CN112329271A - Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs - Google Patents

Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs Download PDF

Info

Publication number
CN112329271A
CN112329271A CN202011403590.4A CN202011403590A CN112329271A CN 112329271 A CN112329271 A CN 112329271A CN 202011403590 A CN202011403590 A CN 202011403590A CN 112329271 A CN112329271 A CN 112329271A
Authority
CN
China
Prior art keywords
index
peak regulation
matrix
module
thermal power
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
CN202011403590.4A
Other languages
Chinese (zh)
Inventor
张绪辉
辛刚
袁森
崔福兴
高嵩
赵中华
庞向坤
董信光
杨兴森
胡志宏
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.)
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
State Grid Shandong Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd
State Grid Shandong Electric Power 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 State Grid Corp of China SGCC, Electric Power Research Institute of State Grid Shandong Electric Power Co Ltd, State Grid Shandong Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202011403590.4A priority Critical patent/CN112329271A/en
Publication of CN112329271A publication Critical patent/CN112329271A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • 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
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Business, Economics & Management (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Economics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Primary Health Care (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Regulation And Control Of Combustion (AREA)

Abstract

The invention provides a thermal power generating unit peak regulation key index identification method and device based on multiple PCAs (principal component analysis), which are used for establishing a peak regulation index collection suitable for a thermal power generating unit and classifying peak regulation indexes to obtain an original data matrix, solving sample correlation coefficients of a converted standardized matrix, solving a characteristic equation of a correlation coefficient matrix to obtain characteristic values, calculating information contribution rates corresponding to the characteristic values, accumulating the information contribution rates one by one from large to small, judging whether the accumulated sum is larger than a threshold value, if so, taking corresponding main components as peak regulation key factors, and outputting the peak regulation key indexes corresponding to the peak regulation indexes. According to the method, the influence degree of key limited factors of the peak regulation capability of the thermal power unit is quantitatively analyzed according to historical operating data of the thermal power unit, the influence degrees of different factors on the peak regulation performance of the thermal power unit are distinguished, various operating risks in peak regulation operation are deeply known, and the safe and stable operation of the unit is guaranteed.

Description

Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs
Technical Field
The invention relates to the field of peak shaving operation of thermal power generating units, in particular to a method for analyzing each limited factor in the peak shaving operation of the thermal power generating units by utilizing a principal component analysis technology so as to identify key factors of the peak shaving operation of the units.
Background
At present, renewable energy sources such as wind power, thermal power and the like are rapidly developed in the installed scale in China, meanwhile, in order to guarantee new energy consumption, the state sets out policies of preferential consumption of power generation such as wind power and photovoltaic, and in order to ensure real-time balance of electric power, a power grid needs a thermal power generating unit to provide peak regulation service to support power grid peak regulation. Therefore, the thermal power generating unit participates in the peak shaving of the power grid more, the time and frequency of the low-load operation are obviously improved, and the difference is caused by the operation process which is more adaptive to the prior unit.
The existing thermal power generating unit participates in peak shaving and has the following problems: (1) because the operation load of the thermal power generating unit is relatively stable and the average load is higher, the thermal power generating unit operation personnel can not know the peak regulation performance of the unit and can not know various operation risks in the peak regulation operation deeply; (2) the peak regulation process is a great test for auxiliary machines such as boilers, steam turbines, coal mills, induced draft fans and the like, the safety performance of each unit in peak regulation operation is different, and key indexes of the peak regulation operation of each unit need to be specifically analyzed.
Therefore, an identification method for key indexes of peak shaving operation of each unit needs to be established, which is helpful for helping operators to establish knowledge of the peak shaving operation of the responsible unit, and can also perform key analysis and improvement on ensuring safe and stable operation of the unit and recognizing key index weak links of the unit in the peak shaving operation.
Disclosure of Invention
The invention provides a thermal power generating unit peak regulation key index identification method based on multiple PCAs, which specifically comprises the following steps:
s1: establishing a peak regulation index collection suitable for the thermal power generating unit;
s2: classifying the peak regulation indexes;
s3: listing a variable and observed quantity table under the peak regulation indexes to obtain an original data matrix;
s4: analyzing each index, determining a positive index and a negative index, and performing matrix conversion;
s5: carrying out standardized transformation on the matrix to obtain a standardized matrix;
s6: solving a sample correlation coefficient for the normalized matrix;
s7: solving a characteristic equation of the correlation coefficient matrix to obtain a characteristic value;
s8: calculating the information contribution rate corresponding to the characteristic value, and accumulating one by one from large to small;
s9: judging whether the accumulated sum in the step S8 is greater than 0.9, if so, outputting peak shaving indexes corresponding to the characteristic values, otherwise, returning to the step S8;
s10: and outputting the key peak regulation indexes corresponding to the peak regulation indexes.
Optionally, in the step S2, the peak shaving index is divided into a stable combustion index, an operation index and an environmental protection index.
Optionally, the stable combustion indicator comprises: negative pressure of the hearth, fire detection signals, excess air coefficients, flue gas temperature at the outlet of the hearth, and differential pressure between the hearth and secondary air.
Optionally, the operation index includes: the method comprises the following steps of main steam temperature, water wall temperature, superheater wall temperature, reheater wall temperature, steam turbine shaft vibration, steam turbine axial displacement, coal mill outlet temperature, air preheater pressure difference, SCR inlet smoke temperature, draught fan current, primary fan current and coal mill current.
Optionally, the environmental protection index includes: ammonia slip concentration, NOx emission concentration, dust emission concentration, SO2 emission concentration.
Optionally, the observation amount in the step S3 is 100% to 10% of the load of the unit.
Optionally, the original data matrix in step S3 is represented as:
Figure BDA0002817859680000031
wherein XijWhen the load of the unit is measured to be 100% -10% by observation, the 1 st-m variable value under the peak regulation index is shown, wherein i is 1-10, and j is 1-m.
Optionally, the above matrix is converted according to the positive index and the inverse index, that is, the matrix is
Figure BDA0002817859680000032
Get Y ═ Yij)n×mWhen the load variable is 10%, m is 10.
Optionally, the normalization matrix in step S5 is represented as:
Figure BDA0002817859680000033
wherein the content of the first and second substances,
Figure BDA0002817859680000034
in the formula
Figure BDA0002817859680000035
Optionally, the sample correlation coefficient in step S6 is expressed as:
Figure BDA0002817859680000036
wherein the content of the first and second substances,
Figure BDA0002817859680000041
optionally, step S7 includes:
solving a characteristic equation
|V-λE|＝0
M characteristic values, lambda, can be obtained1，λ2，λ3…λmAnd are arranged from large to small.
Optionally, the step S8 of calculating the information contribution ratio corresponding to the feature value includes:
calculating the eigenvalue lambdaj(j ═ 1, 2, …, m) of information contribution rate ajThe calculation formula is as follows:
Figure BDA0002817859680000042
the invention also provides a thermal power generating unit peak regulation key index identification device based on multiple PCAs, which comprises the following steps:
an input module: the method is used for establishing a peak regulation index set suitable for the thermal power generating unit;
the classification module is connected with the input module and is used for classifying the peak regulation indexes;
the matrix forming module is connected with the peak regulation index classifying module, lists a variable and observed quantity table under the peak regulation index and obtains an original data matrix;
the matrix conversion module is connected with the matrix forming module, analyzes each index, determines a positive index and a negative index, and performs matrix conversion;
the standardized matrix conversion module is connected with the matrix conversion module and is used for carrying out standardized transformation on the matrix to obtain a standardized matrix;
the coefficient solving module is connected with the standardized matrix conversion module and is used for solving a sample correlation coefficient aiming at the standardized matrix;
the characteristic value calculation module is connected with the coefficient solving module and is used for solving a characteristic equation of the correlation coefficient matrix to obtain a characteristic value;
the sorting module is connected with the characteristic value calculating module, calculates the information contribution rate corresponding to the characteristic value and accumulates the information contribution rate from large to small one by one;
the judging module is connected with the sorting module and is used for judging whether the accumulated sum of the information contribution rates is larger than a threshold value or not, and if so, the corresponding main component is taken as a peak regulation key factor;
and the output module is connected with the judging module and outputs the key peak regulation indexes corresponding to the peak regulation indexes.
Compared with the prior art, the invention has the following beneficial technical effects:
according to the method, an analysis method of each peak regulation factor is established by utilizing a PCA method according to historical operation data of the thermal power generating unit, influence factors of the peak regulation operation of the thermal power generating unit are obtained by analyzing data and characteristics of low-load operation of hundreds of thermal power generating units, and influence degrees of different factors on the peak regulation performance of the thermal power generating unit are distinguished.
Quantitative analysis is established for the influence degree of key limited factors of the peak regulation capacity of the thermal power generating unit, various operation risks in peak regulation operation are deeply known, and safe and stable operation of the unit is guaranteed.
Drawings
Fig. 1 is a flow chart of the method for identifying key indexes of peak shaving of the thermal power generating unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
The invention aims to provide a thermal power generating unit peak regulation operation key index identification method based on multiple PCAs.
The method specifically comprises the following steps:
(1) and establishing a peak regulation operation index collection suitable for most thermal power generating units. In the peak regulation operation of the unit, economic indexes are not considered, and stable combustion indexes, safe operation indexes and environmental protection indexes are mainly considered. In the peak regulation operation process of the thermal power generating unit, boiler stable combustion, safe and stable operation of the unit and environmental standard reaching are used as important references, when index analysis is carried out, if all indexes are not distinguished and PCA analysis is carried out together, part of indexes can be ignored, so that all indexes are not suitable for being analyzed in a unified mode, and a multiple PCA method is adopted for peak regulation operation key index identification.
(2) And establishing a stable combustion index, an operation index and a secondary index under an environment protection index.
The stable combustion indexes include: negative pressure of the hearth, fire detection signals, excess air coefficients, flue gas temperature at the outlet of the hearth, and differential pressure between the hearth and secondary air.
The operation indexes comprise: the method comprises the following steps of main steam temperature, water wall temperature, superheater wall temperature, reheater wall temperature, steam turbine shaft vibration, steam turbine axial displacement, coal mill outlet temperature, air preheater pressure difference, SCR inlet smoke temperature, draught fan current, primary fan current and coal mill current.
The environmental protection indexes comprise: ammonia slip concentration, NOx emission concentration, dust emission concentration, SO2 emission concentration.
(3) And respectively listing a variable and observed quantity table under a stable combustion index, a safe operation index and an environmental protection index, wherein the data taking is based on the unit load, and the data can be sequentially taken according to the unit capacity of 100 percent to 10 percent, and each 10 percent is one grade. Taking the safe operation index as an example, the method is shown in Table 1
TABLE 1
Figure BDA0002817859680000071
Obtaining an original data matrix:
Figure BDA0002817859680000072
(4) and analyzing each index to determine a positive index and a negative index. Taking the safe operation index as an example, in the normal operation range of the unit, the main steam temperature, the wall temperature of a water cooling wall, the wall temperature of a superheater, the wall temperature of a reheater, the axial vibration of a steam turbine, the axial displacement of the steam turbine, the smoke temperature of an SCR inlet, the current of an induced draft fan, the current of a primary air fan and the current of a coal mill are positive indexes, and the outlet temperature of the coal mill and the differential pressure of an air preheater are negative indexes.
The matrix is converted according to the positive index and the inverse index, namely
Figure BDA0002817859680000073
Get Y ═ Yij)n×m
(5) Performing a normalized transformation, i.e.
Figure BDA0002817859680000081
(wherein m is 10 when the load is taken every 10% as the load variable),
Figure BDA0002817859680000082
a normalized matrix Z is obtained:
Figure BDA0002817859680000083
(6) the sample correlation coefficient is calculated for the normalization matrix Z:
Figure BDA0002817859680000084
wherein the content of the first and second substances,
Figure BDA0002817859680000085
(7) solving a characteristic equation of the correlation coefficient matrix for the matrix V:
|V-λE|＝0
m characteristic values, lambda, can be obtained1，λ2，λ3…λmAnd are arranged from large to small.
(8) Calculating the eigenvalue lambdaj(j ═ 1, 2, …, m). The calculation formula is as follows:
Figure BDA0002817859680000086
(9) and accumulating the information contribution rates according to the sequence of the lambda values from large to small, stopping when the information contribution rates are accumulated to 0.9, and taking the corresponding principal component as a peak regulation key factor.
(10) According to the method, the stable combustion index and the environmental protection index are calculated to obtain a key index, and all indexes are used as key peak regulation factors.
The invention also provides a thermal power generating unit peak regulation key index identification device based on multiple PCAs, which comprises the following steps:
an input module: the method is used for establishing a peak regulation index set suitable for the thermal power generating unit;
peak regulation index classification module: classifying the peak regulation indexes;
a matrix forming module: listing a variable and observed quantity table under the peak regulation indexes to obtain an original data matrix;
a matrix conversion module: analyzing each index, determining a positive index and a negative index, and performing matrix conversion;
a normalization matrix conversion module: carrying out standardized transformation on the matrix to obtain a standardized matrix;
a coefficient solving module: solving a sample correlation coefficient for the normalized matrix;
a characteristic value calculation module: solving a characteristic equation of the correlation coefficient matrix to obtain a characteristic value;
the information contribution rate sorting module:
calculating the information contribution rate corresponding to the characteristic value, and accumulating one by one from large to small;
peak regulation index judgment module: judging whether the accumulated sum in the step S8 is greater than 0.9, if so, outputting peak shaving indexes corresponding to the characteristic values, otherwise, returning to the step S8;
an output module: and outputting the key peak regulation indexes corresponding to the peak regulation indexes.
By establishing the identification method aiming at the key indexes of the peak shaving operation of each unit, the method is helpful for helping operators to establish the understanding of the peak shaving operation of the responsible unit, can also ensure the safe and stable operation of the unit, and can perform key analysis and improvement on the key index weak links of the unit in the peak shaving operation.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.

Claims (26)

1. A thermal power generating unit peak regulation key index identification method based on multiple PCAs is characterized by comprising the following steps:
s1: establishing a peak regulation index collection suitable for the thermal power generating unit;
s2: classifying the peak regulation indexes;
s3: listing a variable and observed quantity table under the peak regulation indexes to obtain an original data matrix;
s4: analyzing each index, determining a positive index and a negative index, and performing matrix conversion;
s5: carrying out standardized transformation on the matrix to obtain a standardized matrix;
s6: solving a sample correlation coefficient for the normalized matrix;
s7: solving a characteristic equation of the correlation coefficient matrix to obtain a characteristic value;
s8: calculating the information contribution rate corresponding to the characteristic value, and accumulating one by one from large to small;
s9: judging whether the accumulated sum in the step S8 is larger than a threshold value, if so, taking the corresponding main component as a peak regulation key factor, and if not, returning to the step S8; .
S10: and outputting the key peak regulation indexes corresponding to the peak regulation indexes.
2. The method of claim 1, wherein the peak shaver index is divided into a stable combustion index, an operation index and an environmental index in step S2.
3. The method of claim 2, wherein the stable combustion indicator comprises: negative pressure of the hearth, fire detection signals, excess air coefficients, flue gas temperature at the outlet of the hearth, and differential pressure between the hearth and secondary air.
4. The method of claim 2, wherein the operational indicators comprise: the method comprises the following steps of main steam temperature, water wall temperature, superheater wall temperature, reheater wall temperature, steam turbine shaft vibration, steam turbine axial displacement, coal mill outlet temperature, air preheater pressure difference, SCR inlet smoke temperature, draught fan current, primary fan current and coal mill current.
5. The method of claim 2, wherein the environmental metrics comprise: ammonia slip concentration, NOx emission concentration, dust emission concentration, SO2 emission concentration.
6. The method of claim 1, wherein the observation in step S3 is taken 100% -10% of the unit load.
7. The method of claim 1, wherein the original data matrix in step S3 is represented as:
Figure FDA0002817859670000021
wherein XijWhen the load of the unit is measured to be 100% -10% by observation, the 1 st-m variable value under the peak regulation index is shown, wherein i is 1-10, and j is 1-m.
8. The method of claim 7, wherein the original data matrix is transformed from a positive index to an inverse index, i.e., the transformed data matrix is a matrix of data with a positive index and a negative index
Figure FDA0002817859670000022
Get Y ═ Yij)n×mWhen the load variable is 10%, m is 10.
9. The method of claim 8, wherein the normalized matrix in step S5 is expressed as:
Figure FDA0002817859670000023
wherein the content of the first and second substances,
Figure FDA0002817859670000031
in the formula
Figure FDA0002817859670000032
10. The method as claimed in claim 9, wherein the sample correlation coefficient in step S6 is expressed as:
Figure FDA0002817859670000033
wherein the content of the first and second substances,
Figure FDA0002817859670000034
11. the method of claim 10, wherein step S7 includes:
solving a characteristic equation
|V-λE|＝0
M characteristic values, lambda, can be obtained1，λ2，λ3…λmAnd are arranged from large to small.
12. The method according to claim 10, wherein the step S8 of calculating the information contribution rate corresponding to the eigenvalue includes:
calculating the eigenvalue lambdaj(j ═ 1, 2, …, m) of information contribution rate ajThe calculation formula is as follows:
Figure FDA0002817859670000035
13. the method of claim 12, wherein the threshold value is 0.9.
14. The utility model provides a key index recognition device of thermal power unit peak regulation based on multiple PCA which characterized in that includes:
an input module: the method is used for establishing a peak regulation index set suitable for the thermal power generating unit;
the classification module is connected with the input module and is used for classifying the peak regulation indexes;
the matrix forming module is connected with the peak regulation index classifying module, lists a variable and observed quantity table under the peak regulation index and obtains an original data matrix;
the matrix conversion module is connected with the matrix forming module, analyzes each index, determines a positive index and a negative index, and performs matrix conversion;
the standardized matrix conversion module is connected with the matrix conversion module and is used for carrying out standardized transformation on the matrix to obtain a standardized matrix;
the coefficient solving module is connected with the standardized matrix conversion module and is used for solving a sample correlation coefficient aiming at the standardized matrix;
the characteristic value calculation module is connected with the coefficient solving module and is used for solving a characteristic equation of the correlation coefficient matrix to obtain a characteristic value;
the sorting module is connected with the characteristic value calculating module, calculates the information contribution rate corresponding to the characteristic value and accumulates the information contribution rate from large to small one by one;
the judging module is connected with the sorting module and is used for judging whether the accumulated sum of the information contribution rates is larger than a threshold value or not, and if so, the corresponding main component is taken as a peak regulation key factor;
and the output module is connected with the judging module and outputs the key peak regulation indexes corresponding to the peak regulation indexes.
15. The apparatus of claim 13, wherein the classification module classifies the peak shaver index into a stable combustion index, an operational index, and an environmental index.
16. The apparatus of claim 14, wherein the stable combustion indicator comprises: negative pressure of the hearth, fire detection signals, excess air coefficients, flue gas temperature at the outlet of the hearth, and differential pressure between the hearth and secondary air.
17. The apparatus of claim 14, wherein the operational indicators comprise: the method comprises the following steps of main steam temperature, water wall temperature, superheater wall temperature, reheater wall temperature, steam turbine shaft vibration, steam turbine axial displacement, coal mill outlet temperature, air preheater pressure difference, SCR inlet smoke temperature, draught fan current, primary fan current and coal mill current.
18. The apparatus of claim 14, wherein the environmental metrics comprise: ammonia slip concentration, NOx emission concentration, dust emission concentration, SO2 emission concentration.
19. The apparatus of claim 13, wherein the observations in the matrix formation module take 100% -10% of the unit load.
20. The apparatus of claim 13, wherein the raw data matrix in the matrix formation module is represented as:
Figure FDA0002817859670000051
wherein XijWhen the load of the unit is measured to be 100% -10% by observation, the 1 st-m variable value under the peak regulation index is shown, wherein i is 1-10, and j is 1-m.
21. The apparatus of claim 19, wherein the original data matrix is transformed according to a positive index and an inverse index, i.e., the transformed original data matrix is obtained
Figure FDA0002817859670000052
Get Y ═ Yij)n×mWhen the load variable is 10%, m is 10.
22. The apparatus of claim 20, wherein the normalization matrix is represented as:
Figure FDA0002817859670000053
wherein the content of the first and second substances,
Figure FDA0002817859670000061
in the formula
Figure FDA0002817859670000062
23. The apparatus of claim 21, wherein the sample correlation coefficient is expressed as:
Figure FDA0002817859670000063
wherein the content of the first and second substances,
Figure FDA0002817859670000064
24. the apparatus of claim 22, wherein the eigenvalue calculation module solves an equation of the characteristic
|V-λE|＝0
M characteristic values, lambda, can be obtained1，λ2，λ3…λmAnd are arranged from large to small.
25. The apparatus of claim 23, wherein the calculating the information contribution rate for the eigenvalue comprises:
calculating the eigenvalue lambdaj(j ═ 1, 2, …, m) of information contribution rate ajThe calculation formula is as follows:
Figure FDA0002817859670000065
26. the apparatus of claim 25, wherein the threshold value takes 0.9.
CN202011403590.4A 2020-12-04 2020-12-04 Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs Pending CN112329271A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011403590.4A CN112329271A (en) 2020-12-04 2020-12-04 Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011403590.4A CN112329271A (en) 2020-12-04 2020-12-04 Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs

Publications (1)

Publication Number Publication Date
CN112329271A true CN112329271A (en) 2021-02-05

Family

ID=74302138

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011403590.4A Pending CN112329271A (en) 2020-12-04 2020-12-04 Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs

Country Status (1)

Country Link
CN (1) CN112329271A (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080021750A1 (en) * 2004-07-05 2008-01-24 Hiroaki Masuyama Enterprise Evaluation Device, Enterprise Evaluation Program and Enterprise Evaluation Method
CN102331772A (en) * 2011-03-30 2012-01-25 浙江省电力试验研究院 Method for carrying out early warning of abnormal superheated steam temperature and fault diagnosis on direct current megawatt unit
CN103606115A (en) * 2013-12-05 2014-02-26 国家电网公司 Evaluation method of energy-saving type power grid
CN106446571A (en) * 2016-10-08 2017-02-22 华北电力科学研究院有限责任公司 Error evaluation method of wind power forecasting
CN106447115A (en) * 2016-10-08 2017-02-22 华北电力科学研究院有限责任公司 Regional power grid wind power forecast evaluation method
CN107145973A (en) * 2017-04-21 2017-09-08 东北电力大学 Hydroenergy storage station capacity Method for optimized planning based on principal component analysis
CN108320109A (en) * 2018-02-28 2018-07-24 国信优易数据有限公司 A kind of key index determines method and apparatus
CN109002995A (en) * 2018-07-25 2018-12-14 国网甘肃省电力公司电力科学研究院 A kind of fired power generating unit peak modulation capacity evaluation method based on fuzzy overall evaluation
CN109146274A (en) * 2018-08-09 2019-01-04 中海石油气电集团有限责任公司 A kind of plant gas synthetical condition assessment method based on entropy weight
CN109861310A (en) * 2019-02-28 2019-06-07 上海电力学院 Supercritical thermal power unit primary frequency control system recognizes Variable Selection
CN110084504A (en) * 2019-04-22 2019-08-02 中国南方电网有限责任公司 The comprehensive wire examination method of power plant based on Principal Component Analysis

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080021750A1 (en) * 2004-07-05 2008-01-24 Hiroaki Masuyama Enterprise Evaluation Device, Enterprise Evaluation Program and Enterprise Evaluation Method
CN102331772A (en) * 2011-03-30 2012-01-25 浙江省电力试验研究院 Method for carrying out early warning of abnormal superheated steam temperature and fault diagnosis on direct current megawatt unit
CN103606115A (en) * 2013-12-05 2014-02-26 国家电网公司 Evaluation method of energy-saving type power grid
CN106446571A (en) * 2016-10-08 2017-02-22 华北电力科学研究院有限责任公司 Error evaluation method of wind power forecasting
CN106447115A (en) * 2016-10-08 2017-02-22 华北电力科学研究院有限责任公司 Regional power grid wind power forecast evaluation method
CN107145973A (en) * 2017-04-21 2017-09-08 东北电力大学 Hydroenergy storage station capacity Method for optimized planning based on principal component analysis
CN108320109A (en) * 2018-02-28 2018-07-24 国信优易数据有限公司 A kind of key index determines method and apparatus
CN109002995A (en) * 2018-07-25 2018-12-14 国网甘肃省电力公司电力科学研究院 A kind of fired power generating unit peak modulation capacity evaluation method based on fuzzy overall evaluation
CN109146274A (en) * 2018-08-09 2019-01-04 中海石油气电集团有限责任公司 A kind of plant gas synthetical condition assessment method based on entropy weight
CN109861310A (en) * 2019-02-28 2019-06-07 上海电力学院 Supercritical thermal power unit primary frequency control system recognizes Variable Selection
CN110084504A (en) * 2019-04-22 2019-08-02 中国南方电网有限责任公司 The comprehensive wire examination method of power plant based on Principal Component Analysis

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
万祥: ""基于大数据挖掘技术的火电机组运行优化研究"", 《中国博士学位论文全文数据库 工程科技II辑》 *
周创立: ""火电厂机组运行状态综合评价建模方法研究"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 *

Similar Documents

Publication Publication Date Title
CN108446529B (en) Organic Rankine cycle system fault detection method based on generalized mutual entropy-DPCA algorithm
CN109190950B (en) Energy consumption abnormity identification method for communicating electric meter and water meter files
CN103631681A (en) Method for online restoring abnormal data of wind power plant
CN113624334B (en) Unit vibration monitoring device and method based on Internet of things technology
CN109919516B (en) Peak regulation judgment method based on coal quality change unit
CN113757634B (en) Industrial boiler energy efficiency environment-friendly collaborative detection platform and method
CN112465412A (en) Power plant production information graphical method based on IMS system
CN107607342B (en) Healthy energy efficiency detection method for air conditioner room equipment group
CN108182553B (en) Coal-fired boiler combustion efficiency online measurement method
CN117353436B (en) Solar power supply system based on internet of things monitoring
CN112907074A (en) Energy efficiency sensitive index detection method and system for comprehensive energy system user
CN116805065B (en) Intelligent management method for monitoring data of coal powder heating furnace burner
CN112329271A (en) Thermal power generating unit peak regulation key index identification method and device based on multiple PCAs
CN111898794B (en) Abnormal monitoring method for thermal efficiency of large coal-fired boiler
CN117079442A (en) Chemical industry park hazardous chemical gas leakage diffusion monitoring system based on data analysis
Kaewprapha et al. Machine Learning Approaches for Estimating the Efficiency of Combined Cycle Power Plant
CN112131526A (en) On-line calculation method for fly ash concentration and fly ash flow of coal-fired boiler
CN112948768B (en) Energy conversion system energy efficiency detection method and system based on secondary energy equivalence
CN211479145U (en) Combustion condition image monitoring device based on flame image and deep learning
CN117148017B (en) High-voltage casing oil gas remote monitoring method and system
CN116703333B (en) Power plant technical supervision informatization management system
CN112016038B (en) Method for predicting outer wall temperature of high-temperature reheater of ultra-supercritical coal-fired boiler
CN113657778A (en) Coal blending and burning optimization method
CN111162566B (en) Method and system for determining joint output characteristic of wind-solar combined power generation system
Qingchuan et al. Development and application of peak shaving realtime supervision system of thermal power units

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