Multi-source sensor data analysis method and sensor device for IoT fresh air system

Abstract

In view of the problems existing in the sensor data processing of the above-mentioned existing industrial fresh air systems, the present invention discloses a multi-source sensor data analysis method and a sensor device for an IoT fresh air system. Indoor and outdoor air quality parameter information is obtained and determined through fresh air sensors, and the indoor and outdoor air quality parameter information is integrated and processed based on the fresh air system. After edge computing and analysis, correlation analysis is performed through a cloud computing platform and dynamic adjustment is performed in response to the fresh air system. The present invention uses machine learning to perform in-depth analysis on the collected data, and uses data mining algorithms to identify patterns and trends, so as to intelligently control and optimize the industrial fresh air system. It also has the function of synchronous edge computing of multi-source sensor data based on the Internet of Things nodes, which is closer to the data source of the user terminal, thereby improving the processing effect, high efficiency, security and low latency of multi-source fresh air related data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a multi-source sensor data analysis method and a sensor device for an IoT fresh air system. Background Art

[0002] Industrial fresh air systems can use cooling, heating, humidification and dehumidification equipment to adjust the air according to different production and working environment requirements to create a comfortable working environment; sensors are the source of data. Driven by technological progress and the market demand of the digital and intelligent era, sensors are now endowed with artificial intelligence perception capabilities and are applied to fresh air systems. In particular, fresh air systems in the industrial field transmit the collected sensor data to equipment and monitoring platforms in real time through various intelligent sensor collection and transmission terminals, providing big data support for data monitoring, data analysis, feedback and early warning of fresh air systems, and realizing circulation control and information visualization of fresh air systems. Then the traditional fresh air device or fresh air system extracts outdoor fresh air and introduces it into the room to realize internal and external circulation operations. The collection and detection of indoor and outdoor environments still stays at the acquisition of single data, lacks the support and correlation analysis of official weather and environmental data, and has no further fusion analysis. In addition, the traditional use of cloud computing has general efficiency and latency. For this reason, we propose a multi-source sensor data analysis method and sensor device for IoT fresh air systems. Summary of the invention

[0003] In view of the problems existing in the sensor data processing of the above-mentioned existing industrial fresh air system, the present invention is proposed.

[0004] Therefore, one of the objects of the present invention is to provide a multi-source sensor data analysis method and a sensor device for an IoT fresh air system, which utilizes machine learning to conduct in-depth analysis of the collected data, and uses data mining algorithms to identify patterns and trends, thereby intelligently controlling and optimizing the industrial fresh air system, and based on the Internet of Things nodes, performs synchronous edge computing on multi-source sensor data, thereby improving the processing effect, high efficiency and low latency of multi-source fresh air related data.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] On the one hand, the present invention provides a multi-source sensor data analysis method for an IoT fresh air system, comprising:

[0007] Acquire indoor and outdoor air quality parameter information through a fresh air sensor and determine that the indoor air quality parameter information is the first acquired data and the outdoor air quality parameter information is the second acquired data;

[0008] Based on the fresh air system, indoor and outdoor air quality parameter information is integrated and processed, and the first acquired data and the second acquired data are analyzed to obtain third acquired data, and the third acquired data responds to the data of the edge node to generate the current fresh air system integrated processing information;

[0009] After edge computing analysis, correlation analysis is performed through the cloud computing platform and dynamic adjustment is performed in response to the fresh air system. The third acquired data is transmitted to the edge wireless gateway for early warning, and the data signal is transmitted to the edge server. The collected signal is analyzed by the edge server and reported to the fresh air system cloud computing platform. Correlation analysis is performed and historical data and machine learning are used to build a fresh air system environmental change model. Result data is generated according to the fresh air system environmental change model and the circulation mode is dynamically adjusted in response to the fresh air system fusion processing information.

[0010] As a preferred solution of the present invention, the cloud computing platform of the fresh air system performs correlation analysis and uses historical data and machine learning to build a fresh air system environment change model, that is, by obtaining historical data and machine learning models to predict the change trend of indoor or outdoor air quality parameter information, the circulation mode is dynamically adjusted, specifically as follows:

[0011] Step S301, obtaining sensor data information in the IoT fresh air system to build a fresh air database, wherein the fresh air database includes control parameter information known in the preset edge node under the corresponding circulation mode ventilation mode and air quality parameter information collected by the fresh air sensor;

[0012] Step S302, based on the basic data in the fresh air database, the machine learning prediction is performed, the fresh air database is expanded and preprocessed, and after the standardized data is formed, the training set and the validation set are divided to perform database training. The training is based on the characteristic variables of the preset cycle mode, and after the feature processing, the deep machine learning is performed to learn the relationship between the characteristic variables or category data of each cycle mode, and the linear regression prediction or multivariate linear regression prediction of the cycle mode is performed;

[0013] Step S303, analyzing the circulation mode adjustment strategy of the fresh air system through cluster analysis, and according to the prediction results of linear regression prediction or multivariate linear regression prediction, inputting the prediction results into the circulation mode cases of the known specific edge nodes of the fresh air system as artificial neural networks, obtaining the associated circulation mode adjustment strategy map between the air quality parameter information collected by the fresh air sensors at all positions in the trained specific edge nodes and the prediction results, outputting the corresponding circulation mode adjustment strategy information according to the associated circulation mode adjustment strategy map relationship, that is, using the circulation mode adjustment strategy information as the output layer of the artificial neural network, and obtaining the circulation mode adjustment information of the fresh air system in the specific edge node and then outputting it;

[0014] Step S304: the fresh air system responds to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information to complete the dynamic adjustment strategy.

[0015] As a preferred solution of the present invention, the third acquired data is obtained after the first acquired data and the second acquired data are fused and processed based on the fresh air system, and specifically, the matching degree information of the fresh air system is generated by comparing and analyzing the indoor and outdoor air quality parameter information, and after judging the processing effect of the current fresh air system according to the matching degree information and a preset threshold range, the effect state of the fresh air system is graded and the corresponding third acquired data is generated based on the grade information of the current fresh air system effect state;

[0016] After comparing and analyzing the third acquired data with the matched specific edge node circulation mode adjustment information, fusion processing information of the current fresh air system is generated.

[0017] As a preferred solution of the present invention, wherein: after edge computing analysis, correlation analysis is performed through a cloud computing platform, and the correlation analysis also includes obtaining air quality related information in the weather forecast and then performing correlation analysis with the second acquired data of outdoor air quality parameter information, generating an error value to judge the accuracy of the second acquired data, and automatically adjusting the control parameter information of the fresh air system according to the air quality related information in the weather forecast.

[0018] As a preferred solution of the present invention, wherein: the third acquired data is transmitted to the edge wireless gateway for early warning. Specifically, the edge wireless gateway is set with an early warning threshold, and the edge server compares the abnormal value of the collected data signal with the early warning threshold set by the edge wireless gateway. If it is higher than the threshold or lower than the threshold, an online early warning is issued.

[0019] As a preferred solution of the present invention, the air quality parameter information includes:

[0020] PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration; and take the median or mean value of the data of PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration;

[0021] The data signal transmission of the air quality parameter information obtained by the fresh air sensor adopts the Modbus protocol or the MQTT protocol.

[0022] As a preferred solution of the present invention, the dynamic adjustment of the circulation mode is specifically as follows:

[0023] Step 101, start detecting air parameters, obtain indoor and outdoor air quality parameter information through fresh air sensors, and synchronously obtain air quality related information in weather forecasts based on specific edge nodes;

[0024] Step 102, determine whether the indoor air quality meets the standard. If not, perform fusion processing of indoor and outdoor air quality parameter information based on the fresh air system, start the internal circulation mode according to the fusion processing information of the current fresh air system, and automatically adjust the control parameter information to purify the air; if yes, proceed to the next step to determine whether the outdoor air quality meets the standard;

[0025] Step 103, determine whether the outdoor air quality meets the standard, and respond to the correlation analysis data of the air quality related information in the weather forecast. Otherwise, turn off the internal circulation mode of the fresh air system and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information. If yes, turn on the external circulation mode according to the fusion processing information of the current fresh air system and automatically adjust the control parameter information for ventilation processing and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information;

[0026] Step 104, continuously monitor indoor and outdoor air quality parameter information, determine whether the indoor and outdoor air quality meets the standard, and if so, maintain the current circulation mode and parameter information; otherwise, adjust the circulation mode based on step 102 or step 103 and automatically adjust the matching control parameter information according to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information.

[0027] As a preferred solution of the present invention, the control parameter information includes: the fresh air volume of the fresh air system, maximum and minimum fresh air volumes, exhaust volume, air flow cleanliness, ventilation times, wind force level, temperature, humidity, CO2 concentration and heat recovery amount.

[0028] On the one hand, the present invention provides a sensing device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the multi-source sensing data analysis method of the IoT fresh air system when executing the computer program.

[0029] On the one hand, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the multi-source sensor data analysis method of the IoT fresh air system are implemented.

[0030] Beneficial effects of the present invention: The present invention utilizes machine learning to conduct in-depth analysis of the collected data, and uses data mining algorithms to identify patterns and trends, so as to intelligently control and optimize the industrial fresh air system, and based on the Internet of Things nodes, it performs synchronous edge computing on multi-source sensor data, which is closer to the data source of the user terminal, thereby improving the processing effect, high efficiency, security and low latency of multi-source fresh air related data. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0032] Figure 1 It is a flow chart of a multi-source sensor data analysis method for a fresh air system of the present invention;

[0033] Figure 2 This is a flow chart of the present invention using historical data and machine learning to construct a fresh air system environment change model;

[0034] Figure 3 A schematic diagram of a flow chart of dynamic adjustment of the circulation mode of the present invention;

[0035] Figure 4 It is a schematic diagram of the modular structure of the hardware structure of the sensor device of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0037] Example 1

[0038] Reference Figure 1-Figure 3 , is an embodiment of the present invention, which provides a multi-source sensor data analysis method for an IoT fresh air system, referring to Figure 1 ,as follows:

[0039] Acquire indoor and outdoor air quality parameter information through a fresh air sensor and determine that the indoor air quality parameter information is the first acquired data and the outdoor air quality parameter information is the second acquired data;

[0040] Based on the fresh air system, indoor and outdoor air quality parameter information is integrated and processed, and the first acquired data and the second acquired data are analyzed to obtain the third acquired data. The third acquired data responds to the data of the edge node to generate the current fresh air system integrated processing information;

[0041] After edge computing analysis, correlation analysis is performed through the cloud computing platform and dynamic adjustments are made in response to the fresh air system. The third acquired data is transmitted to the edge wireless gateway for early warning, and the data signal is transmitted to the edge server. The edge server analyzes the collected signal and reports it to the fresh air system cloud computing platform for correlation analysis and uses historical data and machine learning to build a fresh air system environmental change model. The result data is generated according to the fresh air system environmental change model and the circulation mode is dynamically adjusted in response to the fresh air system fusion processing information.

[0042] In one embodiment, preferably, this embodiment needs to be further explained that the edge wireless gateway performs an early warning and transmits the third acquired data to the edge wireless gateway for early warning. Specifically, the edge wireless gateway is provided with an early warning threshold, and the edge server transmits the abnormal value of the collected data signal to the early warning threshold set by the edge wireless gateway for comparison. If it is higher than the threshold or lower than the threshold, an online early warning is performed.

[0043] Among them, this embodiment can obtain indoor and outdoor air quality parameter information through fresh air sensors, and can perform synchronous edge computing on multi-source sensor data based on the Internet of Things node, and perform analysis and processing at the data source closer to the user terminal, thereby improving the processing effect of multi-source fresh air related data and facilitating the subsequent machine learning prediction of the cloud platform.

[0044] refer to Figure 2 In one embodiment, the fresh air system cloud computing platform performs correlation analysis and uses historical data and machine learning to build a fresh air system environment change model, that is, by obtaining historical data and machine learning models to predict the change trend of indoor or outdoor air quality parameter information, the circulation mode is dynamically adjusted, specifically as follows:

[0045] Step S301, obtaining sensor data information in the IoT fresh air system to build a fresh air database, the fresh air database includes known control parameter information in the preset edge node under the corresponding circulation mode ventilation mode and air quality parameter information collected by the fresh air sensor;

[0046] Step S302, based on the basic data in the fresh air database, perform machine learning and prediction, perform data expansion and data preprocessing on the fresh air database, form standardized data and divide the training set and validation set to perform database training, train the characteristic variables according to the preset cycle mode, perform deep machine learning after feature processing to learn the relationship between the characteristic variables or category data of each cycle mode, and perform linear regression prediction or multivariate linear regression prediction of the cycle mode;

[0047] Step S303, analyzing the circulation mode adjustment strategy of the fresh air system through cluster analysis, and according to the prediction results of linear regression prediction or multivariate linear regression prediction, inputting the prediction results into the circulation mode cases of the known specific edge nodes of the fresh air system as artificial neural networks, obtaining the associated circulation mode adjustment strategy map between the air quality parameter information collected by the fresh air sensors at all positions in the trained specific edge nodes and the prediction results, outputting the corresponding circulation mode adjustment strategy information according to the associated circulation mode adjustment strategy map relationship, that is, using the circulation mode adjustment strategy information as the output layer of the artificial neural network, and obtaining the circulation mode adjustment information of the fresh air system in the specific edge node and then outputting it;

[0048] Step S304: the fresh air system responds to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information to complete the dynamic adjustment strategy.

[0049] In one embodiment, the third acquired data is obtained by fusing the first acquired data and the second acquired data based on the fresh air system, and specifically, by comparing and analyzing the indoor and outdoor air quality parameter information, the matching degree information of the fresh air system is generated, and after judging the processing effect of the current fresh air system according to the matching degree information and the preset threshold range, the level of the effect state of the fresh air system is divided and based on the level information of the current fresh air system effect state, the corresponding third acquired data is generated;

[0050] After comparing and analyzing the third acquired data with the matched specific edge node circulation mode adjustment information, fusion processing information of the current fresh air system is generated.

[0051] It needs to be further explained that by comparing and analyzing the indoor and outdoor air quality parameter information, the matching information of the fresh air system is generated, which can be analyzed and processed by a similar algorithm. The high similarity of the indoor and outdoor air quality information matching may indicate that the indoor air purification system is not effective, the pollutants in the indoor air are at similar levels to those in the outdoor air, or outdoor pollution is invading, especially in the case of poor air quality, which may mean that outdoor pollutants are more likely to invade the indoor space, indoor protection measures are insufficient, and there are efficiency problems with the air conditioning or fresh air system, the existence of indoor pollution sources, and frequent indoor and outdoor air exchange. The above high matching conditions generally represent the effect of the air purification system and require further processing. For this purpose, the third acquired data is compared and analyzed with the matched specific edge node circulation mode adjustment information to generate the fusion processing information of the current fresh air system. According to the fusion processing information of the current fresh air system of the edge computing node, high-efficiency purification processing in the internal circulation mode or the external circulation mode can be performed, thereby completing the enhancement of indoor air purification measures and ensuring efficient intelligent control and optimization effects.

[0052] In one embodiment, preferably, after edge computing analysis, correlation analysis is performed through a cloud computing platform. The correlation analysis also includes obtaining air quality related information in the weather forecast and then performing correlation analysis with second acquired data of outdoor air quality parameter information, generating an error value to determine the accuracy of the second acquired data, and automatically adjusting the control parameter information of the fresh air system according to the air quality related information in the weather forecast.

[0053] It can be understood that in the case of poor air quality, this embodiment can reduce the amount of fresh air and increase the filtration level of the filtration system; at the same time, when high-pollution weather is predicted, the fresh air system can start in advance or strengthen the pretreatment program, such as enhancing filtration or using electrostatic dust removal, to reduce the indoor penetration of pollutants. In addition, historical weather and air quality data are used to analyze and predict air quality change trends and optimize the long-term operation strategy of the fresh air system. It can be seen that by incorporating air quality information in weather forecasts into the control parameters of the fresh air system, the intelligence level of the system can be improved, and more accurate and efficient air management can be achieved.

[0054] refer to Figure 3 In one embodiment, the specific steps of dynamically adjusting the cycle mode are given as follows:

[0055] Step 101, start detecting air parameters, obtain indoor and outdoor air quality parameter information through fresh air sensors, and synchronously obtain air quality related information in weather forecasts based on specific edge nodes;

[0056] Step 102, determine whether the indoor air quality meets the standard. If not, perform fusion processing of indoor and outdoor air quality parameter information based on the fresh air system, start the internal circulation mode according to the fusion processing information of the current fresh air system, and automatically adjust the control parameter information to purify the air; if yes, proceed to the next step to determine whether the outdoor air quality meets the standard;

[0057] Step 103, determine whether the outdoor air quality meets the standard, and respond to the correlation analysis data of the air quality related information in the weather forecast. Otherwise, turn off the internal circulation mode of the fresh air system and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information. If yes, turn on the external circulation mode according to the fusion processing information of the current fresh air system and automatically adjust the control parameter information for ventilation processing and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information;

[0058] Step 104, continuously monitor indoor and outdoor air quality parameter information, determine whether the indoor and outdoor air quality meets the standard, and if so, maintain the current circulation mode and parameter information; otherwise, adjust the circulation mode based on step 102 or step 103 and automatically adjust the matching control parameter information according to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information.

[0059] In one embodiment, the air quality parameter information specifically includes:

[0060] PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration; and take the median or mean value of the data of PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration;

[0061] The data signal transmission of the air quality parameter information obtained by the fresh air sensor adopts the Modbus protocol or the MQTT protocol.

[0062] In one embodiment, the control parameter information specifically includes: the fresh air volume, maximum and minimum fresh air volumes, exhaust volume, airflow cleanliness, ventilation times, wind force level, temperature, humidity, CO2 concentration, and heat recovery of the fresh air system. The fresh air volume refers to the amount of fresh air introduced into the room or system per unit time; the exhaust air volume refers to the amount of air exhausted from the room per unit time, and together with the fresh air volume, determines the indoor air replacement efficiency; the ventilation times refers to the number of indoor air replacements per unit time, that is, the ratio of the fresh air volume to the room volume.

[0063] Example 2

[0064] This embodiment provides a hardware structure of a sensing device, which is a multi-type sensor, such as the relevant sensor type that can monitor air quality parameter information in Embodiment 1. In addition, the sensing device also includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the multi-source sensing data analysis method of the IoT fresh air system are implemented.

[0065] refer to Figure 4 This is a schematic diagram of the hardware structure used for controlling a fresh air system when a sensor device according to an embodiment of the present application is applied.

[0066] The electronic device of the sensor device may include a processor 41 and a memory 42 storing computer program instructions. It is understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device of the sensor device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0067] Specifically, the processor 41 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0068] Among them, the memory 42 may include a large capacity memory for data or instructions. For example, but not limitation, the memory 42 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (OPENCV), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 42 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 42 may be inside or outside the data processing device. In a specific embodiment, the memory 42 is a non-volatile memory. In a specific embodiment, the memory 42 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (ErasableProgrammable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically ErasableProgrammable Read-Only Memory, EEPROM for short), an electrically alterable ROM (ElectricallyAlterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0069] The memory 42 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 41; the processor 41 implements the electronic device analysis and processing method of the sensor device in the above embodiment by reading and executing the computer program instructions stored in the memory 42.

[0070] In some of the embodiments, the electronic device may further include a communication interface 43 and a bus 40. Figure 4 As shown, the processor 41, the memory 42, and the communication interface 43 are connected through the bus 40 and complete communication with each other, and establish communication with the ventilation system. The communication interface 43 can use the RS485 communication interface for communication.

[0071] The present invention combines machine learning with Internet of Things technology to perform a series of innovative intelligent control and optimization of industrial fresh air systems. It uses Internet of Things technology to collect multi-source sensor data in industrial fresh air systems in real time, including temperature, humidity, air quality, CO2 concentration, etc. Machine learning algorithms are used to conduct in-depth analysis of the collected data, explore patterns and trends in the data, and provide decision support for system optimization. According to the data analysis results, the operating parameters of the fresh air system, such as fresh air volume, exhaust volume, working status of the filtration system, etc., are automatically adjusted to achieve optimal air quality control.

[0072] At the same time, through edge computing integration, synchronous edge computing is performed through IoT nodes, and data processing tasks are brought closer to the data source, reducing data transmission delays and improving processing efficiency and response speed. With high efficiency and high security, the application of edge computing reduces the amount of data transmission in the network, reduces the computing burden of the central server, and improves the operating efficiency and effectiveness of the entire fresh air system.

[0073] In summary, the IoT fresh air system, based on the multi-source sensor data analysis method implemented in this paper and the hardware of the sensor device, can achieve more intelligent and automated operation, improve indoor air quality, reduce energy consumption, and provide a more comfortable indoor environment for users or industrial environments.

[0074] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0075] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0076] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0077] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0078] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0079] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0080] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0081] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A multi-source sensor data analysis method for an IoT fresh air system, characterized in that: include: Acquire indoor and outdoor air quality parameter information through a fresh air sensor and determine the indoor air quality parameter information as first acquired data and the outdoor air quality parameter information as second acquired data; Based on the fresh air system, indoor and outdoor air quality parameter information is integrated and processed, and the first acquired data and the second acquired data are analyzed to obtain third acquired data. The third acquired data responds to the data of the edge node to generate the current fresh air system integrated processing information. Specifically, by comparing and analyzing the indoor and outdoor air quality parameter information, the matching degree information of the fresh air system is generated. After judging the processing effect of the current fresh air system according to the matching degree information and a preset threshold range, the effect state of the fresh air system is graded and based on the grade information of the current fresh air system effect state, the corresponding third acquired data is generated. After comparing and analyzing the third acquired data with the matching specific edge node circulation mode adjustment information, the integrated processing information of the current fresh air system is generated. After edge computing and parsing the fusion processing information of the current fresh air system, correlation analysis is performed through the cloud computing platform and the fresh air system is dynamically adjusted in response, the third acquired data is transmitted to the edge wireless gateway for early warning, and the data signal is transmitted to the edge server, and the edge server parses the collected signal and reports it to the fresh air system cloud computing platform, performs correlation analysis and uses historical data and machine learning to build a fresh air system environmental change model, generates result data according to the fresh air system environmental change model and responds to the fusion processing information of the fresh air system to dynamically adjust the circulation mode, that is, by acquiring historical data and machine learning models to predict the change trend of indoor or outdoor air quality parameter information, the circulation mode is dynamically adjusted, specifically as follows: Step S301, obtaining sensor data information in the IoT fresh air system to build a fresh air database, wherein the fresh air database includes control parameter information known in the preset edge node under the corresponding circulation mode ventilation mode and air quality parameter information collected by the fresh air sensor; Step S302, based on the basic data in the fresh air database, the machine learning prediction is performed, the fresh air database is expanded and preprocessed, and after the standardized data is formed, the training set and the validation set are divided to perform database training. The training is based on the characteristic variables of the preset cycle mode, and after the feature processing, the deep machine learning is performed to learn the relationship between the characteristic variables or category data of each cycle mode, and the linear regression prediction or multivariate linear regression prediction of the cycle mode is performed; Step S303, analyzing the circulation mode adjustment strategy of the fresh air system through cluster analysis, and according to the prediction results of linear regression prediction or multivariate linear regression prediction, inputting the prediction results into the circulation mode cases of the known specific edge nodes of the fresh air system as artificial neural networks, obtaining the associated circulation mode adjustment strategy map between the air quality parameter information collected by the fresh air sensors at all positions in the trained specific edge nodes and the prediction results, outputting the corresponding circulation mode adjustment strategy information according to the associated circulation mode adjustment strategy map relationship, that is, using the circulation mode adjustment strategy information as the output layer of the artificial neural network, and obtaining the circulation mode adjustment information of the fresh air system in the specific edge node and then outputting it; Step S304: the fresh air system responds to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information to complete the dynamic adjustment strategy.

2. The multi-source sensor data analysis method of the IoT fresh air system according to claim 1, characterized in that: After edge computing and analysis of the fusion processing information of the current fresh air system, correlation analysis is performed through the cloud computing platform. The correlation analysis also includes obtaining the air quality related information in the weather forecast and performing correlation analysis with the second acquired data of the outdoor air quality parameter information, generating an error value to judge the accuracy of the second acquired data, and automatically adjusting the control parameter information of the fresh air system according to the air quality related information in the weather forecast.

3. The multi-source sensor data analysis method of the IoT fresh air system according to claim 1, characterized in that: The third acquired data is transmitted to the edge wireless gateway for early warning. Specifically, the edge wireless gateway is set with an early warning threshold. The edge server compares the abnormal value of the collected data signal with the early warning threshold set by the edge wireless gateway. If it is higher than the threshold or lower than the threshold, an online early warning is issued.

4. The multi-source sensor data analysis method of the IoT fresh air system according to claim 1, characterized in that: The air quality parameter information includes: PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration; and take the median or mean value of the data of PM2.5, PM10, wind speed, wind force, temperature, humidity, noise, air quality and CO2 concentration; The data signal transmission of the air quality parameter information obtained by the fresh air sensor adopts the Modbus protocol or the MQTT protocol.

5. The multi-source sensor data analysis method of the IoT fresh air system according to claim 1, characterized in that: The dynamic adjustment of the circulation mode is as follows: Step 101, start detecting air parameters, obtain indoor and outdoor air quality parameter information through fresh air sensors, and synchronously obtain air quality related information in weather forecasts based on specific edge nodes; Step 102, determine whether the indoor air quality meets the standard. If not, perform fusion processing of indoor and outdoor air quality parameter information based on the fresh air system, start the internal circulation mode according to the fusion processing information of the current fresh air system, and automatically adjust the control parameter information to purify the air; if yes, proceed to the next step to determine whether the outdoor air quality meets the standard; Step 103, determine whether the outdoor air quality meets the standard, and respond to the correlation analysis data of the air quality related information in the weather forecast. Otherwise, turn off the internal circulation mode of the fresh air system and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information. If yes, turn on the external circulation mode according to the fusion processing information of the current fresh air system and automatically adjust the control parameter information for ventilation processing and proceed to the next step of continuously monitoring the indoor and outdoor air quality parameter information; Step 104, continuously monitor indoor and outdoor air quality parameter information, determine whether the indoor and outdoor air quality meets the standard, and if so, maintain the current circulation mode and parameter information; otherwise, adjust the circulation mode based on step 102 or step 103 and automatically adjust the matching control parameter information according to the circulation mode adjustment information of the specific edge node and the current fresh air system fusion processing information.

6. The multi-source sensor data analysis method of the IoT fresh air system according to claim 5, characterized in that: The control parameter information includes: the fresh air volume of the fresh air system, the maximum and minimum fresh air volumes, the exhaust volume, the air flow cleanliness, the ventilation times, the wind force level, the temperature, the humidity, the CO2 concentration and the heat recovery amount.

7. A sensing device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the multi-source sensor data analysis method for an IoT fresh air system as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps in the multi-source sensor data analysis method of the IoT fresh air system as described in any one of claims 1-6 are implemented.

Images