CN112885047B - Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine - Google Patents
Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine Download PDFInfo
- Publication number
- CN112885047B CN112885047B CN202110053557.1A CN202110053557A CN112885047B CN 112885047 B CN112885047 B CN 112885047B CN 202110053557 A CN202110053557 A CN 202110053557A CN 112885047 B CN112885047 B CN 112885047B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- type
- early warning
- preset
- unit
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an intelligent early warning method for monitoring the state of a unit, which comprises the following steps: determining a first monitoring system for monitoring the running state of the hydroelectric generating set, wherein the first monitoring system comprises at least one type of monitoring quantity; judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity; and when the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity, obtaining a type of detection result of each type of monitoring quantity by a continuous increasing trend detection method according to the obtained monitoring record text of each type of monitoring quantity. The invention also discloses an intelligent early warning method for monitoring the state of the transformer and an intelligent early warning method for monitoring the state of the auxiliary machine. The method can intelligently analyze the change trend of different hydropower station equipment state monitoring data, and can effectively improve the timeliness and accuracy of trend early warning.
Description
Technical Field
The invention belongs to the technical field of equipment monitoring, and particularly relates to an intelligent early warning method for monitoring states of a unit, a transformer and an auxiliary machine.
Background
Hydroelectric generating sets, transformers and auxiliary machines are important electrical equipment in hydropower stations, which directly affect the safe operation level of the hydropower station system and cause huge direct and indirect losses once faults occur. At present, an out-of-limit early warning method and a trend early warning method based on manual analysis are mainly adopted for monitoring the running state of equipment (including a hydroelectric generating set, a transformer, an auxiliary machine and the like) in a hydropower station.
(1) And (4) an out-of-limit value alarm method. The method comprises the steps of detecting whether state monitoring data of the equipment reach a set limit value or not in real time by setting limit values, such as an upper limit value and a lower limit value, of monitoring points of the equipment, and outputting early warning if the state monitoring data reach the set limit value. For example, for monitoring the operating state of the transformer, the health state of the transformer can be judged by judging whether the content of each gas in the transformer oil exceeds a standard limit value, and the early deterioration is difficult to find. Because the state monitoring data of the equipment is obviously changed under the influence of factors such as the operation condition of the equipment, the environment and the like, the early warning is carried out by using a fixed limit value, and the early warning error is large, thereby causing the problem of false alarm or abnormal non-alarm.
(2) A trend early warning method based on manual analysis. Monitoring data trend analysis is set in an analysis function of an equipment monitoring system applied to a hydropower station, a data analyst evaluates the running state of the equipment by performing trend analysis on state monitoring data of the equipment, and when the condition monitoring data of the equipment show monotonous change trend, the data analyst manually pushes a conclusion that the equipment is abnormal to perform shutdown maintenance for operation maintenance personnel. However, the monitoring data volume of the equipment state is large, the workload of a data analyst and the sensitivity to the data are high, and the timeliness of the manual participation in analysis and early warning is difficult to guarantee.
Disclosure of Invention
An embodiment of the present invention provides an intelligent early warning method for monitoring states of a unit, a transformer, and an auxiliary machine, so as to overcome at least one of the above problems in the prior art.
Based on the above purpose, in a first aspect, an embodiment of the present invention provides an intelligent early warning method for monitoring a unit state, including:
determining a first monitoring system for monitoring the running state of the hydroelectric generating set, wherein the first monitoring system comprises at least one type of monitoring quantity;
judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity;
and when the current unit working condition data meets the working condition judgment condition corresponding to each type of the monitoring quantity, acquiring a type of detection result of each type of the monitoring quantity through a continuous increasing trend detection method according to the acquired monitoring record text of each type of the monitoring quantity.
Preferably, the intelligent early warning method for monitoring the state of the unit further comprises the following steps:
according to the monitoring record text of each type of the monitoring quantity, obtaining a second type of detection result of each type of the monitoring quantity through a Mankendall trend detection method;
and performing trend early warning of each type of the monitored quantity according to the first type detection result and the second type detection result of each type of the monitored quantity.
Preferably, the obtaining of the second type of detection result of each type of the monitoring amount by a manksendel trend detection method according to the monitoring record text of each type of the monitoring amount includes:
obtaining an average measured value of each type of monitoring quantity in a preset monitoring period from a monitoring record text of each type of monitoring quantity;
processing the average measured value of each type of monitored quantity in a preset monitoring period by adopting a Mankender trend verification algorithm to obtain the trend change of each type of monitored quantity;
and acquiring a second type detection result of each type of the monitored quantity according to the trend change of each type of the monitored quantity and a preset confidence threshold.
Preferably, the first monitoring system comprises a first type monitoring quantity, a second type monitoring quantity and a third type monitoring quantity; the first type of monitoring quantity comprises guide bearing temperature and oil groove temperature; the second type of monitoring includes the stator core temperature, the stator coil temperature, the air cooler outlet temperature and the air cooler inlet temperature; the three types of monitoring quantities comprise oil tank oil level and water flow; the unit working condition data comprises power generation state information and active power information of the unit;
the judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity includes:
when the power generation state information of the unit is changed from '0' to '1', and the starting operation time length reaches a preset first time length, and the active power information of the unit reaches a preset first power, determining that the working condition judgment condition corresponding to one type of monitoring quantity is met;
when the power generation state information of the unit is changed from '0' to '1', and the starting operation time length reaches a preset first time length and the active power information of the unit reaches a preset second power, determining that the working condition judgment condition corresponding to the second type of monitoring quantity is met; the preset second power is set within a preset rated load range;
and when the power generation state information of the unit is changed from '0' to '1' and the active power information of the unit reaches a preset third power, determining that the working condition judgment condition corresponding to the three types of monitoring quantities is met.
Preferably, the obtaining a type of detection result of each type of the monitored quantity by a continuous increasing trend detection method according to the obtained monitoring record text of each type of the monitored quantity includes:
and obtaining the measured value of each type of the monitoring quantity, obtaining the average measured value of each type of the monitoring quantity through a preset average value model, and storing the average measured value in a monitoring record text.
Acquiring preset first number of average measured values from each type of monitoring record text of the monitoring quantity;
fitting the preset first number of average measured values to obtain a fitting curve of each type of the monitored quantity;
acquiring a first characteristic value for representing the variation trend of each type of the monitored quantity according to the fitted curve of each type of the monitored quantity;
and determining a class detection result of each class of the monitored quantity according to each first characteristic value and a preset early warning threshold value.
The intelligent unit state early warning method provided by the embodiment of the invention is based on a first monitoring system for monitoring the running state of a unit, and utilizes a continuous increasing trend detection method to track and analyze the monitoring value change trend of each type of monitoring quantity in the first monitoring system in real time, so as to realize intelligent unit state monitoring early warning.
In a second aspect, an embodiment of the present invention provides an intelligent early warning method for monitoring a transformer state, including:
determining a second monitoring system for monitoring the running state of the transformer;
acquiring class I monitoring parameters from the second monitoring system, and acquiring a class I early warning result according to an acquired monitoring record text of the class I monitoring parameters and a continuous increasing trend detection method when the current unit working condition data meets working condition judgment conditions corresponding to the class I monitoring parameters; the type I monitoring parameters refer to data which have a correlation with the working condition data of the unit;
acquiring class II monitoring parameters from the second monitoring system, and acquiring a class II early warning result set according to the acquired monitoring record text of the class II monitoring parameters and the continuous increasing trend detection method; the type II monitoring parameters refer to data which has no correlation with the unit working condition data.
Preferably, the class i monitoring parameter is a transformer temperature; the monitoring record text of the class I monitoring parameters is a temperature record text; the unit working condition data comprises power generation state information and active power information of the unit;
when the current unit working condition data meet the working condition judgment condition, acquiring a type I early warning result by a continuous increasing trend detection method according to the acquired monitoring record text of the type I monitoring parameters, wherein the method comprises the following steps:
if the power generation state information of the unit is changed from '0' to '1', and after the operation time of the unit reaches the preset second time, the active power information of the unit reaches the preset fourth power, determining that the working condition judgment condition corresponding to the temperature of the transformer is met;
acquiring a measured value of the temperature of the transformer, calculating a temperature average value through a preset average value model, and storing the temperature average value into a temperature recording text;
acquiring a preset second number of temperature average values from the temperature recording text, and fitting the preset second number of temperature average values to acquire a transformer temperature curve;
and acquiring a second characteristic value for representing the temperature trend change of the transformer according to the temperature curve of the transformer, and acquiring a class of early warning results according to the second characteristic value and a preset early warning threshold value.
Preferably, the class II monitoring parameters are the content and the absolute gas production rate of each gas in the transformer oil; the monitoring record text of the II-type monitoring parameters is a gas record text;
the acquiring a second-class early warning result set according to the acquired monitoring record text of the second-class monitoring parameters by the continuous increasing trend detection method comprises the following steps:
the method comprises the steps of obtaining the content of each gas in each operation day through an oil chromatography online monitoring device arranged on a transformer, calculating the average content value and the absolute gas production rate of each gas, and storing the average content value and the absolute gas production rate of each gas in a gas recording text in a correlation manner;
acquiring a preset third quantity of the content average value and the absolute gas production rate from the gas recording text, and fitting the preset third quantity of the content average value and the absolute gas production rate to acquire a gas content curve and a gas production rate curve;
and acquiring a characteristic value set for representing the trend change of the gas content and the trend change of the gas generation rate according to the gas content curve and the gas generation rate curve, and acquiring a second-class early warning result set according to the characteristic value set and a preset early warning threshold value.
The intelligent early warning method for the transformer state provided by the embodiment of the invention is based on a second monitoring system for monitoring the running state of the transformer, and utilizes a continuous increasing trend detection method to track and analyze the monitoring value change trends of class I monitoring parameters and class II monitoring parameters in the second monitoring system in real time, so that the intelligent early warning for the transformer state monitoring is realized.
In a third aspect, an embodiment of the present invention provides an auxiliary machine state monitoring intelligent early warning method, including:
determining a third monitoring system for monitoring the operation state of the auxiliary machine, wherein the third monitoring system comprises at least one monitoring index;
acquiring a monitoring record text of each monitoring index under the operation condition of each unit;
and acquiring a detection result set of each monitoring index through a preset data trend detection system according to the monitoring record text of each monitoring index, and performing trend early warning on each monitoring index according to the detection result set of each monitoring index.
Preferably, the third monitoring system comprises the operation loading time of the auxiliary machine and the start-stop interval time of the auxiliary machine; the data trend detection system includes a continuously increasing trend detection method and a mankendel trend detection method.
Preferably, the auxiliary machine state monitoring intelligent early warning method further includes:
acquiring start-stop state data of a hydroelectric generating set associated with an auxiliary machine;
and inputting the start-stop state data to a preset working condition division model to obtain the unit operation working condition.
Preferably, the start-stop state data includes power generation state information and shutdown state information; the unit operation working conditions comprise a power generation working condition, a shutdown working condition and a start-stop working condition; the working condition division model comprises the following steps:
wherein, condition 1 is a power generation condition, condition 2 is a shutdown condition, condition 3 is an open-shutdown condition, power state is power generation state information, and down state is shutdown state information.
The auxiliary machine state intelligent early warning method provided by the embodiment of the invention is based on a third monitoring system for monitoring the operation state of the auxiliary machine, and the data trend detection system is utilized to track and analyze the monitoring numerical value change trend of each monitoring index in the third monitoring system under different unit operation conditions in real time, so that the auxiliary machine state intelligent early warning is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of an intelligent early warning method for monitoring the state of a unit according to an embodiment of the present invention;
fig. 2 is a flowchart of step S103 in the intelligent pre-warning method for monitoring the state of a unit according to an embodiment of the present invention;
FIG. 3 is a flow chart of an intelligent pre-warning method for monitoring the state of a unit according to another embodiment of the present invention;
FIG. 4 is a flowchart of an intelligent early warning method for monitoring transformer status according to an embodiment of the present invention;
fig. 5 is a flowchart of step S202 in the transformer state monitoring intelligent warning method according to an embodiment of the present invention;
fig. 6 is a flowchart of step S203 in the transformer state monitoring intelligent early warning method according to an embodiment of the present invention;
fig. 7 is a flowchart of an auxiliary device state monitoring intelligent early warning method according to an embodiment of the present invention;
fig. 8 is a flowchart of an auxiliary device state monitoring intelligent warning method according to another embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1, an embodiment of the present invention provides an intelligent early warning method for monitoring a unit state, including the following steps:
step S101, a first monitoring system for monitoring the running state of the water turbine generator set is determined, and the first monitoring system comprises at least one type of monitoring quantity.
In this embodiment, the first monitoring system includes, but is not limited to, a first type of monitoring quantity and a second type of monitoring quantity related to the temperature parameter, and a third type of monitoring quantity related to the liquid level parameter; one type of monitored quantities includes, but is not limited to, guide bearing temperature and oil bath temperature, a second type of monitored quantities includes stator core temperature, stator coil temperature, air cooler outlet temperature and air cooler inlet temperature, and a third type of monitored quantities includes, but is not limited to, oil bath level and water flow.
And S102, judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity.
In the present embodiment, each type of monitoring amount corresponds to one condition determination condition. The unit working condition data comprises power generation state information (the power generation state information is one of start-stop state data) and active power information of the unit.
The guide bearing temperature and the oil groove temperature of the water turbine generator set have a correlation with whether the generator set is in a starting operation state or not and the starting operation time, so that the working condition judgment condition of one type of monitoring quantity can be set to be that the generating state information of the generator set is changed from '0' to '1', and the generator set is in the starting operation state at the moment.
The stator core temperature, the stator coil temperature, the air cooler outlet temperature, the air cooler inlet temperature and the startup operation time have a correlation with the unit load, so that the working condition judgment condition corresponding to the second type can be set as that the active power information of the unit is in a range of 70-100% of rated load, and the unit is in a high-power operation state at the moment.
The oil level and the water flow of the oil groove are related to whether the unit starts to operate, so that the working condition judgment condition corresponding to the third type can be set as that the active power of the unit exceeds (is larger than) the on-load limit value, the on-load limit value is 5 Megawatts (MW), and the unit is in an on-load power generation state at the moment.
Preferably, step S102 specifically includes the following steps:
step one, when the power generation state information of the unit is changed from '0' to '1', the starting operation time length reaches a preset first time length, and the active power information of the unit reaches a preset first power, determining that the working condition judgment condition corresponding to one type of monitoring quantity is met. The preset first time and the preset first power may be set according to requirements, for example, the preset first time is 2 hours, and the preset first power is 5 mw.
After the working condition judgment conditions corresponding to the first type of measurement are met, the measured values of the first type of monitoring quantity can be collected according to the preset collection frequency, the refreshed unit working condition data are obtained when the collection time reaches the preset refreshing time, whether the refreshed unit working condition data meet the working condition judgment conditions corresponding to the first type of monitoring quantity or not is judged again, and the data collection is stopped when the power generation state information of the unit is detected to be changed from '1' to '0'. The preset refresh duration may be set according to a requirement, for example, the preset refresh duration is 2 minutes.
And step two, when the power generation state information of the unit is changed from '0' to '1', the starting operation time length reaches a preset first time length, and the active power information of the unit reaches a preset second power, determining that the working condition judgment condition corresponding to the second type of monitoring quantity is met. Wherein the preset second power is set within the range of 70% -100% of rated load.
After the working condition judgment conditions corresponding to the second-class measurement are met, the measured values of the second-class monitoring quantities can be collected according to the preset collection frequency, the refreshed unit working condition data are obtained when the collection duration reaches the preset refreshing duration, whether the refreshed unit working condition data meet the working condition judgment conditions corresponding to the second-class monitoring quantities or not is judged again, and data collection is stopped when the power generation state information of the unit is detected to be changed from '1' to '0'.
And step three, changing the power generation state information of the unit from '0' to '1', and determining that the working condition judgment conditions corresponding to the three types of monitoring quantities are met when the active power information of the unit reaches a preset third power. The preset third power may be set according to a requirement, for example, the preset third power is 5 Megawatts (MW).
After the working condition judgment conditions corresponding to the three types of measurement are met, the measured values of the three types of monitoring quantities can be collected according to the preset collection frequency, the refreshed unit working condition data are obtained when the collection time reaches the preset refreshing time, whether the refreshed unit working condition data meet the working condition judgment conditions corresponding to the two types of monitoring quantities is judged again, and the data collection is stopped when the active power information of the unit is detected not to reach the preset third power.
It should be noted that step one, step two, and step three may be performed simultaneously, or a certain step may be performed better than other steps.
And S103, when the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity, obtaining a type of detection result of each type of monitoring quantity through a continuous increasing trend detection method according to the obtained monitoring record text of each type of monitoring quantity.
In this embodiment, the monitoring record text is used for storing the monitoring quantity of the monitoring quantity, the data in the monitoring record text is stored according to the sequence of data acquisition, and the data in the monitoring record text has a data validity period, that is, when the data in the monitoring record text exceeds the data validity period, the data will be cleared. Preferably, as shown in fig. 2, step S103 specifically includes the following steps:
and step S1031, obtaining the measured value of each type of monitoring quantity, obtaining the average measured value of each type of monitoring quantity through a preset average value model, and storing the measured average value in a monitoring record text. Wherein, the mean model is specifically expressed as:
in the formula (1), μ is an average measured value, XiIs the ith measurement, and N is the number of measurements involved in the calculation.
Step S1032 acquires the preset first number of average measurement values from the monitoring record text of each type of monitoring amount. The preset first number may be set according to a requirement, for example, the preset first number is 15.
Step S1033, fitting the average measured values of the preset first number to obtain a fitting curve of each type of monitored quantity.
And S1034, acquiring a first characteristic value for representing the variation trend of each type of the monitoring quantity according to the fitted curve of each type of the monitoring quantity. The first characteristic value is a ratio of the last fitting value to the first fitting value obtained by inverse calculation in the fitting curve, and the number of the fitting values in the fitting curve is related to a preset first number.
Step S1035, determining a class detection result of each class of monitored quantity according to each first characteristic value and a preset early warning threshold. The preset early warning threshold value can be set according to the early warning grade, and the higher the early warning grade is, the larger the corresponding early warning threshold value is.
In this embodiment, each type of monitoring amount corresponds to one monitoring record text and one fitting curve. The following monitoring quantities including the guide bearing temperature and the oil groove temperature of the water turbine generator set are used for illustration: after temperature values of the guide bearing temperature and the oil tank temperature are respectively obtained, firstly, measured values of the guide bearing temperature and the oil tank temperature are input into a mean value model to obtain temperature mean values of the guide bearing temperature and the oil tank temperature, the temperature mean values of the guide bearing temperature and the oil tank temperature are stored into a monitoring recording text, then, the latest preset first number of temperature mean values of the guide bearing temperature and the oil tank temperature are obtained from the monitoring recording text to carry out linear regression fitting to obtain a guide bearing temperature curve and an oil tank temperature curve, then, the last temperature value and the first temperature value in each curve are obtained through inverse calculation based on the guide bearing temperature curve and the oil tank temperature curve, the ratio of the last temperature value and the first temperature value is used as a first characteristic value, and finally, each first characteristic value is compared with an early warning threshold value corresponding to each early warning grade, and outputting the early warning grade corresponding to the early warning threshold value met by each first characteristic value as a class of detection result, thereby completing early warning of the temperature trend of the guide bearing and the temperature trend of the oil groove.
It should be noted that the trend early warning process of the second-class monitoring quantity and the third-class monitoring quantity is similar to the trend early warning process of the first-class monitoring quantity, and is not repeated again,
therefore, the intelligent pre-warning method for monitoring the unit state in the embodiment is based on the first monitoring system for monitoring the unit operation state, and the change trend of the monitoring value of each type of monitoring quantity in the first monitoring system is tracked and analyzed in real time by using the continuous increasing trend detection method, so that the intelligent pre-warning for monitoring the unit state is realized.
In an embodiment, as shown in fig. 3, the intelligent pre-warning method for the unit state further includes the following steps:
and step S104, acquiring a second type detection result of each type of monitoring quantity through a Mankendel trend detection method according to the monitoring record text of each type of monitoring quantity.
In this embodiment, for the monitored quantity related to the temperature parameter, the influence of the ambient temperature is large, and there may be a risk that the result may be unstable in one type of detection result obtained by the continuously increasing trend detection method.
Preferably, firstly, an average measured value of each type of monitoring quantity in a preset monitoring period is obtained from a monitoring record text; then, processing the average measured value of each type of monitored quantity in a preset monitoring period by adopting a Mankender trend verification algorithm to obtain the trend change of each type of monitored quantity; and finally, acquiring a second type detection result of each type of monitoring quantity according to the trend change of each type of monitoring quantity and a preset confidence level threshold value. The second type of detection results include normal trend changes and abnormal trend changes. The preset confidence threshold value in the preset monitoring period can be set according to requirements, for example, the preset monitoring period is 30 days, and the preset confidence threshold value is 2. It can be understood that if the trend change exceeds (is larger than) the preset confidence threshold, the second-class detection result is determined as the abnormal trend change, and if the trend change does not exceed (is smaller than or equal to) the preset confidence threshold, the second-class detection result is determined as the normal trend change.
And S105, performing trend early warning of each type of monitoring quantity according to the first type detection result and the second type detection result of each type of monitoring quantity.
Specifically, for a certain type of monitored quantity, if the first type of detection result obtained by the continuously increasing trend detection method is no early warning, and the second type of detection result obtained by the mankendel trend detection method is normal trend change, the trend early warning state of the monitored quantity is determined to be normal. And if the first-class detection result obtained by the continuous increasing trend detection method is any one early warning level or the second-class detection result obtained by the Mankendell trend detection method is abnormal trend change, determining that the trend early warning state of the monitoring quantity is abnormal, and further automatically pushing the unit warning information to equipment maintenance personnel.
It can be understood that the intelligent pre-warning method for monitoring the unit state of the embodiment performs the trend pre-warning of each type of monitoring quantity through the first type detection result and the second type detection result of each type of monitoring quantity, and further improves the accuracy of the trend pre-warning.
In addition, as shown in fig. 4, an embodiment of the present invention further provides an intelligent early warning method for monitoring a transformer state, including the following steps:
step S201, determining a second monitoring system for monitoring the running state of the transformer.
In this embodiment, the second monitoring system includes, but is not limited to, monitoring parameters such as the temperature of the transformer, the content of each gas (e.g., total hydrocarbons, acetylene, hydrogen, carbon monoxide, carbon dioxide, etc.) in the transformer oil, and the absolute gas production rate. In the hydropower station, the generated energy output by the water-turbine generator set is boosted by the transformer and then transmitted to the power grid, so that the temperature of the transformer has a correlation with the load of the water-turbine generator set and the starting operation time, namely, the temperature of the transformer has a correlation with the active power information and the power generation state information of the water-turbine generator set.
The content of each gas in the transformer oil is obtained by an oil chromatogram on-line monitoring device arranged on the transformer, and the daily absolute gas production rate of each gas is calculated.
Step S202, acquiring class I monitoring parameters from a second monitoring system, and acquiring a class I early warning result through a continuous increasing trend detection method according to an acquired monitoring record text of the class I monitoring parameters when the current unit working condition data meets the preset unit working condition corresponding to the class I monitoring parameters; the type I monitoring parameters refer to data which has a correlation relation with the working condition data of the unit.
In this embodiment, it is first detected whether each monitoring parameter in the second monitoring system has a correlation with the unit operating condition data, the monitoring parameter having a correlation with the unit operating condition data is labeled as a class i monitoring parameter, and the other monitoring parameters are labeled as class ii monitoring parameters, thereby completing the classification of the monitoring parameters.
In other embodiments, after step S202, the trend pre-warning of the class i monitoring parameters may be performed according to the monitoring record text of the class i monitoring parameters and by obtaining the reference pre-warning result through the mankendel trend detection method, and further by combining the class i pre-warning result obtained through the continuous increasing trend detection method and the reference pre-warning result obtained through the mankendel trend detection method. It should be noted that the trend early warning process of the class i monitoring parameters is similar to the trend early warning process of the monitoring quantity in the above-mentioned unit state monitoring intelligent early warning method embodiment, and is not repeated again.
Preferably, as shown in fig. 5, when the class i monitoring parameter is a transformer temperature, the monitoring record text of the class i monitoring parameter is a temperature record text, and the unit operating condition data includes active power information and power generation state information of the unit, and when the current unit operating condition data satisfies the operating condition determination condition corresponding to the class i monitoring parameter in step S202, the method obtains a class i warning result by a continuous increasing trend detection method according to the obtained monitoring record text of the class i monitoring parameter, and specifically includes the following steps:
step S2021, if the power generation state information of the unit is changed from "0" to "1", and after the unit operation time reaches the preset second time, the active power information of the unit reaches the preset fourth power, determining that the working condition judgment condition corresponding to the transformer temperature is met. The preset second time and the preset fourth power are set according to requirements, for example, the preset second time is set to 2 hours, and the preset fourth power is set within a range of 90% -100% of a rated load.
Step S2022, obtaining a measured value of the temperature of the transformer, calculating a temperature average value through a preset average value model, and storing the temperature average value into a temperature recording text.
Namely, after the working condition judgment condition corresponding to the transformer temperature is determined to be met, the temperature value of the transformer temperature is collected according to the preset sampling frequency, when the collection time reaches the preset refreshing time, the temperature average value is calculated through the preset average value model, meanwhile, the refreshed unit working condition data is obtained, whether the refreshed unit working condition data meets the working condition judgment condition corresponding to the transformer temperature is judged again, and when the power generation state information of the unit is detected to be changed from '1' to '0', the transformer temperature collection is stopped.
Step S2023, obtaining a preset second number of temperature average values from the temperature recording text, and fitting the preset second number of temperature average values to obtain a transformer temperature curve. The preset second number may be set according to requirements, for example, the preset second number is set to 15.
Step S2024, a second characteristic value used for representing the temperature trend change of the transformer is obtained according to the temperature curve of the transformer, and a type of early warning results are obtained according to the second characteristic value and a preset early warning threshold value.
In this embodiment, a first temperature value and a last temperature value (the last temperature value is related to a first quantity) obtained by inverse calculation according to a transformer temperature curve are used as second characteristic values, then the second characteristic values are compared with the early warning threshold values corresponding to the early warning levels according to preset detection rules (for example, the preset detection rules are from large to small or from small to large), the early warning threshold values met by the second characteristic values are determined, the early warning levels corresponding to the early warning threshold values met by the second characteristic values are output as early warning results, and therefore early warning of the transformer temperature trend by adopting a continuous increasing trend detection method is completed.
Step S203, acquiring class II monitoring parameters from a second monitoring system, and acquiring a class II early warning result set through a continuous increasing trend detection method according to the acquired monitoring record text of the class II monitoring parameters; the class II monitoring parameters refer to data which have no correlation with the working condition data of the unit.
In other embodiments, after step S203, a reference early warning result may be obtained by a mankendel trend detection method according to the monitoring record text of the class ii monitoring parameters, and then the trend early warning of the class ii monitoring parameters may be performed by combining the two types of early warning result sets obtained by the continuous increasing trend detection method and the reference early warning result obtained by the mankendel trend detection method. It should be noted that the trend early warning process of the class ii monitoring parameters is similar to the trend early warning process of the monitoring amount in the above embodiment of the intelligent early warning method for monitoring the unit state, and is not repeated again.
Preferably, as shown in fig. 6, when the type ii monitoring parameters are the content and the absolute gas production rate of each gas in the transformer oil, and the monitoring record text of the type ii monitoring parameters is the gas record text, the step S203 may include the following steps according to the obtained monitoring record text of the type ii monitoring parameters and obtaining a type ii early warning result set by a continuous increasing trend detection method:
step S2031, the content of each gas in each operation day is obtained through an oil chromatogram on-line monitoring device arranged on the transformer, the average value of the content of each gas and the absolute gas production rate are calculated, and the average value of the content of each gas and the absolute gas production rate are stored in a gas recording text in a correlation manner.
Specifically, after the content of each gas on each operation day is obtained, the average content value is calculated through a preset average value model by taking each operation day as a monitoring period, meanwhile, the absolute gas production rate is calculated through a preset gas production rate model, and then the average content value and the absolute gas production rate of each gas are stored in a gas recording text in a correlation mode. Wherein, the gas production rate model is as follows:
in the formula (2), γ is the absolute gas production rate, Ci2Measuring the concentration of a gas, C, in the transformer oil for a second samplingi1And measuring the concentration of a certain gas in the transformer oil for the first sampling, wherein delta t is the actual running time in the time interval of two times of sampling, G is the total oil quantity in the transformer, and rho is the density of the transformer oil.
Step S2032, obtaining the average value of the content and the absolute gas production rate of the preset third quantity from the gas record text, respectively fitting the average value of the content and the absolute gas production rate of the third quantity, and obtaining a gas content curve and a gas production rate curve. The preset third number may be set according to requirements, for example, the preset third number is set to 15.
And S2033, obtaining a characteristic value set for representing the trend change of the gas content and the trend change of the gas generation rate according to the gas content curve and the gas generation rate curve, and obtaining a second-class early warning result set according to the characteristic value set and a preset early warning threshold value.
In this embodiment, each gas in the transformer oil corresponds to a gas record text, and corresponds to a gas content curve and a gas production rate curve. The characteristic value set comprises a third characteristic value used for representing the trend change of the gas content and a fourth characteristic value used for representing the trend change of the gas production rate of the gas, the third characteristic value is the ratio of the last gas content to the first gas content obtained by inverse calculation according to a gas content curve, and the fourth characteristic value is the ratio of the last gas production rate to the first gas production rate obtained by inverse calculation according to a gas production rate curve.
And comparing each characteristic value (namely, a third characteristic value and a fourth characteristic value) of the characteristic value set with the early warning threshold value corresponding to each early warning level according to a preset detection rule, respectively determining the early warning threshold values respectively met by different characteristic values, and outputting the early warning levels corresponding to the early warning threshold values respectively met by different characteristic values as a second-class early warning result set, thereby completing the early warning of the gas content trend and the absolute gas production rate trend by adopting a continuous increasing trend detection method. Understandably, the severity of the abnormal state of the equipment is reflected by setting different early warning levels, so that the equipment abnormality can be found in time and processed in an abnormal way.
Therefore, the transformer state intelligent early warning method provided by the embodiment is based on the second monitoring system for monitoring the operation state of the transformer, and the monitoring value change trends of the class i monitoring parameters and the class ii monitoring parameters in the second monitoring system are tracked and analyzed in real time by using the continuous increasing trend detection method, so that the transformer state intelligent early warning is realized.
In addition, as shown in fig. 7, an embodiment of the present invention further provides an auxiliary device state monitoring intelligent early warning method, including the following steps:
step S301, determining a third monitoring system for monitoring the operation state of the auxiliary machine, wherein the third monitoring system comprises at least one monitoring index.
In the embodiment, in the hydropower station, one hydroelectric generating set can be associated with a plurality of auxiliary machines of the same type, and the auxiliary machine devices include, but are not limited to, a drainage pump and a governor oil pump. The third monitoring system includes, but is not limited to, monitoring indexes such as the auxiliary machine operation loading time and the auxiliary machine start-stop interval time.
Step S302, acquiring a monitoring record text of each monitoring index under each unit operation condition.
Taking a speed regulator oil pump as an example, under each unit operation condition, the oil pump operation loading time and the oil pump start-stop interval time are automatically calculated according to the start-stop state data of the speed regulator oil pump, and the numerical value of the oil pump operation loading time and the numerical value of the oil pump start-stop interval time are respectively stored into corresponding monitoring record texts.
Step S303, obtaining a detection result set of each monitoring index through a preset data trend detection system according to the monitoring record text of each monitoring index, and performing trend early warning on each monitoring index according to the detection result set of each monitoring index.
The detection result set comprises detection results obtained by each data trend detection method in the data trend detection system. The data trend detection system includes a continuously increasing trend detection method and a mankendel trend detection method. Preferably, step S303 specifically includes:
the method comprises the steps of firstly, obtaining a first detection result of each monitoring index through a continuous increasing trend detection method according to a monitoring record text of each monitoring index.
Preferably, firstly, obtaining the nearest N monitoring values from a monitoring record text, and performing linear regression fitting on the N monitoring values to obtain a fitting curve l; then determining a characteristic value lambda for representing the change trend of the monitoring index according to the fitting curve l; finally, according to the characteristic value lambda and a preset early warning threshold value TyiA first detection result is determined. Wherein, the characteristic value lambda is the 1 st fitting value y obtained by inverse calculation according to the fitting curve l1And the Nth fitting value yNRatio y ofN/y1I.e. λ ═ yN/y1. The data volume of monitoring record text storage is greater than monitoring value quantity N, and monitoring value quantity N can set up according to the demand, for example, monitoring value quantity N sets up 15 in advance.
Obtaining the 1 st fitting value y by inverse calculation according to the fitting curve l1And the Nth fitting value yNAnd calculating to obtain the Nth fitting value yNTo the 1 st fitting value y1After the ratio lambda (namely the characteristic value lambda) is obtained, the ratio lambda and the early warning threshold T corresponding to each early warning level are obtainedyiComparing, and determining the early warning threshold T met by the ratio lambdayiAnd then the early warning threshold T that the ratio satisfiesyiAnd outputting the corresponding early warning grade as a first detection result. Illustratively, if the warning level is setSetting I-level early warning and II-level early warning, and setting early warning threshold T corresponding to the I-level early warningy1Setting as 1.25, early warning threshold T corresponding to II-level early warningy2The set 1.5 can be used for setting the early warning threshold T according to the characteristic value lambday1Early warning threshold Ty2Comparing according to the detection rule from large to small, namely firstly judging whether the characteristic value lambda is larger than the early warning threshold value Ty2If λ is>Ty2Determining that the first detection result is a level II early warning; and if λ is less than or equal to Ty2Then further judging whether the characteristic value lambda is larger than the early warning threshold value T or noty1If λ>Ty1If so, determining that the first detection result is I-level early warning; and if λ is less than or equal to Ty1And determining that the first detection result is no early warning.
And secondly, obtaining a second detection result of each monitoring index through a Mankender trend detection method according to the monitoring record text of each monitoring index.
Preferably, firstly, acquiring a monitoring value in a monitoring period T from a monitoring record text; processing the monitoring value in a monitoring period T by adopting a Mann-Kendall trend verification algorithm; then judging whether the trend change exceeds a preset confidence threshold value, and if the trend change exceeds (is larger than) the preset confidence threshold value, outputting abnormal trend change; and if the trend change exceeds (is less than or equal to) a preset confidence coefficient threshold value Z, outputting normal trend change. The confidence threshold Z and the monitoring period T may be set according to requirements, for example, the confidence threshold Z is 2, and the monitoring period T is 30 days. One monitoring period T is less than the validity period of the data in the monitoring record text.
The mankendell trend verification algorithm is a non-parametric verification that does not require data to follow a particular distribution (e.g., gaussian, etc.), allows data to be missing, and is a very common and practical trend verification method. The monitoring value of one monitoring period is processed by adopting a Mankender trend verification algorithm, so that monotonous trend verification can be realized. When the trend changes beyond the confidence threshold, the monitored value that can characterize a monitoring period presents a clear rising trend.
And thirdly, generating a detection result set of each monitoring index according to the first detection result and the second detection result of each monitoring index, and performing trend early warning on each monitoring index according to the detection result set of each monitoring index.
In this embodiment, the set of detection results includes a first detection result obtained by the continuously increasing trend detection method and a second detection result obtained by the continuously increasing trend detection method. The first detection result comprises no early warning and any early warning grade. The second detection result comprises trend abnormal change and trend normal change.
And for each monitoring index, if the first detection result is no early warning and the second detection result is normal trend change, determining that the trend early warning state of the monitoring index is normal. And if the first detection result is any one of the early warning levels or the second detection result is abnormal trend change, determining that the trend early warning state of the monitoring index is abnormal, and further automatically pushing auxiliary machine warning information to equipment maintenance personnel.
In an embodiment, as shown in fig. 8, the intelligent warning method for the unit state further includes the following steps:
and step S304, acquiring start-stop state data of the water turbine generator set associated with the auxiliary machine. The start-stop state data of the water-turbine generator set comprises power generation state information and stop state information.
Step S305, inputting the start-stop state data to a preset working condition division model so as to obtain the unit operation working condition. The unit operation working conditions comprise a power generation working condition, a shutdown working condition and a start-stop working condition. The working condition division model is specifically represented as follows:
in the formula (3), condition 1 is a power generation condition, condition 2 is a shutdown condition, condition 3 is an open-shutdown condition, power state is power generation state information, and down state is shutdown state information. As can be seen from the formula (3), when the power generation state information is "1" and the shutdown state information is "0", the unit operation condition is "power generation condition"; when the power generation state information is '0' and the stop state information is '1', the unit operation working condition is a 'stop working condition'; when the power generation state information is '0' and the stop state information is '0', the unit operation condition is 'start-stop condition'.
In fig. 8, step S304 and step S305 are executed before step S301, but in other embodiments, step S304 and step S305 may be executed before step S302, and thus step S304 and step S305 may be executed before either step S301 or step S302.
Therefore, the auxiliary machine state intelligent early warning method provided by the embodiment is based on the third monitoring system for monitoring the operation state of the auxiliary machine, and the data trend detection system is used for tracking and analyzing the monitoring value change trend of each monitoring index in the third monitoring system under different unit operation conditions in real time, so that the auxiliary machine state intelligent early warning is realized.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (4)
1. The intelligent early warning method for monitoring the state of the unit is characterized by comprising the following steps:
determining a first monitoring system for monitoring the running state of the hydroelectric generating set, wherein the first monitoring system comprises at least one type of monitoring quantity;
judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity;
when the current unit working condition data meets the working condition judgment condition corresponding to each type of the monitoring quantity, obtaining a type of detection result of each type of the monitoring quantity through a continuous increasing trend detection method according to the obtained monitoring record text of each type of the monitoring quantity;
according to the monitoring record text of each type of the monitoring quantity, obtaining a second type of detection result of each type of the monitoring quantity through a Mankendall trend detection method;
and performing trend early warning of each type of the monitored quantity according to the first type detection result and the second type detection result of each type of the monitored quantity.
2. The intelligent unit state monitoring early warning method according to claim 1, wherein the obtaining of the second detection result of each type of the monitored quantity through a manksendel trend detection method according to the monitoring record text of each type of the monitored quantity comprises:
obtaining an average measured value of each type of monitoring quantity in a preset monitoring period from a monitoring record text of each type of monitoring quantity;
processing the average measured value of each type of monitored quantity in a preset monitoring period by adopting a Mankender trend verification algorithm to obtain the trend change of each type of monitored quantity;
and acquiring a second type detection result of each type of the monitored quantity according to the trend change of each type of the monitored quantity and a preset confidence threshold.
3. The unit state monitoring intelligent early warning method according to claim 1, wherein the first monitoring system comprises a first type monitoring quantity, a second type monitoring quantity and a third type monitoring quantity; the first type of monitoring quantity comprises guide bearing temperature and oil groove temperature; therefore, the second type of monitoring quantity comprises the temperature of the stator core, the temperature of the stator coil, the outlet temperature of the air cooler and the inlet temperature of the air cooler; the three types of monitoring quantities comprise oil tank oil level and water flow; the unit working condition data comprises power generation state information and active power information of the unit;
the judging whether the current unit working condition data meets the working condition judgment condition corresponding to each type of monitoring quantity includes:
when the power generation state information of the unit is changed from '0' to '1', and the starting operation time length reaches a preset first time length, and the active power information of the unit reaches a preset first power, determining that the working condition judgment condition corresponding to one type of monitoring quantity is met;
when the power generation state information of the unit is changed from '0' to '1', and the starting operation time length reaches a preset first time length and the active power information of the unit reaches a preset second power, determining that the working condition judgment condition corresponding to the second type of monitoring quantity is met; the preset second power is set within the range of 70% -100% of rated load;
and when the power generation state information of the unit is changed from '0' to '1' and the active power information of the unit reaches a preset third power, determining that the working condition judgment condition corresponding to the three types of monitoring quantities is met.
4. The intelligent unit state monitoring early warning method according to claim 1, wherein the step of obtaining a type of detection result of each type of the monitored quantity by a continuous increasing trend detection method according to the obtained monitoring record text of each type of the monitored quantity comprises the following steps:
obtaining the measured value of each type of the monitored quantity, obtaining the average measured value of each type of the monitored quantity through a preset average value model, and storing the average measured value in a monitoring record text;
acquiring preset first number of average measured values from each type of monitoring record text of the monitoring quantity;
fitting the preset first number of average measured values to obtain a fitting curve of each type of the monitored quantity;
acquiring a first characteristic value for representing the variation trend of each type of the monitored quantity according to the fitted curve of each type of the monitored quantity;
and determining a class detection result of each class of the monitored quantity according to each first characteristic value and a preset early warning threshold value.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053557.1A CN112885047B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine |
| CN202210446543.0A CN114863652B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for transformer state monitoring |
| CN202210445452.5A CN114863651A (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for monitoring state of auxiliary machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110053557.1A CN112885047B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210446543.0A Division CN114863652B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for transformer state monitoring |
| CN202210445452.5A Division CN114863651A (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for monitoring state of auxiliary machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112885047A CN112885047A (en) | 2021-06-01 |
| CN112885047B true CN112885047B (en) | 2022-06-14 |
Family
ID=76048008
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210445452.5A Pending CN114863651A (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for monitoring state of auxiliary machine |
| CN202210446543.0A Active CN114863652B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for transformer state monitoring |
| CN202110053557.1A Active CN112885047B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine |
Family Applications Before (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210445452.5A Pending CN114863651A (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for monitoring state of auxiliary machine |
| CN202210446543.0A Active CN114863652B (en) | 2021-01-15 | 2021-01-15 | Intelligent early warning method for transformer state monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN114863651A (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113312804B (en) * | 2021-07-29 | 2021-12-07 | 湖南五凌电力科技有限公司 | Temperature early warning method, device, equipment and storage medium of transformer |
| CN115013297B (en) * | 2022-05-30 | 2024-03-29 | 广西信发铝电有限公司 | Power plant circulating pump abnormality monitoring method and device, electronic equipment and storage medium |
| CN115017214B (en) * | 2022-08-05 | 2022-12-27 | 湖南五凌电力科技有限公司 | Hydropower station auxiliary equipment operation state analysis early warning method, device and storage medium |
| CN115455651B (en) * | 2022-08-10 | 2024-01-05 | 中国长江电力股份有限公司 | Fault diagnosis and trend analysis method for public auxiliary equipment of hydropower station |
| CN115580637B (en) * | 2022-09-26 | 2023-05-19 | 广州健新科技有限责任公司 | Safety monitoring and early warning method and system for auxiliary equipment of power plant |
| CN116050130B (en) * | 2023-01-10 | 2024-03-12 | 中国长江电力股份有限公司 | Multi-factor-based hydropower station generator deduction oil level prediction method |
Family Cites Families (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5566091A (en) * | 1994-06-30 | 1996-10-15 | Caterpillar Inc. | Method and apparatus for machine health inference by comparing two like loaded components |
| US6714022B2 (en) * | 2001-02-20 | 2004-03-30 | Gary Hoffman | Apparatus and method for cooling power transformers |
| BRPI0502384A (en) * | 2005-06-21 | 2007-02-06 | Siemens Ltda | system and method of monitoring and controlling the operating condition of a power transformer |
| US8451809B2 (en) * | 2007-04-13 | 2013-05-28 | Hart Communication Foundation | Wireless gateway in a process control environment supporting a wireless communication protocol |
| EP2096610A1 (en) * | 2008-02-26 | 2009-09-02 | British Telecommunications Public Limited Company | Remote monitoring thresholds |
| AU2009329205B9 (en) * | 2008-12-19 | 2014-11-20 | Eskom Holdings Soc Limited | Rotating machine shaft signal monitoring method and system |
| CN101555806B (en) * | 2008-12-29 | 2011-06-15 | 浙江浙能嘉兴发电有限公司 | Classification alarm and identification auxiliary method of real-time production parameters of power plant |
| US8400320B2 (en) * | 2009-12-30 | 2013-03-19 | Eduardo Pedrosa Santos | System for monitoring oil level and detecting leaks in power transformers, reactors, current and potential transformers, high voltage bushings and the like |
| DE102010036514A1 (en) * | 2010-07-20 | 2012-01-26 | Sma Solar Technology Ag | Device and method for monitoring a photovoltaic system |
| US9276298B2 (en) * | 2013-02-28 | 2016-03-01 | NDSL, Inc. | Automatically determining alarm threshold settings for monitored battery system components in battery systems, and related components, systems, and methods |
| CN103711645B (en) * | 2013-11-25 | 2016-03-30 | 北京能高自动化技术股份有限公司 | Based on the wind power generating set state evaluating method of modeling parameters signature analysis |
| CN104747367B (en) * | 2013-12-31 | 2017-08-11 | 华能新能源股份有限公司 | Power curves of wind-driven generator sets Characteristics Detection system |
| US9866161B1 (en) * | 2014-05-21 | 2018-01-09 | Williams RDM, Inc. | Universal monitor and fault detector in fielded generators and method |
| CN104121949A (en) * | 2014-08-18 | 2014-10-29 | 中国船舶重工集团公司第七一二研究所 | Condition monitoring method of ship electric propulsion system |
| CN105703364B (en) * | 2016-04-18 | 2018-02-13 | 哈尔滨工业大学 | Photovoltaic plant equivalent modeling method |
| CN106227127B (en) * | 2016-08-08 | 2019-03-29 | 中国神华能源股份有限公司 | Generating equipment intelligent monitoring and controlling device and monitoring method |
| KR101919875B1 (en) * | 2016-12-28 | 2019-02-08 | 경북대학교 산학협력단 | Intelligent protection apparatus of transformer and method for protecting the same |
| CN108169615B (en) * | 2018-02-11 | 2020-02-11 | 南京南瑞继保电气有限公司 | Optical CT-based phase failure detection method for starting standby transformer |
| CN108681319B (en) * | 2018-04-02 | 2019-09-06 | 西南交通大学 | A kind of transformer winding fault recognition methods based on transmission function |
| CN110634271B (en) * | 2018-06-21 | 2022-01-25 | 佛山市顺德区美的电热电器制造有限公司 | Cooking equipment safety early warning method, device, equipment and system |
| CN108875841A (en) * | 2018-06-29 | 2018-11-23 | 国家电网有限公司 | A kind of pumped storage unit vibration trend forecasting method |
| CN110085006B (en) * | 2019-03-13 | 2023-03-24 | 中交广州航道局有限公司 | Ship monitoring method, device and system and storage medium |
| CN110085005B (en) * | 2019-03-13 | 2023-03-24 | 中交广州航道局有限公司 | Ship generator monitoring method, device and system and storage medium |
| JP7154181B2 (en) * | 2019-04-03 | 2022-10-17 | 大阪瓦斯株式会社 | Power generation system and its load input method |
| CN111776006B (en) * | 2019-04-03 | 2021-09-07 | 株洲中车时代电气股份有限公司 | Pre-alarming method and device for train axle temperature |
| CN110020965A (en) * | 2019-04-10 | 2019-07-16 | 华能澜沧江水电股份有限公司 | A kind of huge hydroelectric power plant's intelligence startup-shutdown guiding strategies and system |
| CN111123096A (en) * | 2019-10-15 | 2020-05-08 | 联桥网云信息科技（长沙）有限公司 | Internet of things motor monitoring platform |
| CN111047082B (en) * | 2019-12-02 | 2024-03-29 | 广州智光电气股份有限公司 | Early warning method and device of equipment, storage medium and electronic device |
| CN111047732B (en) * | 2019-12-16 | 2022-04-12 | 青岛海信网络科技股份有限公司 | Equipment abnormity diagnosis method and device based on energy consumption model and data interaction |
| CN111028486A (en) * | 2019-12-26 | 2020-04-17 | 杭州电力设备制造有限公司 | High-temperature early warning method, device, equipment and storage medium for electrical equipment |
| CN111522858B (en) * | 2020-03-16 | 2022-11-18 | 国家电网有限公司 | Multi-dimensional state vector-based pumping unit performance degradation early warning method |
| CN112085930B (en) * | 2020-09-14 | 2022-06-03 | 武汉瑞莱保科技有限公司 | Intelligent monitoring and early warning system and method for generator set |
| CN111929579B (en) * | 2020-09-22 | 2021-02-09 | 北京京能能源技术研究有限责任公司 | Generator online fault diagnosis method and device and computer device |
-
2021
- 2021-01-15 CN CN202210445452.5A patent/CN114863651A/en active Pending
- 2021-01-15 CN CN202210446543.0A patent/CN114863652B/en active Active
- 2021-01-15 CN CN202110053557.1A patent/CN112885047B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114863651A (en) | 2022-08-05 |
| CN114863652B (en) | 2024-01-30 |
| CN112885047A (en) | 2021-06-01 |
| CN114863652A (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112885047B (en) | Intelligent early warning method for state monitoring of unit, transformer and auxiliary machine | |
| CN105372591B (en) | A kind of Hydropower Unit health status method for quantitatively evaluating based on transient process | |
| CN113435652B (en) | Primary equipment defect diagnosis and prediction method | |
| Khalyasmaa et al. | Expert system for engineering assets' management of utility companies | |
| CN113435759B (en) | Primary equipment risk intelligent assessment method based on deep learning | |
| CN110197296B (en) | Unit load prediction method based on time series similarity | |
| CN116167527B (en) | Pure data-driven power system static safety operation risk online assessment method | |
| Basuki | Online dissolved gas analysis of power transformers based on decision tree model | |
| CN114397526A (en) | Power transformer fault prediction method and system driven by state holographic sensing data | |
| Yang et al. | Reconstruction residuals based long-term voltage stability assessment using autoencoders | |
| CN117520951B (en) | Transformer health assessment method and system based on multiple characteristic quantities | |
| CN113505909B (en) | Error compensation method for short-term wind power trend prediction | |
| CN117117258B (en) | Fault monitoring method and device for hydrogen fuel cell system | |
| CN114062993A (en) | CVT error state prediction method based on time convolution network | |
| CN115573845B (en) | Runout trend early warning method and system for offline data of fusion unit | |
| CN115982591A (en) | Method and device for detecting health state of transformer, equipment and storage medium | |
| Wu et al. | A method of prediction for transformer malfunction based on oil chromatography | |
| Nandagopan et al. | Online prediction of DGA results for intelligent condition monitoring of power transformers | |
| Yang et al. | Multichannel energy monitoring based on the sliding window method in an industrial environment | |
| CN113935523A (en) | Voltage trend prediction method based on voltage change rule | |
| CN113949060A (en) | Voltage trend prediction system based on voltage change rule | |
| Ren et al. | Research on wind power prediction | |
| Li et al. | Nonparametric kernel density estimation model of transformer health based on dissolved gases in oil | |
| CN103701112A (en) | System and method for identifying long/short-term weak links of power grid in running state | |
| Bao et al. | Summer Short-Term Electric Load Forecasting Based on Hierarchical Model |
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 |