KR102118966B1 - System and method for fault forecast and diagnostic of power plant - Google Patents

Abstract

A power plant failure prediction and diagnosis system is provided that can predict and diagnose failures of power generation facilities in advance using artificial intelligence-based learning models. The power plant failure prediction and diagnosis system can build a virtual power plant to generate learning data for various failure situations, thereby improving the learning ability of the learning model to increase the accuracy and reliability of power plant failure prediction and diagnosis.

Description

System and method for fault forecast and diagnostic of power plant

The present invention relates to a failure prediction and diagnosis system of a power plant, and more particularly, to a power plant failure prediction and diagnosis system and a method thereof using an artificial intelligence-based learning model.

In general, many power generation facilities are concentrated in a power plant. Many of these power generation facilities must be able to be monitored in real time at all times, and should be able to service them as soon as possible in the event of a malfunction or abnormal condition.

Conventional power plants perform regular preventive maintenance for each of a number of power generation facilities, and collect and analyze sensor data that can determine the state of the power generation facilities to predict the occurrence of failures in the power generation facilities, and take countermeasures accordingly. Is doing.

However, in a conventional power plant, the sensor data collected from the power generation facility is used to notify the occurrence of an alarm by analyzing the cause of the actual generated alarms, and thus, the operator of the power plant simply generates an alarm to generate a large number of power generations. Among the facilities, it was difficult to find a faulty device.

In addition, in a conventional power plant, prediction of a failure of a power generation facility depends on sensor data collected from the power generation facility, so it is difficult to quickly determine the state of the power generation facility when a large number of sensor data is generated. In particular, it was more difficult to predict the occurrence of the failure of the power generation facility simply from the sensor data, if not an experienced power plant operator.

An object of the present invention is to provide a power plant failure prediction and diagnosis system and a method for predicting and diagnosing a failure of each power plant by using an artificial intelligence-based learning model.

A power plant failure prediction and diagnosis system according to an embodiment of the present invention includes a data generation module for constructing a virtual power plant and generating a plurality of learning data; A data processing module that analyzes and converts the learning data and loads the converted data; Predicting and diagnosing failures by performing the learning for predicting and diagnosing failures from the data loaded in the data processing module, and determining the state of the power generation facilities of the power plants from one or more real-time sensor data collected from the power plants based on the learning results. Fault prediction/diagnostic module; And an information display module for displaying prediction and diagnosis results of the failure prediction/diagnostic module and additional information of a corresponding power generation facility together.

A method of predicting and diagnosing a power plant failure according to an embodiment of the present invention includes: constructing a virtual power plant based on information on each of a plurality of power generation facilities of the power plant, and starting the virtual power plant to generate a plurality of learning data; Analyzing the validity of the learning data and converting and loading the learning data according to the analysis result; Learning the failure occurrence prediction and diagnosis of the plurality of power generation facilities using the loaded data, and predicting and diagnosing the failure occurrence of the plurality of power generation facilities from one or more real-time sensor data collected from the power plant based on the learning result. step; And displaying additional information of the power generation facility corresponding to the predicted and diagnosed results of the failure together with the predicted and diagnosed results.

The power plant failure prediction and diagnosis system of the present invention predicts and diagnoses a power generation facility failure in advance using an artificial intelligence-based learning model, and displays it together with additional information of the power generation facility, thereby causing a failure of the actual power generation facility. The failure of the power generation facility before it can be prevented.

In addition, the power plant failure prediction and diagnosis system of the present invention can build a virtual power plant to generate learning data for various failure situations, thereby increasing the learning ability of the learning model to increase the accuracy and reliability of power plant failure prediction and diagnosis.

1 is a view showing the configuration of a power plant failure prediction and diagnostic system according to an embodiment of the present invention.
FIG. 2 is a diagram showing the configuration of the data generation module of FIG. 1.
FIG. 3 is a diagram showing the configuration of the data processing module of FIG. 1.
FIG. 4 is a diagram showing the configuration of the information display module of FIG. 1.
5 is a view showing a power plant failure prediction and diagnosis method according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings for the embodiment of the present invention will be described the configuration and operation.

It should be noted that the same components among the drawings are represented by the same reference numerals and symbols as much as possible, even if they are displayed on different drawings. In the following description of the present invention, when it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. Also, when a part is said to "include" a certain component, this means that other components may be further included rather than excluding other components, unless otherwise stated.

Also, the terms or words used in the specification and claims should not be interpreted in a conventional and lexical sense, and the inventors can properly define the concept of terms to describe their own invention in the best way. Based on the principles, it should be interpreted as meanings and concepts consistent with the technical spirit of the present invention. Therefore, the configuration shown in the embodiments and drawings described in this specification is only a preferred embodiment of the present invention, and does not represent all of the technical spirit of the present invention, and various equivalents that can replace them at the time of this application And variations, and the scope of the present invention is not limited to the embodiments described below.

1 is a view showing the configuration of a power plant failure prediction and diagnosis system according to an embodiment of the present invention, FIGS. 2 to 4 are diagrams showing each configuration of FIG. 1 in detail.

1 to 4, the power plant failure prediction and diagnosis system 100 of the present embodiment analyzes the state of power generation facilities of the power plant 200 from a plurality of real-time sensor data (not shown) collected from the power plant 200 and Therefore, it is possible to predict and diagnose the occurrence of a malfunction in the power generation facility. At this time, the failure prediction and diagnosis system 100 can predict the occurrence of a failure of the power generation facility from real-time sensor data using a pre-trained learning model. Subsequently, the failure prediction and diagnosis system 100 may provide prediction and diagnosis results to operators of the power plant 200 so that preventive maintenance of the power generation facility can be performed. The power plant failure prediction and diagnosis system 100 may include a data generation module 110, a data processing module 120, a failure prediction/diagnosis module 130 and an information display module 140.

The data generation module 110 may generate learning data for prior learning of the failure prediction/diagnosis module 130 to be described later. To this end, the data generation module 110 may generate and start a virtual power plant, thereby generating learning data according to sensor data collected from the virtual power plant. The data generation module 110 may include a modeling unit 111, a simulation unit 113, and a data extraction unit 115.

The modeling unit 111 may build a virtual power plant by modeling each of a plurality of power generation facilities of the power plant 200. The modeling unit 111 may construct a virtual power plant based on information on power generation facilities provided from the outside. At this time, the modeling unit 111 may construct a start control system that can control the start of the virtual power plant.

The simulation unit 113 may virtually start a pre-built virtual power plant based on a predetermined startup scenario. The start-up scenario may include a normal start-up scenario for the normal start-up of a virtual power plant and a failure start-up scenario for a failure of a virtual power plant.

The data extraction unit 115 may extract a plurality of sensor data, for example, virtual sensor data, from a virtual power plant activated by the simulation unit 113. The virtual sensor data may be extracted from at least one sensing point set for each of a plurality of power generation facilities of the virtual power plant. The data extraction unit 115 may generate and output a plurality of extracted virtual sensor data as learning data.

Previously, it was described that the virtual power plants are virtually started based on the normal start-up scenario and the fault start-up scenario, respectively. Accordingly, the data extraction unit 115 extracts virtual sensor data according to the normal start-up of the virtual power plant and virtual sensor data according to the fault-start of the virtual power plant, respectively, and thus learning data, that is, normal start-up learning data and fault start-up learning data. You can create each.

The data processing module 120 collects and processes learning data output from the data generation module 110, that is, a plurality of virtual sensor data, and then loads it. In addition, the data processing module 120 may collect and process real-time sensor data from the power plant 200, and then load it. At this time, the real-time sensor data may be extracted and collected from at least one sensing point of each of a plurality of power generation facilities of the power plant 200. The data processing module 120 may include a data selection unit 121, a data analysis unit 122, a data integration unit 123, a first loading unit 124, and a second loading unit 125.

The data selection unit 121 may select one of learning data collected by the data generation module 110 and real-time sensor data collected by the power plant 200.

The data analysis unit 122 may analyze and convert data selected by the data selection unit 121. The data analysis unit 122 may analyze the validity of the data and standardize the data according to the analysis results. The data analysis unit 122 can convert standardized data. Here, the learning data and real-time sensor data provided to the data analysis unit 122 may be time series data. Accordingly, the data analysis unit 122 may convert the provided time series data. At this time, the data analysis unit 122 may convert learning data and real-time sensor data into 2D or 3D image data.

The data integration unit 123 may determine the correlation between the converted data, and group and integrate the data accordingly. The learning data and the real-time sensor data are data according to the state information of the power generation facility collected according to the start-up of the power plant 200 or the virtual power plant. Accordingly, the data integration unit 123 may group and integrate the converted data by type of power generation facilities. Further, the data integration unit 123 may group and integrate the converted data according to states of power generation facilities.

The integrated data may be loaded in each of the first loading unit 124 and the second loading unit 125. At this time, real-time data may be loaded on the first loading unit 124, and data accumulated for a certain period may be loaded on the second loading unit 125. Here, the first loading unit 124 and the second loading unit 125 may be converted into two-dimensional or three-dimensional image data, and load integrated data in a matrix form according to mutual relationships.

As described above, the data processing module 120 is used for pre-learning and failure prediction of the failure prediction/diagnosis module 130, which will be described later, by loading the collected data, that is, learning data and real-time sensor data through analysis, conversion, and integration. You can build a large data platform that can be.

The failure prediction/diagnosis module 130 may use the data loaded in the data processing module 120, for example, learning data, to perform pre-learning about failure occurrence prediction and diagnosis according to the state of the power generation facility. In addition, the failure prediction/diagnosis module 130 may predict and diagnose a failure of the power generation facility from data loaded in the data processing module 120 based on learning, for example, real-time sensor data.

The failure prediction/diagnosis module 130 may be implemented as an artificial intelligence-based learning model. The failure prediction/diagnosis module 130 may be composed of at least two prediction/diagnosis units (not shown). For example, the first prediction/diagnosis unit and the first prediction/diagnosis unit performing fast calculation in real time. And a second prediction/diagnostic unit for deeply calculating the output. This is because most of the power generation facilities of the ordinary power plant 200 are in a normal state, so it is required to detect an abnormality that is not a normal state through a quick calculation and to analyze it in depth.

The failure prediction/diagnostic module 130 may output a failure occurrence prediction and diagnosis result of the power generation facility. The result may include at least one of response stage information of a failure occurrence, residual response time information, and failure cause information.

The information display module 140 may display a failure prediction/diagnosis module 130 power generation facility failure prediction and diagnosis result to the outside, that is, power plant operators. The information display module 140 may include a database 141, a mapping unit 143, and a display unit 145.

Various additional information about each of the plurality of power generation facilities of the power plant 200 may be stored in the database 141. The additional information may include at least one of on-site photo and video information of the power generation facility, failure history and maintenance history information of the power generation facility, drawing information about the arrangement of the power generation facility, and three-dimensional modeling information of the power generation facility.

The mapping unit 143 may map additional information of the power generation facility and the database 141 on a one-to-one basis based on prediction and diagnosis results provided by the failure prediction/diagnostic module 130. For example, when a failure occurrence of an air intake among a plurality of power generation facilities is predicted by the failure prediction/diagnosis module 130, the mapping unit 143 provides prediction and diagnosis provided by the failure prediction/diagnosis module 130. Based on the results, additional information corresponding to the duct may be extracted and mapped from a plurality of additional information stored in the database 141. At this time, the extracted additional information may include on-site images and photographs of ducts, drawings and three-dimensional modeling, equipment information of ducts, and past failure and maintenance history.

The display unit 145 may display failure prediction and diagnosis results of the power generation facility provided by the failure prediction/diagnosis module 130 and additional information of the power generation facility by the mapping unit 143 together.

5 is a view showing a power plant failure prediction and diagnosis method according to an embodiment of the present invention.

Referring to FIG. 5, the data generation module 110 of the failure prediction and diagnosis system 100 may generate a plurality of learning data for learning the failure prediction/diagnosis module 130 (S10).

First, the modeling unit 111 of the data generation module 110 may construct a virtual power plant based on information on power generation facilities provided from the outside (S11). Subsequently, the simulation unit 113 may start the virtual power plant based on a predetermined scenario, for example, a normal start-up scenario and a failure start-up scenario (S13). Subsequently, the data extraction unit 115 may extract the state information of the power generation facility according to the start of the virtual power plant from the at least one sensing point set for each of the plurality of power generation facilities of the virtual power plant as virtual sensor data (S15). The data generation module 110 may generate and output a plurality of extracted virtual sensor data as learning data.

The data processing module 120 of the failure prediction and diagnosis system 100 collects and analyzes and converts a plurality of real-time sensor data of the power generation unit 200 or a plurality of learning data of the data generation module 110, and loads them by integrating them It can be done (S20).

The data selection unit 121 of the data processing module 120 may select one of a plurality of learning data and real-time sensor data (S21). Subsequently, the data analysis unit 122 analyzes the validity of the selected data to perform standardization, and converts it into 2D or 3D image data (S23). Subsequently, the data integration unit 123 may group and consolidate the converted data and load it (S25).

The failure prediction/diagnosis module 130 may learn the prediction and diagnosis of failures of power generation facilities using a plurality of learning data loaded in the data processing module 120. Subsequently, the failure prediction/diagnosis module 130 may predict and diagnose the actual failure of the power generation facility from real-time sensor data collected from the power plant 200 based on the learning result (S30).

The failure prediction/diagnosis module 130 may be implemented as an artificial intelligence-based learning model. Therefore, the failure prediction/diagnosis module 130 needs a variety of learning to increase the accuracy of prediction and diagnosis of failures. Accordingly, the failure prediction and diagnosis system 100 may generate learning data for various failure conditions of the power generation facility using the data generation module 110 and use this to train the failure prediction/diagnosis module 130. .

In other words, the actual data collected from the power plant 200, that is, the real-time sensor data is mostly data on the state of the power generation facility according to the normal operation of the power plant 200. Therefore, it is difficult to learn the failure prediction/diagnosis module 130 according to various failure conditions of the power generation facility.

Accordingly, the failure prediction and diagnosis system 100 of the present invention builds a virtual power plant through the data generation module 110 and starts the virtual power plant using various failure start-up scenarios, thereby detecting various failure conditions for the power generation facility. Data, ie virtual sensor data, can be extracted. And, by analyzing and converting such virtual sensor data and providing it as learning data to the failure prediction/diagnosis module 130, the failure prediction/diagnosis module 130 can learn about the state of the power generation facility in various failure environments. . Then, the failure prediction/diagnosis module 130 predicts and diagnoses the actual failure of the power generation facility from actual data, that is, real-time sensor data collected from the power plant 200, based on the learning results, and predicts and diagnoses the result. Can print The prediction and diagnosis results output from the failure prediction/diagnosis module 130 may include failure response step information, residual response time information, and failure cause information for a power generation facility in which a failure is predicted.

Next, the information display module 140 may display failure prediction and diagnosis results of the failure prediction/diagnosis module 130 to external power plant operators (S40). The information display module 140 may extract various additional information of a corresponding power generation facility from the database 141 based on the prediction and diagnosis results, map them to the prediction and diagnosis results, and display them together. Here, the additional information may include on-site photo and video information of the power generation facility, failure history and maintenance history information of the power generation facility, drawing information about the arrangement of the power generation facility, and 3D modeling information of the power generation facility.

As described above, the power plant failure prediction and diagnosis system 100 of the present invention predicts a failure of the power generation facility of the power plant 200 through the failure prediction/diagnosis module 130 implemented as an artificial intelligence-based learning model, and By diagnosing and displaying along with the additional information of the power generation facility, the failure of the power generation facility can be prevented before the failure of the actual power generation facility occurs.

In addition, the power plant failure prediction and diagnosis system 100 of the present invention can increase the learning ability of the failure prediction/diagnosis module 130 by constructing a virtual power plant to generate learning data for various failure situations. Through the prediction/diagnostic module 130, it is possible to increase the accuracy of predicting and diagnosing power plant failure of the power plant 200.

100: power plant failure prediction and diagnosis system 110: data generation module
111: modeling unit 113: simulation unit
115: data extraction unit 120: data processing module
121: data selection unit 122: data analysis unit
123: data integration unit 124: first loading unit
125: second loading unit 130: failure prediction / diagnosis module
140: information display module 141: database
143: mapping unit 145: display unit

Claims (12)

A data generation module for constructing a virtual power plant and generating a plurality of learning data;
A data processing module that analyzes and converts the learning data and loads the converted data;
Predicting and diagnosing failures by performing the learning for predicting and diagnosing failures from the data loaded in the data processing module, and determining the status of the power generation facilities of the power plants from one or more real-time sensor data collected from the power plants based on the learning results. Fault prediction/diagnostic module; And
Includes an information display module for displaying the predictive and diagnostic results of the failure prediction/diagnostic module and additional information of the corresponding power generation facility together.
The data generation module,
A modeling unit for constructing the virtual power plant by modeling each of a plurality of power generation facilities of the power plant;
A simulation unit for starting the virtual power plant based on one of a normal start-up scenario and a failure start-up scenario; And
And a data extraction unit that extracts virtual sensor data from the virtual power plant and generates it as the learning data. delete According to claim 1,
The data processing module,
A data selection unit selecting one of the learning data of the data generation module and the real-time sensor data of the power plant;
A data analysis unit for analyzing the validity of the selected data and standardizing and converting the selected data based on the analysis result;
A data integration unit for grouping and consolidating the converted data; And
Power plant failure prediction and diagnostic system comprising a loading unit for loading integrated data. According to claim 1,
The failure prediction/diagnosis module is a power plant failure prediction and diagnosis system, characterized by being implemented as an artificial intelligence-based learning model. According to claim 1,
The information display module,
A database storing the additional information for each of a plurality of power generation facilities;
A mapping unit that maps additional information of at least one power generation facility corresponding to the prediction and diagnosis results among the plurality of power generation facilities to the prediction and diagnosis results; And
And a display unit displaying additional information mapped together with the prediction and diagnosis results. According to claim 1,
The prediction and diagnosis results,
Power plant failure prediction and diagnosis system, characterized in that it comprises at least one of the response step information, residual response time information and failure cause information according to the failure of the power generation facility. According to claim 1,
The additional information,
A power plant comprising at least one of on-site photo and video information of the power generation facility, failure history and maintenance history information of the power generation facility, drawing information on the arrangement of the power generation facility, and three-dimensional modeling information of the power generation facility. Failure prediction and diagnosis system. Constructing a virtual power plant based on information on each of a plurality of power generation facilities of the power plant, and starting the virtual power plant to generate a plurality of learning data;
Analyzing the validity of the learning data and converting and loading the learning data according to the analysis result;
Learning the failure occurrence prediction and diagnosis of the plurality of power generation facilities using the loaded data, and predicting and diagnosing the failure occurrence of the plurality of power generation facilities from one or more real-time sensor data collected from the power plant based on the learning result. step; And
Includes; displaying additional information of the power generation facility corresponding to the prediction and diagnosis results for the failure occurrence together with the prediction and diagnosis results;
The step of generating the plurality of learning data,
Starting the virtual power plant based on one of a normal start-up scenario and a failure start-up scenario; And
And extracting a plurality of virtual sensor data from at least one sensing point set in the virtual power plant, and generating the plurality of learning data based on the plurality of virtual sensor data. Way. delete The method of claim 8,
The step of converting and loading the learning data,
Selecting one of the learning data and the real-time sensor data, and analyzing the validity of the selected data;
Converting the selected data based on an analysis result; And
A method of predicting and diagnosing a power plant failure, comprising the step of grouping and consolidating the transformed data and loading the integrated data. The method of claim 8,
Predicting and diagnosing the failure of the plurality of power generation facilities,
And outputting the prediction and diagnosis results including at least one of response stage information, residual response time information, and failure cause information according to a failure occurrence. The method of claim 8,
The step of displaying the additional information together with the prediction and diagnosis results,
At least one of on-site photo and video information of the power generation facility, failure history and maintenance history information of the power generation facility, drawing information about the arrangement of the power generation facility, and three-dimensional modeling information of the power generation facility corresponding to the prediction and diagnosis results Method for predicting and diagnosing a power plant failure, characterized in that the step of displaying the additional information together.

Images