CN114876699A - Method for judging temperature abnormity of water turbine by utilizing big data - Google Patents
Method for judging temperature abnormity of water turbine by utilizing big data Download PDFInfo
- Publication number
- CN114876699A CN114876699A CN202210622320.5A CN202210622320A CN114876699A CN 114876699 A CN114876699 A CN 114876699A CN 202210622320 A CN202210622320 A CN 202210622320A CN 114876699 A CN114876699 A CN 114876699A
- Authority
- CN
- China
- Prior art keywords
- difference
- sensors
- hydraulic turbine
- abnormal
- temperature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 81
- 230000002159 abnormal effect Effects 0.000 claims abstract description 65
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000013499 data model Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 10
- 238000009434 installation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 10
- 230000007613 environmental effect Effects 0.000 abstract description 6
- 230000002349 favourable effect Effects 0.000 abstract description 5
- 238000011900 installation process Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 description 20
- 230000005540 biological transmission Effects 0.000 description 11
- 238000010276 construction Methods 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03B—MACHINES OR ENGINES FOR LIQUIDS
- F03B11/00—Parts or details not provided for in, or of interest apart from, the preceding groups, e.g. wear-protection couplings, between turbine and generator
- F03B11/008—Measuring or testing arrangements
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03B—MACHINES OR ENGINES FOR LIQUIDS
- F03B13/00—Adaptations of machines or engines for special use; Combinations of machines or engines with driving or driven apparatus; Power stations or aggregates
- F03B13/08—Machine or engine aggregates in dams or the like; Conduits therefor, e.g. diffusors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K1/00—Details of thermometers not specially adapted for particular types of thermometer
- G01K1/02—Means for indicating or recording specially adapted for thermometers
- G01K1/026—Means for indicating or recording specially adapted for thermometers arrangements for monitoring a plurality of temperatures, e.g. by multiplexing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Computation (AREA)
- Combustion & Propulsion (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Mechanical Engineering (AREA)
- Computational Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Control Of Turbines (AREA)
Abstract
The invention discloses a method for judging abnormal temperature of a water turbine by utilizing big data, which belongs to the field of abnormal monitoring of the water turbine, and the method for judging abnormal temperature of the water turbine by utilizing the big data can avoid the influence on the judgment of the abnormal temperature state of the water turbine due to the difference of installation processes by using the difference of a plurality of monitoring points on a single component in the water turbine set as the characteristic for judgment, is favorable for finding the abnormal state in the running process of equipment in advance, judges whether the equipment runs normally or not by using the temperature difference and the statistic value between different components in the same water turbine set, can avoid the influence on the judgment of the temperature of each component in the water turbine set due to the change of working conditions and environmental factors, constructs a historical data model by historical data calculation, can carry out abnormal analysis by means of historical trend, and can also carry out real-time abnormal data detection based on a sliding window, and multiple analysis and judgment further improve the accuracy of temperature abnormity judgment.
Description
Technical Field
The invention relates to the field of abnormal monitoring of water turbines, in particular to a method for judging abnormal temperature of a water turbine by utilizing big data.
Background
In the prior art, in order to guarantee the operational safety and reliability of the hydraulic turbine set, a large number of temperature sensors are added at each part of the hydraulic turbine set to measure the working temperature of the hydraulic turbine set in real time, and a plurality of sensors are usually installed at different positions of the same part of the hydraulic turbine set to guarantee the monitoring comprehensiveness, namely a plurality of temperature measuring points are arranged on the same part to be monitored, and data are collected to a monitoring system through an automatic system.
In the prior art, a maximum threshold alarm, a statistical historical statistical threshold or a threshold mode of carrying out statistical interval according to working conditions are configured, the influence of the environment is not considered, even under the same working conditions, different environmental temperatures can also influence the temperature of components in a hydraulic turbine set, in addition, due to the installation process problem, the measured values of different measuring points of the same monitoring component have larger difference, the statistical values are different due to the difference of the external environment when the historical statistic or the working condition interval is used, even if the data values in the daytime and the evening of the same month in different years have certain difference, the statistical method can only check the general trend change and is not suitable for being used as an alarm judgment threshold, when the standard or empirical alarm threshold is used, due to the difference of the measured point values, if a single point is used for alarm exceeding the limit, part of points are exceeded and other point values are not exceeded, therefore, whether the value is abnormal or not cannot be judged, and the detection accuracy is influenced.
Therefore, a method for judging the temperature abnormity of the water turbine by utilizing big data is provided to solve the problems in the prior art.
Disclosure of Invention
1. Technical problem to be solved
Aiming at the problems in the prior art, the invention aims to provide a method for judging the abnormal temperature of a water turbine by utilizing big data, which can effectively reduce the influence of external environmental factors on the abnormal judgment of the internal temperature of the water turbine unit, judge whether equipment operates normally by using the difference value of a plurality of monitoring points on a single component in the water turbine unit as a characteristic, avoid the influence on the abnormal temperature judgment of the water turbine unit caused by the difference of installation processes, is favorable for finding the abnormal state in the operation process of the equipment in advance, improve the stability and the accuracy of the real-time temperature monitoring of the water turbine unit to a certain extent, judge whether the equipment operates normally by using the temperature difference and the statistical value between different components in the same water turbine unit, avoid the influence on the abnormal temperature judgment of each component in the water turbine unit caused by the change of working conditions and environmental factors, the precision of temperature anomaly detection time has been promoted to a certain extent, has calculated through historical data and has constructed historical data model, can need not to label data, can carry out abnormal analysis through with the help of historical trend, also can carry out real-time data anomaly detection based on the sliding window, and multiple analysis judges, has further promoted the accuracy nature that the temperature anomaly was judged, has promoted the operating efficiency of relevant hydraulic turbine group to a certain extent.
2. Technical scheme
In order to solve the above problems, the present invention adopts the following technical solutions.
A method for judging temperature abnormity of a water turbine by utilizing big data comprises a hydropower station built on a river dam, a plurality of hydraulic turbine units are uniformly installed inside the hydropower station, a plurality of sensors at different positions are uniformly installed on components inside each hydraulic turbine unit in a scattered manner, the sensors are set to be temperature sensors and used for monitoring the temperature of the installation positions of the sensors, a server used for processing signals on the sensors is fixedly installed inside the hydropower station, a monitoring room used for monitoring signals processed inside the server is also installed inside the hydropower station, and the installation positions of the sensors on the same component inside each hydraulic turbine unit are sequentially recorded as D 1 、D 2 、D 3 …D n-1 、D n The inside of the hydraulic turbine set is the same as that of the hydraulic turbine setThe real-time monitoring values of a plurality of sensors on one part are sequentially and correspondingly recorded as V 1 、V 2 、V 3 …V n-1 、V n Obtaining a reference standard of real-time monitoring values of a plurality of sensors on the same part by calculating original difference DIF of the real-time monitoring values of the plurality of sensors on different positions of the same part;
the vector dimension of the original difference DIF is (1, n ═ n-1)/2, and the original difference DIF is [ V ═ V 1 -V 2 ,V 1 -V 3 ,...,V 1 -V n-1 ,V 1 -V n ,V 2 -V 3 ,V 2 -V n-1 ,V 2 -V n ,...,V n-1 -V n ]If an abnormal condition still exists after a numerical value generated by real-time monitoring of a certain sensor on the same component in the hydraulic turbine set is matched with the original difference DIF, the abnormal condition is shown to exist at the position of the sensor of the component, and the server sends the monitored abnormal condition to the inside of the monitoring room for alarming and reminding.
Furthermore, the server also needs to calculate the maximum value, the minimum value, the average value and the variance of the difference values among the monitoring values of the plurality of sensors on the same component in the hydraulic turbine set in the starting process so as to serve as a reference standard of the real-time monitoring values of the sensors on the same component in the same hydraulic turbine set.
Furthermore, the calculation formula of the maximum difference value is DIF _ MAX (MAX) (DIF), the calculation formula of the minimum difference value is DIF _ MIN (MIN) (DIF), the calculation formula of the average difference value is DIF _ AVG (average) (DIF), and the calculation formula of the variance difference value is DIF _ VAR (VAR) (varianc) (DIF).
Furthermore, the server also needs to calculate the difference value of real-time monitoring values of a plurality of sensors on different components in the same hydraulic turbine set, and the installation positions of the plurality of sensors on another component in the hydraulic turbine set are recorded as E in sequence 1 、E 2 、E 3 …E m-1 、E m The real-time monitoring numerical values of a plurality of sensors on another part in the hydraulic turbine set are sequentially and correspondingly recorded as W 1 、W 2 、W 3 ……W m-1 、W m Inside of the calculation hydraulic turbine setAnd monitoring a value difference value by using a sensor between the same component, taking the difference value as a reference standard, and if an abnormal condition still exists after the value monitored by the sensor in real time on the internal component of the hydraulic turbine set is matched with the difference value, then the abnormal problem exists in the hydraulic turbine set.
Furthermore, the server also needs to calculate the max-max difference, the max-min difference, the min-max difference and the min-min difference of the real-time monitoring values of the sensors on different components in the same hydraulic turbine set, so as to be used as a reference standard of the real-time monitoring values of the sensors on different components in the hydraulic turbine set.
Further, the maximum-maximum difference is calculated by MAX _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The maximum-minimum difference calculation formula is MAX _ MIN _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m ) The calculation formula of the MIN-MAX difference is MIN _ MAX _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The minimum-minimum value difference is calculated by MIN _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m )。
Furthermore, a program for performing sliding window statistics on each difference value is installed inside the server.
Further, a historical data model for difference data training is also constructed in the server, and the historical data model training process comprises the following steps:
s1, selecting a reference data time range;
s2, calculating the difference and the related statistics as characteristic parameters;
s3, performing model training;
and S4, saving the model parameters.
Furthermore, the historical data model is constructed by any one or combination of 3-sigma, Tukey, PCA, Oneclass-SVM, isolated forest, neural network self-coding, LocalOutlierFactor and the like.
Furthermore, a 5G wireless network transmission mode is adopted between the sensor and the server to transmit the real-time monitoring signal data.
3. Advantageous effects
Compared with the prior art, the invention has the advantages that:
(1) this scheme is through using the difference of a plurality of monitoring points on the inside single part of hydraulic turbine unit as the characteristic, and whether judge equipment operation normal, can avoid because the difference of mounting process, cause the influence to the judgement of hydraulic turbine unit temperature abnormal state, be favorable to discovering the abnormal state of equipment operation in-process in advance, promoted hydraulic turbine unit temperature real-time monitoring's stable accurate nature to a certain extent.
(2) Through carrying out diversified difference to a plurality of sensor monitoring numerical values on same part and calculating, can effectual definition difference reasonable fluctuation range, promoted abnormal state's judgement precision to a certain extent.
(3) The calculation formulas of the difference values in all modes are pre-recorded into a program inside the server, and the calculation formulas can be directly called during server operation, so that the efficiency of the server in operation processing of the difference values is improved to a certain extent, and the timeliness of the server in judgment of abnormal data is guaranteed.
(4) Through the difference calculation to between two parts, then can judge for the state of part operating temperature, if there is the anomaly after the temperature matching who monitors in real time on certain part corresponds the difference, then this part of surface exists abnormal state, whether normal through the temperature difference and the statistics that use between the inside different parts of same hydraulic turbine group determine equipment operation, can avoid because operating mode and environmental factor change, judge the temperature anomaly of each inside part of hydraulic turbine group and cause the influence, the precision when having promoted temperature anomaly detection to a certain extent.
(5) The monitoring values of the sensors are diversified and calculated according to the difference values of different parts in the same hydraulic turbine set, the reasonable fluctuation range of the difference values can be defined effectively, and the judgment accuracy of abnormal states is improved to a certain extent.
(6) Through will be used for carrying out the program installation of sliding window statistics to each difference inside the server, can avoid the measurement process, because the data sudden change that the acquisition error leads to judges to cause the influence to unusual in this scheme, avoided to a certain extent because the invalid warning that the data sudden change leads to, the effectual convenience that has promoted in the device use.
(7) The historical data model is constructed through historical data calculation, data can be not required to be marked, abnormal analysis can be carried out through the historical trend, real-time data abnormal detection can also be carried out based on a sliding window, multiple analysis and judgment are carried out, the accuracy of temperature abnormal judgment is further improved, and the operating efficiency of the related hydraulic turbine unit is improved to a certain extent.
(8) Historical data model construction is carried out through a plurality of model construction modes, and the accuracy of analysis of internal information of the historical data model is effectively improved.
(9) Data transmission between a plurality of sensors and the server is realized through the mode that adopts 5G wireless transmission, need not to carry out complicated wiring operation to the installation of sensor, is favorable to promoting sensor installation convenience, the effectual mounting process who improves the sensor, simultaneously, based on 5G data transmission, can effectual guarantee data transmission stability and safety.
Drawings
FIG. 1 is a schematic diagram of the working structure of the present invention;
FIG. 2 is a schematic view of the structure of the measurement points of a component of the present invention;
FIG. 3 is a schematic view of the hydraulic turbine assembly of the present invention;
FIG. 4 is a schematic view of the structure of each measuring point of two comparative units according to the present invention;
FIG. 5 is a flow chart of historical data model training of the present invention;
FIG. 6 is a flow chart of the present invention for detecting temperature anomalies at multiple monitoring points for a single component;
FIG. 7 is a flow chart of real-time temperature anomaly detection between sliding window components in accordance with the present invention.
The reference numbers in the figures illustrate:
1. a hydropower station; 2. a water turbine unit; 3. a server; 4. and a monitoring room.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention; it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention.
In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "top/bottom", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "disposed," "sleeved/connected," "connected," and the like are to be construed broadly, e.g., "connected," which may be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
Example 1:
referring to fig. 1 to 7, a method for determining abnormal temperature of a turbine using big data includes building on a dam of a riverHydropower station 1, a plurality of hydraulic turbine units 2 are uniformly installed inside the hydropower station 1, a plurality of sensors at different positions are uniformly installed on parts inside each hydraulic turbine unit 2, the sensors are arranged as temperature sensors and used for monitoring the temperature of the installed positions of the sensors, a server 3 used for processing signals on the sensors is fixedly installed inside the hydropower station 1, a monitoring chamber 4 used for monitoring the internal processed signals of the server 3 is also installed inside the hydropower station 1, and the installed positions of the sensors on the same part inside each hydraulic turbine unit 2 are recorded as D in sequence 1 、D 2 、D 3 …D n-1 、D n The real-time monitoring values of a plurality of sensors on the same component in the hydraulic turbine unit 2 are sequentially and correspondingly recorded as V 1 、V 2 、V 3 …V n-1 、V n Obtaining a reference standard of real-time monitoring values of a plurality of sensors on the same part by calculating original difference DIF of the real-time monitoring values of the plurality of sensors on different positions of the same part;
the vector dimension of the original difference DIF is (1, n ═ n-1)/2, and the original difference DIF is [ V ═ V 1 -V 2 ,V 1 -V 3 ,...,V 1 -V n-1 ,V 1 -V n ,V 2 -V 3 ,V 2 -V n-1 ,V 2 -V n ,...,V n-1 -V n ]If an abnormal condition still exists after the numerical value generated by real-time monitoring of a certain sensor on the same part in the hydraulic turbine unit 2 is matched with the original difference value DIF, the abnormal condition is shown at the position of the sensor of the part, and the server 3 sends the monitored abnormal condition to the inside of the monitoring room 4 to alarm and remind.
When the hydraulic turbine set 2 is in normal operation, in order to ensure real-time monitoring of the working state of the hydraulic turbine set, measurement points are generally dispersedly arranged on a plurality of components in the hydropower station 1, a sensor is arranged on each detection point for real-time temperature monitoring, the absolute value of the temperature value of each measurement point is generally different in the starting process of the hydraulic turbine set 2, however, the relative differences between different measuring points on the same component within the same hydroelectric power station 1 are generally stable within a small interval, the variation of the values is generally small, the difference is usually caused by measurement error or noise, when the hydraulic turbine set 2 is abnormally operated, for example, the temperature of a corresponding measurement point is increased due to poor heat dissipation of a certain measurement point, at this time, the other measuring points of the monitoring component have small temperature change, so that the abnormity can be found early by calculating the difference value of different measuring points of the same monitoring component.
In the operation process of the scheme, the server 3 can mark a plurality of sensors on the same component in the same hydropower station 1, and if n measuring points exist on a certain component, assume that D 1 The real-time measurement of position is V 1 ，D 2 The real-time measurement of position is V 2 ，D n-1 The real-time measurement of position is V n-1 ，D n The real-time measurement of position is V n If the abnormal condition still exists after the value generated by the real-time monitoring of a certain sensor on the same part in the hydraulic turbine set 2 is matched with the original difference DIF, the abnormal condition at the position of the sensor of the part is indicated, the server 3 sends the monitored abnormal condition to the inside of the monitoring room 4 for alarming and reminding, and the difference of a plurality of monitoring points on a single part in the hydraulic turbine set 2 is used as a characteristic to judge whether the equipment is normal or not, thereby avoiding the influence on the judgment of the abnormal condition of the temperature of the hydraulic turbine set 2 due to the difference of the installation process and being beneficial to finding the abnormal condition in the running process of the equipment in advance, the stability and accuracy of the real-time monitoring of the temperature of the hydraulic turbine set 2 are improved to a certain extent.
The server 3 still needs to calculate the difference maximum value, the minimum value, the average value, the variance between a plurality of sensor monitoring values on the same inside part of the hydraulic turbine set 2 in the starting process to be used as the reference standard of the sensor real-time monitoring values on the same inside part of the hydraulic turbine set 2, when the temperature monitoring is carried out by adopting the scheme, the diversified difference calculation is carried out on a plurality of sensor monitoring values on the same part, the reasonable fluctuation range of the difference can be defined effectively, and the judgment accuracy of the abnormal state is improved to a certain extent.
The calculation formula of the maximum difference value is DIF _ MAX (MAX) (DIF), the calculation formula of the minimum difference value is DIF _ MIN (MIN) (DIF), the calculation formula of the mean difference value is DIF _ AVG (AVERAGE) (DIF), and the calculation formula of the VARIANCE difference value is DIF _ VAR (VARIANCE) (DIF), when the scheme is adopted for temperature monitoring, the MAX is the maximum value, the MIN is the minimum value, the AVERAGE is the mean value, and the VARIANCE difference value is recorded in advance in a program in the server 3, so that the calculation formula of the difference values in all modes can be directly called during operation processing of the server 3, the efficiency of the server 3 for operation processing of the difference values is improved to a certain extent, and the timeliness of judging abnormal data by the server 3 is favorably ensured.
Referring to fig. 4, the server 3 also needs to calculate the difference between the real-time monitoring values of the sensors on different components in the same hydraulic turbine set 2, and the installation positions of the sensors on another component in the hydraulic turbine set 2 are sequentially recorded as E 1 、E 2 、E 3 …E m-1 、E m The real-time monitoring values of the sensors on the other part in the hydraulic turbine set 2 are sequentially and correspondingly recorded as W 1 、W 2 、W 3 ……W m-1 、W m And calculating the difference value of the monitoring values of the sensors among different parts in the hydraulic turbine set 2, and taking the difference value as a reference standard, if the values monitored by the sensors in real time on the parts in the hydraulic turbine set 2 are matched with the difference value and then are in an abnormal state, then the problem that the hydraulic turbine set 2 is abnormal is solved.
When the scheme is adopted for temperature monitoring, under the same working condition and environment, the temperature relevance between different parts in the same hydraulic turbine set 2 is strong, the same change trend can be presented generally, the difference value is a dynamic stable state under the normal condition, if a certain part of the hydraulic turbine set 2 fails or fails, the stability can be damaged, and therefore, the difference value of the two monitoring parts is calculated to judge whether the temperature states of the different parts in the hydraulic turbine set 2 are abnormal or notThe decision provides a further criterion, assuming that component 1 and component 2 are present inside the hydro-turbine unit 2, marked with monitoring points D and E on component 1 and component 2, respectively, where component 1 has n (n ≧ 1) monitoring points, D 1 The real-time measurement of position is V 1 ，D 2 The real-time measurement of position is V 2 ，D n-1 The real-time measurement of position is V n-1 ，D n The real-time measurement of position is V n (ii) a Part 2 has m (m is more than or equal to 1) monitoring points, E 1 The real-time measurement of position is W 1 ，E 2 The real-time measurement of position is W 2 ，E m-1 The real-time measurement of position is W m-1 ，E m The real-time measurement of position is W m The difference between the two components is calculated, the state of the running temperature of the components can be judged, if the temperature monitored in real time on one component is abnormal after being matched with the corresponding difference, the component is in an abnormal state on the surface, whether the equipment runs normally is judged by using the temperature difference between different components inside the same hydraulic turbine set 2 and the statistical value, the influence on the abnormal judgment of the temperature of each component inside the hydraulic turbine set 2 due to the change of working conditions and environmental factors can be avoided, and the precision of the abnormal detection of the temperature is improved to a certain extent.
The server 3 also needs to calculate the maximum-maximum difference, the maximum-minimum difference, the minimum-maximum difference and the minimum-minimum difference of the real-time monitoring values of the sensors on different components in the same hydraulic turbine set 2 to serve as a reference standard of the real-time monitoring values of the sensors on different components in the hydraulic turbine set 2, and when the scheme is adopted for temperature monitoring, the reasonable fluctuation range of the difference value can be effectively defined by calculating diversified difference values of the monitoring values of the sensors on different components in the same hydraulic turbine set 2, and the judgment accuracy of the abnormal state is improved to a certain extent.
The maximum-maximum difference is calculated by MAX _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The maximum-minimum difference calculation formula is MAX _ MIN _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m ) The calculation formula of the MIN-MAX difference is MIN _ MAX _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The minimum-minimum value difference is calculated by MIN _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m ) When the scheme is adopted for temperature monitoring, the calculation formula of the related difference value can be directly called by the server 3, and the efficiency of the server 3 for data operation processing is improved to a certain extent.
The server 3 is internally provided with a program for counting the sliding windows of the difference values, and when the scheme is adopted for temperature monitoring, the characteristics and the calculation mode of the difference value sliding window statistics are as follows:
mean window difference mean: AVERAGE (WINDOW (AVG _ DIFF));
window mean difference variance: VARIANCE (WINDOW (AVG _ DIFF));
maximum window mean difference: MAX (WINDOW (AVG _ DIFF));
window average difference minimum: MIN (WINDOW (AVG _ DIFF));
window average difference percentile vector: PERCENTILE (WINDOW (AVG _ DIFF));
window max-max difference mean: AVERAGE (WINDOW (MAX _ DIFF));
window max-max difference variance: VARIANCE (WINDOW (MAX _ DIFF));
window max-min mean of difference: AVERAGE (WINDOW (MAX _ MIN _ DIFF));
window max-min difference variance: VARIANCE (WINDOW (MAX _ MIN _ DIFF));
window min-max mean of difference: AVERAGE (WINDOW (MIN _ MAX _ DIFF));
window min-max difference variance: VARIANCE (WINDOW (MIN _ MAX _ DIFF));
window min-min mean of difference: AVERAGE (WINDOW (MIN _ DIFF));
window min-minimum difference variance: VARIANCE (WINDOW (MIN _ MIN _ DIFF));
wherein: WINDOW is a WINDOW function, and if the size of a WINDOW is 1 of the hydropower station, data is acquired every 5 seconds, and the WINDOW function acquires the data within the last 500 seconds;
through will be used for carrying out the program installation of sliding window statistics to each difference inside server 3, can avoid the measurement process, because the data sudden change that the acquisition error leads to judges to cause the influence to unusual in this scheme, avoided to a certain extent because the invalid warning that the data sudden change leads to, the effectual convenience that has promoted in the device use.
Referring to fig. 5-7, the server 3 also builds a historical data model for difference data training, and the historical data model training process includes the following steps:
s1, selecting a reference data time range;
s2, calculating the difference and the related statistics as characteristic parameters;
s3, performing model training;
s4, model parameters are saved, when the scheme is adopted for temperature monitoring, a historical data model is constructed through historical data calculation, data do not need to be marked, abnormal analysis can be carried out through historical trends, real-time data abnormal detection can also be carried out on the basis of a sliding window, multiple analysis and judgment are carried out, the accuracy of temperature abnormal judgment is further improved, and the operation efficiency of the related hydraulic turbine unit 2 is improved to a certain extent.
The historical data model is constructed by any one or combination of a plurality of 3-sigma, Tukey, PCA, Oneclass-SVM, isolated forest, neural network self-coding, LocalOutlierFactor and the like, and when the scheme is adopted for temperature monitoring, the historical data model is constructed by a plurality of model construction modes, so that the accuracy of internal information analysis of the historical data model is effectively improved.
Adopt 5G wireless network transmission's mode to carry out the transmission of real-time supervision signal data between sensor and the server 3, adopt this scheme to carry out temperature monitoring time measuring, data transmission between a plurality of sensors and the server 3 is realized through the mode that adopts 5G wireless transmission, need not to carry out complicated wiring operation to the installation of sensor, be favorable to promoting sensor installation convenience, the effectual mounting process who improves the sensor, and simultaneously, based on 5G data transmission, can the stable security of effectual guarantee data transmission.
The above are merely preferred embodiments of the present invention; the scope of the invention is not limited thereto. Any person skilled in the art should be able to cover the technical scope of the present invention by equivalent or modified solutions and modifications within the technical scope of the present invention.
Claims (9)
1. A method for judging temperature abnormity of a water turbine by utilizing big data is characterized by comprising the following steps: including building power station (1) on river dam, a plurality of hydraulic turbine group (2), every are evenly installed to the inside of power station (1) a plurality of sensors that are in different positions are equally distributed to install on the inside part of hydraulic turbine group (2), the sensor sets up to temperature sensor for monitor the temperature on its mounted position, the inside fixed mounting of power station (1) has server (3) that is used for going on handling the sensor signal, the inside of power station (1) still installs and is used for carrying out monitoring room (4) that monitor server (3) internal processing signal, the mounted position of a plurality of sensors records in proper order for D on the inside same part of hydraulic turbine group (2) 1 、D 2 、D 3 …D n-1 、D n The real-time monitoring numerical values of a plurality of sensors on the same component in the hydraulic turbine set (2) are sequentially and correspondingly recorded as V 1 、V 2 、V 3 …V n-1 、V n Obtaining a reference standard of real-time monitoring values of a plurality of sensors on the same part by calculating original difference DIF of the real-time monitoring values of the plurality of sensors on different positions of the same part;
the vector dimension of the original difference DIF is (1, n ═ n-1)/2, and the original difference DIF is [ V ═ V 1 -V 2 ,V 1 -V 3 ,...,V 1 -V n-1 ,V 1 -V n ,V 2 -V 3 ,V 2 -V n-1 ,V 2 -V n ,...,V n-1 -V n ]If an abnormal condition still exists after a numerical value generated by real-time monitoring of a certain sensor on the same component in the hydraulic turbine set (2) is matched with an original difference value DIF, the abnormal condition is shown to exist at the position of the sensor of the component, and the server (3) sends the monitored abnormal condition to the inside of the monitoring room (4) for alarming and reminding.
2. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 1, wherein the method comprises the following steps: the server (3) also needs to calculate the maximum value, the minimum value, the average value and the variance of the difference values among the monitoring values of the sensors on the same component in the hydraulic turbine set (2) in the starting process so as to serve as the reference standard of the real-time monitoring values of the sensors on the same component in the hydraulic turbine set (2).
3. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 2, characterized in that: the calculation formula of the maximum difference value is DIF _ MAX (MAX) (DIF), the calculation formula of the minimum difference value is DIF _ MIN (MIN) (DIF), the calculation formula of the average difference value is DIF _ AVG (average) (DIF), and the calculation formula of the variance difference value is DIF _ VAR (VAR) (DIF).
4. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 1, wherein the method comprises the following steps: the server (3) also needs to calculate the difference value of real-time monitoring values of a plurality of sensors on different components in the same hydraulic turbine set (2), and the installation positions of the plurality of sensors on another component in the hydraulic turbine set (2) are recorded as E in sequence 1 、E 2 、E 3 …E m-1 、E m The real-time monitoring numerical values of a plurality of sensors on another part in the hydraulic turbine set (2) are sequentially and correspondingly recorded as W 1 、W 2 、W 3 ……W m-1 、W m And calculating the difference value of the monitoring values of the sensors among different parts in the hydraulic turbine set (2), and taking the difference value as a reference standard, if the values monitored by the sensors in real time on the parts in the hydraulic turbine set (2) are matched with the difference value and then are in an abnormal state, then the problem that the hydraulic turbine set (2) is abnormal is solved.
5. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 4, wherein the method comprises the following steps: the server (3) also needs to calculate the maximum-maximum difference, the maximum-minimum difference, the minimum-maximum difference and the minimum-minimum difference of the real-time monitoring values of the sensors on different components in the same hydraulic turbine set (2) so as to be used as the reference standard of the real-time monitoring values of the sensors on different components in the hydraulic turbine set (2).
6. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 5, wherein the method comprises the following steps: the maximum-maximum difference calculation formula is MAX _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The maximum-minimum difference calculation formula is MAX _ MIN _ DIFF ═ MAX (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m ) The calculation formula of the MIN-MAX difference is MIN _ MAX _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MAX(W 1 ,W 2 ,...,W m-1 ,W m ) The minimum-minimum value difference is calculated by MIN _ DIFF ═ MIN (V) 1 ,V 2 ,...,V n-1 ,V n )-MIN(W 1 ,W 2 ,...,W m-1 ,W m )。
7. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 6, wherein the method comprises the following steps: and a program for counting each difference value by a sliding window is installed in the server (3).
8. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 7, wherein the method comprises the following steps: the server (3) is internally constructed with a historical data model for difference data training, and the historical data model training process comprises the following steps:
s1, selecting a reference data time range;
s2, calculating the difference and the related statistics as characteristic parameters;
s3, carrying out model training;
and S4, saving the model parameters.
9. The method for judging the abnormal temperature of the water turbine by utilizing the big data according to claim 8, wherein the method comprises the following steps: the historical data model is constructed by any one or combination of 3-sigma, Tukey, PCA, Oneclass-SVM, isolated forest, neural network self-coding, LocalOutlierFactor and the like.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210622320.5A CN114876699A (en) | 2022-06-02 | 2022-06-02 | Method for judging temperature abnormity of water turbine by utilizing big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210622320.5A CN114876699A (en) | 2022-06-02 | 2022-06-02 | Method for judging temperature abnormity of water turbine by utilizing big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114876699A true CN114876699A (en) | 2022-08-09 |
Family
ID=82679254
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210622320.5A Pending CN114876699A (en) | 2022-06-02 | 2022-06-02 | Method for judging temperature abnormity of water turbine by utilizing big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114876699A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02230045A (en) * | 1989-02-28 | 1990-09-12 | Daikin Ind Ltd | Air conditioning device |
| JPH09209908A (en) * | 1996-02-06 | 1997-08-12 | Toshiba Eng Co Ltd | Hydraulic turbine control device |
| JP2003262220A (en) * | 2002-03-08 | 2003-09-19 | Nsk Ltd | Structure equipped with bearing device with sensor and abnormality detecting method of bearing device with sensor in the structure |
| CN108362497A (en) * | 2018-03-08 | 2018-08-03 | 云南电网有限责任公司电力科学研究院 | A kind of method and system judged extremely for water turbine set bearing temperature |
| CN111159844A (en) * | 2019-12-02 | 2020-05-15 | 中国电建集团江西省电力设计院有限公司 | Abnormity detection method for exhaust temperature of gas turbine of power station |
| CN113984246A (en) * | 2021-10-28 | 2022-01-28 | 安阳市蓝海安全工程师事务所有限公司 | Chemical safety production monitoring method and system based on temperature sensing |
-
2022
- 2022-06-02 CN CN202210622320.5A patent/CN114876699A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH02230045A (en) * | 1989-02-28 | 1990-09-12 | Daikin Ind Ltd | Air conditioning device |
| JPH09209908A (en) * | 1996-02-06 | 1997-08-12 | Toshiba Eng Co Ltd | Hydraulic turbine control device |
| JP2003262220A (en) * | 2002-03-08 | 2003-09-19 | Nsk Ltd | Structure equipped with bearing device with sensor and abnormality detecting method of bearing device with sensor in the structure |
| CN108362497A (en) * | 2018-03-08 | 2018-08-03 | 云南电网有限责任公司电力科学研究院 | A kind of method and system judged extremely for water turbine set bearing temperature |
| CN111159844A (en) * | 2019-12-02 | 2020-05-15 | 中国电建集团江西省电力设计院有限公司 | Abnormity detection method for exhaust temperature of gas turbine of power station |
| CN113984246A (en) * | 2021-10-28 | 2022-01-28 | 安阳市蓝海安全工程师事务所有限公司 | Chemical safety production monitoring method and system based on temperature sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7933724B2 (en) | Method of tracking the performance of an industrial appliance | |
| CN110674001B (en) | Server, and temperature alarm method and system based on server | |
| CN110378042A (en) | Gearbox of wind turbine oil temperature method for detecting abnormality and system based on SCADA data | |
| CN117082105B (en) | Environment-friendly intelligent hospital facility monitoring system and method | |
| CN113359637A (en) | Data quality guarantee system and method based on station house operation environment and equipment operation state | |
| CN114777003A (en) | Power plant auxiliary engine lubricating oil monitoring system and method | |
| US8955372B2 (en) | Systems and methods for continuous pressure change monitoring in turbine compressors | |
| CN116881673B (en) | Shield tunneling machine operation and maintenance method based on big data analysis | |
| CN116772285B (en) | Intelligent building heating load safety real-time monitoring method | |
| CN114876699A (en) | Method for judging temperature abnormity of water turbine by utilizing big data | |
| CN113934191A (en) | Fault diagnosis system for water chilling unit | |
| CN117455242A (en) | Water conservancy management system based on digital twinning | |
| CN117423225A (en) | Disaster remote sensing early warning system based on high-speed railway operation | |
| CN117134490A (en) | Cloud platform-based intelligent surge protector monitoring system and method | |
| KR100567434B1 (en) | On-Line Monitoring System for Pump Stations | |
| CN110568257A (en) | continuous monitoring method and device for energy consumption of air conditioner | |
| CN111677673A (en) | Water pump health detection device | |
| CN217206708U (en) | Hydroelectric set state monitoring and sensor fault diagnosis system | |
| CN117166970B (en) | Remote monitoring system and method for tower type pumping unit | |
| CN117193095B (en) | Intelligent control system for hydraulic power pump station | |
| CN117708748B (en) | Operation monitoring system and method for centrifugal fan | |
| CN117932440A (en) | Temperature and humidity monitoring method and system for data machine room, computer equipment and storage medium | |
| CN117439540A (en) | PR value monitoring system for photovoltaic station | |
| CN112629710A (en) | Intelligent self-diagnosis method for engine temperature sensor | |
| CN117554785A (en) | Chip detection method and system |
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 |