KR20200052461A - Apparatus and method for predicting train fault - Google Patents

Abstract

According to an embodiment of the present invention, in order to achieve the objective of the present invention, a train malfunction prediction apparatus includes: a data collection module collecting history data, guideline data, past condition data and current condition data of a train; a data preprocessing and storage module preprocessing and storing the history data, the guideline data, the past condition data and the current condition data; a data learning module creating a malfunction diagnosis learning model diagnosing whether the train is malfunctioning by learning the history data, the guideline data, the past condition data and the current condition data, which have been preprocessed and stored, and creating a malfunction prediction learning model predicting at least one of a train malfunction cause and a train malfunction time by learning output data of the malfunction diagnosis learning model; a data diagnosis and prediction module creating diagnosis result data about whether the train is malfunctioning by applying the preprocessed and stored current condition data to the malfunction diagnosis learning model, and creating prediction result data indicating at least one of a predicted train malfunction cause and a predicted train malfunction time by applying the diagnosis result data to the malfunction prediction learning model; and a data providing module outputting at least one of the diagnosis result data and the prediction result data. Therefore, the train malfunction prediction apparatus is capable of enabling convenient repair and reducing periods for repair.

Description

Apparatus and method for predicting train fault}

The present invention relates to an apparatus and method for predicting train failure using artificial intelligence.

A train control and monitoring system (TCMS) is a device for driving and inspecting a train, and can provide information necessary for the train to operate.

In detail, the train comprehensive control device collects status information of each of a plurality of vehicles constituting the train, and provides failure information, etc. of each of the plurality of vehicles based on this, to the engineer, so that the engineer can take necessary measures for the operation. Can provide an opportunity.

On the other hand, the engineer can check the condition of the train by checking the information provided by the comprehensive train control device at the time of the service check and the maintenance person at the regular check, and perform maintenance as necessary. At this time, the engineer and maintenance personnel can check the current state of the train according to the information provided by the comprehensive train control device, and cannot predict the future train failure.

As described above, when the failure of the train cannot be predicted in advance, there are problems such as a sudden failure of the train, the operation of the train is delayed, and the cost of maintenance of the train increases after the failure.

The problem to be solved by the present invention is to provide a failure prediction apparatus and method for improving the accuracy of information provided to an engineer by applying artificial intelligence technology to data recorded in a train comprehensive control device.

In addition, it is to provide an apparatus and method for predicting a failure that prevents an accident due to a failure of a train and reduces costs due to a failure.

Train failure prediction apparatus according to an embodiment for solving the problem to be solved by the present invention is a data collection module for collecting historical data, guidance data, past state data, and current state data of the vehicle, the collected historical data, A data pre-processing and storage module for pre-processing and storing the guidance data, the past status data, and the current status data, pre-processing and storing the history data, the guidance data, and the past status data to diagnose a vehicle failure. A data learning module that generates a failure diagnosis learning model and generates a failure prediction learning model that predicts at least one of a vehicle failure timing and a vehicle failure cause by learning output data of the failure diagnosis learning model, the pre-processed and stored current state data Is applied to the fault diagnosis learning model. Generating diagnosis result data on whether a vehicle has failed, and applying the diagnosis result data to the failure prediction learning model to generate prediction result data indicating at least one of an expected vehicle failure timing and a predicted vehicle failure cause of the vehicle And a data providing module for outputting at least one of the data of the diagnostic result and the prediction result data and the prediction result data.

In this embodiment, the history data may include vehicle maintenance data.

In this embodiment, the past state data and the present state data may each include at least one of driving record data of a vehicle, fault detection record data, passenger load record data, and driving operation data.

In this embodiment, the data learning module uses a machine learning algorithm including at least one of a support vector machine (SVM), artificial neural network, Bayesian learning, deep learning, k-means cluster, and hierarchical agglomerative clustering (HAC) cluster. Thus, the failure diagnosis learning model and the failure prediction learning model may be generated.

In this embodiment, the data learning module classifies and clusters the attributes of the preprocessed and stored history data, the instruction data, and the past state data to infer a characteristic, and grasp a correlation between the characteristic and a vehicle failure By analyzing the cause of the vehicle failure.

In this embodiment, the data collection module is multiplexed so that the multiplexed data collection module simultaneously collects the history data, the instruction data, the past status data, and the current status data, and the data preprocessing and storage module is multiplexed The history data, the guidance data, the past state data, and the data preprocessing and storage module in which the multiplexed data preprocessing and storage module operates as active and standby, and the data preprocessing and storage module operating as active are collected Presence data can be preprocessed and stored.

In this embodiment, the data pre-processing and storage module separates the history data, the instruction data, the past status data, and the current status data into hexa data, image data, and text data, and separates the hexa data by field. Parsing, processing the image data into a graph image and a non-graph image, and analyzing the text data using a text mining technique.

In this embodiment, the data pre-processing and storage module pre-processes the history data, the instruction data, and the past state data in a Hadoop index file in a map-reduce form, and stores the history data, the instruction data, and the The past state data may be maintained in at least one of Hbase and Redis.

Method for predicting a train failure according to an embodiment for solving the problems to be solved by the present invention is by a data collection module, collecting historical data, guidance data, and past state data, by a data pre-processing and storage module, Pre-processing and storing the collected history data, the guidance data, and the past status data, by a data learning module, learning the history data, the guidance data, and the past status data pre-processed and stored to determine whether a vehicle has failed. Generating a failure diagnosis learning model for diagnosing, and generating, by the data learning module, a failure prediction learning model predicting at least one of a vehicle failure timing and a vehicle failure cause by learning output data of the failure diagnosis learning model Step, by the data collection module, the current state data of the vehicle Collecting, preprocessing and storing the collected current state data by the data preprocessing and storage module, and applying the preprocessed and stored current state data to the failure diagnosis learning model by the data diagnosis and prediction module Generating diagnosis result data on whether the vehicle has failed, and applying the diagnosis result data to the failure prediction learning model to generate prediction result data indicating at least one of an expected vehicle failure timing and a predicted vehicle failure cause of the vehicle And outputting at least one of the diagnosis result data and the prediction result data by the data providing module.

In this embodiment, the step of generating the failure diagnosis learning model includes: classifying and clustering attributes of the preprocessed and stored history data, the instruction data, and the past state data, and inferring a characteristic and the vehicle And analyzing the cause of the vehicle failure by grasping the correlation between the failures.

According to embodiments of the present invention, by applying the artificial intelligence technology to various data recorded in the train comprehensive control device, it is possible to provide the engineer with more accurate information required for the operation of the train.

In addition, by predicting the timing and / or cause of failures of other trains by using the failure information of trains manufactured in the same year, it is possible to provide an opportunity for the train to take action in advance before a failure occurs. And reduce the cost of failure.

In addition, since the time of failure of the train can be predicted, it is possible to predict the demand for parts according to the time of failure.

In addition, by multiplexing modules in data collection, preprocessing, and storage, reliability of collection, preprocessing, and storage can be improved.

1 is a block diagram showing the configuration of a train failure prediction apparatus according to an embodiment.
2 is a flowchart illustrating a method for predicting a train failure according to an embodiment.
3 is a view for explaining the flow of data for predicting a train failure according to an embodiment.
4 is a diagram illustrating collection, pre-processing, and storage of data according to an embodiment.
5 is a view for specifically explaining a data collection method according to an embodiment.
6 is a view for specifically explaining a data pre-processing method according to an embodiment.

The present invention can be applied to a variety of transformations and can have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all conversions, equivalents, and substitutes included in the spirit and scope of the present invention. In the description of the present invention, when it is determined that detailed descriptions of related well-known technologies may obscure the subject matter of the present invention, detailed descriptions thereof will be omitted.

In the following embodiments, terms such as first and second may be used to describe various components, but the components should not be limited by terms. The terms are only used to distinguish one component from other components.

The terms used in the following examples are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include multiple expressions, unless the context clearly indicates otherwise. In the following embodiments, the terms “include” or “have” are intended to indicate that there are features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, one or more. It should be understood that the existence or addition possibilities of other features or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

Embodiments of the present invention may be represented by functional block configurations and various processing steps. These functional blocks can be implemented with various numbers of hardware or / and software configurations that perform specific functions. For example, embodiments of the present invention may be implemented directly, such as memory, processing, logic, look-up table, etc., capable of executing various functions by control of one or more microprocessors or other control devices. Circuit configurations can be employed. Similar to the components of an embodiment of the present invention that can be implemented in software programming or software elements, an embodiment of the present invention includes various algorithms implemented in a combination of data structures, processes, routines or other programming configurations. It can be implemented in programming or scripting languages such as C, C ++, Java, and assembler. Functional aspects can be implemented with algorithms running on one or more processors. In addition, embodiments of the present invention may employ conventional techniques for electronic environment setting, signal processing, and / or data processing. Terms such as mechanisms, elements, means, and constructions can be used broadly and are not limited to mechanical and physical constructions. The term may include the meaning of a series of routines of software in connection with a processor or the like.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing the configuration of a train failure prediction apparatus 100 according to an embodiment.

Referring to FIG. 1, the train failure prediction apparatus 100 according to an embodiment includes a data collection module 110 for collecting historical data, guidance data, past state data, and current state data of a vehicle, and collected historical data, Data pre-processing and storage module 120 for pre-processing and storing guidance data, past status data, and current status data, and pre-processing and stored history data, guidance data, and past status data to learn failure diagnosis to diagnose vehicle failure. A data learning module 130 that generates a model and generates a failure prediction learning model that predicts at least one of a vehicle failure timing and a vehicle failure cause by learning the output data of the failure diagnosis learning model and failure of the preprocessed and stored current state data It is applied to the diagnostic learning model to generate diagnostic result data for vehicle failure, and Data diagnosis and prediction module 140 to generate prediction result data including at least one of a predicted vehicle failure timing and a predicted vehicle failure cause of the vehicle by applying the to the failure prediction learning model, and at least one of the diagnostic result data and the prediction result data It includes a data providing module 150 for outputting one.

Meanwhile, the apparatus 100 for predicting train failure according to embodiments of the present invention may be implemented as one physical apparatus. For example, the train failure prediction apparatus 100 may be implemented as one train general control device or one train general information system (TGIS).

The apparatus 100 for predicting train failure according to embodiments of the present invention may be implemented by organically combining a plurality of physical devices. To this end, some of the components included in the train failure prediction apparatus 100 may be implemented as any one physical device, and the other parts may be implemented as another physical device. For example, one physical device may be implemented as a part of the comprehensive train control device, and the other physical device may be implemented as a part of a server provided separately from the comprehensive train control device.

2 is a flowchart illustrating a method for predicting a train failure according to an embodiment.

Referring to FIG. 2, first, when the data collection module 110 collects historical data, guidance data, and past state data (S110), the data preprocessing and storage module 120 collects historical data, guidance data, and past The state data is pre-processed and stored (S120).

Subsequently, the data learning module 130 generates a fault diagnosis learning model for diagnosing a vehicle failure by learning pre-processed and stored history data, guidance data, and past state data (S130).

Subsequently, the data learning module 130 generates a failure prediction learning model that predicts at least one of a vehicle failure timing and a vehicle failure cause by learning the output data of the failure diagnosis learning model (S140).

Meanwhile, when the data collection module 110 collects the current state data of the vehicle (S150), the data preprocessing and storage module 120 preprocesses and stores the collected current state data (S160).

Subsequently, the data diagnosis and prediction module 140 applies the pre-processed and stored current state data to the failure diagnosis learning model generated in S130 to generate diagnosis result data about whether the vehicle has failed (S170), and the diagnosis result data to S140 The prediction result data representing at least one of a predicted vehicle failure timing and a predicted vehicle failure cause of the vehicle is generated by applying to the failure prediction learning model generated in operation S180.

The data providing module 150 outputs at least one of diagnosis result data and prediction result data (S190).

Hereinafter, each process of FIG. 2 will be described in more detail with reference to FIG. 3.

3 is a view for explaining the flow of data for predicting a train failure according to an embodiment.

Referring to FIG. 3, the train failure prediction apparatus 100 performs the operation of the first stage Stg1 for the first time, and then performs the operation of the second stage Stg2 and simultaneously performs the operation of the first stage Stg1. can do.

The operation of the first stage Stg1 relates to a failure diagnosis learning model and a failure prediction learning model generation operation, and the operation of the second stage Stg2 relates to a failure diagnosis learning model and a failure prediction learning model application operation.

When the operation of the first stage Stg1 is first described, the data collection module 110 may collect various past data for each of a plurality of trains and / or a plurality of vehicles constituting the train as a communication interface. .

The data collection module 110 may collect historical data, guidance data, environmental data, and historical status data.

The history data may include vehicle maintenance data. The vehicle maintenance data may be data indicating that a failure in the train has been repaired. Vehicle maintenance data may include, for example, train identification data, vehicle identification data, parts identification data, failure identification data, failure cause identification data, maintenance personnel identification data, maintenance date and time data, maintenance content data, and the like. have.

The instruction data may be data indicating maintenance instructions for a vehicle failure. Instruction data may include, for example, part identification data, failure identification data, failure cause identification data, maintenance content data, and the like.

The environmental data may be data representing an external environment such as temperature, rainfall, snowfall, and wind speed. The environmental data may be necessary data, particularly when the train is operating on the ground.

The past state data may include at least one of driving record data of a vehicle, failure detection record data, passenger load record data, and driving operation data.

The driving record data may include, for example, driving date and time data, train identification data, driving distance data, power consumption data, regenerative power data, and the like.

The failure detection record data is related to the failure detection, time data, speed data, distance data, daytime controller position data, cable voltage data, station data, automatic train control command data, operation mode switch data, passenger information display data, emergency braking relay Data, automatic train operation preparation data, and the like.

The passenger load record data may include date and time data, vehicle identification data, weight data, and the like.

The driving operation data may include door related data, switch related data, forward and / or reverse related data, braking command data, backing command data, and the like.

The data pre-processing and storage module 120 may pre-process the collected historical data, guidance data, environmental data, and historical status data, and store the pre-processed historical data, guidance data, environmental data, and historical status data in a database.

The data pre-processing and storage module 120 may perform pre-processing operations such as text mining, feature extraction, and quantization, but is not limited thereto.

The data learning module 130 can generate a learning model. The data learning module 130 may generate a learning model by learning data preprocessed and stored by the data preprocessing and storage module 120 using a machine learning algorithm. The data learning module 130 diagnoses failures using, for example, machine learning algorithms such as support vector machines (SVM), artificial neural networks, Bayesian learning, deep learning, k-means clusters, and hierarchical aggregator clustering (HAC) clusters. A learning model and a failure prediction learning model can be generated, respectively.

Specifically, the data learning module 130 classifies and clusters the properties of the pre-processed and stored history data, guidance data, environmental data, and past state data, infers characteristics, diagnoses vehicle failures, and compares characteristics and vehicle failures. It is possible to generate a failure diagnosis learning model by analyzing the cause of vehicle failure by grasping the correlation of.

On the other hand, the output data of the failure diagnosis learning model classifies and clusters the properties of the historical data, guidance data, environmental data, and past status data, and infers the characteristics. As a result of diagnosing the vehicle failure, correlation between the characteristics and the vehicle failure It may be data representing a result of analyzing a cause of a vehicle failure by grasping the relationship.

As described above, the data learning module 130 may generate a failure prediction learning model that predicts at least one of a vehicle failure timing and a vehicle failure cause by learning output data of the failure diagnosis learning model.

Meanwhile, data generated by the data learning module 130, for example, output data of the failure diagnosis learning model and output data of the failure prediction learning model may be stored in a database of the data preprocessing and storage module 120.

Next, when the operation of the second stage Stg2 is described, the data collection module 110 may collect various current data for each of a plurality of trains and / or a plurality of vehicles constituting the train.

The data collection module 110 according to an embodiment may collect environmental data and current state data.

The environmental data may be data representing an external environment such as temperature, rainfall, snowfall, and wind speed.

The current state data may include at least one of driving record data of the vehicle, failure detection record data, passenger load record data, and driving operation data.

The data pre-processing and storage module 120 may pre-process the collected environmental data and the current state data, and store the pre-processed environmental data and the current state data in a database.

The data preprocessing and storage module 120 may perform preprocessing operations such as normalization, dimension reduction, feature extraction, quantization, and missing value processing, but is not limited thereto.

The data diagnosis and prediction module 140 may apply the learning model generated in the first stage Stg1. The data diagnosis and prediction module 140 applies the data pre-processed and stored by the data pre-processing and storage module 120 to the learning model generated in the first stage Stg1, and results of diagnosis and prediction of the vehicle's failure. At least one of the data can be generated.

In detail, the data diagnosis and prediction module 140 applies pre-processed and stored environmental data and current state data to the failure diagnosis learning model to generate diagnosis result data on whether the vehicle has failed, and to diagnose the failure result data to diagnose the failure result. It can be applied to generate predictive result data indicating at least one of a predicted vehicle failure timing and a predicted vehicle failure cause of the vehicle.

On the other hand, data generated by the data diagnosis and prediction module 140, for example, at least one of diagnosis result data and prediction result data for whether a vehicle has failed may be stored in a database of the data preprocessing and storage module 120. have.

The data providing module 150 may provide data generated by the data diagnosis and prediction module 140 to an engineer or maintenance personnel. The data providing module 150 may display, for example, at least one of diagnosis result data and prediction result data on whether the vehicle has failed, through a screen.

On the other hand, data provided by the data providing module 150, for example, at least one of diagnosis result data and prediction result data on whether a vehicle has failed may be stored in a database of the data pre-processing and storage module 120.

The data learning module 130 not only pre-processed history data, guidance data, environmental data, and past state data stored in the database of the data pre-processing and storage module 120, but also outputs data of the failure diagnosis learning model and outputs of the failure prediction learning model. By using data, pre-processed environmental data and current status data, diagnostic result data for vehicle failure, and predictive result data for vehicle failure, it is also used to generate a failure diagnosis learning model in S130 and a failure prediction learning model in S140. , Progressive and augmented learning can be performed, and as a result, more accurate fault diagnosis learning models and fault prediction learning models can be generated.

4 is a diagram illustrating collection, pre-processing, and storage of data according to an embodiment.

Referring to FIG. 4, the data collection module 110 may collect data using a plume.

The data pre-processing and storage module 120 may pre-process data using Kafka.

The data pre-processing and storage module 120 may store data in a database based on Hadoop.

In detail, the data pre-processing and storage module 120 stores the pre-processed history data, guide data, environment data, and past state data in a Hadoop index file in a map-reduce form, and stores the stored history data, guide data, environment data, And the past state data may be maintained in at least one of Hbase and Redis.

Meanwhile, the data pre-processing and storage module 120 may apply at least one of Impala, Zeppelin, and Mahout to the diagnosis result data and the prediction result data for whether the vehicle is stored in the database. Can be.

Meanwhile, the data pre-processing and storage module 120 may store data in a database in a Sqoop method. The database in which data is stored in the scan method can be used as a business database.

5 is a view for specifically explaining a data collection method according to an embodiment.

Referring to FIG. 5, the data collection module 110 and the data preprocessing and storage module 120 may be multiplexed.

The multiplexed data collection module 110 may collect historical data, guidance data, environmental data, past status data, and current status data at the same time. For example, the data collection module A 110A and the data collection module B 110B may simultaneously collect historical data, guidance data, environmental data, past status data, and current status data.

 Data collection module A (110A) delivers historical data, guidance data, environmental data, past state data, and current state data collected from source 1 to sink 1 through channel 1, and data collection module B (110B) is source The history data, guidance data, environmental data, past status data, and current status data collected in 2 can be transmitted to sink 2 through channel 2.

The historical data received by the sink 1 of the data collection module A (110A) and the sink 2 of the data collection module B (110B), guidance data, environmental data, past state data, and current state data are respectively collected by the data collection module C (110C). Can be passed on.

Data collection module C (110C) delivers historical data, guidance data, environmental data, past status data, and current status data collected from source 3 to channels 3A and 3B, respectively, through an interceptor, and channels 3A and 3B are Historical data, guidance data, environmental data, past status data, and current status data can be transmitted to sink 3A and sink 3B, respectively.

Sink 3A and sink 3B of data collection module C 110C may deliver historical data, guidance data, environmental data, past status data, and current status data to multiplexed data preprocessing and storage module 120, respectively.

As described above, by multiplexing the data collection module 110, collection reliability can be improved.

The multiplexed data pre-processing and storage module 120 may operate as active and standby. For example, the data pre-processing and storage module A 120A may operate as active, and the data pre-processing and storage module B 120B may operate as a standby.

The active data pre-processing and storage module 120 may pre-process and store the collected history data, guidance data, past status data, and current status data.

For example, the buffer and divider 1 of the data preprocessing and storage module A (120A) operating as active can be used to transfer the historical data, guidance data, environmental data, past status data, and current status data to hexa data, image data, and Separated into text data, hexa data can be processed by hexa data preprocessor 1, image data by image data preprocessor 1, and text data by text data preprocessor 1.

The hexa data may be, for example, operation data or alarm data.

At this time, the hexa data preprocessor 1 may preprocess the hexa data by parsing the hexa data for each field. The image data preprocessor 1 may preprocess image data by separating and processing the image data into a graph image and a non-graph image. The text data preprocessor 1 may preprocess the text data by analyzing the text data using a text mining technique.

Thereafter, the pre-processed hexa data may be classified and stored as a bit unit field defined by the train synthesis control device, and the pre-processed graph image data may be stored with sampling and quantized graph information, and the pre-processed non-graph image data The summary information may be stored through dimension reduction and feature extraction, and the pre-processed text data may be basically stored as classified unit sentences, and may be patterned and stored if necessary.

While the data preprocessing and storage module A 120A operating as active performs the above operations, the data preprocessing and storage module B 120B operating as standby performs operations performed by the data preprocessing and storage module A 120A. It may not.

As such, the data pre-processing and storage module 120 is multiplexed, so that the reliability of collection can be improved.

6 is a view for specifically explaining a data pre-processing method according to an embodiment.

Referring to FIG. 6, the data pre-processing and storage module 120 includes a buffer 121, a distributor 122, a pre-processing manager 123, a data pre-processor 124A, 124B, 124C, and a log recorder 125 do.

The buffer 121 may temporarily store data received from the data collection module 110.

The divider 122 may classify data temporarily stored in the buffer 121 into hexa data, image data, and text data.

The distributor 122 may include a buffer loader 1221, a file rule loader 1222, a header parser 1223, a classification and anomaly verifier 1224, and a file anomaly verifier 1225.

The buffer loader 1221 may transmit data temporarily stored in the buffer 121 to the header parser 1223. Data transmitted to the header parser 1223 may be transmitted to the pre-processing manager 123 and the log recorder 125 through the classification and anomaly verifier 1224 and the file anomaly verifier 1225.

The file rule loader 1222 may receive an XML file in which the file type and structure are defined from the outside and transmit the XML file to the classification and anomaly verifier 1224. The XML file can be composed of <Header>, <Body>, and <Parser>.

Meanwhile, the pre-processing manager 123 transmits the hexa data received from the distributor 122 to the hexa data pre-processor 124A, the image data received from the distributor 122 to the image data pre-processor 124B, and the distributor 122. The text data received from can be transferred to the text data preprocessor 124C.

As described above, the hexa data preprocessor 124A can parse the hexa data for each field, and the image data preprocessor 124B can process the image data by separating it into a graph image and a non-graph image. The text data preprocessor 124C may analyze text data using a text mining technique.

According to embodiments of the present invention, by applying the artificial intelligence technology to various data recorded in the train comprehensive control device, it is possible to provide the engineer with more accurate information required for the operation of the train.

In addition, by predicting the timing and / or cause of failures of other trains by using the failure information of trains manufactured in the same year, it is possible to provide an opportunity for the train to take action in advance before a failure occurs. And reduce the cost of failure.

In addition, since the time of failure of the train can be predicted, it is possible to predict the demand for parts according to the time of failure.

In addition, by multiplexing modules in data collection, preprocessing, and storage, reliability of collection, preprocessing, and storage can be improved.

So far, the present invention has been focused on preferred embodiments. Those skilled in the art to which the present invention pertains will understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention.

Therefore, the disclosed embodiments should be considered in terms of explanation, not limitation. The scope of the present invention is shown in the claims rather than the foregoing description, and the invention claimed by the claims and the inventions equivalent to the claimed invention should be construed as being included in the present invention.

100: train failure prediction device
110: data collection module
120: data pre-processing and storage module
130: data learning module
140: data diagnosis and prediction module
150: data provision module

Claims (10)

A data collection module for collecting historical data, guidance data, past status data, and current status data of the vehicle;
A data preprocessing and storage module for preprocessing and storing the collected history data, the instruction data, the past status data, and the current status data;
A failure diagnosis learning model for diagnosing a vehicle failure by generating the pre-processed and stored history data, the instruction data, and the past state data is generated, and the vehicle failure timing and vehicle failure by learning the output data of the failure diagnosis learning model A data learning module generating a failure prediction learning model predicting at least one of the causes;
Pre-processed and stored current state data is applied to the failure diagnosis learning model to generate diagnosis result data on whether the vehicle has failed, and the diagnosis result data is applied to the failure prediction learning model to predict a vehicle's expected vehicle failure time. And a data diagnosis and prediction module generating prediction result data indicating at least one of a predicted vehicle failure cause. And
And a data providing module that outputs at least one of the diagnosis result data and the prediction result data. The method according to claim 1,
The historical data includes vehicle maintenance data, a train failure prediction device. The method according to claim 1,
The past state data and the current state data are respectively,
An apparatus for predicting train failure, comprising at least one of a vehicle driving record data, a failure detection record data, a passenger load record data, and a driving operation data. The method according to claim 1,
The data learning module uses the machine learning algorithm including at least one of SVM (Support Vector Machine), artificial neural network, Bayesian learning, deep learning, k-means clustering, and HAC (Hierarchical Agglomerative Clustering) clustering. A train failure prediction apparatus for generating a model and the failure prediction learning model. The method according to claim 1,
The data learning module classifies and clusters the properties of the pre-processed and stored history data, the instruction data, and the past state data, infers a characteristic, understands a correlation between the characteristic and a vehicle failure, and causes the vehicle failure. Train breakdown prediction device to analyze. The method according to claim 1,
The data collection module is multiplexed so that the multiplexed data collection module simultaneously collects the history data, the instruction data, the past status data, and the current status data,
The history data, the instruction data from which the data preprocessing and storage module is multiplexed, the multiplexed data preprocessing and storage module is active and standby, and the active data preprocessing and storage module is collected , Pre-processing and storing the past state data and the present state data, Train failure prediction device. The method according to claim 1,
The data pre-processing and storage module separates the history data, the instruction data, the past status data, and the current status data into hexa data, image data, and text data, parses the hexa data per field, and the image A train failure prediction apparatus that processes data by separating it into a graph image and a non-graph image, and analyzes the text data using a text mining technique. The method according to claim 1,
The history data, the instruction data, and the past status data pre-processed by the data pre-processing and storage module are stored in a Hadoop index file in a MapReduce format, and the stored history data, the instruction data, and the past status data are Hbase. And redis maintained in at least one form. Collecting historical data, guidance data, and historical status data by a data collection module;
Pre-processing and storing the collected historical data, the instruction data, and the past state data by a data pre-processing and storage module;
Generating a failure diagnosis learning model for diagnosing a vehicle failure by learning the history data, the instruction data, and the past state data pre-processed and stored by the data learning module;
Generating, by the data learning module, a failure prediction learning model predicting at least one of a vehicle failure timing and a vehicle failure cause by learning output data of the failure diagnosis learning model;
Collecting, by the data collection module, current state data of the vehicle;
Pre-processing and storing the collected current state data by the data pre-processing and storage module;
The data diagnosis and prediction module applies the preprocessed and stored current state data to the failure diagnosis learning model to generate diagnosis result data on whether the vehicle has failed, and applies the diagnosis result data to the failure prediction learning model Generating prediction result data indicating at least one of a predicted vehicle failure timing and a predicted vehicle failure cause of the vehicle; And
And outputting at least one of the diagnosis result data and the prediction result data by a data providing module. The method according to claim 9,
Generating the failure diagnosis learning model,
Classifying and clustering attributes of the pre-processed and stored history data, the instruction data, and the past state data to infer a characteristic; And
And analyzing a cause of the vehicle failure by understanding a correlation between the characteristic and a vehicle failure.

Images