CN113312800B - Data simulation method for power station industrial control safety target range - Google Patents
Data simulation method for power station industrial control safety target range Download PDFInfo
- Publication number
- CN113312800B CN113312800B CN202110716929.4A CN202110716929A CN113312800B CN 113312800 B CN113312800 B CN 113312800B CN 202110716929 A CN202110716929 A CN 202110716929A CN 113312800 B CN113312800 B CN 113312800B
- Authority
- CN
- China
- Prior art keywords
- data
- state
- influence
- target range
- industrial control
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A data simulation method for a power station industrial control safety target range comprises the following steps: determining an operation set and a simulation state parameter set according to the range of the target range configuration equipment, extracting historical data, finding out the historical record of single operation in the operation set, generating an operation influence item set according to load intervals of the single operation and the influence result of the single operation on the state parameter, and the like, acquiring an association rule algorithm in data mining for the operation influence item set, calculating a frequent operation item set corresponding to the single operation according to the minimum support degree, calculating the association rule and the confidence coefficient of the single operation and the influence result for the frequent operation item set, and obtaining a strong association rule according to the minimum confidence coefficient; and calculating simulation data after the execution of the single operation according to the initial data of the target range and the corresponding load interval and the strong association rule. The method can meet the requirement of the power station industrial control safety target range on local simulation of the industrial control system, and mining the incidence relation based on the real historical data, thereby realizing high fidelity simulation of the state parameter data.
Description
Technical Field
The invention relates to the technical field of industrial control simulation, in particular to a data simulation method for a power station industrial control safety target range.
Background
In order to deeply research the network security problem of the industrial control system, electric power enterprises construct industrial control security shooting ranges of the electric power industry in a dispute and conduct attack and defense exercises, security incident analysis and technical verification. However, considering factors such as cost and site limitation, a complete industrial control system is not required to be built, only the network structure characteristics of the industrial control system and the safety characteristics such as industrial control equipment, an operating system and a protocol are required to be reserved, the real power station industrial control system is properly cut, and few equipment and sensor measuring points of a field equipment layer are not installed or installed, so that field state parameter data cannot be acquired through clamping pieces such as AI and DI, after production adjustment operation is carried out, the change of the state parameter data can only be obtained through calculation of a simulation system, and then the data is sent to the industrial control equipment in a modbus mode and the like, so that simulation of part of production control process is realized.
The construction side of the target range mostly belongs to safety manufacturers, the construction side is unfamiliar with physical equipment of a power station, physical models are required to be established aiming at different equipment, the workload is high, the applicability is poor, and the target range is not suitable for models of wind power and water power and lacks a universal data simulation method if thermal power is used. The industrial control safety target range only configures partial equipment, carries out equipment adjustment operation under the condition that only partial running state parameter data exist, calculates the state parameter data after the adjustment operation, and can realize high-fidelity simulation of working conditions and parameter data by ensuring that the whole state parameter data basically accords with the physical characteristics of production equipment.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a data simulation method for a power station industrial control safety target range. The method aims to find the change rule of industrial control operation and actual state parameters based on an association rule algorithm in data mining, and realize high-fidelity simulation of operation state parameter data under the condition of carrying out local configuration on an industrial control system.
In order to achieve the purpose, the invention adopts the following technical scheme:
a data simulation method for a power station industrial control safety target range comprises the following steps:
(1) According to the actual power station industrial control system to be simulated in the target range, for example, the lowest integer load of a single unit of the power station is G min MW, maximum integer load of G max MW, to guarantee data accuracyDividing the load interval into 2 x (G) max -G min ) Determining the operation set as C = (C) according to the equipment range of the target range configuration 1 ，C 2 …C m ) Selecting n state parameters representing the operation conditions of the power station and the configuration equipment to form a simulation state parameter set S = (S) 1 ，S 2 …S n ) S at least comprises a load;
(2) Sorting the set of operation impact items by load interval for each individual operation in the operation set C, e.g. individual operation C i Extracting historical data of 3 years from an operation historical database of a power station industrial control system, finding k operation records and corresponding operation time thereof, obtaining working condition initial state data of a simulation state parameter set S according to the operation time of each operation record by adopting an accurate interpolation method, classifying the operation records into a certain divided load interval according to load interpolation, recording the state data, finding the next stable state as a working condition final state and recording the corresponding parameter data and time, wherein the working condition final state is a state in which the state parameters are concentrated after the operation records for 20 seconds;
for single operation C i Obtaining the influence result of the operation on the state parameter set S according to the change from the working condition initial state to the working condition final state of the operation record, wherein the influence result of the operation on the state in the state parameter set S is the change of the state data of the working condition final state relative to the working condition initial state, the influence result of the operation on the parameter in the state parameter set S is that the data of the working condition final state relative to the working condition initial state is large, the data is small and the data is unchanged, the time difference between the working condition final state and the working condition initial state is calculated for the parameter, and the operation record corresponds to a single operation C i The time difference, the state parameter data of the n working condition final states and the influence results of the n state parameters are arranged into operation influence items and also included into the load interval section to which the operation records belong, and a plurality of operation influence items corresponding to the operation records form an operation influence item set;
(3) Calculating the support degree of single operation in the operation influence item set of each load interval by adopting an association rule algorithm in data mining, and then calculating the association rule and of the single operation and the influence resultThe confidence of the rule; such as load interval F i Corresponding set of operation impact items Y i Operation influencing item set Y i Comprising several single operations, influencing the set of items Y i Number of terms of p, single-term operation C i In operation influence item set Y i The number of corresponding items in (1) is a, and the operation set C = (C) 1 ，C 2 …C m ) Respectively calculating the support degree sigma = a/p of the single operation, wherein a is the number of terms of the single operation in the operation influence term set, and p is the number of all operation influence terms; setting a minimum support degree, wherein items which are larger than the minimum support degree and belong to a frequent operation item set corresponding to single operation and items which are smaller than the minimum support degree belong to a working condition and an operation abnormal item set;
a set of operation impact terms may include multiple sets of frequently operated terms, single term operation C i The corresponding frequently-operated item set is J i One-item operation C i The association rule of (2) includes 4 items: one-item operation C i Single state parameter data, the influence result of the single state parameter, and the operation influence duration; in frequently operating item set J i In one operation C i B is the number of items which are the same as the single state parameter influence result, the confidence coefficient lambda = b/a of the association rule is set, the minimum confidence coefficient is set to be 50%, the strong association rule can be obtained, the operation influence duration in the strong association rule is the minimum value of all time differences in the b items, and the parameter is the average value of all parameters in the b items;
(4) During operation of the firing ground, when a single operation C is performed on the firing ground configuration equipment i And (3) according to the initial data of the state parameters at the operation moment, finding a corresponding load interval according to the initial load data, and the strong association rule in the interval obtained in the step (3), directly obtaining data according to the association rule for the state, gradually changing the initial parameter data into final state parameter data in the association rule once per second for the parameter according to the time difference in the association rule, calculating the intermediate data by using a linear interpolation method according to time, and displaying data abnormality if no corresponding rule exists.
The invention has the following beneficial technical effects: the general industrial control safety target range data simulation method applicable to various energy type power stations is provided, data simulation of the influence of operation on operation state parameters is realized, the requirement of local simulation of an industrial control system by a safety target range can be met, the incidence relation of operation and the influence result is extracted from real operation historical data, and simulation data basically accord with the physical characteristics of equipment.
Drawings
FIG. 1 is a schematic diagram of a data simulation method according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the following figures and examples:
as shown in fig. 1, a data simulation method for a power station industrial control safety target range is described by taking a single unit of a thermal power station with installed capacity of 600MW as an example, and includes the following steps:
(1) According to an actual power station industrial control system to be simulated in a target range, if the lowest integer load of a single unit of a power station is 180MW and the maximum integer load is 600MW, in order to ensure data accuracy, a load interval is divided into 840 sections, two pairs of DCS controllers are configured in the target range, the configured equipment range comprises a coal mill, a coal feeder, a primary fan and a secondary fan, and the operation set is determined to be C = (C) 1 ，C 2 …C m ) Selecting n state parameters representing the operation conditions of the power station and the configuration equipment, selecting parameters from a monitoring picture of a DCS (distributed control system), selecting coal mill current, coal feeder current, inlet air temperature, primary fan current, main steam pressure and the like to form a simulation state parameter set S = (S) 1 ，S 2 …S n ) S comprises unit load;
(2) Sorting the set of operation impact items by load interval for each individual operation in the operation set C, e.g. individual operation C i Extracting historical data according to 3 years from an operation historical database of the power station industrial control system, finding k operation records and corresponding operation time thereof, obtaining working condition initial state data of a simulation state parameter set S according to the operation time of each operation record by adopting an accurate interpolation method, classifying the operation records into a certain divided load interval according to the load interpolation, and obtaining the state of the state parameter set after 20 seconds of operation recordWorking condition final state, for the parameters in the state parameter set, finding out the next stable state as the working condition final state, and recording the corresponding parameter data and time;
for single operation C i Obtaining the influence result of the operation on the state parameter set S according to the change from the working condition initial state to the working condition final state of the operation record, wherein the influence result of the operation on the state is the state data change of the working condition final state relative to the working condition initial state, the influence result of the operation on the parameter is the data increase, the data decrease and the data no change of the working condition final state relative to the working condition initial state, calculating the time difference between the working condition final state and the working condition initial state, and performing single operation C i The time difference, the state parameter data of the n working condition final states and the influence results of the n state parameters are arranged into operation influence items, and a plurality of operation influence items corresponding to the plurality of operation records form an operation influence item set;
(3) Calculating the support degree of single operation for the operation influence item set of each load interval by adopting an association rule algorithm in data mining, and then calculating the association rule of the single operation and the influence result and the confidence coefficient of the rule; such as load interval section F i Corresponding set of operation impact items Y i Operation influencing item set Y i Comprises a plurality of single operations, the number of all operation influence items corresponding to the operations is p, and the single operation C i In operation influence item set Y i The number of corresponding items in (1) is a, and the operation set C = (C) 1 ，C 2 …C m ) Respectively calculating the support degree sigma = a/p of the single operation, setting the minimum support degree, and setting the frequent operation item set J corresponding to the single operation and larger than the minimum support degree i Items smaller than the minimum support degree belong to a set of items with abnormal working conditions and operations;
a set of operation affecting items may include multiple sets of frequently operated items, a single operation C i The corresponding frequently-operated item set is J i One-item operation C i The association rule of (2) includes 4 items: one-item operation C i Single state parameter data, an influence result of the single state parameter, and an operation influence duration; in frequently operating item set J i In one operation C i The same number of terms as a single state parameter effect result is b,setting the minimum confidence coefficient of 50% for the confidence coefficient lambda = b/a of the association rule, so as to obtain a strong association rule, wherein the operation influence duration in the strong association rule is the minimum value of all time differences in the item b, and the parameter is the mean value of all parameters in the item b;
(4) During operation of the firing ground, when a single operation C is performed on the firing ground configuration equipment i And (4) according to initial data of state parameters in the state parameter set at the operation moment, finding a corresponding load interval according to the initial load data and the strong association rule in the interval obtained in the step (3), directly obtaining data according to the association rule for the state, gradually changing the initial parameter data into final state parameter data in the association rule once per second according to the time difference in the association rule for the parameter, calculating the intermediate data by using a linear interpolation method according to time, and displaying data abnormality if no corresponding rule exists.
The examples of the present invention are set forth merely to help illustrate the invention and not to describe in detail all the details of the technical solutions that one skilled in the art could make to replace, modify and implement some of the technical solutions without departing from the spirit and scope of the embodiments of the present invention.
Claims (4)
1. A data simulation method for a power station industrial control safety target range is characterized by comprising the following steps: the method comprises the following steps:
(1) According to an actual power station industrial control system to be simulated in a target range, in order to ensure data accuracy, a load interval is divided into a plurality of load interval sections, an operation set consisting of m operations is determined according to the equipment range of the target range configuration, n state parameters representing the operation condition of the power station and the operation condition of configuration equipment are selected to form a simulation state parameter set, and the simulation state parameter set at least comprises loads;
(2) Arranging an operation influence item set for each single operation in the operation set according to a load interval, extracting historical data of 3 years from an operation historical database of a power station industrial control system, and finding a plurality of operation records of the single operation and corresponding operation time; obtaining the working condition initial state data of the simulation state parameter set by adopting an accurate interpolation method for each operation record according to the operation time, and classifying the operation record into the divided load interval section according to the interpolation of the load; for the state with the state parameter set, operating and recording the state which is a working condition final state after 20 seconds, and recording state data; for the parameters in the state parameter set, finding the next stable state as the final state of the working condition, and recording the corresponding parameter data and time;
for each operation record, obtaining an influence result of the operation on the state parameter set according to the change from the working condition initial state to the working condition final state of the operation record, wherein the influence result of the operation on the state parameter set is the state data change of the working condition final state relative to the working condition initial state, the influence result of the operation on the parameters in the state parameter set is that the data of the working condition final state relative to the working condition initial state is enlarged, the data is reduced and the data is unchanged, the time difference between the working condition final state and the working condition initial state is further calculated for the parameters, the influence results of single operation, the time difference, the n working condition final state parameter data and the n state parameters corresponding to the operation record are arranged into operation influence items, the operation influence items are also included in the load section to which the operation record belongs, and the operation influence items corresponding to the plurality of operation records form the operation influence item set;
(3) Calculating the support degree of single operation in the operation influence item set of each load interval by adopting an association rule algorithm in data mining, and then calculating association rules of the single operation and influence results and the confidence coefficient of the rules; each load zone corresponds to an operation influence item set, the operation influence item set comprises a plurality of single operations, the number of items of the operation influence item set is p, the number of items of a certain single operation in the operation influence item set is a, the support degree sigma = a/p of the single operation is respectively calculated for the operation set, wherein a is the number of items of the single operation in the operation influence item set; setting a minimum support degree, wherein items which are larger than the minimum support degree and belong to a frequent operation item set corresponding to single operation and items which are smaller than the minimum support degree belong to a working condition and an operation abnormal item set;
one operation influence item set comprises a plurality of frequently-operated item sets, and the association rule corresponding to a single operation comprises 4 items: single operation, single state parameter data, influence result of single state parameter, and operation influence duration; in the frequent operation item set, if the number of items with the same single operation and single state parameter influence result is b, the confidence coefficient lambda = b/a of the association rule is set to be 50% of the minimum confidence coefficient, so as to obtain a strong association rule, the operation influence duration in the strong association rule is the minimum value of all time differences in the items b, and the parameter is the average value of all parameters in the items b;
(4) In the operation process of the target range, when single operation is executed for the target range configuration equipment, a corresponding load interval is found according to initial data of state parameters at the operation moment and the initial load data, and the strong association rule in the interval is obtained in the step (3), data are directly obtained according to the association rule for the state, the initial parameter data are gradually changed into final state parameter data in the association rule once per second according to time difference in the association rule for the parameters, the intermediate data are calculated by a linear interpolation method according to time, and if no corresponding rule exists, data abnormity is displayed.
2. The power station industrial control safety target range oriented data simulation method of claim 1, characterized in that: the method is suitable for data simulation of the industrial control safety target range of the power station with various energy types such as water, fire, wind, light and nuclear.
3. The power station industrial control safety target range oriented data simulation method of claim 1, characterized in that: the method can meet the requirement of the industrial control safety target range in the elastic configuration range, and can be used for calculating data simulation corresponding to a plurality of adjustment operations.
4. The power station industrial control safety target range oriented data simulation method of claim 1, characterized in that: and the abnormal state and the operation item set obtained according to the minimum support degree can be used for alarming the abnormal operation and the abnormal operation of the power station industrial control safety target range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110716929.4A CN113312800B (en) | 2021-06-28 | 2021-06-28 | Data simulation method for power station industrial control safety target range |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110716929.4A CN113312800B (en) | 2021-06-28 | 2021-06-28 | Data simulation method for power station industrial control safety target range |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113312800A CN113312800A (en) | 2021-08-27 |
| CN113312800B true CN113312800B (en) | 2023-01-17 |
Family
ID=77380520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110716929.4A Active CN113312800B (en) | 2021-06-28 | 2021-06-28 | Data simulation method for power station industrial control safety target range |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113312800B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN107817756A (en) * | 2017-10-27 | 2018-03-20 | 西北工业大学 | Networking DNC system target range design method |
| CN111464530A (en) * | 2020-03-31 | 2020-07-28 | 中电运行(北京)信息技术有限公司 | Network security simulation target range platform service providing method and device |
-
2021
- 2021-06-28 CN CN202110716929.4A patent/CN113312800B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016029570A1 (en) * | 2014-08-28 | 2016-03-03 | 北京科东电力控制系统有限责任公司 | Intelligent alert analysis method for power grid scheduling |
| CN107817756A (en) * | 2017-10-27 | 2018-03-20 | 西北工业大学 | Networking DNC system target range design method |
| CN111464530A (en) * | 2020-03-31 | 2020-07-28 | 中电运行(北京)信息技术有限公司 | Network security simulation target range platform service providing method and device |
Non-Patent Citations (2)
| Title |
|---|
| Design and Implementation of Cyberspace Security Shooting Range in Colleges;LF Xuan等;《Science & Technology Vision》;20191130(第11期);全文 * |
| 基于过程数据模型的视景仿真系统研究与设计;邓春新等;《计算机仿真》;20050330(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113312800A (en) | 2021-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200396B (en) | A kind of wind turbine component fault early warning method | |
| CN109144986A (en) | A kind of importance appraisal procedure of industrial equipment data | |
| CN106017729A (en) | SPC (Statistical Process Control) based motor temperature monitoring method | |
| CN116993329B (en) | Communication equipment operation maintenance decision management system based on data analysis | |
| CN105652845A (en) | Fermentation process fault monitoring method based on just-in-time learning local model | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN116660672A (en) | Power grid equipment fault diagnosis method and system based on big data | |
| CN113285452A (en) | Method for prejudging transient instability of power system and generating generator tripping control strategy | |
| CN109184821A (en) | A kind of on-line monitoring method of the closed-loop information analysis towards intelligent power plant's Generator Set steam turbine | |
| CN118311352A (en) | Bus duct fault diagnosis method and system for photovoltaic energy storage system | |
| CN113740666B (en) | Method for positioning root fault of storm alarm in power system of data center | |
| CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
| CN113312800B (en) | Data simulation method for power station industrial control safety target range | |
| CN110887899A (en) | Turbine blade water erosion defect monitoring and identifying method | |
| CN117391357B (en) | Scheduling self-checking system for power grid scheduling operation management based on big data | |
| CN110443481A (en) | Distribution power automation terminal state evaluation system and method based on mixing K- nearest neighbor algorithm | |
| CN116662466B (en) | Land full life cycle maintenance system through big data | |
| CN112240267B (en) | Fan monitoring method based on wind speed correlation and wind power curve | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
| CN108960332A (en) | A kind of on-line monitoring method based on multidirectional the analysis of main elements | |
| CN114811858A (en) | Air conditioner load online learning method | |
| CN110456191B (en) | Method and system for detecting operation unit of super-large-scale battery energy storage power station | |
| CN109492855B (en) | Condenser type steam turbine exhaust temperature prediction method based on data model | |
| CN118096117A (en) | Digital twinning-based power equipment fault detection method and system | |
| CN117968405B (en) | Pressure sintering furnace monitoring method based on clustering 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |