CN112950024A - Decision-making method based on hydropower station emergency command, storage medium and electronic equipment - Google Patents
Decision-making method based on hydropower station emergency command, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112950024A CN112950024A CN202110229210.8A CN202110229210A CN112950024A CN 112950024 A CN112950024 A CN 112950024A CN 202110229210 A CN202110229210 A CN 202110229210A CN 112950024 A CN112950024 A CN 112950024A
- Authority
- CN
- China
- Prior art keywords
- emergency
- factors
- prediction
- influence
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The application provides a decision-making method, a storage medium and electronic equipment based on hydropower station emergency command, wherein the method comprises the following steps: inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of various types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event; inputting the predicted value of the impact factor into an emergency risk grade prediction model to obtain a predicted value of the emergency risk grade; and performing coupling prediction based on the risk grade prediction value of the emergency event, and determining an auxiliary decision according to the coupling prediction result so as to improve the emergency command capability of the hydropower station.
Description
Technical Field
The application relates to the technical field of emergency management of hydropower stations, in particular to a decision-making method based on emergency command of hydropower stations, a storage medium and electronic equipment.
Background
The hydropower station faces the threats of various disasters such as weather, geology, equipment, hydrology and the like in the daily operation process, when the disasters occur, field on-site on-duty personnel are required to perform emergency treatment immediately according to an emergency plan, and at the moment, the emergency command has the characteristics of more personnel, more equipment, time tightness, high process complexity and the like, and has greater challenge on correct response of the on-duty personnel; in the actual process, when an emergency event occurs, a plurality of emergency plans are often triggered to be started simultaneously, higher requirements are provided for emergency disposal levels, rapid allocation and deployment of a plurality of emergency disposal resources are required to be realized in a short time, the emergency disposal resources are seriously dependent on the personal skill level of emergency commanders, and great uncertainty is brought to disposal effects. Under the conditions, emergency treatment failure and accident scope expansion are often caused, and great threats are brought to the safety and stability of the power station and the equipment property safety. Therefore, research related to decision assistance based on hydropower station production emergency command is urgently developed.
Disclosure of Invention
The application aims to provide a decision-making method based on hydropower station emergency command, a storage medium and electronic equipment, which are used for overcoming the technical defects of low emergency response speed and low emergency efficiency in the prior art.
In a first aspect, an embodiment of the present application provides a decision method based on emergency command of a hydropower station, where the method includes: inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of various types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event; inputting the predicted value of the impact factor into an emergency risk grade prediction model to obtain a predicted value of the emergency risk grade; and performing coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result.
With reference to the first aspect, in a first possible implementation manner, inputting a plurality of impact factors obtained based on a plurality of sets of emergency data into an impact factor prediction model, and obtaining corresponding impact factor prediction values includes: obtaining a correlation parameter of the influence factors and a characteristic parameter of each influence factor based on the correlation among the influence factors and the autocorrelation of each influence factor; simultaneously inputting the correlation parameters and the characteristic parameters of the influence factors into a plurality of machine learning regression models and a plurality of time series models for prediction, wherein at least two machine learning regression models are different in type, and at least two time series models are different in type; establishing a prediction result evaluation model, evaluating the prediction results of each machine learning regression model and each time series model, and selecting an optimal prediction model; and determining the optimal prediction model output value as the influence factor predicted values corresponding to the plurality of influence factors respectively.
With reference to the first aspect, in a second possible implementation manner, inputting the predicted value of the impact factor into the emergency risk level prediction model to obtain the predicted value of the emergency risk level includes: establishing an emergency event prediction model based on a plurality of machine learning classification algorithm models, and training the emergency event prediction model by using all influence factors corresponding to a plurality of emergency events, a main control factor corresponding to each emergency event and the emergency event risk grade of each emergency event to obtain an emergency event risk grade prediction model, wherein the emergency event risk grade prediction model comprises a plurality of classification prediction models; inputting the predicted values of the influence factors corresponding to the plurality of influence factors to an emergency event risk level prediction model to obtain a plurality of classification prediction results; evaluating various prediction classification results, and determining an optimal classification prediction model from the emergency risk level prediction models; and determining the output value of the optimal classification prediction model as the emergency event risk grade prediction values corresponding to the multiple influence factors respectively.
With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner, the inputting the impact factor predicted value to an emergency risk level prediction model to obtain an emergency risk level predicted value further includes: and judging whether the influence factors contain important marks or not, if so, determining the emergency events corresponding to the influence factors according to the important marks, and determining the influence factors containing the important marks as the main control factors of the emergency events corresponding to the influence factors.
With reference to the first possible implementation manner of the first aspect, in a fourth possible implementation manner, performing a coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result includes: establishing a multi-emergency risk coupling prediction model based on the predicted value of the risk grades of the multiple emergency events, the correlation parameters of the multiple influence factors and a KSIM prediction method; and determining emergency personnel and emergency treatment plans for treating the emergency according to the coupling prediction result of the multi-emergency risk coupling prediction model.
With reference to the first aspect, in a fifth possible implementation manner, before inputting multiple impact factors obtained based on several sets of emergency data into an impact factor prediction model and obtaining corresponding impact factor prediction values, the method further includes: acquiring all emergency data related to hydropower station emergency command within a preset time, wherein the emergency data comprises characteristic quantity data, emergency command processing data and meteorological data; preprocessing all emergency data to obtain a plurality of groups of emergency data with unified formats, wherein the preprocessing comprises the following steps: deleting filtering invalid data, filling missing values in emergency data and performing data normalization processing; and acquiring multiple emergency disaster-causing factors related to the hydropower station emergency command based on a plurality of groups of emergency data in a unified format.
With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation manner, after obtaining multiple emergency disaster-causing factors related to emergency command of the hydropower station based on multiple sets of emergency data in a unified format, before inputting multiple impact factors obtained based on the multiple sets of emergency data into the impact factor prediction model and obtaining corresponding impact factor prediction values, the method further includes: dividing a plurality of emergency disaster factors into hazard factors and threat factors according to a preset rule, wherein the hazard factors are used for representing the emergency disaster factors with high frequency of hydropower stations, and the threat factors are used for representing the emergency disaster factors with low frequency of hydropower stations; and determining the emergency disaster-causing factor corresponding to the hazard factor as an influence factor.
With reference to the sixth possible implementation manner of the first aspect, in a seventh possible implementation manner, after determining an emergency disaster causing factor corresponding to the hazard factor as an influence factor, the method further includes: and performing risk rating on the emergency events corresponding to the influence factors, and determining the emergency event risk rating of the emergency event corresponding to each influencer, wherein the emergency event rating is used for indicating the risk of the emergency event.
In a second aspect, an embodiment of the present application provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a computer, the method for decision making based on emergency command of a hydropower station according to the first aspect and any one of the possible implementations in combination with the first aspect is performed.
In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes: a processor, a communication bus, a communication interface, and a memory; the communication bus is respectively connected with the processor, the communication interface and the memory; the memory stores computer readable instructions that, when executed by the processor, perform a hydropower station emergency command-based decision method according to the first aspect and any one of the possible implementations in combination with the first aspect.
Compared with the prior art, the invention has the beneficial effects that: the embodiment of the application provides a hydropower station emergency command decision method based on a multi-feature analysis hybrid machine learning algorithm, scientific and structured association management of multi-source data is realized by combining multi-year meteorological data, hydrological data, equipment data, emergency plans and emergency personnel configuration data, a scheme for implementing emergency disposal of scientific personnel, materials, vehicles, measures and the like can be provided for emergency commanders in advance, advanced reminding, scientific management, efficient disposal and reasonable resource allocation of emergency event disposal are realized, and therefore emergency response speed and emergency treatment efficiency are improved.
Drawings
Fig. 1 is a block diagram illustrating an exemplary structure of an electronic device according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a decision method based on emergency command of a hydropower station according to an embodiment of the present application;
fig. 3 is a schematic flow chart of another decision method for emergency command of a hydropower station according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, some possible embodiments of the present application provide an electronic device 10. The electronic device 10 may be a Personal Computer (PC), a tablet PC, a smart phone, a Personal Digital Assistant (PDA), or the like, or the electronic device 10 may be a web server, a database server, a cloud server, or a server assembly composed of a plurality of sub-servers, or the like.
Further, the electronic device 10 may include: memory 111, communication interface 112, communication bus 113, and processor 114, wherein processor 114, communication interface 112, and memory 111 are connected by communication bus 113. The processor 114 is used to execute executable modules, such as computer programs, stored in the memory 111. The components and configurations of electronic device 10 shown in FIG. 1 are for example, and not for limitation, and electronic device 10 may have other components and configurations as desired.
The Memory 111 may include a high-speed Random Access Memory (Random Access Memory RAM) and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The communication bus 113 may be an ISA bus (Industry Standard Architecture), PCI bus (Peripheral Component Interconnect), EISA bus (Extended Industry Standard Architecture), or the like.
The processor 114 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 114. The Processor 114 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the present invention 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, or a discrete hardware component, which may implement or execute the methods, steps, and logic blocks disclosed in the embodiments of the present invention. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art.
The method performed by the apparatus defined by the embodiment of the present invention may be applied to the processor 114, or may be implemented by the processor 114. The processor 114 may implement a hydropower station emergency command-based decision-making method by cooperating with other modules or components in the electronic device 10. The implementation of the decision method based on hydropower station emergency commanders will be explained in detail below.
Referring to fig. 2 and 3, some possible embodiments of the present application provide a decision method based on emergency command of a hydropower station, including: step S11, step S12, and step S13.
Step S11: inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of various types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event;
step S12: inputting the predicted value of the impact factor into an emergency risk grade prediction model to obtain a predicted value of the emergency risk grade;
step S13: and performing coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result.
The execution flow of the decision method based on the hydropower station emergency command is described in detail below.
Before step S11, the hydropower station emergency command-based decision method further includes: acquiring all emergency data related to hydropower station emergency command within a preset time, wherein the emergency data comprises characteristic quantity data, emergency command processing data and meteorological data; preprocessing all emergency data to obtain a plurality of groups of emergency data with unified formats, wherein the preprocessing comprises the following steps: deleting filtering invalid data, filling missing values in emergency data and performing data normalization processing; and acquiring multiple emergency disaster-causing factors related to the hydropower station emergency command based on a plurality of groups of emergency data in a unified format.
In detail, data related to the hydropower station emergency event is collected, and the data related to the hydropower station emergency event comprises: characteristic quantity data, emergency command processing data, meteorological data and the like. Specifically, the feature quantity data includes a reason for the occurrence of the emergency event; the emergency command processing data comprises an emergency event processing plan; the meteorological data includes: temperature, rainfall, flow and water level. As a possible embodiment, the data relating to the hydroelectric emergency event further comprises: the emergency capacity data of the emergency personnel is obtained by comprehensively calculating the acquired management years, management authorities and working posts related to the emergency personnel by Using a BIRCH (balanced objective reduction and Clustering Using hierarchy Clustering algorithm), and the emergency capacity data of the emergency personnel can objectively reflect the emergency capacity of the emergency personnel.
In the embodiment of the application, the preset duration is the distance from the last five years, and all the acquired emergency data are preprocessed. The method comprises the steps of preprocessing emergency data, unifying data formats, deleting invalid data, filtering error data, normalizing data and the like, ensuring the integrity, the comprehensiveness, the legality and the uniqueness of the emergency data, eliminating the abnormality in the emergency data, filling missing values in the emergency data by using adjacent values, and finally obtaining various emergency disaster-causing factors related to hydropower station emergency commands.
As a possible implementation, after obtaining the plurality of emergency disaster factors associated with the hydropower station emergency command, the method further comprises: dividing a plurality of emergency disaster factors into hazard factors and threat factors according to a preset rule, wherein the hazard factors are used for representing the emergency disaster factors with high frequency of hydropower stations, and the threat factors are used for representing the emergency disaster factors with low frequency of hydropower stations; and determining the emergency disaster-causing factor corresponding to the hazard factor as an influence factor. Specifically, the preset rules divide multiple emergency disaster-causing factors into hazard factors and threat factors according to the industrial regulations of the hydropower station and the actual operation experience of the hydropower station on site, wherein the hazard factors are factors which are easy to generate by the hydropower station and have high occurrence frequency, so that the characteristic data engineering is performed on the hazard factors determined as the influence factors, and the characteristic research of the hazard factor factors is established by using emergency event correlation coefficients, such as Spearman rank correlation coefficients and kendall rank correlation coefficients.
After determining the emergency disaster factors corresponding to the hazard factors as the influence factors, the method further comprises: and performing risk rating on the emergency events corresponding to the influence factors, and determining the emergency event risk rating of the emergency event corresponding to each influencer, wherein the emergency event rating is used for indicating the risk of the emergency event. In the examples of the present application, LEC evaluation was used for risk rating. The method evaluates the casualty risk of the operator by the product of three factor index values related to system risk, wherein the risk score D is LEC, L is the accident occurrence probability, E is the exposure risk degree of the personnel, and C is the accident consequence. The larger the value of D, the greater the risk of the system. For different risk values, a discrete method is adopted and divided into different emergency event grades, and the specific emergency measures comprise: increase safety measures, change the possibility of accidents, reduce the frequency of human exposure to hazardous environments and reduce accident losses. Through the steps, the influence factors related to the hydropower station emergency command, the influence factors and the emergency event risk level are determined.
Step S11: inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of various types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event.
In detail, based on the correlation among the various influence factors and the autocorrelation of each influence factor, obtaining a correlation parameter of the influence factors and a characteristic parameter of each influence factor; simultaneously inputting the correlation parameters and the characteristic parameters of the influence factors into a plurality of machine learning regression models and a plurality of time series models for prediction, wherein at least two machine learning regression models are different in type, and at least two time series models are different in type; establishing a prediction result evaluation model, evaluating the prediction results of each machine learning regression model and each time series model, and selecting an optimal prediction model; and determining the optimal prediction model output value as the influence factor predicted values corresponding to the plurality of influence factors respectively.
The influence factors of the emergency events are mostly dangerous factors, and because the conditions of the emergency events are different, the influence of external environment factors such as meteorological factors in the dangerous factors on the emergency events is different, the risk level of the emergency events is estimated, and the influence factors influencing the emergency events need to be predicted.
When analyzing the impact factors of an emergency event, the impact factors of the emergency event need to be subjected to correlation analysis, so as to obtain characteristic parameters of each impact factor and correlation parameters of the impact factors, and establish a correlation network of a plurality of impact factors, wherein the correlation parameters of the impact factors include: the correlation among the influence factors and the autocorrelation of each influence factor, and the characteristic parameter represents the parameter influencing the influence factor.
Besides the influence of external environmental factors, certain autocorrelation characteristics also exist among the influencing factors. Therefore, the influence factors are predicted by adopting a machine learning regression algorithm. In the embodiment of the present application, the machine learning Regression Algorithm includes Local Weighted Regression (LWR) and K-Nearest Neighbor Algorithm for Regression (KNN Regression). Because part of the influence factors are greatly influenced by multiple aspects such as weather, seasons and the like, the influence factors can be analyzed and predicted through a time sequence prediction analysis method, and the influence factors of the time sequence are predicted by adopting two time sequence models of an ARIMA algorithm and a Holt-Winters algorithm. The ARIMA algorithm carries out differential operation on time series data to enable the time series data to be stable, the Holt-Winters algorithm is constructed based on an addition model, can fit nonlinear trends with factors such as year, week, season and even holidays, and has strong prediction capability on the time series data.
Modeling is carried out by using a plurality of types of machine learning regression algorithms and a plurality of types of time series algorithms, characteristic parameters influencing each influence factor and correlation parameters of the influence factors are input into different model algorithms for training and verification, the generalization capability of the model is evaluated, and the influence factors are predicted. And inputting the influence factors into a plurality of machine learning regression models and time series models, and outputting corresponding output values of the influence factors under each model.
Establishing a prediction result evaluation model, comprising: and fitting goodness R square, mean absolute error MAE, mean square error MSE and root mean square error RMSE evaluation indexes, evaluating the prediction results of all model algorithms, selecting an optimal prediction model and an optimal prediction algorithm corresponding to the optimal prediction model, and determining the output value of the optimal prediction model as the influence factor prediction values corresponding to a plurality of influence factors respectively.
The optimal prediction algorithm is selected from the plurality of models, which is determined by the characteristics of the influence factors, different influence factors have different characteristics, and the optimal prediction model selected from the influence factor prediction models is different.
Step S12: and inputting the predicted value of the influence factor into an emergency event risk grade prediction model to obtain the predicted value of the emergency event risk grade.
And in consideration of the diversity of the emergency events and the diversity of the influence factors influencing the emergency events, establishing an emergency event risk level prediction model by adopting a multi-dimensional and multi-level machine learning classification algorithm based on the correlation analysis result between the influence factors and the emergency events and the main control factors of each emergency event.
In detail, an emergency event prediction model is established based on a plurality of machine learning classification algorithm models, and is trained by using all influence factors corresponding to a plurality of emergency events, a master control factor corresponding to each emergency event and the emergency event risk grade of each emergency event to obtain an emergency event risk grade prediction model, wherein the emergency event risk grade prediction model comprises a plurality of classification prediction models; inputting the predicted values of the influence factors corresponding to the plurality of influence factors to an emergency event risk level prediction model to obtain a plurality of classification prediction results; evaluating various prediction classification results, and determining an optimal classification prediction model from the emergency risk level prediction models; and determining the output value of the optimal classification prediction model as the emergency event risk grade prediction values corresponding to the multiple influence factors respectively.
As a possible implementation manner, whether the influence factor includes an important identifier is judged, if yes, the emergency event corresponding to the influence factor is determined according to the important identifier, and the influence factor including the important identifier is determined as the main control factor of the emergency event corresponding to the influence factor. Namely, manually labeling the main control factor of each emergency event, wherein the main control factor represents the influence factor with the maximum relevance to the emergency event.
In an embodiment of the present application, the plurality of machine learning classification algorithms includes: naive Bayesian classification algorithm (NBC), Random Forest algorithm (RF), logistic algorithm based on softmax.
Establishing an emergency event prediction model by using a plurality of machine learning classification algorithms, wherein the emergency event prediction model comprises a plurality of machine learning classification models; and training an emergency event prediction model by using all the influence factors corresponding to the plurality of emergency events, the main control factor corresponding to each emergency event and the emergency event risk level of each emergency event, and evaluating the generalization capability of the model to adjust each model algorithm parameter in the emergency event prediction model to obtain the emergency event risk level prediction model.
And inputting the predicted values of the influence factors corresponding to the plurality of influence factors into an emergency event risk grade prediction model, predicting the emergency event risk grade, and obtaining a plurality of classification prediction results. Establishing a PRF classification evaluation system, evaluating various classification prediction results, preferably selecting an optimal classification algorithm, and determining an output value of an optimal classification prediction model as emergency event risk grade prediction values corresponding to a plurality of influence factors respectively, wherein the PRF classification evaluation system comprises accuracy (Precision), Recall (Recall) and F1 (F1-score).
Step S13: and performing coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result.
Among the impact factors for an emergency event, there are many that will impact multiple emergency event risk levels. Most of the impact factors of different emergency events are the same, i.e. one impact factor may have an impact on multiple emergency events. In addition, in multiple emergency events, there are many emergency events which have an association relationship and generate mutual influence, so that the risk level of the emergency event changes.
In the embodiment of the application, emergency events and influence factors of hydropower stations in severe weather are selected based on meteorological data, and a multi-emergency event risk coupling prediction Model is established based on multiple emergency event risk grade prediction values, correlation parameters of the multiple influence factors and a KSIM (Kane Simulation Model, KSIM) prediction method; and determining emergency personnel and emergency treatment plans for treating the emergency according to the coupling prediction result of the multi-emergency risk coupling prediction model. Through the method, the possibility that one influence factor causes other emergency events can be deduced based on cross influence analysis, the overall emergency event risk of the power station is evaluated, advanced early warning is realized, and the safe operation of the power station is ensured.
According to the hydropower station emergency command-based decision method, emergency plan disposal measures including personnel arrangement in advance, preparation of various materials in advance, optimal vehicle scheduling, accident prevention measures and the like can be established according to an influence factor prediction model and an emergency event risk level prediction model, auxiliary decisions are provided for emergency commanders, accident prevention is made in advance, and safe and efficient operation of equipment is guaranteed.
In summary, the embodiment of the present application provides a decision method based on hydropower station emergency command, and the method includes: inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of various types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event; inputting the predicted value of the impact factor into an emergency risk grade prediction model to obtain a predicted value of the emergency risk grade; and performing coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A decision-making method based on hydropower station emergency command is characterized by comprising the following steps:
inputting a plurality of influence factors obtained based on a plurality of groups of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values, wherein the emergency data are of a plurality of types, the influence factors are used for representing disaster causing types related to hydropower station emergency commands, and one influence factor corresponds to at least one emergency event;
inputting the predicted value of the influence factor into an emergency risk grade prediction model to obtain a predicted value of the emergency risk grade;
and performing coupling prediction based on the emergency risk level prediction value, and determining an auxiliary decision according to a coupling prediction result.
2. The hydropower station emergency command-based decision method according to claim 1, wherein the step of inputting a plurality of influence factors obtained based on a plurality of sets of emergency data into an influence factor prediction model to obtain corresponding influence factor prediction values comprises the steps of:
obtaining a correlation parameter of the influence factors and a characteristic parameter of each influence factor based on the correlation among the influence factors and the autocorrelation of each influence factor;
inputting the correlation parameters and the characteristic parameters of the influence factors into a plurality of machine learning regression models and a plurality of time series models simultaneously for prediction, wherein at least two machine learning regression models are different in type, and at least two time series models are different in type;
establishing a prediction result evaluation model, evaluating the prediction results of each machine learning regression model and each time series model, and selecting an optimal prediction model;
and determining the optimal prediction model output value as the influence factor prediction values corresponding to the plurality of influence factors respectively.
3. The hydropower station emergency command-based decision method according to claim 1, wherein the inputting the predicted value of the influence factor into an emergency event risk level prediction model to obtain a predicted value of an emergency event risk level comprises:
establishing an emergency event prediction model based on a plurality of machine learning classification algorithm models, and training the emergency event prediction model by using all influence factors corresponding to a plurality of emergency events, a main control factor corresponding to each emergency event and an emergency event risk level of each emergency event to obtain the emergency event risk level prediction model, wherein the emergency event risk level prediction model comprises a plurality of classification prediction models;
inputting the predicted values of the influence factors corresponding to the plurality of influence factors to the emergency risk level prediction model to obtain a plurality of classification prediction results;
evaluating the multiple prediction classification results, and determining an optimal classification prediction model from the emergency risk level prediction model;
and determining the output value of the optimal classification prediction model as the emergency event risk grade prediction values corresponding to the multiple influence factors respectively.
4. The hydropower station emergency command based decision method according to claim 3, wherein the step of inputting the predicted value of the influence factor into an emergency event risk level prediction model to obtain a predicted value of an emergency event risk level further comprises the steps of:
judging whether the influence factors contain important marks or not, if so, determining the emergency events corresponding to the influence factors according to the important marks, and determining the influence factors containing the important marks as the main control factors of the emergency events corresponding to the influence factors.
5. The hydropower station emergency command based decision method according to claim 2, wherein the coupling prediction is performed based on the emergency event risk level prediction value, and an auxiliary decision is determined according to a coupling prediction result, and the method comprises the following steps:
establishing a multi-emergency risk coupling prediction model based on the multiple emergency risk grade prediction values, the correlation parameters of the multiple influence factors and a KSIM prediction method;
and determining emergency personnel and emergency treatment plans for treating the emergency according to the coupling prediction result of the multi-emergency risk coupling prediction model.
6. The hydropower station emergency commander-based decision making method according to claim 1, wherein before inputting a plurality of influence factors obtained based on a plurality of sets of emergency data into an influence factor prediction model and obtaining corresponding influence factor prediction values, the method further comprises:
acquiring all emergency data related to hydropower station emergency command within a preset time length, wherein the emergency data comprises characteristic quantity data, emergency command processing data and meteorological data;
preprocessing all the emergency data to obtain a plurality of groups of emergency data with uniform formats, wherein the preprocessing comprises the following steps: deleting filtering invalid data, filling missing values in emergency data and performing data normalization processing;
and acquiring multiple emergency disaster-causing factors related to the hydropower station emergency command based on a plurality of groups of emergency data in a unified format.
7. The hydropower station emergency command-based decision method according to claim 6, wherein after obtaining a plurality of emergency disaster-causing factors related to the hydropower station emergency command based on the plurality of sets of emergency data in the unified format, before inputting the plurality of influence factors obtained based on the plurality of sets of emergency data into the influence factor prediction model to obtain corresponding influence factor prediction values, the method further comprises:
dividing the multiple emergency disaster factors into hazard factors and threat factors according to a preset rule, wherein the hazard factors are used for representing the emergency disaster factors with high frequency of hydropower stations, and the threat factors are used for representing the emergency disaster factors with low frequency of hydropower stations;
and determining the emergency disaster factors corresponding to the hazard factors as influence factors.
8. The hydropower station emergency commander-based decision method according to claim 7, wherein after the determining of the emergency disaster causing factor corresponding to the hazard factor as an influence factor, the method further comprises:
and performing risk rating on the emergency events corresponding to the influence factors, and determining the emergency event risk rating of the emergency event corresponding to each influencer, wherein the emergency event rating is used for indicating the risk of the emergency event.
9. A storage medium having stored thereon a computer program for executing the method of hydropower station emergency commander based decision-making according to any one of claims 1-8 when the computer program is executed.
10. An electronic device, characterized in that the electronic device comprises: a processor, a communication bus, a communication interface, and a memory;
the communication bus is respectively connected with the processor, the communication interface and the memory;
the memory stores computer readable instructions which, when executed by the processor, operate a hydropower station emergency commander based decision method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110229210.8A CN112950024A (en) | 2021-03-02 | 2021-03-02 | Decision-making method based on hydropower station emergency command, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110229210.8A CN112950024A (en) | 2021-03-02 | 2021-03-02 | Decision-making method based on hydropower station emergency command, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112950024A true CN112950024A (en) | 2021-06-11 |
Family
ID=76247096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110229210.8A Pending CN112950024A (en) | 2021-03-02 | 2021-03-02 | Decision-making method based on hydropower station emergency command, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950024A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113869562A (en) * | 2021-09-10 | 2021-12-31 | 中铁二十局集团有限公司 | Abnormal event response level determining method, device, equipment and readable storage medium |
| CN114066288A (en) * | 2021-11-24 | 2022-02-18 | 广州交投工程检测有限公司 | Intelligent data center-based emergency detection method and system for operation road |
-
2021
- 2021-03-02 CN CN202110229210.8A patent/CN112950024A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113869562A (en) * | 2021-09-10 | 2021-12-31 | 中铁二十局集团有限公司 | Abnormal event response level determining method, device, equipment and readable storage medium |
| CN114066288A (en) * | 2021-11-24 | 2022-02-18 | 广州交投工程检测有限公司 | Intelligent data center-based emergency detection method and system for operation road |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yazdi | Improving failure mode and effect analysis (FMEA) with consideration of uncertainty handling as an interactive approach | |
| Choi et al. | Machine learning predictive model based on national data for fatal accidents of construction workers | |
| CN106844663B (en) | Ship collision risk assessment method and system based on data mining | |
| CN102801739A (en) | Network risk determining and evidence obtaining method based on cloud computing environment | |
| CN115098705B (en) | Network security event analysis method and system based on knowledge graph reasoning | |
| CN105989155A (en) | Method and device for identifying risk behaviors | |
| CN103793853A (en) | Overhead power transmission line running state assessment method based on bidirectional Bayesian network | |
| CN112950024A (en) | Decision-making method based on hydropower station emergency command, storage medium and electronic equipment | |
| Babaei et al. | Risk assessment of agricultural water conveyance and delivery systems by fuzzy fault tree analysis method | |
| Sirisha et al. | Profit prediction using ARIMA, SARIMA and LSTM models in time series forecasting: A comparison | |
| Shadabfar et al. | Resilience-based design of infrastructure: Review of models, methodologies, and computational tools | |
| US11906112B2 (en) | Methods for safety management of compressors in smart gas pipeline network and internet of things systems thereof | |
| CN115063020B (en) | Multi-dimensional safety scheduling device and method for cascade hydropower station based on risk monitoring fusion | |
| CN104461896A (en) | Aerospace system key software evaluation method based on credible attribute | |
| CN103810383A (en) | Method for identifying and analyzing single-point failure mode of launch vehicle | |
| CN110636066A (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN115577701B (en) | Risk behavior identification method, device, equipment and medium aiming at big data security | |
| CN106779222B (en) | Airport ground waiting time prediction method and device | |
| CN112087445A (en) | Electric power Internet of things security vulnerability assessment method fusing business security | |
| CN107632590A (en) | A kind of bottom event sort method based on priority | |
| CN110895495A (en) | Human error analysis method, system, computer device and storage medium | |
| CN111507603A (en) | Method and system for evaluating current environmental risk situation of in-production enterprise | |
| Recal et al. | Comparison of machine learning methods in predicting binary and multi-class occupational accident severity | |
| CN107145995A (en) | Production environment safety prediction methods, devices and systems | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network |
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 |