CN116302957A - Supercritical unit early warning model test method and device based on big data platform - Google Patents
Supercritical unit early warning model test method and device based on big data platform Download PDFInfo
- Publication number
- CN116302957A CN116302957A CN202310071732.9A CN202310071732A CN116302957A CN 116302957 A CN116302957 A CN 116302957A CN 202310071732 A CN202310071732 A CN 202310071732A CN 116302957 A CN116302957 A CN 116302957A
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- mathematical model
- preset
- measuring point
- 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
- 238000010998 test method Methods 0.000 title claims abstract description 8
- 238000013178 mathematical model Methods 0.000 claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000005259 measurement Methods 0.000 claims abstract description 39
- 238000012795 verification Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims description 25
- 230000004044 response Effects 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013499 data model Methods 0.000 abstract description 9
- 239000003921 oil Substances 0.000 description 20
- 238000004422 calculation algorithm Methods 0.000 description 12
- 239000003245 coal Substances 0.000 description 10
- 238000001223 reverse osmosis Methods 0.000 description 10
- 230000007774 longterm Effects 0.000 description 8
- 230000009970 fire resistant effect Effects 0.000 description 6
- 230000000903 blocking effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 239000010865 sewage Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 239000010687 lubricating oil Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 238000010298 pulverizing process Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 239000010729 system oil Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3688—Test management for test execution, e.g. scheduling of test suites
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a supercritical unit early warning model test method and device based on a big data platform. The specific scheme is as follows: acquiring measurement point data of each of a plurality of mathematical models; respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model; responding to the verification of the plurality of measuring points, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model; determining whether the operation data of the supercritical unit meet the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result; and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the data model. The method and the device improve the accuracy and timeliness of early warning of the supercritical unit through the mathematical model.
Description
Technical Field
The application relates to the technical field of big data platforms of supercritical units, in particular to a method and a device for testing an early warning model of a supercritical unit based on a big data platform.
Background
In the related art, because the thermal power plant has the characteristics of complex system, multiple devices, refined process flow and safety, workers must pay careful attention to the field operation and the remote operation of a centralized control room, so that the most basic normal operation of the thermal power plant can be maintained. When related systems and equipment are in failure, if an operator cannot remotely operate in the centralized control room at the first time to close the failed equipment and open corresponding protection equipment, further expansion, danger and severity of accidents are likely to be caused. The thermal power plant at present has the problems that the mechanism level judgment and early warning are carried out by dividing boundary conditions and boundary information of each device of each system, and the method is generally based on a mechanism analysis library by taking factory parameter values provided by a device manufacturer, expert experience reference values drawn by experienced technical enrichment staff and reasonable values of the prior safe operation of related units of the same type as the basis, so that different types of fault early warning judgment and division are carried out on each working condition, system and device of the thermal power plant, and fault early warning is realized. However, the thermal power plant is composed of complex system equipment, and the early warning method is single in pertinence and limited in adaptability by dividing threshold values and working conditions of single equipment.
Disclosure of Invention
Therefore, the application provides a supercritical unit early warning model test method and device based on a big data platform. The technical scheme of the application is as follows:
according to a first aspect of embodiments of the present application, there is provided a method for testing a supercritical unit early warning model based on a big data platform, the method including:
acquiring measurement point data of each of a plurality of mathematical models; the plurality of mathematical models are machine learning models which are obtained by training in advance based on historical operation data of the supercritical unit; the measuring point data comprises a measuring point name, a measuring point identifier and a monitoring value;
for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model;
responding to the fact that all the measuring points pass verification, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model;
determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement;
determining whether the triggering time meets a preset requirement;
determining whether the early warning result meets a preset requirement;
and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the mathematical model.
According to an embodiment of the present application, the determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model at the trigger time, to obtain a first intermediate result, includes:
determining at least one preset trigger condition of the mathematical model based on the mathematical model;
acquiring operation data of the supercritical unit at the trigger time;
acquiring operation information corresponding to each of the at least one preset trigger condition based on the operation data;
determining whether each piece of operation information meets respective corresponding preset triggering conditions;
responding to each piece of operation information to meet respective corresponding preset triggering conditions, and determining that the triggering time meets preset requirements as the first intermediate result;
and responding to at least one piece of operation information to fail to meet the corresponding preset triggering conditions, and determining that the triggering time fails to meet the preset requirement as the first intermediate result.
According to an embodiment of the present application, the determining whether the triggering time meets a preset requirement includes:
acquiring a preset trigger period of the mathematical model;
comparing the preset trigger period with the trigger time to obtain a first comparison result;
and responding to the first comparison result that the trigger time does not fall into the preset trigger period, and determining that the trigger time does not meet a preset requirement.
According to an embodiment of the present application, the determining whether the early warning result meets a preset requirement respectively includes:
acquiring an actual early warning result corresponding to the measuring point data;
comparing the early warning result with the actual early warning result to obtain a second comparison result;
and responding to the second comparison result that the early warning result is not consistent with the actual early warning result, and determining that the early warning result does not meet a preset requirement.
According to an embodiment of the present application, the verifying the respective station names of the plurality of stations based on the mathematical model includes:
based on the respective measuring point names and the measuring point identifications of the plurality of measuring points of the mathematical model, searching the respective historical data of the plurality of measuring point identifications of the mechanical model stored in a database in advance;
determining, in response to not finding historical data for at least one measurement point in the database, a relevant measurement point for the at least one measurement point among the plurality of measurement points based on a measurement point name of the at least one measurement point;
searching historical data of the related measuring points stored in the database in advance;
and in response to the fact that the historical data of the related measuring points stored in the database in advance are not found, determining that the at least one measuring point is not verified, respectively performing parameter adjustment processing on the at least one measuring point, and repeatedly executing the steps of searching the historical data of each of a plurality of measuring point identifiers of the mechanism model stored in the database in advance.
According to one embodiment of the present application, the historical operating data of the supercritical unit includes any one or more of: steam turbine type historical operation data, boiler type historical operation data, electric type historical operation data, thermal control type historical operation data and chemical type historical operation data; each type of historical operation data comprises shutdown data, starting process data and operation data; the shutdown data, the starting process data and the operation data comprise normal data and abnormal data.
According to a second aspect of embodiments of the present application, there is provided a supercritical unit early warning model testing device based on a big data platform, the device including:
the acquisition module is used for acquiring the measurement point data of each of the plurality of mathematical models; the plurality of mathematical models are machine learning models which are obtained by training in advance based on historical operation data of the supercritical unit; the measuring point data comprises a measuring point name, a measuring point identifier and a monitoring value;
the verification module is used for verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of each mathematical model;
the input module is used for inputting the monitoring value into the mathematical model in response to the fact that the plurality of measuring points pass verification, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model;
the first determining module is used for determining whether the operation data of the supercritical unit meet the preset trigger conditions of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement;
the second determining module is used for determining whether the triggering time meets the preset requirement;
the third determining module is used for determining whether the early warning result meets a preset requirement;
and the parameter adjusting module is used for adjusting parameters of the mathematical model in response to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement.
According to a third aspect of embodiments of the present application, there is provided an electronic device, including: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored by the memory to implement the method of any one of the first aspects.
According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored therein computer-executable instructions for implementing the method according to any of the first aspects when executed by a processor.
According to a fifth aspect of embodiments of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the first aspects.
The technical scheme provided by the embodiment of the application at least brings the following beneficial effects:
acquiring measuring point data of each of a plurality of mathematical models; for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model; responding to the verification of the plurality of measuring points, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model; determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement; determining whether the triggering time meets a preset requirement; determining whether the early warning result meets the preset requirement; and in response to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, parameter adjustment processing is carried out on the data model, so that the accuracy and timeliness of early warning of the supercritical unit in a plurality of professional directions through the data model are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute an undue limitation on the application.
FIG. 1 is a flow chart of a supercritical unit early warning model test method based on a big data platform in an embodiment of the application;
FIG. 2 is a block diagram of a supercritical unit early warning model test device based on a big data platform in an embodiment of the present application;
fig. 3 is a block diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
In the related art, because the thermal power plant has the characteristics of complex system, multiple devices, refined process flow and safety, workers must be careful and strict in field operation and remote operation of a centralized control room, so that the most basic normal operation of the thermal power plant can be maintained. When related systems and equipment are in failure, if an operator cannot remotely operate in the centralized control room at the first time to close the failed equipment and open corresponding protection equipment, further expansion, danger and severity of accidents are likely to be caused. The thermal power plant at present has the problems that the mechanism level judgment and early warning are carried out by dividing boundary conditions and boundary information of each device of each system, and the method is generally based on a mechanism analysis library by taking factory parameter values provided by a device manufacturer, expert experience reference values drawn by experienced technical enrichment staff and reasonable values of the prior safe operation of related units of the same type as the basis, so that different types of fault early warning judgment and division are carried out on each working condition, system and device of the thermal power plant, and fault early warning is realized. However, the thermal power plant is composed of complex system equipment, and the early warning method is single in pertinence and limited in adaptability by dividing threshold values and working conditions of single equipment.
Based on the problems, the application provides a supercritical unit early warning model testing method and device based on a big data platform, which can realize that the data of each measuring point of a plurality of mathematical models can be obtained; for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model; responding to the verification of the plurality of measuring points, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model; determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement; determining whether the triggering time meets a preset requirement; determining whether the early warning result meets the preset requirement; and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the data model. Therefore, accuracy and timeliness of early warning of the supercritical unit in multiple professional directions through the mathematical model are improved.
Fig. 1 is a flowchart of a supercritical unit early warning model testing method based on a big data platform in an embodiment of the present application.
As shown in FIG. 1, the supercritical unit early warning model test method based on the big data platform comprises the following steps:
and step 101, acquiring measurement point data of each of a plurality of mathematical models.
In this embodiment of the present application, the plurality of mathematical models are machine learning models that are trained in advance based on historical operation data of the supercritical unit.
In this embodiment of the present application, the measurement point data includes a measurement point name, a measurement point identifier, and a monitoring value.
In some embodiments of the present application, the historical operating data of the supercritical unit includes any one or more of: steam turbine type historical operation data, boiler type historical operation data, electric type historical operation data, thermal control type historical operation data and chemical type historical operation data; each type of historical operation data comprises shutdown data, starting process data and operation data; the shutdown data, the startup process data and the operation data comprise normal data and abnormal data.
As an example of one possible implementation, modeling directions are classified into 5 large categories for the characteristics of multiple systems of a power plant, including: steam turbine professional direction mathematical modeling, boiler professional direction mathematical modeling, electric professional direction mathematical modeling, thermal control professional direction mathematical modeling and chemical professional direction mathematical modeling.
Extracting operational data within the 5 modeling directions system, comprising: shutdown data, startup procedure data, operation data, these 3 broad categories, wherein:
the shutdown data includes: the method comprises the steps of stopping data during short-term overhaul of a unit, stopping data during long-term overhaul of the unit, stopping data during short-term accident state of the unit, stopping data during long-term accident state of the unit, short-term normal stopping data of the unit and long-term normal stopping data of the unit;
the start-up procedure data includes: the method comprises the steps of unit cold starting process data, unit warm starting process data, unit hot starting process data, unit extreme hot starting process data, unit cold starting process accident state data, unit warm starting process accident state data, unit hot starting process accident state data and unit extreme hot starting process accident state data;
the operation data includes: low load (0 MW-105 MW) normal operation data of a unit, high load (105.1 MW-297.5 MW) normal operation data of the unit, full load (297.6 MW-350 MW) normal operation data of the unit, low load (0 MW-105 MW) operation data of the unit in an accident state, high load (105.1 MW-297.5 MW) operation data of the unit in the accident state, and full load (297.6 MW-350 MW) operation data of the unit in the accident state.
Alternatively, the normal data and the accident situation data can be found out from the shutdown data, the startup procedure data and the operation data:
normal data: the machine set short-term maintenance shutdown data, the machine set long-term maintenance shutdown data, the machine set short-term normal shutdown data, the machine set long-term normal shutdown data, the machine set cold start process data, the machine set warm start process data, the machine set hot start process data, the machine set extremely hot start process data, the machine set low load (0 MW-105 MW) normal operation data, the machine set high load (105.1 MW-297.5 MW) normal operation data and the machine set full load (297.6 MW-350 MW) normal operation data;
data under accident conditions: the system comprises machine set short-term accident state shutdown data, machine set long-term accident state shutdown data, machine set cold state starting process accident state data, machine set warm state starting process accident state data, machine set hot state starting process accident state data, machine set extremely hot state starting process accident state data, machine set accident state low load (0 MW-105 MW) operation data, machine set accident state high load (105.1 MW-297.5 MW) operation data and machine set accident state full load (297.6 MW-350 MW) operation data.
Optionally, any one or more algorithms of a linear regression algorithm, a support vector machine algorithm, a nearest neighbor/k-neighbor algorithm, a logistic regression algorithm, a decision tree algorithm, a k-average algorithm, a random forest algorithm, a naive Bayesian algorithm, a dimension reduction algorithm and a gradient enhancement algorithm can be utilized to perform model training and learning based on normal data and data under an accident state, so that a mathematical model is learned to identify the normal operation state and the accident state of the unit, and the establishment of the mathematical model is completed.
Optionally, after the establishment of the mathematical model is completed, randomly extracting a section of data under the accident state as a verification set to test the function of the mathematical model, wherein the test success condition is that the model sends out early warning in advance as a judgment standard when the accident state is about to occur, and the model is regarded as the success of the test of the mathematical model; if the early warning is not in time, the situations of early warning missing report, early warning false report, early warning multiple report, early warning less report and the like appear, the situations are regarded as unsuccessful in the mathematical model test.
In some embodiments of the present application, step 102 includes:
step a1, based on the respective measuring point names and the measuring point identifications of the plurality of measuring points of the mathematical model, searching the respective historical data of the plurality of measuring point identifications of the mechanism model stored in the database in advance.
Alternatively, the site identification may be a plant identification system code of the site.
Step a2, in response to the historical data of the at least one measuring point not being found in the database, determining the relevant measuring point of the at least one measuring point in the plurality of measuring points based on the measuring point name of the at least one measuring point.
As one possible implementation example, the historical data of the measuring point is verified in a big data platform through the power plant identification system code of the measuring point of the corresponding mechanism model, and the correctness, the accuracy and the authenticity of the measuring point are judged. Based on the respective measuring point names and the measuring point identifications of the plurality of measuring points of the mechanism model, searching whether the respective historical data of the plurality of measuring point identifications of the mechanism model are stored in a database, responding to the historical data of at least one measuring point which is not searched in the database, indicating that the measuring point does not meet the accuracy requirement, and determining the relevant measuring point of the at least one measuring point in the plurality of measuring points based on the measuring point name of the at least one measuring point.
Optionally, keywords and keywords 'paraphraseology in the measurement point name may be determined according to the measurement point name, and the related measurement point of the measurement point may be found based on the keywords, keywords and keywords' paraphraseology, where the attribute of the detection value of the related measurement point is consistent with the attribute of the detection value of the measurement point. It can be understood that, in the data transmission process, due to unstable network and other reasons, incomplete or distorted data transmission may be caused, so that verification of the power plant identification system code of the measuring point is required, the plurality of measuring points may monitor the same value, and only the names of the measuring points are slightly different, so that the integrity of the data can be verified through the related measuring points.
In an embodiment of the present application, the at least one measurement point is determined to be validated in response to the historical data of the at least one measurement point being found in the database.
And a3, searching historical data of related measuring points stored in a database in advance.
And a4, determining that at least one measuring point fails to pass verification in response to the fact that the historical data of the related measuring point stored in the database is not found, performing parameter adjustment processing on the at least one measuring point respectively, and repeatedly executing the step of finding the historical data of each of a plurality of measuring point identifiers of the mechanism model stored in the database.
As one possible implementation example, in response to not finding the historical data of the relevant measurement points stored in advance in the database, determining that at least one measurement point is not verified, performing parameter tuning processing on the at least one measurement point respectively, and repeating the step of finding the historical data of each of the plurality of measurement point identifiers of the mechanism model stored in advance in the database.
And step 103, responding to the fact that the plurality of measuring points pass through verification, inputting the monitoring value into the mathematical model, and obtaining the early warning result output by the mathematical model and the triggering time of the mathematical model.
In some embodiments of the present application, step 104 includes:
and b1, determining at least one preset triggering condition of the mathematical model based on the mathematical model.
It can be understood that as a plurality of mathematical models belong to different professional directions of the power plant, corresponding model triggering rules need to be respectively formulated, so that the models can be used more flexibly, more sensitively and more conveniently.
For example, the model triggering rules of the coal mill body blocking and grinding model of the coal mill body of the coal mill system and the coal mill outlet powder pipe blocking and grinding model of the coal mill system can be that the coal mill is operated, the coal feeder is operated and the coal feeding amount is normal; the model triggering rule of the lubricating oil system oil tank leakage model and the high-pressure fire-resistant oil system oil tank leakage model can be that the oil pump operates, the oil level of the oil tank is normal, and the pressure of an oil way main pipe is normal; the model triggering rule of the high-pressure heater leakage model of the high-pressure adding system can be that the liquid level of the high-pressure heater is normal, the pressure and the flow of a main pipe are normal; the model triggering rule of the reverse osmosis system first section reverse osmosis sewage blocking model and the reverse osmosis system second section reverse osmosis sewage blocking model can be that the total water production amount, the first section reverse osmosis differential pressure and the second section reverse osmosis differential pressure are normal.
And b2, acquiring operation data of the supercritical unit at the triggering time.
And b3, acquiring operation information corresponding to at least one preset trigger condition respectively based on the operation data.
And b4, determining whether each piece of operation information meets the corresponding preset triggering condition.
It can be understood that the operation data of the supercritical unit at the trigger time is acquired, the operation information corresponding to at least one preset trigger condition is acquired based on the operation data, and whether the current operation state of the supercritical unit meets the trigger condition of the mathematical model is determined based on the operation information.
And b5, determining that the first intermediate result is that the triggering time meets the preset requirement in response to each piece of operation information meeting the corresponding preset triggering condition.
And b6, determining that the first intermediate result is that the triggering time does not meet the preset requirement in response to at least one piece of operation information not meeting the corresponding preset triggering conditions.
In some embodiments of the present application, step 105 includes:
step c1, acquiring a preset trigger period of the mathematical model.
And c2, comparing the preset trigger period with the trigger time to obtain a first comparison result.
And c3, determining that the triggering time does not meet the preset requirement according to the fact that the triggering time does not fall into the preset triggering period as a result of the first comparison.
As an example of one possible implementation, since each mathematical model differs from one accident determination period to another, the trigger period and the trigger rule may be divided into different categories.
For example, the preset trigger period of the mathematical model may include:
short-term rapid triggering accident early warning, wherein the set time period is within 10 seconds;
the short-term gradual rising triggers accident early warning, and the set time period is within 10 seconds to 10 minutes;
the medium-term uniform change triggers accident early warning, and the set time period is within 10 minutes to 60 minutes;
the long-term slow change triggers accident early warning, and the set time period is within 60 minutes to 600 minutes.
For example, the coal mill body of the pulverizing system is blocked, and the coal mill outlet powder pipe of the pulverizing system is blocked, which belongs to short-term rapid triggering accident early warning, the accident situation is particularly rapid, and a shorter time is required to be set in a model judging period;
for example, the leakage of the oil tank of the lubricating oil system and the leakage of the oil tank of the high-pressure fire-resistant oil system belong to short-term gradual rising triggering accident early warning, the accident situation of the early warning gradually rises in a short time, and a shorter time is required to be set in a model judging period;
for example, the leakage of a high-pressure heater of a high-pressure system belongs to medium-term uniform change triggering accident early warning, the accident situation of the high-pressure heater gradually rises in a period of time, and a period of time is required to be set in a model judging period;
for example, the first section reverse osmosis sewage plug of the reverse osmosis system and the second section reverse osmosis sewage plug of the reverse osmosis system belong to long-term slow change triggering accident early warning, the accident situation of the system can gradually rise in a long time, and a long time is required to be set in a model judging period.
And step 106, determining whether the early warning result meets the preset requirement.
In some embodiments of the present application, step 106 includes:
and d1, acquiring an actual early warning result corresponding to the measurement point data.
And d2, comparing the early warning result with the actual early warning result to obtain a second comparison result.
And d3, determining that the early warning result does not meet the preset requirement in response to the second comparison result that the early warning result is not consistent with the actual early warning result.
And step 107, performing parameter adjustment processing on the data model in response to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirements.
For example, taking the leakage early warning of the high-pressure fire-resistant oil system in the gas turbine industry as an example, using the oil level of the high-pressure fire-resistant oil tank, the pressure of a main pipe and the operation data of the oil pump as training data, dividing the training data into shutdown data, starting process data and operation data, using the data in the 3 stages as training set data and verification set data, constructing a model by using a convolutional neural network algorithm, and finally performing model verification. And then deploying the high-pressure fire-resistant oil system leakage early-warning model operator block to a big data platform, wherein the input measuring points on the platform need to be included: and (3) checking the oil level of the high-pressure fire-resistant oil tank, the pressure of the main pipe, the operation of the oil pump and the like, setting a judging period to be within 10 seconds to 10 minutes, setting a model triggering rule to be that the oil pump is operated, the oil level of the oil tank is normal, the pressure of the main pipe of the oil way is normal, and finally testing and verifying the operator blocks of the data model by utilizing fault data.
According to the supercritical unit early warning model test method based on the big data platform, the data of each measuring point of a plurality of mathematical models is obtained; for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model; responding to the verification of the plurality of measuring points, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model; determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement; determining whether the triggering time meets a preset requirement; determining whether the early warning result meets the preset requirement; and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the data model. Therefore, accuracy and timeliness of early warning of the supercritical unit in multiple professional directions through the mathematical model are improved.
Fig. 2 is a flowchart of a supercritical unit early warning model testing device based on a big data platform in an embodiment of the present application.
As shown in FIG. 2, the supercritical unit early warning model testing device based on the big data platform comprises:
an acquisition module 201, configured to acquire measurement point data of each of a plurality of mathematical models; the plurality of mathematical models are machine learning models which are obtained by training in advance based on historical operation data of the supercritical unit; the measuring point data comprises a measuring point name, a measuring point identifier and a monitoring value;
the verification module 202 is configured to perform verification processing on each of the plurality of measurement points based on the respective measurement point names of the plurality of measurement points of the mathematical model for each of the mathematical models;
the input module 203 is configured to input the monitoring value into the mathematical model in response to the plurality of measurement points passing the verification, and obtain an early warning result output by the mathematical model and a triggering time of the mathematical model;
a first determining module 204, configured to determine whether the operation data of the supercritical unit meets a preset trigger condition of the mathematical model at the trigger time, obtain a first intermediate result, and determine whether the first intermediate result meets a preset requirement;
a second determining module 205, configured to determine whether the triggering time meets a preset requirement;
a third determining module 206, configured to determine whether the early warning result meets a preset requirement;
and the parameter tuning module 207 is configured to perform parameter tuning processing on the data model in response to any one or more of the first intermediate result, the trigger time and the early warning result not meeting a preset requirement.
According to the supercritical unit early warning model testing device based on the big data platform, the measuring point data of each of a plurality of mathematical models are obtained; for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model; responding to the verification of the plurality of measuring points, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model; determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement; determining whether the triggering time meets a preset requirement; determining whether the early warning result meets the preset requirement; and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the data model. Therefore, accuracy and timeliness of early warning of the supercritical unit in multiple professional directions through the mathematical model are improved.
Fig. 3 is a block diagram of an electronic device in an embodiment of the present application. As shown in fig. 3, the electronic device may include: a transceiver 31, a processor 32, a memory 33.
Processor 32 executes the computer-executable instructions stored in memory, causing processor 32 to perform the aspects of the embodiments described above. The processor 32 may be a general-purpose processor including a central processing unit CPU, a network processor (network processor, NP), etc.; but may also be a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.
The memory 33 is connected to the processor 32 via a system bus and communicates with each other, the memory 33 being arranged to store computer program instructions.
The transceiver 31 may be used to obtain a task to be run and configuration information of the task to be run.
The system bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The system bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The transceiver is used to enable communication between the database access device and other computers (e.g., clients, read-write libraries, and read-only libraries). The memory may include random access memory (random access memory, RAM) and may also include non-volatile memory (non-volatile memory).
The electronic device provided in the embodiment of the present application may be a terminal device in the above embodiment.
The embodiment of the application also provides a chip for running the instruction, which is used for executing the technical scheme of the message processing method in the embodiment.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores computer instructions, and when the computer instructions run on a computer, the computer is caused to execute the technical scheme of the message processing method of the embodiment.
The embodiment of the application also provides a computer program product, which comprises a computer program stored in a computer readable storage medium, wherein at least one processor can read the computer program from the computer readable storage medium, and the technical scheme of the message processing method in the embodiment can be realized when the at least one processor executes the computer program.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A supercritical unit early warning model test method based on a big data platform is characterized by comprising the following steps:
acquiring measurement point data of each of a plurality of mathematical models; the plurality of mathematical models are machine learning models which are obtained by training in advance based on historical operation data of the supercritical unit; the measuring point data comprises a measuring point name, a measuring point identifier and a monitoring value;
for each mathematical model, respectively verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of the mathematical model;
responding to the fact that all the measuring points pass verification, inputting the monitoring value into the mathematical model, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model;
determining whether the operation data of the supercritical unit meets the preset trigger condition of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement;
determining whether the triggering time meets a preset requirement;
determining whether the early warning result meets a preset requirement;
and responding to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement, and performing parameter adjustment processing on the mathematical model.
2. The method according to claim 1, wherein determining whether the operation data of the supercritical unit at the trigger time satisfies the preset trigger condition of the mathematical model, to obtain the first intermediate result, includes:
determining at least one preset trigger condition of the mathematical model based on the mathematical model;
acquiring operation data of the supercritical unit at the trigger time;
acquiring operation information corresponding to each of the at least one preset trigger condition based on the operation data;
determining whether each piece of operation information meets respective corresponding preset triggering conditions;
responding to each piece of operation information to meet respective corresponding preset triggering conditions, and determining that the triggering time meets preset requirements as the first intermediate result;
and responding to at least one piece of operation information to fail to meet the corresponding preset triggering conditions, and determining that the triggering time fails to meet the preset requirement as the first intermediate result.
3. The method of claim 1, wherein the determining whether the trigger time meets a preset requirement comprises:
acquiring a preset trigger period of the mathematical model;
comparing the preset trigger period with the trigger time to obtain a first comparison result;
and responding to the first comparison result that the trigger time does not fall into the preset trigger period, and determining that the trigger time does not meet a preset requirement.
4. The method according to claim 1, wherein the determining whether the pre-warning result meets a preset requirement includes:
acquiring an actual early warning result corresponding to the measuring point data;
comparing the early warning result with the actual early warning result to obtain a second comparison result;
and responding to the second comparison result that the early warning result is not consistent with the actual early warning result, and determining that the early warning result does not meet a preset requirement.
5. The method according to claim 1, wherein the verifying the respective station names of the plurality of stations based on the mathematical model includes:
based on the respective measuring point names and the measuring point identifications of the plurality of measuring points of the mathematical model, searching the respective historical data of the plurality of measuring point identifications of the mechanical model stored in a database in advance;
determining, in response to not finding historical data for at least one measurement point in the database, a relevant measurement point for the at least one measurement point among the plurality of measurement points based on a measurement point name of the at least one measurement point;
searching historical data of the related measuring points stored in the database in advance;
and in response to the fact that the historical data of the related measuring points stored in the database in advance are not found, determining that the at least one measuring point is not verified, respectively performing parameter adjustment processing on the at least one measuring point, and repeatedly executing the steps of searching the historical data of each of a plurality of measuring point identifiers of the mechanism model stored in the database in advance.
6. The method of claim 1, wherein the historical operating data of the supercritical unit includes any one or more of: steam turbine type historical operation data, boiler type historical operation data, electric type historical operation data, thermal control type historical operation data and chemical type historical operation data; each type of historical operation data comprises shutdown data, starting process data and operation data; the shutdown data, the starting process data and the operation data comprise normal data and abnormal data.
7. The utility model provides a supercritical unit early warning model testing arrangement based on big data platform which characterized in that, the device includes:
the acquisition module is used for acquiring the measurement point data of each of the plurality of mathematical models; the plurality of mathematical models are machine learning models which are obtained by training in advance based on historical operation data of the supercritical unit; the measuring point data comprises a measuring point name, a measuring point identifier and a monitoring value;
the verification module is used for verifying the plurality of measuring points based on the respective measuring point names of the plurality of measuring points of each mathematical model;
the input module is used for inputting the monitoring value into the mathematical model in response to the fact that the plurality of measuring points pass verification, and acquiring an early warning result output by the mathematical model and the triggering time of the mathematical model;
the first determining module is used for determining whether the operation data of the supercritical unit meet the preset trigger conditions of the mathematical model under the trigger time to obtain a first intermediate result, and determining whether the first intermediate result meets the preset requirement;
the second determining module is used for determining whether the triggering time meets the preset requirement;
the third determining module is used for determining whether the early warning result meets a preset requirement;
and the parameter adjusting module is used for adjusting parameters of the mathematical model in response to any one or more of the first intermediate result, the triggering time and the early warning result not meeting the preset requirement.
8. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-6.
9. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310071732.9A CN116302957A (en) | 2023-01-18 | 2023-01-18 | Supercritical unit early warning model test method and device based on big data platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310071732.9A CN116302957A (en) | 2023-01-18 | 2023-01-18 | Supercritical unit early warning model test method and device based on big data platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116302957A true CN116302957A (en) | 2023-06-23 |
Family
ID=86798664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310071732.9A Pending CN116302957A (en) | 2023-01-18 | 2023-01-18 | Supercritical unit early warning model test method and device based on big data platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116302957A (en) |
-
2023
- 2023-01-18 CN CN202310071732.9A patent/CN116302957A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832896A (en) | A kind of electric power factory equipment soft fault method for early warning and device | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| Borchersen et al. | Model‐based fault detection for generator cooling system in wind turbines using SCADA data | |
| JP2018190245A (en) | Facility equipment abnormality diagnosis system | |
| CN111597223A (en) | Fault early warning processing method, device and system | |
| CN110391840B (en) | Method and system for judging abnormality of telemetry parameters of sun synchronous orbit satellite | |
| CN111624986A (en) | Case base-based fault diagnosis method and system | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN111929579B (en) | Generator online fault diagnosis method and device and computer device | |
| CN111581191B (en) | Nuclear safety data verification method, device, computer equipment and storage medium | |
| CN115018220A (en) | Household appliance fault prediction method and system based on knowledge graph | |
| Di Maio et al. | Risk‐based clustering for near misses identification in integrated deterministic and probabilistic safety analysis | |
| CN113935443B (en) | Heterogeneous equipment multi-domain joint fault prediction method, device, terminal and storage medium | |
| CN118425863A (en) | Sensor data anomaly detection method, device, equipment and storage medium | |
| CN111312420A (en) | Fault diagnosis method and device | |
| CN116490933A (en) | Device and method for tracking abnormal state judgment basis by using neural network model | |
| CN116302957A (en) | Supercritical unit early warning model test method and device based on big data platform | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| CN114576102A (en) | Method, device and equipment for predicting bearing state of wind turbine generator and storage medium | |
| Costello et al. | Self-tuning routine alarm analysis of vibration signals in steam turbine generators | |
| CN112737120A (en) | Generation method and device of regional power grid control report and computer equipment | |
| KR20200087302A (en) | Method for risk prediction based on pipeline pressure data | |
| CN115167371B (en) | Reverse verification-based thermal protection fault diagnosis method and system and self-checking method | |
| CN118297580B (en) | Petroleum equipment maintenance management method, system and storage medium based on big data | |
| CN118116165A (en) | HAZOP-based natural gas automatic separate-transmission alarm method and system |
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 |