as the microbiological-air pollutant mapping model for the micro-environmental unit.
  • i 1,2,3,...,m+n+p ⁇ , where f represents the mapping relationship.
  • Step 3 Causal relationship test based on microbial diffusion mechanism
  • the spatial distribution and diffusion of microorganisms in the carriage are affected by air movement, and there is a causal relationship at the data level in the total number of bacterial colonies between the measurement points. For each compartment, the causal relationship between the time series of the total number of bacterial colonies at the seat and each air outlet and exhaust outlet was analyzed.
  • GCT() stands for Granger causality test. Obtain a set of inspection results for each seat detection point and m air supply vents and n air exhaust vents:
  • Step 4 Nonlinear description modeling of causal correlation measurement points
  • B1 Read the PM2.5 concentration, PM10 concentration, CO concentration, NO2 concentration, SO2 concentration, and O3 concentration of seats, air supply outlets, and exhaust outlets at 100 consecutive historical moments, and calculate 100 consecutive histories according to the mapping relationship obtained in step 2 The total number of bacterial colonies at each measurement point in time.
  • B2 Dataset partitioning.
  • the above data set contains 100 consecutive historical moments, the data from time 1 to 60 is used as the training set, the data from time 61 to 80 is used as the validation set, and the data from time 81 to 100 is used as the test set.
  • B3 Read the total number of bacterial colonies at the i-th seat detection point And the total number of bacterial colonies at the air supply and exhaust vents that have a causal relationship with the i-th seat detection point is the total number of bacterial colonies at the air outlet; is the total number of bacterial colonies at the exhaust outlet; which is or which is or
  • the deep echo state network is used to construct a nonlinear description model.
  • the input of the model is I i and the output of the model is O i to learn the corresponding relationship between the seat and the total number of bacterial colonies at the air supply/exhaust vent at different historical moments.
  • the number of reservoir nodes in the deep echo state network is set to 10, and the number of reservoir layers and the spectral radius of reservoir matrix in each layer are determined by 5-fold cross-validation.
  • the selection range of the above two parameters is [1, 2, 3 ,...,10] and [0.1, 0.3, 0.5, 0.7, 0.9], select a set of parameters with the highest description accuracy on the validation set to obtain a fully trained nonlinear description model h(I i ).
  • Step 5 Vehicle ventilation regulation strategy based on multi-objective optimization
  • the optimization variable is the ventilation rate v of all air supply and exhaust outlets, and the search range of the variable satisfies the following formula:
  • uk and lk are the upper and lower limits of the ventilation rate of the kth air supply/exhaust outlet, respectively.
  • the fitting results of the total bacterial colonies of the air supply/exhaust outlet under different ventilation rates are calculated.
  • the optimization objective is set to minimize the fitting result of the total number of bacterial colonies at each seat at the same time, and the optimization function is:
  • the evaluation index is the total number of bacterial colonies at the seat, and the cumulative fitting result of the total number of bacterial colonies on all seats is combined with the variance (Var):
  • the non-dominated solution NS * arg min E that minimizes the evaluation index is selected to determine the ventilation rates of all supply and exhaust ports.
  • Step 6 After completing the ventilation adjustment of the train compartment according to the obtained ventilation rate, each detection point continuously detects the total number of bacterial colonies and transmits the data to the data storage platform.
  • Step 7 In a period of time after the completion of the first ventilation adjustment, there is no need to re-train the model, and it is only necessary to calculate and output the optimal ventilation adjustment strategy according to the subsequent detection data. Due to the changes in the distribution of airborne microorganisms caused by the behavior of different people, the causality test, nonlinear description and multi-objective optimization models all require regular retraining and parameter updating to ensure the validity of the model, and the retraining time can be adjusted. The interval is set to 3 hours.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Organic Chemistry (AREA)
  • Mechanical Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Wood Science & Technology (AREA)
  • Immunology (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Zoology (AREA)
  • Molecular Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Thermal Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Microbiology (AREA)
  • Genetics & Genomics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Pathology (AREA)
  • Toxicology (AREA)
  • Biotechnology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Dispersion Chemistry (AREA)
  • Epidemiology (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)

Abstract

本发明公开了一种列车车厢空气调控方法、装置、存储介质及程序产品，根据各测点间微生物扩散情况调节通风系统，进而降低乘客所在区域的微生物污染指标。该方法对铁路列车空气质量调控有着指导作用。本发明研究了微生物污染与大气污染物浓度的映射关系，能有效解决微生物检测的实时性问题，确保对列车车厢内微生物污染的实时调控。

Description

列车车厢空气调控方法、装置、存储介质及程序产品 技术领域
本发明涉及列车环境监测领域，特别是一种列车车厢空气调控方法、装置、存储介质及程序产品。
背景技术
随着我国轨道交通行业的不断发展，旅客列车舒适性要求也逐渐被公众所关注。受到空气压力波影响，列车车厢需在高速行驶时保证适当的内外压差，因此高速列车通常采用密封式车体结构，所有车窗均无法打开。在此情况下，车厢内部的空气污染物处理完全依赖于通风系统。因此，通风系统的质量和调节策略将直接影响到乘客舒适性。如何对列车环境进行监测并相应地调节通风系统成为了亟待解决的问题。
现有关于列车车厢环境控制的技术主要涉及以下两方面：
1、新型空气质量检测装置及净化装置的安装。如公开号为CN101885338A的专利申请提出了列车空调通风系统智能化采样检测及空气净化装置，包括变频旋流捕尘器和高效过滤器等。公开号为CN105172818A的专利申请提出了一种列车专用空气净化器，包括上箱体和与上箱体相互配合的下箱体。
2、基于大气污染物检测的车厢环境调节方法。公开号为CN110239577A的专利申请提出了一种车内污染环境下列车乘员健康防护系统及其方法，包括基础数据获取模块、列车外部空气质量预测模块、列车内部空气质量预测模块和通风策略制定模块。公开号为CN104608785A的专利申请提出了一种高速列车空调系统智能化管控方法。
以上方法主要以列车内部的PM2.5等大气污染物作为空气质量评估依据，然而，现有技术并未关注空气环境中生物污染对人体健康的危害，现阶段没有相关研究重视列车车厢这一密闭环境的生物性污染物。此外，由于微生物测量机理与PM2.5等污染物不同，微生物测量必须通过长时间菌落培养，难以直接进行检测并采取实时调控措施。
发明内容
本发明所要解决的技术问题是，针对现有技术不足，提供一种列车车厢空气调控方法、装置、存储介质及程序产品，根据车厢内的微生物分布情况对乘客健康做出最优级别的防护措施。
为解决上述技术问题，本发明所采用的技术方案是：一种列车车厢空气调控方法、系统及存储介质，包括以下步骤：
1)检测列车送风口、排风口和座椅处的PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度和细菌菌落总数；
2)根据车厢内各测点的PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度和细菌菌落总数，建立每个微小环境单元内细菌菌落总数D和大气污染物浓度d之间的映射关系；其中，所述微小环境单元即测点；
3)选取时间长度为N分钟的实测大气污染物浓度数据集，根据所述映射关系计算细菌菌落总数，将第i个座椅处细菌菌落总数时间序列记为
Figure PCTCN2021122732-appb-000001
第j个送风口或排风口细菌菌落总数时间序列记为
Figure PCTCN2021122732-appb-000002
采用格兰杰因果关系检验进行假设检验，
判断
Figure PCTCN2021122732-appb-000003
与
Figure PCTCN2021122732-appb-000004
是否存在因果关系，进而得到每个座椅检测点与m个送风口和n个排风口的检验结果集合；
4)根据所述映射关系和检验结果集合，获取所有座椅检测点的非线性描述模型库；
5)将列车所有送风口、排风口的通风速率作为灰狼优化算法的输入，计算在不同通风速率下的送风口/排风口细菌菌落总数拟合结果，将所述拟合结果作为所述非线性描述模型库的输入，得到各座椅处细菌菌落总数的拟合结果，利用所述各座椅处细菌菌落总数的拟合结果确定所有送风口和排风口的通风速率。
本发明通过学习车厢内微生物污染与空气污染物浓度的映射关系，并根据车厢内的微生物分布情况实时做出对乘客健康的最优防护措施。本发明对列车车厢的微生物进行检测和分析处理，根据各测点间微生物分布情况调节通风系统，进而降低乘客所在区域的微生物污染。该方法对铁路列车空气质量调控有着指导作用。
步骤2)中，建立每个微小环境单元内细菌菌落总数D和大气污染物浓度d之间的映射关系的具体实现过程包括：
A、读取M个连续历史时刻内当前微小环境单元的空气污染物浓度和细菌菌落总数指标数据集，并将所述数据集划分为训练集和测试集；
B、采用深度置信网络构建微生物-空气污染物模型，将空气污染物浓度作为深度置信网络的输入，同一时刻的细菌菌落总数作为深度置信网络的输出，训练所述深度置信网络；
C、将所述测试集作为训练后的深度置信网络的输入，选取在测试集上描述精度最高的一组参数作为该微小环境单元的微生物-空气污染物映射模型；
D、重复上述步骤A～C，直至遍历完所有的微小环境单元，得到共计m+n+p个检测点内细菌菌落总数和空气污染物的映射关系；m，n，p分别为送风口、排风口和座椅的检测点数。
本发明研究了微生物污染与空气污染物浓度的映射关系，能有效解决微生物检测的实时性问题，确保对列车车厢内微生物污染的实时调控。
步骤3)中，检验结果集合
Figure PCTCN2021122732-appb-000005
其中，
Figure PCTCN2021122732-appb-000006
为送风口的检验结果，
Figure PCTCN2021122732-appb-000007
Figure PCTCN2021122732-appb-000008
为排风口的检验结果，
Figure PCTCN2021122732-appb-000009
检验结果
Figure PCTCN2021122732-appb-000010
(即
Figure PCTCN2021122732-appb-000011
和
Figure PCTCN2021122732-appb-000012
)取值为0或1。
本发明的方法通过对不同测点之间微生物时间序列数据进行因果关系检验，进一步筛选与乘客所在座椅处的密切相关测点用于后续建模，实现测点空间维度的压缩，使所提供的数据特征应具有较强表征能力。
步骤4)的具体实现过程包括：
I)读取P个连续历史时刻的座椅、送风口、排风口PM2.5浓度、PM10浓度、CO浓度、NO2浓度、SO2浓度、O3浓度，根据所述映射关系计算该P个连续历史时刻内各检测点的细菌菌落总数；
II)读取第i个座椅检测点的细菌菌落总数
Figure PCTCN2021122732-appb-000013
以及与第i个座椅检测点存在因果关系的送风口和排风口的细菌菌落总数
Figure PCTCN2021122732-appb-000014
Figure PCTCN2021122732-appb-000015
为送风口的细菌菌落总数；
Figure PCTCN2021122732-appb-000016
为排风口的细菌菌落总数；
Figure PCTCN2021122732-appb-000017
即
Figure PCTCN2021122732-appb-000018
或
Figure PCTCN2021122732-appb-000019
Figure PCTCN2021122732-appb-000020
即
Figure PCTCN2021122732-appb-000021
或
Figure PCTCN2021122732-appb-000022
III)将I i作为深度回声状态网络的输入，以O i为深度回声状态网络的输出，学习在不同历史时刻下座椅与送风口/排风口细菌菌落总数的对应关系；
IV)重复步骤I)～III)，直至遍历完所有的座椅检测点，得到所有座椅检测点的非线性描述模型库；所述非线性描述模型库即所有座椅检测点与送风口/排风口细菌菌落总数的对应关系的集合。
本发明采用深度神经网络对微生物-空气污染物浓度及座椅-送风口/排风口微生物的非线性映射关系进行描述，保证了其描述精度。
步骤5)中，计算在不同通风速率下的送风口/排风口细菌菌落总数拟合结果的具体实现过程包括：
i)等间隔增加通风速率，并测定相应通风速率下的细菌菌落总数；
ii)对第k个送风口/排风口的细菌菌落总数进行最小二乘拟合，得到细菌菌落总数
Figure PCTCN2021122732-appb-000023
关于通风速率v k的多项式表达方法；
iii)重复步骤i)和步骤ii)，遍历至所有送风口和排风口，得到所有送风口和排风口的细菌菌落总数随通风速率变化的多项式拟合结果
Figure PCTCN2021122732-appb-000024
m，n分别为送风口、排风口的检测点数。
步骤5)中，设置优化目标为同时最小化各座椅处细菌菌落总数拟合结果，优化函数为：
Figure PCTCN2021122732-appb-000025
本发明采用多目标优化方法最小化各座椅处的细菌菌落总数，使乘客所在区域的微生物污染达到总体最优，避免在通风系统调节过程中导致的部分区域二次污染现象。
步骤5)中，选取使评估指标
Figure PCTCN2021122732-appb-000026
达到最小的非支配解NS *＝arg min E，用于确定所有送风口和排风口的通风速率NS *；其中，
Figure PCTCN2021122732-appb-000027
为测试集中所有座椅处细菌菌落总数的方差；u k和l k分别为第k个送风口/排风口的通风速率v k的上限和下限。
评估指标为所有座椅处细菌菌落总数的累计拟合结果和方差的结合，其中所有座椅处细菌菌落总数的累计拟合结果代表通风调控后的微生物污染程度，而方差代表各个座椅之间微生物污染的离散程度。选取使该评估指标最小的非支配解可确保：(1)车厢内的微生物污染程度总体最小；(2)各个座椅之间的微生物污染差异最小，避免个别区域出现极端污染情况。
本发明还提供了一种计算机装置，包括存储器、处理器及存储在存储器上的计算机程序；其特征在于，所述处理器执行所述计算机程序，以实现本发明列车车厢空气调控方法的步骤。
作为一个发明构思，本发明还提供了一种计算机可读存储介质，其上存储有计算机程序/指令；所述计算机程序/指令被处理器执行时实现本发明列车车厢空气调控方法的 步骤。
作为一个发明构思，本发明还提供了一种计算机程序产品，包括计算机程序/指令；该计算机程序/指令被处理器执行时实现本发明列车车厢空气调控方法的步骤。
与现有技术相比，本发明所具有的有益效果为：
1)本发明对列车车厢的微生物进行检测和分析处理。根据各测点间微生物扩散情况调节通风系统，进而降低乘客所在区域的微生物污染指标。该方法对铁路列车空气质量调控有着指导作用。
2)本发明研究了微生物污染与大气污染物浓度的映射关系，能有效解决微生物检测的实时性问题，确保对列车车厢内微生物污染的实时调控。
3)本发明采用送风口、排风口和座椅多测点综合检测的方式，能有效描述车厢内部环境的大气污染物和微生物分布情况，确保检测结果对实际空间分布情况的刻画真实性。
4)本发明的方法通过对不同测点之间微生物时间序列数据进行因果关系检验，进一步筛选与乘客所在座椅处的密切相关测点用于后续建模，实现测点空间维度的压缩，使所提供的数据特征应具有较强表征能力。
5)本发明采用深度神经网络对微生物-大气污染物浓度及座椅-送风口/排风口微生物的非线性映射关系进行描述，保证了其描述精度。
6)本发明采用多目标优化方法最小化各座椅处的细菌菌落总数，使乘客所在区域的微生物污染达到总体最优，避免在通风系统调节过程中导致的部分区域二次污染现象。
附图说明
图1为本发明方法流程图。
具体实施方式
如图1所示，本发明实施例的具体实现过程如下：
步骤1：污染数据多测点采集
列车车厢内部包括PM 2.5、PM 10、CO、NO 2、SO 2和O 3六种大气污染物以及细菌、真菌、病毒等微生物污染。微生物与空气质量状况密切相关，一般情况下空气中的细菌菌落总数与致病性微生物(细菌、真菌、病毒)的存在概率呈正相关，因此本专利以细菌菌落总数指标来衡量微生物的致病性。于列车车厢的多个送风口、排风口和座椅处布置TS WES-C空气污染物检测器(测量PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度，实时检测)以及安德生撞击式空气微生物采样器(测量细菌菌落总 数，需经过48h微生物培养)。
所得数据包括送风口、排风口和座椅处的PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度和细菌菌落总数，可表示为
Figure PCTCN2021122732-appb-000028
和
Figure PCTCN2021122732-appb-000029
式中
Figure PCTCN2021122732-appb-000030
代表第m个送风口的大气污染物浓度，
Figure PCTCN2021122732-appb-000031
代表第n个排风口的大气污染物浓度，
Figure PCTCN2021122732-appb-000032
代表第p个座椅处的大气污染物浓度，式中
Figure PCTCN2021122732-appb-000033
代表第m个送风口的细菌菌落总数，
Figure PCTCN2021122732-appb-000034
代表第n个排风口的细菌菌落总数，
Figure PCTCN2021122732-appb-000035
代表第p个座椅处的细菌菌落总数，i代表PM2.5、PM10、CO、NO2、SO2和O3六种大气污染物，m，n，p分别为送风口、排风口和座椅的测点数。将每个检测点视为微小环境单元，检测数据与车厢编号进行对应，并记录检测数据的时间戳，相邻数据间隔为5分钟。采集数据通过4G方式传输至数据存储平台。
步骤2：微生物-大气污染物映射学习
根据车厢测点历史污染数据，建立模型学习每个微小环境单元内细菌菌落总数D和大气污染物浓度d之间的映射关系。具体建模过程如下：
A1：选定微小环境单元，读取200个连续历史时刻内该微小环境单元的大气污染物浓度和细菌菌落总数指标数据集。
A2：数据集划分。上述数据集包含200个连续历史时刻，将1～160时刻的数据作为训练集，161～200时刻的数据作为测试集。
A3：采用深度置信网络构建微生物-大气污染物模型，将大气污染物浓度作为深度置信网络的输入，同一时刻的细菌菌落总数作为深度置信网络的输出。深度置信网络的层数采用5折交叉验证确定，选取范围为[1,2,3,4,5]。
A4：将训练完备的深度置信网络在测试集上进行模型检验，选取在测试集上描述精度最高的一组参数作为该微小环境单元的微生物-大气污染物映射模型。
A5：将A1～A4遍历至所有微小环境单元(即检测点)，得到所有共计m+n+p个检测点内细菌菌落总数和大气污染物的映射关系{D＝f(d)|i＝1,2,3,...,m+n+p}，其中f代表该映射关系。
步骤3：基于微生物扩散机理的测点因果关系检验
微生物在车厢中的空间分布及扩散情况受空气运动影响，各测点之间的细菌菌落总数存在数据层面的因果关系。针对每个车厢，分析座椅处与各送风口、排风口细菌菌落总数时间序列的因果关系。
选取时间长度为N分钟的实测大气污染物浓度数据集，根据步骤2所得映射关系计算细菌菌落总数。将第i个座椅处细菌菌落总数时间序列记为
Figure PCTCN2021122732-appb-000036
第j个送风口或排风口细菌菌落总数时间序列记为
Figure PCTCN2021122732-appb-000037
采用格兰杰因果关系检验(Granger causality test,GCT)，进行假设检验从而判断
Figure PCTCN2021122732-appb-000038
与
Figure PCTCN2021122732-appb-000039
是否存在因果关系。检验结果
Figure PCTCN2021122732-appb-000040
输出为0或1，其中0代表座椅处细菌菌落总数时间序列
Figure PCTCN2021122732-appb-000041
与送风口/排风口细菌菌落总数时间序列
Figure PCTCN2021122732-appb-000042
不存在因果关系，反之1代表存在因果关系：
Figure PCTCN2021122732-appb-000043
GCT()代表格兰杰因果关系检验。得到每个座椅检测点与m个送风口和n个排风口的检验结果集合：
Figure PCTCN2021122732-appb-000044
步骤4：因果关联测点非线性描述建模
针对每个座椅检测点建立其相关送风口/排风口的非线性描述模型，具体建模过程如下：
B1：读取100个连续历史时刻的座椅、送风口、排风口PM2.5浓度、PM10浓度、CO浓度、NO2浓度、SO2浓度、O3浓度，根据步骤2所得映射关系计算100个连续历史时刻内各测点的细菌菌落总数。
B2：数据集划分。上述数据集包含100个连续历史时刻，将1～60时刻的数据作为训练集，61～80时刻的数据作为验证集，81～100时刻的数据作为测试集。
B3：读取第i个座椅检测点的细菌菌落总数
Figure PCTCN2021122732-appb-000045
以及与第i个座椅检测点存在因果关系的送风口和排风口的细菌菌落总数
Figure PCTCN2021122732-appb-000046
Figure PCTCN2021122732-appb-000047
为送风口的细菌菌落总数；
Figure PCTCN2021122732-appb-000048
为排风口的细菌菌落总数；
Figure PCTCN2021122732-appb-000049
即
Figure PCTCN2021122732-appb-000050
或
Figure PCTCN2021122732-appb-000051
Figure PCTCN2021122732-appb-000052
即
Figure PCTCN2021122732-appb-000053
或
Figure PCTCN2021122732-appb-000054
B4：采用深度回声状态网络构建非线性描述模型，模型输入为I i，模型输出为O i，以学习在不同历史时刻下座椅与送风口/排风口细菌菌落总数的对应关系。将深度回声状态网络的储蓄池节点数设置为10，储蓄池层数和在每一层储蓄池矩阵谱半径采用5折交叉验证确定，上述两个参数的选取范围分别为[1,2,3,...,10]和[0.1,0.3,0.5,0.7,0.9]，选取在验证集上描述精度最高的一组参数得到训练完备后的非线性描述模型h(I i)。
B5：将A1～A4遍历至所有座椅检测点，得到所有座椅检测点的非线性描述模型库{h(I i)|i＝1,2,3,...,p}。
步骤5：基于多目标优化的车厢通风调节策略
C1：测算所有送风口/排风口处细菌菌落总数随通风速率的变化关系。按以下步骤进行：
1)等间隔增加通风速率，并测定相应通风速率下的细菌菌落总数，以时间戳-通风速率-细菌菌落总数的数据格式记录于数据存储平台中。
2)针对第k个送风口/排风口，进行最小二乘拟合，得到细菌菌落总数
Figure PCTCN2021122732-appb-000055
关于通风速率v k的多项式表达方法：
Figure PCTCN2021122732-appb-000056
3)重复以上步骤，遍历至所有送风口和排风口，得到所有送风口和排风口的细菌菌落总数随通风速率变化的多项式拟合结果
Figure PCTCN2021122732-appb-000057
C2：建立多目标优化模型，具体实施细节如下：
1)选取优化算法并设定初始超参数：采用多目标灰狼优化，并嵌入领导者选择机制和存档储存机制来提高收敛能力(MIRJALILI S,SAREMI S,MIRJALILI S M,et al.Multi-objective grey wolf optimizer[J].Expert Systems With Applications,2016,47:106-19.)。多目标灰狼优化的搜索种群数，最大迭代次数，存档大小分别设置为200，100和50。
2)优化变量为所有送风口和排风口的通风速率v，变量的搜索范围满足下式：
l k≤v k≤u k
其中u k和l k分别为第k个送风口/排风口的通风速率上下限。
3)根据C1所得送风口和排风口的细菌菌落总数随通风速率变化的多项式拟合方法，计算在不同通风速率下的送风口/排风口细菌菌落总数拟合结果。将所得细菌菌落总数输入B5所得座椅检测点的非线性描述模型库，输出各座椅处细菌菌落总数的拟合结果。设置优化目标为同时最小化各座椅处细菌菌落总数拟合结果，优化函数为：
Figure PCTCN2021122732-appb-000058
Figure PCTCN2021122732-appb-000059
4)执行多目标优化(MIRJALILI S,SAREMI S,MIRJALILI S M,et al.Multi-objective grey wolf optimizer[J].Expert Systems With Applications,2016,47:106-19.)，并记录迭代次数Itr＝1。计算所有搜索结果的优化函数值，并选取非支配解存入档案中。
5)更新搜索路径，生成新的通风速率搜索结果。
6)搜索次数It＝It+1，若更新后的It小于最大迭代次数，则返回步骤4)；否则多目标优化算法结束，输出最终存档中的非支配解集NS。
7)评估非支配解在测试集上的表现性能，评估指标为座椅处细菌菌落总数将所有座椅细菌菌落总数的累计拟合结果和方差(Var)的结合：
Figure PCTCN2021122732-appb-000060
选取使评估指标达到最小的非支配解NS *＝arg min E，用于确定所有送风口和排风口的通风速率。
步骤6：根据所得通风速率完成列车车厢通风调节后，各检测点对细菌菌落总数进行持续检测并将数据传输至数据存储平台。
步骤7：在第一次通风调节完成后的一段时间内不需再次进行模型训练，只需根据后续检测数据进行计算并输出最优通风调节策略。由于不同人群行为导致的空气微生物分布状况会发生改变，所述因果关系检验、非线性描述和多目标优化模型均需要定期进行重新训练、更新参数以保证模型的有效性，可以将重新训练的时间间隔设定为3小时。

Claims (10)

  1. 一种列车车厢空气调控方法，其特征在于，包括以下步骤：
    1)检测列车送风口、排风口和座椅处的PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度和细菌菌落总数；
    2)根据车厢内各测点的PM 2.5浓度、PM 10浓度、CO浓度、NO 2浓度、SO 2浓度、O 3浓度和细菌菌落总数，建立每个微小环境单元内细菌菌落总数D和大气污染物浓度d之间的映射关系；其中，所述微小环境单元即测点；
    3)选取时间长度为N分钟的实测大气污染物浓度数据集，根据所述映射关系计算细菌菌落总数，将第i个座椅处细菌菌落总数时间序列记为
    Figure PCTCN2021122732-appb-100001
    第j个送风口或排风口细菌菌落总数时间序列记为
    Figure PCTCN2021122732-appb-100002
    判断
    Figure PCTCN2021122732-appb-100003
    与
    Figure PCTCN2021122732-appb-100004
    是否存在因果关系，进而得到每个座椅检测点、m个送风口和n个排风口的检验结果集合；
    4)根据所述映射关系和检验结果集合，获取所有座椅检测点的非线性描述模型库；
    5)将列车所有送风口、排风口的通风速率作为灰狼优化算法的输入，计算在不同通风速率下的送风口/排风口细菌菌落总数拟合结果，将所述拟合结果作为所述非线性描述模型库的输入，得到各座椅处细菌菌落总数的拟合结果，利用所述各座椅处细菌菌落总数的拟合结果确定所有送风口和排风口的通风速率。
  2. 根据权利要求1所述的列车车厢空气调控方法，其特征在于，步骤2)中，建立每个微小环境单元内细菌菌落总数D和大气污染物浓度d之间的映射关系的具体实现过程包括：
    A、读取M个连续历史时刻内当前微小环境单元的空气污染物浓度和细菌菌落总数指标数据集，并将所述指标数据集划分为训练集和测试集；
    B、采用深度置信网络构建微生物-空气污染物模型，将空气污染物浓度作为深度置信网络的输入，同一时刻的细菌菌落总数作为深度置信网络的输出，训练所述深度置信网络；
    C、将所述测试集作为训练后的深度置信网络的输入，选取在测试集上描述精度最高的一组参数作为该微小环境单元的微生物-空气污染物映射模型；
    D、重复上述步骤A～C，直至遍历完所有的微小环境单元，得到共计m+n+p个检测点内细菌菌落总数和空气污染物的映射关系；m，n，p分别为送风口、排风口和座椅的检测点数。
  3. 根据权利要求1或2所述的列车车厢空气调控方法，其特征在于，步骤3)中，检验结果集合
    Figure PCTCN2021122732-appb-100005
    其中，
    Figure PCTCN2021122732-appb-100006
    为送风口的检验结果，
    Figure PCTCN2021122732-appb-100007
    为排风口的检验结果，
    Figure PCTCN2021122732-appb-100008
    检验结果
    Figure PCTCN2021122732-appb-100009
    和
    Figure PCTCN2021122732-appb-100010
    取值为0或1；GCT()代表格兰杰因果关系检验。
  4. 根据权利要求3所述的列车车厢空气调控方法，其特征在于，步骤4)的具体实现过程包括：
    I)读取P个连续历史时刻座椅、送风口、排风口的PM2.5浓度、PM10浓度、CO浓度、NO2浓度、SO2浓度、O3浓度，根据所述映射关系计算该P个连续历史时刻内各检测点的细菌菌落总数；
    II)读取第i个座椅检测点的细菌菌落总数
    Figure PCTCN2021122732-appb-100011
    以及与第i个座椅检测点存在因果关系的送风口和排风口的细菌菌落总数
    Figure PCTCN2021122732-appb-100012
    为送风口的细菌菌落总数；
    Figure PCTCN2021122732-appb-100013
    为排风口的细菌菌落总数；
    Figure PCTCN2021122732-appb-100014
    即
    Figure PCTCN2021122732-appb-100015
    或
    Figure PCTCN2021122732-appb-100016
    即
    Figure PCTCN2021122732-appb-100017
    或
    Figure PCTCN2021122732-appb-100018
    III)将I i作为深度回声状态网络的输入，以O i为深度回声状态网络的输出，获取在不同历史时刻下座椅与送风口/排风口细菌菌落总数的对应关系；
    IV)重复步骤I)～III)，直至遍历完所有的座椅检测点，得到所有座椅检测点的非线性描述模型库；所述非线性描述模型库即所有座椅检测点与送风口/排风口细菌菌落总数的对应关系的集合。
  5. 根据权利要求2～4之一所述的列车车厢空气调控方法，其特征在于，步骤5)中，计算在不同通风速率下的送风口/排风口细菌菌落总数拟合结果的具体实现过程包括：
    i)等间隔增加通风速率，并测定相应通风速率下的细菌菌落总数；
    ii)对第k个送风口/排风口的细菌菌落总数进行最小二乘拟合，得到细菌菌落总数
    Figure PCTCN2021122732-appb-100019
    关于通风速率v k的多项式g(v k)表达方法；
    iii)重复步骤i)和步骤ii)，遍历所有送风口和排风口，得到所有送风口和排风口的细菌菌落总数随通风速率变化的多项式拟合结果
    Figure PCTCN2021122732-appb-100020
    m，n分别为送风口、排风口的检测点数。
  6. 根据权利要求5所述的列车车厢空气调控方法，其特征在于，步骤5)中，设置优化目标为同时最小化各座椅处细菌菌落总数拟合结果，优化函数为：
    Figure PCTCN2021122732-appb-100021
    u k和l k分别为第k个送风口/排风口的通风速率v k
    Figure PCTCN2021122732-appb-100022
    的上限和下限。
  7. 根据权利要求6所述的列车车厢空气调控方法，其特征在于，步骤5)中，选取使评估指标
    Figure PCTCN2021122732-appb-100023
    达到最小的非支配解NS *＝arg min E，用于确定所有送风口和排风口的通风速率NS *；其中，
    Figure PCTCN2021122732-appb-100024
    为测试集中所有座椅处细菌菌落总数的方差。
  8. 一种计算机装置，包括存储器、处理器及存储在存储器上的计算机程序；其特征在于，所述处理器执行所述计算机程序，以实现权利要求1～7之一所述方法的步骤。
  9. 一种计算机可读存储介质，其上存储有计算机程序/指令；其特征在于，所述计算机程序/指令被处理器执行时实现权利要求1～7之一所述方法的步骤。
  10. 一种计算机程序产品，包括计算机程序/指令；其特征在于，该计算机程序/指令被处理器执行时实现权利要求1～7之一所述方法的步骤。
PCT/CN2021/122732 2020-12-30 2021-10-09 列车车厢空气调控方法、装置、存储介质及程序产品 WO2022142569A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022527144A JP7360218B2 (ja) 2020-12-30 2021-10-09 列車車両用空気調和方法に用いる評価方法、装置、記憶媒体及びプログラム製品
US18/267,450 US20230366004A1 (en) 2020-12-30 2021-10-09 Train compartment air adjustment and control method and apparatus, storage medium, and program product

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011616109.X 2020-12-30
CN202011616109.XA CN112680501B (zh) 2020-12-30 2020-12-30 基于微生物的列车车厢空气调控方法、系统及存储介质

Publications (1)

Publication Number Publication Date
WO2022142569A1 true WO2022142569A1 (zh) 2022-07-07

Family

ID=75453516

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/122732 WO2022142569A1 (zh) 2020-12-30 2021-10-09 列车车厢空气调控方法、装置、存储介质及程序产品

Country Status (4)

Country Link
US (1) US20230366004A1 (zh)
JP (1) JP7360218B2 (zh)
CN (1) CN112680501B (zh)
WO (1) WO2022142569A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112680501B (zh) * 2020-12-30 2023-02-24 中南大学 基于微生物的列车车厢空气调控方法、系统及存储介质
CN114088476B (zh) * 2021-10-21 2022-11-04 上海交通大学 自适应采集控制的气溶胶病毒采集富集装置及方法
CN114254249B (zh) * 2022-03-01 2022-05-17 深圳市今典建筑科技有限公司 一种空间区域健康指数确定方法及系统
CN115115293B (zh) * 2022-08-31 2023-01-31 安徽逸天科技有限公司 一种基于大数据的公共交通环境监测分析管理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100168499A1 (en) * 2006-08-18 2010-07-01 Drexel University Method and device for air disinfection and sterilization
CN103557579A (zh) * 2013-11-14 2014-02-05 江苏万全科技有限公司 一种室内环境监测系统及其监测方法
CN106564512A (zh) * 2016-11-08 2017-04-19 武汉理工大学 一种列车车厢空气质量监控调节系统
CN110239577A (zh) * 2019-07-25 2019-09-17 中南大学 一种车内污染环境下列车乘员健康防护系统及其方法
CN112680501A (zh) * 2020-12-30 2021-04-20 中南大学 基于微生物的列车车厢空气调控方法、系统及存储介质

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2765630B2 (ja) * 1996-05-23 1998-06-18 東京都地下鉄建設株式会社 地下空間における空気調和・換気シミュレータ
US9109981B2 (en) * 2013-03-15 2015-08-18 Aircuity, Inc. Methods and apparatus for indoor air contaminant monitoring
CN203404859U (zh) 2013-07-11 2014-01-22 惠觅宙 一种空气除味净化湿化装置
CN107848362A (zh) 2015-04-14 2018-03-27 奥泰克斯有限责任公司 车辆通风系统
WO2016186534A1 (ru) 2015-05-15 2016-11-24 Общество с ограниченной ответственностью "АВТЭКС" Система вентиляции помещений и салонов транспортных средств (варианты)
CN106004347B (zh) * 2016-05-31 2018-12-21 重庆长安汽车股份有限公司 车内空气质量控制系统及方法
CN106644866A (zh) * 2016-12-28 2017-05-10 重庆金鑫科技产业发展有限公司 Pm2.5空气检测器及pm2.5空气检测系统
CN210241813U (zh) 2019-03-04 2020-04-03 上海市肺科医院 一种洁净手术室空气品质在线实时可视化的监控装置
CN110334452B (zh) * 2019-07-09 2021-03-16 中南大学 一种智慧农业大气污染物浓度分层次预警方法
CN110361505B (zh) * 2019-07-25 2021-06-22 中南大学 一种车外大气污染环境下列车乘员健康预警系统的方法
CN110395286B (zh) * 2019-08-02 2020-08-07 中南大学 一种列车车内空气品质监测与通风调控方法、系统
CN110333325B (zh) * 2019-08-02 2021-09-17 中南大学 一种大气污染环境下列车运行防护方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100168499A1 (en) * 2006-08-18 2010-07-01 Drexel University Method and device for air disinfection and sterilization
CN103557579A (zh) * 2013-11-14 2014-02-05 江苏万全科技有限公司 一种室内环境监测系统及其监测方法
CN106564512A (zh) * 2016-11-08 2017-04-19 武汉理工大学 一种列车车厢空气质量监控调节系统
CN110239577A (zh) * 2019-07-25 2019-09-17 中南大学 一种车内污染环境下列车乘员健康防护系统及其方法
CN112680501A (zh) * 2020-12-30 2021-04-20 中南大学 基于微生物的列车车厢空气调控方法、系统及存储介质

Also Published As

Publication number Publication date
CN112680501B (zh) 2023-02-24
JP2023511478A (ja) 2023-03-20
US20230366004A1 (en) 2023-11-16
JP7360218B2 (ja) 2023-10-12
CN112680501A (zh) 2021-04-20

Similar Documents

Publication Publication Date Title
WO2022142569A1 (zh) 列车车厢空气调控方法、装置、存储介质及程序产品
CN109086946B (zh) 一种常规能源和新能源公交车辆的污染气体排放预测方法
CN106920007B (zh) 基于二阶自组织模糊神经网络的pm2.5智能预测方法
CN106056210B (zh) 一种基于混合神经网络的pm2.5浓度值预测方法
CN108133295B (zh) 一种针对目标路段的机动车尾气浓度连续时间预测方法
US11938784B2 (en) Health protection system for passengers on a train in a polluted indoor environment and method thereof
CN107402586A (zh) 基于深度神经网络的溶解氧浓度控制方法及系统
CN107688701B (zh) 基于wasp模型的水质软测量及水体富营养化评价方法
EP3932773A1 (en) In-train air quality monitoring and ventilation control method and system
CN106067079B (zh) 一种基于bp神经网络的灰霾预测的系统和方法
CN110309609B (zh) 一种基于粗糙集和wnn的建筑室内空气品质评价方法
CN112734186B (zh) 列车车厢空气微生物污染实时评估方法、系统及存储介质
CN115711148A (zh) 一种基于车流车型的城市地下交通隧道智能通风方法与装置
CN101673096B (zh) 一种丹参注射液生产浓缩过程密度的软测量方法
CN109376903B (zh) 一种基于博弈神经网络的pm2.5浓度值预测方法
CN113257425B (zh) 一种优化LSTM和LightGBM参数的流感预测系统、存储介质和装置
CN111814976B (zh) 一种空调系统传感器故障误差再学习方法及系统
CN111204867B (zh) 膜生物反应器-mbr膜污染智能决策方法
CN115206444A (zh) 基于fcm-anfis模型的最佳投药量预测方法
CN114065624A (zh) 一种炼化装置管网完整性管理水平智能评估方法
Wang A neural network algorithm based assessment for marine ecological environment
Gültepe et al. Daily SO2 air pollution prediction with the use of artificial neural network models
Li et al. The Prediction Model of Air Quality in Changsha City Based on Artificial Neural Network
Hou et al. Statistical Analysis of Guangxi's Per Capita GDP Based on Deep Neural Network Model
Du Total indoor environmental pollutant control of intelligent building based on dynamic CGE

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022527144

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 21913314

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: 21913314

Country of ref document: EP

Kind code of ref document: A1