CN118339457A - Analysis system, server, analysis method, and program - Google Patents
Analysis system, server, analysis method, and program Download PDFInfo
- Publication number
- CN118339457A CN118339457A CN202280079402.8A CN202280079402A CN118339457A CN 118339457 A CN118339457 A CN 118339457A CN 202280079402 A CN202280079402 A CN 202280079402A CN 118339457 A CN118339457 A CN 118339457A
- Authority
- CN
- China
- Prior art keywords
- data
- associated data
- particulate matter
- correlation
- feature extraction
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 193
- 239000013618 particulate matter Substances 0.000 claims abstract description 204
- 238000000605 extraction Methods 0.000 claims abstract description 162
- 239000000284 extract Substances 0.000 claims abstract description 68
- 238000009826 distribution Methods 0.000 claims description 35
- 239000002245 particle Substances 0.000 claims description 31
- 230000036962 time dependent Effects 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 21
- 239000008187 granular material Substances 0.000 claims description 14
- 238000003860 storage Methods 0.000 description 38
- 238000010586 diagram Methods 0.000 description 28
- 230000006870 function Effects 0.000 description 26
- 239000007789 gas Substances 0.000 description 26
- 230000005856 abnormality Effects 0.000 description 22
- 238000013480 data collection Methods 0.000 description 16
- 230000005250 beta ray Effects 0.000 description 15
- 230000009471 action Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000001914 filtration Methods 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 230000002123 temporal effect Effects 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 229910052815 sulfur oxide Inorganic materials 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004804 winding Methods 0.000 description 4
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 description 3
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 description 3
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 3
- YXFVVABEGXRONW-UHFFFAOYSA-N Toluene Chemical compound CC1=CC=CC=C1 YXFVVABEGXRONW-UHFFFAOYSA-N 0.000 description 3
- 229910002091 carbon monoxide Inorganic materials 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 239000010703 silicon Substances 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 239000012855 volatile organic compound Substances 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 2
- KDLHZDBZIXYQEI-UHFFFAOYSA-N Palladium Chemical compound [Pd] KDLHZDBZIXYQEI-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000011575 calcium Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000011651 chromium Substances 0.000 description 2
- 238000002485 combustion reaction Methods 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000000921 elemental analysis Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000011669 selenium Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- XTQHKBHJIVJGKJ-UHFFFAOYSA-N sulfur monoxide Chemical class S=O XTQHKBHJIVJGKJ-UHFFFAOYSA-N 0.000 description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- OKTJSMMVPCPJKN-NJFSPNSNSA-N Carbon-14 Chemical compound [14C] OKTJSMMVPCPJKN-NJFSPNSNSA-N 0.000 description 1
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 238000002083 X-ray spectrum Methods 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052785 arsenic Inorganic materials 0.000 description 1
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 229910052804 chromium Inorganic materials 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010894 electron beam technology Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000004745 nonwoven fabric Substances 0.000 description 1
- 229910052763 palladium Inorganic materials 0.000 description 1
- -1 polyethylene Polymers 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 239000002861 polymer material Substances 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 206010037844 rash Diseases 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 229910052711 selenium Inorganic materials 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 229910052712 strontium Inorganic materials 0.000 description 1
- CIOAGBVUUVVLOB-UHFFFAOYSA-N strontium atom Chemical compound [Sr] CIOAGBVUUVVLOB-UHFFFAOYSA-N 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- JBQYATWDVHIOAR-UHFFFAOYSA-N tellanylidenegermanium Chemical compound [Te]=[Ge] JBQYATWDVHIOAR-UHFFFAOYSA-N 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- LEONUFNNVUYDNQ-UHFFFAOYSA-N vanadium atom Chemical compound [V] LEONUFNNVUYDNQ-UHFFFAOYSA-N 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The analysis system of the present invention efficiently and accurately extracts features contained in data related to particulate matter. The analysis system (100) is provided with a data acquisition unit (1), a feature extraction unit (35), and an output unit (37). The data acquisition unit (1) acquires association data (RD) relating to the particulate matter. A feature extraction unit (35) extracts features contained in the associated data (RD) by performing a predetermined feature extraction process that takes the associated data (RD) as an input. An output unit (37) outputs information associated with the features extracted by the feature extraction unit (35).
Description
Technical Field
The present invention relates to an analysis system for performing analysis on particulate matter, a server for performing analysis on particulate matter, an analysis method for particulate matter, and a program for causing a computer to execute the analysis method.
Background
In recent years, various particulate matters (for example, PM 2.5) have become a serious environmental problem. Therefore, a system is known in which data concerning a particulate matter such as the concentration of the particulate matter contained in a predetermined region and information concerning an element contained in the particulate matter (for example, the element contained in the particulate matter and the content of the element) are acquired, and analysis concerning the particulate matter is performed based on the acquired data (for example, refer to patent document 1).
Prior art literature
Patent document 1: international publication No. 2018/117146
In order to accurately perform analysis on the particulate matter, it is necessary to extract features contained in the data on the particulate matter, but for this purpose, it is necessary to analyze a large amount of data obtained. In the conventional system, since a user analyzes a large amount of data and extracts features, it is difficult to efficiently and accurately extract features contained in data related to particulate matter.
Disclosure of Invention
The present invention aims to effectively and accurately extract characteristics contained in data related to granular substances.
Hereinafter, a plurality of embodiments will be described as means for solving the problems. These modes can be arbitrarily combined as needed.
An analysis system according to an aspect of the present invention is a system for performing analysis on particulate matter. The analysis system includes a data acquisition unit, a feature extraction unit, and an output unit. The data acquisition unit acquires associated data relating to the particulate matter. The feature extraction unit extracts features included in the associated data by performing predetermined feature extraction processing that takes the associated data as input. The output section outputs information associated with the feature extracted by the feature extraction section.
In the analysis system, the feature extraction unit automatically performs a predetermined feature extraction process for inputting the associated data associated with the particulate matter obtained by the data acquisition unit, and automatically extracts the features included in the associated data. In this way, by automatically extracting the features included in the associated data by the feature extraction unit, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by the output unit outputting information related to the feature extracted by the feature extraction unit, it is possible to indicate to the user what feature is extracted from the related data.
In the above analysis system, the feature extraction unit may extract the associated data in which the instantaneous value exceeds the first threshold value. In this case, the output unit may display a list of information associated with the associated data whose instantaneous value exceeds the first threshold value. In this way, it is possible to automatically extract the associated data including the abnormality when the instantaneous value exceeds the first threshold value, and to present to the user which associated data has the abnormality.
In the above analysis system, the feature extraction unit may extract the related data in which the average value or the median value exceeds the second threshold value. In this case, the output unit may display the information associated with the associated data in which the average value or the median value exceeds the second threshold in a list. In this way, the related data including the abnormality whose average value or median value exceeds the second threshold can be automatically extracted, and the user can be presented with which related data the abnormality has occurred.
In the analysis system, the output unit may graphically display associated data corresponding to the specified information among the information displayed in the list. This allows visual confirmation of the fluctuation of the related data including the abnormality.
In the above analysis system, the feature extraction unit may calculate the correlation of the plurality of pieces of correlation data, and extract information associated with the pieces of correlation data whose calculated correlation is equal to or greater than a third threshold. Thus, the user does not need to calculate and analyze the correlation for each combination of the plurality of pieces of correlation data, and thus can efficiently and accurately extract correlation data having a large correlation.
In the analysis system, the output unit may display a distribution map of a plurality of pieces of associated data having a correlation equal to or greater than a third threshold. This allows the magnitude of the correlation of the extracted correlation data to be visually confirmed.
In the analysis system, the output unit may display a plurality of distribution charts of a plurality of pieces of correlation data, and may highlight distribution charts of a plurality of pieces of correlation data having a correlation equal to or greater than a third threshold. This makes it possible to visually identify which associated data has a high correlation among all the associated data.
In the analysis system, the associated data may be time-varying data. In this case, the feature extraction unit may calculate correlations of a plurality of pieces of associated data in a predetermined time interval. Thus, correlation of a plurality of pieces of correlation data in a specific time zone can be calculated. Information about a phenomenon occurring in a specific time zone is obtained from the correlation of the correlation data in the time zone.
In the analysis system, the predetermined time period may be variable. This makes it possible to flexibly set a time zone for calculating the correlation of a plurality of pieces of correlation data.
In the above analysis system, the feature extraction unit may calculate correlations of a plurality of pieces of associated data for each of a plurality of cells included in a predetermined time zone. Thus, information on the phenomenon occurring in the specific period is obtained in more detail from the correlation of the associated data in the specific cell.
The output unit may graphically display a time-dependent change in the plurality of pieces of associated data having a correlation equal to or greater than the third threshold. This allows visual confirmation of the time-dependent change of the plurality of associated data having the association.
In the above-described analysis system, the data acquisition unit may acquire, as the associated data, the mass concentration of the particulate matter and information associated with the element included in the particulate matter. Thereby, analysis related to the particulate matter can be performed based on the features extracted from the mass concentration of the particulate matter and/or the information related to the elements contained in the particulate matter.
In the above-described analysis system, the data acquisition unit may acquire, as the associated data, a wind direction of the portion where the particulate matter is collected. In this case, the feature extraction unit may extract, from the associated data of the specific wind direction, associated data in which an instantaneous value of the content of the element contained in the particulate matter exceeds a first threshold value or in which an average value or a median value of the content of the element contained in the particulate matter exceeds a second threshold value. Thus, it is possible to extract related data indicating abnormality with respect to the particulate matter flying from a specific direction, that is, the particulate matter flying from a specific generation source.
In the above analysis system, the data acquisition unit may acquire information on the particle size of the particulate matter as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the particulate matter has a predetermined particle size range. Thus, for example, characteristics relating to the generation source of the particulate matter, such as near or far from the generation source of the particulate matter, can be extracted.
In the analysis system, the data acquisition unit may acquire data on the gas at the portion where the particulate matter is collected as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the gas is a predetermined type of gas. Thus, for example, it is possible to extract a feature relating to the state of the atmosphere at the installation position of the data acquisition unit, such as whether or not corrosive gas is present at the installation position.
In the above-described analysis system, the data acquisition unit may acquire data on a wind speed of a portion where the particulate matter is collected as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the wind speed exceeds a predetermined threshold value or is equal to or less than the predetermined threshold value. Thus, for example, characteristics relating to the generation source of the particulate matter, such as near or far from the generation source of the particulate matter, can be extracted.
In the analysis system, the output unit may generate the alarm when the feature extraction unit extracts, from the associated data, associated data that matches a predetermined index for a predetermined feature. This can visually and/or audibly confirm that the associated data satisfying the predetermined index is acquired.
A server according to another aspect of the present invention is a server for acquiring and analyzing related data related to particulate matter. The server includes a feature extraction unit and an output unit. The feature extraction unit extracts features included in the associated data by performing predetermined feature extraction processing that takes the associated data as input. The output section outputs information associated with the feature extracted by the feature extraction section.
In the server, the feature extraction unit automatically performs a predetermined feature extraction process that receives as input associated data associated with the particulate matter, and automatically extracts features included in the associated data. In this way, by automatically extracting the features included in the associated data by the feature extraction unit, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by the output unit outputting information related to the feature extracted by the feature extraction unit, it is possible to indicate to the user what feature is extracted from the related data.
The analysis method according to still another aspect of the present invention is an analysis method relating to a particulate matter. The analysis method includes the following steps.
And a step of acquiring correlation data concerning the particulate matter.
And a step of extracting the feature included in the associated data by executing a predetermined feature extraction process that takes the associated data as an input.
Outputting information associated with the extracted features.
In the above analysis method, a predetermined feature extraction process is automatically performed, which takes as input association data associated with the particulate matter, and features contained in the association data are automatically extracted. Thus, by automatically extracting the features included in the associated data, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by outputting information associated with the extracted feature, it is possible to indicate to the user what feature is extracted from the associated data.
A program according to still another aspect of the present invention is a program for causing a computer to execute the above analysis method.
Features contained in data related to the particulate matter can be extracted efficiently and accurately.
Drawings
Fig. 1 is a diagram showing a configuration of an analysis device.
Fig. 2 is a diagram showing a configuration example of the first analyzer.
Fig. 3 is a diagram showing the functional block configuration of the analysis server.
Fig. 4 is a flowchart showing a peak search operation.
Fig. 5 is a diagram showing an example of displaying the associated data list in which the peak value exceeds the first threshold value.
Fig. 6 is a graph showing an example of a time-dependent graph of correlation data having peaks equal to or higher than a first threshold value.
Fig. 7 is a flowchart showing an average value search operation.
Fig. 8 is a diagram showing an example of displaying the associated data including the peak value equal to or higher than the first threshold value and the associated data including the average value equal to or higher than the second threshold value.
Fig. 9 is a diagram showing an example of a graph of time-dependent data including an average value equal to or higher than a second threshold value.
Fig. 10 is a flowchart showing an automatic correlation extraction operation.
Fig. 11 is a diagram showing an example of a distribution chart in the case where a plurality of correlations are observed between two pieces of correlation data.
Fig. 12 is a diagram showing an example of a case where only a distribution map having a large correlation is displayed.
Fig. 13 is a diagram showing an example of a case where a distribution map having a large correlation is highlighted.
Fig. 14 is a diagram showing an example of a state in which a time-dependent graph of correlation is displayed.
Fig. 15 is a diagram showing an example of a state in which time-dependent graphs of values of two related data having a large correlation are displayed.
Fig. 16 is a diagram showing a modification of the first analyzer.
Detailed Description
1. First embodiment
(1) Analysis system
Next, the analysis system 100 will be described. The analysis system 100 is the following: for acquiring data related to the particulate matter, called correlation data RD, and analyzing the particulate matter by extracting features contained in the acquired correlation data RD.
The particulate matter to be analyzed in the analysis system 100 is, for example, a micron-sized particulate matter produced by combustion processing in factories and the like, brakes of various transportation devices (automobiles, ships and the like), tires, internal combustion engines, steam engines, exhaust gas purification devices, motors, natural disasters such as volcanic eruptions, and mine development.
The structure of the analysis system 100 will be described with reference to fig. 1. Fig. 1 is a diagram showing a configuration of an analysis system. The analysis system 100 mainly includes a data acquisition unit 1 and an analysis server 3.
The data acquisition unit 1 is disposed at or near a source of particulate matter, and acquires various data concerning particulate matter generated from the source as associated data RD. The data acquisition unit 1 is disposed, for example, in a factory or its vicinity where there is a possibility of generating particulate matter, along a road (a trunk road, a highway, or the like) where the traffic volume is large, or in the vicinity thereof. The data acquisition unit 1 may be mounted on a mobile body (for example, an automobile) so as to be movable.
The analysis server 3 is a computer system including a CPU, a storage device (RAM, ROM, SSD, HDD, etc.), various interfaces, and the like. The analysis server 3 is connected to the data acquisition unit 1, and collects and stores the associated data RD acquired by the data acquisition unit 1. The analysis server 3 also extracts the features included in the associated data RD by performing a predetermined feature extraction process that receives the associated data RD collected from the data acquisition unit 1 as input.
The analysis server 3 is connected to the client terminal 5. The client terminal 5 is an information terminal such as a personal computer, a tablet terminal, or a smart phone used by a user. The user accesses the analysis server 3 using the client terminal 5, and can read, for example, the associated data RD stored in the analysis server 3, the analysis result of the associated data RD output from the analysis server 3, and the like.
In fig. 1, an example is shown in which one analysis system 100 is provided for each of the data acquisition unit 1, the analysis server 3, and the client terminal 5, but the number of the data acquisition unit 1, the analysis server 3, and the client terminal 5 in the analysis system 100 is arbitrary.
(2) Data acquisition unit
(2-1) Integral construction
The specific configuration of the data acquisition unit 1 included in the analysis system 100 will be described below with reference to fig. 1. The data acquisition unit 1 includes a first analyzer 11, a second analyzer 13, a third analyzer 15, and a data collection device 17.
The first analysis device 11 collects the particulate matter present at the arrangement position of the data acquisition unit 1 at each predetermined time (for example, every 1 hour), and acquires the mass concentration of the collected particulate matter and information on the elements contained in the particulate matter as the correlation data RD. Here, "information on the element contained in the particulate matter" means the element contained in the particulate matter and the content of the element. The information may include a composition ratio (element ratio) of elements included in the granular material. The data acquisition unit 1 includes the first analysis device 11, and thus in the analysis system 100, it is possible to perform analysis on the particulate matter based on features extracted from the mass concentration of the particulate matter and/or information on elements contained in the particulate matter.
The particulate matter may vary depending on the generation source or the like, and contains, for example, chromium (Cr), copper (Cu), iron (Fe), aluminum (Al), silicon (Si), lead (Pb), zinc (Zn), mercury (Hg), vanadium (V), calcium (Ca), potassium (K), arsenic (As), selenium (Se), sulfur (S), an element that causes a flame reaction (for example, strontium (Sr)), or the like. The first analysis device 11 can acquire at least information (the element included, the content of the element) related to these elements and other elements.
A specific configuration example of the first analyzer 11 capable of acquiring the mass concentration of the particulate matter and information about the elements contained in the particulate matter will be described later.
The second analyzer 13 is a wind direction meter that obtains the wind direction and the wind speed of the arrangement position (the position where the particulate matter is collected) of the data acquisition unit 1 as the correlation data RD at each predetermined time (for example, every 1 hour). Particulate matter is susceptible to wind-borne fly from its source of production. Therefore, by providing the second analyzer 13 in the data acquisition unit 1, it is possible to determine from which direction the particulate matter collected by the first analyzer 11 flies.
The third analysis device 15 is a device that analyzes the gas contained in the atmosphere around the arrangement position (the position where the particulate matter is collected) of the data acquisition unit 1 at each predetermined time (for example, every 1 hour). Specifically, the third analysis device 15 identifies the gas contained in the atmosphere around the arrangement position of the data acquisition unit 1 and/or acquires the concentration of the gas as the correlation data RD. The gas that can be analyzed by the third analysis device 15 is, for example, a gas such as hydrocarbon, carbon monoxide (CO), carbon dioxide (CO 2), nitrogen oxides (NOx), ozone (O 3), sulfur oxides (SOx), hydrogen sulfide (H 2 S), or a volatile organic compound (Volatile Organic Compounds, VOC) such as acetone, ethanol, toluene, benzene, freon.
The data collection device 17 is a data recorder that acquires the related data RD acquired by the first to third analysis devices 11 to 15 and transmits the acquired data to the analysis server 3. The data collection device 17 determines the timing of acquiring the correlation data RD from each analysis device in consideration of the time deviation between each analysis device and the data collection device 17. Thus, the data collection device 17 does not miss the associated data RD obtained by the respective analysis devices. The data collection device 17 also associates the association data RD acquired from each analysis device with the time (time stamp) at which the association data RD was acquired. When sending the association data RD to the analysis server 3, the data collection means 17 also send the time stamp associated with the association data RD to the analysis server 3.
With the above configuration, the data acquisition unit 1 can acquire the mass concentration of the particulate matter, information on the elements contained in the particulate matter, the wind direction, the wind speed, and information on the gas contained in the surrounding atmosphere as the correlation data RD associated with the particulate matter, and supply the correlation data to the analysis server 3. The correlation data RD acquired by each analysis device is acquired at predetermined time intervals, and thus the correlation data RD is data whose result varies with time. That is, the association data RD is data in which results (values, etc.) obtained at respective times are arranged in time series.
The data acquisition unit 1 may have other measuring devices in addition to the first to third analyzing devices 11 to 15. For example, a positioning device such as a GPS may be provided to acquire the arrangement position of the data acquisition unit 1.
(2-2) Structure of first analysis device
A specific configuration example of the first analyzer 11 will be described with reference to fig. 2. Fig. 2 is a diagram showing a configuration example of the first analyzer. The first analysis device 11 includes a collection filter 111, a collection unit 113, a first analysis unit 115, a second analysis unit 117, and a control unit 119.
The collecting filter 111 is, for example, a belt-shaped member in which a collecting layer (also referred to as a collecting region) made of a porous fluororesin-based material having pores capable of collecting particulate matter is laminated on a reinforcing layer made of a nonwoven fabric of a polymer material (such as polyethylene). As the collection filter 111, for example, a single glass filter, a single fluororesin-based filter, or other filter may be used.
In the present embodiment, the collection filter 111 is movable in the longitudinal direction (the direction indicated by the thick arrow in fig. 2) by winding the collection filter 111 fed from the feeding roller 111a by rotation of the winding roller 111 b.
The trap portion 113 is provided so as to correspond to the first position P1 in the longitudinal direction of the trap filter 111. The collecting unit 113, for example, blows out the air sucked by the suction force of the suction port 135 connected to the suction pump 131 from the discharge port 133 to the collecting region existing at the first position P1 of the collecting filter 111, thereby collecting the particulate matter contained in the air in the collecting region.
The first analysis unit 115 measures the amount of particulate matter collected by the collection filter 111. Specifically, the first analysis unit 115 includes a β -ray source 51 and a β -ray detector 53. The β -ray source 51 is provided at the discharge port 133 of the trap portion 113, and emits β -rays to the trap region of the trap filter 111 disposed at the first position P1. The beta ray source 51 is, for example, a beta ray source using carbon 14 (14C).
The β -ray detector 53 is provided in the suction port 135 of the collecting unit 113 so as to face the β -ray source 51, and measures the intensity of the β -ray transmitted through the particulate matter collected in the collecting region at the first position P1. The β -ray detector 53 is, for example, a photomultiplier tube provided with a scintillator. The amount of particulate matter trapped (mass concentration) is calculated based on the intensity of the beta rays measured by the beta ray detector 53.
The second analysis unit 117 is provided so as to correspond to the second position P2 in the longitudinal direction of the collection filter 111, and measures data related to fluorescent X-rays generated from the particulate matter present at the second position P2. Specifically, the second analysis unit 117 includes an X-ray source 71 and a detector 73.
The X-ray source 71 irradiates X-rays onto the particulate matter present at the second position P2. The X-ray source 71 is, for example, a device that irradiates a metal such as palladium with an electron beam to generate X-rays. The detector 73 detects fluorescent X-rays generated from the particulate matter. The detector 73 is, for example, a silicon semiconductor detector or a silicon drift detector.
The control unit 119 obtains data for calculating the mass concentration of the particulate matter using the first analysis unit 115 provided at the first position P1. The control unit 119 controls the winding drum 111b to move the collection filter 111 so as to obtain the elemental analysis result using the second analysis unit 117 provided at the second position P2. Specifically, the control unit 119 moves the collection area (area where the particulate matter is collected) of the collection filter 111 from the first position P1 where the first analysis unit 115 is provided to the second position P2 where the second analysis unit 117 is provided each time the collection of the particulate matter by the collection unit 113 is completed and the measurement of the collection amount is completed.
After the collection region reaches the second position P2, the control unit 119 irradiates the second position P2 with X-rays from the X-ray source 71, and acquires fluorescent X-rays generated from the particulate matter in the collection region by the irradiation of the X-rays as data for elemental analysis.
The control unit 119 calculates the mass concentration of the particulate matter as the correlation data RD based on the intensity of the β -ray measured by the first analysis unit 115. The control unit 119 acquires fluorescence X-ray data (for example, fluorescence X-ray spectrum) obtained by the second analysis unit 117, and calculates the element contained in the granular material and the content thereof as the correlation data RD based on the fluorescence X-ray data. The calculated above-mentioned association data RD are transmitted to the data collection means 17.
(3) Function module constitution of analysis server
The functional block configuration of the analysis server 3 will be described below with reference to fig. 3. Fig. 3 is a diagram showing the functional block configuration of the analysis server. The functional blocks of the analysis server 3 described below may be stored in a storage device of the analysis server 3, and may be realized by the analysis server 3 through an executable program. In addition, part of the functional modules may be realized by hardware constituting the analysis server 3. The analysis server 3 has a storage section 31, a data receiving section 33, a feature extracting section 35, and an output section 37 as functional modules.
The storage unit 31 stores various data, programs, setting values, and the like used in the analysis server 3. Specifically, the storage unit 31 stores the associated data RD acquired by the data acquisition unit 1. By having the storage unit 31, the analysis server 3 can function as a database of the association data RD.
The data receiving unit 33 receives the related data RD from the data collecting device 17 of the data acquiring unit 1 and stores the data in the storage unit 31. The data receiving unit 33 receives the associated data RD stored in the data collecting device 17 at a predetermined timing. The data receiving unit 33 may receive the related data RD via the data collecting device 17 immediately after each analysis device outputs the related data RD (that is, the related data RD is not accumulated in the data collecting device 17), or may receive the related data RD at a timing when the related data RD is accumulated in the data collecting device 17 to some extent.
The feature extraction unit 35 extracts features included in the associated data RD by performing a predetermined feature extraction process that receives as input the associated data RD stored in the storage unit 31. Specifically, as a predetermined feature extraction process, the feature extraction unit 35 performs statistical analysis on the associated data RD and extracts features included in the associated data RD. More specifically, each value included in the correlation data RD whose value varies with time is filtered, and the feature included in the correlation data RD is extracted. This feature extraction process is referred to as a data screening function.
Specifically, as the data filtering function, the feature extraction unit 35 extracts a feature that the peak value (instantaneous value) included in the associated data RD exceeds the first threshold value, and notifies the output unit 37 of the time when the peak value exceeding the first threshold value is measured and information (for example, a data name or the like) identifying the associated data RD whose peak value exceeds the first threshold value. This feature extraction process is referred to as a peak search function.
Further, as another data filtering function, the feature extraction unit 35 extracts a feature that the average value of the values included in the associated data RD exceeds the second threshold value, and notifies the output unit 37 of the time when the average value exceeds the second threshold value and information identifying the associated data RD that the average value exceeds the second threshold value. This feature extraction process is referred to as an average value search function. The average value is an average value of a plurality of values included in a predetermined time range around the specific time included in the association data RD, for example. In this case, the "time at which the average value exceeds the second threshold value" is the time of the reference when the average value is calculated. In addition, in the data filtering function, a median value of values included in the associated data RD may be used instead of the average value of values included in the associated data RD.
The threshold value used in the data filtering function may be a predetermined fixed value or may be a value that can be changed according to the type of the associated data RD. In the case where the threshold value can be changed, for example, the standard deviation can be calculated on the correlation data RD of the object to be screened for data, and an integer multiple (for example, 1-fold or 2-fold) of the standard deviation can be set as the threshold value.
The feature extraction unit 35 automatically calculates the correlation of the plurality of pieces of correlation data RD stored in the storage unit 31, extracts information associated with the plurality of pieces of correlation data RD having a correlation higher than the third threshold value as features included in the correlation data RD, and notifies the information to the output unit 37. This feature extraction process is referred to as an auto-correlation extraction function.
The data filtering function and the automatic correlation extraction function may be executed by the feature extraction unit 35 by an instruction from the client terminal 5, or may be automatically executed at a predetermined timing. In addition, when the automatic correlation extraction function is executed, the plurality of pieces of correlation data RD to be the object of correlation calculation may be selected by the user using the client terminal 5, or the plurality of pieces of correlation data RD to be the object of correlation calculation may be automatically extracted by the feature extraction unit 35.
The output section 37 outputs information associated with the feature extracted by the feature extraction section 35 to the client terminal 5. When the feature extraction unit 35 performs the data filtering function, the output unit 37 displays a list of times when the peak value of the first threshold value or more is generated and/or times when the average value or median value is equal to or more than the second threshold value on the client terminal 5. Links associated with the association data RD containing the peak value and/or the average value (median value) are added to each time point of the list display. If the link is selected, the output section 37 displays the data value of the corresponding association data RD and/or a graph of the association data RD on the client terminal 5.
On the other hand, when the feature extraction unit 35 performs the automatic correlation extraction function, the output unit 37 outputs information associated with a plurality of association data RD having a calculated correlation higher than the third threshold value to the client terminal 5. For example, the output unit 37 displays a distribution map of a plurality of association data RD whose correlation is equal to or higher than the third threshold value on the client terminal 5.
Alternatively, the output unit 37 may output a profile for a plurality of combinations of the association data RD to the client terminal 5, and highlight a profile for a combination of the association data RD whose correlation is equal to or greater than the third threshold value among the displayed profiles. Specifically, for example, the highlighting can be performed by the following method: surrounding a distribution diagram of a combination of the related data RD having a correlation equal to or higher than the third threshold value with a frame of a predetermined color (for example, red), and displaying a distribution diagram of a combination of the related data RD having a correlation Guan Xingxiao equal to or higher than the third threshold value in a shallower manner.
The output unit 37 can display a distribution map for a plurality of associated data RD designated by the user using the client terminal 5. For example, the output unit 37 can generate and display a distribution map of the content of a combination of two elements among a plurality of elements selected by the user using the client terminal 5. For example, in the case where three elements are selected by the user, a distribution map of the content of two elements can be displayed on the client terminal 5 for each of the combinations (three combinations) of two elements further selected from the three elements. Thus, the user can visually confirm the combination of the correlation data RD having high correlation based on the displayed plurality of distribution charts.
(4) Analysis actions for associated data in an analysis system
(4-1) Peak search action
The following describes an analysis operation of the correlation data RD in the analysis system 100. First, an operation of a peak search function (peak search operation) which is one of the data filtering functions will be described with reference to fig. 4. Fig. 4 is a flowchart showing a peak search operation. The peak search action shown in the flowchart of fig. 4 is performed by the analysis server 3.
The peak search operation may be performed on all the associated data RD (including the time-varying values) stored in the storage unit 31, or may be performed on a plurality of associated data RD specified in advance. For example, the present invention can be executed on other related data RD (for example, related data RD related to the content of a specific element) acquired while the specific wind direction is indicated in the related data RD related to the wind direction acquired by the second analysis device 13. By searching for peaks in the correlation data RD obtained in a specific wind direction, for example, the state of particulate matter from a specific generation source can be monitored.
For example, when correlation data RD indicating the content of the element contained in the particulate matter is the object of the peak search, when a specific wind direction is observed, the correlation data RD whose peak value of the content of the element contained in the particulate matter exceeds the first threshold value can be extracted. Thus, it is possible to extract related data indicating abnormality for the particulate matter flying from a specific direction, that is, the particulate matter flying from a specific generation source.
First, in step S11, the feature extraction unit 35 searches for a peak included in the correlation data RD that is the object of the peak search. For example, in the case where the association data RD is data of the content of the element contained in the particulate matter, a peak value of the content is searched for. For example, the feature extraction unit 35 scans the values included in the association data RD one by one, and if the value of the current scan is greater than the values before and after it, determines the value of the current scan as a sub-peak value, and determines the maximum value of all sub-peak values included in the association data RD as a peak value.
Next, in step S12, the feature extraction unit 35 determines whether or not the peak observed by executing step S11 is equal to or greater than a first threshold. For example, it is determined whether or not the peak value of the content of the element is equal to or higher than a first threshold value. The first threshold value can be appropriately determined according to the kind of element or the like. If the peak value is not equal to or greater than the first threshold value (no in step S12), the feature extraction unit 35 determines that the peak value equal to or greater than the first threshold value is not included in the association data RD to be subjected to the current peak search, and ends the peak search operation. If there are other associated data RD as an object of the peak search, a peak search action is performed on the associated data RD.
On the other hand, when the peak observed by executing step S11 is equal to or higher than the first threshold (yes in step S12), in step S13, the feature extraction unit 35 notifies the output unit 37 of the timing at which the peak occurs in the associated data RD and information identifying the associated data RD including the peak. For example, when the peak value of the content of the element is equal to or greater than the first threshold value, the timing at which the peak value of the content of the element occurs and the identification information of the association data RD including the peak value are output to the output unit 37.
The output unit 37 that has received the above-described time and the identification information of the associated data RD displays the time when the peak value equal to or greater than the first threshold value occurs on the client terminal 5 in step S14. When the client terminal 5 accesses the analysis server 3 using a browser or the like, the output unit 37 generates, for example, an HTML file that displays a list shown in fig. 5 and displays the above-described time table. In the list display shown in fig. 5, the time when the Peak occurs is displayed in the "Date" field, and a display (Peak) indicating that the Peak is included at or above the first threshold is performed in the "Type" field. Fig. 5 is a diagram showing an example of displaying the associated data list in which the peak value exceeds the first threshold value.
The output unit 37 also generates a link for displaying a graph showing a time-dependent change of a value in the associated data RD on the client terminal 5 based on the information identifying the associated data RD received from the feature extraction unit 35 in step S13. The output unit 37 adds the generated link to the display section of the time when the peak included in the associated data RD occurs in the list display of the time. In the list display shown in fig. 5, the underlined representation attached to each time point is attached with the above-described links.
The client terminal 5 selects (e.g., clicks on) the timing at which the link is added, and displays the graph shown in fig. 6 on the client terminal 5. The graph shown in fig. 6 is a graph showing the time-dependent content of a specific element a. Fig. 6 is a graph showing an example of a time-dependent graph of correlation data having peaks equal to or higher than a first threshold value.
By the peak search operation described above, the analysis server 3 can automatically, efficiently and accurately extract the features including a large peak in the correlation data RD. For example, when the peak exceeding the first threshold value indicates the occurrence of an abnormality, the analysis server 3 can automatically extract the associated data RD including the abnormality by the peak exceeding the first threshold value by the peak search operation described above, and present the user with which associated data RD the abnormality has occurred. Further, by graphically displaying the associated data RD including the large peak on the client terminal 5, the user can visually confirm the temporal change of the associated data RD including the abnormality, for example.
(4-2) Average search action
Next, the operation of the average value search function (average value search operation) as another data filtering function will be described with reference to fig. 7. Fig. 7 is a flowchart showing an average value search operation. The average value search operation shown in the flowchart of fig. 7 is performed by the analysis server 3.
The average value search operation may be performed on all the associated data RD stored in the storage unit 31, or may be performed on a plurality of associated data RD specified in advance, similarly to the peak value search operation.
For example, when the correlation data RD indicating the content of the element contained in the particulate matter is the object of the average value search operation, the correlation data RD that the average value or the median value of the content of the element contained in the particulate matter exceeds the second threshold value can be extracted when a specific wind direction is observed. Thus, it is possible to extract related data indicating abnormality for the particulate matter flying from a specific direction, that is, the particulate matter flying from a specific generation source.
First, in step S21, the feature extraction unit 35 calculates an average value of the associated data RD as the object of the average value search. For example, in the case where the association data RD is data of the content of the element contained in the particulate matter, an average value of the content is calculated. For example, the feature extraction unit 35 calculates an average value of the reference value and a predetermined number of values before and after the reference value with reference to one value included in the association data RD. The feature extraction unit 35 changes the reference value from the value at the beginning to the value at the end of the associated data RD, and performs calculation of the average value. As a result, for example, when the correlation data RD includes N values that change with time, when an average value of three values centered on the reference value is calculated, N-2 average values are calculated. That is, by executing step S21, a plurality of average values are calculated for one association data RD.
The average value may be calculated by calculating a moving average of the associated data RD. In addition, instead of the average value, a median value may be calculated.
Next, in step S22, the feature extraction unit 35 determines whether or not there is an average value equal to or greater than the second threshold value among the plurality of average values calculated by executing step S21. For example, it is determined whether or not the average value of the content of the element is equal to or greater than a second threshold value. The second threshold value can be appropriately determined according to the kind of element or the like. If any of the plurality of average values is not equal to or greater than the second threshold value (no in step S22), the feature extraction unit 35 determines that the average value equal to or greater than the second threshold value is not included in the associated data RD, and ends the average value search operation. If there are other associated data RD as an object of the average search, an average search action is performed on the associated data RD.
On the other hand, when any one of the plurality of average values calculated in step S21 is equal to or greater than the second threshold value (yes in step S22), in step S23, the feature extraction unit 35 notifies the output unit 37 of the time at which the average value is equal to or greater than the second threshold value and information identifying the associated data RD for calculating the average value. For example, when the average value of the content of the element is equal to or greater than the second threshold value, the identification information of the association data RD including the average value and the time when the average value of the content of the element is equal to or greater than the second threshold value are output to the output unit 37.
The output unit 37 that has received the above-described time and the identification information of the related data RD displays the time when the average value becomes equal to or greater than the second threshold value on the client terminal 5 in step S24. As shown in fig. 8, the time is displayed together with the peak generation time in a table in which the time at which the peak is generated at the first threshold or higher is displayed in a list. In a row (third row in fig. 8) corresponding to a time when the Average value in the "Type" column is equal to or greater than the second threshold value, a display (Average) indicating that the association data RD includes the Average value equal to or greater than the second threshold value is performed. Fig. 8 is a diagram showing an example of displaying the associated data including the peak value equal to or higher than the first threshold value and the associated data including the average value equal to or higher than the second threshold value.
The output unit 37 generates a link for displaying a graph showing a time-dependent change of a value in the associated data RD on the client terminal 5 based on the information identifying the associated data RD received from the feature extraction unit 35 in step S23, and adds the link to a display of a time when the average value is equal to or greater than the second threshold value.
The client terminal 5 selects (e.g., clicks on) the time point at which the link is added, and displays the graph shown in fig. 9 on the client terminal 5, for example. The graph shown in fig. 9 is a graph showing the time-dependent change of the content of the specific element B. Fig. 9 is a diagram showing an example of a graph of time-dependent data including an average value equal to or higher than a second threshold value. Further, the value included in the corresponding association data RD may be displayed by selecting the link.
By the above average value searching operation, the analysis server 3 can automatically, efficiently and accurately extract the features including a large average value or median value in the associated data RD. For example, when the average value or the median value exceeding the second threshold value indicates that an abnormality has occurred, the analysis server 3 can automatically extract the associated data RD containing the abnormality by the average value or the median value exceeding the second threshold value by the above-described average value search operation, and present to the user which associated data RD the abnormality has occurred in. Further, by graphically displaying the association data RD including the large average value or median value on the client terminal 5, the user can visually confirm, for example, the temporal variation of the association data RD including the abnormality.
(4-3) Automatic relevance extraction action
The operation of the automatic correlation extraction function (automatic correlation extraction operation) will be described with reference to fig. 10. Fig. 10 is a flowchart showing an automatic correlation extraction operation. The automatic correlation extraction action shown in the flowchart of fig. 10 is performed by the analysis server 3.
First, in step S31, the feature extraction unit 35 selects a plurality of association data RD (two association data RD) of the object for which the correlation is calculated. For example, before executing step S31, the user selects a plurality of association data RD of the object to be investigated for the correlation (a plurality of data items of the object to be investigated for the correlation) using the client terminal 5. Thereafter, in step S31, the feature extraction section 35 that has received the result of the selection by the user selects two association data RD for calculating the correlation from the plurality of association data RD selected by the user.
Alternatively, the feature extraction unit 35 may automatically select two pieces of correlation data RD to be investigated for correlation from among all pieces of correlation data RD stored in the storage unit 31. The correlation data RD is a target for calculating correlation when a specific wind direction is observed in the correlation data RD.
Next, in step S32, the feature extraction section 35 calculates the correlation of the two associated data RD selected by executing step S31. Specifically, the feature extraction unit 35 calculates a determination coefficient (square of a correlation coefficient) indicating the degree of correlation of the two associated data RD, using a value included in one of the two associated data RD as the first element (x) and a value included in the other as the second element (y).
The data acquisition unit 1 acquires the values of the associated data RD at predetermined time intervals, and therefore includes a plurality of values that change with time in the associated data RD. When the correlation data RD is obtained as a result of a long-term measurement, as shown in fig. 11, a plurality of large correlations may be observed between two correlation data RD. In the example shown in fig. 11, two large correlations are observed in the region surrounded by the ellipse. In addition, the determination coefficients calculated for the values of the correlation data RD including a plurality of large correlations tend to be smaller. That is, the determination coefficient calculated from the long-term correlation data RD may not indicate the presence of a plurality of large correlations. Fig. 11 is a diagram showing an example of a distribution chart in the case where a plurality of correlations are observed between two pieces of correlation data.
A plurality of large correlations are observed between the plurality of correlation data RD, for example, indicating that the characteristics of the particulate matter generated in a particular generation source have changed during the acquisition period of the correlation data RD. It is important to grasp at which timing the characteristic of the particulate matter has changed during the acquisition period of the correlation data RD in analyzing the particulate matter.
Therefore, the feature extraction unit 35 calculates the determination coefficient not only by using the value of the entire period in which the association data RD is acquired, but also by dividing the period into a plurality of small periods and calculating the determination coefficient by using the value within the small period. For example, when the correlation data RD of the object of the investigation of the correlation is data acquired over one year, the calculation of the determination coefficients using the first one month value included in the correlation data RD and the calculation of the determination coefficients using the next month value are repeatedly performed, whereby a total of 12 determination coefficients can be calculated for the correlation data RD acquired over one year.
As described above, the correlation data RD obtained over the long period is calculated as a determination coefficient for each of a plurality of small periods included in the long period, and information on a phenomenon occurring in the small period is obtained. For example, when the determination coefficient is small in a specific small period (the correlation between the associated data RD is small) and the determination coefficient is large in another small period (the correlation between the associated data RD is large), it can be estimated that a particular phenomenon occurs with respect to the generation of the particulate matter between these two small periods.
The period of time may be variable. For example, the determination coefficients can be calculated using the first one month value contained in the association data RD, and then calculated using the first two months value contained in the association data RD. By flexibly setting the periods in this way, it is possible to determine in which period the correlation of the associated data has changed. For example, when a large correlation is not observed in the association data RD during the first one month (the determination coefficient is small), and a relatively large correlation is observed in the association data RD during the first two months (the determination coefficient is relatively large), it can be determined that the correlation of the association data RD has changed during at least the latter half of the two months. That is, it can be determined that the characteristic of the particulate matter has changed during at least the latter half of one month.
The above-described small period may be divided into finer cells, and the determination coefficient may be calculated for each cell. For example, the association data RD acquired over one year can be divided into small periods of one month, and the small periods of one month can be divided into each cell of one week. In this case, information about a phenomenon occurring between the cells is obtained in more detail. The inter-cell area may be variable in the same manner as the small period.
As described above, when calculating the correlation (determination coefficient) of the two correlation data RD, the correlation data RD is divided into the respective short-term intervals to calculate the determination coefficient, whereby the timing at which the characteristic change of the particulate matter occurs can be analyzed in more detail, and the timing at which the specific phenomenon occurs in the generation source of the particulate matter or the like can be analyzed in detail.
After calculating the correlation of the two correlation data RD, in step S33, the feature extraction unit 35 determines whether the correlation (determination coefficient) calculated in step S32 is equal to or greater than a third threshold value. Since a plurality of determination coefficients are calculated in step S32, the feature extraction unit 35 determines whether or not a determination coefficient equal to or greater than a third threshold value exists among the plurality of determination coefficients. The third threshold for evaluating the magnitude of the correlation can be appropriately determined by determining the degree of the correlation based on the magnitude of the determination coefficient.
If the calculated determination coefficients are not equal to or greater than the third threshold value (no in step S33), the feature extraction unit 35 determines that the correlation between the two currently selected association data RD is small, and proceeds to step S35.
On the other hand, when the calculated determination coefficient has a determination coefficient equal to or higher than the third threshold value (yes in step S33), the feature extraction unit 35 determines that the correlation between the currently selected two associated data RD is large, and in step S34, notifies the output unit 37 of information identifying the currently selected two associated data RD. At this time, the feature extraction unit 35 notifies the output unit 37 of information identifying two associated data RD together with information on a period in which the determination coefficient is equal to or greater than the third threshold value.
After the above steps S32 to S34 are performed using the combination of the two associated data RD currently selected, in step S35, the feature extraction unit 35 determines whether or not the correlation (determination coefficient) is calculated for all combinations of the two associated data RD included in all the associated data RD specified by the user or stored in the storage unit 31. If correlations are not calculated for all combinations (no in step S35), the feature extraction unit 35 returns to step S31, selects another combination of the two associated data RD, and executes steps S32 to S34 for the other combination.
On the other hand, when the correlations are calculated for all the combinations (yes in step S35), in step S35, the output unit 37 displays a predetermined graph for a plurality of correlated data RD having a high correlation, based on the information identifying the two correlated data RD and the correlation (determination coefficient) of the two correlated data RD, which are notified from the feature extraction unit 35 in step S34, of the third threshold value or more.
The output unit 37 generates a distribution map of values in the period in which the two related data RD having high correlation are notified, and outputs the distribution map to the client terminal 5.
When outputting the distribution map of the two related data RD having the correlation (determination coefficient) of the third threshold value or more, the output unit 37 may display only the distribution map of the two related data RD having the correlation of the third threshold value or more on the client terminal 5 as shown in fig. 12, may perform highlighting as shown in fig. 13, display a plurality of distribution maps of all combinations of the two related data RD, surround the distribution map having the correlation (determination coefficient) of the third threshold value or more with a frame, or the like. Fig. 12 is a diagram showing an example of a case where only a distribution map having a large correlation is displayed. Fig. 13 is a diagram showing an example of a case where a distribution map having a large correlation is highlighted.
The output unit 37 can graphically display the time-dependent changes in the plurality of related data RD having high correlation based on the information identifying the two related data RD and the period in which the correlation between the two related data RD is equal to or greater than the third threshold value, which are notified from the feature extraction unit 35 in step S34. Either or both of the display profile and the time-dependent profile can be arbitrarily determined.
For example, as a result of performing the automatic correlation extraction function, between the time T1 and the time T2, there is a high correlation between the content of the element C and the content of the element D (the determination coefficient is the third threshold value (TH 3) or more), there is a high correlation between the content of the element E and the content of the element F, and in the case where there is a high correlation between the content of the element G and the content of the element H, the graph shown in fig. 14 can be displayed for each of the combinations of the three elements. In fig. 14, a time-varying graph of the correlation between the content of the element C and the content of the element D is indicated by a solid line, a time-varying graph of the correlation between the content of the element E and the content of the element F is indicated by a broken line, and a time-varying graph of the correlation between the content of the element G and the content of the element H is indicated by a dash-dot line. Fig. 14 is a diagram showing an example of a state of the graphic display correlation with time.
By the above-described automatic correlation extraction action, the analysis server 3 can automatically efficiently and accurately extract features having large correlations among the plurality of correlation data RD. For example, when there is a large correlation between the contents of a plurality of elements, it can be presumed that the particulate matter having the same content (element ratio) of the plurality of elements is measured while the correlation is observed.
Further, by displaying the distribution map of the two correlation data RD having a large correlation, the magnitude of the correlation of the two correlation data RD can be visually confirmed. Further, by displaying a plurality of distribution charts irrespective of the magnitude of the correlation and highlighting a distribution chart having a large correlation among the displayed plurality of distribution charts, it is possible to visually confirm which one of all the correlation data RD has a large correlation.
Further, by graphically displaying the temporal change in correlation with respect to the plurality of correlation data RD having high correlation, it is possible to visually confirm what temporal change is performed in correlation with respect to the plurality of correlation data RD.
For example, when the correlation data RD is data indicating the content of an element contained in the granular material, it is possible to visually confirm how the correlation of the content of a plurality of elements changes with time. The high correlation between the contents of the plurality of elements means that the plurality of elements having a high correlation are contained in the particulate matter at a certain composition ratio. The kind and composition ratio of the elements contained in the particulate matter largely depend on the characteristics of the particulate matter such as the generation source and/or the generation conditions of the particulate matter.
Therefore, by graphically displaying the temporal change in correlation with respect to the content of the plurality of elements having high correlation, for example, the user can visually confirm the temporal change in correlation, it is possible to estimate the change in the characteristics of the particulate matter, that is, at which timing the particulate matter flies from which generation source and/or how the generation condition of the particulate matter changes at which timing, and the like.
When a profile is specified during the process of displaying the profile of the two related data RD having a large correlation, the output unit 37 may graphically display the time-dependent changes in the values of the two related data RD for which the profile is generated, as shown in fig. 15. Fig. 15 is a diagram showing an example of a state of a time-dependent value of two related data having a large graphic display correlation. Fig. 15 is an example of: by specifying the distribution diagram of the content of the element C and the content of the element D, which are shown in fig. 12 and have large correlation, the time-dependent change of the content of the element C and the time-dependent change of the content of the element D are arranged to be graphically displayed.
It is not clear from the distribution diagram shown in fig. 12 only in which period the correlation of the two correlation data RD becomes large, but it can be estimated in which period the correlation becomes large by graphically displaying the time-dependent change shown in fig. 14. In the example shown in fig. 14, it can be estimated that the tendency of increasing or decreasing the content of the element C is the same as the tendency of increasing or decreasing the content of the element D between the time T1 and the time T2, and the correlation between the content of the element C and the content of the element D increases during this period.
When generating the distribution map of the two associated data RD shown in fig. 11, the output unit 37 may output the color-separated points of the associated data RD to the client terminal 5 during the period in which the correlation is high. Thus, even when the two correlation data RD include a plurality of periods of high correlation, the plurality of correlations of the two correlation data RD of high correlation can be identified by the color of the points of the distribution map. For example, in the case where the two associated data RD are data related to particulate matter produced from the same production source, it can be visually confirmed that the properties of the particulate matter (for example, the composition ratio of elements, etc.) change for each time.
(5) Variation of the first analysis device
The first analyzing device 11 that obtains the correlation data RD related to the particulate matter is not limited to the configuration shown in fig. 2. Specifically, as shown in fig. 16, the first analyzer 11 may include a light source 51 'and a scattered light detector 53' instead of the β -ray source 51 and the β -ray detector 53 for measuring the amount of particulate matter collected. Fig. 16 is a diagram showing a modification of the first analyzer.
The light source 51' emits the laser light L into the discharge port 133. The scattered light detecting section 53' detects scattered light generated by scattering of the laser light L by the particulate matter while passing through the inside of the discharge port 133. The scattered light detector 53' is a photodetector such as a photodiode, for example. In this way, the control unit 119 can acquire information on the particulate matter contained in the atmosphere at the arrangement position of the first analyzer 11 based on the intensity of the scattered light detected by the scattered light detecting unit 53'. Specifically, data on the particle size of the particulate matter contained in the atmosphere (for example, particle size distribution of the particulate matter) can be acquired as the correlation data RD based on the intensity of the scattered light. Further, based on the intensity of the scattered light, data concerning the content of the particulate matter, such as the amount of the particulate matter contained in the atmosphere, can be acquired as the correlation data RD.
(6) Application example of analysis system
An example of application of the analysis system 100 will be described below. The analysis system 100 can be applied to, for example, environmental management in a storage place of a product or the like. Specifically, the analysis system 100 can be used, for example, to analyze whether or not corrosive gas, corrosive particulate matter, or the like affecting a product or the like is present at a storage location of the product or the like.
More specifically, the first to third analysis devices 11 to 15 are installed in a storage location for a product or the like, and the correlation data RD relating to the elements included in the granular material present in the space of the storage location, the correlation data RD relating to the particle size of the granular material, the correlation data RD relating to the gas present in the space of the storage location, the correlation data RD relating to the wind direction of the storage location, and the correlation data RD relating to the wind speed of the storage location are acquired, whereby the environmental management of the storage location can be performed based on these correlation data RD.
As a method for obtaining the correlation data RD concerning the particle diameter of the particulate matter, the following method may be used: using the first analyzer 11 shown in fig. 16, correlation data RD relating to the particle size is obtained based on the intensity of scattered light generated at the discharge port 133.
The correlation data RD relating to the particle size may be obtained by using a plurality of first analysis devices 11 shown in fig. 2. Specifically, the collecting unit 113 for collecting the granular materials in the different particle size ranges is provided for each of the plurality of first analysis devices 11, and the associated data RD (the associated data RD concerning the elements included in the granular materials, the associated data RD concerning the content (mass concentration) of the granular materials) obtained by the plurality of first analysis devices 11 are classified based on the associated data RD obtained by which first analysis device 11, and the associated data RD classified based on the particle size of the granular materials (that is, the associated data RD including the data concerning the particle size of the granular materials) can be obtained.
In addition to the first to third analyzers 11 to 15, other analyzers that can measure the particle size of the particulate matter may be connected to the data collection device 17, and the correlation data RD relating to the particle size of the particulate matter may be measured by the analyzers.
In this case, the feature extraction unit 35 of the analysis server 3 can perform feature extraction processing to extract the associated data RD indicating that the particulate matter has a predetermined particle size range, among the associated data RD stored in the storage unit 31. For example, when the feature extraction unit 35 extracts the association data RD indicating that the particle size range is within the predetermined range, the output unit 37 of the analysis server 3 can output information about the presence of the particulate matter having the particle size range in the space of the storage place.
For example, when the feature extraction unit 35 extracts the correlation data RD indicating that the particulate matter has a large particle diameter equal to or larger than a predetermined threshold value, the output unit 37 can output information including particulate matter generated in a relatively close place in a space of a storage place for a product or the like. On the other hand, when the feature extraction unit 35 extracts the correlation data RD indicating that the particulate matter has a small particle diameter equal to or smaller than the predetermined threshold value, the output unit 37 can output information including particulate matter generated at a relatively distant place in a space of a storage place for a product or the like.
The feature extraction unit 35 can extract the association data RD concerning the particulate matter having a specific particle size range, which is flying from a specific direction and contains a specific element, based on the information concerning the wind direction, the information concerning the wind speed, the information concerning the element contained in the particulate matter, and the like, in addition to the information concerning the particle size of the particulate matter. Thereby, more detailed information about the generation source of the particulate matter is obtained. When the feature extraction unit 35 extracts the correlation data RD concerning the particulate matter generated from the specific generation source, the output unit 37 can output information that the particulate matter generated from the specific generation source is present in the storage space.
As described above, by extracting the correlation data RD based on the information on the particle size of the particulate matter, the information on the wind direction, the information on the wind speed, and the information on the elements included in the particulate matter, it can be determined that the correlation data RD is the correlation data RD on the particulate matter artificially generated due to the operation of the plant or the like, or the correlation data RD on the particulate matter existing in the nature such as the soil.
For example, when the feature extraction unit 35 extracts the correlation data RD relating to the particulate matter having a large particle diameter, which is flying from a specific direction and contains a specific element that is easily generated from a predetermined plant, the output unit 37 can output information on the particulate matter having a plant located near the specific direction as a generation source at the storage location. For example, when the feature extraction unit 35 extracts the association data RD concerning the particulate matter which flies from another direction, contains a specific element contained in the soil, and has a small particle diameter, the output unit 37 can output information that the particulate matter is generated from the soil located at a position far from the other direction in the storage place.
When the feature extraction unit 35 extracts the associated data RD indicating that the wind speed exceeds the predetermined threshold value from the associated data RD stored in the storage unit 31, the output unit 37 can output information indicating that the particulate matter may fly from a relatively distant position. On the other hand, when the associated data RD indicating that the wind speed is equal to or lower than the predetermined threshold value is extracted, the output unit 37 can output information indicating that the particulate matter may fly from a relatively close position.
When the feature extraction unit 35 extracts the correlation data RD indicating that the particle size of the particulate matter is small and the wind speed exceeds the predetermined threshold value, the output unit 37 can output information indicating that the particulate matter may fly from a very distant position. On the other hand, when the correlation data RD indicating that the particle size of the particulate matter is large and the wind speed is equal to or less than the predetermined threshold value is extracted, the output unit 37 can output information indicating that the particulate matter may fly from a very near position.
As described above, the feature extraction unit 35 can more accurately determine the generation source of the particulate matter by extracting the feature obtained by combining the feature related to the wind speed and the feature related to the particle size of the particulate matter.
As described above, by extracting the characteristics related to the particulate matter, it is possible to determine the handling of the product stored in the storage location based on the properties of the particulate matter existing in the space of the storage location. For example, when the feature extraction unit 35 extracts the correlation data RD indicating that the granular material having an influence on the product such as corrosion exists in the space of the storage location, it is possible to perform treatments such as moving the product to another location, laying a cover on the product so that the granular material does not adhere to the product, and cleaning the product by sprinkling water.
The feature extraction unit 35 can extract the association data RD indicating that the predetermined type of gas is contained in the association data RD stored in the storage unit 31 by performing feature extraction processing. For example, when the feature extraction unit 35 extracts the association data RD indicating that the predetermined type of gas is contained, the output unit 37 can output information about the presence of the predetermined type of gas in the space of the storage location.
For example, when the feature extraction unit 35 extracts the correlation data RD indicating the presence of corrosive gases such as sulfur oxides (SOx) and hydrogen sulfide (H 2 S), the output unit 37 can output information indicating the presence of corrosive gases in the space of the storage location. In this way, when information indicating that corrosive gas is present in the space of the storage location is output, it is possible to perform handling such as moving the product to another location.
The output unit 37 may generate an alarm when the feature extraction unit 35 extracts association data RD matching a predetermined index for predetermined features such as a particle size of the particulate matter exceeding a predetermined threshold value, a wind direction indicating a specific direction, a wind speed exceeding a predetermined threshold value, a predetermined element being included in the particulate matter, a predetermined kind of gas being present, and the like. The output unit 37 can generate an alarm by, for example, making a sound, causing a predetermined display on the display unit of the analysis server 3, or the like.
By generating an alarm when the associated data RD satisfying the predetermined index is extracted, for example, the user can visually and/or audibly recognize the presence of particulate matter and/or gas in the space of the storage place that may affect the product. As a result, when an alarm is generated, handling such as movement of the product can be performed promptly.
2. Features of the embodiments
The embodiment described above can be expressed as follows.
(1) An analytical system is a system that performs an analysis related to particulate matter. The analysis system includes a data acquisition unit, a feature extraction unit, and an output unit. The data acquisition unit acquires associated data relating to the particulate matter. The feature extraction unit extracts features included in the associated data by performing predetermined feature extraction processing that takes the associated data as input. The output section outputs information associated with the feature extracted by the feature extraction section.
In the analysis system, the feature extraction unit automatically performs a predetermined feature extraction process for inputting the associated data associated with the particulate matter obtained by the data acquisition unit, and automatically extracts the features included in the associated data. In this way, by automatically extracting the features included in the associated data by the feature extraction unit, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by the output unit outputting information related to the feature extracted by the feature extraction unit, it is possible to indicate to the user what feature is extracted from the related data.
(2) In the analysis system according to (1) above, the feature extraction unit may extract the associated data in which the instantaneous value exceeds the first threshold value. In this case, the output unit may display a list of information associated with the associated data whose instantaneous value exceeds the first threshold value. In this way, it is possible to automatically extract the associated data including the abnormality when the instantaneous value exceeds the first threshold value, and to present to the user which associated data has the abnormality.
(3) In the analysis system according to (1) or (2), the feature extraction unit may extract the associated data in which the average value or the median value exceeds the second threshold value. In this case, the output unit may display the information associated with the associated data in which the average value or the median value exceeds the second threshold in a list. In this way, the related data including the abnormality whose average value or median value exceeds the second threshold can be automatically extracted, and the user can be presented with which related data the abnormality has occurred.
(4) In the analysis system according to (2) or (3), the output unit may graphically display associated data corresponding to the specified information among the information displayed in the list. This allows visual confirmation of the fluctuation of the related data including the abnormality.
(5) In the analysis systems (1) to (4), the feature extraction unit may calculate correlations of the plurality of pieces of correlation data, and extract information associated with the pieces of correlation data whose calculated correlations are equal to or greater than a third threshold. Thus, the user does not need to calculate and analyze the correlation for each combination of the plurality of pieces of correlation data, and thus can efficiently and accurately extract correlation data having a large correlation.
(6) In the analysis system according to (5), the output unit may display a distribution map of a plurality of pieces of associated data having a correlation equal to or greater than a third threshold. This allows the magnitude of the correlation of the extracted correlation data to be visually confirmed.
(7) In the analysis system according to (5), the output unit may display a plurality of distribution charts of a plurality of pieces of related data, and may highlight distribution charts of a plurality of pieces of related data having a correlation equal to or higher than a third threshold value. This makes it possible to visually identify which associated data has a high correlation among all the associated data.
(8) In the analysis systems (5) to (7), the associated data may be time-varying data. In this case, the feature extraction unit may calculate correlations of a plurality of pieces of associated data in a predetermined time interval. Thus, correlation of a plurality of pieces of correlation data in a specific time zone can be calculated. Information about a phenomenon occurring in a specific time zone is obtained from the correlation of the correlation data in the time zone.
(9) In the analysis system according to (8), the predetermined time period may be variable. This makes it possible to flexibly set a time zone for calculating the correlation of a plurality of pieces of correlation data.
(10) In the analysis system according to (8) or (9), the feature extraction unit may calculate a correlation of a plurality of pieces of correlation data for each of a plurality of cells included in the predetermined time zone. Thus, information on the phenomenon occurring in the specific period is obtained in more detail from the correlation of the associated data in the specific cell.
(11) In the analysis systems (8) to (10), the output unit may graphically display a time-dependent change in the plurality of pieces of associated data having a correlation equal to or greater than the third threshold. This allows visual confirmation of the time-dependent change of the plurality of associated data having the association.
(12) In the analysis systems (1) to (11), the data acquisition unit may acquire, as the associated data, the mass concentration of the particulate matter and information associated with the element contained in the particulate matter. Thereby, analysis related to the particulate matter can be performed based on the features extracted from the mass concentration of the particulate matter and/or the information related to the elements contained in the particulate matter.
(13) In the analysis system according to the above (12), the data acquisition unit may acquire, as the associated data, the wind direction of the portion where the particulate matter is collected. In this case, the feature extraction unit may extract, from the associated data of the specific wind direction, associated data in which an instantaneous value of the content of the element contained in the particulate matter exceeds a first threshold value or in which an average value or a median value of the content of the element contained in the particulate matter exceeds a second threshold value. Thus, it is possible to extract related data indicating abnormality with respect to the particulate matter flying from a specific direction, that is, the particulate matter flying from a specific generation source.
(14) In the analysis systems (1) to (13), the data acquisition unit may acquire information on the particle size of the particulate matter as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the particulate matter has a predetermined particle size range. Thus, for example, characteristics relating to the generation source of the particulate matter, such as near or far from the generation source of the particulate matter, can be extracted.
(15) In the analysis systems (1) to (14), the data acquisition unit may acquire data on the gas at the portion where the particulate matter is collected as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the gas is a predetermined type of gas. Thus, for example, it is possible to extract a feature relating to the state of the atmosphere at the installation position of the data acquisition unit, such as whether or not corrosive gas is present at the installation position.
(16) In the analysis systems (1) to (15), the data acquisition unit may acquire data on the wind speed of the portion where the particulate matter is collected as the associated data. In this case, the feature extraction unit may extract, from the associated data, associated data in which the wind speed exceeds a predetermined threshold value or is equal to or less than the predetermined threshold value. Thus, for example, characteristics relating to the generation source of the particulate matter, such as near or far from the generation source of the particulate matter, can be extracted.
(17) In the analysis systems (1) to (16), the output unit may generate the alarm when the feature extraction unit extracts, from the associated data, associated data that matches a predetermined index for a predetermined feature. This can visually and/or audibly confirm that the associated data satisfying the predetermined index is acquired.
(18) The server is a server that obtains and analyzes associated data related to the particulate matter. The server includes a feature extraction unit and an output unit. The feature extraction unit extracts features included in the associated data by performing predetermined feature extraction processing that takes the associated data as input. The output section outputs information associated with the feature extracted by the feature extraction section.
In the server, the feature extraction unit automatically performs a predetermined feature extraction process that receives as input associated data associated with the particulate matter, and automatically extracts features included in the associated data. In this way, by automatically extracting the features included in the associated data by the feature extraction unit, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by the output unit outputting information related to the feature extracted by the feature extraction unit, it is possible to indicate to the user what feature is extracted from the related data.
(19) The analysis method is an analysis method related to the particulate matter. The analysis method includes the following steps.
And a step of acquiring correlation data concerning the particulate matter.
And a step of extracting the feature included in the associated data by executing a predetermined feature extraction process that takes the associated data as an input.
Outputting information associated with the extracted features.
In the above analysis method, a predetermined feature extraction process is automatically performed, which takes as input association data associated with the particulate matter, and features contained in the association data are automatically extracted. Thus, by automatically extracting the features included in the associated data, the features included in the associated data can be extracted efficiently and accurately. Since the characteristic included in the related data imparts a characteristic to the particulate matter to be analyzed, the characteristic included in the related data can be extracted efficiently and accurately, and thus the particulate matter can be analyzed efficiently. Further, by outputting information associated with the extracted feature, it is possible to indicate to the user what feature is extracted from the associated data.
(20) A program according to still another aspect of the present invention is a program for causing a computer to execute the above analysis method.
3. Other embodiments
While the embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, and various modifications can be made without departing from the spirit of the invention. In particular, the plurality of embodiments and modifications described in the present specification may be arbitrarily combined as necessary.
(A) The order and/or processing content of the steps shown in the flowcharts of fig. 4, 7, and 10 may be changed within a range not departing from the gist of the present invention.
(B) The peak search function and the average search function may be provided in the data collection device 17 of the data acquisition unit 1. When the correlation data RD stored in the data collection device 17 includes a peak value equal to or higher than the first threshold value and/or an average value equal to or higher than the second threshold value, the data collection device 17 having the peak value search function or the average value search function transmits the result and/or the alarm to the outside by email.
More specifically, for example, when the correlation data RD in which the concentration of the specific component detected in the wind direction of the specific azimuth exceeds a certain value is present in the correlation data RD stored in the data collection device 17 for a certain period of time, the data collection device 17 can send an alarm mail.
(C) In the automatic correlation extraction operation, in the case of calculating the correlation using the element ratio of the element contained in the granular substance, the calculation of the correlation (determination coefficient) may be performed by removing data in which the element ratio is extremely small or extremely large.
(D) In the first embodiment described above, the analysis system 100 is a so-called "client-server system" having the analysis server 3, but is not limited thereto. For example, the data acquisition unit 1 may be (each analysis device or data collection device 17) provided with the function of the feature extraction unit 35 and/or the output unit 37, and may be an analysis system called "edge calculation". In this case, the data acquisition unit 1 may transmit the feature extracted from the associated data RD to the analysis server in addition to the associated data RD.
(E) The feature extraction unit 35 may implement feature extraction processing by a machine learning algorithm such as a neural network, for example. Specifically, for example, the learning completion model of the neural network may be generated using the association data RD having the feature to be extracted and the feature possessed by the association data RD as training data, and may be used as the feature extraction unit 35. By inputting the correlation data RD to be analyzed to the feature extraction unit 35 as a learning model, the features included in the correlation data RD can be extracted.
(F) The feature extraction unit 35 can extract features included in the associated data RD by other statistical analysis methods such as data mining on the associated data RD, in addition to the statistical analysis method described in the first embodiment.
(G) The feature extraction unit 35 may set a predetermined threshold value, and execute a plurality of algorithms for determining whether or not the data value included in the associated data RD exceeds the threshold value, thereby extracting the feature included in the associated data RD.
(H) The analysis server 3 may be configured to predict the analysis results (correlation data RD) concerning the particulate matter in the analysis devices (the first to third analysis devices 11 to 15) based on information concerning various processes in the factory and the like (for example, temperature, humidity, pressure, gas flow rate and the like). Specifically, for example, models of various processes for predicting the analysis result can be created, and the analysis result can be predicted from the calculation result of the model.
Industrial applicability
The present invention can be widely applied to analysis systems for analysis of particulate matter.
Description of the reference numerals
100. Analysis system
1. Data acquisition unit
11. First analysis device
111. Trapping filter
111A feeding roller
111B winding roller
P1 first position
P2 second position
113. Trapping part
115. A first analysis unit
51. Beta ray source
53. Beta-ray detector
51' Light source
53' Scattered light detection section
117. A second analysis unit
71 X-ray source
73. Detector for detecting a target object
119. Control unit
131. Suction pump
133. Discharge outlet
135. Suction port
13. Second analysis device
15. Third analysis device
17. Data collection device
3. Analysis server
31. Storage unit
33. Data receiving unit
35. Feature extraction unit
37. Output unit
5. Client terminal
RD associated data
Claims (20)
1. An analysis system for performing an analysis on a particulate matter, the analysis system comprising:
a data acquisition unit configured to acquire associated data related to the particulate matter;
A feature extraction unit that extracts features included in the associated data by performing a predetermined feature extraction process that takes the associated data as an input; and
And an output unit configured to output information associated with the feature extracted by the feature extraction unit.
2. The analytical system of claim 1, wherein the analytical system comprises,
The feature extraction section extracts the associated data whose instantaneous value exceeds a first threshold,
The output unit displays a list of information associated with the associated data whose instantaneous value exceeds a first threshold.
3. The analysis system according to claim 1 or 2, wherein,
The feature extraction section extracts the associated data whose average or median exceeds a second threshold,
The output unit displays a list of information associated with the associated data whose average or median exceeds a second threshold.
4. The analysis system according to claim 2 or 3, wherein the output unit graphically displays the associated data corresponding to the specified information among the information displayed in the list.
5. The analysis system according to any one of claims 1 to 4, wherein the feature extraction unit calculates correlations of the plurality of pieces of correlation data, and extracts information on the pieces of correlation data for which the calculated correlations are equal to or greater than a third threshold.
6. The analysis system according to claim 5, wherein the output unit displays a distribution map of a plurality of associated data whose correlation is equal to or higher than the third threshold value.
7. The analysis system according to claim 5, wherein the output unit displays a plurality of profiles of the plurality of associated data, and highlights the profile of the plurality of associated data having a correlation equal to or higher than the third threshold.
8. The analysis system according to any one of claims 5 to 7, wherein,
The associated data is time-varying data,
The feature extraction unit calculates correlations of a plurality of pieces of associated data in a predetermined time interval.
9. The analytical system of claim 8, wherein the specified time interval is variable.
10. The analysis system according to claim 8 or 9, wherein the feature extraction unit calculates a correlation of a plurality of pieces of associated data in each of a plurality of cells included in the predetermined time interval.
11. The analysis system according to any one of claims 8to 10, wherein the output unit graphically displays a time-dependent change in the plurality of associated data having a correlation equal to or greater than the third threshold value.
12. The analysis system according to any one of claims 1 to 11, wherein the data acquisition unit acquires, as the correlation data, information on a mass concentration of the granular material and information on an element contained in the granular material.
13. The analytical system of claim 12, wherein the analytical system comprises,
The data acquisition unit acquires the wind direction of the portion where the particulate matter is collected as the associated data,
The feature extraction unit extracts, from the associated data of a specific wind direction, the associated data that an instantaneous value of a content of an element contained in the particulate matter exceeds a first threshold value or that an average value or a median value of a content of an element contained in the particulate matter exceeds a second threshold value.
14. The analysis system according to any one of claims 1 to 13, wherein,
The data acquisition unit acquires information on the particle size of the particulate matter as the associated data,
The feature extraction unit extracts, from the associated data, the associated data in which the particulate matter has a predetermined particle size range.
15. The analytical system according to any one of claims 1 to 14, wherein,
The data acquisition unit acquires data relating to the gas at the portion where the particulate matter is collected as the associated data,
The feature extraction unit extracts the associated data in which the gas is a predetermined type of gas from the associated data.
16. The analytical system according to any one of claims 1 to 15, wherein,
The data acquisition unit acquires data relating to a wind speed of a portion where the particulate matter is collected as the associated data,
The feature extraction unit extracts, from the associated data, the associated data in which the wind speed exceeds a predetermined threshold value or is equal to or less than a predetermined threshold value.
17. The analysis system according to any one of claims 1 to 16, wherein the output unit generates an alarm when the associated data satisfying a predetermined index is extracted for a predetermined feature from the associated data by the feature extraction unit.
18. A server for acquiring and analyzing associated data related to particulate matter, the server comprising:
A feature extraction unit that extracts features included in the associated data by performing a predetermined feature extraction process that takes the associated data as an input; and
And an output unit configured to output information associated with the feature extracted by the feature extraction unit.
19. An analysis method for a particulate matter, comprising:
a step of acquiring correlation data concerning the particulate matter;
A step of extracting a feature included in the associated data by performing a predetermined feature extraction process that takes the associated data as an input; and
Outputting information associated with the extracted feature.
20. A program for causing a computer to execute an analysis method, the analysis method comprising:
A step of acquiring correlation data concerning the particulate matter;
A step of extracting a feature included in the associated data by performing a predetermined feature extraction process that takes the associated data as an input; and
Outputting information associated with the extracted feature.
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021-196752 | 2021-12-03 | ||
| JP2022069773 | 2022-04-20 | ||
| JP2022-069773 | 2022-04-20 | ||
| PCT/JP2022/043916 WO2023100854A1 (en) | 2021-12-03 | 2022-11-29 | Analysis system, server, analysis method, and program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118339457A true CN118339457A (en) | 2024-07-12 |
Family
ID=91782788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202280079402.8A Pending CN118339457A (en) | 2021-12-03 | 2022-11-29 | Analysis system, server, analysis method, and program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118339457A (en) |
-
2022
- 2022-11-29 CN CN202280079402.8A patent/CN118339457A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Steffen et al. | A comparison of data quality control protocols for atmospheric mercury speciation measurements | |
| Angot et al. | A 2-year record of atmospheric mercury species at a background Southern Hemisphere station on Amsterdam Island | |
| Shuttleworth et al. | Assessment of lead contamination in peatlands using field portable XRF | |
| Zhang et al. | A synthesis of research needs for improving the understanding of atmospheric mercury cycling | |
| Debevec et al. | Origin and variability in volatile organic compounds observed at an Eastern Mediterranean background site (Cyprus) | |
| Perrino et al. | Influence of natural events on the concentration and composition of atmospheric particulate matter | |
| CN110088604B (en) | Analysis device, analysis system, analysis method, and storage medium | |
| CN114424058A (en) | Tracing method for VOCs pollution | |
| Gustin et al. | Comparison of 4 methods for measurement of reactive, gaseous oxidized, and particulate bound mercury | |
| McDonnell et al. | A new method for the estimation of sinking particle fluxes from measurements of the particle size distribution, average sinking velocity, and carbon content | |
| Chappuis et al. | Automatic pollen monitoring: first insights from hourly data | |
| CN105469224A (en) | Odor pollution source key odor causing substance recognition method | |
| CN114062649B (en) | Soil pollution trend analysis method | |
| Cuccia et al. | An alternative way to determine the size distribution of airborne particulate matter | |
| Boltersdorf et al. | Lichens as a useful mapping tool?—an approach to assess atmospheric N loads in Germany by total N content and stable isotope signature | |
| Cangialosi et al. | On line monitoring of odour nuisance at a sanitary landfill for non-hazardous waste | |
| CN117875573B (en) | Water environment evaluation method and system based on biotoxicity and bioavailability | |
| CN114199856A (en) | Method for rapidly calibrating element content ratio of laser-induced breakdown spectroscopy | |
| Badicu et al. | PMs concentration forecasting using ARIMA algorithm | |
| RU2413220C1 (en) | Method for environmental monitoring of hazardous production facilities | |
| CN118393097A (en) | Groundwater pollution site risk assessment system | |
| Li et al. | Direct measurements of methane emissions from key facilities in Alberta's oil and gas supply chain | |
| CN113590663A (en) | Environment detection method and system | |
| CN118339457A (en) | Analysis system, server, analysis method, and program | |
| WO2023100854A1 (en) | Analysis system, server, analysis method, and program |
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 |