KR20210105195A - Apparatus and method of plant failure prediction - Google Patents

Abstract

The present invention relates to a device and method for predicting a plant failure, which may select an optimal failure prediction model among a plurality of failure prediction models using data collected from a plant, and predict a failure of a plant by using the selected optimal failure prediction model. According to an embodiment of the present invention, the method for predicting a plant failure includes the steps of: storing a previously derived failure prediction model in a memory; collecting data measured from the plant; determining whether the collected data is data for predicting which type of failure among plant failure types; selecting an optimal failure prediction model from among the plurality of failure prediction models for predicting the determined type of failure; and predicting the failure of the plant by using the selected failure prediction model.

Description

Apparatus and method of plant failure prediction

The present invention relates to an apparatus and method for predicting plant failure, and more particularly, selecting an optimal failure predictive model from among a plurality of failure predictive models using data collected from a plant, and using the selected optimal failure predictive model. It relates to an apparatus and method for predicting plant failure for predicting failure of a plant.

In general, large-scale plants, such as power generation or chemical, are operated in which hundreds of various types of mechanical and electrical equipment are intricately connected. In order to secure the reliability of these plants and to operate them normally, it is necessary to constantly monitor the abnormal signs that cause accidents. Therefore, a monitoring device that detects damage to major components constituting the plant in real time and generates an alarm to the driver when abnormal signs are found in the parts is being used.

That is, failure of the plant may cause damage to the plant, resulting in undesirable performance, or furthermore, when the plant is destroyed, a person may be injured or killed, and environmental problems may occur. Therefore, an early warning system that can detect failure at an early stage is essential.

In general, failure prediction of a plant for an early warning system is performed based on domain-knowledge. Plant failures are not properly predicted due to plant complexity, lack of quality data and failure data, and insufficient use of failure detection/diagnosis information.

The present invention is to solve the above-described problems, by using data collected from a plant to select an optimal failure predictive model from among a plurality of failure predictive models, and to detect plant failures using the selected optimal failure predictive model. An object of the present invention is to provide an apparatus and method for predicting plant failure.

In addition to the technical problems of the present invention mentioned above, other features and advantages of the present invention will be described below or will be clearly understood by those skilled in the art from such description and description.

A plant failure prediction method according to an embodiment of the present invention for achieving the above-described object includes the steps of storing a failure prediction model derived in advance in a memory, collecting data measured from the plant, and collecting the collected data from the plant. Determining which type of failure among failure types is the data for predicting a failure, selecting an optimal failure prediction model from among a plurality of failure prediction models for predicting the determined type of failure, and using the selected failure prediction model It may include the step of predicting failure of the plant by using it.

In addition, the apparatus for predicting plant failure according to an embodiment of the present invention for achieving the above-described object collects data measured from a memory for storing a failure prediction model derived in advance, and the plant, and the collected data is a type of plant failure. Determining which type of failure is the data for predicting the type of failure, selecting the optimal failure prediction model from among a plurality of failure prediction models for predicting the determined type of failure, and using the selected failure prediction model to detect plant failure It may include a foresight processor.

The apparatus and method for predicting plant failure according to an embodiment of the present invention may predict failure of a plant by using an optimal failure prediction model.

In addition, the reliability of failure prediction may be increased by generating a new failure prediction model using the result of predicting the failure of the plant, and then using the generated new failure prediction model to predict the failure of the plant.

In addition, other features and advantages of the present invention may be newly recognized through embodiments of the present invention.

1 is a diagram showing the configuration of a plant failure prediction system according to an embodiment of the present invention.
2 is a diagram illustrating a configuration of a failure prediction device according to an embodiment of the present invention.
3 is a diagram illustrating a failure prediction model according to a failure type according to an embodiment of the present invention.
4 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.
5 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.
6 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.
7 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.
8 is a diagram illustrating a method for predicting plant failure according to an embodiment of the present invention.

In order to clearly explain the present invention, parts irrelevant to the description are omitted, and the same reference numerals are given to the same or similar elements throughout the specification.

Although not defined otherwise, all terms including technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention belongs. Commonly used terms defined in the dictionary are additionally interpreted as having a meaning consistent with the related technical literature and the presently disclosed content, and unless defined, they are not interpreted in an ideal or very formal meaning.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein.

1 is a diagram showing the configuration of a plant failure prediction system according to an embodiment of the present invention.

Referring to FIG. 1 , a plant failure prediction system 1000 according to an embodiment of the present invention may include a plant 100 and a failure prediction apparatus 200 .

The failure predictive device 200 selects an optimal failure predictive model from among a plurality of failure predictive models using data collected from the plant 100 , and uses the selected optimal failure predictive model to cause failure of the plant 100 . can predict

Here, the data collected from the plant 100 may include temperature, pressure and humidity, NOx, SOx, O2, exhaust amount, efficiency and power generation output, etc. for a specific configuration included in the plant 100 of the plant 100. have. In addition, the data collected from the plant 100 is data about the state of the plant 100, and may include data collected from the plant 100 at a previous time point and data collected from the plant 100 at the current time point. .

The failure prediction device 200 determines the time and location when a failure occurs in the plant 100 using an optimal predictive model selected based on data collected from the plant 100 , and the failure occurs in the plant 100 . It is possible to determine the cause, expected alarm level, predictive value, and trend. Accordingly, the failure prediction apparatus 200 detects the failure and predicts the failure of the plant 100 using the diagnosed information, thereby predicting the failure of the plant 100 more accurately.

In addition, the failure prediction device 200 generates a new failure prediction model based on the result of predicting the failure of the plant 100 , and then uses the new failure prediction model additionally when predicting the failure of the plant 100 . By doing so, the reliability of the result of failure prediction can be increased.

2 is a diagram illustrating a configuration of a failure prediction device according to an embodiment of the present invention.

Referring to FIG. 2 , the failure prediction apparatus 200 according to an embodiment of the present invention may include a memory 210 and a processor 220 .

The memory 210 may store a failure prediction model derived in advance. Here, the failure prediction model derived in advance is a failure prediction model newly created using the failure prediction model that has been generally used to predict the failure of the existing plant 100 and the result of predicting the failure of the plant 100 . may include.

The memory 210 may classify the failure prediction model according to the type of failure occurring in the plant 100 , and store the classified failure prediction model according to the type of failure for each group.

For example, a failure may occur in the plant 100 due to a failure of the turbine. Accordingly, the memory 210 may store failure prediction models for determining the failure of the turbine as a group. In addition, a failure may occur in the plant 100 due to an engine failure. Accordingly, in the memory 210 , failure prediction models for determining engine failure may be stored as one group. That is, the memory 210 stores a first failure predictive model group including failure predictive models for determining a failure of a turbine and a second failure predictive model group including failure predictive models for determining a failure of an engine, respectively. can

The processor 220 may collect data from the plant 100 and analyze the collected data. Here, the data collected from the plant 100 may include temperature, pressure and humidity, NOx, SOx, O2, exhaust amount, efficiency and power generation output, etc. for a specific configuration included in the plant 100 of the plant 100. have. In addition, the data collected from the plant 100 is data about the state of the plant 100, and may include data collected from the plant 100 at a previous time point and data collected from the plant 100 at the current time point. .

The processor 220 may generate new feature data based on the collected data. For example, the processor 220 may generate characteristic data for an average value, a minimum/maximum value, etc. based on the collected data. In addition, the processor 220 may analyze the correlation between the collected data and the generated data to analyze changes and trends in data.

In addition, the processor 220 may classify the data collected from the plant 100 into input data and output data. For example, the power generation output may be different depending on the temperature, pressure, and humidity for a specific configuration included in the plant 100 , and the temperature, pressure, humidity, and power generation output for the specific configuration may be collected in the processor 220 . . In this case, the power generation output may be a parameter capable of determining a failure of a specific configuration as a final result. For example, when the power generation output is less than or equal to a predetermined value, a specific configuration may be an index for determining a failure, such as determining that a failure is present. Accordingly, the processor 220 may classify the data on the power generation output as output data.

On the other hand, temperature, pressure, and humidity for a particular configuration may be parameters that affect the final result. For example, as the temperature, pressure, and humidity for a particular configuration change, the final result, power generation output, may also change. Accordingly, the processor 220 may classify the temperature, pressure, and humidity for a specific configuration as input data.

The processor 220 may determine whether the collected data is data for predicting which type of failure among types of failures that may occur in the plant 100 . Specifically, several types of components may be included in the plant 100 , and when a failure occurs in one of the various types of components, the plant 100 may be determined as a failure. Accordingly, the processor 220 may predict the failure of the plant 100 by predicting the failure of each component included in the plant 100 . To this end, the processor 220 may determine whether the collected data is data for predicting a failure of any of several types of components.

For example, when the data collected from the plant 100 is a frequency, the processor 220 may determine that the data collected from the plant 100 is data for predicting the failure of the turbine among various types of configurations. In addition, when the data collected from the plant 100 is the number of revolutions, the processor 220 may determine that the data collected from the plant 100 is data for predicting engine failure among various types of configurations. .

In addition, the processor 220 may classify the data for predicting a failure of which configuration for various types of data collected from the plant 100 . For example, when the data collected from the plant 100 is a frequency and a rotation speed, the processor 220 classifies the frequency as data for predicting the failure of the turbine, and the rotation speed as data for predicting the failure of the engine. can do.

The processor 220 may select an optimal failure predictive model from among failure predictive models according to failure types that can be predicted by the data collected from the plant 100 . Specifically, the processor 220 may read the failure prediction models for the corresponding failure type from the memory 210 . For example, when the configuration for predicting a failure is an engine, the processor 220 reads a failure prediction model group for predicting failure of the engine stored in the memory 210, and a failure corresponding to the read failure prediction model group. Can lead predictive models.

The processor 220 may select a failure prediction model having a value most similar to the collected data among the read failure prediction models as an optimal failure prediction model. Specifically, the processor 220 may select an optimal failure prediction model using a result of dividing the data collected from the plant 100 into input data and output data. The processor 220 may set the input data as input values of the failure predictive models, and may compare output values output by the failure predictive models with the output data according to the input values.

The processor 220 may select a failure predictive model having the smallest residual as an optimal failure predictive model as a result of comparing an output value output from each of the failure predictive models with output data.

The processor 220 may predict the failure of the plant 100 using the selected optimal failure prediction model. The processor 220 may predict the predicted value and trend for a specific time point, the time and location at which the failure is expected to occur, the cause of the failure and the alarm level. That is, the processor 220 may predict an output value at a specific time in the future by inputting input data for a future time point as an input value to the optimal failure prediction model according to the current state of the plant 100 .

For example, when the current engine rotation speed is continuously increasing, the rotation speed at a specific point in the future may be estimated based on the increase degree. The processor 220 may input the estimated rotation speed as an input value of the optimal failure prediction model, and predict plant failure based on the output value.

In addition, the processor 220 may generate a new failure prediction model based on a result of predicting the failure of the plant 100 using the optimal failure prediction model. Here, the generated new failure prediction model may be stored in the memory 210 , and may be stored separately in a failure prediction model group according to the type of failure.

For example, when engine failure is predicted using a failure prediction model for predicting engine failure, a new failure prediction model generated using the result of predicting engine failure is a failure prediction model for predicting engine failure. can be Accordingly, the newly generated failure prediction model may be stored in the failure prediction model group for predicting the failure of the engine in the memory 210 . Accordingly, when predicting engine failure later, it is possible to select an optimal failure predictive model among a new failure predictive model and a failure predictive model previously stored in the memory 210 .

The failure predictive apparatus 200 according to an embodiment of the present invention selects an optimal failure predictive model from among a plurality of failure predictive models using data collected from the plant 100, and uses the selected optimal failure predictive model. Thus, the failure of the plant 100 can be predicted.

3 is a diagram illustrating a failure prediction model according to a failure type according to an embodiment of the present invention.

Referring to FIG. 3 , the memory 210 may store a failure prediction model derived in advance. Here, the failure prediction models may be models for predicting types of failures that may occur in the plant 100 . That is, at least one failure prediction model may be stored in the memory 210 according to the failure type. In addition, the failure prediction model groups according to the type of failure that may occur in the plant 100 may be separately stored in the memory 210 , and each failure prediction model group may include a plurality of failure prediction models for predicting the corresponding failure. have.

For example, Model1-1 to Model1-5 may be failure prediction models for predicting the failure of the turbine, and the failure prediction models for predicting the failure of the turbine are stored in the memory 210 as the first failure prediction model group TYPE1. They can be grouped and stored.

In addition, Model2-1 to Model2-5 may be failure predictive models for predicting engine failure, and the memory 210 includes failure predictive models for predicting engine failure as a second failure predictive model group TYPE2. They can be grouped and stored.

In addition, Model3-1 to Model3-5 may be failure prediction models for predicting the failure of the blade, and the failure prediction models for predicting the failure of the blade are in the memory 210 as a third failure prediction model group (TYPE3). They can be grouped and stored.

4 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.

Referring to FIG. 4 , the processor 220 may determine which data collected from the plant 100 is data for predicting failure of any of several types of components included in the plant 100 .

The processor 220 may read one of the failure prediction model groups stored in the memory 210 according to a result of determining which configuration of the data to predict the failure of the data collected from the plant 100 is. For example, when the data collected from the plant 100 is the frequency, the processor 220 may determine that the data is for predicting the failure of the turbine. Accordingly, the processor 220 may read the first failure predictive model group TYPE1 in which failure predictive models for predicting the failure of the turbine are grouped from the memory 210 .

The processor 220 may set input data to the failure prediction models Model1-1 to Model1-5 included in the read first failure prediction model group TYPE1 as input values. In the failure prediction models Model1-1 to Model1-5, an output value according to an input value may be output.

That is, the failure prediction model Model1-1 may output an output value 1 according to an input value, and the failure prediction model Model1-2 may output an output value 2 according to an input value, and the failure prediction model Model1- 3), the output value 3 can be output according to the input value, the failure prediction model (Model1-4) can output the output value 4 according to the input value, and the failure prediction model (Model1-5) is the output value according to the input value 5 can be output.

Here, the input data is data collected from the plant 100 and may be a result classified according to the characteristics of the data. For example, the input data may be data that affects the final result among data collected in the plant 100 .

5 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.

Referring to FIG. 5 , the processor 220 may compare output values output from each of the failure prediction models Model1-1 to Model1-5 with output data. Here, the output data is data collected from the plant 100 and may be a result of classification according to the characteristics of the data. For example, the output data may be data serving as an index for determining the failure of the plant 100 .

That is, the processor 220 compares the output value 1 output from the failure prediction model (Model1-1) with the output data, compares the output value 2 outputted from the failure prediction model (Model1-2) with the output data, and the failure prediction model Compare the output value 3 output from (Model1-3) with the output data, compare the output value 4 output from the failure prediction model (Model1-4) with the output data, and compare the output value 5 output from the failure prediction model (Model1-5) and the output data can be compared.

6 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.

Referring to FIG. 6 , the processor 220 compares output data output from each of the output values output from the failure prediction models Model1-1 to Model1-5 and outputs the output data from the failure prediction models Model1-1 to Model1-5. A residual between each of the output values and the output data can be calculated.

For example, as a result of comparing the output value 1 output from the failure prediction model (Model1-1) with the output data, the residual between the output value 1 and the output data may be 10, and the output value 2 output from the failure prediction model (Model1-2) and As a result of comparing the output data, the residual between the output value 2 and the output data may be 8. In addition, as a result of comparing the output value 3 and the output data output from the failure prediction model (Model1-3), the residual between the output value 3 and the output data may be 2, and the output value 4 output from the failure prediction model (Model1-4) and As a result of comparing the output data, the residual between the output value 4 and the output data may be 3, and as a result of comparing the output value 5 and the output data output from the failure prediction model (Model1-5), the residual between the output value 5 and the output data is 6 can be

7 is a diagram illustrating selection of an optimal failure prediction model according to a failure type according to an embodiment of the present invention.

Referring to FIG. 7 , the processor 220 may select an optimal failure prediction model based on a result of comparing each output value output from the failure prediction models Model1-1 to Model1-5 with output data.

The processor 220 may select a failure predictive model having the smallest residual with output data among the output values output from the failure predictive models Model1-1 to Model1-5 as the optimal failure predictive model Model1-3. . The selected optimal failure prediction model (Model 1-3) is the model most similar to the current state of the plant 100, and by predicting the failure of the plant 100 using this, it is possible to predict the failure of the plant 100 more accurately. can

The processor 220 predicts the predictive value and trend for a specific time point, the time and location at which the failure is expected to occur, the cause of the failure and the alarm level using the selected optimal failure prediction model (Model 1-3). can do.

8 is a diagram illustrating a method for predicting plant failure according to an embodiment of the present invention.

Referring to FIG. 8 , the processor 220 may collect data from the plant 100 ( S100 ). The data collected from the plant 100 may include temperature, pressure and humidity, NOx, SOx, O2, exhaust amount, efficiency, and power generation output for a specific configuration included in the plant 100 of the plant 100 . In addition, the data collected from the plant 100 is data about the state of the plant 100, and may include data collected from the plant 100 at a previous time point and data collected from the plant 100 at the current time point. .

In addition, the processor 220 may classify the data collected from the plant 100 into input data and output data. For example, the output data may be a parameter that can determine a failure of a specific configuration as a final result, and the input data may be a parameter that affects the final result for a specific configuration.

The processor 220 may determine whether the collected data is data for predicting which type of failure among types of failures that may occur in the plant 100 ( S200 ). Specifically, several types of components may be included in the plant 100 , and when a failure occurs in one of the various types of components, the plant 100 may be determined as a failure. Accordingly, the processor 220 may predict the failure of the plant 100 by predicting the failure of each component included in the plant 100 . To this end, the processor 220 may determine whether the collected data is data for predicting a failure of any of several types of components.

The processor 220 may read the failure prediction model group according to the failure type predictable by the data collected from the plant 100 from the memory 210 ( S300 ). The memory 210 may store failure prediction models classified according to the type of failure for each group. The processor 220 may read a failure prediction model group corresponding to a failure type predictable by the collected data from the memory 210 .

The processor 220 may select an optimal failure predictive model from among the failure predictive models included in the read failure predictive model group ( S400 ). The processor 220 may select a failure predictive model having a value most similar to the collected data among failure predictive models included in the read failure predictive model group as the optimal failure predictive model.

Specifically, the processor 220 may select an optimal failure prediction model using a result of dividing the data collected from the plant 100 into input data and output data. The processor 220 may set the input data as input values of the failure predictive models, and may compare output values output by the failure predictive models with the output data according to the input values.

The processor 220 may select a failure predictive model having the smallest residual as an optimal failure predictive model as a result of comparing an output value output from each of the failure predictive models with output data.

The processor 220 may predict the failure of the plant 100 using the selected optimal failure prediction model ( S500 ). The processor 220 may predict the predicted value and trend for a specific time point, the time and location at which the failure is expected to occur, the cause of the failure and the alarm level. That is, the processor 220 may predict an output value at a specific time in the future by inputting input data for a future time point as an input value to the optimal failure prediction model according to the current state of the plant 100 .

As described above, according to an embodiment of the present invention, an optimal failure predictive model is selected from among a plurality of failure predictive models using data collected from a plant, and failure of the plant is predicted using the selected optimal failure predictive model. It is possible to realize an apparatus and method for predicting plant failure.

Those skilled in the art to which the present invention pertains should understand that the present invention may be embodied in other specific forms without changing the technical spirit or essential characteristics thereof, so the embodiments described above are illustrative in all respects and not restrictive. only do The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. .

100: plant
200: failure prediction device
210: memory
220: processor

Claims (14)

storing the pre-derived failure prediction model in a memory;
collecting measured data from the plant;
determining whether the collected data is data for predicting which type of failure among plant failure types;
selecting an optimal failure predictive model from among a plurality of failure predictive models for predicting the determined type of failure;
A plant failure prediction method comprising the step of predicting failure of a plant using a selected failure prediction model.
According to claim 1,
Collecting the data includes:
Classifying data that can determine plant failure among data collected from the plant as output data, and classifying data affecting the output data as input data,
A plant failure prediction method for matching and storing the input data and the output data.
According to claim 1,
Storing the failure prediction model includes:
A plant failure prediction method for classifying and storing a plurality of failure prediction models into at least one failure prediction model group according to failure types.
4. The method of claim 3,
The step of selecting the optimal failure prediction model is,
A plant failure prediction method that selects the failure prediction model having the most similar value to the collected data among the output values of a plurality of failure prediction models included in the failure prediction model group corresponding to the determined type of failure as the optimal failure prediction model.
3. The method of claim 2,
The step of selecting the optimal failure prediction model is,
The input data is input to the plurality of failure predictive models, an output value output from each of the plurality of failure predictive models is compared with the output data matching the input data, and the residual between the output value and the output data is the most A plant failure prediction method that selects a small failure predictive model as an optimal failure predictive model.
According to claim 1,
The step of predicting the failure of the plant,
Predictions and trends for a specific point in time, when a failure is expected to occur, its location and alarm level, and a plant failure prediction method that predicts what causes a failure to occur.
According to claim 1,
generating a new failure prediction model based on a result of predicting failure of the plant; and
The plant failure predictive method further comprising the step of storing the new failure predictive model in a failure predictive model group to which the new failure predictive model corresponds.
a memory for storing the pre-derived failure prediction model;
The optimal failure prediction model among a plurality of failure prediction models for collecting data measured from the plant, determining which type of failure among the types of plant failure is the collected data, and predicting the determined type of failure A plant failure prediction device including a processor for selecting and predicting plant failure using the selected failure prediction model.
9. The method of claim 8,
The processor classifies data that can determine a failure of a plant among data collected from the plant as output data, and classifies data affecting the output data as input data,
The memory is a plant failure predicting device for storing the input data and the output data by matching.
9. The method of claim 8,
The memory is a plant failure prediction device for classifying and storing a plurality of failure prediction models into at least one failure prediction model group according to a failure type.
11. The method of claim 10,
The processor selects a failure prediction model having a value most similar to the collected data among output values of a plurality of failure prediction models included in the failure prediction model group corresponding to the determined type of failure as an optimal failure prediction model. Device.
10. The method of claim 9,
The processor inputs the input data to the plurality of failure predictive models, compares an output value output from each of the plurality of failure predictive models and the output data matching the input data, between the output value and the output data A plant failure predictive device that selects the failure predictive model with the smallest residual as the optimal failure predictive model.
9. The method of claim 8,
The processor is a plant failure predicting device for predicting a predictive value and trend for a specific point in time, a time when a failure is expected to occur, a location and an alarm level, and a cause of the failure.
9. The method of claim 8,
The processor generates a new failure predictive model based on a result of predicting the failure of the plant, and stores the new failure predictive model in a failure predictive model group to which the new failure predictive model corresponds.

Images