CN113342794B - Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering - Google Patents
Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering Download PDFInfo
- Publication number
- CN113342794B CN113342794B CN202110692941.6A CN202110692941A CN113342794B CN 113342794 B CN113342794 B CN 113342794B CN 202110692941 A CN202110692941 A CN 202110692941A CN 113342794 B CN113342794 B CN 113342794B
- Authority
- CN
- China
- Prior art keywords
- filtering
- module
- node
- result
- dhpff
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 202
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 239000000809 air pollutant Substances 0.000 title claims abstract description 26
- 231100001243 air pollutant Toxicity 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012806 monitoring device Methods 0.000 title claims abstract description 8
- 230000001149 cognitive effect Effects 0.000 claims abstract description 60
- 238000004140 cleaning Methods 0.000 claims abstract description 26
- 241000854291 Dianthus carthusianorum Species 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 239000000356 contaminant Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000019771 cognition Effects 0.000 claims 6
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000003915 air pollution Methods 0.000 description 7
- 230000036541 health Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 239000010419 fine particle Substances 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Food Science & Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Combustion & Propulsion (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Selective Calling Equipment (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an air pollutant concentration monitoring device, an air pollutant concentration monitoring system and an air pollutant concentration monitoring method based on combined filtering. The device comprises a plurality of node devices, wherein each node device comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter base, a cognitive management module and a transceiving module; the sensor group is connected with a data cleaning module, the data cleaning module is respectively connected with a DHPFF filtering module and a Kalman filtering module, the DHPFF filtering module is respectively connected with the Kalman filtering module and a parameter library, the Kalman filtering module is respectively connected with a cognitive management module and the parameter library, and the cognitive management module is connected with a receiving and sending module. The invention is used for solving the problem that the measurement of a single sensor is inaccurate due to factors such as air humidity, air pressure and wind speed.
Description
Technical Field
The invention belongs to the field of air pollution monitoring; in particular to an air pollutant concentration monitoring device, a monitoring system and a monitoring method based on combined filtering.
Background
Along with the rapid development of economy in China, the living standard of people is greatly improved, but the problems of air pollution and the like are also brought, more and more air pollution is caused by factory waste gas, automobile tail gas and coal heating, and the air pollution not only influences the production and the life of people, but also greatly influences the body health of people. In recent years, the air quality of China is far lower than the recommended standard of the World Health Organization (WHO), and fine particulate pollution becomes an extreme environmental and social problem which has important influence on human health and national economy. In the face of severe fine particle pollution problems, governments also actively adopt various comprehensive treatment measures, and the monitoring of air pollution concentration is of great importance in the air pollution treatment process. The fine particle pollutants in the monitored air are easily influenced by factors such as air pressure, air flow, illumination, temperature and humidity, environmental characteristics and the like, so that the data measured by the sensor is inaccurate. How to accurately monitor the concentration of air pollutants is a significant issue.
Most of the current researches directly use the air pollution concentration measured by a single sensor as a monitoring result, so that the obtained result is not accurate enough; the measurement accuracy of the air pollutant concentration may be improved by simple processing, for example, filtering by using particle filtering, kalman filtering, KZ filtering, impulse response filtering, etc., but when the factors such as wind speed and air pressure change dramatically in a short time, the pollutant concentration measured by the sensor has a large error.
Disclosure of Invention
The invention discloses an air pollutant concentration monitoring device, an air pollutant concentration monitoring system and an air pollutant concentration monitoring method based on combined filtering, which are used for solving the problem that a single sensor is inaccurate in measurement due to factors such as air humidity, air pressure and air speed.
The invention is realized by the following technical scheme:
an air pollutant concentration monitoring device based on combined filtering comprises a plurality of node devices, wherein each node device comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter library, a cognitive management module and a transceiver module;
the sensor group is connected with a data cleaning module, the data cleaning module is respectively connected with a DHPFF filtering module and a Kalman filtering module, the DHPFF filtering module is respectively connected with the Kalman filtering module and a parameter library, the Kalman filtering module is respectively connected with a cognitive management module and the parameter library, and the cognitive management module is connected with a receiving and sending module.
An air pollutant concentration monitoring system based on combined filtering comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter base, a cognitive management module and a receiving and transmitting module;
the sensor group transmits signals to the data cleaning module, the data cleaning module transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively, the Kalman filtering module and the DHPFF filtering module transmit the signals to the cognitive management module, the cognitive management module transmits the signals to the transceiving module and the parameter library respectively, and the parameter library transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively.
A monitoring method of an air pollutant concentration monitoring system based on distributed Kalman filtering specifically comprises the following steps:
step 1: obtaining time sequence filtering among a plurality of time slots by utilizing an air pollutant concentration monitoring system;
step 2: obtaining spatial filtering performed by a plurality of sensors over a single time slot using an air contaminant concentration monitoring system;
and step 3: and updating the time sequence filtering parameters according to the filtering result by utilizing time sequence filtering among a plurality of time slots in the step 1 and spatial filtering on a single time slot in the step 2.
Further, the obtaining of the timing filtering among the multiple time slots in step 1 specifically includes the following steps:
step 1.1: at an arbitrary time slot t k To any Node i The direct observation value of the air quality detection result is a state matrix A ki ；
Step 1.2: for the Node in step 1.1 i The corrected observation values of the air quality detection results at all historical moments and the direct observation value of the air quality detection result at the current moment form a vector P aki ＝(B 1i ,B 2i ,…,B (k-1)i ,A ki ) Opposite vector P aki DHPFF filtering is carried out to obtain the current time slot t k The direct observation value of the air quality detection result is B ki ；
Step 1.3: for all NODEs in the set NODE 1 ,Node 2 ,…,Node n ) DHPFF filtering is carried out to obtain the current time slot t k Corrected observation value set { B) of air quality detection result k1 ,B k2 ,…,B kn }；
Step 1.4: if a certain NODE NODE z In the inactive state, B kz Is empty.
Further, the obtaining of the spatial filtering on the single timeslot in step 2 specifically includes the following steps:
step 2.1: at any time slot t k According to the node numbering sequence, all nodes in an active state form a directed acyclic graph;
step 2.2: at cluster head nodes, according to the direction of the directed acyclic graph in the step 2.1, the state matrix B of the air quality detection results of the nodes in all the graphs is used ki Form a sequence, i.e. S k ＝(B k1 ,B k2 ,…,B ks )；
Step 2.3: for the sequence S of step 2.2 k Performing Kalman filtering, and recording the filtering result as C k ；
Step 2.4: filtering result C of step 2.2 k For the current time slot t k The final result of the air quality test of (1).
Further, the step 3 of updating the time sequence filtering parameter according to the filtering result is specifically that the filtering result C is k And the cognitive management module of each node makes a decision to update the time sequence filtering parameters of the local node, namely the parameters of the DHPFF filtering module.
The invention has the beneficial effects that:
the invention processes the monitoring data of the air pollutant concentration by integrating a plurality of sensors, filtering technology and cognitive calculation, so that the monitoring is more accurate.
The invention has better robustness when the air humidity, the air pressure and the wind speed change violently.
The distributed structure is adopted in the invention, so that the conditions of single sensor failure, restart and fault can be dealt with.
Drawings
FIG. 1 is a system block diagram of the present invention.
FIG. 2 is a sensor profile in the context of an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The monitoring system consists of a group of NODEs, and is marked as NODE 1 ,Node 2 ,…,Node n The nodes comprise 1 cluster head node, and the rest are common nodes; the nodes are according to the set time slot (t) 0 ,t 1 ,…,t m ) Air quality is monitored.
For any Node therein i The system comprises 8 modules, namely a sensor group, a data cleaning module, a DHPFF (Distributed hybrid/Fine impulse response Filter) filtering module, a Kalman filtering module, a parameter base, a cognitive management module, a memory and a transceiver module, wherein the relationship among the modules follows the following rules:
(1) the sensor group comprises a set of sensors for collecting different parameters of the air, such as PM10, PM2.5, SO 2 And the like. And the sensing result of the sensor group is sent to the data cleaning module.
(2) The data cleaning module receives data from the sensor group and performs data cleaning, such as deleting empty data packets, checking and error data packets, and the like. And the output result of the data cleaning module is sent to the DHPFF filtering module and the Kalman filtering module.
(3) The DHPFF filtering module executes DHPFF filtering of the existing method according to historical records before the current moment and input air quality monitoring data at the current moment so as to avoid severe fluctuation of air quality in different time slots. If the current node is a cluster head, the output result of the DHPFF filtering module is sent to the Kalman filtering module, and meanwhile, the output result is recorded in the storage module; if not, the output result D of the DHPFF filtering module is used i And sending the information to a cognitive management module and recording the information in a storage module.
(4) The Kalman filtering module is started only when the current node is a cluster head, and is dormant when the current node is a common node. The Kalman filtering module firstly receives data directly delivered by the DHPFF filtering module or data indirectly delivered by the transceiving module. And secondly, receiving the directed acyclic graphs of all the nodes at the current moment, which are sent by the parameter base, by the Kalman filtering module. And thirdly, according to the sequence of the directed acyclic graph, taking the air quality monitoring results of all the nodes at the current moment as input to execute Kalman filtering. And finally, sending the Kalman filtering result K to a cognitive management module.
(5) The parameter library contains 4 functions. Firstly, parameters of DHPFF filtering are set by a user according to historical records at the starting time, and in the system operation process, a parameter base is controlled by a cognitive module to be updated according to the accumulated historical records at the initial time of each time slot. And secondly, setting parameters of a Kalman filtering module of the cluster head node, wherein the parameters are set by a user according to historical records at the starting time. And thirdly, for the cluster head nodes, at the initial moment of each time slot, searching all node information in an active state at the current moment according to the interaction between the common nodes and the cluster head nodes, and forming a directed acyclic graph by all the nodes in the active state according to the numbers.
(6) And the cognitive management module is responsible for receiving the filtering result of the Kalman filtering module and the result of the DHPFF filtering module, performing cognitive learning and finally outputting a cognitive instruction. Firstly, when the current node is a cluster head node, directly receiving a filtering result K of a Kalman filtering module; otherwise, the cognitive management forwards the filtering result K to all other nodes through the transceiving module. Secondly, the cognitive management module receives the filtering result K and the result of the DHPFF filtering module of the node, cognitive learning is carried out at the moment, and the output result is 0 or 1; and when the result is 1, sending an instruction to the parameter library to shield the node by one time slot in the next time slot, namely setting the node to be in an inactive state in the next time slot. In addition, at the initial moment of each time slot, according to the historical record of the air quality result recorded in the storage module, a cognitive instruction is output to update the parameters of the DHPFF filtering in the parameter library.
The cognitive learning process of the cognitive management module further comprises the following characteristics: the cognitive management module comprises an analysis submodule, a decision submodule, an execution submodule and a knowledge base. The analysis submodule takes the filtering result of the Kalman filtering module and the result of the DHPFF filtering module as input, an input matrix is obtained after normalization, and the input matrix is input to the decision submodule; and the decision sub-module performs supervised learning classification under the participation of the knowledge base, and the classification result is 0 or 1. The supervised learning method comprises a convolution neural network, a graph neural network and the like. And the execution sub-module sends an instruction to the parameter library according to the classification result.
(7) The transceiver module is mainly responsible for receiving and transmitting data. On one hand, the result of the DHPFF filtering module of the common node is sent to the cluster head node; and on the other hand, the filtering result of the Kalman filtering module of the cluster head node is sent to all other nodes.
An air pollutant concentration monitoring device based on combined filtering comprises a plurality of node devices, wherein each node device comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter library, a cognitive management module and a transceiver module;
the sensor group is connected with a data cleaning module, the data cleaning module is respectively connected with a DHPFF filtering module and a Kalman filtering module, the DHPFF filtering module is respectively connected with the Kalman filtering module and a parameter library, the Kalman filtering module is respectively connected with a cognitive management module and the parameter library, and the cognitive management module is connected with a receiving and sending module.
An air pollutant concentration monitoring system based on combined filtering comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter base, a cognitive management module and a receiving and transmitting module;
the sensor group transmits signals to the data cleaning module, the data cleaning module transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively, the Kalman filtering module and the DHPFF filtering module transmit the signals to the cognitive management module, the cognitive management module transmits the signals to the transceiving module and the parameter library respectively, and the parameter library transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively.
An air pollutant concentration monitoring method based on distributed Kalman filtering specifically comprises the following steps:
step 1: obtaining time sequence filtering among a plurality of time slots by utilizing an air pollutant concentration monitoring system;
step 2: obtaining spatial filtering performed by a plurality of sensors over a single time slot using an air contaminant concentration monitoring system;
and step 3: and updating the time sequence filtering parameters according to the filtering result by utilizing time sequence filtering among a plurality of time slots in the step 1 and spatial filtering on a single time slot in the step 2.
Further, the obtaining of the timing filtering among the multiple time slots in step 1 specifically includes the following steps:
step 1.1: at an arbitrary time slot t k To any Node i The direct observation value of the air quality detection result is a state matrix A ki ；
Step 1.2: for the Node in step 1.1 i The corrected observation values of the air quality detection results at all historical moments and the direct observation value of the air quality detection result at the current moment form a vector P aki ＝(B 1i ,B 2i ,…,B (k-1)i ,A ki ) Opposite vector P aki DHPFF filtering is carried out to obtain the current time slot t k The direct observation value of the air quality detection result is B ki ；
Step 1.3: for all NODEs in the set NODE 1 ,Node 2 ,…,Node n ) DHPFF filtering is carried out to obtain the current time slot t k Corrected observation value set { B) of air quality detection result k1 ,B k2 ,…,B kn }；
Step 1.4: if a certain NODE NODE z In the inactive state, B kz Is empty.
Further, the DHPFF filtering in step 1.2 is sent to a cognitive management module, and a working process of the cognitive management module specifically includes the following steps:
step 1.2.1: if the current node is a cluster head node, performing the step 1.2.2, and if the current node is a common node, performing the step 1.2.3;
step 1.2.2: directly receiving a filtering result K of the Kalman filtering module, and entering the step 1.2.3 or skipping to the step 1.2.4;
step 1.2.3: the filtering result K is forwarded to all other nodes through a receiving and sending module;
step 1.2.4: the cognitive management module receives the filtering result K and the result of the DHPFF filtering module of the node, at the moment, cognitive learning is carried out, and the output result is 0 or 1; when the result is 1, performing step 1.2.5; when the result is 0, performing step 1.2.6;
step 1.2.5: sending an instruction to a parameter library to shield the node by one time slot in the next time slot, namely setting the node to be in an inactive state in the next time slot;
step 1.2.6: and outputting a cognitive instruction to update the parameters of the DHPFF filtering in the parameter library at the initial moment of each time slot according to the historical record of the air quality result recorded in the storage module.
Further, the obtaining of the spatial filtering on the single timeslot in step 2 specifically includes the following steps:
step 2.1: at any time slot t k According to the node numbering sequence, all nodes in an active state form a directed acyclic graph;
step 2.2: at cluster head nodes, according to the direction of the directed acyclic graph in the step 2.1, the state matrix B of the air quality detection results of the nodes in all the graphs is used ki Form a sequence, i.e. S k ＝(B k1 ,B k2 ,…,B ks )；
Step 2.3: for the sequence S of step 2.2 k Performing Kalman filtering, and recording the filtering result as C k ；
Step 2.4: filtering result C of step 2.2 k For the current time slot t k The final result of the air quality test of (1).
Further, the step 3 of updating the time sequence filtering parameter according to the filtering result is specifically that the filtering result C is k The decision is made by the cognitive management module of each nodeAnd whether to update the timing filtering parameters of the local node, namely the parameters of the DHPFF filtering module.
Claims (5)
1. The air pollutant concentration monitoring device based on combined filtering is characterized by comprising a plurality of node devices, wherein each node device comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter base, a cognitive management module and a transceiver module;
the sensor group is connected with a data cleaning module, the data cleaning module is respectively connected with a DHPFF filtering module and a Kalman filtering module, the DHPFF filtering module is respectively connected with a Kalman filtering module and a parameter library, the Kalman filtering module is respectively connected with a cognitive management module and the parameter library, and the cognitive management module is connected with a receiving and transmitting module;
the DHPFF filtering module executes DHPFF filtering of the existing method according to historical records before the current moment and input air quality monitoring data at the current moment so as to avoid severe fluctuation of air quality in different time slots; if the current node is a cluster head, the output result of the DHPFF filtering module is sent to the Kalman filtering module, and meanwhile, the output result is recorded in the storage module; if not, the output result D of the DHPFF filtering module is used i Sending the information to a cognitive management module, and recording in a storage module;
the cognition management module is responsible for receiving the filtering result of the Kalman filtering module and the result of the DHPFF filtering module, performing cognition learning and finally outputting a cognition instruction; firstly, when the current node is a cluster head node, directly receiving a filtering result K of a Kalman filtering module; otherwise, the cognitive management forwards the filtering result K to all other nodes through the transceiving module; secondly, the cognitive management module receives the filtering result K and the result of the DHPFF filtering module of the node, cognitive learning is carried out at the moment, and the output result is 0 or 1; when the result is 1, sending an instruction to the parameter library to shield the node by one time slot in the next time slot, namely setting the node to be in an inactive state in the next time slot; in addition, at the initial moment of each time slot, according to the historical record of the air quality result recorded in the storage module, a cognitive instruction is output to update the parameters of the DHPFF filtering in the parameter library.
2. The air pollutant concentration monitoring system based on joint filtering is characterized by consisting of a group of NODEs, and is marked as NODE 1 ,Node 2 ,…,Node n A group of nodes comprises 1 cluster head node, and the rest are common nodes; a group of nodes according to the set time slot (t) 0 ,t 1 ,…,t m ) The monitoring air quality comprises a sensor group, a data cleaning module, a DHPFF filtering module, a Kalman filtering module, a parameter base, a cognitive management module and a receiving and transmitting module;
the sensor group transmits signals to the data cleaning module, the data cleaning module transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively, the Kalman filtering module and the DHPFF filtering module both transmit the signals to the cognitive management module, the cognitive management module transmits the signals to the transceiver module and the parameter library, and the parameter library transmits the signals to the DHPFF filtering module and the Kalman filtering module respectively;
the DHPFF filtering module executes DHPFF filtering of the existing method according to historical records before the current moment and input air quality monitoring data at the current moment so as to avoid severe fluctuation of air quality in different time slots; if the current node is a cluster head, the output result of the DHPFF filtering module is sent to the Kalman filtering module, and meanwhile, the output result is recorded in the storage module; if not, the output result D of the DHPFF filtering module is used i Sending the information to a cognitive management module, and recording in a storage module;
the cognition management module is responsible for receiving the filtering result of the Kalman filtering module and the result of the DHPFF filtering module, performing cognition learning and finally outputting a cognition instruction; firstly, when the current node is a cluster head node, directly receiving a filtering result K of a Kalman filtering module; otherwise, the cognitive management forwards the filtering result K to all other nodes through the transceiving module; secondly, the cognitive management module receives the filtering result K and the result of the DHPFF filtering module of the node, cognitive learning is carried out at the moment, and the output result is 0 or 1; when the result is 1, sending an instruction to the parameter library to shield the node by one time slot in the next time slot, namely setting the node to be in an inactive state in the next time slot; in addition, at the initial moment of each time slot, according to the historical record of the air quality result recorded in the storage module, a cognitive instruction is output to update the parameters of the DHPFF filtering in the parameter library.
3. The monitoring method of the air pollutant concentration monitoring system based on the combined filtering as claimed in claim 2, is characterized in that the monitoring method specifically comprises the following steps:
step 1: obtaining time sequence filtering among a plurality of time slots by utilizing an air pollutant concentration monitoring system;
step 2: obtaining spatial filtering performed by a plurality of sensors over a single time slot using an air contaminant concentration monitoring system;
and 3, step 3: updating a time sequence filtering parameter according to a filtering result by utilizing time sequence filtering among a plurality of time slots in the step 1 and spatial filtering on a single time slot in the step 2;
the obtaining of the time sequence filtering among the multiple time slots in the step 1 specifically includes the following steps:
step 1.1: at an arbitrary time slot t k To any Node i The direct observation value of the air quality detection result is a state matrix A ki ；
Step 1.2: for the Node in step 1.1 i The corrected observation values of the air quality detection results at all historical moments and the direct observation value of the air quality detection result at the current moment form a vector P aki ＝(B 1i ,B 2i ,…,B (k-1)i ,A ki ) Opposite vector P aki DHPFF filtering is carried out to obtain the current time slot t k The direct observation value of the air quality detection result is B ki ；
Step 1.3: for all NODEs in the set NODE 1 ,Node 2 ,…,Node n ) DHPFF filtering is carried out to obtain the current time slot t k Corrected observation value set { B) of air quality detection result k1 ,B k2 ,…,B kn Transmitting the corrected observation value set to a cognitive management module;
step 1.4: if a certain NODE NODE z In the inactive state, B kz Is empty;
the DHPFF filtering in step 1.2 is sent to a cognitive management module, and a working process of the cognitive management module specifically includes the following steps:
step 1.2.1: if the current node is a cluster head node, performing the step 1.2.2, and if the current node is a common node, performing the step 1.2.3;
step 1.2.2: directly receiving a filtering result K of the Kalman filtering module, and entering the step 1.2.3 or skipping to the step 1.2.4;
step 1.2.3: the filtering result K is forwarded to all other nodes through a receiving and sending module;
step 1.2.4: the cognitive management module receives the filtering result K and the result of the DHPFF filtering module of the node, at the moment, cognitive learning is carried out, and the output result is 0 or 1; when the result is 1, performing step 1.2.5; when the result is 0, performing step 1.2.6;
step 1.2.5: sending an instruction to a parameter library to shield the node by one time slot in the next time slot, namely setting the node to be in an inactive state in the next time slot;
step 1.2.6: and outputting a cognitive instruction to update the parameters of the DHPFF filtering in the parameter library at the initial moment of each time slot according to the historical record of the air quality result recorded in the storage module.
4. The monitoring method of the air pollutant concentration monitoring system based on the joint filtering as claimed in claim 3, wherein the step 2 of obtaining the spatial filtering on a single time slot specifically comprises the following steps:
step 2.1: at any time slot t k According to the node numbering sequence, all nodes in an active state form a directed acyclic graph;
step 2.2: at cluster head nodes, according to the direction of the directed acyclic graph in the step 2.1, the state matrix B of the air quality detection results of the nodes in all the graphs is used ki Form a sequence, i.e. S k ＝(B k1 ,B k2 ,…,B ks )；
Step 2.3: for the sequence S of step 2.2 k Performing Kalman filtering, and recording the filtering result as C k ；
Step 2.4: filtering result C of step 2.2 k For the current time slot t k The final result of the air quality test of (1).
5. The monitoring method of the air pollutant concentration monitoring system based on the combined filtering as claimed in claim 3, wherein the updating of the time sequence filtering parameter according to the filtering result in the step 3 is specifically that the filtering result C is k And the cognitive management module of each node makes a decision to update the time sequence filtering parameters of the local node, namely the parameters of the DHPFF filtering module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110692941.6A CN113342794B (en) | 2021-06-22 | 2021-06-22 | Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110692941.6A CN113342794B (en) | 2021-06-22 | 2021-06-22 | Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113342794A CN113342794A (en) | 2021-09-03 |
| CN113342794B true CN113342794B (en) | 2022-08-02 |
Family
ID=77478704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110692941.6A Expired - Fee Related CN113342794B (en) | 2021-06-22 | 2021-06-22 | Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113342794B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880542A (en) * | 2015-05-29 | 2015-09-02 | 国家海洋局北海海洋技术保障中心 | Real-time water pollution condition and pollutant concentration detecting device and method |
| CN106650159A (en) * | 2016-12-31 | 2017-05-10 | 中国科学技术大学 | Real-time monitoring system of temporal and spatial distribution of air pollutant concentration on urban road network |
| KR20210060909A (en) * | 2019-11-19 | 2021-05-27 | 경북대학교 산학협력단 | Multi-layered filter for separating blood components and disease diagnosis kit using the same |
-
2021
- 2021-06-22 CN CN202110692941.6A patent/CN113342794B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104880542A (en) * | 2015-05-29 | 2015-09-02 | 国家海洋局北海海洋技术保障中心 | Real-time water pollution condition and pollutant concentration detecting device and method |
| CN106650159A (en) * | 2016-12-31 | 2017-05-10 | 中国科学技术大学 | Real-time monitoring system of temporal and spatial distribution of air pollutant concentration on urban road network |
| KR20210060909A (en) * | 2019-11-19 | 2021-05-27 | 경북대학교 산학협력단 | Multi-layered filter for separating blood components and disease diagnosis kit using the same |
Non-Patent Citations (2)
| Title |
|---|
| Distributed Hybrid Particle/FIR Filtering for Mitigating NLOS Effects in TOA-Based Localization Using Wireless Sensor Networks;Jung Min Pak等;《IEEE Transactions on Industrial Electronics》;20161231;全文 * |
| 大气波导的研究现状与思考;张玉生等;《电波科学学报》;20201215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113342794A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Belavadi et al. | Air quality forecasting using LSTM RNN and wireless sensor networks | |
| CN106777864A (en) | A kind of calibration method of inexpensive PM2.5 monitoring nodes | |
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| CN205647550U (en) | Monitoring system for intelligence laboratory | |
| CN104994535B (en) | Sensor data stream method for detecting abnormality based on Multidimensional Data Model | |
| CN112986492B (en) | Method and device for establishing gas concentration prediction model | |
| CN107121463A (en) | A kind of multi-channel electronic nose detecting system and its measuring method | |
| CN116519895B (en) | Water quality on-line monitoring analysis management system based on big data platform | |
| CN110631640A (en) | Intelligent monitoring system and method for storage tobacco leaf mildew state based on Internet of things | |
| CN106297252A (en) | A kind of industrial park air pollution surveillance system | |
| CN112075940A (en) | Tremor detection system based on bidirectional long-time and short-time memory neural network | |
| Aygün et al. | Sensor fusion for IoT-based intelligent agriculture system | |
| Lanjewar et al. | Air pollution monitoring & tracking system using mobile sensors and analysis of data using data mining | |
| Guanochanga et al. | Towards a real-time air pollution monitoring systems implemented using wireless sensor networks: preliminary results | |
| CN109407629B (en) | Pathogen online monitoring system and method | |
| CN106526077A (en) | Air quality detection system and method based on information fusion technology | |
| CN107607682A (en) | A kind of vehicle mounted tail gas monitoring terminal of dipper system | |
| CN112702408A (en) | Internet of things system and method based on multi-sensing function | |
| Zhang et al. | Cooperative sensor anomaly detection using global information | |
| CN114966422A (en) | Real-time monitoring and early warning system based on power battery parameters | |
| CN113342794B (en) | Air pollutant concentration monitoring device, monitoring system and monitoring method based on combined filtering | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN106195247B (en) | A kind of control system of speed variator based on big data management mode | |
| Mathur et al. | High resolution air pollution mapping using wireless sensor nodes | |
| zu Westerhausen et al. | Reliability analysis for sensor networks and their data acquisition: A systematic literature review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220802 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |