CN113536673A - Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling - Google Patents
Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling Download PDFInfo
- Publication number
- CN113536673A CN113536673A CN202110788659.8A CN202110788659A CN113536673A CN 113536673 A CN113536673 A CN 113536673A CN 202110788659 A CN202110788659 A CN 202110788659A CN 113536673 A CN113536673 A CN 113536673A
- Authority
- CN
- China
- Prior art keywords
- simulation
- algorithm
- subsystem
- fault
- evaluation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012423 maintenance Methods 0.000 title claims abstract description 30
- 238000005094 computer simulation Methods 0.000 title claims abstract description 25
- 238000004088 simulation Methods 0.000 claims abstract description 58
- 238000011156 evaluation Methods 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 8
- 230000008676 import Effects 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an algorithm evaluation optimization method for an operation and maintenance system through simulation modeling, which well simulates the whole operation and maintenance embodiment by analyzing the historical input and output logs of the subsystem, simulating the subsystem through an algorithm model and connecting the subsystems. The simulator built in this way can be completely generated by a program, and the simulator does not need to know the internal structure of the system. The fault simulation is also to simulate the occurrence of an actual fault by adjusting input parameters and predicting the corresponding output. According to the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling, due to low-cost simulation and rapid fault introduction, various scenes can be tested quickly when a fault root algorithm is researched, and the method has the advantages of low simulation cost and capability of rapid testing.
Description
Technical Field
The invention relates to the technical field of simulation modeling, and can establish a model of a system at low cost by means of a digital simulation modeling technology and utilize the simulation model to evaluate and optimize various algorithms of an operation and maintenance system.
Background
The fault discovery of the current operation and maintenance system basically belongs to a post analysis type. Once the system fails, the input and output indexes of each component and the related logs are used for finding out the abnormity, and then the problem root is found out. After the intelligent operation and maintenance algorithm is introduced, the fault root cause analysis becomes an important application of the algorithm. However, utility evaluation of an algorithm is difficult. Many times, the system can not be predicted when the system fails, and the evaluation is time-consuming and labor-consuming after the system simply waits for the failure to occur. Meanwhile, the effect of the algorithm is strongly correlated with the parameter setting, and how to quickly find the optimal parameter is also a challenge of popularizing the algorithm.
In the algorithm evaluation process, a common method is to establish a physical simulation system. The method comprises the steps of building a test environment which is the same as or similar to an actual combat system, deploying an algorithm, then intentionally carrying out fault occurrence (such as power failure) on a partial molecular system, finding out a fault analysis report by the algorithm, and comparing the fault analysis report with known fault points to judge the effectiveness of the algorithm. By trial and error, the optimal values of the algorithm parameters can be well found. The existing algorithm evaluation process has the following disadvantages: 1. the simulation cost is high, and the software and hardware cost is very high when the environment similar to actual combat is built. 2. The means for simulating failures is limited, and many failures, such as low probability of damage (read-write failure rate increase due to disk aging), are difficult to simulate. 3. Both environment building and fault simulation require a great deal of manual intervention, and are time-consuming and labor-consuming.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a simulation model which is low in cost and can be rapidly put into use, and various algorithm evaluation optimization methods for testing an operation and maintenance system.
The technical scheme of the invention is as follows:
a simulation modeling operation and maintenance system algorithm evaluation optimization method comprises the following steps:
s1, analyzing the system to be simulated, and disassembling the system to a plurality of subsystems;
s2, collecting and recording the logs of each subsystem;
s3, importing the input log and the output log of the subsystem into an algorithm model, and training the algorithm to obtain a subsystem model;
s4, connecting the subsystem models corresponding to the actual system to obtain the digital simulation of the system;
and S5, performing simulation evaluation on the digital simulation system.
As a preferable technical solution, when "importing the input and output logs of the subsystem into the algorithm model" in the step S3, the input and output indexes and logs of the subsystem are input and output indexes and logs in a period of time.
As a preferable technical solution, "connect subsystem models" in step S4 is to specifically import the output of one subsystem into another subsystem as input according to the interaction situation of each component in the actual system.
As a preferred technical solution, after the step S4 obtains the digital simulation of the system, the method further includes the following steps: and continuously collecting and analyzing indexes and logs of each node of the actual system, and continuously optimizing the simulation model.
As a preferred technical solution, the step S5 of "performing simulation evaluation on the digital simulation system" includes fault simulation, and the fault simulation is implemented by adjusting parameters input to the subsystem.
As a further preferable technical solution, the parameter adjustment is to introduce an erroneous input, and simulate a fault scenario.
As a further preferable technical solution, the step S5 of "performing simulation evaluation on the digital simulation system" further includes performing fault simulation on the actual subsystem, collecting a generated fault log, and training a fault model.
As a preferred technical solution, the algorithm model in step S3 is a deep learning model.
According to the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling, the logs of historical input and output of the subsystem are analyzed, the subsystem is simulated through an algorithm model, and then all the subsystems are connected, so that the whole operation and maintenance embodiment is well simulated. The simulator built in this way can be completely generated by a program, and the simulator does not need to know the internal structure of the system. The fault simulation is also to simulate the occurrence of an actual fault by adjusting input parameters and predicting the corresponding output. According to the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling, due to low-cost simulation and rapid fault introduction, various scenes can be tested quickly when a fault root algorithm is researched, and the method has the advantages of low simulation cost and capability of rapid testing.
Drawings
FIG. 1 is a flow chart of a specific embodiment of the method for evaluating and optimizing an operation and maintenance system algorithm through simulation modeling.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, and "a" and "an" generally include at least two, but do not exclude at least one, unless the context clearly dictates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a good or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such good or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a commodity or system that includes the element.
As shown in fig. 1, a flow chart of a specific embodiment of the method for evaluating and optimizing an operation and maintenance system algorithm through simulation modeling of the present invention is shown, and the method for evaluating and optimizing an operation and maintenance system algorithm through simulation modeling of the present invention includes the following steps:
s1, analyzing the system to be simulated, and disassembling the system to a plurality of subsystems;
s2, collecting, recording and storing the input and output logs of each subsystem;
s3, importing the input logs and the output logs of the subsystem into an algorithm model, and training the algorithm to obtain a subsystem model;
s4, connecting the subsystem models corresponding to the actual system to obtain the digital simulation of the system;
and S5, performing simulation evaluation on the digital simulation system.
Specifically, in this embodiment, the algorithm model in step S3 is a deep learning model. In the step S3, "import log of input and output of the subsystem" into the algorithm model, the log of input and output of the subsystem is a log of input and output for a period of time.
The step S4 of "connecting the subsystem models" is to import the output of one subsystem into another subsystem as input according to the interaction of each component in the actual system.
After the step S4 obtains the digital simulation of the system, the method further includes the following steps: and continuously collecting and analyzing logs of all nodes of the actual system, and continuously optimizing the simulation model.
The step S5, "evaluation of simulation of digital simulation system" includes fault simulation, which is realized by adjusting parameters input to the subsystem. The parameters are adjusted to import erroneous inputs, simulating a fault scenario. The step S5 of "performing simulation evaluation on the digital simulation system" further includes collecting a generated fault log after performing fault simulation on the actual subsystem, and training a fault model. For fault simulation, fault simulation is achieved by adjusting subsystem input parameters. A fault scenario can be simulated by deliberately introducing erroneous inputs. Or carrying out fault simulation on the actual subsystem to generate a fault log and training a fault model. And switching to a fault model when fault simulation needs to be carried out later.
The method for evaluating and optimizing the operation and maintenance system algorithm by simulation modeling does not need to pay attention to the prior details of the system, and the system implementation is unknown in many cases; only the inputs and outputs of the system need to be collected continuously, assuming that both are causal. Based on the assumption, the simulator of the method for evaluating and optimizing the operation and maintenance system algorithm by simulation modeling is an algorithm model which can obtain the same or similar output under the same input condition. Once model training is completed, the cost of actual operation is much lower than that of traditional physical simulation. The generation of the simulated fault is easier. The fault scene of a subsystem can be simulated by adjusting the corresponding output result (such as an error log and the like) in the simulator. Even the simultaneous failure of a plurality of subsystems can be simply simulated, which is difficult to realize by a plurality of simulations based on actual systems. Due to low-cost simulation and rapid fault introduction, various scenes can be tested quickly when a fault root algorithm is researched. If the algorithm effect is found to be poor, the algorithm parameters can be quickly adjusted to carry out a new round of simulation. The key of the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling in the embodiment is to perform deep learning algorithm-based simulation on each subsystem. In practical applications, if the subsystem is deeply known, other algorithms can be used to simulate the subsystem, and the method is not limited to the deep learning algorithm simulation in this embodiment, and all of them fall within the protection scope of claim 1.
According to the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling, the logs of historical input and output of the subsystem are analyzed, the subsystem is simulated through an algorithm model, and then all the subsystems are connected, so that the whole operation and maintenance embodiment is well simulated. The simulator built in this way can be completely generated by a program, and the simulator does not need to know the internal structure of the system. The fault simulation is also to simulate the occurrence of an actual fault by adjusting input parameters and predicting the corresponding output. According to the method for evaluating and optimizing the operation and maintenance system algorithm through simulation modeling, due to low-cost simulation and rapid fault introduction, various scenes can be tested quickly when a fault root algorithm is researched, and the method has the advantages of low simulation cost and capability of rapid testing.
In summary, the embodiments of the present invention are merely exemplary and should not be construed as limiting the scope of the invention. All equivalent changes and modifications made according to the content of the claims of the present invention should fall within the technical scope of the present invention.
Claims (8)
1. A simulation modeling operation and maintenance system algorithm evaluation optimization method is characterized by comprising the following steps: the method comprises the following steps:
s1, analyzing the system to be simulated, and disassembling the system to a plurality of subsystems;
s2, collecting, recording and storing the input and output logs of each subsystem;
s3, importing the input logs and the output logs of the subsystem into an algorithm model, and training the algorithm model to obtain a subsystem model;
s4, connecting the subsystem models corresponding to the actual system to obtain the digital simulation of the system;
and S5, performing simulation evaluation on the digital simulation system.
2. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 1, wherein the method comprises the following steps: in the step S3, "import log of input and output of the subsystem" into the algorithm model, the log of input and output of the subsystem is a log of input and output for a period of time.
3. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 1, wherein the method comprises the following steps: the step S4 of "connecting the subsystem models" is to import the output of one subsystem into another subsystem as input according to the interaction of each component in the actual system.
4. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 1, wherein the method comprises the following steps: after the step S4 obtains the digital simulation of the system, the method further includes the following steps: and continuously collecting and analyzing logs of all nodes of the actual system, and continuously optimizing the simulation model.
5. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 1, wherein the method comprises the following steps: the step S5, "evaluation of simulation of digital simulation system" includes fault simulation, which is realized by adjusting parameters input to the subsystem.
6. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 5, wherein the method comprises the following steps: the parameters are adjusted to import erroneous inputs, simulating a fault scenario.
7. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 5, wherein the method comprises the following steps: the step S5 of "performing simulation evaluation on the digital simulation system" further includes collecting a generated fault log after performing fault simulation on the actual subsystem, and training a fault model.
8. The method for optimizing the evaluation of the operation and maintenance system algorithm by simulation modeling according to claim 1, wherein the method comprises the following steps: the algorithm model in the step S3 is a deep learning model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788659.8A CN113536673A (en) | 2021-07-13 | 2021-07-13 | Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788659.8A CN113536673A (en) | 2021-07-13 | 2021-07-13 | Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113536673A true CN113536673A (en) | 2021-10-22 |
Family
ID=78098797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110788659.8A Pending CN113536673A (en) | 2021-07-13 | 2021-07-13 | Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536673A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117038064A (en) * | 2023-10-07 | 2023-11-10 | 之江实验室 | Evaluation method, device, storage medium and equipment for auxiliary analysis algorithm |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102354298A (en) * | 2011-07-27 | 2012-02-15 | 哈尔滨工业大学 | Software testing automation framework (STAF)-based fault injection automation testing platform and method for high-end fault-tolerant computer |
| CN103090898A (en) * | 2011-10-31 | 2013-05-08 | 北京临近空间飞行器系统工程研究所 | Flight data recording equipment ground integrated test system |
| CN104155596A (en) * | 2014-08-12 | 2014-11-19 | 北京航空航天大学 | Artificial circuit fault diagnosis system based on random forest |
| CN109541353A (en) * | 2018-11-30 | 2019-03-29 | 广州供电局有限公司 | Power distribution automation detection system |
| CN112345276A (en) * | 2020-11-10 | 2021-02-09 | 北京交通大学 | State evaluation and prediction system for key components of medium-speed maglev train |
-
2021
- 2021-07-13 CN CN202110788659.8A patent/CN113536673A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102354298A (en) * | 2011-07-27 | 2012-02-15 | 哈尔滨工业大学 | Software testing automation framework (STAF)-based fault injection automation testing platform and method for high-end fault-tolerant computer |
| CN103090898A (en) * | 2011-10-31 | 2013-05-08 | 北京临近空间飞行器系统工程研究所 | Flight data recording equipment ground integrated test system |
| CN104155596A (en) * | 2014-08-12 | 2014-11-19 | 北京航空航天大学 | Artificial circuit fault diagnosis system based on random forest |
| CN109541353A (en) * | 2018-11-30 | 2019-03-29 | 广州供电局有限公司 | Power distribution automation detection system |
| CN112345276A (en) * | 2020-11-10 | 2021-02-09 | 北京交通大学 | State evaluation and prediction system for key components of medium-speed maglev train |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117038064A (en) * | 2023-10-07 | 2023-11-10 | 之江实验室 | Evaluation method, device, storage medium and equipment for auxiliary analysis algorithm |
| CN117038064B (en) * | 2023-10-07 | 2024-01-09 | 之江实验室 | Evaluation method, device, storage medium and equipment for auxiliary analysis algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108809948B (en) | Abnormal network connection detection method based on deep learning | |
| CN113094975B (en) | Smart grid node vulnerability assessment method, smart grid node vulnerability assessment system, smart grid node vulnerability assessment device and storage medium | |
| CN116401532B (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| CN115687115A (en) | Automatic testing method and system for mobile application program | |
| CN113536673A (en) | Method for evaluating and optimizing operation and maintenance system algorithm through simulation modeling | |
| CN117526561A (en) | Digital twinning-based transformer substation equipment abnormality monitoring and early warning method and system | |
| CN108805419B (en) | Power grid node importance calculation method based on network embedding and support vector regression | |
| CN118035100A (en) | Large model enhanced test design intelligent design method | |
| CN112860587B (en) | UI automatic test method and device | |
| CN117665437A (en) | Feeder automation closed loop test method and system based on movable mode simulation | |
| CN111127242A (en) | Power system reliability dynamic real-time assessment method based on small sample data | |
| CN108233356B (en) | Consistency evaluation method and evaluation platform for photovoltaic inverter controller | |
| Fuentes Jr et al. | Leak detection in water distribution networks via pressure analysis using a machine learning ensemble | |
| CN108959721B (en) | Method for calculating reliability of long-span bridge member under action of windmill load | |
| KR101335657B1 (en) | System and method using realtime simulator and programmed system switching for the validation of large-scaled dcs | |
| CN113206712B (en) | Software radio conformance testing method and system | |
| CN115455764A (en) | Multi-node damage diagnosis method for frame structure | |
| CN114782788A (en) | Industrial fault diagnosis method and system based on priori knowledge | |
| CN118096117B (en) | Digital twinning-based power equipment fault detection method and system | |
| CN111044808A (en) | Power utilization information acquisition system operation and maintenance quality reliability assessment system and method | |
| CN117130942B (en) | Simulation test method for simulating domestic production environment | |
| CN115473788B (en) | Storage alarm test method, device, equipment and storage medium | |
| CN104407972B (en) | A kind of embedded software power consumption method of testing based on improvement neutral net | |
| CN117973285B (en) | Depth test method and device for abnormality of rear silicon circuit and computing equipment | |
| CN118519424B (en) | Fault detection method and system for papermaking clothing production control 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 |