CN112183896B - Intelligent identification and auxiliary compilation method for regional power grid maintenance plan - Google Patents
Intelligent identification and auxiliary compilation method for regional power grid maintenance plan Download PDFInfo
- Publication number
- CN112183896B CN112183896B CN202011196028.9A CN202011196028A CN112183896B CN 112183896 B CN112183896 B CN 112183896B CN 202011196028 A CN202011196028 A CN 202011196028A CN 112183896 B CN112183896 B CN 112183896B
- Authority
- CN
- China
- Prior art keywords
- maintenance
- overhaul
- power grid
- equipment
- constraint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas 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
- 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
Abstract
The invention discloses an intelligent identification and auxiliary compilation method for a regional power grid maintenance plan, which belongs to the technical field of electric power maintenance and comprises the following steps: constructing a standard basic database through standard data resources in a power grid information physical fusion system, and forming an overhaul knowledge base according to various constraint conditions influencing intelligent reasoning by using fuzzy logic; loading power grid equipment ledger information, maintenance knowledge base information, power grid operation data and network parameter information; reading power grid maintenance plan information; according to the maintenance time constraint, arranging the devices which are due and need to be maintained; searching each piece of overhaul basic data in the overhaul effective variable set through a particle swarm algorithm, triggering an active rule mode respectively, and completing intelligent diagnosis analysis and adjustment of overhaul data by using a user-defined expert system in the regional power grid overhaul plan intelligent identification and auxiliary compilation system. The invention can effectively improve the rationality of the equipment maintenance plan arrangement, avoid repeated power failure and improve the equipment utilization rate.
Description
Technical Field
The invention relates to the technical field of electric power overhaul, in particular to an intelligent identification and auxiliary compilation method for a regional power grid overhaul plan.
Background
With the continuous development of power technology and power demand in China and the increasing scale of modern power grids, the number of power supply equipment and power transmission and transformation facilities also increases. The normal service of each power supply device is the guarantee of the high-quality operation of the power grid, however, the time from the beginning to the final scrapping of the device is limited, and the abnormality and the failure of the device are the main reasons influencing the safe operation of the device. Within the normal service life of equipment, rationally arrange the overhaul of equipment to certain mode, can effectual reduction accident, the life of extension equipment, and then guarantee that the electric wire netting is safe, stable, economic operation.
For a power grid company, maintenance planning of power supply equipment is complex and daily work, most of the maintenance planning is completed by special staff of a regulation and control center, and the power supply equipment has less reliable and practical auxiliary software or tools and generally needs multiple departments and multiple professionals such as planning, operation and maintenance, scheduling, transformer maintenance work area, ultrahigh voltage work area and the like to cooperate and closely cooperate with each other. At present, the maintenance plans of power supply equipment in most power grid companies are still manually compiled, the traditional method forms the maintenance plans on the basis of personal experience by means of examination and approval and coordination among different units, different departments and different specialties, the dependence on the personal experience and the state is large, the workload of planning is heavy, the efficiency is low, the power failure frequency, the time and the safety analysis of the equipment are not very accurate, and the limitation is large. In addition, the reliability and the economy of the power grid maintenance plan cannot be guaranteed, so that unreasonable arrangement is caused, such as repeated power failure, voltage out-of-limit and the like, and meanwhile, the conditions of incomplete data accumulation and difficulty in data statistical analysis exist, and the analysis basis cannot be provided for state maintenance and more reasonable maintenance plan making.
The patent document with publication number CN 104077651 a discloses a power grid maintenance plan optimization method, which adopts single-target satisfaction and overall target closeness to realize the quantitative processing of preference information of a decision maker, reduces complexity, and is beneficial for the maintenance plan decision maker to conveniently obtain a maintenance optimization scheme; the whole optimization problem is decomposed into a subsection sub-optimization problem based on an interactive process through three decision models, and contradictions among multiple optimization targets are balanced and coordinated. The method aims at minimizing the overhaul cost and the expected power shortage amount, establishes a multi-objective optimization model of the overhaul plan, and comprehensively considers the multiple objectives of the economy and the reliability of the overhaul plan. However, this invention does not allow for intelligent diagnostic analysis and adjustment of service data.
The patent with publication number CN 103150685B discloses an intelligent maintenance plan optimization compilation system and method, wherein the system comprises a model calculation screening module, an evaluation and rating module, a model algorithm library module and a target constraint library module; and the module calculation screening module acquires the rating information and the algorithm and the model corresponding to the rating information from the model algorithm library module, screens the rating information, selects the algorithm with the highest rating for optimization compilation operation, and the user grades the optimization compilation operation result through the evaluation rating module and stores the rating result in the model algorithm library module or the target constraint library module. The accumulated mass algorithm reserves can be screened out to meet the requirements of specific users according to the means adjustment and history rating of the users. After the intelligent maintenance planning optimization compilation system is used for a long time, different algorithm selections and parameter presettings under different conditions can be accumulated, and the intelligent maintenance planning optimization compilation system can be more and more suitable for various dynamically changed environments and requirements. However, the invention only screens out the accumulated large amount of algorithm reserves according to the means adjustment and the historical rating of the user to meet the requirements of the specific user, and cannot provide analysis basis for implementing state maintenance and formulating a more reasonable maintenance plan.
Disclosure of Invention
In view of the above, the invention provides an intelligent identification and auxiliary compilation method for a regional power grid maintenance plan, which can effectively improve rationality of equipment maintenance plan arrangement, aiming at the defects of the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: an intelligent identification and auxiliary compilation method for a regional power grid maintenance plan comprises the following steps:
s1: constructing an intelligent identification and auxiliary compilation system of a regional power grid maintenance plan;
s2: constructing a standard basic database through standard data resources in a power grid information physical fusion system, and forming an overhaul knowledge base according to various constraint conditions influencing intelligent reasoning by using fuzzy logic;
s3: loading power grid equipment ledger information, maintenance knowledge base information, power grid operation data and network parameter information into the regional power grid maintenance plan intelligent identification and auxiliary compilation system;
s4: reading power grid maintenance plan information;
s5: according to the maintenance time constraint, arranging the devices which are due and need to be maintained;
s6: carrying out intelligent judgment on equipment needing to be overhauled according to an overhaul knowledge base, wherein the intelligent judgment comprises simultaneous overhaul constraint, mutual exclusion overhaul constraint, sequential overhaul constraint, unchangeable overhaul constraint, overhaul start time constraint and overhaul persistence constraint to form an overhaul effective variable set;
s7: searching each piece of overhaul basic data in the overhaul effective variable set through a particle swarm algorithm, triggering an active rule mode respectively, and completing intelligent diagnosis analysis and adjustment of overhaul data by using a user-defined expert system in the regional power grid overhaul plan intelligent identification and auxiliary compilation system.
Further, in S2, the constraint conditions include exclusive overhaul, simultaneous overhaul, sequential overhaul, unalterable overhaul, overhaul start time, and overhaul continuity.
Further, in S5, the processing method of the repair time is represented by the following formula:
mutually exclusive overhaul constraint:
and (4) maintenance and restraint are carried out simultaneously:
and (4) sequential maintenance constraint:
non-modifiable service constraints:
and (4) constraint of maintenance starting time:
maintenance continuity:
in the formula: x is the number of i And x j Respectively starting maintenance time of the ith equipment and the jth equipment;
days for the ith equipment overhaul duration;
indicating the maintenance start time of the ith equipment which is not changeable; x i Allowing a set of start-of-service times for the ith equipment; t is the total number of overhaul periods; and if the condition of the ith equipment in the f-th period is 0, indicating that the equipment normally operates, and if the condition of the ith equipment is 1, indicating that the equipment is stopped for maintenance.
Further, in S7, the particle swarm algorithm includes the following steps:
(1) initializing a particle population, and setting related parameters of a particle swarm algorithm;
(2) calculating the new speed and position of the particles according to a speed and position change formula;
(3) and (4) judging whether the termination condition is met, if so, stopping searching, outputting an optimal scheme, and if not, turning to the step (1).
Further, in S7, the method for intelligently diagnosing, analyzing and adjusting the service data includes the following steps:
(a) acquiring a maintenance network model structure R and a maintenance knowledge base set N, defining a traversal node queue O and a maintenance conflict set L;
(b) selecting an initial node R from the R, and storing the initial node R into a queue Q;
(c) taking out the first node Q from the queue Q, then obtaining all adjacent points of Q, and sequentially storing the adjacent points into the queue Q;
(d) judging whether the node q is in a maintenance state at the current time point, if not, indicating that the node q is not scheduled to be maintained at the current time point and is impossible to maintain unreasonable conditions with other equipment, and directly jumping to (f) to execute; if so, the node q is explained to have maintenance schedule arrangement at the current time point, and possibly has the situation of conflict of other equipment, and the next operation is executed;
(e) finding out other equipment associated with the node q from the N, sequentially judging whether the associated equipment has a maintenance plan at the current time point, detecting whether conflicts exist, and recording the node q into a set L if the conflicts exist;
(f) judging whether the queue Q is empty, and if not, directly jumping to the step (c) for execution; if the current time is empty, the next operation is carried out;
(g) judging whether the set L is empty, and if so, indicating that the maintenance plan is reasonably arranged; if not, checking the reason of the conflict of the equipment maintenance plans, and giving adjustment suggestions in sequence;
(h) and (5) finishing the search and exiting the program.
At present, when a power grid maintenance plan is compiled by a power grid dispatching center, maintenance staff usually complete the maintenance according to experience by the power grid dispatching center, and when the maintenance is compiled, equipment maintenance tasks reported or issued by different departments are comprehensively arranged according to a power grid operation mode, a height plan compiling principle and equipment maintenance management regulations, so that the compiled maintenance plan not only meets the safe and reliable operation needs of a power grid, but also meets the requirements of reasonable matching and no repeated maintenance among the maintenance departments. In the screening of the maintenance plans, prior art persons usually think of directly screening out low-cost maintenance plans by an algorithm in an experience base based on consideration of cost and timeliness, for example, an equipment maintenance plan optimization method and a related device disclosed in patent document No. CN 111445040 a are used for solving the problem that the selection of an optimal maintenance plan of equipment is influenced by the limited process accuracy of the change of the depicted equipment operation efficiency when a small amount of operation efficiency data is obtained by manual testing. The method in the embodiment of the application comprises the following steps: acquiring historical operation information and different maintenance plans of equipment, generating a predicted load curve of the equipment according to the historical operation information, generating a non-maintenance operation efficiency change curve of the equipment according to the predicted load curve, generating a non-maintenance operation energy consumption cost curve of the equipment according to the non-maintenance operation efficiency change curve, generating a reference operation efficiency change curve after each maintenance plan is adopted by the equipment according to each maintenance plan and the predicted load curve, generating a corresponding post-maintenance total cost curve after each maintenance plan is adopted according to each reference operation efficiency change curve, comparing all maintenance plans of the equipment in a cost comparison period, and obtaining and selecting a target maintenance plan; also for example, patent publication No. CN 103150685B discloses an intelligent maintenance plan optimization compilation system and method, the system includes a model calculation screening module, an evaluation rating module, a model algorithm library module and a target constraint library module; and the module calculation screening module acquires the rating information and the algorithm and the model corresponding to the rating information from the model algorithm library module, screens the rating information, selects the algorithm with the highest rating for optimization compilation operation, and the user grades the optimization compilation operation result through the evaluation rating module and stores the rating result in the model algorithm library module or the target constraint library module. The accumulated mass algorithm reserves can be screened out to meet the requirements of specific users according to the means adjustment and history rating of the users. After the intelligent maintenance planning system is used for a long time, different algorithm selections and parameter presettings under different conditions can be accumulated, and the intelligent maintenance planning optimization compilation system can be more and more suitable for various dynamically changed environments and requirements; therefore, the technicians in the field can easily think of directly screening out the maintenance plans meeting the cost and the stability in the maintenance module algorithm library, but can not easily think of reconstructing the maintenance knowledge library, reselecting the screening algorithm and carrying out intelligent diagnosis analysis and adjustment on the maintenance knowledge library.
In addition, the service plan optimization is a complex multi-stage dynamic planning process. The method is a multi-objective multi-constraint planning problem which takes the overhaul starting time of equipment as an optimization variable, and is essentially a multi-objective optimization problem with decision preference and complex constraints. In the process of optimizing the power grid maintenance plan, a plurality of optimization targets are correlated and even contradictory, and different optimization targets have different importance degrees. The method comprises the steps that a maintenance knowledge base is constructed, a plurality of links such as maintenance objects, constraint conditions and processing algorithms need to be considered, each link has a plurality of variables, the maintenance objects, the constraint conditions and the processing algorithms are selected and combined to obtain a comprehensive maintenance database, the selection of a screening algorithm is carried out on the maintenance database to obtain a reasonable effective variable set of a maintenance plan, and the intelligent diagnosis analysis and adjustment are carried out on maintenance data according to a user-defined expert base.
Compared with the prior art, the invention has the following beneficial effects:
the intelligent identification and auxiliary compilation method for the regional power grid maintenance plan can effectively improve the reasonability of equipment maintenance plan arrangement, avoid repeated power failure, improve the utilization rate of equipment and have remarkable benefit. After the achievement is successfully applied in the pilot area, the achievement can be gradually popularized to maintenance plan management systems of other power grid companies, and the method has wide application prospect and practicability.
In addition, the invention analyzes the function and the fault of the equipment, determines the result of each fault of the equipment, determines the preventive maintenance strategy of each fault by a standardized logic decision method, and optimizes the maintenance strategy of the equipment by taking the minimum maintenance shutdown loss as the target on the premise of ensuring the safety and the completeness of the equipment through means of field fault data statistics, expert evaluation, quantitative modeling and the like.
In addition, in the power grid maintenance plan optimization process, a standard taste basic database is constructed by fusing standard data resources in a source system, and a power grid maintenance knowledge base is formed by utilizing fuzzy logic according to various constraint conditions influencing intelligent reasoning. Then searching each piece of maintenance basic data, and triggering an active rule mode respectively to complete intelligent diagnosis analysis and adjustment of the maintenance data by using an expert system, so that the power grid maintenance plan finally reaches the scientific and normative target; by analyzing the power grid maintenance plan and applying the latest results of artificial intelligence technologies such as comprehensive knowledge diagnosis, fuzzy theory, expert system and the like, the power grid maintenance plan is analyzed and optimized, and a comprehensive and accurate decision basis is provided for a decision maker to determine a final maintenance scheme.
Detailed Description
In order to better understand the present invention, the following examples are further provided to clearly illustrate the contents of the present invention, but the contents of the present invention are not limited to the following examples. In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details.
Example one
An intelligent identification and auxiliary compilation method for a regional power grid maintenance plan comprises the following steps:
s1: constructing an intelligent identification and auxiliary compilation system of a regional power grid maintenance plan;
s2: constructing a standard basic database through standard data resources in a power grid information physical fusion system, and forming a maintenance knowledge base by utilizing fuzzy logic according to various constraint conditions influencing intelligent reasoning, including mutual exclusion maintenance, simultaneous maintenance, sequential maintenance, unchangeable maintenance, maintenance starting time and maintenance continuity;
s3: loading power grid equipment ledger information, maintenance knowledge base information, power grid operation data and network parameter information into the regional power grid maintenance plan intelligent identification and auxiliary compilation system;
s4: reading power grid maintenance plan information;
s5: according to the maintenance time constraint, arranging the devices which are due and need to be maintained;
s6: carrying out intelligent judgment on equipment needing to be overhauled according to an overhaul knowledge base, wherein the intelligent judgment comprises simultaneous overhaul constraint, mutual exclusion overhaul constraint, sequential overhaul constraint, unchangeable overhaul constraint, overhaul start time constraint and overhaul persistence constraint to form an overhaul effective variable set;
s7: searching each piece of overhaul basic data in the overhaul effective variable set through a particle swarm algorithm, triggering an active rule mode respectively, and completing intelligent diagnosis analysis and adjustment of overhaul data by using a user-defined expert system in the regional power grid overhaul plan intelligent identification and auxiliary compilation system.
The intelligent identification and auxiliary compilation method for the regional power grid maintenance plan used in the embodiment of the invention comprises a high-level application layer, a service support layer, a basic management layer and a data storage layer which are sequentially interconnected by information, wherein the data storage layer comprises a storage device, a file system and a database, the basic management layer comprises a maintenance database, a maintenance knowledge base, a network communication module, a process management module, an authority management module, a graph conversion module, a model conversion module and a visual interaction module, the service support layer comprises an online network modeling module, a state estimation processing module, a user-defined expert system and an integrated optimization algorithm, the high-level application layer comprises a maintenance plan optimization auxiliary decision-making module and a network publishing and query statistical module, and a maintenance plan is recorded into the basic management layer through the visual interaction module, after the optimization and identification of the service supporting layer, outputting a result through the advanced application layer; the data storage layer is in signal connection with the basic management layer through a data storage interface, the basic management layer is in signal connection with the service support layer through a data interface, the service support layer is in signal connection with the advanced application layer through a service interface, and the basic management layer is provided with a third-party interface; the maintenance database consists of a power grid basic database, a maintenance equipment library and a maintenance plan library, and the maintenance equipment library and the maintenance plan library are respectively used for storing generated maintenance data and a final maintenance schedule; the overhaul knowledge base comprises overhaul rules, safety regulations and operation regulations of various electrical equipment and lines; the overhaul database and the overhaul knowledge base are both stored in the data storage layer, and the online network modeling module comprises a power grid information physical fusion system.
According to the intelligent identification and auxiliary compilation method for the regional power grid maintenance plan, provided by the embodiment of the invention, functions and fault analysis are carried out on equipment, the consequence of each fault of the equipment is clarified, a standardized logic decision method is used for determining preventive maintenance countermeasures of each fault, and the maintenance strategy of the equipment is optimized by taking the minimum maintenance shutdown loss as a target on the premise of ensuring the safety and completeness of the equipment through means of field fault data statistics, expert evaluation, quantitative modeling and the like.
Example two
The intelligent identification and auxiliary compilation method for the regional power grid maintenance plan of the embodiment of the invention is different from the first embodiment in that: in S5, the repair time is processed according to the following equation:
mutually exclusive overhaul constraint:
and (4) maintenance and restraint are carried out simultaneously:
and (4) sequential maintenance constraint:
non-modifiable service constraints:
and (4) constraint of maintenance starting time:
maintenance continuity:
in the formula: x is the number of i And x j Respectively starting maintenance time of the ith equipment and the jth equipment;
days for the ith equipment overhaul duration;
indicating the maintenance start time of the ith equipment which is not changeable; x i Allowing a set of start-of-service times for the ith equipment; t is the total number of overhaul periods; and if the condition of the ith equipment in the f-th period is 0, indicating that the equipment normally operates, and if the condition of the ith equipment is 1, indicating that the equipment is stopped for maintenance.
In the embodiment of the invention, in the process of optimizing the power grid maintenance plan, a standard taste basic database is constructed by fusing standard data resources in a source system, and a power grid maintenance knowledge base is formed by utilizing fuzzy logic according to various constraint conditions influencing intelligent reasoning. And then searching each piece of maintenance basic data, and respectively triggering an active rule mode to complete intelligent diagnosis analysis and adjustment of the maintenance data by using an expert system, so that the power grid maintenance plan finally achieves the scientific and normative target.
EXAMPLE III
The intelligent identification and auxiliary compilation method for the regional power grid maintenance plan of the embodiment of the invention is different from the first embodiment and the second embodiment in that: in S7, the particle swarm algorithm includes the steps of:
(1) initializing a particle population, and setting related parameters of a particle swarm algorithm;
(2) calculating the new speed and position of the particles according to a speed and position change formula;
(3) and (4) judging whether the termination condition is met, if so, stopping searching, outputting an optimal scheme, and if not, turning to the step (1).
Further, in S7, the method for intelligently diagnosing, analyzing and adjusting the service data includes the following steps:
(a) acquiring a maintenance network model structure R and a maintenance knowledge base set N from a power grid information physical fusion system, and defining a traversal node queue O and a maintenance conflict set L;
(b) selecting an initial node R from the R, and storing the initial node R into a queue Q;
(c) taking out the first node Q from the queue Q, then obtaining all adjacent points of Q, and sequentially storing the adjacent points into the queue Q;
(d) judging whether the node q is in a maintenance state at the current time point, if not, indicating that the node q is not scheduled to be maintained at the current time point and is impossible to maintain unreasonable conditions with other equipment, and directly jumping to (f) to execute; if so, the node q is explained to have maintenance schedule arrangement at the current time point, and possibly has the situation of conflict of other equipment, and the next operation is executed;
(e) finding out other equipment associated with the node q from the N, sequentially judging whether the associated equipment has a maintenance plan at the current time point, detecting whether conflicts exist, and recording the node q into a set L if the conflicts exist;
(f) judging whether the queue Q is empty, and if not, directly jumping to the step (c) for execution; if the current time is empty, the next operation is carried out;
(g) judging whether the set L is empty, and if so, indicating that the maintenance plan arrangement is reasonable; if not, checking the reason of the conflict of the equipment maintenance plans, and giving adjustment suggestions in sequence;
(h) and (5) finishing the search and exiting the program.
Finally, the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting, and other modifications or equivalent substitutions made by the technical solutions of the present invention by those of ordinary skill in the art should be covered within the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. An intelligent identification and auxiliary compilation method for a regional power grid maintenance plan is characterized by comprising the following steps:
s1: constructing an intelligent identification and auxiliary compilation system of a regional power grid maintenance plan;
s2: constructing a standard basic database through standard data resources in a power grid information physical fusion system, and forming an overhaul knowledge base by utilizing fuzzy logic according to various constraint conditions influencing intelligent reasoning;
s3: loading power grid equipment ledger information, maintenance knowledge base information, power grid operation data and network parameter information into the regional power grid maintenance plan intelligent identification and auxiliary compilation system;
s4: reading power grid maintenance plan information;
s5: according to the maintenance time constraint, arranging the devices which are due and need to be maintained;
s6: carrying out intelligent judgment on equipment needing to be overhauled according to an overhaul knowledge base, wherein the intelligent judgment comprises simultaneous overhaul constraint, mutual exclusion overhaul constraint, sequential overhaul constraint, unchangeable overhaul constraint, overhaul start time constraint and overhaul persistence constraint to form an overhaul effective variable set;
s7: searching each piece of overhaul basic data in the overhaul effective variable set through a particle swarm algorithm, triggering an active rule mode respectively, and completing intelligent diagnosis analysis and adjustment of overhaul data by utilizing a user-defined expert system in the regional power grid overhaul plan intelligent identification and auxiliary compilation system;
the system comprises a high-level application layer, a service supporting layer, a basic management layer and a data storage layer, wherein the high-level application layer, the service supporting layer, the basic management layer and the data storage layer are sequentially interconnected, the data storage layer comprises a storage device, a file system and a database, the basic management layer comprises a maintenance database, a maintenance knowledge base, a network communication module, a process management module, an authority management module, a graph conversion module, a model conversion module and a visual interaction module, the service supporting layer comprises an online network modeling module, a state estimation processing module, a user-defined expert system and an integrated optimization algorithm, the high-level application layer comprises a maintenance plan optimization auxiliary decision-making module and a network publishing and inquiry statistical module, a maintenance plan is recorded into the basic management layer through the visual interaction module, and the maintenance plan is optimized through the service supporting layer, After identification, outputting a result through the advanced application layer; the data storage layer is in signal connection with the basic management layer through a data storage interface, the basic management layer is in signal connection with the service support layer through a data interface, the service support layer is in signal connection with the advanced application layer through a service interface, and the basic management layer is provided with a third-party interface; the maintenance database consists of a power grid basic database, a maintenance equipment library and a maintenance plan library, wherein the maintenance equipment library is used for storing generated maintenance data, and the maintenance plan library is used for storing a final maintenance schedule; the overhaul knowledge base comprises overhaul rules, safety regulations and operation regulations of various electrical equipment and lines; the overhaul database and the overhaul knowledge base are both stored in the data storage layer, and the online network modeling module comprises a power grid information physical fusion system.
2. The intelligent identification and auxiliary compilation method for the maintenance plan of the regional power grid as claimed in claim 1, wherein the method comprises the following steps: in S2, the constraint conditions include exclusive overhaul, simultaneous overhaul, sequential overhaul, unchangeable overhaul, overhaul start time, and overhaul continuity.
3. The intelligent identification and auxiliary compilation method for the maintenance plan of the regional power grid as claimed in claim 1, wherein the method comprises the following steps: in S5, the repair time is processed according to the following equation:
mutually exclusive overhaul constraint:
and (4) maintenance and restraint are carried out simultaneously:
and (4) sequential maintenance constraint:
non-modifiable service constraints:
and (4) constraint of maintenance starting time:
maintenance continuity:
in the formula: x is a radical of a fluorine atom i And x j Respectively starting maintenance time of the ith equipment and the jth equipment;
days for the ith equipment overhaul duration;
indicating the maintenance start time of the ith equipment which is not changeable; x i Allowing a set of start-of-service times for the ith equipment; t is the total number of overhaul periods; u. of if And if the condition of the ith equipment in the f-th period is 0, indicating that the equipment normally operates, and if the condition of the ith equipment is 1, indicating that the equipment is stopped for maintenance.
4. The intelligent identification and auxiliary compilation method for the maintenance plan of the regional power grid as claimed in claim 1, wherein the method comprises the following steps: in S7, the particle swarm algorithm includes the steps of:
(1) initializing a particle population, and setting related parameters of a particle swarm algorithm;
(2) calculating the new speed and position of the particles according to a speed and position change formula;
(3) and (4) judging whether the termination condition is met, if so, stopping searching, outputting an optimal scheme, and if not, turning to the step (1).
5. The intelligent identification and auxiliary compilation method for the maintenance plan of the regional power grid as claimed in claim 1, wherein the method comprises the following steps: in S7, the method for intelligently diagnosing, analyzing, and adjusting overhaul data includes the following steps:
(a) acquiring a maintenance network model structure R and a maintenance knowledge base set N, defining a traversal node queue O and a maintenance conflict set L;
(b) selecting an initial node R from the R, and storing the initial node R into a queue Q;
(c) taking out the first node Q from the queue Q, then obtaining all adjacent points of Q, and sequentially storing the adjacent points into the queue Q;
(d) judging whether the node q is in a maintenance state at the current time point, if not, indicating that the node q is not scheduled to be maintained at the current time point and is impossible to maintain unreasonable conditions with other equipment, and directly jumping to (f) to execute; if so, the node q is explained to have maintenance schedule arrangement at the current time point, and possibly has the situation of conflict of other equipment, and the next operation is executed;
(e) finding out other equipment associated with the node q from the N, sequentially judging whether the associated equipment has a maintenance plan at the current time point, detecting whether conflicts exist, and recording the node q into a set L if the conflicts exist;
(f) judging whether the queue Q is empty, and if not, directly jumping to the step (c) for execution; if the current time is empty, the next operation is carried out;
(g) judging whether the set L is empty, and if so, indicating that the maintenance plan is reasonably arranged; if not, checking the reason of the conflict of the equipment maintenance plans, and giving adjustment suggestions in sequence;
(h) and (5) finishing the search and exiting the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011196028.9A CN112183896B (en) | 2020-10-31 | 2020-10-31 | Intelligent identification and auxiliary compilation method for regional power grid maintenance plan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011196028.9A CN112183896B (en) | 2020-10-31 | 2020-10-31 | Intelligent identification and auxiliary compilation method for regional power grid maintenance plan |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112183896A CN112183896A (en) | 2021-01-05 |
| CN112183896B true CN112183896B (en) | 2022-08-09 |
Family
ID=73916201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011196028.9A Active CN112183896B (en) | 2020-10-31 | 2020-10-31 | Intelligent identification and auxiliary compilation method for regional power grid maintenance plan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112183896B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095525A (en) * | 2021-05-24 | 2021-07-09 | 国网湖北省电力有限公司直流运检公司 | Intelligent management and control cross operation system for power grid maintenance |
| CN113451988B (en) * | 2021-06-02 | 2022-05-27 | 合占电力有限公司 | Modeling method based on upgrading and modifying system equipment |
| CN113283619A (en) * | 2021-06-11 | 2021-08-20 | 广西电网有限责任公司南宁供电局 | Power failure maintenance planning auxiliary method and system based on knowledge graph |
| CN113421062B (en) * | 2021-06-25 | 2023-05-23 | 国网山东省电力公司汶上县供电公司 | Auxiliary reminding system for power dispatching planning flow time |
| CN114386878A (en) * | 2022-03-04 | 2022-04-22 | 中铁第一勘察设计院集团有限公司 | Method and system for generating maintenance schedule of railway communication equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002342412A (en) * | 2001-05-21 | 2002-11-29 | Nihon Meccs Co Ltd | Maintenance and management plan preparing system for construction equipment |
| JP2006152767A (en) * | 2004-11-25 | 2006-06-15 | Mizu Joho Gijutsu Kenkyusho:Kk | Door-to-door repairing plan preparation support system of temporary faucet in disaster recovery |
| CN104252646A (en) * | 2013-06-29 | 2014-12-31 | 贵州黔驰信息股份有限公司 | Method for automatically formulating daily power grid maintenance plans |
| CN104573845A (en) * | 2014-12-03 | 2015-04-29 | 国家电网公司 | Auxiliary decision-making method for equipment state maintenance of information system |
| CN106570567A (en) * | 2016-10-26 | 2017-04-19 | 国家电网公司 | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method |
| CN207233015U (en) * | 2017-07-06 | 2018-04-13 | 贵州电网有限责任公司 | A kind of optimization device of maintenance scheduling for power systems |
| CN110633839A (en) * | 2019-08-06 | 2019-12-31 | 广州供电局有限公司 | Kneading algorithm-based power failure maintenance plan analysis and optimization system |
| CN111144589A (en) * | 2019-12-27 | 2020-05-12 | 中国人民解放军32181部队 | Maintenance equipment management system |
-
2020
- 2020-10-31 CN CN202011196028.9A patent/CN112183896B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002342412A (en) * | 2001-05-21 | 2002-11-29 | Nihon Meccs Co Ltd | Maintenance and management plan preparing system for construction equipment |
| JP2006152767A (en) * | 2004-11-25 | 2006-06-15 | Mizu Joho Gijutsu Kenkyusho:Kk | Door-to-door repairing plan preparation support system of temporary faucet in disaster recovery |
| CN104252646A (en) * | 2013-06-29 | 2014-12-31 | 贵州黔驰信息股份有限公司 | Method for automatically formulating daily power grid maintenance plans |
| CN104573845A (en) * | 2014-12-03 | 2015-04-29 | 国家电网公司 | Auxiliary decision-making method for equipment state maintenance of information system |
| CN106570567A (en) * | 2016-10-26 | 2017-04-19 | 国家电网公司 | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method |
| CN207233015U (en) * | 2017-07-06 | 2018-04-13 | 贵州电网有限责任公司 | A kind of optimization device of maintenance scheduling for power systems |
| CN110633839A (en) * | 2019-08-06 | 2019-12-31 | 广州供电局有限公司 | Kneading algorithm-based power failure maintenance plan analysis and optimization system |
| CN111144589A (en) * | 2019-12-27 | 2020-05-12 | 中国人民解放军32181部队 | Maintenance equipment management system |
Non-Patent Citations (7)
| Title |
|---|
| A technique of generation equipment maintenance scheduling in deregulated electric power systems;G. A. Fedotova等;《2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies》;20080516;全文 * |
| Generation units maintenance scheduling considering gas network constraints;M. Yazdani Damavandi等;《2009 International Conference on Electric Power and Energy Conversion Systems, (EPECS)》;20100217;全文 * |
| 电网检修计划优化编制方法研究及应用;谢昶;《中国博士学位论文全文数据库》;20131115;全文 * |
| 电网检修计划编制的智能可视化方法及应用;李刚等;《电力系统保护与控制》;20120701;第40卷(第13期);全文 * |
| 电网检修计划编制系统的设计;周德东等;《自动化与仪器仪表》;20161231(第8期);全文 * |
| 省级电网检修可视化辅助决策研究及系统设计实现;应小诚;<中国优秀硕士学位论文全文数据库>;20120715;全文 * |
| 面向省级电网的检修可视化设计和辅助决策实现;廖胜利等;《电力系统自动化》;20111110;第35卷(第21期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112183896A (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183896B (en) | Intelligent identification and auxiliary compilation method for regional power grid maintenance plan | |
| CN108491969B (en) | Big data-based space load prediction model construction method | |
| CN112183895B (en) | Intelligent identification and auxiliary compilation system for regional power grid maintenance plan | |
| Zia et al. | Microgrids energy management systems: A critical review on methods, solutions, and prospects | |
| Neimane | On development planning of electricity distribution networks | |
| Zhao et al. | Dynamic jobshop scheduling algorithm based on deep Q network | |
| CN112785454A (en) | Intelligent scheduling method for flood season of cascade hydropower station and decision support system | |
| CN108182485A (en) | A kind of power distribution network maintenance opportunity optimization method and system | |
| Ouyang et al. | A multi-stage intelligent system for unit commitment | |
| KR20200084454A (en) | A Device and Method for Predictively Operating An ESS Charging Based On Artificial Intelligence | |
| Cominesi et al. | A multi-layer control scheme for microgrid energy management | |
| CN110994790B (en) | Enterprise power grid dispatching knowledge decision analysis system | |
| CN111680452A (en) | Power grid engineering accurate investment decision simulation method based on full-factor data mining | |
| Guan et al. | A GAN-based fully model-free learning method for short-term scheduling of large power system | |
| Yuill et al. | Application of Adaptive Neuro Fuzzy Inference System (ANFIS) based short term load forecasting in South African power networks | |
| CN117595391A (en) | Coordination control method of power grid system | |
| CN104077231A (en) | Transformer maintenance optimization method based on symbol dynamics and LS-SVM | |
| CN115169816A (en) | Energy management method and energy management system of wind and light storage station | |
| CN112053086B (en) | Working method of operation diagnosis system based on big data power grid | |
| CN117526432B (en) | Distribution network regulation and control system and method for source-load interaction | |
| Wang et al. | Research on Disturbance for Job-shops Based on Production Data | |
| Alves et al. | Linear Programming and Genetic Algorithm for Generation Maintenance Scheduling and Hydrothermal Dispatch considering Uncertainties in Multicriteira Decision Making | |
| Omondi et al. | Smart grid energy management system for industrial applications | |
| Anderson et al. | SMARTER Rules-Based Distributed Deconfliction of ADMS Applications | |
| Yan et al. | Look-Ahead Unit Commitment with Adaptive Horizon Based on Deep Reinforcement Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |