CN111027744A - Real-time benchmarking optimization method for multi-level power plant - Google Patents
Real-time benchmarking optimization method for multi-level power plant Download PDFInfo
- Publication number
- CN111027744A CN111027744A CN201911077532.4A CN201911077532A CN111027744A CN 111027744 A CN111027744 A CN 111027744A CN 201911077532 A CN201911077532 A CN 201911077532A CN 111027744 A CN111027744 A CN 111027744A
- Authority
- CN
- China
- Prior art keywords
- benchmarking
- optimization
- target
- marker post
- benchmarks
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 115
- 239000003550 marker Substances 0.000 claims abstract description 117
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000000556 factor analysis Methods 0.000 claims abstract description 15
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 230000015556 catabolic process Effects 0.000 claims abstract description 4
- 238000006731 degradation reaction Methods 0.000 claims abstract description 4
- 238000003745 diagnosis Methods 0.000 claims description 26
- 238000012550 audit Methods 0.000 claims description 23
- 238000012216 screening Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000006866 deterioration Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 239000004615 ingredient Substances 0.000 claims description 3
- 230000003068 static effect Effects 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 230000008685 targeting Effects 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 238000003339 best practice Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000004134 energy conservation Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004781 supercooling Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a real-time benchmarking optimization method for a multilevel power plant, and particularly relates to the field of benchmarking optimization algorithms, wherein the method comprises the following steps: establishing an index system template; establishing a benchmark library, and establishing a transverse benchmark library and a longitudinal benchmark library according to historical data and similar objects; obtaining a marker post; carrying out optimization guidance on the standard finding deviation, finding out relevant factors through mechanism analysis, locking main deviation factors through main factor analysis, displaying adjustable parameters through enhanced analysis, and providing degradation reminding; the benchmarking result is analyzed, the benchmarking optimization knowledge base is perfected, and the benchmarking is more accurate and effective; and (4) feedback and optimization, namely checking whether the optimization guidance is effective or not, further optimizing a benchmark, and enriching the knowledge and factor analysis of the optimization guidance. The embodiment of the invention can solve the problems that the existing power plant benchmarking method adopts static benchmarking and has no transverse comparison and optimization guidance, and can realize real-time benchmarking, combination of benchmarking and optimization, combination of mathematics and mechanism, and combination of transverse benchmarking and longitudinal benchmarking.
Description
Technical Field
The embodiment of the invention relates to the field of benchmarking optimization algorithms, in particular to a real-time benchmarking optimization method for a multi-level power plant.
Background
The ideas of operation optimization and energy conservation are long-standing, and the realization methods are various, including optimization according to design values, optimization according to performance test values and optimization according to theoretical calculation values. Essentially, the idea of "optimization" is provided. I.e., setting one or more optimal desired goals, and adjusting the operating parameters in the direction of the goal in an attempt to achieve the predetermined goal. The results of optimization using the above methods have been less than ideal for many years and most often not achieved at all. The main reason is that the target setting is idealized, and the field conditions are complicated and different from the conditions under which the design values and the test values are generated.
In addition, even if two identical units have different installation, equipment conditions and even regional environments, the actual operating conditions have great differences and are optimized according to the same target, and the results are necessarily different.
The traditional benchmarking is static, the benchmarking value is manually specified, only the difference is found out, and no optimization guidance exists. Although the traditional operation optimization is dynamic calculation, the traditional operation optimization is usually only mechanistic calculation and has no transverse comparison.
Disclosure of Invention
The embodiment of the invention aims to provide a multi-level power plant real-time benchmarking optimization method, which is used for solving the problems that the existing power plant benchmarking method adopts static benchmarking, and has no transverse comparison and realizable optimization guidance.
In order to achieve the above object, the embodiments of the present invention mainly provide the following technical solutions:
a multi-stage power plant real-time benchmarking optimization method is provided, and comprises the following steps: step 1: establishing an index system template, and establishing a corresponding level index system template according to indexes concerned by each level; step 2: establishing a benchmark library, performing transverse and longitudinal optimization according to historical data and similar objects, and establishing a transverse and longitudinal benchmark library; and step 3: the method comprises the steps that a marker post is obtained, the marker post has a self-learning function, a system marker post library continuously learns and updates the marker post in real time in the running of a unit, and the marker post is guaranteed to be optimal in real time; and 4, step 4: finding a deviation of the benchmarks, selecting a benchmarking method, carrying out benchmarking, carrying out optimization guidance according to the deviation, finding out relevant factors through mechanism analysis, locking main deviation factors through main factor analysis, displaying adjustable parameters through enhanced analysis, and providing a degradation prompt; and 5: analyzing the benchmarking result, and analyzing the energy-saving measures, the main factor component table, the adding reasons and the measures by classification by an analyst respectively to perfect a benchmarking optimization knowledge base so that benchmarks are more accurate and effective; step 6: and (4) feedback and optimization, wherein after the operator adjusts, the result is fed back, whether optimization guidance is effective or not is checked, and the benchmarking is further optimized, and knowledge and factor analysis of the optimization guidance are enriched.
Further, the method for obtaining the marker post in step 3 specifically includes: a template generation method, the template generation method comprising: presetting the range and the target of a benchmark as filtering conditions, screening historical data according to the filtering conditions to obtain data meeting the filtering conditions as the benchmark, and storing the data in a benchmark library, wherein the specific implementation steps comprise: determining the name of the target marker post, including the name or the self-defined name of the target marker post, so that the target marker post can be conveniently stored in a marker post library for later reference and citation; determining a range, including determining the range around the target and recording the dimension, the boundary and the attribute of the range, and simultaneously recording the dimension, the boundary and the attribute of the target; determining a target name, including an index or an event, within the selected range; carrying out sorting and screening on the benchmarks, obtaining a plurality of time periods or moments meeting the conditions through the range and the target, and screening and sorting excellent working conditions according to the set conditions; and determining factors, and determining the factors influencing the target through correlation analysis.
Further, the determining the range specifically includes: determining the dimension: selecting indexes, basic information, events and time data under a tree structure tree or in a database; determining a dimension boundary: searching the time, the recording condition, the value or the time period of the value meeting the condition requirement in the database by utilizing event detection; determining the attribute: and after the boundary event detection of each dimension is finished, determining the relationship of the boundary events.
Further, the method for obtaining the marker post in step 3 further includes: presetting and comparing methods, wherein the presetting method comprises the following steps: directly taking the existing optimal index as a marker post, or taking the working condition of good operation per se as the marker post; the method for finding the benchmarks by the contrast method comprises the following steps: calling the benchmark library, and traversing and inquiring all benchmarks meeting the conditions in the benchmark library according to the benchmark names; calculating the similarity between the range of the marker post meeting the conditions and the range of the benchmarking object, and screening the marker post with the similarity meeting a set value with the range of the benchmarking object as a matched marker post; if no matched marker post exists, acquiring the marker post by using a template generation method; if the matched marker posts exist to form a marker post group, respectively calculating the similarity between each marker post in the marker post group and the target object, screening out the marker post with the maximum similarity, and judging whether the similarity of the marker post with the maximum similarity meets the requirement of a set value or not; if the similarity is not satisfied, the matched marker post with the maximum similarity is used as the marker post, and if the similarity is not satisfied, the marker post is obtained by using a template generation method.
Further, the method for calculating the similarity between the target post and the target object comprises the following steps: extracting factors from the benchmarks as the factors of the benchmarks; acquiring the current factor value of the benchmarking object factor from a real-time database through a template; and calculating the similarity between the target object factor and the target rod factor through the Euclidean distance.
Further, the method for finding the deviation of the standard in step 4 specifically includes: selecting different benchmarking methods according to the requirements of users; and (4) carrying out mechanism analysis: extracting the same associated factors as the benchmarks in the benchmarking object; performing principal factor analysis: acquiring data corresponding to stable working conditions of the target object factors in a current period of time from a real-time database, calculating difference values of each factor of the target object and the benchmark factor, acquiring overrun factors according to the difference values, calculating influence degrees of the overrun factors on the target, sequencing the influence degrees, generating a criterion and factor component table, and taking the influence degrees which are sequenced in the front as main factors influencing the target of the target object; performing reinforced analysis, displaying adjustable parameters, optimizing and guiding, analyzing the deterioration condition caused by uncontrollable factors, and providing a deterioration prompt; the main cause triggers a benchmarking optimization knowledge base to obtain energy-saving measures and generate a benchmarking diagnosis list, wherein the benchmarking diagnosis list comprises the following contents: criteria, a factor component table, main factors influencing the target object and specific energy-saving measures.
Further, the benchmarking method comprises the following steps: presetting a target bar for target alignment, not presetting a target bar for target alignment, immediately aligning, aligning in real time, aligning transversely, aligning longitudinally and combining a plurality of target alignment methods for target alignment; the combined benchmarking of the multiple benchmarking methods comprises the following steps: presetting a post for transverse real-time mark alignment, presetting a post for longitudinal real-time mark alignment, presetting a post for transverse real-time mark alignment, and presetting a post for longitudinal real-time mark alignment; the benchmarking optimization system comprises a plurality of levels including five levels of groups, regional companies, power plants, units and equipment, and the benchmarking method of different levels and combinations forms full benchmarking.
Further, the step 5 of analyzing the targeting result specifically includes: analyzing energy-saving measures: manually judging whether the energy-saving measures in the benchmarking diagnosis list are feasible, if so, adjusting equipment operation parameters according to the energy-saving measures, and storing the energy-saving measures in a benchmarking optimization knowledge base; if not, the energy-saving measures are manually added or modified and audited by auditors, if the audits are passed, the modified energy-saving measures are stored in the benchmarking optimization knowledge base, and if the audits are not passed, the energy-saving measures are continuously modified until the audits are passed; analytical factor ingredient table: manually judging whether the main factors in the factor component table are reasonable or not, if so, storing the main factors and the criteria thereof in a benchmarking optimization knowledge base, if not, selecting new main factors and auditing by an auditor, and if the auditing is passed, optimizing a target influence degree sorting algorithm of the deviation factors; if the audit is not passed, new main factors are selected again until the audit is passed; if the energy-saving measures and the factor analysis table are unreasonable, reasons or measures are manually added and are audited by auditors, after the audits are passed, the operating parameters of the equipment are adjusted according to various indexes of the benchmarks, the system automatically traces the adjusting process, the working conditions of the benchmarks after the adjustment and before the adjustment are compared, if the working conditions of the benchmarks after the adjustment are superior to the working conditions of the benchmarks before the adjustment, the benchmarks are effective, the benchmarks are stored in a benchmarking library, and the sequencing of the benchmarks is improved; and if the working condition of the target is poor after adjustment, the target rod is invalid, the working conditions before and after adjustment are locked, and the reason is analyzed.
Further, the method for performing feedback optimization on the benchmarks according to the change condition of each index after adjustment of the suggestions given by the result analysis sheet in the step 6 comprises the following steps: adjusting the operation parameters of the benchmarking object according to the optimization suggestions in the result analysis sheet, if the data of each index after adjustment is better than that before adjustment, the optimization suggestions are correct, then improving the priority of the benchmarking, and then perfecting a benchmarking optimization knowledge base according to the benchmarking diagnosis sheet and the result analysis sheet; if the data of each index after adjustment is worse than that before adjustment, the operation optimization suggestion is incorrect, related personnel analyze reasons, the sequence of benchmarks is reduced, records in the benchmark optimization knowledge base are modified according to the benchmark diagnosis list and the result analysis list, and meanwhile, the optimization algorithm is adjusted and the algorithm model base is updated.
The technical scheme provided by the embodiment of the invention at least has the following advantages:
(1) the real-time benchmarking optimization method for the multilevel power plant provided by the embodiment of the invention combines the benchmarking idea, expands the online history optimizing range, carries out benchmarking in multiple directions from the angle between the real-time benchmarking method and each level, is beneficial to finely analyzing the reason for the gap and proposing specific operation optimization measures, and improves the operation level;
(2) the embodiment of the invention adopts a mode of combining transverse direction and longitudinal direction, obtains the best practice of working conditions similar to the target through transverse direction and similar unit, system and equipment target alignment and longitudinal direction and own historical target alignment, not only can realize the online optimization of the changing working conditions, but also furthest excavates the energy-saving potential;
(3) the embodiment of the invention adopts a mode of combining mathematical calculation and mechanism analysis, finds out a gap by benchmarking, combines a benchmarking optimization knowledge base to obtain an energy-saving suggestion, adjusts and operates according to the suggestion, traces whether the operation condition of a benchmarking object is optimal after adjustment and optimizes a benchmarking base before adjustment, the whole process is closed-loop, and the benchmarking process is a self-learning and continuous optimization process;
(4) the benchmarking layer of the embodiment of the invention is a group layer, a regional company layer and a power plant layer, realizes the best operation practice sharing of various units or equipment, provides reference for continuously improving the operation level and provides scientific basis for decision making;
(5) the benchmarking of the embodiment of the invention is a dynamic process, the benchmarking is updated in real time, and the benchmarking result tends to be 'better';
(6) the embodiment of the invention combines the benchmarking with the optimization, fully utilizes the advantages of the benchmarking and the optimization, helps to analyze the optimization direction of the benchmarking result while benchmarking, enables the benchmarking to be more accurate by the optimization result, and perfects a benchmarking optimization knowledge base and an algorithm.
Drawings
Fig. 1 is a general flowchart of a multi-stage power plant real-time benchmarking optimization method according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for obtaining a post according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for generating a benchmarking diagnostic sheet according to an embodiment of the present invention.
Fig. 4 is a flowchart of an auditing and analyzing method for a benchmarking diagnostic sheet according to an embodiment of the present invention.
Fig. 5 is a general flow chart of feedback and optimization according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided for illustrative purposes, and other advantages and effects of the present invention will become apparent to those skilled in the art from the present disclosure.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
Before describing the embodiments of the present invention, an application scenario of the present invention is first introduced:
the ideas of operation optimization and energy conservation are long-standing, and the realization methods are various, including optimization according to design values, optimization according to performance test values and optimization according to theoretical calculation values. Essentially, the idea of "optimization" is provided. I.e., setting one or more optimal desired goals, and adjusting the operating parameters in the direction of the goal in an attempt to achieve the predetermined goal. The results of optimization using the above methods have been less than ideal for many years and most often not achieved at all. The main reason is that the target setting is idealized, and the field conditions are complicated and different from the conditions under which the design values and the test values are generated. Even if two identical units have different installation, equipment conditions and even regional environments, the actual operation conditions have great differences and are optimized according to the same target, and the results are necessarily different.
Combining the benchmarking and the optimization, using a brand new 'more optimal' benchmarking idea based on practice, continuously searching the best practice, repeating the best practice to obtain the more optimal practice by using a data mining method through a real-time self-learning function, circularly increasing and continuously optimizing.
The benchmarking method can be divided into preset benchmarking, non-preset benchmarking, instant benchmarking, real-time benchmarking, transverse benchmarking and longitudinal benchmarking. Presetting a target pole for target alignment, namely, a target pole corresponding to a target object exists in a target pole library before target alignment, searching a target pole meeting conditions according to the range and the target of the target object when the target alignment is performed, and then starting operations such as target alignment, analysis and the like; if the marker post is not preset for marker post alignment, no marker post meeting the conditions is arranged in a marker post library before the marker post is aligned or a new marker post is established for the marker post, and aiming at the condition, a new marker post needs to be established before the marker post is aligned, stored in the marker post library and then aligned by the marker post; carrying out instant benchmarking, and searching for a marker post in real time to carry out benchmarking; real-time benchmarking is to select a benchmarking bar from a benchmarking bar library or to establish a new benchmarking bar, real-time benchmarking is carried out within a certain time, and benchmarking results are recorded and prompted; the horizontal benchmarking is the benchmarking between the units and the equipment in the same category; and the longitudinal benchmarking is to find the historical optimal operation condition of the unit or equipment and then benchmarking with the historical optimal operation condition. The above-mentioned benchmarking methods can also be combined to operate, such as: presetting a horizontal real-time benchmarking of a marker post, presetting a vertical real-time benchmarking of the marker post, presetting a horizontal historical benchmarking of the marker post, and presetting a vertical instant benchmarking of the marker post.
The target structure level is divided into a power generation group layer, a regional company layer, a power plant layer, a unit layer and an equipment layer from top to bottom in sequence according to the characteristics of an organization system, a business process and a power generation industry of a power generation group and by combining the functional requirements of the system.
The benchmarking method or the combination of a plurality of benchmarking methods can realize benchmarking among units of the same type and equipment of the same type at different levels, further excavate and optimize potential, promote safe and economic operation of the units of the power generation enterprises, continuously improve the management level of production and operation, and finally realize economic benefit.
Therefore, an embodiment of the present invention provides a real-time benchmarking optimization method for a multi-tier power plant, which takes a pump as a benchmarking object with reference to fig. 1, and the method includes the following specific implementation steps:
step 1: in the index system template, the circulating pump is an index template of an equipment layer, the template of the circulating pump is instantiated, a circulating pump object is obtained, relevant indexes of the circulating pump are determined, the indexes mainly comprise power consumption rate, load, environment temperature, outlet pressure, outlet flow, current, power and efficiency, the indexes are correlated with points corresponding to the indexes in a field database, and the index values can be read in real time.
Step 2: and establishing a transverse and longitudinal marker post library by the historical data of the circulating pump and circulating pumps of the same type. The transverse marker post library is a marker post library formed by marker post data among the same type of units and equipment; the method is characterized in that a longitudinal marker post library is a marker post library formed by historical optimal operating conditions of a unit or equipment, and marker posts in the marker post library are formed by boundary conditions, target optimal values and influence factors.
And step 3: the method comprises the steps of acquiring a marker post, wherein the marker post has a self-learning function, a system marker post library continuously learns and updates the marker post in real time during operation of a unit, the marker post is used for guaranteeing real-time optimization of the marker post, and the method comprises the steps of creating a marker aligning template, setting a marker aligning object and acquiring the marker post according to the marker aligning object;
specifically, the creating principle of the benchmarking template can be created according to three element principles of a range, a target and factors, the template is created, the benchmarking object is created by the template, taking the circulation pump benchmarking of a 300MW unit of a certain plant as an example, the example of the benchmarking template refers to table 1, the screening conditions of the created template are listed in table 1, the range includes the level where the benchmarking object is located, the fluctuation range of load values, benchmarking equipment and the like, the benchmarking object target is the power consumption rate, and the target related factors are the factors such as outlet pressure, outlet flow, current, power and efficiency.
Table 1:
referring to fig. 2, the method for obtaining the benchmarks includes a template generation method, a preliminary method and a comparison method, wherein the template generation method includes: the range and the target of the benchmark are preset in the benchmarking template as filtering conditions, the filtering conditions can also be formed by one or more of parameters, indexes or events, historical data are screened according to the filtering conditions, data which accord with the filtering conditions are obtained and used as the benchmark, and the data are stored in the benchmark library.
The concrete implementation steps comprise: determining the name of the target marker post, including the name or the self-defined name of the target marker post, so that the target marker post can be conveniently stored in a marker post library for later reference and citation; determining a range, including determining the range around the target and recording the dimension, the boundary and the attribute of the range, and simultaneously recording the dimension, the boundary and the attribute of the target; determining a target name, including an index or an event, within the selected range; carrying out sorting and screening on the benchmarks, obtaining a plurality of time periods or moments meeting the conditions through the range and the target, and screening and sorting excellent working conditions according to the set conditions; determining the factors, and determining the factors through correlation analysis.
Wherein, determining the range specifically comprises: determining dimensions, determining boundaries, and determining attributes.
Determining the dimension: selecting indexes, basic information, events and time data under a tree structure tree or in a database;
determining a boundary: searching the time, the recording condition, the value or the time period of the value meeting the condition requirement in the database by utilizing event detection;
determining the attribute: and after the boundary event detection of each dimension is finished, determining the relationship of the boundary events.
The presetting method comprises the following steps: the existing optimal index is directly used as a marker post, or the working condition of good operation of the marker post is used as the marker post, namely the marker post is manually set.
The comparison method comprises the following steps: calling a benchmark library, traversing and inquiring all benchmarks meeting the conditions in the benchmark library according to the names of the benchmarks, calculating the similarity between the scope of the benchmarks meeting the conditions and the scope of the benchmarks, and screening the benchmarks of which the similarity with the scope of the benchmarks meets a set value as matching benchmarks. The range and the target of the targeting object are elements such as the range, the target, and the factor in the targeting template. And if no matched marker post exists, obtaining the marker post by using a template generation method, namely selecting the working condition meeting the conditions in the historical data according to the screening conditions in the calibration template. And if the matched benchmarks exist, generating a benchmark group, respectively calculating the similarity between each matched benchmark in the benchmark group and the target object, screening out the matched benchmarks with the maximum similarity, judging whether the similarity of the matched benchmarks with the maximum similarity meets the requirement, if so, taking the matched benchmarks with the maximum similarity as the benchmarks, and if not, acquiring the benchmarks by using a template generation method. The method can obtain a better marker post.
The similarity calculation method of the benchmarks and the benchmarking objects comprises the following steps: extracting factors from the benchmarks as the factors of the benchmarks; acquiring the current factor value of the benchmarking object factor from a real-time database through a template; and calculating the similarity between the target object factor and the target rod factor through the Euclidean distance.
It should be noted that, when the template method is used to create the target object template, field historical or real-time data is used, data needs to be collected and preprocessed, and when the data is preprocessed, the measured point data needs to be screened by using the 3sigma principle, abnormal values are eliminated, and then the measured data of each measured point is normalized according to respective extreme values, so that the actual measured value is mapped to the [ 01 ] interval.
And 4, step 4: finding the deviation of the benchmarks, selecting a benchmarking method, carrying out benchmarking, carrying out optimization guidance according to the deviation, finding out relevant factors through mechanism analysis, locking main deviation factors through main factor analysis, displaying adjustable parameters through enhanced analysis, and providing a degradation prompt;
selecting different benchmarking methods according to the requirements of users;
and (4) carrying out mechanism analysis: extracting the same associated factors as the benchmarks in the benchmarking object;
performing principal factor analysis: acquiring data corresponding to stable working conditions of the target object factors in a current period of time from a real-time database, calculating difference values of each factor of the target object and the benchmark factor, acquiring overrun factors according to the difference values, calculating influence degrees of the overrun factors on the target object, sequencing the influence degrees, generating a criterion and factor component table, and taking the influence degrees which are sequenced in the front as main factors influencing the target object;
performing reinforced analysis, displaying adjustable parameters, optimizing and guiding, analyzing the deterioration condition caused by uncontrollable factors, and providing a deterioration prompt;
the main cause triggers a benchmarking optimization knowledge base to obtain energy-saving measures and generate a benchmarking diagnosis list, wherein the benchmarking diagnosis list comprises the following contents: criteria, a factor component table, main factors influencing the target object and specific energy-saving measures.
In practical application, it can be understood that: creating a benchmarking object template, setting a benchmarking object, selecting a benchmarking method, and acquiring benchmarks according to the benchmarking object and a benchmarking library of a hierarchy where users are located;
before the benchmarking, a proper marker post needs to be selected firstly, the marker post is compared with the benchmarking object, the marker post which is most similar to the benchmarking object is selected for benchmarking, and the comparability is ensured to be strongest. The marker post is a working condition, the similarity of the marker post and a target object is ensured, the working condition is mainly grasped from main factors influencing the working condition, then the similarity of the main factors is compared to ensure the similarity of the working condition, the similarity of the target object and the target object is respectively calculated, and the target object are sorted according to the similarity.
Specifically, referring to fig. 3, extracting the same factors as the benchmarks in the benchmarks object, calculating the difference between each factor of the benchmarks object and the factor of the benchmarks, obtaining the overrun factor according to the size of the difference, the overrun factor being the factor that the difference between the benchmarks object and the benchmarks exceeds the preset limit, calculating the influence degree of the overrun factor on the targets of the benchmarks object, sorting the influence degrees, and generating a criterion and a factor component table by using the influence degrees sorted in the front as the main factors influencing the benchmarks object; the main cause triggers the benchmarking optimization knowledge base to obtain energy-saving measures or suggestions, and finally generates a benchmarking diagnosis list, wherein the benchmarking diagnosis list comprises the following contents: the data related to the benchmarking process, such as criteria, a factor component table, main factors influencing the benchmarking target, specific energy-saving measures and the like.
The method for calculating the influence degree of the deviation factors comprises the following steps:
and calculating a Pearson correlation coefficient of the overrun factor x to the target y, and calculating the correlation coefficient according to a Pearson correlation coefficient calculation formula if n sample values exist, wherein the Pearson correlation coefficient calculation formula is as follows:
the method is divided into three stages: low degree of correlation: r < 0.4; significant correlation is shown: 0.4< ═ r | < 0.7; highly correlated: 0.7< ═ r |; and (4) quantifying the influence degree of the overrun factors on the target by utilizing the magnitude r of the correlation coefficient, and obtaining the main factor.
And 5: and (4) analyzing the benchmarking result, wherein an analyst analyzes the energy-saving measures, the main factor component table, the addition reasons and the measures in a classification way respectively, and perfects a benchmarking optimization knowledge base to enable benchmarking to be more accurate and effective.
The specific method comprises the following steps:
analyzing energy-saving measures: manually judging whether the energy-saving measures in the benchmarking diagnosis list are feasible, if so, adjusting equipment operation parameters according to the energy-saving measures, and storing the energy-saving measures in a benchmarking optimization knowledge base; if not, the energy-saving measures are manually added or modified and audited by auditors, if the audits are passed, the modified energy-saving measures are stored in the benchmarking optimization knowledge base, and if the audits are not passed, the energy-saving measures are continuously modified until the audits are passed;
analytical factor ingredient table: manually judging whether the main factors in the factor component table are reasonable or not, if so, storing the main factors and the criteria thereof in a benchmarking optimization knowledge base, if not, selecting new main factors and auditing by an auditor, and if the auditing is passed, optimizing an importance ranking algorithm; if the audit is not passed, new main factors are selected again until the audit is passed;
if the energy-saving measures and the factor analysis table are unreasonable, reasons or measures are manually added and are audited by auditors, after the audits are passed, the operating parameters of the equipment are adjusted according to various indexes of the benchmarks, the system automatically traces the adjusting process, the working conditions of the benchmarks after the adjustment and before the adjustment are compared, if the working conditions of the benchmarks after the adjustment are superior to the working conditions of the benchmarks before the adjustment, the benchmarks are effective, the benchmarks are stored in a benchmarking library, and the sequencing of the benchmarks is improved; and if the working condition of the target is poor after adjustment, the target rod is invalid, the working conditions before and after adjustment are locked, and the reason is analyzed.
The benchmarking optimization knowledge base is similar to an expert knowledge base, and is an interconnected knowledge piece set which is stored, organized, managed and used in a computer memory in a knowledge representation mode according to the requirement of solving problems in the field of power plants. These knowledge pieces include theoretical knowledge, factual data, heuristic knowledge derived from expert experience, definitions, theorems and algorithms, and general knowledge, etc., which are relevant to the field of power generation industry.
In actual operation, the result is fed back after the adjustment is carried out by an operator, so that the accumulation and precipitation of optimized knowledge and experience are realized.
Referring to fig. 4, since different workers have different requirements on the equipment, the content in the benchmarking diagnosis list needs to be audited and analyzed in a classified manner, and generally, the main application population of benchmarking optimization is operators, specialists and other related personnel. The method comprises the following steps that an operator pays attention to energy-saving measures corresponding to benchmarks under real-time working conditions, so that the operator manually judges whether the energy-saving measures in a benchmark diagnosis list are feasible, if yes, the operator adjusts equipment operation parameters according to the energy-saving measures in the benchmark diagnosis list and stores the energy-saving measures in a benchmark optimization knowledge base; and if the verification is not passed, the energy-saving measures are continuously modified until the verification is passed, and finally the energy-saving measures which pass the verification are stored in the benchmarking optimization knowledge base.
The method comprises the following steps that a professional worker and other personnel pay attention to certain statistics and certain general trends, so the statistics can be used for carrying out alignment when aligning standard, the professional worker and other personnel analyze the statistics of a factor component table and an alignment target and factors, whether main factors in the factor component table are reasonable or not is judged manually, if the main factors are reasonable, the main factors and criteria thereof are stored in an alignment optimization knowledge base, if the main factors are unreasonable, new main factors are selected and audited by auditors, and if the audits are passed, an importance ranking algorithm is optimized; and if the audit is not passed, reselecting the new main factors until the audit is passed, and optimizing the importance ranking algorithm according to the main factors passed by the audit.
It should be noted that: if the energy-saving measures and the factor analysis table are unreasonable in the manual auditing process, the reasons or measures are manually added by related personnel, the auditing personnel audits, after the auditing is passed, the operating parameters of the equipment are adjusted according to various indexes of the benchmarks, the system automatically traces the adjusting process, the working conditions of the benchmarks after the adjustment and the benchmarks before the adjustment are compared, if the working conditions of the benchmarks after the adjustment are superior to the working conditions of the benchmarks before the adjustment, the benchmarks are effective, the benchmarks are stored in a benchmarks library, and the sequencing of the benchmarks is improved; and if the working condition of the target is poor after adjustment, the target rod is invalid, the working conditions before and after adjustment are locked, and the reason is analyzed. The system refers to a benchmarking management system applying the method.
Step 6: and (4) feedback and optimization, wherein after the operator adjusts, the result is fed back, whether optimization guidance is effective or not is checked, and the benchmarking is further optimized, and knowledge and factor analysis of the optimization guidance are enriched.
The optimization method comprises the following steps: and adjusting the equipment according to the suggestions in the result analysis list, comparing various indexes before and after the equipment is adjusted, and optimizing the benchmarks according to the change conditions of the various indexes after the equipment is adjusted.
Since there is a step of adjusting the device parameters in the above steps, optimization feedback is required to verify whether the adjusted target object is better than the target object before adjustment and whether the selected target object is correct.
Specifically, the operation parameters of the equipment are adjusted according to the optimization suggestions in the result analysis list, if the data of each index after adjustment is better than that before adjustment, the optimization suggestions are correct, the priority of the benchmarks is improved, then the benchmarking optimization knowledge base is perfected according to the benchmarking diagnosis list and the result analysis list, and the knowledge state in the benchmarking optimization knowledge base is updated to be the completion state. The system obtains an optimization algorithm model with higher comprehensive evaluation score through the optimized indexes and the correlation data of the factors, deep learning again and algorithm training; specifically, the training method can be realized by a convolutional neural network or the like.
If the data of each index after adjustment is worse than that before adjustment, the operation optimization suggestion is incorrect, relevant personnel analyze the reasons, judge the reasons influencing the operation index, give a solution suggestion, reduce the sequence of corresponding benchmarks, modify the record in the benchmarking optimization knowledge base according to the benchmarking diagnosis list and the result analysis list, adjust the optimization algorithm and update the algorithm model base.
Referring to fig. 5, in a specific example, the method for optimizing the real-time benchmarking of the multi-stage power plant according to the present embodiment may include: a user selects a marker post from the marker post library, judges whether the marker post is suitable or not, if the marker post is not suitable, the marker post is regenerated, and if the marker post is suitable, the marker object and the selected marker post are subjected to marker alignment; the system generates a benchmarking diagnostic sheet; then, manually analyzing the diagnosis result in the benchmarking diagnosis list, if the diagnosis result is incorrect, performing supplementary modification until the examination is passed, if the diagnosis result is correct, adjusting the operation parameters of the equipment according to the result passed by the examination, detecting whether the adjusted operation data is superior to the operation data before the adjustment, if the data of each index after the adjustment is superior to the operation data before the adjustment, indicating that the optimization suggestion is correct, improving the priority of the user for selecting the benchmarking, and then perfecting a benchmarking optimization knowledge base according to the benchmarking diagnosis list and the result analysis list; if the data of each index after adjustment is worse than that before adjustment, the operation optimization suggestion is incorrect, relevant personnel analyze the reasons, judge the reasons influencing the operation index, give a solution suggestion, reduce the sequence of corresponding benchmarks, modify the record in the benchmarking optimization knowledge base according to the benchmarking diagnosis list and the result analysis list, adjust the optimization algorithm and update the algorithm model base.
The benchmarking result of the embodiment of the invention comprises a benchmarking result display table and a benchmarking result interpretation, wherein the benchmarking result display table of the group layer circulating pump is shown as table 2:
table 2:
the interpretation of the benchmarking results of the circulation pumps in the clique layers comprises the following steps:
marking a post: a power plant #1 circulating pump;
and (3) comprehensive ranking: the pump of the power plant #1 is more than the pump of the power plant # 1;
targeting object with large current: c, a difference value of a pump of a #1 power plant and a benchmark is 4A;
targeting object with lower outlet pressure: c, the difference between the pump of the #1 power plant and the standard pole is-0.01 MPa; targeting object with smaller outlet flow: c, the difference between the pump of the #1 power plant and the standard pole is-400 t/h; the calibration object with larger power: c, a difference value between a pump of a #1 power plant and a benchmark is 30 kw;
less efficient targeting objects: b, a difference value between a pump of a power plant #1 and a benchmark is-2.5%;
and (4) proposing: the pump technology of the C power plant #1 has a large potential for energy conservation and optimization, and focuses attention.
Another comparative result of the circulation pump in the group layer of the embodiment of the present invention is shown in table 3,
table 3:
the benchmarking results are interpreted as:
marking a post: e, circulating a pump by a power plant # 1;
and (3) comprehensive ranking: e, the #1 pump of the power plant, D, the #2 pump of the power plant, F, and the #3 pump of the power plant;
targeting object with large current: f, a power plant #3 is driven by a pump, and the difference value of the power plant #3 and the mark post is 7A;
targeting object with lower outlet pressure: d, a difference value between a power plant #2 circulating pump and a benchmark rod is-0.01 MPa; targeting object with smaller outlet flow: d, a difference value between a power plant #2 circulating pump and the benchmark is-100 t/h; the calibration object with larger power: f, a difference value between a power plant #3 circulating pump and a benchmark is 63 kw;
less efficient targeting objects: f, a power plant #3 is driven by a pump, and the difference value between the power plant #3 and the standard pole is-1.5%;
and (4) proposing: the pump technology of the F power plant #3 has a large potential for energy conservation and optimization, and focuses attention on the technology.
The table of the horizontal calibration result display of the condenser on the equipment layer in the embodiment of the invention is shown in table 4,
table 4:
| horizontal alignment mark of A power plant #1 condenser | Unit of | A power plant #1 machine condenser | C power plant #1 machine condenser | Difference from the marker post |
| End difference | ℃ | 3.8 | 1.2 | 2.6 |
| Degree of supercooling | ℃ | 0.45 | 0.2 | 0.25 |
| Inlet temperature of circulating water | ℃ | 17 | 14 | 3 |
| Outlet temperature of circulating water | ℃ | 29.7 | 28.8 | 0.9 |
| Inlet pressure of circulating water | MPa | 0.21 | 0.28 | -0.07 |
| Flow rate of condensate | t/h | 604 | 596 | 8 |
| Water level of condenser | mm | 803 | 725 | 72 |
| Condenser vacuum | kPa | 96 | 96.9 | -0.9 |
| Load of unit | MW | 300 | 295 | 5 |
| Temperature of condensate | ℃ | 33.5 | 30 | 3.5 |
Transversely reading the standard result at the equipment layer condenser as follows:
condenser performance indexes are all worse than the benchmarks, detailed information:
end difference: is 2.6 ℃ larger than the marker post;
supercooling degree: is 0.25 ℃ larger than the marker post;
the reason is as follows: the circulating water pressure is lower, and the water level of the condenser is higher;
energy-saving optimization measures: the flow of the circulating water is properly increased, and the water level of the condenser is reduced.
The table of the results of the longitudinal calibration of the condenser on the equipment level in the embodiment of the invention is shown in table 5,
table 5:
the vertical calibration result of the condenser on the equipment level is read as follows:
condenser performance indexes are all worse than the benchmarks, detailed information:
end difference: is 1.4 ℃ larger than the marker post;
supercooling degree: is 0.2 ℃ larger than the marker post;
the reason is as follows: the circulating water pressure is lower, and the water level of the condenser is higher;
energy-saving optimization measures: the flow of the circulating water is properly increased, and the water level of the condenser is reduced.
In addition, some definitions related to the examples of the present invention are shown in table 6.
Table 6:
the embodiment of the invention combines the benchmarking idea, expands the online historical optimization range, finds the historical optimal operation practice of the online historical optimization range, also finds the optimal operation practice of the same type of units, systems and equipment under the group, and carries out benchmarking from multiple directions and multiple levels, thereby being beneficial to analyzing reasons for gap finely and proposing specific operation optimization measures and improving the operation level; the target pole is selected according to the real running states of the unit, the system and the equipment, the best practice of working conditions similar to target objects is obtained, the online optimization of the changing working conditions can be realized, and the energy-saving potential is excavated to the maximum extent; the difference is found out through benchmarking, benchmarking results are analyzed, energy-saving suggestions are obtained, operation is adjusted according to the suggestions, whether the optimized benchmarks are superior to the benchmarks before adjustment or not is judged, if the adjusted benchmarks are superior to the benchmarks before adjustment, the operation optimization suggestions are correct, the benchmarking sequence is improved, and on the contrary, the benchmarking sequence is reduced or the benchmarks are reselected, so that closed-loop management is realized, and the management effect is greatly improved; continuously updating the benchmarking optimization knowledge base to enable benchmarking results to be more accurate; the benchmarking level is a group level, a regional company level, a power plant level, a unit level and an equipment level, best operation practice of various units or equipment is provided, information islands are eliminated, best operation information sharing is achieved, and reference is provided for constantly improving operation level of each plant. Those skilled in the art will appreciate that the functionality described in the present invention may be implemented in a combination of hardware and software in one or more of the examples described above. When software is applied, the corresponding functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present invention should be included in the scope of the present invention.
Claims (9)
1. A multi-stage power plant real-time benchmarking optimization method is characterized by comprising the following steps:
step 1: establishing an index system template, and establishing a corresponding level index system template according to indexes concerned by each level;
step 2: establishing a benchmark library, performing transverse and longitudinal optimization according to historical data and similar objects, and establishing a transverse and longitudinal benchmark library;
and step 3: the method comprises the steps that a marker post is obtained, the marker post has a self-learning function, a system marker post library continuously learns and updates the marker post in real time in the running of a unit, and the marker post is guaranteed to be optimal in real time;
and 4, step 4: finding a deviation of the benchmarks, selecting a benchmarking method, carrying out benchmarking, carrying out optimization guidance according to the deviation, finding out relevant factors through mechanism analysis, locking main deviation factors through main factor analysis, displaying adjustable parameters through enhanced analysis, and providing a degradation prompt;
and 5: analyzing the benchmarking result, and analyzing the energy-saving measures, the main factor component table, the adding reasons and the measures by classification by an analyst respectively to perfect a benchmarking optimization knowledge base so that benchmarks are more accurate and effective;
step 6: and (4) feedback and optimization, wherein after the operator adjusts, the result is fed back, whether optimization guidance is effective or not is checked, and the benchmarking is further optimized, and knowledge and factor analysis of the optimization guidance are enriched.
2. The method for optimizing the benchmarking in real time of the multi-tier power plant according to claim 1, wherein the method for obtaining the benchmarking in step 3 specifically comprises:
a template generation method, the template generation method comprising: presetting the range and the target of a benchmark as filtering conditions, screening historical data according to the filtering conditions to obtain data meeting the filtering conditions as the benchmark, and storing the data in a benchmark library, wherein the specific implementation steps comprise:
determining the name of the target marker post, including the name or the self-defined name of the target marker post, so that the target marker post can be conveniently stored in a marker post library for later reference and citation;
determining a range, including determining the range around the target and recording the dimension, the boundary and the attribute of the range, and simultaneously recording the dimension, the boundary and the attribute of the target;
determining a target name, including an index or an event, within the selected range;
carrying out sorting and screening on the benchmarks, obtaining a plurality of time periods or moments meeting the conditions through the range and the target, and screening and sorting excellent working conditions according to the set conditions;
and determining factors, and determining the factors influencing the target through correlation analysis.
3. The method according to claim 2, wherein the determining the range specifically comprises:
determining the dimension: selecting indexes, basic information, events and time data under a tree structure tree or in a database;
determining a dimension boundary: searching the time, the recording condition, the value or the time period of the value meeting the condition requirement in the database by utilizing event detection;
determining the attribute: and after the boundary event detection of each dimension is finished, determining the relationship of the boundary events.
4. The method for optimizing benchmarking in real time at a multi-stage power plant according to claim 2, wherein the method for obtaining benchmarking in step 3 further comprises: a pre-determined method and a comparison method are provided,
the presetting method comprises the following steps: directly taking the existing optimal index as a marker post, or taking the working condition of good operation per se as the marker post;
the method for finding the benchmarks by the contrast method comprises the following steps:
calling the benchmark library, and traversing and inquiring all benchmarks meeting the conditions in the benchmark library according to the benchmark names;
calculating the similarity between the range of the marker post meeting the conditions and the range of the benchmarking object, and screening the marker post with the similarity meeting a set value with the range of the benchmarking object as a matched marker post;
if no matched marker post exists, acquiring the marker post by using a template generation method;
if the matched marker posts exist to form a marker post group, respectively calculating the similarity between each marker post in the marker post group and the target object,
screening out a marker post with the maximum similarity, and judging whether the similarity of the marker post with the maximum similarity meets the requirement of a set value or not; if the similarity is not satisfied, the matched marker post with the maximum similarity is used as the marker post, and if the similarity is not satisfied, the marker post is obtained by using a template generation method.
5. The method for optimizing the real-time benchmarking of the multi-level power plant according to claim 4, wherein the method for calculating the similarity between the benchmarking and the benchmarking object comprises:
extracting factors from the benchmarks as the factors of the benchmarks;
acquiring the current factor value of the benchmarking object factor from a real-time database through a template;
and calculating the similarity between the target object factor and the target rod factor through the Euclidean distance.
6. The method for optimizing the benchmarking in real time of the multi-level power plant according to claim 1, wherein the method for finding the deviation of the benchmarking in step 4 includes:
selecting different benchmarking methods according to the requirements of users;
and (4) carrying out mechanism analysis: extracting the same associated factors as the benchmarks in the benchmarking object;
performing principal factor analysis: acquiring data corresponding to stable working conditions of the target object factors in a current period of time from a real-time database, calculating difference values of each factor of the target object and the benchmark factor, acquiring overrun factors according to the difference values, calculating influence degrees of the overrun factors on the target, sequencing the influence degrees, generating a criterion and factor component table, and taking the influence degrees which are sequenced in the front as main factors influencing the target of the target object;
performing reinforced analysis, displaying adjustable parameters, optimizing and guiding, analyzing the deterioration condition caused by uncontrollable factors, and providing a deterioration prompt;
the main cause triggers a benchmarking optimization knowledge base to obtain energy-saving measures and generate a benchmarking diagnosis list, wherein the benchmarking diagnosis list comprises the following contents: criteria, a factor component table, main factors influencing the target object and specific energy-saving measures.
7. The method of claim 6, wherein the benchmarking method comprises: presetting a target bar for target alignment, not presetting a target bar for target alignment, immediately aligning, aligning in real time, aligning transversely, aligning longitudinally and combining a plurality of target alignment methods for target alignment;
the combined benchmarking of the multiple benchmarking methods comprises the following steps: presetting a post for transverse real-time mark alignment, presetting a post for longitudinal real-time mark alignment, presetting a post for transverse real-time mark alignment, and presetting a post for longitudinal real-time mark alignment;
the benchmarking optimization system comprises a plurality of levels including five levels of groups, regional companies, power plants, units and equipment, and the benchmarking method of different levels and combinations forms full benchmarking.
8. The method according to claim 1, wherein the step 5 of analyzing the benchmarking result comprises:
analyzing energy-saving measures: manually judging whether the energy-saving measures in the benchmarking diagnosis list are feasible, if so, adjusting equipment operation parameters according to the energy-saving measures, and storing the energy-saving measures in a benchmarking optimization knowledge base; if not, the energy-saving measures are manually added or modified and audited by auditors, if the audits are passed, the modified energy-saving measures are stored in the benchmarking optimization knowledge base, and if the audits are not passed, the energy-saving measures are continuously modified until the audits are passed;
analytical factor ingredient table: manually judging whether the main factors in the factor component table are reasonable or not, if so, storing the main factors and the criteria thereof in a benchmarking optimization knowledge base, if not, selecting new main factors and auditing by an auditor, and if the auditing is passed, optimizing a target influence degree sorting algorithm of the deviation factors; if the audit is not passed, new main factors are selected again until the audit is passed;
if the energy-saving measures and the factor analysis table are unreasonable, reasons or measures are manually added and are audited by auditors, after the audits are passed, the operating parameters of the equipment are adjusted according to various indexes of the benchmarks, the system automatically traces the adjusting process, the working conditions of the benchmarks after the adjustment and before the adjustment are compared, if the working conditions of the benchmarks after the adjustment are superior to the working conditions of the benchmarks before the adjustment, the benchmarks are effective, the benchmarks are stored in a benchmarking library, and the sequencing of the benchmarks is improved; and if the working condition of the target is poor after adjustment, the target rod is invalid, the working conditions before and after adjustment are locked, and the reason is analyzed.
9. The method according to claim 1, wherein the method for optimizing the benchmarks in real time by the multi-tier power plant according to the change of each index after adjustment of the recommendations given by the result analysis sheet in step 6 comprises:
adjusting the operation parameters of the benchmarking object according to the optimization suggestions in the result analysis sheet, if the data of each index after adjustment is better than that before adjustment, the optimization suggestions are correct, then improving the priority of the benchmarking, and then perfecting a benchmarking optimization knowledge base according to the benchmarking diagnosis sheet and the result analysis sheet;
if the data of each index after adjustment is worse than that before adjustment, the operation optimization suggestion is incorrect, related personnel analyze reasons, the sequence of benchmarks is reduced, records in the benchmark optimization knowledge base are modified according to the benchmark diagnosis list and the result analysis list, and meanwhile, the optimization algorithm is adjusted and the algorithm model base is updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911077532.4A CN111027744A (en) | 2019-11-06 | 2019-11-06 | Real-time benchmarking optimization method for multi-level power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911077532.4A CN111027744A (en) | 2019-11-06 | 2019-11-06 | Real-time benchmarking optimization method for multi-level power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111027744A true CN111027744A (en) | 2020-04-17 |
Family
ID=70204941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911077532.4A Pending CN111027744A (en) | 2019-11-06 | 2019-11-06 | Real-time benchmarking optimization method for multi-level power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027744A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880499A (en) * | 2020-07-16 | 2020-11-03 | 国电黄金埠发电有限公司 | Online optimization system and method for operating parameters of thermal power plant |
| CN112396280A (en) * | 2020-07-31 | 2021-02-23 | 上海湃睿信息科技有限公司 | Product benchmarking management method, system, electronic device and medium |
| CN112667634A (en) * | 2020-12-29 | 2021-04-16 | 广州广电运通信息科技有限公司 | Benchmarking analysis method, system, device and storage medium for enterprise data |
| CN114219461A (en) * | 2022-02-22 | 2022-03-22 | 希望知舟技术(深圳)有限公司 | Production control method and device based on multiple production working conditions |
| CN114413249A (en) * | 2022-03-29 | 2022-04-29 | 朗坤智慧科技股份有限公司 | Data analysis method for power station boiler efficiency benchmarking optimization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| CN104504509A (en) * | 2014-12-16 | 2015-04-08 | 华润电力湖北有限公司 | Dynamic reference value-adopting thermal power plant consumption analyzing system and method |
| CN106249728A (en) * | 2016-09-28 | 2016-12-21 | 清华大学 | A kind of thermal power generation unit on-line performance monitoring method based on characteristics of components |
| US20170371305A1 (en) * | 2016-06-28 | 2017-12-28 | General Electric Company | Systems and methods for providing an integrated power plant advisor |
-
2019
- 2019-11-06 CN CN201911077532.4A patent/CN111027744A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101187804A (en) * | 2006-11-15 | 2008-05-28 | 北京华电天仁电力控制技术有限公司 | Thermal power unit operation optimization rule extraction method based on data excavation |
| CN104504509A (en) * | 2014-12-16 | 2015-04-08 | 华润电力湖北有限公司 | Dynamic reference value-adopting thermal power plant consumption analyzing system and method |
| US20170371305A1 (en) * | 2016-06-28 | 2017-12-28 | General Electric Company | Systems and methods for providing an integrated power plant advisor |
| CN106249728A (en) * | 2016-09-28 | 2016-12-21 | 清华大学 | A kind of thermal power generation unit on-line performance monitoring method based on characteristics of components |
Non-Patent Citations (2)
| Title |
|---|
| 蒋叶舟: "标杆管理在广钢炼钢总厂的实践和应用" * |
| 黄新: "火电机组节能对标管理***的研究与开发" * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111880499A (en) * | 2020-07-16 | 2020-11-03 | 国电黄金埠发电有限公司 | Online optimization system and method for operating parameters of thermal power plant |
| CN111880499B (en) * | 2020-07-16 | 2022-02-22 | 国电黄金埠发电有限公司 | Online optimization system and method for operating parameters of thermal power plant |
| CN112396280A (en) * | 2020-07-31 | 2021-02-23 | 上海湃睿信息科技有限公司 | Product benchmarking management method, system, electronic device and medium |
| CN112667634A (en) * | 2020-12-29 | 2021-04-16 | 广州广电运通信息科技有限公司 | Benchmarking analysis method, system, device and storage medium for enterprise data |
| CN114219461A (en) * | 2022-02-22 | 2022-03-22 | 希望知舟技术(深圳)有限公司 | Production control method and device based on multiple production working conditions |
| CN114413249A (en) * | 2022-03-29 | 2022-04-29 | 朗坤智慧科技股份有限公司 | Data analysis method for power station boiler efficiency benchmarking optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111027744A (en) | Real-time benchmarking optimization method for multi-level power plant | |
| CN111191906A (en) | Systematic implementation benefit evaluation method for technical standards of large and medium-sized enterprises | |
| CN104573106A (en) | Intelligent urban construction examining and approving method based on case-based reasoning technology | |
| CN104809658B (en) | A kind of rapid analysis method of low-voltage distribution network taiwan area line loss | |
| CN107169633A (en) | A kind of gas line network, gas storage peak regulating plan integrated evaluating method | |
| CN104572449A (en) | Automatic test method based on case library | |
| CN111539845B (en) | Enterprise environment-friendly management and control response studying and judging method based on power consumption mode membership grade | |
| CN106056235A (en) | Power transmission grid efficiency and benefit detection method based on Klee method and matter element extension model | |
| CN110942242A (en) | Method for evaluating operation performance of incubator of scientific and technological enterprise | |
| CN114529038A (en) | Intelligent matching business recruitment strategy system and method based on enterprise demands | |
| CN116384704A (en) | Management method of engineering progress and cost management system | |
| CN115543973A (en) | Data quality rule recommendation method based on knowledge spectrogram and machine learning | |
| CN103353895A (en) | Pre-processing method of power distribution network line loss data | |
| CN110738565A (en) | Real estate finance artificial intelligence composite wind control model based on data set | |
| CN109685133A (en) | The data classification method of prediction model low cost, high discrimination based on building | |
| CN116596395B (en) | Operation quality control platform for engineering project evaluation unit guidance and detection | |
| Pernetti et al. | Towards the definition of a nZEB cost spreadsheet as a support tool for the design | |
| CN107093018A (en) | Communication engineering project information method for visualizing and device based on health model | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN110866694A (en) | Power grid construction project financial evaluation system and method | |
| Yu et al. | Supplier evaluation analysis based on AHP-entropy-TOPSIS method | |
| CN113743994A (en) | Provider's season-busy prediction method, system, equipment and storage medium | |
| CN111581823A (en) | Construction quality-construction period-cost optimization method and device and electronic equipment | |
| CN110955700A (en) | 4D mode-based engineering cost lean control method and system | |
| CN111160635A (en) | Regional logistics demand influence factor prediction method based on Relieff algorithm |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |