Indoor environment monitoring system suitable for near-zero energy consumption building
By integrating high-precision bioaerosol sensors and multiple detection technology, combined with deep learning algorithms, the problems of inaccurate monitoring of bacteria and viruses and complex sensor wiring in the existing technology are solved, and accurate monitoring and automatic purification of indoor air is achieved, which improves health Safety and energy efficiency.
Patent Information
- Application Number
- CN202411247052.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing indoor environmental monitoring system has defects in bacterial and virus monitoring, making it difficult to achieve accurate monitoring and timely purification. The wiring of independent sensors is complex and data acquisition is incoherent, which affects energy efficiency and system integration.
Adopt integrated high-precision bioaerosol sensors and multiple detection technology, combining sensor networks with wall materials to achieve comprehensive monitoring of bacteria and viruses in the air, and seamlessly connect with air purification equipment, using deep learning algorithms for intelligent early warning and automatic adjustment. .
Accurate monitoring and timely purification of bacteria and viruses in indoor air, reduce manual intervention and costs, improve the consistency of monitoring data and the effectiveness of purification measures, ensure the health and safety of residents, and reduce hardware costs and construction. Complexity.
Smart Images

Figure FDA0005031076060000021 
Figure FDA0005031076060000023 
Figure FDA0005031076060000041
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of indoor environment monitoring, and in particular to an indoor environment monitoring system suitable for nearly zero energy consumption buildings. Background Art
[0002] A near-zero energy building refers to a building that uses renewable energy to optimize the operation of the energy system, provides a comfortable indoor environment with minimal energy consumption, and has a comprehensive energy saving rate of more than 60%.
[0003] However, the current indoor environment monitoring system still has certain defects in the monitoring of pathogens and viruses. Traditional indoor environment monitoring systems often only focus on conventional environmental parameters such as indoor temperature and humidity, but lack the ability to accurately monitor tiny biological particles in the air, especially microorganisms such as pathogens and viruses. It is difficult to timely monitor whether the pathogens and viruses exceed the standard and take efficient purification measures, which affects the health and safety of indoor residents. Therefore, it is necessary to propose an indoor environment monitoring system suitable for near-zero energy buildings to solve the problems in the existing technology.
[0004] At the same time, indoor environment monitoring systems generally use independent sensor devices. Although these devices can provide necessary data, they have some obvious limitations. First, the installation of independent sensors usually requires complex wiring and additional space, which not only increases construction costs, but also destroys the beauty of the building and the utilization efficiency of the internal space. Secondly, the decentralized layout of traditional sensors leads to the inconsistency and incompleteness of data collection, making it difficult to form a global environmental perception. In addition, independent sensors are easily disturbed by the external environment, resulting in reduced accuracy and reliability of monitoring data. Therefore, while existing technologies can achieve the goals of building intelligence and energy saving, it is difficult to meet the requirements of energy efficiency and system integration. Summary of the invention
[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an indoor environment monitoring system suitable for near-zero energy buildings. It can realize comprehensive and accurate monitoring of microbial particles such as bacteria and viruses in indoor air by integrating high-precision bioaerosol sensors and multiple detection technologies, and realize seamless docking and linkage with air purification equipment in the building. It can automatically start and adjust related purification equipment when it detects that the bacteria and viruses exceed the standard, reducing the need and cost of manual intervention, and ensuring the timeliness and effectiveness of purification measures. It can eliminate the need for a large number of independent sensors by integrating the sensor network into the wall material.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an indoor environment monitoring system suitable for near-zero energy consumption buildings, the system comprising:
[0007] Sensor unit: It is composed of a variety of embedded sensors, distributed in various key locations of the building; the sensor unit is combined with the wall material through conductive concrete and conductive coating to form a continuous conductive network. The signal is transmitted through the conductive path in the wall material. The signal encoding and decoding technology is used to separate the independent information of each environmental parameter from the composite signal conducted by the wall;
[0008] High-precision bacteria and virus monitoring module, used to monitor the concentration of bacteria and viruses in indoor air in real time;
[0009] Cloud management and data analysis platform for centralized storage, processing and analysis of monitoring data;
[0010] Intelligent early warning module, used to intelligently analyze the concentration of monitored pathogens and viruses and issue early warning signals;
[0011] The intelligent early warning module includes a deep learning algorithm application unit, a multi-mode early warning unit and a custom threshold setting unit. The specific execution steps of the intelligent early warning module include:
[0012] Receive monitoring data collected in real time by the high-precision pathogen and virus monitoring module from the cloud management and data analysis platform;
[0013] Extract features useful for pathogen and virus identification from the received data;
[0014] The deep learning algorithm application unit trains a neural network-based deep learning model to identify the characteristics of pathogens and viruses;
[0015] Pass the preprocessed data as input to the deep learning model;
[0016] The linkage control strategy module is used to automatically start and adjust the air purification equipment when the pathogens and viruses are detected to exceed the standard.
[0017] Furthermore, in the sensor unit: orthogonal frequency division multiplexing is used to transmit signals in the wall material, and orthogonal frequency division multiplexing is used to distribute signals in the frequency domain to reduce the impact of multipath propagation, and convert sensor data into a signal form that can be conducted in the wall. The application process is as follows:
[0018] Data encoding: The sensor node encodes the collected environmental data into a binary sequence digital signal and maps it to a complex value to form a complex symbol, i.e. N is the number of subcarriers, X[k] is the complex symbol on the kth subcarrier, x[n] is the signal sample in the time domain, n represents the index in the time domain, and k represents the index in the frequency domain;
[0019] IFFT conversion: Before transmission, complex symbols are converted into time domain signals through inverse fast Fourier transform. IFFT distributes the complex symbols to multiple orthogonal subcarriers, each subcarrier occupies a different frequency band, thus achieving parallel transmission in the frequency domain;
[0020] Guard interval insertion: In order to prevent inter-symbol interference caused by multipath effects, a guard interval, i.e., a cyclic prefix, is inserted before and after each OFDM symbol. This can avoid interference even if the signal encounters reflection and delay when transmitting through walls.
[0021] Signal transmission: The coded and guard-interval-inserted signal is transmitted through the conductive path in the wall material. The wall material acts as a transmission medium, and the signal propagates inside it in the form of electromagnetic waves.
[0022] Furthermore, the data of the time domain signal after OFDM encoding is decoded using Fast Fourier Transform FFT, and the decoding process is as follows:
[0023] Received signal: Receives the signal that has experienced attenuation, reflection and multipath propagation to reach the receiving end, and the receiving end restores the original signal;
[0024] Guard interval removal: removes the cyclic prefix from the signal in preparation for FFT processing;
[0025] FFT conversion: The receiver uses Fast Fourier Transform (FFT) to convert the received time domain signal back to the frequency domain. FFT allows the receiver to demodulate the signal on the subcarrier and thus recover the original complex symbol, i.e. y[n] is the time domain signal at the receiving end, and Y[k] is the corresponding frequency domain signal;
[0026] Channel equalization: The receiving end performs channel equalization to ensure that the OFDM signal is orthogonal on the subcarriers and compensate for the frequency selective fading introduced by the channel;
[0027] Data decoding: The receiving end demodulates the recovered complex symbols back to the original data stream, completing the signal decoding process.
[0028] Furthermore, the high-precision pathogen and virus monitoring module includes a high-precision bioaerosol sensor, a multiple detection technology fusion unit, and a data recording and transmission unit. The specific execution steps of the high-precision pathogen and virus monitoring module include:
[0029] Set the monitoring area, install high-precision bioaerosol sensors at the monitored indoor locations to capture tiny biological particles in the air, and initialize sensor parameters, including sensitivity and sampling frequency;
[0030] Using high-precision bioaerosol sensors to continuously collect samples in the air, the sensor converts the collected signals into digital data for subsequent processing;
[0031] Use optical sensors to detect the scattered light and fluorescence characteristics of particles in the air to preliminarily identify biological particles;
[0032] Electrochemical sensors can be used to detect the redox reactions of specific biomolecules, providing complementary information;
[0033] The PCR amplification technology is used for molecular biological testing. The nucleic acid (DNA / RNA) in the sample is extracted and PCR amplification (polymerase chain reaction) is performed using specific primers to amplify the signal of the target biological molecule.
[0034] The multiple detection technology fusion unit fuses the data of the above multiple detection technologies;
[0035] The data recording and transmission unit will record the monitored pathogen and virus concentration data in real time, store it in local and cloud databases, and upload the data to the cloud data platform for subsequent analysis and processing.
[0036] Furthermore, in the intelligent early warning module: the model calculates the existence, type and concentration of pathogens and viruses based on the input data, and the formula for the forward propagation of the neural network is as follows: (l) =W (l) ·a (l-1) +b (l) , a (l) =f(z (l) ), where z (l) is the weighted input of the lth layer, W (l) is the weight matrix from layer l-1 to layer l, b (l) is the bias term of the lth layer, a (l-1) is the activation output of the l-1th layer, and f is the activation function;
[0037] The deep learning model learns the mapping relationship from input data to predicted values of pathogen and virus concentration through multiple layers of nonlinear transformations.
[0038] Furthermore, the specific execution steps of the intelligent early warning module also include:
[0039] Compare the pathogen and virus concentration output by the model with the preset threshold value, with C representing the monitored pathogen and virus concentration and T representing the preset threshold value. The threshold judgment is expressed as: C>T, and an early warning signal is issued. Here, > is a comparison operator, which is used to determine whether C is greater than T.
[0040] The threshold can be defined by the user through the custom threshold setting unit;
[0041] When the concentration of pathogens and viruses exceeds the preset threshold, the multi-mode early warning unit will send early warning signals to users through sound, light signals and APP push.
[0042] Furthermore, the linkage control strategy module includes an equipment linkage interface, an automatic purification control unit and an energy-saving optimization unit. The specific execution steps of the linkage control strategy module include:
[0043] The linkage control strategy module receives the warning signal of excessive concentration of pathogens and viruses from the intelligent warning module in real time;
[0044] According to the detailed content of the warning signal and the actual situation of the current indoor environment, determine the air purification equipment that needs to be started and adjusted;
[0045] Select the most appropriate combination of air purification equipment and make control decisions based on purification requirements and equipment characteristics;
[0046] The automatic purification control unit sends startup and adjustment instructions to the selected air purification equipment through the equipment linkage interface. The instructions include equipment on / off, operation mode selection, and power adjustment.
[0047] Furthermore, the specific execution steps of the linkage control strategy module also include:
[0048] During the operation of the air purification equipment, the indoor bacteria and virus concentration is continuously monitored, and the equipment operation strategy is adjusted as needed;
[0049] Under the premise of ensuring the purification effect, optimize the equipment operation strategy to reduce unnecessary energy consumption, adjust the equipment operation parameters to achieve the best purification effect while reducing energy consumption, and use the PID control algorithm. The PID control algorithm formula is: Among them, u(t) is the control quantity, e(t) is the error, that is, the difference between the target concentration of pathogens and viruses and the actual concentration of pathogens and viruses, and K p , K i , K d They are proportional, integral, and differential gains respectively.
[0050] Furthermore, the cloud management and data analysis platform includes a cloud data storage unit, a data analysis unit and a multi-region management unit. The specific execution steps of the cloud management and data analysis platform include:
[0051] The cloud platform receives real-time monitoring data uploaded by the high-precision pathogen and virus monitoring module through a secure data transmission protocol;
[0052] Use databases and big data storage systems to centrally store this data;
[0053] Clean the received data, remove noise and outliers, and format the data to meet the requirements of subsequent analysis;
[0054] Develop a real-time data processing engine to process and analyze uploaded data in real time;
[0055] Display real-time monitoring data through visualization tools, supporting remote access and viewing;
[0056] The data analysis unit uses big data analysis technology to batch process and analyze the stored data;
[0057] Data mining algorithms are applied to discover patterns and trends in the data, and the K-means clustering algorithm is used to identify the distribution of pathogen virus concentrations in different time periods and regions. Its objective function is usually expressed as minimizing the sum of the squared distances from all points to their cluster centers: Where K is the number of clusters, C k is the set of the kth cluster, x is the cluster C k Point in, μ k It is cluster C k the center of
[0058] Based on the data analysis results, potential health risks are assessed.
[0059] Furthermore, the specific execution steps of the cloud management and data analysis platform also include:
[0060] Utilize multi-region management units to achieve unified management of monitoring data in multiple regions and buildings, and support cross-regional data comparison and analysis;
[0061] Design scheduling algorithms to automatically adjust the operating status of air purification equipment in each area and indoor space based on data analysis results and preset scheduling rules;
[0062] Through a user-friendly interactive interface, it provides data query and report generation functions, supporting users to view real-time monitoring data, historical records and analysis reports.
[0063] Compared with the existing technology, the indoor environment monitoring system suitable for near-zero energy buildings has the following beneficial effects:
[0064] The present invention integrates high-precision bioaerosol sensors and multiple detection technologies to achieve comprehensive and accurate monitoring of pathogens and viruses in indoor air, improve the monitoring level of indoor environmental health and safety, and use deep learning algorithms to perform real-time analysis of monitoring data. It can quickly identify the characteristics of pathogens and viruses, immediately trigger multi-mode early warning signals when the concentration exceeds the standard, and promptly monitor whether the pathogens and viruses exceed the standard. It can achieve seamless docking and linkage with the air purification equipment in the building, and automatically start and adjust related purification equipment when the pathogens and viruses exceed the standard, reducing the need and cost of manual intervention, and ensuring the timeliness and effectiveness of purification measures, which can ensure the health and safety of indoor residents.
[0065] The indoor environment monitoring system of the present invention integrates multiple sensors into wall materials through embedded sensor node design, reducing the use of independent sensors. This design not only reduces hardware costs, but also simplifies the installation process, reduces construction complexity and working hours, thereby significantly reducing the cost of the overall system. At the same time, due to the integrated design of sensors and wall materials, the occupation of indoor space by traditional independent sensors is avoided, thereby improving the aesthetics of the building and the space utilization efficiency.
[0066] The sensor network of the present invention is closely integrated with the wall material to form a monitoring network covering the entire building, which can collect and transmit environmental data in real time. Through the conductive properties of the wall material, the signal can be efficiently transmitted inside the wall without being restricted by traditional wiring and wireless signal interference, so that the system can provide more consistent and accurate environmental parameter monitoring, which helps to timely discover and solve potential environmental problems and ensure the health and comfort of residents and users. DETAILED DESCRIPTION
[0067] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0068] An indoor environment monitoring system suitable for a near-zero energy building, the system comprising:
[0069] Sensor unit: By integrating the sensor network into the wall material, the need for traditional independent sensors is eliminated, thereby significantly reducing the cost of system installation and deployment. Due to the embedded design of the sensor, it does not take up additional indoor space and does not require complex wiring. This not only improves the utilization of space, but also reduces interference with the interior beauty and design of the building. This design allows the building to maintain its original aesthetics and structural integrity while achieving efficient indoor environment monitoring.
[0070] In the specific implementation, embedded sensors are evenly distributed inside the walls, ceilings and floors of the building, including temperature sensors, humidity sensors, light intensity sensors and particle mass sensors. The sensor unit adopts a miniaturized design and is compatible with gypsum board wall materials. Through embedding process and coating technology, it is closely integrated with the wall surface without affecting the overall aesthetics and structural strength of the wall surface. The sensor network adopts a hybrid topology to ensure reliable data transmission and redundant backup. A low-power microprocessor is integrated inside the sensor unit to be responsible for data collection and preliminary processing. For the conductive medium transmission method, the steel mesh and metal coating inside the wall material are used as conductive paths to transmit data in the form of electrical signals and digital signals. For the optical fiber transmission method, micro optical fibers are embedded in the wall material, and optical signals are used to transmit data. Orthogonal frequency division multiplexing encoding and fast Fourier transform are used for decoding to ensure that the signal will not be distorted or interfered when it is transmitted inside the wall. For example, when the sensor node collects environmental data, the following operations are performed: the environmental data is encoded into a binary sequence digital signal and mapped to a complex value to form a complex symbol, that is, The complex symbols are converted into time domain signals through inverse fast Fourier transform, and cyclic prefixes are inserted before and after each OFDM symbol. The coded and guard interval-inserted signals are transmitted through the conductive path in the wall material. The decoding process at the receiving end is: receiving the signal that arrives after attenuation, reflection and multipath propagation, removing the cyclic prefix from the signal, and using fast Fourier transform to convert the time domain signal back to the frequency domain to restore the original complex symbols, that is, Channel equalization is performed to ensure that the OFDM signal is orthogonal on the subcarriers, and the recovered complex symbols are demodulated back to the original data stream.
[0071] High-precision bacteria and virus monitoring module, used to monitor the concentration of bacteria and viruses in indoor air in real time;
[0072] By using high-precision bioaerosol sensors and combining multiple detection technologies, the module can achieve accurate and real-time monitoring of the concentration of pathogens and viruses in indoor air. This high-precision monitoring provides a reliable data basis for subsequent early warning and control. Due to the real-time and high-precision monitoring, the system can detect potential threats of indoor pathogens and viruses earlier, so as to take timely measures to effectively prevent the spread and spread of diseases. The continuously uploaded monitoring data provides a rich data source for the cloud management and data analysis platform, supporting data-based decision-making and optimizing prevention and control strategies.
[0073] The high-precision pathogen and virus monitoring module includes a high-precision bioaerosol sensor, a multiple detection technology fusion unit, and a data recording and transmission unit. The specific execution steps of the high-precision pathogen and virus monitoring module include: setting the monitoring area, installing the high-precision bioaerosol sensor at the monitored indoor location to capture tiny biological particles in the air, and initializing the sensor parameters, including sensitivity and sampling frequency; using the high-precision bioaerosol sensor to continuously collect samples in the air, and the sensor converts the collected signals into digital data for subsequent processing;
[0074] Optical sensors are used to detect the scattered light and fluorescence characteristics of particles in the air to preliminarily identify biological particles; electrochemical sensors are used to detect the redox reactions of specific biological molecules (such as proteins on the surface of viruses) to provide supplementary information; PCR amplification technology is used for molecular biology testing to extract nucleic acids (DNA / RNA) from samples, and specific primers are used for PCR amplification (polymerase chain reaction) to amplify the signals of target biological molecules;
[0075] The multiple detection technology fusion unit will fuse the data of the above-mentioned multiple detection technologies to improve the accuracy and sensitivity of monitoring; the data recording and transmission unit will record the monitored pathogen and virus concentration data in real time, and store it in the local and cloud databases, and upload the data to the cloud data platform for subsequent analysis and processing.
[0076] Intelligent early warning module, used to intelligently analyze the concentration of monitored pathogens and viruses and issue early warning signals;
[0077] The intelligent early warning system based on deep learning algorithms can automatically learn and identify changing patterns in pathogen and virus concentrations, improve the accuracy and timeliness of early warnings, support users to customize early warning thresholds according to actual needs, make the system more flexible to adapt to different scenarios and needs, improve user experience, and send out early warning signals through sound, light signals, APP push, etc., to ensure that users can receive early warning information in a timely manner and take corresponding protective measures.
[0078] The intelligent early warning module includes a deep learning algorithm application unit, a multi-mode early warning unit, and a custom threshold setting unit. The specific execution steps of the intelligent early warning module include: receiving the monitoring data collected in real time by the high-precision pathogen and virus monitoring module from the cloud management and data analysis platform; extracting features useful for pathogen and virus identification from the received data. This step may be automatically completed by the deep learning model, but in some cases, it may also be necessary to manually design a feature extractor;
[0079] The deep learning algorithm application unit trains a deep learning model based on a neural network to identify the characteristics of pathogens and viruses; the preprocessed data (or extracted features) are passed as input to the deep learning model; the model calculates the existence, type and concentration of pathogens and viruses based on the input data. The formula for the forward propagation of the neural network is as follows: (l) =W (l) ·a (l-1) +b (l) , a (l) =f(z (l) ), where z (l) is the weighted input of the lth layer, W (l) is the weight matrix from layer l-1 to layer l, b (l) is the bias term of the lth layer, a (l-1) is the activation output of the l-1th layer, and f is the activation function (such as ReLU, sigmoid); the deep learning model learns the mapping relationship from input data to the predicted value of pathogen and virus concentration through multiple layers of nonlinear transformation, and the model outputs the type and concentration prediction value of pathogens and viruses.
[0080] The pathogen and virus concentration output by the model is compared with the preset threshold value, with C representing the monitored pathogen and virus concentration, and T representing the preset threshold value. The threshold judgment is expressed as: C>T, and an early warning signal is issued. Here, > is a comparison operator, which is used to determine whether C is greater than T. If the condition is met, the corresponding early warning operation is performed; if not, no operation is performed or monitoring continues; the threshold value can be defined by the user through the custom threshold setting unit; when the pathogen and virus concentration exceeds the preset threshold value, the multi-mode early warning unit sends an early warning signal to the user through sound, light signal and APP push.
[0081] The above algorithm formulas (such as the forward propagation of neural networks) are only examples. In actual applications, the intelligent early warning system may use more complex deep learning models and algorithms. The training process of the deep learning model (i.e. the process of learning weights W and bias b) is usually not performed in the real-time analysis stage, but is trained offline with a large amount of historical data before the system is deployed. The setting of the warning threshold can be flexibly adjusted according to different scenarios, different time periods, and different user needs to achieve more accurate and personalized warning services.
[0082] The linkage control strategy module is used to automatically start and adjust the air purification equipment when the pathogens and viruses are detected to exceed the standard;
[0083] The linkage control strategy module is seamlessly connected with the air purification equipment in the building, ensuring that the relevant equipment can be quickly started or adjusted when excessive pathogens and viruses are detected, thereby improving the response speed. Under the premise of ensuring the purification effect, unnecessary energy consumption is reduced by optimizing the equipment operation strategy, which complies with the design concept of near-zero energy buildings, reduces operating costs, and works in conjunction with the cloud management and data analysis platform to intelligently schedule the operation of purification equipment based on real-time monitoring data and historical data, thereby improving overall prevention and control efficiency.
[0084] The linkage control strategy module includes an equipment linkage interface, an automatic purification control unit and an energy-saving optimization unit. The specific execution steps of the linkage control strategy module include: the linkage control strategy module receives the warning signal of excessive concentration of pathogens and viruses from the intelligent early warning module in real time; according to the detailed content of the warning signal and the actual situation of the current indoor environment (including the type and concentration of pathogens and viruses, indoor population density, etc.), judge the air purification equipment that needs to be started and adjusted; according to the purification needs and equipment characteristics (including purification efficiency, energy consumption, coverage), select the most suitable combination of air purification equipment and make control decisions; the automatic purification control unit sends startup and adjustment instructions to the selected air purification equipment through the equipment linkage interface, and the instructions include equipment on / off, operation mode selection, and power adjustment.
[0085] During the operation of the air purification equipment, the indoor bacteria and virus concentration is continuously monitored, and the equipment operation strategy is adjusted as needed. If the purification effect is not ideal or the energy consumption is too high, it may be necessary to adjust the equipment settings or choose other purification methods; Under the premise of ensuring the purification effect, optimize the equipment operation strategy (including timer switch, power adjustment, collaborative work, etc.) to reduce unnecessary energy consumption, adjust the equipment's operating parameters (such as wind speed, power) to achieve the best purification effect while reducing energy consumption, and use PID control algorithm. The PID control algorithm formula is: Among them, u(t) is the control quantity, e(t) is the error, that is, the difference between the target concentration of pathogens and viruses and the actual concentration of pathogens and viruses, and K p , K i , K d They are proportional, integral, and differential gains respectively.
[0086] Cloud management and data analysis platform for centralized storage, processing and analysis of monitoring data;
[0087] The cloud management and data analysis platform centrally stores and processes monitoring data from multiple monitoring points, supports centralized management and analysis of large-scale data, improves data processing efficiency, supports remote access and real-time monitoring functions, enables users to view monitoring data and system status anytime and anywhere, improves management convenience, and uses big data analysis technology to conduct in-depth mining of monitoring data to identify potential health risks, provide a scientific basis for prevention and control measures, support more accurate and effective prevention and control strategy formulation, support unified scheduling and management of multiple regions and multiple buildings, and improve overall prevention and control efficiency and management level.
[0088] The cloud management and data analysis platform includes a cloud data storage unit, a data analysis unit, and a multi-region management unit. The specific execution steps of the cloud management and data analysis platform include: the cloud platform receives real-time monitoring data uploaded by the high-precision pathogen and virus monitoring module through a secure data transmission protocol (such as HTTPS); uses a database (such as MySQL, MongoDB, etc.) and a big data storage system (such as Hadoop HDFS) to centrally store these data; cleans the received data, removes noise and outliers, and formats the data to meet the requirements of subsequent analysis;
[0089] Develop real-time data processing engines (such as Apache Kafka, Apache Flink, etc.) to process and analyze uploaded data in real time; display real-time monitoring data through visualization tools (such as Grafana, Kibana, etc.) and support remote access and viewing; the data analysis unit uses big data analysis technologies (such as Hadoop, Spark, etc.) to batch process and analyze stored data;
[0090] Data mining algorithms are applied to discover patterns and trends in the data, and the K-means clustering algorithm is used to identify the distribution of pathogen virus concentrations in different time periods and regions. Its objective function is usually expressed as minimizing the sum of the squared distances from all points to their cluster centers: Where K is the number of clusters, C k is the set of the kth cluster, x is the cluster C k Point in, μ k It is cluster C k center; assess potential health risks based on data analysis results.
[0091] Utilize the multi-area management unit to realize the unified management of monitoring data of multiple areas and multiple buildings, support cross-area data comparison and analysis, design scheduling algorithms, and automatically adjust the operating status of air purification equipment in each area and indoor according to data analysis results and preset scheduling rules; provide data query and report generation functions through a user-friendly interactive interface, and support users to view real-time monitoring data, historical records and analysis reports.
[0092] Furthermore, a user-friendly interactive interface is included to provide users with a way to access monitoring data and receive warning information.
[0093] The user-friendly interactive interface supports multiple access methods such as mobile APP and web pages to meet the access needs of different users, improve the popularity and usability of the system, and design a simple and clear interactive interface so that users can easily get started and quickly master how to use the system. It displays monitoring data and historical records in the form of charts, lists, etc., making the data more intuitive and easy to understand, and convenient for users to understand and analyze. It provides a friendly user interaction experience, allowing users to easily view monitoring data, receive warning information, and query historical records, thereby improving user satisfaction and loyalty.
[0094] The user-friendly interactive interface includes a multi-platform access interface and a history query unit. The specific execution steps of the user-friendly interactive interface include: the user opens a supported device, including a mobile phone, a tablet computer, and a computer, starts the corresponding application and accesses the web page through the multi-platform access interface. If it is the first time to use, the user may need to register and log in; if the user is a registered user, just log in directly; after successful login, the user enters the main interface, which displays the core functions and important information of the system, including the current indoor pathogen and virus concentration and the most recent warning record;
[0095] Users can choose to view real-time monitoring data and historical monitoring data through the navigation menu and buttons on the main interface. The system responds to user requests, retrieves relevant data from the cloud data platform and local cache, and displays it to users in the form of charts and lists on the interface.
[0096] When the intelligent early warning module detects that the concentration of pathogens and viruses exceeds the preset threshold, the system will send an early warning signal to the user through a user-friendly interactive interface. The early warning signal is displayed in the form of pop-up windows, sounds, light signals (if supported by the device) and APP push notifications to ensure that users can obtain early warning information in a timely manner; users can enter query conditions (such as time range, area, etc.) through the historical record query unit on the interface to retrieve and view historical monitoring data and early warning records. The system retrieves relevant data from the cloud data platform and local database based on the query conditions entered by the user, and displays it to the user on the interface;
[0097] Users can customize system parameters, including warning thresholds and device linkage strategies, through the setting interface. Clear setting options and instructions are provided to help users understand the role of each parameter and set it according to their needs. After the user completes the operation, he or she can choose to exit the application and automatically save the user's current status (such as login status, interface layout, etc.) so that the user can quickly restore it when logging in next time.
[0098] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
Claims
1. An indoor environment monitoring system suitable for near-zero energy buildings, characterized in that: The system includes: Sensor unit: It is composed of a variety of embedded sensors, distributed in various key locations of the building; the sensor unit is combined with the wall material through conductive concrete and conductive coating to form a continuous conductive network. The signal is transmitted through the conductive path in the wall material. The signal encoding and decoding technology is used to separate the independent information of each environmental parameter from the composite signal conducted by the wall; High-precision bacteria and virus monitoring module, used to monitor the concentration of bacteria and viruses in indoor air in real time; Cloud management and data analysis platform for centralized storage, processing and analysis of monitoring data; Intelligent early warning module, used to intelligently analyze the concentration of monitored pathogens and viruses and issue early warning signals; The intelligent early warning module includes a deep learning algorithm application unit, a multi-mode early warning unit and a custom threshold setting unit. The specific execution steps of the intelligent early warning module include: Receive monitoring data collected in real time by the high-precision pathogen and virus monitoring module from the cloud management and data analysis platform; Extract features useful for pathogen and virus identification from the received data; The deep learning algorithm application unit trains a deep learning model based on a neural network to identify the characteristics of pathogens and viruses; Pass the preprocessed data as input to the deep learning model; The linkage control strategy module is used to automatically start and adjust the air purification equipment when the pathogens and viruses are detected to exceed the standard.
2. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 1 is characterized in that: In the sensor unit: orthogonal frequency division multiplexing is used to transmit signals in the wall material, and orthogonal frequency division multiplexing is used to distribute signals in the frequency domain to reduce the impact of multipath propagation and convert sensor data into a signal form that can be conducted in the wall. The application process is as follows: Data encoding: The sensor node encodes the collected environmental data into a binary sequence digital signal and maps it to a complex value to form a complex symbol, i.e. N is the number of subcarriers, X[k] is the complex symbol on the kth subcarrier, x[n] is the signal sample in the time domain, n represents the index in the time domain, and k represents the index in the frequency domain; IFFT conversion: Before transmission, complex symbols are converted into time domain signals through inverse fast Fourier transform. IFFT distributes the complex symbols to multiple orthogonal subcarriers, each subcarrier occupies a different frequency band, thus achieving parallel transmission in the frequency domain; Guard interval insertion: In order to prevent inter-symbol interference caused by multipath effects, a guard interval, i.e., a cyclic prefix, is inserted before and after each OFDM symbol. This can avoid interference even if the signal encounters reflection and delay when transmitting through walls. Signal transmission: The coded and guard-interval-inserted signal is transmitted through the conductive path in the wall material. The wall material acts as a transmission medium, and the signal propagates inside it in the form of electromagnetic waves.
3. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 2, characterized in that: The data of the time domain signal after OFDM encoding is decoded using Fast Fourier Transform FFT. The decoding process is as follows: Received signal: Receives the signal that has experienced attenuation, reflection and multipath propagation to reach the receiving end, and the receiving end restores the original signal; Guard interval removal: removes the cyclic prefix from the signal in preparation for FFT processing; FFT conversion: The receiver uses Fast Fourier Transform (FFT) to convert the received time domain signal back to the frequency domain. FFT allows the receiver to demodulate the signal on the subcarrier and thus recover the original complex symbol, i.e. y[n] is the time domain signal at the receiving end, and Y[k] is the corresponding frequency domain signal; Channel equalization: The receiving end performs channel equalization to ensure that the OFDM signal is orthogonal on the subcarriers and compensate for the frequency selective fading introduced by the channel; Data decoding: The receiving end demodulates the recovered complex symbols back to the original data stream, completing the signal decoding process.
4. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 1, characterized in that: The high-precision pathogen and virus monitoring module includes a high-precision bioaerosol sensor, a multiple detection technology fusion unit, and a data recording and transmission unit. The specific execution steps of the high-precision pathogen and virus monitoring module include: Set the monitoring area, install high-precision bioaerosol sensors at the monitored indoor locations to capture tiny biological particles in the air, and initialize sensor parameters, including sensitivity and sampling frequency; Using high-precision bioaerosol sensors to continuously collect samples in the air, the sensor converts the collected signals into digital data for subsequent processing; Use optical sensors to detect the scattered light and fluorescence characteristics of particles in the air to preliminarily identify biological particles; Electrochemical sensors can be used to detect the redox reactions of specific biomolecules, providing complementary information; Use PCR amplification technology for molecular biology testing, extract nucleic acid (DNA / RNA) from the sample, use specific primers for PCR amplification, and amplify the signal of the target biological molecule; The multiple detection technology fusion unit fuses the data of the above multiple detection technologies; The data recording and transmission unit will record the monitored pathogen and virus concentration data in real time, store it in local and cloud databases, and upload the data to the cloud data platform for subsequent analysis and processing.
5. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 1, characterized in that: In the intelligent early warning module: the model calculates the existence, type and concentration of pathogens and viruses based on the input data. The formula for the forward propagation of the neural network is as follows: (l) =W (l) ·a (l-1) +b (l) , a (l) =f(z (l) ), where z (l) is the weighted input of layer l, W (l) is the weight matrix from layer l-1 to layer l, b (l) is the bias term of the lth layer, a (l-1) is the activation output of the l-1th layer, and f is the activation function; The deep learning model learns the mapping relationship from input data to predicted values of pathogen and virus concentration through multiple layers of nonlinear transformations.
6. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 5, characterized in that: The specific execution steps of the intelligent early warning module also include: Compare the pathogen and virus concentration output by the model with the preset threshold value, with C representing the monitored pathogen and virus concentration and T representing the preset threshold value. The threshold judgment is expressed as: C>T, and an early warning signal is issued. Here, > is a comparison operator, which is used to determine whether C is greater than T. The threshold can be defined by the user through the custom threshold setting unit; When the concentration of pathogens and viruses exceeds the preset threshold, the multi-mode early warning unit will send early warning signals to users through sound, light signals and APP push.
7. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 1, characterized in that: The linkage control strategy module includes an equipment linkage interface, an automatic purification control unit and an energy-saving optimization unit. The specific execution steps of the linkage control strategy module include: The linkage control strategy module receives the warning signal of excessive concentration of pathogens and viruses from the intelligent warning module in real time; According to the detailed content of the warning signal and the actual situation of the current indoor environment, determine the air purification equipment that needs to be started and adjusted; Select the most appropriate combination of air purification equipment and make control decisions based on purification requirements and equipment characteristics; The automatic purification control unit sends startup and adjustment instructions to the selected air purification device through the device linkage interface. The instructions include device on / off, operation mode selection, and power adjustment.
8. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 7, characterized in that: The specific execution steps of the linkage control strategy module also include: During the operation of the air purification equipment, the indoor bacteria and virus concentrations are continuously monitored, and the equipment operation strategy is adjusted as needed; Under the premise of ensuring the purification effect, optimize the equipment operation strategy to reduce unnecessary energy consumption, adjust the equipment operation parameters to achieve the best purification effect while reducing energy consumption, and use the PID control algorithm. The PID control algorithm formula is: Among them, u(t) is the control quantity, e(t) is the error, that is, the difference between the target concentration of pathogens and viruses and the actual concentration of pathogens and viruses, and K p , K i , K d They are proportional, integral, and differential gains respectively.
9. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 1, characterized in that: The cloud management and data analysis platform includes a cloud data storage unit, a data analysis unit, and a multi-region management unit. The specific execution steps of the cloud management and data analysis platform include: The cloud platform receives real-time monitoring data uploaded by the high-precision pathogen and virus monitoring module through a secure data transmission protocol; Use databases and big data storage systems to centrally store this data; Clean the received data, remove noise and outliers, and format the data to meet the requirements of subsequent analysis; Develop a real-time data processing engine to process and analyze uploaded data in real time; Display real-time monitoring data through visualization tools, supporting remote access and viewing; The data analysis unit uses big data analysis technology to batch process and analyze the stored data; Data mining algorithms are applied to discover patterns and trends in the data, and the K-means clustering algorithm is used to identify the distribution of pathogen virus concentrations in different time periods and regions. Its objective function is usually expressed as minimizing the sum of the squared distances from all points to their cluster centers: Where K is the number of clusters, C k is the set of the kth cluster, x is the cluster C k Point in, μ k It is cluster C k the center of Based on the data analysis results, potential health risks are assessed.
10. The indoor environment monitoring system suitable for near-zero energy consumption buildings according to claim 9, characterized in that: The specific execution steps of the cloud management and data analysis platform also include: Utilize multi-region management units to achieve unified management of monitoring data in multiple regions and buildings, and support cross-regional data comparison and analysis; Design scheduling algorithms to automatically adjust the operating status of air purification equipment in each area and indoor space based on data analysis results and preset scheduling rules; Through a user-friendly interactive interface, it provides data query and report generation functions, supporting users to view real-time monitoring data, historical records and analysis reports.
Citation Information
Patent Citations
Indoor environment monitoring system and monitoring method thereof
CN103557579A
Virus monitoring and early warning system based on cloud platform
CN107645545A
Method and system for improving air quality
CN111637607A
Indoor environment monitoring system suitable for near-zero energy consumption building
CN116734918A
Intelligent ward risk nursing assessment early warning system based on deep learning
CN117409932A
Cited By
Fabricated near-zero energy consumption building external wall thermal insulation performance field test method
CN122330191A
