CN113095551A - High-pressure rotor temperature soft measurement method and system based on grey prediction model - Google Patents

High-pressure rotor temperature soft measurement method and system based on grey prediction model Download PDF

Info

Publication number
CN113095551A
CN113095551A CN202110331051.2A CN202110331051A CN113095551A CN 113095551 A CN113095551 A CN 113095551A CN 202110331051 A CN202110331051 A CN 202110331051A CN 113095551 A CN113095551 A CN 113095551A
Authority
CN
China
Prior art keywords
pressure
temperature
prediction model
sequence
gray
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110331051.2A
Other languages
Chinese (zh)
Inventor
李达
张兴
武海澄
张剑
庄义飞
甄诚
章佳威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Datang Boiler Pressure Vessel Examination Center Co Ltd
East China Electric Power Test Institute of China Datang Corp Science and Technology Research Institute Co Ltd
Original Assignee
Datang Boiler Pressure Vessel Examination Center Co Ltd
East China Electric Power Test Institute of China Datang Corp Science and Technology Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Datang Boiler Pressure Vessel Examination Center Co Ltd, East China Electric Power Test Institute of China Datang Corp Science and Technology Research Institute Co Ltd filed Critical Datang Boiler Pressure Vessel Examination Center Co Ltd
Priority to CN202110331051.2A priority Critical patent/CN113095551A/en
Publication of CN113095551A publication Critical patent/CN113095551A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00—Thermometers specially adapted for specific purposes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34—Testing dynamo-electric machines
    • G01R31/343—Testing dynamo-electric machines in operation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/34—Testing dynamo-electric machines
    • G01R31/346—Testing of armature or field windings
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/13—Differential equations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

A high-pressure rotor temperature soft measurement method and system based on a gray prediction model belong to the technical field of power plant equipment, and solve the problem of how to design a high-pressure rotor temperature soft measurement method and system based on a gray prediction model to provide a reliable prediction value to monitor unit operation after the temperature of a high-pressure inner cylinder becomes a dead point.

Description

High-pressure rotor temperature soft measurement method and system based on grey prediction model
Technical Field
The invention belongs to the technical field of power plant equipment, and relates to a high-pressure rotor temperature soft measurement method and system based on a grey prediction model.
Background
The starting process of the steam turbine is a process of accelerating the rotor from a static state or a turning state to a rated rotating speed and normally operating with load. After the high-temperature and high-pressure steam enters the steam turbine, the temperature of the high-pressure rotor of the steam turbine is not immediately increased to the steam temperature, which is to be heated for a period of time. During the heating process of the high-pressure rotor of the steam turbine, the temperature inside metal parts is uneven, and the expansion or contraction of parts is not equal, thereby causing thermal stress. Thermal stresses occur as a result of temperature differences between the surface and the interior of the metal component. In the starting process of the steam turbine, thermal stress is one of the main causes of equipment damage, and especially for high-parameter and high-capacity steam turbines, equipment damage accidents such as cylinder cracks, bolt fracture, rotor cracks and bending and the like are caused by overlarge thermal stress due to insufficient warming or improper steam parameters. Therefore, the monitoring and the control of the thermal stress in the starting process are very important, and the thermal stress is properly controlled, so that the steam turbine can be started safely and quickly, the service life loss can be reduced, and the service life can be prolonged.
In the thermal stress estimator of the Siemens steam turbine set, the measured temperature of the high-pressure inner cylinder is firstly used for approximately representing the temperature of the surface of the high-pressure rotor, the volume average temperature of the rotor is indirectly calculated by accumulating first-order inertia links with 3 different weights of the surface temperature of the high-pressure rotor, and the difference value of the surface temperature of the rotor and the volume average temperature of the rotor represents the magnitude of the stress of the rotor. Therefore, whether the measurement of the surface temperature value of the rotor used in the thermal stress monitoring is accurate or not directly influences the accuracy of the thermal stress value, and the method is the key for ensuring the thermal stress control of the steam turbine. However, because the rotor rotates, the temperature measuring element cannot be installed to directly measure the temperature of the rotor, the measured temperature of the high-pressure inner cylinder is adopted to approximately represent the temperature of the surface of the high-pressure rotor at present, and the problems that the temperature measuring element of the high-pressure inner cylinder temperature measuring point is easy to damage and a unit is inconvenient to overhaul and replace during operation exist.
In the prior art, a chinese patent application "a prediction model soft measurement method based on deep learning" with an application number of 201711498840.5 and a publication date of 2018, 6 and 22 discloses a prediction model soft measurement method based on deep learning, which includes: obtaining historical data; the historical data is normalized according to the time window; extracting multi-scale information of the structured historical data by using stationary wavelet transform; combining the multi-scale information with the current observable variable data corresponding to each time point to form a sample data set; forming a training set and a test set according to the sample data set; training and testing the depth model with the attention mechanism by using a training set and a testing set to form a complete model; and obtaining a predicted value according to the current observable data and the complete model.
Although the technical scheme aims at the characteristic that some important variables in the chemical production process are difficult to directly measure, the prediction model soft measurement method based on deep learning provided by the invention realizes accurate prediction of unobservable variables in the chemical production process, provides a reference index for subsequent energy efficiency analysis, and thus improves the productivity and reduces the energy consumption. However, the problem of how to provide a reliable predicted value to monitor the operation of the unit after the temperature of the high-pressure inner cylinder becomes a dead center is not solved.
Disclosure of Invention
The invention aims to design a high-pressure rotor temperature soft measurement method and system based on a grey prediction model, so that a reliable prediction value is provided to monitor the operation of a unit after the temperature of a high-pressure inner cylinder becomes a dead pixel.
The invention solves the technical problems through the following technical scheme:
a high-pressure rotor temperature soft measurement method based on a grey prediction model comprises the following steps:
s1, inputting multiple groups of parameters of rated load working conditions of different proportions, calculating parameter values of corresponding prediction models of rated load working conditions of different proportions according to the grey prediction model, and storing the parameter values in the single-input multi-output function converter;
s2, after the temperature of the high-pressure inner cylinder is changed into a dead center, detecting and inputting the actual load working condition parameters of the unit on line, calling the parameter values of the corresponding prediction models of the rated load working conditions with different proportions from the single-input multi-output function converter, inputting the parameter values into the gray prediction model, and calculating and outputting the predicted value of the surface temperature of the high-pressure rotor under the actual load working condition of the unit;
s3, comparing the difference value between the predicted value of the surface temperature of the high-pressure rotor output in the step S2 and the actual temperature of the high-pressure inner cylinder, if the deviation is within the set threshold value range, performing the step S4, otherwise, returning to the step S2;
and S4, outputting the predicted value of the surface temperature of the high-pressure rotor and the parameter value of the gray model.
As a further improvement of the technical solution of the present invention, the rated loads with different proportions described in step S1 include 50% -100% of the rated load.
As a further improvement of the technical solution of the present invention, the multiple sets of parameters in step S1 include a high-pressure inner cylinder temperature, a turbine generator set electric power, a main steam temperature, a main steam pressure, a high-pressure cylinder 1 st stage extraction pressure, and a high-pressure cylinder exhaust pressure.
As a further improvement of the technical scheme of the invention, the whitening differential equation of the gray prediction model is as follows:
Figure BDA0002994428790000021
wherein the content of the first and second substances,
Figure BDA0002994428790000022
respectively showing high-pressure inner cylinder temperature sequence, steam turbine generator set electric power sequence, main steam temperature sequence, main steam pressure sequence, high-pressure cylinder 1 st stage steam extraction pressure sequence and high-pressure cylinder steam extraction pressure sequence, a and b1、b2、b3、b4、b5T represents time for the parameter values of the prediction model.
As a further improvement of the technical solution of the present invention, the set threshold value in step S3 is: (-3, +3) deg.C.
A high-pressure rotor temperature soft measurement system based on a grey prediction model comprises:
the parameter storage module is used for inputting multiple groups of parameters of rated load working conditions in different proportions, calculating parameter values of corresponding prediction models of the rated load working conditions in different proportions according to the grey prediction model, and storing the parameter values in the single-input multi-output function converter;
the calculation module detects and inputs the actual load working condition parameters of the unit on line after the temperature of the high-pressure inner cylinder becomes a dead point, calls the parameter values of the corresponding prediction models of the rated load working conditions with different proportions from the single-input multi-output function converter, inputs the parameter values into the grey prediction model, and calculates and outputs the predicted value of the surface temperature of the high-pressure rotor under the actual load working condition of the unit;
and the comparison output module compares the difference value between the high-pressure rotor surface temperature predicted value output by the calculation module and the actual high-pressure inner cylinder temperature, outputs the high-pressure rotor surface temperature predicted value and the parameter value of the gray model if the deviation is within a set threshold range, and returns to the calculation module to recalculate and output the high-pressure rotor surface temperature predicted value under the actual load working condition of the unit if the deviation is not within the set threshold range.
As a further improvement of the technical scheme of the invention, the rated loads with different proportions in the parameter storage module comprise 50% -100% of rated loads.
As a further improvement of the technical scheme of the invention, the multiple groups of parameters in the parameter storage module comprise high-pressure inner cylinder temperature, electric power of a steam turbine generator set, main steam temperature, main steam pressure, 1 st-stage steam extraction pressure of the high-pressure cylinder and high-pressure cylinder exhaust pressure.
As a further improvement of the technical scheme of the invention, the whitening differential equation of the gray prediction model in the parameter storage module and the calculation module is as follows:
Figure BDA0002994428790000031
wherein the content of the first and second substances,
Figure BDA0002994428790000032
respectively showing high-pressure inner cylinder temperature sequence, steam turbine generator set electric power sequence, main steam temperature sequence, main steam pressure sequence, high-pressure cylinder 1 st stage steam extraction pressure sequence and high-pressure cylinder steam extraction pressure sequence, a and b1、b2、b3、b4、b5T represents time for the parameter values of the prediction model.
As a further improvement of the technical solution of the present invention, the set threshold in the comparison output module is: (-3, +3) deg.C.
The invention has the advantages that: according to the soft measurement method and system for the high-pressure rotor temperature based on the gray prediction model, after the high-pressure inner cylinder temperature is changed into a dead pixel, the actual load working condition parameters of a unit are detected and input on line, the parameter values of the prediction model of the corresponding rated load working conditions in different proportions are called from the single-input multi-output function converter and input into the gray prediction model, the predicted value of the high-pressure rotor surface temperature under the actual load working condition of the unit is calculated and output, the high-pressure rotor temperature is predicted accurately, and a reliable predicted value is provided to monitor the unit operation.
Drawings
FIG. 1 is a schematic diagram of a high pressure rotor temperature soft measurement method based on a grey prediction model according to an embodiment of the present invention;
FIG. 2 is a flow chart of the gray model creation of the soft measurement method of the high-pressure rotor temperature based on the gray prediction model according to the embodiment of the invention;
fig. 3 is a structural diagram of a high-pressure rotor temperature soft measurement system based on a gray prediction model according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all 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 technical scheme of the invention is further described by combining the drawings and the specific embodiments in the specification:
1. as shown in fig. 1, a gray prediction model is established by 5 parameters of steam turbine generator set electric power (I1), main steam temperature (I2), main steam pressure (I3), high-pressure cylinder stage 1 extraction pressure (I4) and high-pressure cylinder exhaust pressure (I5) which are detected on line. The principle of the gray prediction model p (predict) is as follows:
the gray system theory is a gray derivative and gray differential equation defined based on concepts of correlation space, smooth discrete function, etc., and the model is approximate and non-unique and is denoted as GM (Grey model). The gray model is a generated number that becomes less random and more regular by using discrete random numbers, which makes it more accurate to describe its course of variation.
The grey prediction model in the invention adopts a grey GM (1, N) model, and the generation method is accumulation generation. The number series of 6 elements in total:
Figure BDA0002994428790000041
Figure BDA0002994428790000042
the cumulative generation (AGO) generation sequence of (a) is:
Figure BDA0002994428790000043
wherein
Figure BDA0002994428790000051
The principle of gray GM (1, N) modeling is as follows.
There are 6 number sequences:
Figure BDA0002994428790000052
note the book
Figure BDA0002994428790000053
Is composed of
Figure BDA0002994428790000054
To obtain a generation sequence:
Figure BDA0002994428790000055
note the book
Figure BDA0002994428790000056
Average number series of (c):
Figure BDA0002994428790000057
the gray differential equation for GM (1, N) can be obtained:
Figure BDA0002994428790000058
wherein a and b are parameters
We will count up
Figure BDA0002994428790000059
The time k of (1), (2), (…), (6) is regarded as a continuous variable t, and the sequence is counted
Figure BDA00029944287900000510
Viewed in turn as a function of time t
Figure BDA00029944287900000511
If array
Figure BDA00029944287900000512
To pair
Figure BDA00029944287900000513
Has an effect on the rate of change of the signal, a whitening differential equation can be established:
Figure BDA00029944287900000514
this differential equation is modeled as GM (1, N). a, b1,b2,b3,b4,b5The parameter values of the prediction model are denoted as P (X).
2. The rotor temperature prediction model creates a flow chart, as shown in FIG. 2.
Step 1: respectively introducing 11 groups of parameters (high-pressure inner cylinder temperature, electric power of a steam turbine generator set, main steam temperature, main steam pressure, 1 st-stage steam extraction pressure of a high-pressure cylinder and high-pressure cylinder exhaust pressure) under 50-100% rated load working conditions, wherein the parameters are respectively 50%, 55%, 60%, 65%, 70%, 75%, 80%, 85%, 90%, 95% and 100% rated working conditions.
Step 2: the 11 groups of data were sequentially subjected to gray prediction model calculation.
And step 3: in turn, 11 sets of model parameter values were obtained.
And 4, step 4: and calculating to obtain a predicted value of the surface temperature of the high-pressure rotor under each working condition through 11 groups of model parameter values, comparing the predicted value with the actual temperature of the high-pressure inner cylinder, and carrying out the next step when the deviation is less than +/-3 ℃. Otherwise, returning to the step 2.
And 5: and outputting the predicted value of the surface temperature of the high-pressure rotor and the parameter value P (X) of the gray model.
3. As shown in fig. 3, the parameter values p (x) of 11 sets of gray models are recorded in the single-input multiple-output function converter t (transform). And outputting corresponding grey model parameter values by the current load through a single-input multi-output function converter T, and calculating to obtain a high-pressure rotor surface temperature predicted value through model operation.
Using electric power (I) of steam turbine generator sets1) Main steam temperature (I)2) Main steam pressure (I)3) High pressure cylinder 1 st stage extraction pressure (I)4) And high pressure cylinder exhaust pressure (I)5) And 5 parameters, respectively calculating model parameters under the working condition of 50-100% rated load, and outputting the model parameters when the error between the high-pressure rotor temperature obtained by model operation and the actually measured high-pressure inner cylinder temperature is within +/-3 ℃.
The temperature of the high pressure rotor surface is currently approximated by the measured high pressure inner cylinder temperature. The temperature measuring element of the high-pressure inner cylinder temperature measuring point is easy to damage, and the unit is inconvenient to overhaul and replace during operation. The high-pressure rotor temperature soft measurement method based on the gray prediction model can provide a reliable predicted value to monitor the operation of the unit after the temperature of the high-pressure inner cylinder is changed into a dead pixel, and is very important for monitoring and controlling the thermal stress in the starting process of the unit.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A high-pressure rotor temperature soft measurement method based on a grey prediction model is characterized by comprising the following steps:
s1, inputting multiple groups of parameters of rated load working conditions of different proportions, calculating parameter values of corresponding prediction models of rated load working conditions of different proportions according to the grey prediction model, and storing the parameter values in the single-input multi-output function converter;
s2, after the temperature of the high-pressure inner cylinder is changed into a dead center, detecting and inputting the actual load working condition parameters of the unit on line, calling the parameter values of the corresponding prediction models of the rated load working conditions with different proportions from the single-input multi-output function converter, inputting the parameter values into the gray prediction model, and calculating and outputting the predicted value of the surface temperature of the high-pressure rotor under the actual load working condition of the unit;
s3, comparing the difference value between the predicted value of the surface temperature of the high-pressure rotor output in the step S2 and the actual temperature of the high-pressure inner cylinder, if the deviation is within the set threshold value range, performing the step S4, otherwise, returning to the step S2;
and S4, outputting the predicted value of the surface temperature of the high-pressure rotor and the parameter value of the gray model.
2. The method for soft measurement of the temperature of the high-pressure rotor based on the gray prediction model is characterized in that the rated loads with different proportions in the step S1 comprise 50% -100% of the rated loads.
3. The gray prediction model-based soft measurement method for the temperature of the high-pressure rotor according to claim 1, wherein the plurality of sets of parameters in step S1 include high-pressure inner cylinder temperature, steam turbine generator set electric power, main steam temperature, main steam pressure, high-pressure cylinder stage 1 extraction pressure, and high-pressure cylinder exhaust pressure.
4. The method for soft measurement of the temperature of the high-pressure rotor based on the gray prediction model as claimed in claim 1, wherein the whitening differential equation of the gray prediction model is as follows:
Figure FDA0002994428780000011
wherein the content of the first and second substances,
Figure FDA0002994428780000012
respectively showing high-pressure inner cylinder temperature sequence, steam turbine generator set electric power sequence, main steam temperature sequence, main steam pressure sequence, high-pressure cylinder 1 st stage steam extraction pressure sequence and high-pressure cylinder steam extraction pressure sequence, a and b1、b2、b3、b4、b5T represents time for the parameter values of the prediction model.
5. The method for soft measurement of the temperature of the high-pressure rotor based on the gray prediction model as claimed in claim 1, wherein the set threshold values in step S3 are: (-3, +3) deg.C.
6. A high-pressure rotor temperature soft measurement system based on a grey prediction model is characterized by comprising:
the parameter storage module is used for inputting multiple groups of parameters of rated load working conditions in different proportions, calculating parameter values of corresponding prediction models of the rated load working conditions in different proportions according to the grey prediction model, and storing the parameter values in the single-input multi-output function converter;
the calculation module detects and inputs the actual load working condition parameters of the unit on line after the temperature of the high-pressure inner cylinder becomes a dead point, calls the parameter values of the corresponding prediction models of the rated load working conditions with different proportions from the single-input multi-output function converter, inputs the parameter values into the grey prediction model, and calculates and outputs the predicted value of the surface temperature of the high-pressure rotor under the actual load working condition of the unit;
and the comparison output module compares the difference value between the high-pressure rotor surface temperature predicted value output by the calculation module and the actual high-pressure inner cylinder temperature, outputs the high-pressure rotor surface temperature predicted value and the parameter value of the gray model if the deviation is within a set threshold range, and returns to the calculation module to recalculate and output the high-pressure rotor surface temperature predicted value under the actual load working condition of the unit if the deviation is not within the set threshold range.
7. The gray prediction model-based soft measurement system for the temperature of the high-pressure rotor according to claim 6, wherein the rated loads of different proportions in the parameter storage module comprise 50% -100% of the rated load.
8. The gray predictive model-based soft measurement system for high pressure rotor temperature according to claim 6, wherein the plurality of sets of parameters in the parameter storage module include high pressure inner cylinder temperature, steam turbine generator set electrical power, main steam temperature, main steam pressure, high pressure cylinder stage 1 extraction pressure, and high pressure cylinder extraction pressure.
9. The soft measurement system for the temperature of the high-pressure rotor based on the gray prediction model as claimed in claim 6, wherein the whitening differential equation of the gray prediction model in the parameter storage module and the calculation module is as follows:
Figure FDA0002994428780000021
wherein the content of the first and second substances,
Figure FDA0002994428780000022
respectively showing high-pressure inner cylinder temperature sequence, steam turbine generator set electric power sequence, main steam temperature sequence, main steam pressure sequence, high-pressure cylinder 1 st stage steam extraction pressure sequence and high-pressure cylinder steam extraction pressure sequence, a and b1、b2、b3、b4、b5T represents time for the parameter values of the prediction model.
10. The grey prediction model-based high-pressure rotor temperature soft measurement system according to claim 6, wherein the set threshold values in the comparison output module are: (-3, +3) deg.C.
CN202110331051.2A 2021-03-26 2021-03-26 High-pressure rotor temperature soft measurement method and system based on grey prediction model Pending CN113095551A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110331051.2A CN113095551A (en) 2021-03-26 2021-03-26 High-pressure rotor temperature soft measurement method and system based on grey prediction model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110331051.2A CN113095551A (en) 2021-03-26 2021-03-26 High-pressure rotor temperature soft measurement method and system based on grey prediction model

Publications (1)

Publication Number Publication Date
CN113095551A true CN113095551A (en) 2021-07-09

Family

ID=76670478

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110331051.2A Pending CN113095551A (en) 2021-03-26 2021-03-26 High-pressure rotor temperature soft measurement method and system based on grey prediction model

Country Status (1)

Country Link
CN (1) CN113095551A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102705078A (en) * 2012-04-19 2012-10-03 哈尔滨工程大学 Diesel engine fault prediction method based on gray model
CN103226664A (en) * 2013-05-07 2013-07-31 上海发电设备成套设计研究院 External surface temperature pre-testing method and device for high pressure rotor of throttle adjusting type steam turbine
CN104573170A (en) * 2014-10-13 2015-04-29 芜湖扬宇机电技术开发有限公司 Method for determining initial pressure of optimal operation of steam turbine
WO2018001338A1 (en) * 2016-06-30 2018-01-04 上海海洋大学 Grey system-based pelagic squid resource richness forecasting method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102705078A (en) * 2012-04-19 2012-10-03 哈尔滨工程大学 Diesel engine fault prediction method based on gray model
CN103226664A (en) * 2013-05-07 2013-07-31 上海发电设备成套设计研究院 External surface temperature pre-testing method and device for high pressure rotor of throttle adjusting type steam turbine
CN104573170A (en) * 2014-10-13 2015-04-29 芜湖扬宇机电技术开发有限公司 Method for determining initial pressure of optimal operation of steam turbine
WO2018001338A1 (en) * 2016-06-30 2018-01-04 上海海洋大学 Grey system-based pelagic squid resource richness forecasting method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
汤镭等: "基于灰色系统理论的火电机组3种实时数据的预测", 上海电机学院学报, vol. 22, no. 2, pages 74 - 77 *

Similar Documents

Publication Publication Date Title
CN110298455B (en) Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction
Qian et al. Data-driven condition monitoring approaches to improving power output of wind turbines
CN110763997A (en) Early fault early warning method for synchronous motor stator
CN110262450B (en) Fault prediction method for cooperative analysis of multiple fault characteristics of steam turbine
Liu et al. Research on fault diagnosis of wind turbine based on SCADA data
TW201224786A (en) Method of efficacy anticipation and failure examination for an apparatus
CN102663412A (en) Power equipment current-carrying fault trend prediction method based on least squares support vector machine
CN111415070A (en) Wind turbine generator gearbox oil temperature over-temperature fault early warning method based on SCADA data
CN112132394B (en) Power plant circulating water pump predictive state evaluation method and system
CN111929579B (en) Generator online fault diagnosis method and device and computer device
CN115453356B (en) Power equipment operation state monitoring and analyzing method, system, terminal and medium
CN115313930A (en) Method for predicting excitation current of large-scale steam turbine generator in real time
CN111723982A (en) Medium-and-long-term power load combined prediction method based on gray-Markov chain
CN115294671A (en) Air compressor outlet pressure prediction method and prediction system
CN111814849A (en) DA-RNN-based wind turbine generator key component fault early warning method
CN116956203B (en) Method and system for measuring action characteristics of tapping switch of transformer
CN113095551A (en) High-pressure rotor temperature soft measurement method and system based on grey prediction model
CN112240267B (en) Fan monitoring method based on wind speed correlation and wind power curve
CN115238573A (en) Hydroelectric generating set performance degradation trend prediction method and system considering working condition parameters
CN105095650A (en) Method for selecting remanufacturing time of mechanical part based on reliability evaluation
Tingting et al. Early warning method for power station auxiliary failure considering large-scale operating conditions
Zheng et al. Fault prediction of fan gearbox based on deep belief network
Fang et al. Failure Prediction of Wind Turbines Using Improved Gray Relation Analysis Based Support Vector Machine Method
Ou et al. Fault Prediction Model of Wind Power Pitch System Based on BP Neural Network
CN111914353B (en) Rotor low-cycle fatigue loss detection method, device and computer equipment

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