CN110455370B - Flood-prevention drought-resisting remote measuring display system - Google Patents
Flood-prevention drought-resisting remote measuring display system Download PDFInfo
- Publication number
- CN110455370B CN110455370B CN201910761502.9A CN201910761502A CN110455370B CN 110455370 B CN110455370 B CN 110455370B CN 201910761502 A CN201910761502 A CN 201910761502A CN 110455370 B CN110455370 B CN 110455370B
- Authority
- CN
- China
- Prior art keywords
- data
- flood
- water level
- value
- display system
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0793—Remedial or corrective actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
Abstract
The invention relates to a flood-prevention drought-resisting remote telemetering display system which comprises field acquisition equipment, a local acquisition server and terminal display equipment internally provided with an RTU (remote terminal Unit), wherein the field acquisition equipment transmits data to the local acquisition server by adopting a wireless transmission technology, and the local acquisition server remotely transmits the data to the terminal display equipment for display. The flood-prevention drought-fighting remote telemetering display system adopts the LED display screen as an upper computer display system, and has excellent intuition and attractiveness. The acquisition server is locally placed, so that various faults can be effectively processed in time, the field faults are maintained in advance, and management and maintenance separation is realized; the normal operation of the flood season system is guaranteed, and convenience and reliability are achieved. The flood-prevention drought-resisting remote telemetering display system can get rid of the influence caused by improper manual operation, has good safety, and can provide convenient and fast service for water supply management departments.
Description
Technical Field
The invention relates to a flood-prevention drought-fighting remote telemetry display system, and belongs to the technical field of flood-prevention drought-fighting.
Background
With the development of modern science and technology, flood prevention and drought control automatic monitoring systems are rapidly developed. In a flood season, water pipe departments often need to monitor and report numerous water level points in real time, monitoring points are dispersed and are wide in distribution range, stations without automatic monitoring equipment report in an artificial measurement mode, timeliness of water condition monitoring of departments in charge is affected, most of the stations with the automatic monitoring equipment collect data through an automatic monitoring system, and particularly in the flood season, once a system fails, maintenance personnel cannot repair the system in time, and delay of water condition observation is caused.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a flood prevention and drought control remote measurement display system, and the specific technical scheme is as follows:
the flood-prevention drought-resisting remote telemetering display system comprises field acquisition equipment, a local acquisition server and terminal display equipment internally provided with an RTU, wherein the field acquisition equipment transmits data to the local acquisition server through a wireless transmission technology, and the local acquisition server remotely transmits the data to the terminal display equipment and displays the data.
According to the technical scheme, the field acquisition equipment is a water level meter arranged in a flood prevention and drought resisting area.
According to the further optimization of the technical scheme, the data adopted by the field acquisition equipment is water level data.
According to the further optimization of the technical scheme, a data error correction module is further arranged in the terminal display equipment, and the data error correction module directly calculates the deviation value of the newly-coming data; if the deviation value is smaller than the set threshold value, the data is abnormal.
According to the further optimization of the technical scheme, the latest k pieces of uploading data are taken according to the time t and the water level data w; k value is selected according to the number W of water level data uploaded every daydaDivide by the number of dots D of the uploading devicenDivided by the frequency F of the hourly equipment uploadshThe value of k is obtained and the value of k,
for two-dimensional data vectors of time t and uploaded water level value w, the calculation formula of the data difference distance Dc (w, t) is as follows:
adding historical uploaded water level data into a training data set TR [ n ], and predicting the category with the most categories in the k samples with the training data set TR [ n ] and the nearest predicted sample characteristics by using a majority decision method;
calculating the current uploading water level data Wr, the time Tr and the distance Dc (Wr, Tr) of the samples in the training data set TR [ n ] according to a data difference distance Dc (w, t) calculation formula, then calculating the minimum k Dc (wmin, tmin), then carrying out majority voting, and if the number is a small number, the data is abnormal data and is inserted into an abnormal database.
The technical scheme is further optimized, and the system further comprises an early warning module, wherein the early warning module comprises the following steps:
step 1, data preprocessing
The method comprises the steps of summarizing time and space data attention missing values of various regions, summarizing data with small time intervals based on a specified summarizing function, filling the missing data, and replacing or filling the missing values by using an average value of the closest point, namely an average value of three nearest non-null values before a time period to be created;
step 2, modeling early warning space-time data
The space-time early warning model is an extended model based on linear regression, and the formula is as follows:
Y＝xβ+Z；
wherein, the coefficient beta is the coefficient of the independent variable and represents the influence degree of the independent variable on the target variable; z is used as a residual error of linear fitting, is a part which cannot be represented by an independent variable linear combination in the target variable change, is used for capturing time autocorrelation in an autoregressive model and is further used for describing the correlation of a space;
step 3, processing the space-time early warning data
Firstly, preparing and recording time data, space data, water level data and alarm data into a database; secondly, a standard linear regression model is adopted in the regression model, and the coefficient of linear regression is used for measuring the influence degree of time, position and water level on the early warning value; the autoregressive model predicts the current value using a specified autoregressive order N of 20, i.e., a value 20 moments before a specified time; the coefficient of autoregressive is used for measuring the influence of the residual error of past time on the current value;
the method comprises the steps that a covariance model based on a geographic space is established on the basis of a time autoregressive model residual error, and the space covariance model uses a parameter method; given that the data given can be modeled parametrically, X is provided1，Z1Two parametric inspection methods to determine the accuracy of the model; x1Is to detect whether there is attenuation in space that varies with distance, Z1Detecting that spatial variance is prevalent in a given region;
X1Z1and X2Z2Normalized covariance matrix R1R1And R2R2Respectively as follows:
R1＝X1Z1Ttrace(X1Z1T)；
R2＝X2Z2Ttrace(X2Z2T)；
XZT denotes the transpose of the XX matrix, trace (x) denotes the sum of the elements on the diagonal of the matrix;
then, a mixed spatial covariance matrix RR is calculated:
R＝R1-+R2-(3)(3)R＝R1-+R2-；
after the estimation process of the model is finished, the obtained model can generate an estimation value of a target variable, the estimation value is compared with an observed value, meanwhile, the detection is carried out by a parameter detection method, and then the model is stored;
and interpolating regression residual errors of the initial geographic position after conversion by using the constructed spatial covariance matrix according to the data of the selected time period, so as to obtain the geographic position of the prediction alarm.
The invention has the beneficial effects that:
the flood-prevention drought-resisting remote telemetering display system adopts the LED display screen as an upper computer display system, and has excellent intuition and attractiveness. The acquisition server is locally placed, so that various faults can be effectively processed in time, the field faults are maintained in advance, and management and maintenance separation is realized; the normal operation of the flood season system is guaranteed, and convenience and reliability are achieved. The flood-prevention drought-resisting remote telemetering display system can get rid of the influence caused by improper manual operation, is good in safety, and can provide convenient and fast service for water supply management departments.
Drawings
Fig. 1 is a flow chart of the flood-prevention drought-resistance remote telemetry display system.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the flood-prevention and drought-resistance remote telemetry display system comprises field acquisition equipment 1, a local acquisition server 2 and terminal display equipment 3 with an RTU (remote terminal unit) arranged therein, wherein the field acquisition equipment 1 transmits data to the local acquisition server 2 by adopting a wireless transmission technology, and the local acquisition server 2 remotely transmits the data to the terminal display equipment 3 for display.
Wherein, the field acquisition equipment 1 is a water level meter installed in a flood prevention and drought control area. The data used by the field acquisition device 1 is water level data.
The flood-prevention drought-resisting remote telemetering display system mainly solves the technical problems as follows:
1) the management and maintenance separation mode is implemented, the acquisition server is placed locally, the acquisition server is remotely transmitted to a management department, and once the problems of abnormity or faults and the like occur in the acquisition data or the acquisition system, the maintenance is timely and effective.
2) And the terminal display equipment adopts an LED display large screen as the terminal display equipment, so that the terminal display equipment is visual and attractive. The large screen is internally provided with the RTU (RTU and large screen are integrated), an acquisition server and a wired transmission device are replaced, the influence caused by manual misoperation of field management personnel is also eliminated, and the large screen has certain safety, reliability and convenience.
3) The data storage is multiple backup, the large screen is connected with the RTU, the remote server collects data backup, the data backup can be automatically carried out in the RTU, and the collected data can be conveniently led into other computers by the USB flash disk plug-in card.
The field acquisition equipment 1 is mainly installed in a flood prevention field, acquires and stores a field water level value at regular time, remotely measures and stores information acquired by the field acquisition equipment 1 to the local acquisition server 2, the terminal display equipment 3 is mainly used for displaying the information acquired by the local acquisition server 2, the local acquisition server 2 communicates with the remote terminal unit 4, and transmits and stores data to the remote terminal unit 4; the remote terminal unit 4 is simply referred to as RTU.
The flood-prevention drought-resisting remote telemetry display system is a full-automatic operation process after being installed, manual operation is generally not needed, and maintenance personnel only need to perform data check on the local acquisition server 2 regularly (unqualified early warning data can be automatically recorded and reported), analyze reasons and perform maintenance.
The flood-prevention drought-resisting remote telemetering display system is also internally provided with a data error correction module, and the data error correction module directly calculates the deviation value of newly-arrived data; if the deviation value is smaller than the set threshold value, the data is abnormal.
The data error correction module collects error data aiming at the condition that the forecast data is interfered by the collection environment or network transmission faults, obtains an effective range value through a machine learning algorithm, and corrects and records the abnormal peak or valley data. The deviation function of the reported data can be estimated, the deviation value of the reported data is directly calculated for the new data, and if the deviation value is less than a certain threshold value, the reported data is abnormal. Whereas the deviation function typically takes a multidimensional gaussian distribution. The two-dimensional data of the current water level and time dimension can also be regarded as being in accordance with Gaussian distribution.
Due to the fact that a large amount of data are uploaded, timeliness is needed for data error correction, and machine learning needs to be conducted effectively in the shortest time after the system uploads each piece of data and errors are found.
The K-nearest neighbor method (KNN method) is used.
Taking the latest k pieces of uploading data according to the time t and the water level data w; k value is selected according to the number W of water level data uploaded every daydaDivide by the number of dots D of the uploading devicenDivided by the frequency F of the hourly equipment uploadshThe value of k is obtained and the value of k,
the k value result is in a middle value, the field of data samples is moderate, the training error is small, the normalization error is not large, the whole model is balanced, and the fitting is accurate.
For two-dimensional data vectors of time t and uploaded water level value w, the calculation formula of the data difference distance Dc (w, t) is as follows:
adding historical uploaded water level data into a training data set TR [ n ], and predicting the category with the most categories in the k samples with the training data set TR [ n ] and the nearest predicted sample characteristics by using a majority decision method.
Calculating the current uploading water level data Wr, the time Tr and the distance Dc (Wr, Tr) of the samples in the training data set TR [ n ] according to a data difference distance Dc (w, t) calculation formula, then calculating the minimum k Dc (wmin, tmin), then carrying out majority voting, and if the number is a small number, the data is abnormal data and is inserted into an abnormal database.
The flood-prevention drought-resisting remote telemetering display system further comprises an early warning module, and the early warning module performs the following steps:
1. data preprocessing:
missing values are focused by summarizing the time and space data of each region, data with smaller time intervals are summarized based on a specified summarizing function, then the missing data are filled, and the missing values are replaced or filled by using the average value of the closest points, namely the average value of three nearest non-null values before the time period to be created. And (4) integrating alarm data of various places and processed time and space data.
2. Early warning spatiotemporal data modeling
The space-time early warning model is an extended model based on linear regression, and the formula is as follows:
Y＝xβ+Z
wherein, the coefficient beta is the coefficient of the independent variable and represents the influence degree of the independent variable on the target variable; z is the residual of the linear fit, which is the portion of the target variable variation that cannot be represented by the linear combination of the independent variables, and can be used to capture the temporal autocorrelation in the autoregressive model, and thus to describe the spatial correlation.
3. Spatio-temporal early warning data processing
The treatment comprises the following steps
A) Preparing a data source:
preparing and recording time data, space data, water level data, alarm data and other data sources into a database
B) Fitting linear regression model
The regression model adopts a standard linear regression model, but due to the space-time correlation relationship of data, the residual error of the regression model forms a non-independent space-time correlation random process with zero mean value. The linear regression coefficient can measure the influence degree of time, position and water level on the early warning value, and the water level and time change corresponding to a larger coefficient can generate a larger early warning value change.
C) Fitting time autoregressive model
The autoregressive model predicts the current value using the specified autoregressive order N of 20, i.e., the value 20 moments before the specified time. The coefficients of the autoregressive can be used to measure the effect of the residuals at past times on the current value. The autoregressive model also contains residuals, which are independent of each other in time due to the removal of temporal autocorrelation factors.
D) Computing time autoregressive model residual error and establishing space covariance model
The covariance model based on the geographic space is established on the basis of the time autoregressive model residual error, and the spatial covariance model uses a parameter method. Two parametric test methods of x1 and z1 are provided to determine the accuracy of the model, assuming that the data given can be modeled parametrically. X1 is to detect if there is attenuation in space that varies with distance, z1 detects that the spatial variance is prevalent in a given area (variance homogeneity test).
X1Z1And X2Z2Normalized covariance matrix R1R1And R2R2Respectively as follows:
R1＝X1Z1Ttrace(X1Z1T)；
R2＝X2Z2Ttrace(X2Z2T)；
XZT denotes the transpose of the XX matrix, trace (x) denotes the sum of the elements on the diagonal of the matrix;
then, a mixed spatial covariance matrix RR is calculated:
R＝R1-+R2-(3)(3)R＝R1-+R2-；
E) calculating the measured statistical value and storing the result
After the estimation process of the model is completed, the obtained model can generate an estimated value of the target variable, the estimated value is compared with the observed value, meanwhile, the detection is carried out through a parameter detection method, and then the model is stored.
F) Selecting time segment data for prediction
And D), interpolating regression residual errors of the initial geographic position after conversion by using the space covariance matrix constructed in the step D) according to data of the selected time period, so as to obtain the geographic position of the prediction alarm.
Through actual data detection, the calculated early warning value and the actual possible early warning have a linear relation, the later period is more and more accurate along with more and more data, and the result obtained by the algorithm has a reference effect.
In the embodiment, a data error correction module is arranged to establish a model for each feature in a training set sample, after the model is established, algorithm evaluation is performed in a verification set, a certain sample value w in the verification set is input into the model, a label of the verification set sample is predicted according to a threshold k, if the sample value is greater than the threshold k, a normal point is obtained, and if the sample value is less than the threshold k, an abnormal point is obtained.
The anomaly detection is applied to samples having a very small number of positive samples (y ═ 1) and a very large number of negative samples (y ═ 0). Because the number of the positive samples is too small, all the causes of the abnormalities cannot be found, if supervised learning is performed, all the samples cannot be learned, new abnormalities which can occur in the future may exist, and the abnormalities cannot be observed at present and cannot be modeled. In contrast, anomaly detection models a large number of negative examples, so that any sample that deviates from the model can be identified as an anomaly without investigating what the cause of the anomaly is.
Therefore, when the number of the negative samples, namely the abnormal points is very small, the negative samples in the data can be modeled by using an abnormal detection method, and the data deviating from the normal points are considered as the abnormal points; when the number of the abnormal points is very large, the supervised learning algorithm can effectively learn, so that the supervised learning algorithm can be selected to identify the abnormal points.
The data error correction module has the advantages that: it relies mainly on machine learning, especially supervised learning, such as classification, regression. Machine learning may be based on data to help the intelligent system make various decisions, possibly corresponding to perceptual processing, or cognitive processing, such as identifying whether a face is inside a photograph, or determining which step should be taken when playing go. The data error correction module has the advantages that the data driving is used for establishing a model according to the judgment continuously made by data training, the judgment is far faster than manual work, and the accuracy is far higher than manual work. Helping the service administrator to make decisions.
The early warning module is a method for early warning based on space-time big data measured and reported by a system, and is used for storing space-time data as parameters and extracting early warning rules from nonlinear and massive space-time data aiming at gps position data, time and water level data acquired by measured and reported data and the past year warning condition of each city and county recorded manually. The early warning reference is achieved through a big data algorithm, a certain area can be estimated, the warning condition can be generated in a certain time period, and the warning condition is provided for an expert to make a decision.
The characteristics and advantages of the early warning module are as follows:
the early warning module constructs a theory and method model of the large space-time data around a space-time large data scientific theory, a space-time large data computing system and scientific theory, a space-time large data driven application model exploring multi-source heterogeneous space-time large data integration, a space-time large data statistical analysis model and mining algorithm, a space-time large data quick visualization method and the like.
The early warning module surrounds space-time big data storage management, space-time big data intelligent synthesis, multi-scale space-time database automatic generation and incremental cascade updating, space-time big data cleaning, analysis and mining, space-time big data visualization, natural language understanding, deep learning and deep reinforcement learning, improves space-time big data analysis and processing capability, knowledge discovery capability and decision support capability, and realizes the conversion from 'data → information → knowledge → auxiliary decision' to 'data → knowledge → auxiliary decision'.
The advantages of the early warning module are as follows:
the multidimensional space-time big data acquisition and artificial intelligence technology are utilized to establish a model, and according to a model analysis method, early warning can be automatically made efficiently and quickly, and decision reference can be made for managers at the first time.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (3)
1. Flood-prevention drought-resisting remote measurement display system is characterized by comprising: the system comprises field acquisition equipment, a local acquisition server and terminal display equipment internally provided with an RTU, wherein the field acquisition equipment transmits data to the local acquisition server by adopting a wireless transmission technology, and the local acquisition server remotely transmits the data to the terminal display equipment for display;
the terminal display equipment is also internally provided with a data error correction module which directly calculates the deviation value of the newly coming data; if the deviation value is smaller than the set threshold value, indicating that the data is abnormal;
taking the latest k pieces of uploading data according to the time t and the water level data w; k value is selected according to the number W of water level data uploaded every daydaDivide by the number of dots D of the uploading devicenDivided by the frequency F of the hourly equipment uploadshThe value of k is obtained and the value of k,
for two-dimensional data vectors of time t and uploaded water level value w, the calculation formula of the data difference distance Dc (w, t) is as follows:
adding historical uploaded water level data into a training data set TR [ n ], and predicting the category with the most categories in the k samples with the training data set TR [ n ] and the nearest predicted sample characteristics by using a majority decision method;
calculating the current uploading water level data Wr, the time Tr and the distance Dc (Wr, Tr) of the samples in the training data set TR [ n ] according to a data difference distance Dc (w, t) calculation formula, then calculating the minimum k Dc (wmin, tmin), then carrying out majority voting, and if the number is a small number, the data is abnormal data and is inserted into an abnormal database.
2. The flood prevention drought resisting remote telemetry display system according to claim 1, characterized in that: the field acquisition equipment is a water level meter arranged in a flood prevention and drought resisting area.
3. The flood prevention drought resisting remote telemetry display system according to claim 1, characterized in that: the data used by the field acquisition device is water level data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910761502.9A CN110455370B (en) | 2019-08-18 | 2019-08-18 | Flood-prevention drought-resisting remote measuring display system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910761502.9A CN110455370B (en) | 2019-08-18 | 2019-08-18 | Flood-prevention drought-resisting remote measuring display system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110455370A CN110455370A (en) | 2019-11-15 |
| CN110455370B true CN110455370B (en) | 2020-10-02 |
Family
ID=68487434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910761502.9A Active CN110455370B (en) | 2019-08-18 | 2019-08-18 | Flood-prevention drought-resisting remote measuring display system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110455370B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1657884A (en) * | 2004-02-20 | 2005-08-24 | 林金 | Measuring method of level sensor and its device |
| WO2013063152A1 (en) * | 2011-10-28 | 2013-05-02 | Zettaset, Inc. | Split brain resistant failover in high availability clusters |
| CN106909487A (en) * | 2017-01-18 | 2017-06-30 | 北京盛世全景科技股份有限公司 | It is applied to the method for early warning and device of information system |
| CN207602024U (en) * | 2017-12-20 | 2018-07-10 | 珠海康宝莱仪表有限公司 | A kind of radar level wireless GPRS remote transmitting system based on sponge city |
| JP6474504B1 (en) * | 2018-01-23 | 2019-02-27 | 株式会社野村総合研究所 | Handwritten character recognition system |
| CN109855698A (en) * | 2017-11-30 | 2019-06-07 | 波音公司 | The combination of level gauging and maximum redundancy from individual compartment |
-
2019
- 2019-08-18 CN CN201910761502.9A patent/CN110455370B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1657884A (en) * | 2004-02-20 | 2005-08-24 | 林金 | Measuring method of level sensor and its device |
| WO2013063152A1 (en) * | 2011-10-28 | 2013-05-02 | Zettaset, Inc. | Split brain resistant failover in high availability clusters |
| CN106909487A (en) * | 2017-01-18 | 2017-06-30 | 北京盛世全景科技股份有限公司 | It is applied to the method for early warning and device of information system |
| CN109855698A (en) * | 2017-11-30 | 2019-06-07 | 波音公司 | The combination of level gauging and maximum redundancy from individual compartment |
| CN207602024U (en) * | 2017-12-20 | 2018-07-10 | 珠海康宝莱仪表有限公司 | A kind of radar level wireless GPRS remote transmitting system based on sponge city |
| JP6474504B1 (en) * | 2018-01-23 | 2019-02-27 | 株式会社野村総合研究所 | Handwritten character recognition system |
Non-Patent Citations (2)
| Title |
|---|
| Retracking Cryosat data in the SARIn mode and robust lake level extraction;M. Kleinherenbrink等;《Remote Sensing of Environment》;20140915(第152期);第38-50页 * |
| 多要素智能RTU设备系统研发及在水利行业中的应用;孙晶晶;《治淮》;20190315(第03期);第20-21页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110455370A (en) | 2019-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109298697A (en) | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model | |
| CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
| US20160369777A1 (en) | System and method for detecting anomaly conditions of sensor attached devices | |
| CN112925279A (en) | Fault comprehensive analysis system based on MES system | |
| JP2016063590A (en) | Failure sign diagnosis system for distribution network, and method therefor | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| CN115329812A (en) | Road infrastructure abnormity monitoring method based on artificial intelligence | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN114781476A (en) | Fault analysis system and method for measuring equipment | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN117194919A (en) | Production data analysis system | |
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| CN108093210A (en) | A kind of transformer oil level warning system and its alarm method | |
| CN117196066A (en) | Intelligent operation and maintenance information analysis model | |
| CN117193222A (en) | Intelligent quality control system based on industrial Internet of things and big data and control method thereof | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN110989042A (en) | Intelligent prediction method for highway fog-clustering risk | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN116679653A (en) | Intelligent acquisition system for industrial equipment data | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN114417741B (en) | One-machine one-file equipment data management and processing system | |
| CN113036917B (en) | Power distribution network monitoring information monitoring system and method based on machine learning | |
| WO2021186762A1 (en) | Maintenance assistance system and maintenance assistance method |
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 |