CN111412025B - Method and system for monitoring state of high-side system of steam turbine - Google Patents
Method and system for monitoring state of high-side system of steam turbine Download PDFInfo
- Publication number
- CN111412025B CN111412025B CN202010224796.4A CN202010224796A CN111412025B CN 111412025 B CN111412025 B CN 111412025B CN 202010224796 A CN202010224796 A CN 202010224796A CN 111412025 B CN111412025 B CN 111412025B
- Authority
- CN
- China
- Prior art keywords
- pressure reducing
- reducing valve
- monitoring
- data
- steam
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 55
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 47
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 238000005457 optimization Methods 0.000 claims description 15
- 239000003921 oil Substances 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 239000010720 hydraulic oil Substances 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 239000000446 fuel Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000010977 unit operation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 9
- 230000005856 abnormality Effects 0.000 abstract 2
- 230000001276 controlling effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
- F01D21/003—Arrangements for testing or measuring
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
- F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
- F01D21/12—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for responsive to temperature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Control Of Turbines (AREA)
Abstract
The invention discloses a method for monitoring the state of a high-side system of a steam turbine, which comprises the following steps: acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system; establishing a monitoring model of the high-side system according to the optimized data; and judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal. The invention also discloses a system applied to the method for monitoring the state of the high-side system of the steam turbine. The method for monitoring the state of the high-side system of the steam turbine can alarm the abnormality of the high-side pressure reducing valve and the high-side temperature reducing water valve of the high-side system and the abnormality of the steam pressure and the temperature behind the high-side pressure reducing valve so as to remind operators to check and process in time, thereby effectively monitoring the state of the high-side system.
Description
Technical Field
The invention relates to the technical field of thermal power generation, in particular to a method for monitoring the state of a high-side system of a steam turbine. The invention also relates to a steam turbine high side system state monitoring system applied to the steam turbine high side system state monitoring method.
Background
With the increasing market development of power systems, thermal power plants have more and more peak shaving functions, and the units are required to be started and stopped at any time on the basis of stable operation, so that the starting and stopping times of the units are increased continuously, and the units can be automatically regulated to operate under 30% -100% rated load, which puts higher requirements on the automation control level of equipment of the thermal power plant.
The high-side system, namely a high-pressure bypass system of a steam turbine is short, and for a coal-fired thermal power generating unit, the high-side system is used in cooperation with the start and stop of the unit or the quick load shedding of the unit, is an important protection system of the unit, is also one of important means for automatically controlling the main steam pressure in the start stage of the unit, and plays an important role in the safety and the economy of economic operation. However, the high-side systems of the prior art have the following drawbacks:
the high-side system generally adopts DCS monitoring, only when a fault (trip) occurs, an alarm can be found, the degradation trend that equipment or the system deviates from a normal state is difficult to find, and when the system fails, equipment is damaged or a unit is shut down unplanned;
most of the pressure control behind the high-bypass pressure reducing valve is manual operation control, and the operation amount of operators is large during the starting period of the unit, so that the control is delayed and inaccurate;
the temperature after the high-side temperature reducing valve is controlled by the high-side temperature reducing valve is mostly controlled manually, the operation amount of operators is large during the starting period of the unit, the control is lagged and inaccurate, the overtemperature is easy to occur, and the service life of a pipeline is shortened;
the high-bypass oil system has no monitoring means, and the abnormal equipment and the oil leakage of the oil pipeline are difficult to find through an operation monitoring disc.
Therefore, how to avoid the problem that the safety and reliability of the motion of the high-side system are affected due to the fact that the state of the high-side system and the equipment cannot be monitored in real time and optimized automatically is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide a method for monitoring the state of a high-side system of a steam turbine, which can be used for carrying out whole-process and effective monitoring on the high-side system and equipment and giving an alarm when the state of the high-side system is abnormal, so that an operator can be reminded to check and process in time. The invention also aims to provide a device applied to the method for monitoring the state of the high-side system of the steam turbine.
In order to achieve the above object, the present invention provides a method for monitoring the state of a turbine high-side system, comprising:
acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system;
establishing a monitoring model of the high-side system according to the optimized data;
and judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal.
Optionally, the acquiring optimization data of a plurality of high-side system measuring points includes:
acquiring optimized data of steam pressure behind the high-side pressure reducing valve through the high-side pressure reducing valve automatic control system;
and acquiring optimized data of the steam temperature behind the high-side pressure reducing valve through the high-side temperature reducing water valve automatic control system.
Optionally, the obtaining, by the high-side pressure reducing valve automatic control system, optimization data of the steam pressure after the high-side pressure reducing valve includes:
acquiring steam pressure data of three pressure measuring points behind a high-side pressure reducing valve;
calculating a first median of three steam pressure data;
and acquiring steam pressure data after the high-side reducing valve according to the first median and the boiler fuel quantity.
Optionally, the obtaining, by the high-side temperature-reducing water valve automatic control system, optimization data of the steam temperature after the high-side pressure-reducing valve, includes:
acquiring steam temperature data of three temperature measuring points behind a high-side pressure reducing valve;
calculating a second median of the three steam temperature data;
and acquiring the steam temperature data behind the high-side pressure reducing valve according to the second median and the opening of the high-side pressure reducing valve.
Optionally, before the step of creating a monitoring model of the high-side system according to the optimization data, the method includes:
acquiring a high-side pressure reducing valve opening instruction and a high-side pressure reducing valve position feedback;
calculating to obtain a first difference value fed back by the opening instruction of the high-side pressure reducing valve and the valve position of the high-side pressure reducing valve;
acquiring an opening instruction of a high-side desuperheating water valve and valve position feedback of the high-side desuperheating water valve;
and calculating to obtain a second difference value fed back by the opening instruction of the high-side desuperheating water valve and the valve position of the high-side desuperheating water valve.
Optionally, the creating a monitoring model of the high-side system according to the optimization data includes:
selecting modeling data corresponding to each measuring point, wherein the modeling data comprises the opening instruction of the high-side pressure reducing valve, the valve position feedback of the high-side pressure reducing valve, the first difference, the opening instruction of the high-side temperature reducing water valve, the valve position feedback of the high-side temperature reducing water valve, the second difference, the steam pressure data behind the high-side pressure reducing valve, the steam temperature data behind the high-side pressure reducing valve, the rotating speed of a steam turbine, the oil pressure of a main pipe at an outlet of a hydraulic oil station, the oil pump current of the hydraulic oil station and the power PW of a unit;
selecting an algorithm, wherein the algorithm is a machine learning algorithm or a deep learning algorithm;
selecting modes, wherein the modes comprise a normal unit operation mode, a low-load mode after unit synchronization, a turbine turning mode and a boiler ignition mode;
selecting historical data with normal parameter change as a training sample;
setting and adjusting the threshold value of each measuring point;
creating the monitoring model.
Optionally, the determining, by the monitoring model, the state of the high-side system, and sending an alarm when the state of the high-side system is abnormal includes:
generating a predicted value curve of each measuring point through the monitoring model;
acquiring an actual value curve of each measuring point;
obtaining a deviation value curve according to the predicted value curve and the actual value curve;
and comparing the deviation value corresponding to each measuring point with a threshold value according to the deviation value curve, and giving an alarm when the deviation value of any measuring point is greater than the threshold value.
Optionally, the method further comprises:
and training and adjusting the monitoring model.
The invention also provides a system for monitoring the state of the high-side system of the steam turbine, which comprises the following components:
an acquisition module: the system comprises a high-side pressure reducing valve automatic control system, a high-side pressure reducing water valve automatic control system and a high-side pressure reducing water valve automatic control system, wherein the high-side pressure reducing valve automatic control system is used for acquiring optimized data of a plurality of high-side system measuring points;
a creation module: a monitoring model of the high-side system is created according to the optimization data;
a judging module: the monitoring model is used for judging the state of the high-side system, and when the state of the high-side system is abnormal, an alarm is given out.
Optionally, the determining module includes:
a generation unit: the prediction value curve of each measuring point is generated through the monitoring model;
an acquisition unit: the method is used for acquiring an actual value curve of each measuring point;
a calculation unit: obtaining a deviation value curve according to the predicted value curve and the actual value curve;
an alignment unit: and comparing the deviation value corresponding to each measuring point with a threshold value according to the deviation value curve, and giving an alarm when the deviation value of any measuring point is greater than the threshold value.
Compared with the prior art, the invention designs a method for monitoring the state of the high-side system of the steam turbine aiming at different requirements of boiler combustion, and particularly the method for monitoring the state of the high-side system of the steam turbine comprises the following steps: s1: acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system; s2: establishing a monitoring model of the high-side system according to the optimized data; s3: and judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal. Meanwhile, on the basis of the method for monitoring the state of the high-side system of the steam turbine, the invention also provides a system for monitoring the state of the high-side system of the steam turbine, which comprises an acquisition module, a creation module and a judgment module, wherein: the acquisition module is used for acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system; the creation module is used for creating a monitoring model of the high-side system according to the optimized data; the judging module is used for judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal.
According to the method for monitoring the state of the high-side system of the steam turbine, firstly, optimized data of a plurality of high-side system measuring points are obtained through a high-side pressure reducing valve automatic control system and a high-side temperature reducing valve automatic control system, then a monitoring model capable of monitoring the high-side system and equipment is established, finally, the state of the high-side system is judged through the monitoring model, and an alarm is given out when the state of the high-side system is abnormal. Therefore, the monitoring method can give an alarm for the abnormity of the high-side pressure reducing valve and the high-side temperature reducing water valve of the high-side system and the abnormity of the steam pressure and the temperature behind the high-side pressure reducing valve so as to remind operators to check and process in time, thereby effectively monitoring the state of the high-side system.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for monitoring the condition of a turbine high side system according to an embodiment of the present invention;
FIG. 2 is a schematic control diagram of an automatic control system of a high-pressure by-pass pressure reducing valve according to an embodiment of the present invention;
FIG. 3 is a schematic control diagram of an automatic control system for a high-side desuperheating water valve according to an embodiment of the present invention;
FIG. 4 is a flow chart of monitoring model creation and operation in an embodiment of the present invention.
Detailed Description
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.
The core of the invention is to provide a method for monitoring the state of a high-side system of a steam turbine, which can carry out whole-course and effective monitoring on the high-side system and the equipment thereof and send out an alarm when the state of the high-side system is abnormal, thereby reminding operators to check and process in time. The invention also provides a device applied to the method for monitoring the state of the high-side system of the steam turbine.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1 to 4, fig. 1 is a flowchart illustrating a method for monitoring a state of a turbine high-side system according to an embodiment of the present invention; FIG. 2 is a schematic control diagram of an automatic control system of a high-pressure by-pass pressure reducing valve according to an embodiment of the present invention; FIG. 3 is a schematic control diagram of an automatic control system for a high-side desuperheating water valve according to an embodiment of the present invention; FIG. 4 is a flow chart of monitoring model creation and operation in an embodiment of the present invention.
The method for monitoring the state of the high-side system of the steam turbine provided by the embodiment of the invention comprises the following steps:
s1: acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system;
s2: establishing a monitoring model of the high-side system according to the optimized data;
s3: and judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal.
In S1, the optimization data of the plurality of high-side system measurement points are obtained by the high-side pressure reducing valve autonomous system and the high-side temperature reducing valve autonomous system. Preferably, the acquiring of the optimization data of the plurality of high-side system measuring points comprises: and acquiring optimized data of the steam pressure behind the high-side pressure reducing valve by the high-side pressure reducing valve automatic control system and acquiring optimized data of the steam temperature behind the high-side pressure reducing valve by the high-side temperature reducing water valve automatic control system.
It should be noted that the high-side pressure reducing valve automatic control system is used for strictly controlling the steam pressure value after the high-side pressure reducing valve in the starting process of the unit, namely the optimized steam pressure value after the high-side pressure reducing valve can be obtained through the control of the high-side pressure reducing valve automatic control system, and meanwhile, the system can improve the response speed and accuracy of the steam pressure control, so that the pipeline can be prevented from being damaged due to overpressure when steam enters a low-pressure bypass pipeline.
The high-side temperature-reducing water valve automatic control system is used for strictly controlling the steam temperature value after the high-side pressure-reducing valve in the starting process of the unit, and meanwhile, the system can improve the response speed and accuracy of steam temperature control, so that the operation intensity of operators is reduced; when the unit normally operates, if the high-side pressure reducing valve leaks internally, the temperature of steam behind the high-side pressure reducing valve can be controlled to prevent the pipeline from being damaged due to overtemperature when the steam enters a low-pressure bypass pipeline (or a reheater pipeline). Therefore, the pressure and temperature of the steam need to be strictly controlled during the starting process of the unit and the normal operation of the unit.
Further, obtaining optimization data of the steam pressure behind the high-side pressure reducing valve through the high-side pressure reducing valve automatic control system comprises:
the first step is as follows: acquiring steam pressure data of three pressure measuring points behind a high-side pressure reducing valve;
the second step is that: calculating a first median value of the three steam pressure data;
the third step: and acquiring steam pressure data after the high-side pressure reducing valve according to the first median and the boiler fuel quantity.
The control loop of the high by-pass pressure relief valve autonomous system is shown in fig. 2. Firstly, three steam pressure measuring points P are taken behind a high-side pressure reducing valve 1 、P 2 、P 3 Obtaining a first median value P after three median value taking processing M A signal, then a PID module of the automatic control system of the high-side pressure reducing valve receives P M The signal is used as the actual value PV value of the PID, the P _ SP is used as the pressure set value of the PID, and the FF is the PID feedforward signal (the boiler fuel quantity is used as the feedforward signal, thereby reducing the PID control response time, reducing the control delay and improving the PID control rapidity and accuracy); AO is the output signal of the PID module of the high by-pass pressure reducing valve automatic control system, namely is the high by-pass pressure reducing valve position instruction, and sends the instruction to the control loop of the local high by-pass pressure reducing valve, thus the opening of the high by-pass pressure reducing valve can be controlled, and the purpose of controlling the steam pressure behind the high by-pass pressure reducing valve is achieved.
Obtain the optimization data of steam temperature behind the high other relief pressure valve through high other relief pressure water valve autonomous system, include:
the first step is as follows: acquiring steam temperature data of three temperature measuring points behind a high-side pressure reducing valve;
the second step is that: calculating to obtain a second median of the three steam temperature data;
the third step: and acquiring the steam temperature data behind the high-side pressure reducing valve according to the second median and the opening of the high-side pressure reducing valve.
The control loop of the high bypass temperature-reducing water valve automatic control system is shown in figure 3. Firstly, three steam temperatures are taken after a high-side pressure reducing valveMeasuring point T 1 、T 2 、T 3 Obtaining a second median value T after the treatment of' taking the median value of three M Signal, then PID module of automatic control system of high-side desuperheating water valve receives T M The signal is used as the actual value PV value of the PID, T _ SP is used as the temperature set value of the PID, and FF is a PID feedforward signal (the opening of a high bypass pressure reducing valve is used as the feedforward signal, so that the PID control response time can be reduced, the control delay can be reduced, and the rapidity and the accuracy of PID control can be improved); AO is the output signal of high by-pass desuperheating water valve automatic control system PID module, is high by-pass desuperheating water valve position instruction, send this instruction to on-the-spot high by-pass desuperheating water valve control circuit to control high by-pass desuperheating water valve aperture, thereby reach the purpose of controlling the steam temperature behind the high by-pass relief pressure valve.
In the embodiment of the present invention, before S2, the method further includes:
acquiring a high-side pressure reducing valve opening instruction and a high-side pressure reducing valve position feedback;
calculating to obtain a first difference value of the opening instruction of the high-side pressure reducing valve and the valve position feedback of the high-side pressure reducing valve;
acquiring an opening instruction of a high-side desuperheating water valve and valve position feedback of the high-side desuperheating water valve;
and calculating to obtain a second difference value of the opening instruction of the high-side desuperheating water valve and the valve position feedback of the high-side desuperheating water valve.
In S2, the creating the monitoring model of the high-side system includes:
selecting modeling data corresponding to each measuring point: the modeling data comprises a high-side pressure reducing valve opening instruction, a high-side pressure reducing valve position feedback, a first difference value, a high-side temperature reducing water valve opening instruction, a high-side temperature reducing water valve position feedback, a second difference value, high-side pressure reducing valve post-steam pressure data, high-side pressure reducing valve post-steam temperature data, steam turbine rotating speed, hydraulic oil station outlet main pipe oil pressure, hydraulic oil station oil pump current, unit power PW and the like;
selecting an algorithm: machine learning or deep learning algorithms such as support vector machine model algorithm (SVM), gaussian mixture model algorithm (GMM), recursive gaussian mixture model algorithm (RGMM), and other deep learning algorithms can be selected as desired;
selecting a mode: the mode comprises a normal unit operation mode, a low-load mode after the unit is connected to the grid, a turbine running mode and a boiler ignition mode; the mode is a trigger condition for putting the monitoring model into the monitoring system, when the mode is satisfied, the model can be put into monitoring, and if the mode is not satisfied, the model is not monitored; in the embodiment of the present invention, the mode selection of the monitoring model can be divided into the following four types:
the normal operation mode of the unit: when the power PW of the unit is larger than 30% of rated power (if the rated power of the unit is 660WM, when the power of the unit is larger than 198MW, the model mode meets the condition, and the model is put into monitoring;
and (3) low-load mode after the unit is connected to the grid: when the PW is more than or equal to 0 and less than or equal to 30 percent of rated power (if the rated power of the unit is 660WM, when the power of the unit is less than 198MW, the model mode meets the condition, and the model is put into monitoring);
the turbine rushes to rotate the mode: when the rotating speed of the steam turbine is more than or equal to 0 and less than or equal to 3000RPM and the unit power is less than or equal to 0MW, the mode is satisfied;
the ignition mode of the boiler is satisfied when the coal feeding amount of the boiler is more than or equal to 0 and less than or equal to 15T/H and the rotating speed of the steam turbine is less than or equal to 0; through the four modes, the whole process can be covered by the state monitoring of the high-side system, and the whole-process monitoring is realized.
Selecting historical data with normal parameter change as a training sample: selecting historical data which meets the four modes and has normal parameter change as a training sample (a plurality of time periods) for the model, wherein the sample data is to cover samples of the unit under different load working conditions in four seasons of spring, summer, autumn and winter during the operation of the unit;
setting and adjusting the threshold value of each measuring point: the threshold is a set value of the deviation between the calculated predicted value of the model measuring point and the actual value of the measuring point, when the deviation is greater than the threshold, an alarm signal is sent out, and the threshold can be adjusted through experience of operators;
finally, a monitoring model is created.
In order to improve the accuracy of the monitoring model, the method further comprises the following steps: training and optimizing the model.
Wherein, training the model means: a button for model training can be clicked to enable the model to learn so as to calculate the predicted values of all the measuring points in the model; the model optimization means that: in order to improve the model accuracy, when the characteristic change occurs after the equipment of the unit is overhauled or the model accuracy is low, the model needs to be retrained, the steps required by modeling are circulated, and a new round of model training is performed to improve the model accuracy.
It should be noted that when the model does not need to be optimized, the model can be put into online operation.
In S3, the method includes determining the state of the high-side system through the monitoring model, and issuing an alarm when the state of the high-side system is abnormal, where the method specifically includes:
the first step is as follows: generating a predicted value curve of each measuring point through a monitoring model;
the second step is that: acquiring an actual value curve of each measuring point;
the third step: acquiring a deviation value curve according to the predicted value curve and the actual value curve;
the fourth step: and comparing the deviation value corresponding to each measuring point with the threshold value according to the deviation value curve, and giving an alarm when the deviation value of any measuring point is greater than the threshold value.
That is, the purpose of creating the monitoring model is to generate predicted value curves of all the measuring points; on the basis, the actual value curves of all the corresponding measuring points can be obtained by combining the actual values of all the measuring points of the high-side system, and a deviation value curve can be generated through the predicted value curve and the actual value curve, wherein the deviation value curve corresponds to the deviation between the predicted value of each measuring point and the actual value of the measuring point.
In addition, the monitoring model can monitor the deviation value curve, and when the deviation value is larger than the threshold value corresponding to each measuring point, the monitoring model gives an alarm to prompt field operators that the system is abnormal.
In summary, in the above method for monitoring the state of the high-side system of the steam turbine, firstly, the high-side pressure reducing valve automatic control system and the high-side temperature reducing valve automatic control system acquire optimized data of a plurality of high-side system measuring points, then, a monitoring model capable of monitoring the high-side system and the equipment is established, and finally, the state of the high-side system is judged through the monitoring model, and an alarm is given when the state of the high-side system is abnormal.
Therefore, the monitoring method can give an alarm for the abnormity of the high-side pressure reducing valve and the high-side temperature reducing water valve of the high-side system and the abnormity of the steam pressure and the temperature behind the high-side pressure reducing valve so as to remind operators to check and process in time, thereby effectively monitoring the state of the high-side system.
When the state and the parameters of the high-side system are abnormal, an alarm is sent out, and the method comprises the following steps: the method comprises the following steps of high-side pressure reducing valve internal leakage alarm, high-side pressure reducing valve position feedback abnormity alarm, high-side pressure reducing valve position instruction and feedback deviation large alarm, high-side temperature reducing valve internal leakage alarm, high-side temperature reducing valve position feedback abnormity alarm, high-side temperature reducing valve position instruction and feedback deviation large alarm, high-side pressure reducing valve back pressure abnormity alarm, high-side pressure reducing valve back temperature abnormity alarm, high-side oil station outlet main pipe pressure abnormity alarm, oil station oil pump current abnormity alarm and the like.
Meanwhile, on the basis of the method for monitoring the state of the high-side system of the steam turbine, the invention also provides a system for monitoring the state of the high-side system of the steam turbine, which comprises an acquisition module, a creation module and a judgment module, wherein:
an acquisition module: the system is used for acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data are optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system;
a creation module: the monitoring model is used for creating a high-side system according to the optimization data;
a judging module: the monitoring module is used for judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal.
In an embodiment of the present invention, the determining module includes:
a generation unit: the system is used for generating a predicted value curve of each measuring point through a monitoring model;
an acquisition unit: the method comprises the steps of obtaining an actual value curve of each measuring point;
a calculation unit: the system is used for acquiring a deviation value curve according to the predicted value curve and the actual value curve;
an alignment unit: and the deviation value and the threshold value corresponding to each measuring point are compared according to the deviation value curve, and when the deviation value of any measuring point is greater than the threshold value, an alarm is given.
It is noted that, in this specification, relational terms such as first and second, and the like are used solely to distinguish one entity from another entity without necessarily requiring or implying any actual such relationship or order between such entities.
The method and the system for monitoring the state of the high-side system of the steam turbine provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (9)
1. A method for monitoring the state of a high-side system of a steam turbine is characterized by comprising the following steps:
acquiring optimized data of a plurality of high-side system measuring points, wherein the optimized data is optimized by a high-side pressure reducing valve automatic control system and a high-side temperature reducing water valve automatic control system;
establishing a monitoring model of the high-side system according to the optimized data;
judging the state of the high-side system through the monitoring model, and giving an alarm when the state of the high-side system is abnormal;
before the step of creating a monitoring model of the high-side system according to the optimization data, the method comprises the following steps:
acquiring a high-side pressure reducing valve opening instruction and a high-side pressure reducing valve position feedback;
calculating to obtain a first difference value fed back by the opening instruction of the high-side pressure reducing valve and the valve position of the high-side pressure reducing valve;
acquiring an opening instruction of a high-side desuperheating water valve and valve position feedback of the high-side desuperheating water valve;
and calculating to obtain a second difference value fed back by the opening instruction of the high-side desuperheating water valve and the valve position of the high-side desuperheating water valve.
2. The method for monitoring the condition of the high side system of the steam turbine according to claim 1, wherein the step of obtaining the optimized data of a plurality of high side system measuring points comprises the following steps:
acquiring optimized data of steam pressure behind the high-side pressure reducing valve through the high-side pressure reducing valve automatic control system;
and acquiring optimized data of the steam temperature behind the high-side pressure reducing valve through the high-side temperature reducing water valve automatic control system.
3. The method for monitoring the condition of the high side system of the steam turbine according to claim 2, wherein the step of obtaining the optimized data of the steam pressure after the high side pressure reducing valve by the automatic control system of the high side pressure reducing valve comprises the following steps:
acquiring steam pressure data of three pressure measuring points behind a high-side pressure reducing valve;
calculating a first median of three steam pressure data;
and acquiring steam pressure data behind a high-side reducing valve according to the first median and the boiler fuel quantity.
4. The method for monitoring the condition of the high side system of the steam turbine according to claim 3, wherein the obtaining of the optimized data of the steam temperature after the high side pressure reducing valve by the high side temperature reducing water valve automatic control system comprises:
acquiring steam temperature data of three temperature measuring points behind a high-side pressure reducing valve;
calculating a second median of the three steam temperature data;
and acquiring the steam temperature data behind the high-side pressure reducing valve according to the second median and the opening of the high-side pressure reducing valve.
5. The method for monitoring the condition of a turbine high side system according to claim 4, wherein said creating a monitoring model of a high side system based on said optimization data comprises:
selecting modeling data corresponding to each measuring point, wherein the modeling data comprises the opening instruction of the high-side pressure reducing valve, the valve position feedback of the high-side pressure reducing valve, the first difference, the opening instruction of the high-side temperature reducing water valve, the valve position feedback of the high-side temperature reducing water valve, the second difference, the steam pressure data behind the high-side pressure reducing valve, the steam temperature data behind the high-side pressure reducing valve, the rotating speed of a steam turbine, the oil pressure of a main pipe at an outlet of a hydraulic oil station, the oil pump current of the hydraulic oil station and the power PW of a unit;
selecting an algorithm, wherein the algorithm is a machine learning algorithm or a deep learning algorithm;
selecting modes, wherein the modes comprise a normal unit operation mode, a low-load mode after the unit is connected to the grid, a turbine running mode and a boiler ignition mode;
selecting historical data with normal parameter change as a training sample;
setting and adjusting the threshold value of each measuring point;
creating the monitoring model.
6. The method for monitoring the state of the high-side system of the steam turbine according to claim 5, wherein the step of judging the state of the high-side system through the monitoring model and giving an alarm when the state of the high-side system is abnormal comprises the following steps:
generating a predicted value curve of each measuring point through the monitoring model;
acquiring an actual value curve of each measuring point;
obtaining a deviation value curve according to the predicted value curve and the actual value curve;
and comparing the deviation value corresponding to each measuring point with a threshold value according to the deviation value curve, and giving an alarm when the deviation value of any measuring point is greater than the threshold value.
7. The method for monitoring the condition of the high side steam turbine system according to any of claims 1 to 6, further comprising:
and training and adjusting the monitoring model.
8. A steam turbine high side system condition monitoring system, comprising:
an acquisition module: the system comprises a high-side pressure reducing valve automatic control system, a high-side pressure reducing water valve automatic control system and a high-side pressure reducing water valve automatic control system, wherein the high-side pressure reducing valve automatic control system is used for acquiring optimized data of a plurality of high-side system measuring points;
a creation module: a monitoring model of the high-side system is created according to the optimization data;
a judging module: the monitoring model is used for judging the state of the high-side system, and when the state of the high-side system is abnormal, an alarm is given out.
9. The system for monitoring the condition of the high side system of a steam turbine according to claim 8, wherein the determining module comprises:
a generation unit: the prediction value curve of each measuring point is generated through the monitoring model;
an acquisition unit: the method is used for acquiring an actual value curve of each measuring point;
a calculation unit: obtaining a deviation value curve according to the predicted value curve and the actual value curve;
an alignment unit: and comparing the deviation value corresponding to each measuring point with a threshold value according to the deviation value curve, and giving an alarm when the deviation value of any measuring point is greater than the threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010224796.4A CN111412025B (en) | 2020-03-26 | 2020-03-26 | Method and system for monitoring state of high-side system of steam turbine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010224796.4A CN111412025B (en) | 2020-03-26 | 2020-03-26 | Method and system for monitoring state of high-side system of steam turbine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111412025A CN111412025A (en) | 2020-07-14 |
| CN111412025B true CN111412025B (en) | 2022-08-02 |
Family
ID=71489298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010224796.4A Active CN111412025B (en) | 2020-03-26 | 2020-03-26 | Method and system for monitoring state of high-side system of steam turbine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111412025B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112212358B (en) * | 2020-09-03 | 2023-01-20 | 海南热带海洋学院 | Thermal power generating unit coordination control system and coordination control method thereof |
| CN113034306B (en) * | 2021-03-05 | 2023-04-07 | 西安热工研究院有限公司 | On-line judgment thermal power generating unit method for starting a standstill |
| CN113027545B (en) * | 2021-03-25 | 2022-09-27 | 西安热工研究院有限公司 | Bypass control method for stabilizing steam drum liquid level of gas-steam combined cycle unit |
| CN113756886A (en) * | 2021-04-20 | 2021-12-07 | 通辽霍林河坑口发电有限责任公司 | Fault judgment method and system for steam turbine heater |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103382860A (en) * | 2013-05-24 | 2013-11-06 | 华电国际电力股份有限公司山东分公司 | Control method for steam turbine power generation and heat supply system |
| CN104633638A (en) * | 2014-09-01 | 2015-05-20 | 国家电网公司 | Comprehensive control method for function of machine halt without boiler shutdown in power plant FCB |
| CN106870484A (en) * | 2015-12-13 | 2017-06-20 | 申久祝 | A kind of turbine high-pressure bypass valve control system based on electro-hydraulic proportional valve |
| CN109933048A (en) * | 2019-03-26 | 2019-06-25 | 华电国际电力股份有限公司技术服务分公司 | Turbine shafting stability assessment, Warning System and method |
| CN110159362A (en) * | 2019-06-17 | 2019-08-23 | 南海发电一厂有限公司 | A kind of turbine by-pass control system |
-
2020
- 2020-03-26 CN CN202010224796.4A patent/CN111412025B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103382860A (en) * | 2013-05-24 | 2013-11-06 | 华电国际电力股份有限公司山东分公司 | Control method for steam turbine power generation and heat supply system |
| CN104633638A (en) * | 2014-09-01 | 2015-05-20 | 国家电网公司 | Comprehensive control method for function of machine halt without boiler shutdown in power plant FCB |
| CN106870484A (en) * | 2015-12-13 | 2017-06-20 | 申久祝 | A kind of turbine high-pressure bypass valve control system based on electro-hydraulic proportional valve |
| CN109933048A (en) * | 2019-03-26 | 2019-06-25 | 华电国际电力股份有限公司技术服务分公司 | Turbine shafting stability assessment, Warning System and method |
| CN110159362A (en) * | 2019-06-17 | 2019-08-23 | 南海发电一厂有限公司 | A kind of turbine by-pass control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111412025A (en) | 2020-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111412025B (en) | Method and system for monitoring state of high-side system of steam turbine | |
| Park et al. | Development of a novel power curve monitoring method for wind turbines and its field tests | |
| CN102193532B (en) | Automatic start-up and shut-down optimization control system of heat-engine plant unit plant | |
| CN111503620B (en) | Water supply whole-course control system suitable for deep peak shaving of coal-fired unit | |
| US4467216A (en) | Multiple fixed hydraulic geometry turbine control system | |
| CN103628933B (en) | Realize the controlling method of Miniature steamer unit emergency protective system function | |
| US20140142766A1 (en) | Methods and systems to improve power plant performance by corrective set points | |
| CN109519233A (en) | For nuclear power plant's steam turbine into the on-line monitoring method and system of steam control valve | |
| CN108153255B (en) | DCS-based thermal power generating unit performance monitoring method and device | |
| CN117846858A (en) | Hydropower station speed regulator running state analysis method based on trend analysis system | |
| CN206818334U (en) | It is a kind of that stove coal burning caloricity real-time monitoring system is entered based on DSC | |
| CN112065647A (en) | Automatic control method for automatic power generation of small hydropower station | |
| CN113757633B (en) | Nuclear power plant steam generator water level control method and device and computer equipment | |
| CN108877973B (en) | Control method and control system for steam turbine of nuclear power station | |
| CN112502894B (en) | Method and device for controlling speed regulator of water turbine for monitoring efficiency of generator set | |
| CN106406080B (en) | A kind of long-range optimization system of AGC function and method of thermal power generation unit | |
| CN104165352B (en) | A kind of nuclear power plant evaporator Water-Level Supervising System and method for supervising thereof | |
| CN111486441B (en) | Control method for boiler superheated steam temperature override loop | |
| CN114294637B (en) | Low-temperature economizer state monitoring system and method based on machine learning | |
| CN109340038B (en) | Power gradual change fault judgment method based on continuous slope change threshold judgment | |
| CN105781646A (en) | Bypass pressure whole course automatic control method for gas-steam turbine combined cycle unit and system | |
| CN111911907A (en) | Heater water level control quality evaluation method based on normalized error integral | |
| CN114065990A (en) | Method for monitoring feed pump in thermal power plant, storage medium and electronic device | |
| CN117028220A (en) | Optimized method and system for trip override control of million-unit peak shaving single water supply pump | |
| CN111082432B (en) | Method for predicting and controlling large-frequency-difference accident condition of power grid of thermal power generating unit |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240328 Address after: 518066 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee after: Shenzhen goes out new knowledge property right management Co.,Ltd. Country or region after: China Address before: 523808 Room 308, unit 1, building 18, no.6, Libin Road, Songshanhu Park, Dongguan City, Guangdong Province Patentee before: CR POWER TECHNOLOGY INSTITUTE Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |