CN113128590A - Equipment data optimization and fusion method - Google Patents
Equipment data optimization and fusion method Download PDFInfo
- Publication number
- CN113128590A CN113128590A CN202110419769.7A CN202110419769A CN113128590A CN 113128590 A CN113128590 A CN 113128590A CN 202110419769 A CN202110419769 A CN 202110419769A CN 113128590 A CN113128590 A CN 113128590A
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- monitoring
- time
- fusion
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a method for optimizing and fusing equipment data, which comprises the steps of firstly carrying out fitting duplication elimination, mean value interpolation and filtration through monitoring data automatically acquired by acquisition equipment, then carrying out quality judgment including error suspicious judgment, equipment distortion judgment, water level jump and data examination and correction, and finally storing the equipment data in a main storage and a standby storage. The method can solve the problems of inaccurate statistics caused by abnormal change of data monitoring periods or discontinuous data time axis in upper layer statistical analysis, inaccurate statistics caused by discontinuous data time axis in upper layer statistical analysis, and incapability of statistics or inaccurate statistics caused by repeated data and poor quality in upper layer statistical analysis.
Description
Technical Field
The invention relates to the technical field of data acquisition and fusion, in particular to a method for optimizing and fusing equipment data.
Background
With the development of big data technology, the basic level data acquisition also continuously advances automatic transformation, so that the traditional manual acquisition is gradually replaced by the data acquired by the automatic equipment, and the timeliness, real-time property and stability of data acquisition are enhanced to a great extent. However, there still exist some risks in automated acquisition, for example, in the hydrology field, uploading of device data is based on a network environment, and instability of the network environment may result in failure to upload the data, or data deviation or failure in acquisition devices due to device failure caused by some inefficacy factors, and these factors may result in failure to acquire complete and accurate data in time.
Aiming at the problems, the existing scheme is to add acquisition equipment, manually acquire and manually check. The increase of the acquisition equipment means that a plurality of pieces of equipment are added to the same observation station for monitoring simultaneously, so that risks are shared; the manual collection is to manually collect data on the spot; the manual review is to manually verify the uploaded data. However, even if monitoring equipment and monitoring modes are added, data abnormality or data loss of some stations still exists in a probability, manual acquisition has limitation, manpower is consumed, the timeliness of acquired data is far inferior to that of the acquired data acquired by automatic equipment, and manual acquisition is difficult to achieve in some special situations. Meanwhile, due to the scheme, multiple pieces of repeated data exist in the same observation station at the same monitoring time, data quality levels of different monitoring modes and data sources based on respective characteristic advantages are different, and random storage can affect data quality, so that inaccurate statistical analysis is caused. In the face of massive data, it is not accurate enough or practical to control the data quality only by manual review.
Based on the above problems, what is needed is a technology for collecting and fusing real-time data from multiple data sources in a distributed environment, so as to obtain real-time, stable, complete and accurate data.
Disclosure of Invention
The invention aims to provide a real-time data acquisition optimization and fusion method of multiple data sources in a distributed environment aiming at the defects of the prior art, and solves the problems that the existing basic level data acquisition method has data deviation and cannot acquire complete data under extreme conditions.
The purpose of the invention is realized by the following technical scheme: a method for optimizing and fusing equipment data comprises the following specific steps:
s1: through collection equipment automatic acquisition monitoring data, wherein data contain accumulative total data and instantaneous data two kinds, carry out the fitting deduplication to monitoring data, obtain the data that accords with monitoring cycle's law, specifically do: fitting the irregular data monitoring time to the regular data time of a certain monitoring period, and then removing the duplicate according to the main key;
and S2, performing mean interpolation on the accumulated data subjected to the fitting and de-weighting in the step S1, comparing each piece of real-time data acquired by the acquisition equipment with the latest data of the same monitoring frequency of the same observation station equipment in the fusion library, and performing mean interpolation on each missing time threshold T for the real-time data with the time difference larger than a certain time threshold T. The calculation method is as follows:
N＝(TM2-TM1)/T
P＝(P2-P1)/N
in the formula, P2 and TM2 are currently acquired real-time accumulated data and time, P1 and TM1 are currently latest accumulated data and time in the fusion library, N is the number of data pieces requiring mean interpolation, and P is accumulated data within a time threshold T of mean interpolation. The interpolated time point is the time point of each time threshold T between TM1 and TM2 (front open and back closed);
s3, filtering the data after the mean value interpolation in the step S2, comparing each piece of data with the existing data in the fusion library, and if the data exist, judging to repeat and abandon the data; and for the data which is delayed to be uploaded, performing corresponding processing after the priority matching of the equipment, specifically: the step S4 is entered if the data uploaded by the primary device is delayed, and the step S entered if the data uploaded by the backup device is delayed;
s4, the quality judgment is carried out on the data filtered in the step S3, and the method specifically comprises the following steps:
s41, false and suspicious judgment: each site and monitoring element (accumulated rainfall, water level, flow and the like) have respective monitoring value ranges, a suspicious data value range and an error data value range are configured according to the specific actual conditions of different sites, the quality of the monitoring values is judged, data in the suspicious data value range are stored in a suspicious data table, a person on duty confirms the data, the data are temporarily stored in a fusion target table in a normal data state, the data in the error data value range are marked as error data, the error data are stored in an original target table, and the fusion target table is not recorded;
s42, judging the distortion of the equipment: and part of the monitoring equipment has a certain range, and once the monitoring value exceeds or is lower than the range of the equipment, the obtained data is inaccurate, so that the data is judged to be distorted, and the distorted data is marked as distorted data and is put into a distorted data table.
S43, sudden jump of water level: configuring a water level sudden jump index, marking sudden jump data as suspicious data when the water level value rises or falls to reach the sudden jump index within a specified interval time, storing the suspicious data into a suspicious data table, and waiting for a person on duty to confirm;
and S44, data examination and correction: the data stored in the suspicious data table needs to be checked by an operator on duty, if the data is correct, the suspicious data table is removed, if the data is wrong, the monitoring value range in S41 is corrected, the corrected data replaces the data in the fusion target table, and the suspicious data table is removed.
And S5, after the data is examined and corrected in the step S4, the data of the main equipment is copied into two parts for storage, one part is put into the original target table of the fusion library, the other part is selected to be preferred to be put into the fusion target table of the fusion library after grade judgment, and the data of the standby equipment is put into the temporary table of the standby equipment to wait for starting.
Further, in step S1, the monitoring data includes data with a monitoring period of 1 minute, data with a monitoring period of 5 minutes, and data with a monitoring period of 1 hour, or 3 hours, or 24 hours.
Further, in step S2, since the accuracy of mean interpolation is lower as the time span is larger, only data whose time difference is within one hour is interpolated.
Further, in step S5, the grade determination specifically includes: and comparing the data in the stream acquired in real time with the data of the same key in the fusion library, if the data of the same key does not exist, directly entering the fusion library, and if the data of the same key exists, comparing the fusion grade, and keeping the one with the larger fusion grade.
Further, the fusion level has 4 levels (4>3>2> 1): 1. other equipment automatically collects the data; 2. automatic acquisition by remote measuring equipment; 3. manually reporting; 4. modified manually.
Further, when the main device has data missing, starting the data of the standby device to perform mean interpolation, and when the standby device has more than one standby device, selecting the standby device with the highest priority according to the starting priority of the standby device to perform data interpolation, wherein the data of the standby device has two copies, one copy is used for interpolating the original target table, and the other copy is used for selecting the optimal interpolation fusion target table after grade judgment, so that the discontinuous data missing caused by the data missing of the main device is filled.
Further, in step S44, the modification is performed according to the monitoring value range of the monitoring element, and the modification is performed by modifying on the visual interface of the project.
The invention has the beneficial effects that:
1. in the invention, fitting duplication elimination is carried out before data acquisition and storage so as to solve the problem of inaccurate statistics caused by abnormal change of a data monitoring period or discontinuous data time axis in upper layer statistical analysis.
2. In the invention, mean interpolation is needed before data acquisition and storage so as to solve the problem of inaccurate statistics caused by discontinuous data time axis in upper layer statistical analysis.
3. In the invention, priority screening and fusion are required before data acquisition and storage, and since the accuracy and reliability of manual review are highest and the data quality of other sources cannot be guaranteed, the repeated data is fused and stored according to the priority of manual priority, equipment priority and other data sources. The problem that data repetition and poor quality cause incapability of statistics or inaccuracy of statistics in upper layer statistical analysis is solved.
Drawings
FIG. 1 is an overall flow chart of a device data optimization and fusion method of the present invention;
fig. 2 is a flowchart of the quality determination step in the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
As shown in fig. 1, the method for optimizing and fusing device data provided by the present invention specifically includes the following steps:
the method comprises the steps that firstly, monitoring data are automatically acquired through acquisition equipment, wherein the data comprise accumulated data and instantaneous data, the monitoring data comprise data with a monitoring period of 1 minute, data with a monitoring period of 5 minutes and data with a monitoring period of 1 hour or 3 hours or 24 hours. Typically, the device collects data at a time point of five minutes, for example, 10:05:00, but sometimes the device does not collect data at the time point of five minutes, for example, 10:04:20, and sometimes the device does not collect data at the time point of five minutes. Therefore, the 10:04:20 second data is required to replace the 10:05:00 data vacancy, so that the acquired monitoring data needs to be subjected to fitting de-duplication to obtain data according with the rule of the monitoring period, specifically: fitting the irregular data monitoring time to the regular data time of a certain monitoring period, and then removing the duplicate according to the main key; the fitting is specifically to draw the monitoring time of the data which does not accord with the monitoring period to the nearest monitoring time which accords with the detection period. For example: when the monitoring period is 5 minutes, the data monitoring time corresponding to the monitoring period is similar to 10:00:00, 10:05:00 and 10:10:00, and the monitoring time is 10:02:30 to 10:07:29, the monitoring time is modified to 10:05:00, and the like. The primary key is one or more fields in a database table that identify data uniqueness.
Step two, the device can cause data loss due to self failure or network failure or other various reasons. Therefore, it is necessary to perform difference averaging using data before and after the missing time point to complement the missing time point, and perform mean interpolation on the accumulated data after the fitting and the de-duplication in step one, because the larger the time span is, the lower the accuracy of the mean interpolation is, only data with a time difference of less than one hour is interpolated. And comparing each piece of real-time data acquired by the acquisition equipment with the latest data of the same monitoring frequency of the same station equipment in the current fusion library, and performing mean value compensation on each missing time threshold T for the real-time data with the time difference larger than a certain time threshold T. Taking the accumulated data as the accumulated rainfall as an example, the calculation method is as follows:
N＝(TM2-TM1)/T
P＝(P2-P1)/N
in the formula, P2 and TM2 are the accumulated rainfall and time of the currently acquired real-time data, P1 and TM1 are the latest accumulated rainfall and time in the current library, N is the number of data pieces requiring mean interpolation, and P is the time threshold T rainfall of the mean interpolation. The interpolated time point is the time point of each time threshold T between TM1 and TM2 (front open and back closed); the time threshold T is a monitoring period, for example, a certain 5 minutes, and P is the accumulated rainfall in the 5 minutes.
Step three, filtering the data subjected to the mean interpolation in the step two, comparing each piece of data with the existing data in the fusion library, and if the data exist, judging to repeat and abandoning; and for the data which is delayed to be uploaded, performing corresponding processing after the priority matching of the equipment, specifically: if the data uploaded by the main equipment is delayed, entering a step four, and if the data uploaded by the standby equipment enters a standby equipment temporary table;
step four, performing quality judgment on the data filtered in step three, as shown in fig. 2, specifically including:
1. and (3) false and suspicious judgment: each site and monitoring element (accumulated rainfall, water level, flow and the like) have respective monitoring value ranges, a suspicious data value range and an error data value range are configured according to the specific actual conditions of different sites, the quality of the monitoring values is judged, data in the suspicious data value range are stored in a suspicious data table, a person on duty confirms the data, the data are temporarily stored in a fusion target table in a normal data state, the data in the error data value range are marked as error data, the error data are stored in an original target table, and the fusion target table is not recorded;
2. and (3) equipment distortion judgment: part of monitoring equipment has a certain range, and once the monitoring value exceeds or is lower than the range of the equipment, the obtained data is inaccurate, so that the data is judged to be distorted, and the distorted data is marked to be distorted and put in storage;
3. water level jump: configuring a water level sudden jump index, marking sudden jump data as suspicious data when the water level value rises or falls to reach the sudden jump index within a specified interval time, storing the suspicious data into a suspicious data table, and waiting for a person on duty to confirm;
4. and (3) data examination and correction: and the data stored in the suspicious data table needs to be checked by an operator on duty, the suspicious data table is removed if the data is correct, the data in the fusion target table is replaced by the corrected data and the suspicious data table is removed if the data is wrong, the correction is carried out according to the monitoring value range of the monitoring elements, and the correction method is that the correction is carried out on a visual interface of the project.
And fifthly, monitoring data sources are numerous, wherein the monitoring data sources comprise data acquired by a main device, data acquired by a secondary device, data acquired from a city, data uploaded manually, data corrected manually and the like, so that the situation that data are repeated at the same monitoring time point of the same station is caused, the data quality levels are not uniform due to the characteristics of the various sources, the data quality is influenced when the various sources are randomly put in storage, the statistical analysis is inaccurate, and the priority screening is required. After the data is examined and corrected in the fourth step, the data of the main equipment is duplicated into two parts, one part is put into the original target table of the fusion library, the other part is subjected to grade judgment, the fusion target table which is preferred to be put into the fusion library is selected, and the standby equipment is put into the standby equipment temporary table of the fusion library to wait for starting. The grade judgment specifically comprises the following steps: and comparing the data in the stream with the data of the same main key which is already stored in the library, directly storing the data in the library if the data of the same main key does not already exist, and comparing the fusion grade if the data of the same main key exists, and reserving the strip with the large fusion grade. Wherein the fusion level has a level 4 (4>3>2> 1): 1. other equipment automatically collects the data; 2. automatic acquisition by remote measuring equipment; 3. manually reporting; 4. modified manually.
When the main equipment has data missing, starting the data of the standby equipment to perform mean interpolation, and when the standby equipment has more than one standby equipment, selecting the standby equipment with the highest priority to perform data interpolation according to the starting priority of the standby equipment, wherein the standby equipment data has two copies, one copies of an interpolation original target table, and the other copies of the standby equipment data have a grade judgment and then select a preferred interpolation fusion target table, so that the discontinuous data vacancy caused by the missing data of the main equipment is filled.
Examples
The above embodiments are described in detail with reference to an example of a station in a certain area. An example survey station is a rainfall station, the acquisition source is remote measurement, flood reporting items are rainfall and acquisition frequency is 5 minutes, and the original data are shown in table 1:
TABLE 1
The method comprises the first step of collecting rainfall equipment data corresponding to a measuring station from a telemetering data source to perform data fitting. The data monitoring time collected by the device is not accurate to the whole five minutes, and after data fitting and deduplication are performed, the obtained data are shown in table 2:
TABLE 2
And secondly, calculating a 5-minute rainfall value, performing mean difference compensation on the missing value, wherein the rainfall data of the remote measuring source is an accumulated rainfall value, the rainfall needs to be calculated according to the difference value of the 5-minute rainfall, the station is a 5-minute rainfall device, the rainfall data is one in every 5 minutes, the missing value exists between 8 visible points and 20 minutes, and the missing time length of the data does not exceed 1 hour, judging that the data difference compensation needs to be performed, dividing the data obtained by subtracting the data of 08:00:00 from the data of 08:20:00 by the interval number of 5 minutes (namely: 20/5), assigning the obtained mean values to 08:05:00, 08:10:00, 08:15:00 and 08:20:00, and processing the data as shown in table 3:
TABLE 3
And thirdly, judging the priority of the equipment, wherein the station only has one main equipment and has no standby equipment, and the data of the main equipment continues the next step.
And fourthly, quality judgment, namely judging whether the rainfall equipment is wrong or suspicious, and avoiding equipment distortion and water level jump.
1. And (4) false suspicious judgment, wherein the rainfall of the equipment in 5 minutes has no suspicious domain, the upper limit of the error is 50mm, the data exceeding the upper limit of the error is marked as error data, the rainfall of 5 minutes at 8 points and 30 minutes is 55mm and is more than 50mm, so that the error data is marked as error data, the error data is input into the original target table, and the fusion target table is not input.
2. Data is checked and corrected, and the rainfall of the device for 5 minutes has no suspicious domain, so that the device does not need to be checked by a person on duty.
And fifthly, judging grade, comparing the data in the stream with the data of the same main key in the existing library, directly warehousing if no data of the same main key exists, comparing the fusion grade if the data of the same main key exists, and reserving the piece with the large fusion grade, wherein the equipment is a remote measuring source and the measuring station is known to have no data of other sources.
And sixthly, putting the data into a warehouse, and finally putting one part of the data into the original target table of the rainfall station and putting one part of the data into the rainfall fusion table after the data are subjected to the steps. The rainfall original table warehousing condition is shown in table 4:
TABLE 4
The rainfall fusion table storage situation is shown in table 5:
TABLE 5
The above-described embodiments are intended to illustrate rather than to limit the invention, and any modifications and variations of the present invention are within the spirit of the invention and the scope of the appended claims.
Claims (7)
1. A method for optimizing and fusing equipment data is characterized by comprising the following specific steps:
s1: through collection equipment automatic acquisition monitoring data, wherein data contain accumulative total data and instantaneous data two kinds, carry out the fitting deduplication to monitoring data, obtain the data that accords with monitoring cycle's law, specifically do: fitting the irregular data monitoring time to the regular data time of a certain monitoring period, and then removing the duplicate according to the main key;
and S2, performing mean interpolation on the accumulated data subjected to the fitting and de-weighting in the step S1, comparing each piece of real-time data acquired by the acquisition equipment with the latest data of the same monitoring frequency of the same observation station equipment in the fusion library, and performing mean interpolation on each missing time threshold T for the real-time data with the time difference larger than a certain time threshold T. The calculation method is as follows:
N＝(TM2-TM1)/T
P＝(P2-P1)/N
in the formula, P2 and TM2 are currently acquired real-time accumulated data and time, P1 and TM1 are currently latest accumulated data and time in the fusion library, N is the number of data pieces requiring mean interpolation, and P is accumulated data within a time threshold T of mean interpolation. The interpolated time point is the time point of each time threshold T between TM1 and TM2 (front open and back closed);
s3, filtering the data after the mean value interpolation in the step S2, comparing each piece of data with the existing data in the fusion library, and if the data exist, judging to repeat and abandon the data; and for the data which is delayed to be uploaded, performing corresponding processing after the priority matching of the equipment, specifically: the step S4 is entered if the data uploaded by the primary device is delayed, and the step S entered if the data uploaded by the backup device is delayed;
s4, the quality judgment is carried out on the data filtered in the step S3, and the method specifically comprises the following steps:
s41, false and suspicious judgment: each site and monitoring element have their own monitoring value range, configure its suspicious data value range and wrong data value range according to the concrete actual conditions of different sites, carry on the quality judgement to the monitoring value, the data in suspicious data value range are stored in the suspicious data table, wait for the person on duty to confirm, store into the fusion target table in the state of the normal data temporarily at the same time, the data in wrong data value range is marked as the wrong data, enter the primitive target table, do not input the fusion target table;
s42, judging the distortion of the equipment: and part of the monitoring equipment has a certain range, and once the monitoring value exceeds or is lower than the range of the equipment, the obtained data is inaccurate, so that the data is judged to be distorted, and the distorted data is marked as distorted data and is put into a distorted data table.
S43, sudden jump of water level: configuring a water level sudden jump index, marking sudden jump data as suspicious data when the water level value rises or falls to reach the sudden jump index within a specified interval time, storing the suspicious data into a suspicious data table, and waiting for a person on duty to confirm;
and S44, data examination and correction: the data stored in the suspicious data table needs to be checked by an operator on duty, if the data is correct, the suspicious data table is removed, if the data is wrong, the monitoring value range in S41 is corrected, the corrected data replaces the data in the fusion target table, and the suspicious data table is removed.
And S5, after the data is examined and corrected in the step S4, the data of the main equipment is copied into two parts for storage, one part is put into the original target table of the fusion library, the other part is selected to be preferred to be put into the fusion target table of the fusion library after grade judgment, and the data of the standby equipment is put into the standby equipment temporary table of the fusion library to wait for starting.
2. The method for optimizing and fusing device data according to claim 1, wherein in step S1, the monitoring data includes data with a monitoring period of 1 minute, data with a monitoring period of 5 minutes, and data with a monitoring period of 1 hour, or 3 hours, or 24 hours.
3. The device data optimizing and fusing method of claim 1, wherein in step S2, the larger the time span, the lower the accuracy of mean interpolation, so that only data with time difference within one hour are interpolated.
4. The device data optimizing and fusing method according to claim 1, wherein in step S5, the grade determination specifically comprises: and comparing the data in the stream acquired in real time with the data of the same key in the fusion library, if the data of the same key does not exist, directly entering the fusion library, and if the data of the same key exists, comparing the fusion grade, and keeping the one with the larger fusion grade.
5. The device data optimizing and fusing method of claim 4, wherein the fusing level has a 4-level (4>3>2> 1): 1. other equipment automatically collects the data; 2. automatic acquisition by remote measuring equipment; 3. manually reporting; 4. modified manually.
6. The method for optimizing and fusing equipment data according to claim 1, wherein when the main equipment has data missing, the standby equipment data is started for mean interpolation, when more than one standby equipment exists, the standby equipment with the highest priority is selected according to the starting priority of the standby equipment for data interpolation, the standby equipment data is duplicated, one original target table is interpolated, the other fusion target table is optimized after grade judgment, and discontinuous data missing caused by the missing data of the main equipment is filled.
7. The method for optimizing and fusing plant data according to claim 1, wherein the modification is performed according to the monitoring value range of the monitoring element in step S44, and the modification is performed by modifying on the visual interface of the project.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419769.7A CN113128590B (en) | 2021-04-19 | 2021-04-19 | Equipment data optimization and fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110419769.7A CN113128590B (en) | 2021-04-19 | 2021-04-19 | Equipment data optimization and fusion method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113128590A true CN113128590A (en) | 2021-07-16 |
| CN113128590B CN113128590B (en) | 2022-03-15 |
Family
ID=76777709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110419769.7A Active CN113128590B (en) | 2021-04-19 | 2021-04-19 | Equipment data optimization and fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128590B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115550227A (en) * | 2022-09-02 | 2022-12-30 | 中盈优创资讯科技有限公司 | Service flow collection and monitoring guarantee method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810392A (en) * | 2013-12-13 | 2014-05-21 | 北京航空航天大学 | Degradation data missing interpolation method based on support vector machine and RBF neural network |
| CN103825930A (en) * | 2013-11-12 | 2014-05-28 | 浙江省水文局 | Real-time data synchronization method in distributed environment |
| US20170024529A1 (en) * | 2015-07-26 | 2017-01-26 | Macau University Of Science And Technology | Semi-Supervised Learning Framework based on Cox and AFT Models with L1/2 Regularization for Patient's Survival Prediction |
| CN107403004A (en) * | 2017-07-24 | 2017-11-28 | 邱超 | A kind of suspicious numerical examination method of remote gauged rainfall website based on terrain data |
| CN110880014A (en) * | 2019-10-11 | 2020-03-13 | 中国平安财产保险股份有限公司 | Data processing method and device, computer equipment and storage medium |
| US20200334093A1 (en) * | 2019-04-17 | 2020-10-22 | Microsoft Technology Licensing, Llc | Pruning and prioritizing event data for analysis |
-
2021
- 2021-04-19 CN CN202110419769.7A patent/CN113128590B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103825930A (en) * | 2013-11-12 | 2014-05-28 | 浙江省水文局 | Real-time data synchronization method in distributed environment |
| CN103810392A (en) * | 2013-12-13 | 2014-05-21 | 北京航空航天大学 | Degradation data missing interpolation method based on support vector machine and RBF neural network |
| US20170024529A1 (en) * | 2015-07-26 | 2017-01-26 | Macau University Of Science And Technology | Semi-Supervised Learning Framework based on Cox and AFT Models with L1/2 Regularization for Patient's Survival Prediction |
| CN107403004A (en) * | 2017-07-24 | 2017-11-28 | 邱超 | A kind of suspicious numerical examination method of remote gauged rainfall website based on terrain data |
| US20200334093A1 (en) * | 2019-04-17 | 2020-10-22 | Microsoft Technology Licensing, Llc | Pruning and prioritizing event data for analysis |
| CN110880014A (en) * | 2019-10-11 | 2020-03-13 | 中国平安财产保险股份有限公司 | Data processing method and device, computer equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 吴泓等: "气象监测中降水资料的质量控制", 《气象科学》 * |
| 周佳宁等: ""流空间"视域下淮海经济区城乡融合发展驱动机制", 《自然资源学报》 * |
| 赵一凡等: "数据清洗方法研究综述", 《软件导刊》 * |
| 路昂: "基于用电负荷的缺失数据插补方法研究", 《分布式能源》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115550227A (en) * | 2022-09-02 | 2022-12-30 | 中盈优创资讯科技有限公司 | Service flow collection and monitoring guarantee method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113128590B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106022592B (en) | Electricity consumption behavior abnormity detection and public security risk early warning method and device | |
| CN112035544B (en) | Power distribution network data anomaly monitoring and diagnosis method | |
| CN113128590B (en) | Equipment data optimization and fusion method | |
| CN109376924A (en) | A kind of method, apparatus, equipment and the readable storage medium storing program for executing of material requirements prediction | |
| CN111612647B (en) | Meter abnormal data detection method, device, meter and readable storage medium | |
| CN112668772B (en) | State development trend prediction method, device, equipment and storage medium | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| CN115512518B (en) | Method and device for processing early warning information of multiple disasters based on space-time correlation | |
| CN109542742A (en) | Database server hardware health evaluating method based on expert model | |
| CN115204583A (en) | Method, system and device for hierarchical management, control, evaluation and analysis of regional risks in chemical industry park | |
| CN116089405A (en) | Power consumption data outlier detection and cleaning method based on DBSCAN and KNN algorithms | |
| CN117538503A (en) | Real-time intelligent soil pollution monitoring system and method | |
| CN113283824A (en) | Comprehensive management method and system for intelligent park data | |
| CN111966746A (en) | Meteorological disaster prevention and reduction flow monitoring system and monitoring method thereof | |
| CN117972153A (en) | Intelligent water meter data management and control method and system | |
| CN117708735A (en) | Measurement data fitting method, medium and system based on multipoint checking | |
| CN111999691A (en) | Error calibration method and error calibration device for metering sensor device | |
| CN112345972A (en) | Power failure event-based power distribution network line transformation relation abnormity diagnosis method, device and system | |
| CN113011477A (en) | Solar irradiation data cleaning and complementing system and method | |
| CN115951123A (en) | Electric energy metering method and system based on wireless communication | |
| CN113506193B (en) | Method for estimating residence relocation area and method for formulating residence relocation policy | |
| Green et al. | Quality controlling daily read rainfall data for the intensity-frequency-duration (IFD) revision project | |
| CN118190051A (en) | Fault detection method and device and computer readable storage medium | |
| CN110751398B (en) | Regional ecological quality evaluation method and device | |
| CN118606876B (en) | Night water quantity leakage early warning method and system based on denoising |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |