KR102078654B1 - System and method for predicting error of electric rail car - Google Patents

Abstract

Disclosed herein is a system and method for predicting failure of an electric vehicle. In one embodiment of the present application, in a system for predicting a failure of an electric vehicle, an integrated failure code table is generated based on previously collected failure information, the integrated failure code table is analyzed, and the frequency of each failure code generated within a specific reference date Data generation unit for extracting and generating failure frequency data, a data processing unit for generating a time series graph based on the failure frequency data and converting the time series graph to a stable time series graph, and analyzing the time series graph and applying it to the Arima model It provides an electric vehicle failure prediction system including a data prediction unit that derives optimal parameters for performing the above and substitutes the Arima model completed through the optimal parameters into the Arima prediction function to obtain failure prediction result data.

Description

System and method for predicting failure of an electric vehicle {SYSTEM AND METHOD FOR PREDICTING ERROR OF ELECTRIC RAIL CAR}

The present invention relates to a system and method for predicting a failure of an electric vehicle, and more particularly, to a system and method for predicting a failure of an electric vehicle based on data obtained by extracting a frequency of failure of the electric vehicle occurring within a specific reference date.

As one of the important public transportation, subways, which are used by many people, are formed by connecting multiple electric cars. Electric vehicles consist of a variety of electronic components, from relatively simple sensors, such as lighting, to important power lines that provide power to electric vehicles. As such, most of the elements that make up the electric vehicle are electronic components, and thus are not free from failures such as signal transmission errors or power cuts.

In subways that are frequently used by people, minor breakdowns of electronic components constituting an electric vehicle may lead to accidents such as fires or human accidents. In addition, this may cause a large accident due to the nature of public transportation, and it is necessary to monitor whether the electric vehicle has broken down for 24 hours.

Accordingly, the subway is equipped with a control center for each station to monitor the failure of electric vehicles in real time. However, various failure-related data obtained through such monitoring are used only for the purpose of determining a failed component and repairing the component in one time, but are not used as a means for predicting whether or not a failure has occurred again.

The present invention has been devised to solve the above-mentioned problems, and the technical problem to be achieved by the present invention is a system and method for predicting the failure of an electric vehicle by analyzing data extracting the frequency of failure of the electric vehicle occurring within a specific reference date using an Arima model. Is to provide

The technical problems to be achieved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the following description. There will be.

In order to solve the above technical problem, an embodiment of the present application, in a system for predicting a failure of an electric vehicle, generates an integrated failure code table for the electric vehicle based on previously collected failure information of the electric vehicle, and the integrated failure code Data generation unit that analyzes a table and generates failure frequency data based on the frequency of failure of the electric vehicle that occurs within a specific reference date, and data that generates a time series graph based on the failure frequency data and converts the time series graph into a stable time series graph Processing unit, and data obtained by analyzing the time series graph to derive the optimal parameters for applying to the Arima model, and substitute the completed Arima model through the optimal parameters to the Arima prediction function to obtain the failure prediction result data for the electric vehicle Po the forecaster Provides a train failure prediction system.

In the present embodiment, the previously collected fault information includes train fault code information, train operation record information, train maintenance information, and wheel trimming information of the electric vehicle, and the integrated fault code table includes the train fault code information, train It may include failure data of at least one of the number of failures, failure dates, failure codes, failure parts, and failure names of the electric vehicles according to driving record information, train maintenance information, and wheel trimming information.

In this embodiment, the data generation unit may analyze the integrated failure code table, and extract failure frequency of the electric vehicle that occurred within 3 days based on the number of failures per day to generate failure frequency data.

In the present embodiment, the data processing unit may convert the time series graph into a logarithmic function, and then convert the logarithmic function into a difference function to convert the time series graph into a stable time series graph.

In this embodiment, the failure prediction result data generated by the data prediction unit is formed as a graph in which the x-axis is a date and the y-axis is a failure frequency, and the data prediction unit extracts data having a failure frequency of 1 or more. can do.

In this embodiment, the optimal parameter corresponds to ARIMA (p, d, q) for analyzing the time series graph and applying it to the Arima model, where d is the difference order, p is the autoregression (AR) model order, q may be the moving average (MA) model order.

In the present embodiment, the Arima model may be a combined model of an autoregressive model based on weighted sums of past data and a moving average model based on weighted sums of errors of past predictions.

In addition, another embodiment of the present application in order to solve the technical problem, in the electric vehicle failure prediction method using the electric vehicle failure prediction system including a data generation unit, a data processing unit and a data prediction unit, the data generation unit is the pre-collected A data generation step of generating an integrated failure code table for the electric vehicle based on the failure information of the electric vehicle, and analyzing the integrated failure code table to generate failure frequency data based on the failure frequency of the electric vehicle occurring within a specific reference date, the data A data processing step in which the processing unit generates a time series graph based on the failure frequency data and converts the time series graph into a stable time series graph, and the data prediction unit analyzes the time series graph and derives optimal parameters for applying to the Arima model. , The Arima model completed with the optimal parameter provides a failure prediction result train failure prediction comprising the prediction data comprising: obtaining a data for the train by applying the prediction function Arima.

In the present embodiment, the previously collected fault information includes train fault code information, train operation record information, train maintenance information, and wheel trimming information of the electric vehicle, and the integrated fault code table includes the train fault code information, train It may include failure data of at least one of the number of failures, failure dates, failure codes, failure parts, and failure names of the electric vehicles according to driving record information, train maintenance information, and wheel trimming information.

In the present embodiment, the data generation step includes analyzing the integrated failure code table, and extracting the failure frequency of the electric vehicle occurring within 3 days based on the number of failures per day to generate failure frequency data. can do.

In the present embodiment, the data processing step may include converting the time series graph to a logarithmic function and then converting the logarithm function to a differential function to convert the time series graph to a stable time series graph.

In the present embodiment, the failure prediction result data generated through the data prediction step is a graph in which the x-axis is a date and a y-axis is a failure frequency, and the data prediction step includes data having a failure frequency of 1 or more. It may include the process of extraction.

In this embodiment, the optimal parameter corresponds to ARIMA (p, d, q) for analyzing the time series graph and applying it to the Arima model, where d is the difference order, p is the autoregression (AR) model order, q may be the moving average (MA) model order.

In the present embodiment, the Arima model may be a combined model of an autoregressive model based on weighted sums of past data and a moving average model based on weighted sums of errors of past predictions.

According to the present invention, it is possible to predict the failure of the electric vehicle by analyzing the data extracting the frequency of the failure of the electric vehicle occurring within a specific reference date using the Arima model.

In addition, according to the present invention, various electric vehicle-related failure data used only for one time can be used as a means for predicting whether a failure reoccurs or a failure, and by using big data technology, failure-related observation data and prediction data are integrated. I can manage it.

It should be understood that the effects of the present invention are not limited to the above-described effects, and include all effects that can be deduced from the configuration of the invention described in the detailed description or claims of the present invention.

1 is a block diagram showing a schematic configuration of an electric vehicle failure prediction system according to an embodiment of the present invention.
2 and 3 are diagrams for explaining in more detail the data generation process according to an embodiment of the present invention.
4 and 5 are views illustrating a stable time series graph according to an embodiment of the present invention.
6 and 7 are views illustrating an optimal parameter and an Arima model according to an embodiment of the present invention.
8 is a diagram illustrating a prediction function according to an embodiment of the present invention.
9 is a flowchart illustrating a procedure of a method for predicting a failure of an electric vehicle according to another embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. However, the present invention may be implemented in various different forms, and thus is not limited to the embodiments described herein. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in the present specification, and the technical spirit disclosed in the specification is not limited by the accompanying drawings, and all modifications included in the spirit and technical scope of the present invention It should be understood to include water, equivalents or substitutes. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and the size, shape, and shape of each component shown in the drawings may be variously modified. The same / similar reference numerals are attached.

The suffixes "modules" and "parts" for the components used in the following description are given or mixed only considering the ease of writing the specification, and do not have meanings or roles distinguished from each other in themselves. In addition, in the description of the embodiments disclosed herein, when it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed herein, detailed descriptions thereof are omitted.

Throughout the specification, when a part is "connected (connected, contacted, or coupled)" with another part, this means that other members in the middle, as well as when "directly connected (connected, contacted or coupled)" Also included is a case in which they are "indirectly connected (connected, contacted, or combined)" between them. Also, when a part is said to "include (equipment or provision)" a component, it does not exclude other components unless specifically stated to "include (equipment or provision)" other components. It means you can.

The terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions, unless the context clearly indicates otherwise, and distributed components may be implemented in a combined form unless otherwise specified. In this specification, terms such as “include” or “have” are intended to indicate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, and that one or more other features are present. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

1 is a block diagram showing a schematic configuration of an electric vehicle failure prediction system (hereinafter, “electric vehicle failure prediction system 10”) according to an embodiment of the present invention.

Referring to FIG. 1, the electric vehicle failure prediction system 10 includes a data generation unit 11, a data processing unit 12, and a data prediction unit 13, and may further include a database 14.

The data generation unit 11 generates an integrated failure code table for the electric vehicle based on the previously collected failure information of the electric vehicle, and analyzes the integrated failure code table to analyze the failure frequency based on the frequency of failure of the electric vehicle occurring within a specific reference date. Generate data.

In addition, the data generation unit 11 may analyze the integrated fault code table, and extract failure frequency of the electric vehicle generated within 3 days based on the number of failures per day to generate failure frequency data.

The previously collected failure information used by the data generation unit 11 may be at least one or more of train failure code information, train operation record information, train maintenance information, and wheel trimming information.

In addition, the integrated fault code table generated by the data generating unit 11 includes the number of failures of each information according to the train fault code information, train operation record information, train maintenance information, and wheel trimming information, a fault date, a fault code, and a fault region. And a record of at least one of the failure names.

The data processing unit 12 generates a time series graph based on the failure frequency data and converts the time series graph into a stable time series graph.

In addition, the data processing unit 12 may convert the time series graph into a logarithmic function, and then convert the logarithmic function into a difference function to convert the time series graph into a stable time series graph.

The data prediction unit 13 analyzes the time series graph, derives optimal parameters for applying to the Arima model, and obtains failure prediction result data for the electric vehicle by substituting the Arima model completed through the optimal parameters into the Arima prediction function. do.

The Arima model described herein is an Auto-regressive Integrated Moving Average, which corresponds to an integration of an Auto-Regressive model and a Moving Average model, and corresponds to a data analysis method. .

The failure prediction result data generated by the data prediction unit 13 may be formed as a graph in which the x-axis is the date and the y-axis is the failure frequency, and the data prediction unit 13 is data having a failure frequency of 1 or more. Can be extracted.

The database 14 may store data generated and processed through the data generation unit 11, the data processing unit 12, and the data prediction unit 13, and then record the data by indexing and digitizing the data. The creation can be performed.

2 and 3 are diagrams for explaining in more detail the data generation process according to an embodiment of the present invention.

The data generation unit 11 described with reference to FIG. 1 generates an integrated fault code table based on data of events occurring in an electric vehicle such as train fault code information, train operation record information, train maintenance information, abnormality detection information, and wheel trimming information. do. The integrated fault code table may be generated to include not only the previously collected fault information, but also additional fault information. For example, in the case of train failure code information, the data generating unit 11 uses a separate electric vehicle data collection program to query the failure record of the corresponding electric vehicle in real time and integrates the failure code information corresponding to the failure record into an integrated failure code table You can register at

Specifically, referring to FIG. 2 showing an example of the above-described train operation record information, the data generation unit 11 may determine a logic error of the train operation record information through a separate device such as a PC or a kiosk ( Rule), collect train operation record information of a specific electric vehicle, extract train operation record information of the part corresponding to the generated rule from the collected data, and reflect the fault code of the extracted information in the integrated fault code table can do.

For example, referring to FIG. 2, the data generation unit 11 determines rules and registers fault codes corresponding to various fault names, fault results, and the like in the Rule information. In addition, the data generation unit 11 enters one of the information list in Val1 of the Rule detail part, enters the information list and numbers in Val2, enters the formula of two Vals in the symbol, and connects with the following Rule: Relationships can be registered. Here, the information list means a data list of train operation record information.

In addition, referring to FIG. 3, which shows an example of the above-described train maintenance information, the data generation unit 11 may search for words (filters) for extracting fault codes from train maintenance information through a separate device such as a PC or a kiosk. When describing and defining and registering the connection classification, data including the corresponding rule can be searched among the text records described in the train maintenance data collected through the preset rule, and the data generating unit 11 has a corresponding failure. The code can be registered in the integrated fault code table.

Likewise, the abnormality detection information, the data generation unit 11 collects abnormality detection data of the corresponding facility through a separate data collection program, checks whether abnormalities such as heat and vibration are detected based on the reference data, and abnormality data The fault code of can be registered in the integrated fault code table.

In addition, the data generation unit 11 collects the wheel cut data of the electric vehicle through a separate data collection program and checks whether the data is abnormal based on the reference data to register the fault code of the faulty data in the integrated fault code table do.

4 and 5 are views illustrating a stable time series graph according to an embodiment of the present invention.

As described above, the data processing unit 12 generates a time series graph based on the failure frequency data and converts the time series graph into a stable time series graph. At this time,

A stable time series graph refers to a time series graph when the average is unchanged, the variance is unchanged, or the covariance between two time points on the graph is independent of the reference point. Therefore, as shown in the graph shown in FIG. 4, when the data processing unit 12 includes a date with a failure frequency of 0 in the failure frequency data generated by the data generation unit 11, it is formed based on the failure frequency data. Time series graphs do not correspond to stable time series graphs.

Accordingly, the data processing unit 12 may convert the time series graph into a logarithmic function, and then convert the logarithmic function into a difference function to convert the time series graph into a stable time series graph. At this time, an algorithm as shown in FIG. 5 may be used.

Specifically, referring to FIG. 5, the normal time series has the following characteristics.

First, in the case of the AR model, ACF initially has a high correlation coefficient and then gradually decreases. Since it is an autocorrelation coefficient, the correlation becomes less as the past value. In the case of the moving average (MA) model, ACF decreases completely after time k, because moving average is not considered after time k. In the case of the autoregressive (AR) model, PACF decreases completely after time k. In the case of the MA model, PACF has a high correlation coefficient and then gradually decreases.

Through these features, it is possible to grasp the p, d, and q of the Arima coefficient. In this embodiment, the optimal coefficient can be automatically derived through the existing auto.arima function, where d is the difference order. , p is the autoregressive (AR) model order, and q is the moving average (MA) model order.

6 and 7 are views illustrating an optimal parameter and an Arima model according to an embodiment of the present invention.

Optimal parameters are extracted through a set of formulas for applying the Arima model. The preset equation may be formed by an algorithm as shown in FIG. 7. Similarly, in ARIMA (p, d, q), d denotes the difference order, p denotes the autoregression (AR) model order, and q denotes the moving average (MA) model order.

The optimal parameter derived using the algorithm shown in FIG. 7 is applied to the time series graph described above to create an Arima model. As described above, the autoregressive integrated moving average (ARIMA) method combines the weighted sum of the past data (AR: autoregression) and the weighted sum of the errors of the past prediction (MA, moving average). It means the way to derive a model.

8 is a diagram illustrating a prediction function according to an embodiment of the present invention.

Referring to FIG. 8, with the generated Arima model, data after 3 days may be predicted through a preset prediction function, and a value having a frequency of 1 or more may be determined as a possible failure.

In other words, the ARIMA model to which the optimal parameter is applied is applied to the existing forecast.Arima function to obtain the predicted value, finds a value with a frequency of 1 or more, and stores the data and image in the database to display the predicted failure code. You can.

9 is a block diagram illustrating an embodiment of an electric vehicle failure prediction system according to an embodiment of the present invention.

9 is a flowchart illustrating a procedure of a method for predicting a vehicle failure according to another embodiment of the present invention, and the method for predicting a vehicle failure according to this embodiment is a vehicle failure prediction system 10 described with reference to FIGS. 1 to 8 above. It is a method for predicting the failure of an electric vehicle using. Therefore, hereinafter, descriptions overlapping with the above-described contents will be omitted.

Referring to FIG. 9, in the electric vehicle failure prediction method according to the present embodiment, in the electric vehicle failure prediction method using the electric vehicle failure prediction system including a data generation unit, a data processing unit, and a data prediction unit, the data generation unit previously collected failures A data generation step (S91) of generating an integrated fault code table based on information, analyzing the integrated fault code table, and extracting the frequency of each fault code generated within a specific reference date to generate fault frequency data (S91). A data processing step (S92) of generating the failure frequency data into a time series graph and converting the time series graph into a stable time series graph, and the data prediction unit analyzes the time series graph to derive an optimal parameter for applying the Arima model, and Arima created through optimal parameters By substituting the prediction type to the function it includes a data prediction step (S93) for obtaining a prediction result of failure data.

Here, the previously collected failure information may include train failure code information, train operation record information, train maintenance information, and wheel trimming information. In addition, the integrated fault code table may include at least one of the number of failures, the failure date, the failure code, the failure part, and the failure name of each information according to the train failure code information, train operation record information, train maintenance information, and wheel trimming information. Records may be included.

The data generation step S91 may include a process of analyzing the integrated fault code table, but extracting the frequency of the fault codes generated within 3 days based on the daily generated fault codes to generate fault frequency data.

The data processing step S92 may include a process of converting the time series graph into a logarithmic function and then converting the logarithm function into a difference function to form the time series graph into a stable time series graph.

In addition, the failure prediction result data generated through the data prediction step S93 may be a graph in which the x-axis is the date and the y-axis is the frequency of the failure. At this time, the data prediction step S93 may include a process of extracting data having a failure frequency of 1 or more.

Also in the electric vehicle failure prediction method according to the present embodiment, the optimal parameter corresponds to ARIMA (p, d, q) for analyzing the time series graph and applying it to the Arima model, where d is the difference order and p is the self-regression (AR) Model order, q may be a moving average (MA) model order, wherein the Arima model is a self-regression model based on weighted sums of past data and a moving average model based on weighted sums of errors in past predictions It can be a combined model.

The above-described electric vehicle failure prediction system 10 and the electric vehicle failure prediction method can be implemented through a mobile PC and a mobile application, respectively. For example, the electric vehicle failure prediction system 10 may be implemented in the form of a smartphone, and the functions of the data generation unit 11, the data processing unit 12, the data prediction unit 13, and the database 14 are smart. It can be implemented through storage devices such as wireless communication technology, central processing unit (Application Processor), liquid crystal display, RAM mounted on the phone, and each procedure can be performed through the application for the smartphone built in or downloaded from the smartphone. You can.

The above description of the present invention is for illustration only, and those of ordinary skill in the art to which the present invention pertains can understand that the present invention can be easily modified to other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be interpreted to be included in the scope of the present invention.

Claims (14)

A data generation unit that generates an integrated failure code table for the electric vehicle based on the previously collected failure information of the electric vehicle, and analyzes the integrated failure code table to generate failure frequency data based on the failure frequency of the electric vehicle occurring within a specific reference date. (11) and; A data processing unit (12) for generating a time series graph based on the failure frequency data and converting the time series graph into a stable time series graph; The data predicting unit (13) that analyzes the time series graph, derives optimal parameters for application to the Arima model, and substitutes the completed Arima model through the optimal parameters to the Arima prediction function to obtain failure prediction result data for the electric vehicle. Including, the previously collected fault information includes train fault code information, train operation record information, train maintenance information, and wheel trimming information of the electric vehicle, and the integrated fault code table includes the train fault code information, train operation records The failure data of at least one of the electric vehicles according to information, train maintenance information, and the number of failures of the electric vehicle, a failure date, a failure code, a failure site, and a failure name according to the wheel trimming information, and the data generation unit includes the integrated failure code Analyze the table, but record the number of failures per day In the electric vehicle failure prediction system 10 to extract the failure frequency of the electric vehicle generated within 3 days to generate a failure frequency data as a reference,
The data processing unit is configured to convert the time series graph to a logarithmic function and then convert the logarithmic function to a differential function to convert the time series graph to a stable time series graph, and the failure prediction result data generated by the data prediction unit is an x-axis. This date, the y-axis is formed as a graph set to the frequency of failure, the data prediction unit is formed to extract the data of the failure frequency of 1 or more, the optimal parameter for analyzing the time series graph to apply to the Arima model Corresponds to ARIMA (p, d, q), where d is the difference order, p is the autoregression (AR) model order, q is the moving average (MA) model order, and the Arima model is based on weighted sums of past data. The auto-regression model is a moving average model based on the weighted sum of the errors of the past prediction, The failure prediction system 10 allows the database 14 to be further provided, but the database 14 is generated and processed through the data generation unit 11, the data processing unit 12, and the data prediction unit 13 Electric vehicle failure prediction system, characterized in that it can be stored, and by indexing and numerically recording the data, it is possible to perform big data generation later.
delete delete delete delete delete delete delete delete delete delete delete delete delete

Images