CN114398988A - Detection method and system of natural gas energy metering point detection device - Google Patents
Detection method and system of natural gas energy metering point detection device Download PDFInfo
- Publication number
- CN114398988A CN114398988A CN202210045109.1A CN202210045109A CN114398988A CN 114398988 A CN114398988 A CN 114398988A CN 202210045109 A CN202210045109 A CN 202210045109A CN 114398988 A CN114398988 A CN 114398988A
- Authority
- CN
- China
- Prior art keywords
- detection data
- detection
- data set
- sub
- vector
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 496
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 title claims abstract description 204
- 239000003345 natural gas Substances 0.000 title claims abstract description 93
- 230000005856 abnormality Effects 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims description 94
- 230000002159 abnormal effect Effects 0.000 claims description 61
- 238000000034 method Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 27
- 238000007689 inspection Methods 0.000 claims description 14
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 16
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 16
- 239000007789 gas Substances 0.000 description 14
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000012937 correction Methods 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 9
- 239000004215 Carbon black (E152) Substances 0.000 description 8
- UCKMPCXJQFINFW-UHFFFAOYSA-N Sulphide Chemical compound [S-2] UCKMPCXJQFINFW-UHFFFAOYSA-N 0.000 description 8
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 8
- 229910002092 carbon dioxide Inorganic materials 0.000 description 8
- 239000001569 carbon dioxide Substances 0.000 description 8
- 229930195733 hydrocarbon Natural products 0.000 description 8
- 150000002430 hydrocarbons Chemical group 0.000 description 8
- 229910052757 nitrogen Inorganic materials 0.000 description 8
- 239000001301 oxygen Substances 0.000 description 8
- 229910052760 oxygen Inorganic materials 0.000 description 8
- 239000000126 substance Substances 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the specification provides a detection method and a detection system for a natural gas energy metering point detection device, and the detection method and the detection system comprise the following steps: acquiring a first detection data set acquired by a detection device arranged at a natural gas energy metering point; and determining whether the detection device has an abnormality or not based on the first detection data set and the first historical detection data set.
Description
Technical Field
The specification relates to the field of gas detection, in particular to a detection method and a detection system of a natural gas energy metering point detection device.
Background
With the increasing frequency of natural gas used by human beings, the requirements on a detection device of the natural gas are increased, but no matter how good the detection device is, the detection device cannot be always prevented from being damaged.
Accordingly, it is desirable to provide a method and system for detecting a natural gas energy metering point detection device to determine whether there is an anomaly in the natural gas energy metering point detection device.
Disclosure of Invention
One of the embodiments of the present specification provides a detection method for a natural gas energy metering point detection device, where the method includes: acquiring a first detection data set acquired by a detection device arranged at a natural gas energy metering point; and determining whether the detection device has an abnormality or not based on the first detection data set and a first historical detection data set.
One of the embodiments of the present specification provides a detection system of a natural gas energy metering point detection device, where the system includes: the acquisition module is used for acquiring a first detection data set acquired by a detection device arranged at a natural gas energy metering point; and the determining module is used for determining whether the detection device has an abnormality or not based on the first detection data set and the first historical detection data set.
One of the embodiments of the present disclosure provides a detection device for a natural gas energy metering point detection device, including a processor, where the processor is configured to execute the detection method for the natural gas energy metering point detection device in any one of the embodiments.
One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions, which when executed by a processor, implement the detection method of the natural gas energy metering point detection apparatus described in any one of the above embodiments.
Drawings
The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
FIG. 1 is a schematic diagram of an application scenario of a detection system of a natural gas energy metering point detection apparatus according to some embodiments of the present description;
FIG. 2 is an exemplary block diagram of a detection system of a natural gas energy meter point detection device according to some embodiments described herein;
FIG. 3 is an exemplary flow diagram of a detection method of a natural gas energy meter point detection device according to some embodiments described herein;
FIG. 4 is a schematic diagram illustrating a determination of whether an anomaly exists in a detection device according to some embodiments of the present description;
FIG. 5 is another schematic diagram illustrating a determination of whether an anomaly exists in a detection device according to some embodiments of the present description;
fig. 6 is an exemplary flow chart illustrating correction of detection data of an abnormality detection device according to some embodiments of the present description.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Fig. 1 is a schematic view of an application scenario of a detection system of a natural gas energy metering point detection device according to some embodiments of the present disclosure.
As shown in fig. 1, an application scenario 100 according to an embodiment of the present disclosure may include at least a processing device 110, a network 120, a storage device 130, a detection apparatus 140, and a user terminal 150.
The processing device 110 may be used to process data and/or information from at least one component of the application scenario 100 or an external data source (e.g., a cloud data center). Processing device 110 may access data and/or information from storage device 130, detection apparatus 140, and user terminal 150 via network 120. The processing device 110 may be directly connected to the storage device 130, the detection apparatus 140 and the user terminal 150 to access information and/or data. For example, the processing device 110 may acquire detection data and/or information from the detection apparatus 140 and process the acquired data and/or information. For example, the processing device 110 may determine whether an anomaly exists in the detection apparatus based on the acquired data and/or information. In some embodiments, the processing device 110 may be a single processing device or a group of processing devices. The processing device 110 may be local, remote. The processing device 110 may be implemented on a cloud platform.
The network 120 may include any suitable network that provides information and/or data exchange capable of facilitating the application scenario 100. In some embodiments, information and/or data may be exchanged between one or more components of the application scenario 100 (e.g., the processing device 110, the storage device 130, the detection apparatus 140, and the user terminal 150) via the network 120. Network 120 may include a Local Area Network (LAN), a Wide Area Network (WAN), a wired network, a wireless network, and the like, or any combination thereof. In some embodiments, the network 120 may be any one or more of a wired network or a wireless network. In some embodiments, network 120 may include one or more network access points. For example, the network 120 may include wired or wireless network access points, such as base stations and/or network switching points, through which one or more components of the application scenario 100 may connect to the network 120 to exchange data and/or information.
The detection device 140 may be a device for acquiring data information related to the detection of the natural gas, which is disposed at the energy metering point of the natural gas. In some embodiments, the detection device 140 may detect flow rates, temperatures, pressures, compositions, concentrations, contents, flow rates, compression factors, densities, and heat generation of natural gas, including but not limited to. In some embodiments, the detection apparatus 140 may send the collected gas related data information to other components of the application scenario 100 (e.g., the processing device 110) or other components outside of the application scenario 100 (e.g., a gas toll station) via the network 120. In some embodiments, the detection device 140 may include one or more data detection units to detect different parameters of the natural gas, respectively. For example, the detection device 140 may include a temperature sensor 140-1, a pressure sensor 140-2, and other data detection units, etc.
Terminal 150 may refer to one or more terminal devices or software used by a user. In some embodiments, the terminal 150 may include a mobile device 150-1, a tablet 150-2, a laptop 150-3, or the like, or any combination thereof. In some embodiments, a user may interact with other components in the application scenario 100 through the terminal 150. For example, the user may receive first detection data detected by the detection device 140 through the terminal 150. In some embodiments, the user may control other components of the application scenario 100 through the terminal 150. For example, the user may control the detection device 140 to detect the relevant parameters of the natural gas energy metering point through the terminal 150. In some embodiments, a user may obtain the status of the natural gas energy metering point detection device through the terminal 150.
FIG. 2 is an exemplary block diagram of a detection system of a natural gas energy meter point detection device according to some embodiments described herein.
In some embodiments, the detection system 200 of the natural gas energy metering point detection device may include an acquisition module 210 and a determination module 220.
In some embodiments, the acquisition module 210 may be configured to acquire a first set of detection data acquired by a detection device disposed at a natural gas energy metering point. For more details on the natural gas energy metering point, the detection device and the first detection data set, reference is made to fig. 3 and the related description thereof, and details are not repeated here.
In some embodiments, the determination module 220 may be configured to determine whether an anomaly exists in the detection device based on the first set of detection data and the first set of historical detection data. For the first historical detection data set and the manner of determining whether there is an abnormality in the detection apparatus, refer to fig. 3 and its related description, which are not repeated herein.
In some embodiments, the detection system 200 of the natural gas energy metering point detection device may further include a correction module 230. The modification module 230 may obtain abnormal sub-detection data corresponding to the abnormal data detection unit in the first detection data set; correcting the abnormal sub-detection data based on the first detection data set to obtain corrected detection data; and obtaining a target detection data set based on the corrected detection data and the first detection data set. For more about the abnormal data detection unit, refer to fig. 4 and the related description thereof, and for more about the abnormal sub-detection data, the corrected detection data, and the target detection data set, refer to fig. 6 and the related description thereof, which are not repeated herein.
It should be noted that the above description of the modules is for convenience only and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the system, any combination of modules or sub-system configurations can be used to connect to other modules without departing from such teachings. In some embodiments, the obtaining module 210 and the determining module 220 disclosed in fig. 2 may be different modules in a system, or may be a module that implements the functions of two or more modules described above. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.
Fig. 3 is an exemplary flow diagram of a detection method of a natural gas energy meter point detection device according to some embodiments described herein. In some embodiments, flow 300 may be performed by processing device 110. As shown in fig. 3, the process 300 may include the following steps:
step 310, a first detection data set collected by a detection device arranged at a natural gas energy metering point is obtained. In some embodiments, step 310 may be performed by acquisition module 210.
The natural gas energy metering point may refer to a detection point where natural gas is measured. The units of attribution of the natural gas energy metering points can be divided in advance. For example, natural gas energy metering points in cells. As another example, a natural gas energy metering point in units of households. In some embodiments, one or more components of the natural gas at the natural gas energy metering point may be detected by the detection device. Such as methane in natural gas. In some embodiments, one or more properties in the natural gas at the natural gas energy metering point may also be detected by the detection device. Such as the temperature of natural gas. The processing device 110 may bill the energy of the natural gas based on the aforementioned detected data.
The detection device can be a device which is arranged at the energy metering point of the natural gas and is used for detecting various parameters of the natural gas. In some embodiments, the detection device may include a plurality of data detection units, each of which may detect a different parameter of the natural gas. For example, the detection means may include one or more of a gas chromatograph for detecting components of natural gas, a gas sensor for detecting concentrations of components in natural gas, a temperature sensor for detecting a temperature of natural gas, a pressure sensor for detecting a pressure of natural gas, and the like.
The first set of detection data may be a set of natural gas related data detected by the detection device. For example, a set of data based on data of each parameter acquired by the detection device each time. As another example, the parameters of the natural gas (e.g., natural gas composition, concentration of the components, natural gas temperature, natural gas pressure, etc.) detected during the past week of the natural gas energy metering point may be packaged into a data set. In some embodiments, the first detection data set may include sub-detection data respectively collected by at least two data detection units in the detection apparatus. For example, the detection means comprises a gas chromatograph, a temperature sensor and a pressure sensor, and correspondingly, the first detection data set may comprise a natural gas composition, a natural gas temperature and a natural gas pressure.
The sub-detection data may be data detected by the data detection unit. One or more sub-detection data may be included in the first detection data set. For example, the first detection data set may include three kinds of seed detection data, which are a natural gas component detected by a gas chromatograph in the detection apparatus, a temperature of the natural gas detected by a temperature sensor, and a pressure of the natural gas detected by a pressure sensor.
The first set of historical detection data may be a set of data relating to natural gas detected by the detection device over a past period of time.
In some embodiments, the first set of historical detection data may be a first set of detection data for the same gas energy metering point over a past period of time. For example, the first historical detection data set may be a first detection data set of the same natural gas energy metering point detected by the detection device within the past week. In some embodiments, the first historical detection data set may also be a set of natural gas detection data for a plurality of sets of natural gas energy metering points including the natural gas energy metering point during the elapsed time period. For example, the gas energy metering point is a family, and the first historical detection data set may be a set of gas detection data of all gas energy metering points in a cell including the family in the past week. In some embodiments, the first set of historical detection data may also be a set of natural gas detection data for other one or more natural gas energy metering points over a past time period. For example, the gas energy metering point is a family, and the first historical detection data set may be a set of gas detection data of all gas energy metering points in a cell except the family within a past week. In some embodiments, the first set of historical detection data may be obtained from historical data of detection devices distributed at various points of the natural gas energy meter. In some embodiments, the first set of historical detection data may also be obtained in other ways, for example, over a network.
It should be understood that it is necessary to determine whether there is an abnormality in the detection apparatus corresponding to the first detection data set based on the first historical detection data set, and therefore the detection apparatus corresponding to the first historical detection data set should be a normal detection apparatus, and the data in the first historical detection data set should be normal detection data. In some embodiments, normal detection data may be determined in a variety of ways. For example, by manual screening.
In some embodiments, the processing device 110 may determine whether the detection apparatus is abnormal by modeling or performing analysis processing on the first historical detection data set and the first detection data by using various data analysis algorithms, such as regression analysis, discriminant analysis, and the like. In some embodiments, the first set of historical detection data may be one or more.
In some embodiments, the processing device 110 may process the first historical detection data set through a clustering algorithm and analyze the first detection data set in conjunction therewith to determine whether the detection device is abnormal. For more details about processing the first historical detection data set by the clustering algorithm, and analyzing in combination with the first detection data set to determine whether the detection device is abnormal, refer to fig. 4 and 5 and the related description thereof, and details thereof are not repeated here.
Some embodiments of this specification determine whether the detection device is abnormal through the first historical detection data and the first detection data of the natural gas energy metering point, avoid detecting the detection device specially, save detection time, and thus can make the natural gas energy metering point more accurate when energy is being priced.
FIG. 4 is a schematic diagram illustrating a determination of whether an anomaly exists in a detection device according to some embodiments of the present description. In some embodiments, the flow 400 may be performed by the determination module 220. As shown in fig. 4, the process 400 may include the following steps:
In some embodiments, a first set of historical detection data based on a first set of historical detection data may constitute a first set of historical detection data feature vector. The elements of the feature vector of the first set of historical detection data may correspond to the first set of historical detection data. The plurality of feature vectors of the first historical detection data set may correspond to the plurality of first historical detection data sets, respectively. In some embodiments, the elements in the feature vector of the first set of historical detection data may correspond to the content of the component in the natural gas and/or the value of the parameter in the first set of historical detection data. For example, the feature vector of the first historical detection data set may be (a, b, c, d, e, f, g), where a-g may represent seven kinds of detection data related to natural gas in the first historical detection data set, and illustratively, a represents a methane concentration, b represents a hydrocarbon concentration, c represents a nitrogen concentration, d represents an oxygen concentration, e represents a carbon dioxide concentration, f represents a sulfide concentration, and g represents a concentration of other substances. For another example, the first historical sensed data set feature vector may further include h representing temperature, i representing pressure, and the like, and finally the first historical sensed data set feature vector (a, b, c, d, e, f, g, h, i) may be constructed. The elements in the feature vector of the first set of historical detection data may also include other detection data, and the feature vector of the first set of historical detection data may be constructed in a manner similar to that described above.
In some embodiments, the values of the elements in the feature vector of the first set of historical detection data may be actual detection values. In other embodiments, the actual detection values may be classified according to a preset correspondence, and the classified values are used as values of elements in the feature vector of the first historical detection data set. For example, 90% -91% is represented by 1, 91% -92% is represented by 2, and so forth.
In some embodiments, the determining module 220 may cluster the feature vectors of the first historical detection data set by a clustering algorithm to determine a first set of cluster centers, where the first set of cluster centers may include one or more cluster centers. For example, the first history detection vector may be clustered by a clustering algorithm to obtain a first cluster center set, where the first cluster center set may include cluster centers I and II.
The determination module 220 may cluster the plurality of first sets of historical detection data based on the type of natural gas and/or the supply region of the natural gas, and the like. Types of clustering algorithms may include, but are not limited to, K-Means clustering and/or density-based clustering methods (DBSCAN), among others.
The first vector may be a feature vector corresponding to the first detection data set. Elements of the first vector may correspond to a first set of detection data. For example, the first vector may be (a)1,b1,c1,d1,e1,f1,g1) Wherein a is1-g1Can respectively represent seven kinds of detection data related to natural gas in the first detection data set, and exemplarily, a1Represents the concentration of methane, b1Represents the concentration of hydrocarbon, c1Represents the nitrogen concentration, d1Represents the oxygen concentration, e1Representing the concentration of carbon dioxide, f1Represents the sulfide concentration, g1Representing the concentration of other substances. The determination method of the first vector is similar to that of the feature vector of the first historical detection data set, and for more details of the first vector, reference is made to the relevant portion of the feature vector of the first historical detection data set, and details are not repeated here.
The first target cluster center may refer to a cluster center of the first set of cluster centers that is closest to the first vector. In some embodiments, a distance between the first vector and each cluster center in the first set of cluster centers may be calculated, and a cluster center corresponding to the shortest distance may be determined as the first target cluster center. For example, by calculating the distance of the first vector from each cluster center in the first set of cluster centers, the first target cluster center having the shortest distance from the first vector is (A)1,B1,C1,D1,E1,F1,G1). Methods of calculating distance may include, but are not limited to, Euclidean distance, cosine distance, Mahalanobis distance, Chebyshev distance, and/or Manhattan distance, among others.
The first distance may refer to a vector distance of the first vector from a center of the first target cluster. The manner of obtaining the first distance may include, but is not limited to, calculation by algorithms such as euclidean distance, cosine distance, mahalanobis distance, chebyshev distance, and/or manhattan distance.
In some embodiments, the determining module 220 may compare the first distance with a first threshold and determine whether the detection device has an abnormality based on the comparison result. The first threshold value may be determined based on actual experience of the user in detecting the detection means. In some embodiments, if the first distance is greater than a first threshold, determining that an anomaly exists in the detection device; and if the first distance is smaller than or equal to the first threshold value, determining that the detection device is normal.
In some embodiments, in order to obtain a more specific detection result, the sub-detection data in the first detection data set may be further analyzed to further determine an abnormal data detection unit in the abnormal detection device. In some embodiments, the sub-detection data in the first detection data set is analyzed and processed, and the abnormal data detection unit in the detection device for determining the specific abnormality further may perform the following steps for each sub-detection data in the first detection data set:
The second vector may be a feature vector corresponding to the first detection data set from which a certain sub-detection data is removed, and may be used to represent the first detection data set from which a certain sub-detection data is removed. In some embodiments, for a certain sub-detection data, a first vector with elements corresponding to the sub-detection data removed may be used as a second vector. For example, the first vector may be (a)1,b1,c1,d1,e1,f1,g1) The vector a corresponding to the methane concentration in the first vector can be eliminated1The second vector obtained is (b)1,c1,d1,e1,f1,g1)。
The second target cluster center may be a cluster center from which a vector corresponding to a sub-detection data in the first target cluster center is removed. For example, the first target cluster center may be (A)1,B1,C1,D1,E1,F1,G1) Element A corresponding to the concentration of methane in the first target cluster can be removed1The obtained second target clustering center is (B)1,C1,D1,E1,F1,G1)。
The abnormal data detecting unit may be a data detecting unit that detects the presence of an abnormality in the apparatus. In some embodiments, the processing device 110 may calculate a second distance between the second vector and the second target cluster center, compare the second distance with a second threshold, and determine whether the data detection unit corresponding to the pruned sub-detection data is an abnormal data detection unit based on the comparison result. The value of the second threshold may be determined according to actual experience of the user in detecting the detection device. In some embodiments, if the second distance is greater than the second threshold, determining that the data detection unit is an abnormal data detection unit; and if the second distance is smaller than or equal to the second threshold value, determining that the data detection unit is normal.
In some embodiments, steps 450-470 may be performed on each of the sub-detection data in the first detection data set to determine whether each of the data detection units in the detection apparatus is an abnormal data detection unit.
It should be understood that, the distance between the first vector formed by the sub-detection data acquired by the normal data detection unit and the first target cluster center should be within a corresponding normal error range (e.g., a first threshold), and when the detected data unit is abnormal, the distance between the first vector formed finally and the first target cluster center may exceed the normal error range due to the fact that the sub-detection data acquired by the detected data unit is also abnormal. Similarly, when the sub-detection data in the second vector obtained by removing a certain sub-detection data is normal sub-detection data, the distance between the second vector and the second target clustering center should also be within the corresponding normal error range, and when the distance between the second vector and the second target clustering center is not within the normal error range, it indicates that the sub-detection data in the second vector has abnormal sub-detection data. Therefore, when the distance between the second vector and the second target cluster center is recovered to the corresponding normal error range (e.g., the second threshold) after the element corresponding to a certain sub-detection data is removed, it indicates that the removed sub-detection data is abnormal sub-detection data, and the corresponding data detection unit is an abnormal data detection unit. Meanwhile, by eliminating and processing certain sub-detection data one by one, all abnormal data detection units in the detection device can be confirmed through the processing result.
Some embodiments of the present description determine a first set of cluster centers by clustering a first set of historical detection data; determining a first vector corresponding to the first detection data set based on the first detection data set; then, determining a first target clustering center based on the first vector and the first clustering center set; and finally, determining whether the detection device is abnormal or not based on the first distance between the first vector and the first target clustering center, thereby further improving the detection accuracy. In addition, some embodiments of the present description further determine a specific abnormal data detection unit in the detection device having an abnormality by processing the sub-detection data, so as to facilitate subsequent maintenance only for the specific abnormal data detection unit, reduce maintenance difficulty and cost, and improve efficiency.
FIG. 5 is a schematic diagram illustrating a determination of whether an anomaly exists in a detection device according to some embodiments of the present description. In some embodiments, flow 500 may be performed by determination module 220. As shown in fig. 5, the data flow 500 may include the following steps:
in some embodiments, the following steps may be performed for each sub-detection data in the first detection data set:
The second historical detection data set may be a data set from which data corresponding to a certain sub-detection data in the first historical detection data set is removed. For example, a first set of historical detection data may include methane concentration, hydrocarbon concentration, nitrogen concentration, oxygen concentration, carbon dioxide concentration, sulfide concentration, and concentrations of other substances, the methane concentration in the first set of historical detection data may be eliminated, and a resulting second set of historical detection data may include hydrocarbon concentration, nitrogen concentration, oxygen concentration, carbon dioxide concentration, sulfide concentration, and concentrations of other substances.
In some embodiments, a second set of historical detection data based on a second set of historical detection data may constitute a second set of historical detection data feature vector. The feature vectors of the second historical detection data sets may correspond to the second historical detection data sets, respectively. In some embodiments, the elements in the feature vector of the second set of historical detection data may correspond to the content of the component in the natural gas and/or the value of the parameter in the second set of historical detection data. For example, the feature vector of the second historical detection data set may be (b, c, d, e, f, g), where b-g may represent six detection data related to natural gas in the second historical detection data set, and illustratively, b represents hydrocarbon concentration, c represents nitrogen concentration, d represents oxygen concentration, e represents carbon dioxide concentration, f represents sulfide concentration, and g represents the concentration of other substances. Similar to the feature vector of the first historical detection data set, the elements in the feature vector of the second historical detection data set may also include other detection data.
In some embodiments, the determining module 220 may cluster the feature vectors of the second historical detection data set by a clustering algorithm to determine a second cluster center set, wherein the second cluster center set may include one or more cluster centers. The manner of clustering the second historical detection data set is similar to that of clustering the first historical detection data set, and further contents of the second historical detection data set and the second cluster center set refer to fig. 4 and the related description thereof, which are not repeated herein.
The second detection data set may be a data set from which a certain sub-detection data in the first detection data set is removed. For example, a first set of sensed data may include methane concentration, hydrocarbon concentration, nitrogen concentration, oxygen concentration, carbon dioxide concentration, sulfide concentration, and concentrations of other substances, the methane concentration in the first set of sensed data may be rejected, and a second set of sensed data may be obtained that includes hydrocarbon concentration, nitrogen concentration, oxygen concentration, carbon dioxide concentration, sulfide concentration, and concentrations of other substances.
The third vector may be a feature vector corresponding to the second set of detection data. The elements of the third vector may correspond to the second set of detection data. For example, the third vector may be (b)3,c3,d3,e3,f3,g3) Wherein a is3-g3Can represent six kinds of detection data related to the natural gas parameter in the second detection data set respectively, and exemplarily, b3Represents the concentration of hydrocarbon, c3Represents the nitrogen concentration, d3Represents the oxygen concentration, e3Representing the concentration of carbon dioxide, f3Represents the sulfide concentration, g3Representing the concentration of other substances. The determination method of the third vector is similar to that of the feature vector of the first historical detection data set, and for more details of the third vector, reference is made to the relevant part of the feature vector of the first historical detection data set, and details are not repeated here.
The third target cluster center may refer to a cluster center of the second set of cluster centers that is closest to the third vector. In some embodiments, a distance between the third vector and each cluster center in the second cluster center set may be calculated, and a cluster center corresponding to the shortest distance may be determined as the third target cluster center. For example, by calculating the distance of the third vector from each cluster center in the second cluster center set, the third target cluster center having the shortest distance from the third vector is (B)3,C3,D3,E3,F3,G3). Methods of calculating distance may include, but are not limited to, Euclidean distance, cosine distance, Mahalanobis distance, Chebyshev distance, and/or Manhattan distance, among others.
And step 560, determining whether the data detection unit corresponding to the sub-detection data is an abnormal data detection unit based on a third distance between the third vector and the third target cluster center.
The third distance may refer to a vector distance of the third vector from a center of the third target cluster. The manner of obtaining the third distance may include, but is not limited to, calculation by algorithms such as euclidean distance, cosine distance, mahalanobis distance, chebyshev distance, and/or manhattan distance.
In some embodiments, the determining module 220 may compare the third distance with a third threshold, and determine whether the data detection unit corresponding to the sub-detection data is an abnormal data detection unit based on the comparison result. The third threshold value may be determined based on actual experience of the user in detecting the data detection unit in the detection apparatus. In some embodiments, if the third distance is greater than the third threshold, determining that the data detection unit corresponding to the sub-detection data is an abnormal data detection unit; and if the third distance is smaller than or equal to the third threshold, determining that the data detection unit corresponding to the sub-detection data is normal.
Some embodiments of the present description respectively obtain a second historical detection data set and a second detection data set by removing sub-detection data in the first historical detection data set and the first detection data set; determining a third vector corresponding to the second detection data set based on the second detection data set; determining a third target clustering center based on the third vector and the second clustering center set; and determining whether the data detection unit corresponding to the sub-detection data is an abnormal data detection unit or not based on the third distance between the third vector and the third target clustering center, so that the whole detection device is prevented from being judged, and abnormal data in the detection device can be rapidly and accurately determined for later maintenance and processing.
FIG. 6 is an exemplary flow diagram illustrating a modification of a first set of detection data for the presence of anomaly detection data according to some embodiments of the present description. In some embodiments, the flow 600 may be performed by the modification module 230. As shown in fig. 6, the process 600 may include the following steps:
step 610, obtaining abnormal sub-detection data corresponding to the abnormal data detection unit in the first detection data set.
The abnormal sub-detection data may refer to sub-detection data in which an abnormality exists in the first detection data set.
In some embodiments, the anomaly sub-detection data may be determined based on the anomaly data detection unit. The sub detection data corresponding to the abnormal data detection unit may be determined as abnormal sub detection data. For more about the abnormal data detection unit, refer to fig. 4 and fig. 5 and the related description thereof, which are not repeated herein.
And step 620, correcting the abnormal sub-detection data based on the first detection data set to obtain corrected detection data.
The corrected detection data may refer to the abnormal sub-detection data after being corrected. For example, the abnormal sub-detection data is corrected to the normal range.
In some embodiments, modeling may be performed or various data analysis algorithms, such as regression analysis, discriminant analysis, and the like, may be used to analyze the first detection data set with the abnormal sub-detection data, so as to obtain modified detection data corresponding to the abnormal sub-detection data.
In some embodiments, the corrected detection data may be obtained by means of fitting. For example, the first historical detection data set may be fitted to obtain a fitting function between various types of detection data in the first detection data set. And correcting the abnormal sub-detection data based on the fitting function to obtain corrected detection data. The manner of fitting may include, but is not limited to, linear fitting, non-linear fitting, least squares fitting, and the like.
In some embodiments, abnormal sub-detection data in the first detection data set can be eliminated to obtain a third detection data set
The third detection data set may refer to a detection data set obtained by removing all abnormal sub-detection data in the first detection data set. For example, if the temperature sensor in the detection device is an abnormal data unit, the temperature data in the first detection data set may be eliminated to obtain a third detection data set.
In some embodiments, the third set of inspection data may be processed based on the modified model to determine modified inspection data.
The corrected detection data is detection data obtained by correcting the abnormal sub-detection data. The type of data in the modified detected data may correspond to the type of abnormal sub-detected data. For example, when the anomaly detection data is temperature data, the corrected detection data may be corrected temperature data. For another example, when the abnormality sub-detection data includes temperature data and pressure data, the correction detection data may include corrected temperature data and pressure data.
In some embodiments, the third set of inspection data may be input to the rework model and output as rework inspection data.
In some embodiments, the modified model may be trained based on a plurality of first sets of historical inspection data. For more details on the first historical detection data set, refer to fig. 3 and its related description, which are not repeated herein. In some embodiments, the first historical detection data set after the at least one sub-detection data is rejected may be used as a training sample, and the identification of the training sample may be the at least one rejected sub-detection data. Inputting a plurality of training samples with identifications into the initial correction model, updating parameters of the initial correction model through training, and when the trained model meets preset conditions, finishing the training to obtain the trained correction model. In some embodiments, the modified model may include, but is not limited to, a support vector machine model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a neural network model, and the like.
In some embodiments, the modified model may also be trained by masking. Specifically, a sample mask feature matrix may be constructed: firstly, constructing a sample initial matrix based on a first historical detection data set, wherein each vector in the matrix represents the type of detection data (such as components, temperature or pressure of natural gas) and can be subjected to barrel separation to obtain a corresponding vector; then, masking different types of detection data in the sample initial matrix to obtain a sample mask feature matrix; and training as a training sample based on the sample mask matrix and the corresponding label, wherein the label is the matrix obtained after mask recovery. In some embodiments, a mask matrix may be constructed based on a first detection data set including anomaly detection data, and the mask matrix may be used as an input of a correction model, and input into the correction model for processing and output as correction detection data.
Some embodiments of the present description determine the corrected detection data through the model, which may improve the accuracy of the corrected detection data, make the corrected abnormal sub-detection data more practical, and reduce the labor cost.
Step 630, a target detection data set is obtained based on the corrected detection data and the first detection data set.
The target detection data set may be the modified first detection data set. In some embodiments, all the abnormal sub-detection data in the first detection data set may be replaced with the corrected detection data, resulting in the target detection data set.
Some embodiments of the present description obtain the target detection data set by correcting the abnormal sub-detection data in the first detection data set, so that the target detection data set with normal detection data can be obtained even when the acquired first detection data set is abnormal, and thus energy pricing can be performed based on the target detection data set, and a pricing error is avoided.
The embodiment of the present specification further provides a detection device of a natural gas energy metering point detection device, which includes a processor, and the processor is configured to execute the detection method of the natural gas energy metering point detection device according to any one of the foregoing embodiments.
The present specification further provides a computer-readable storage medium, where the storage medium may store computer instructions, and when the computer reads the computer instructions in the storage medium, the computer implements the detection method of the natural gas energy metering point detection apparatus according to any one of the foregoing embodiments.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing processing device or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows
A change of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (10)
1. A detection method of a natural gas energy metering point detection device is characterized by comprising the following steps:
acquiring a first detection data set acquired by a detection device arranged at a natural gas energy metering point;
and determining whether the detection device has an abnormality or not based on the first detection data set and a first historical detection data set.
2. The method of claim 1, wherein the determining whether the detection device has an anomaly based on the first set of detection data and a first set of historical detection data comprises:
clustering the first historical detection data set, and determining a first clustering center set;
determining a first vector corresponding to the first detection data set based on the first detection data set;
determining a first target cluster center based on the first vector and the first set of cluster centers;
determining whether the detection device is abnormal based on a first distance between the first vector and the first target cluster center.
3. The method of claim 2, wherein the first set of inspection data includes sub-inspection data respectively acquired by at least two data inspection units in the inspection apparatus;
the method further comprises the following steps:
when the detection device has an abnormality, the following steps are executed for each sub-detection data in the first detection data set:
elements corresponding to the sub-detection data are removed from the first vector to obtain a second vector;
removing elements corresponding to the sub-detection data in the first target clustering center to obtain a second target clustering center;
and determining whether the data detection unit corresponding to the sub-detection data is an abnormal data detection unit or not based on the second vector and a second distance of the second target clustering center.
4. The method of claim 1, wherein the first set of inspection data includes sub-inspection data respectively acquired by at least two data inspection units in the inspection apparatus;
the determining whether the detection device has an anomaly based on the first detection data set and a first historical detection data set comprises:
performing the following steps for each of the sub-detection data in the first detection data set:
removing historical sub-detection data corresponding to the sub-detection data in the first historical detection data set to obtain a second historical detection data set;
determining a second cluster center set based on the second set of historical detection data;
removing the sub-detection data from the first detection data set to obtain a second detection data set;
determining a third vector corresponding to the second detection data set based on the second detection data set;
determining a third target cluster center based on the third vector and the second cluster center set;
and determining whether the data detection unit corresponding to the sub-detection data is an abnormal data detection unit or not based on a third distance between the third vector and the third target clustering center.
5. The method of claim 3 or 4, further comprising:
acquiring abnormal sub-detection data corresponding to the abnormal data detection unit in the first detection data set;
correcting the abnormal sub-detection data based on the first detection data set to obtain corrected detection data;
and obtaining a target detection data set based on the corrected detection data and the first detection data set.
6. The method of claim 5, wherein the modifying the abnormal sub-detection data based on the first detection data set to obtain modified detection data comprises:
rejecting the abnormal sub-detection data in the first detection data set to obtain a third detection data set;
processing the third detection data set based on a modified model to determine the modified detection data.
7. A detection system for a natural gas energy metering point detection device, the system comprising:
the acquisition module is used for acquiring a first detection data set acquired by a detection device arranged at a natural gas energy metering point;
and the determining module is used for determining whether the detection device has an abnormality or not based on the first detection data set and the first historical detection data set.
8. The method of claim 7, wherein the determination module is further to:
clustering the first historical detection data set, and determining a first clustering center set;
determining a first vector corresponding to the first detection data set based on the first detection data set;
determining a first target cluster center based on the first vector and the first set of cluster centers;
determining whether the detection device is abnormal based on a first distance between the first vector and the first target cluster center.
9. A detection device of a natural gas energy metering point detection device comprises a processor, and is characterized in that the processor is used for executing the detection method of the natural gas energy metering point detection device according to any one of claims 1-6.
10. A computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer executes the detection method of the natural gas energy metering point detection device according to any one of claims 1 to 6.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045109.1A CN114398988A (en) | 2022-01-14 | 2022-01-14 | Detection method and system of natural gas energy metering point detection device |
| US17/649,343 US11562182B2 (en) | 2021-02-04 | 2022-01-28 | Methods and systems for detecting detection devices located at energy metering points of natural gas |
| US18/060,975 US11853398B2 (en) | 2021-02-04 | 2022-12-02 | Methods and systems for detecting detection devices located at energy metering points of natural gas preliminary class |
| US18/061,474 US11860978B2 (en) | 2021-02-04 | 2022-12-04 | Methods and systems for detecting detection devices located at energy metering points of natural gas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210045109.1A CN114398988A (en) | 2022-01-14 | 2022-01-14 | Detection method and system of natural gas energy metering point detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114398988A true CN114398988A (en) | 2022-04-26 |
Family
ID=81231153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210045109.1A Pending CN114398988A (en) | 2021-02-04 | 2022-01-14 | Detection method and system of natural gas energy metering point detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114398988A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110115669A1 (en) * | 2009-11-17 | 2011-05-19 | Topcon Positioning Systems, Inc. | Detection and Correction of Anomalous Measurements and Ambiguity Resolution in a Global ... |
| CN108614895A (en) * | 2018-05-10 | 2018-10-02 | 中国移动通信集团海南有限公司 | The recognition methods of abnormal data access behavior and data processing equipment |
| CN111612048A (en) * | 2020-04-30 | 2020-09-01 | 中国西安卫星测控中心 | Unsupervised clustering anomaly detection method |
| CN112650608A (en) * | 2020-12-28 | 2021-04-13 | 广州虎牙科技有限公司 | Abnormal root cause positioning method and related device and equipment |
-
2022
- 2022-01-14 CN CN202210045109.1A patent/CN114398988A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110115669A1 (en) * | 2009-11-17 | 2011-05-19 | Topcon Positioning Systems, Inc. | Detection and Correction of Anomalous Measurements and Ambiguity Resolution in a Global ... |
| CN108614895A (en) * | 2018-05-10 | 2018-10-02 | 中国移动通信集团海南有限公司 | The recognition methods of abnormal data access behavior and data processing equipment |
| CN111612048A (en) * | 2020-04-30 | 2020-09-01 | 中国西安卫星测控中心 | Unsupervised clustering anomaly detection method |
| CN112650608A (en) * | 2020-12-28 | 2021-04-13 | 广州虎牙科技有限公司 | Abnormal root cause positioning method and related device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deng et al. | Nonlinear process fault diagnosis based on serial principal component analysis | |
| US11860978B2 (en) | Methods and systems for detecting detection devices located at energy metering points of natural gas | |
| CN109740648B (en) | Method and device for identifying abnormal data of power load and computer equipment | |
| CN109799269A (en) | Electronic nose gas sensor array optimization method based on behavioral characteristics different degree | |
| CN111639304B (en) | CSTR fault positioning method based on Xgboost regression model | |
| CN112101635A (en) | Method and system for monitoring electricity utilization abnormity | |
| CN115936262B (en) | Yield prediction method, system and medium based on big data environment interference | |
| CN116485020B (en) | Supply chain risk identification early warning method, system and medium based on big data | |
| CN116453438A (en) | Display screen parameter detection method, device, equipment and storage medium | |
| CN115439003A (en) | Gas meter replacement prompting method and system based on intelligent gas Internet of things | |
| Kalinowski et al. | Efficiency of linear and non-linear classifiers for gas identification from electrocatalytic gas sensor | |
| Hassan et al. | Gas classification using binary decision tree classifier | |
| CN116308963A (en) | Government affair data analysis method and system | |
| Corcoran et al. | Optimal configuration of a thermally cycled gas sensor array with neural network pattern recognition | |
| CN117592656A (en) | Carbon footprint monitoring method and system based on carbon data accounting | |
| CN100370453C (en) | Rare-earth cascade extraction separation component content soft measuring method | |
| CN114398988A (en) | Detection method and system of natural gas energy metering point detection device | |
| CN115201394A (en) | Multi-component transformer oil chromatography online monitoring method and related device | |
| CN115222145A (en) | Driving range prediction method and system based on new energy automobile operation big data | |
| WO2018083720A1 (en) | Abnormality analysis method, program, and system | |
| CN113869373A (en) | Equipment abnormality detection method and device, computer equipment and storage medium | |
| CN112733903A (en) | Air quality monitoring and alarming method, system, device and medium based on SVM-RF-DT combination | |
| CN113139673A (en) | Method, device, terminal and storage medium for predicting air quality | |
| CN111553383A (en) | Data risk detection method, device and equipment | |
| Ren et al. | Fault detection and process monitoring of industrial process based on spherical kernel T-PLS |
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 |