KR102077255B1 - Method and computer program for inferring fault part of e-train - Google Patents

Abstract

According to an embodiment of the present invention, a method of inferring a failure site of the electric locomotive based on failure identification information of the electric locomotive includes: detection results of the failure identification information of the electric locomotive and a plurality of parts constituting the electric locomotive. Acquiring first sensor data comprising a; Determining, by the case analyzer, one or more candidate failure cases corresponding to the failure identification information; Comparing second sensor data with respect to each of the one or more candidate failure cases and the first sensor data to determine any one of the one or more candidate failure cases as a failure case of an electric locomotive; And determining, by the failure analyzer, a failure site corresponding to the failure case of the electric locomotive.

Description

METHODS AND COMPUTER PROGRAM FOR INFERRING FAULT PART OF E-TRAIN}

The present invention relates to a method and a computer program for inferring a failure site of an electric locomotive, and to a method and a computer program for inferring a failure site based on the failure identification information of the electric locomotive.

BACKGROUND OF THE INVENTION The development of techniques to find the cause that affects the failure or deterioration of a mechanical device has been attempted in various fields including the medical field and the industrial field. In particular, many researches related to various products have been conducted in the industrial field.

In this regard, Bonnet (2000) presented a methodology to find the failure cause through RCA (Root Cause Analysis) by collecting failure mode, failure pattern, appearance, maintenance history, etc. for analysis of AC motor and failure cause. Stefanovych (2015) proposed a methodology based on the Markov model by visualizing the failure state base in a diagram.

In relation to the failure cause analysis of electric locomotives, the actual companies use the method to identify the cause of the failure by collecting the causes of the failure caused by the maintenance personnel's subjective experience. This method has a problem in that failure cause analysis results vary according to the individual engineers' ability.

In addition, depending on the individual's experience and knowledge, there is a problem that the analysis technology of the cause of failure is difficult to be incorporated into the company's own technology.

 Therefore, there is a need for a more systematic method of analyzing the causes of product failures based on the various data generated by electric locomotives.

The background art described above is technical information possessed by the inventors for the derivation of the present invention or acquired in the derivation process of the present invention, and may not necessarily be known technology disclosed to the general public before the present application.

The present invention seeks to provide information about a failure site corresponding to the failure identification information.

In particular, the present invention is intended to be able to perform a more precise cause analysis of the failure by clearly telling where the failure site in the failure diagnosis of the train.

In addition, the present invention is intended to enable the user to more easily, quickly and accurately diagnose the failure of the electric locomotive.

The present invention further seeks to reduce costs and resources for the maintenance of electric locomotives.

According to an embodiment of the present invention, a method of inferring a failure site of the electric locomotive based on failure identification information of the electric locomotive includes: detection results of the failure identification information of the electric locomotive and a plurality of parts constituting the electric locomotive. Acquiring first sensor data comprising a; Determining, by the case analyzer, one or more candidate failure cases corresponding to the failure identification information; Comparing second sensor data with respect to each of the one or more candidate failure cases and the first sensor data to determine any one of the one or more candidate failure cases as a failure case of an electric locomotive; And determining, by the failure analyzer, a failure site corresponding to the failure case of the electric locomotive.

The case analyzer is a data set representing a correlation between a plurality of failure identification information and a plurality of failure cases, and the failure part reasoning method of the electric locomotive may include: learning the case analyzer before the obtaining; It may further include.

The training of the case analyzer may include obtaining a plurality of first learning data including failure identification information and a failure case corresponding to the failure identification information; And updating the case analyzer based on the plurality of first learning data.

The determining of the failure case of the electric locomotive may include retrieving second sensor data having the highest similarity with the first sensor data among the second sensor data; And determining a candidate failure case corresponding to the second sensor data having the highest similarity as the failure case of the electric locomotive.

The failure analyzer may be a data set expressing a correlation between a plurality of failure cases and a plurality of failure sites, and the failure location inference method of the electric locomotive may further include: learning the failure analyzer prior to the acquiring step. have.

The training of the failure analyzer may include obtaining a plurality of second learning data including third sensor data including detection results of a plurality of parts of the electric locomotive and a failure case corresponding to the third sensor data. Making; Calculating a degree of association between a plurality of portions constituting the electric locomotive and a first failure case based on the plurality of second learning data; And updating the failure analyzer to match the first failure case with a site having an association degree that satisfies a predetermined condition.

The training of the failure analyzer may be performed by repeatedly calculating the correlation and determining the failure site for a plurality of first failure cases.

The method for inferring a failure site of the electric locomotive may further include providing information regarding the failure site to a user terminal after determining the failure site.

According to the present invention, it is possible to provide information about a failure site corresponding to the failure identification information.

In particular, in the diagnosis of train failure, it is possible to perform a more precise cause analysis of the failure by clearly indicating where the failure is.

It also allows users to more easily, quickly and accurately diagnose faults on electric locomotives.

Furthermore, the cost and resources for the maintenance of the electric locomotive can be saved.

1 and 2 schematically show the configuration of the failure site inference system of the electric locomotive according to an embodiment of the present invention.
3 is a diagram for describing failure identification information and first sensor data of an electric locomotive obtained by a processor according to an exemplary embodiment of the present invention.
4 is a diagram for describing a process of determining, by a processor, a candidate failure case using a case analyzer according to an embodiment of the present invention.
FIG. 5 is a diagram for describing a process of determining, by a processor, a failure case of an electric locomotive from one or more candidate failure cases according to an embodiment of the present invention.
6 is a diagram for describing a process of determining, by a processor, a failure site by using a failure analyzer, according to an exemplary embodiment.
7 is a flowchart illustrating a failure site inference method performed by the failure site inference apparatus according to an embodiment of the present invention.
8 is an illustration of a screen displayed on the display means of the user terminal according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION The following detailed description of the invention refers to the accompanying drawings that show, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It is to be understood that the various embodiments of the invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein may be implemented with changes from one embodiment to another without departing from the spirit and scope of the invention. In addition, it is to be understood that the location or arrangement of individual components within each embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention should be taken as encompassing the scope of the claims of the claims and all equivalents thereof. Like reference numerals in the drawings indicate the same or similar elements throughout the several aspects.

DETAILED DESCRIPTION Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention.

1 and 2 schematically show the configuration of the failure site inference system of the electric locomotive according to an embodiment of the present invention.

The failure site inference system of the electric locomotive according to an embodiment of the present disclosure may infer the failure site of the electric locomotive 300 based on the failure identification information of the electric locomotive 300. To this end, the failure site inference system of the electric locomotive according to an embodiment of the present invention, the electric locomotive 300, the failure site inference device 100, the user terminal 200 and the communication network that interconnects them to determine the failure site ( 400).

The electric locomotive 300 according to an embodiment of the present invention includes a sensor for detecting an abnormality of a corresponding part in a plurality of parts constituting the electric locomotive 300, and outputs failure identification information when a failure occurs. It can mean a variety of devices. For example, the electric locomotive 300 is an electric train driven as its name, and may include a sensor for detecting an abnormal state and / or an operation state of each brake, door, control panel, and the like.

In addition, despite the name, the electric locomotive 300 is a train driven by various energy sources (for example, coal, oil, gas, etc.) in addition to electricity, and may also mean a train having sensors in a plurality of parts. The electric locomotive 300 may refer to a mechanical device having a sensor at a plurality of portions as various devices driven by various energy sources.

However, hereinafter, for convenience of description, the electric locomotive 300 is a train driven by electricity as its name, and a sensor for detecting an abnormality and / or an operation state in a plurality of parts constituting the electric locomotive 300. It will be explained on the premise that it is provided.

In the present invention, the 'failure identification information' is information generated by the control device of the electric locomotive 300 to inform the failure status and / or the situation of the electric locomotive 300, and is used for diagnosing the state of the electric locomotive 300. It can mean information.

For example, the failure identification information is a predefined failure code, and may be a string consisting of numbers and / or letters such as '4004'. However, this is merely exemplary and the spirit of the present invention is not limited thereto.

The electric locomotive 300 according to an embodiment of the present invention may transmit the above-described failure identification information to the failure site inference device 100 at the request of the failure site inference device 100 described later, and the failure site inference device ( 100 may infer the failure site of the electric locomotive 300 based on the failure identification information. Detailed description thereof will be described later.

The user terminal 200 according to an exemplary embodiment of the present invention may refer to various devices that receive information about a failure site of the electric locomotive 300 from the failure site inference apparatus 100 and display or provide the same to a user. have. In this case, the terminal may be a portable terminal 201 or may be a personal computer 202.

The user terminal 200 may be provided with display means for displaying information on a failure site, input means for obtaining a user input, and the like. At this time, the input means and the display means may be configured in various ways. For example, the input means may include a keyboard, a mouse, a trackball, a microphone, a button, a touch panel, and the like. The display means may include any one of a cathode ray tube (CRT), a liquid-crystal display (LCD), a plasma display panel (PDP), and an organic light emitting diode (OLED). However, this is merely exemplary and the spirit of the present invention is not limited thereto.

The communication network 400 according to an embodiment of the present invention may provide a data transmission / reception path between the above-described user terminal 200 and the failure site inference apparatus 100 described later. In this case, the communication network 400 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broad band network (BBN), and the Internet ( One or more of a network such as the Internet).

In addition, the communication network 400 may include any one or more of network topologies including a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree, or a hierarchical network. It is not limited.

The failure site inference apparatus 100 according to an embodiment of the present invention may infer the failure site of the electric locomotive 300 based on the failure identification information of the electric locomotive 300. To this end, the failure site inference apparatus 100 according to an embodiment of the present invention may include a memory 111, a processor 112, a communication module 113, and an input / output interface 114 as shown in FIG. 2. have.

The memory 111 may be a computer-readable recording medium, and may include a non-volatile mass storage device such as a random access memory (RAM), a read only memory (ROM), and a disk drive. In addition, the memory 111 may store an operating system and at least one program code.

These software components may be loaded from a computer readable recording medium separate from the memory 111 using a drive mechanism. Such a separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, and the like.

In other embodiments, the software components may be loaded into the memory 111 via the communication module 113 rather than the computer readable recording medium. For example, the at least one program may be loaded into the memory 111 based on a program installed by files provided through a communication network 400 by a file distribution system for distributing installation files of developers or applications. .

The processor 112 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor 112 by the memory 111 or the communication module 113. For example, the processor 112 may be configured to execute a command received according to a program code stored in a recording device such as the memory 111.

The communication module 113 provides a function for the failure site inference apparatus 100 and the user terminal 200 to communicate with each other through the communication network 400, or the failure site inference apparatus 100 and the electric locomotive 300 are in contact with each other. It may provide a function for communicating.

For example, a request generated by the processor 112 of the failure site inference apparatus 100 according to a program code stored in a recording device such as the memory 111 may be transmitted to a user through the communication network 400 under the control of the communication module 113. It may be delivered to the terminal 200.

Of course, the communication module 113 may provide a function for communicating with the electric locomotive 300 (particularly, the controller of the electric locomotive).

The input / output interface 114 may be a means for interfacing with the input / output device 115. In this case, the input device may include, for example, a device such as a keyboard or a mouse. The output device may also include a device such as a display for displaying a communication session of the application. As another example, the input / output interface 114 may be a means for interfacing with a device in which functions for input and output are integrated into one, such as a touch screen. In addition, in another embodiment, the failure site inference apparatus 100 may include more components than those of FIG. 2.

Hereinafter, the failure site of the electric locomotive 300 is based on the failure identification information of the electric locomotive 300 by the processor 112 of the failure site inference apparatus 100 according to an exemplary embodiment of the present disclosure through FIGS. 3 to 6. Explain how to reason.

The processor 112 according to an embodiment of the present disclosure may acquire failure identification information of the electric locomotive 300 and first sensor data of the electric locomotive 300. As described above, in the present invention, the 'failure identification information' is information generated by the control device of the electric locomotive 300 to inform the failure situation and / or the current state of the electric locomotive 300, for example, predefined such as '4004'. It can be a failure code.

In addition, in the present invention, the 'sensor data' such as the first sensor data and the second sensor data may refer to sensor values obtained by the controller of the electric locomotive 300 from sensors installed at respective parts of the electric locomotive 300.

FIG. 3 is a diagram for describing failure identification information 510 and first sensor data 520 of the electric locomotive 300 obtained by the processor 112 according to an embodiment of the present invention.

As described above, the failure identification information 510 may be in the form of a predefined failure code. In addition, the sensor data 520 may be in the form of numbers (or in the form of numbers and letters, as shown).

For example, referring to the first sensor data 501, the processor 112 may acquire the failure identification information 511 and corresponding first sensor data (numbers corresponding to X1 to X3).

Meanwhile, although FIG. 3 shows two sensor data and each sensor data includes only three sensor values (X1, X2, X3), it should be understood as an example.

Meanwhile, the processor 112 according to an embodiment of the present invention may determine one or more candidate failure cases corresponding to the failure identification information by the case analyzer.

FIG. 4 is a diagram for describing a process of determining, by the processor 112, candidate failure cases 531 to 533 using the case analyzer 610 according to an embodiment of the present invention.

First, in the present invention, the 'case analyzer' 610 may be a data set representing a correlation between a plurality of failure identification information and a plurality of failure cases. In other words, when the case analyzer 610 receives the specific failure identification information 511, the case analyzer 610 may output one or more candidate failure cases 531 to 533 with respect to the received failure identification information 511.

In this case, the candidate failure case may refer to one or more failure states that share failure identification information. For example, when there are three failure states in which the failure identification information is '4004' as shown in FIG. 4, each of the three failure states is a candidate failure case (531 to 533) when the failure identification information is '4004'. It may correspond to.

Looking at the process of the processor 112 according to an embodiment of the present invention to learn the case analyzer 610 in more detail, the processor 112 includes a plurality of failure identification information and a failure case corresponding to the failure identification information; First training data may be obtained. In addition, the processor 112 may update the case analyzer 610 based on the plurality of first learning data.

In other words, the processor 112 according to an exemplary embodiment of the present disclosure may update the case analyzer 610 based on the failure identification information and the failure case in which the corresponding relationship is already known.

In this case, the processor 112 may update the case analyzer 610 by creating information about a failure case for each failure identification information in the form of a look-up table. In this case, 'learning' may mean updating the lookup table.

Meanwhile, the processor 112 may generate and update the case analyzer 610 using a machine learning method. In this case, 'learning' may mean updating the coefficients constituting the case analyzer. However, the two cases described above are exemplary and the spirit of the present invention is not limited thereto.

As described above, various failure cases 531 to 533 may exist under the same failure identification information 511. Accordingly, in order to clarify the failure site according to the failure identification information 511, the processor 112 according to an embodiment of the present invention may include the second sensor data and each of the one or more candidate failure cases 531 to 533. 1 Sensor data can be compared. The processor 112 may also determine any one of the one or more candidate failure cases 531 to 533 as the failure case of the electric locomotive. In this case, the first sensor data may be obtained by the processor 112 from the electric locomotive 300 by the above-described process.

FIG. 5 is a diagram for describing a process of determining, by the processor 112, a failure case of an electric locomotive among one or more candidate failure cases 531 to 533 according to an embodiment of the present invention.

For convenience of description, the second sensor data 541 to 543 for each of the candidate failure cases 531 to 533 are shown in FIG. 5, and each of the second sensor data 541 to 543 and the first sensor data is shown in FIG. 5. Assume that the similarity between the sensor data 521 is as shown.

Under the foregoing assumption, the processor 112 according to an embodiment of the present invention searches for the second sensor data 542 having the highest similarity with the first sensor data 521 among the second sensor data 541 to 543. Can be. In this case, the processor 112 according to an embodiment of the present invention may determine the similarity between sensor data according to various known techniques. For example, the processor 112 may generate two vectors having individual sensor values as components of a vector for each of the first sensor data and the second sensor data, and determine similarity between the sensor data based on the distance between the two vectors. have. However, this is merely exemplary and the spirit of the present invention is not limited thereto.

Subsequently, the processor 112 according to an embodiment of the present invention may determine the candidate failure case 532 corresponding to the second sensor data 542 having the highest similarity as the failure case of the electric locomotive 300.

The processor 112 according to an embodiment of the present invention may determine, by the failure analyzer, a failure site corresponding to the failure case (that is, the candidate failure case 532) of the electric locomotive 300.

FIG. 6 is a diagram for describing a process of determining a failure area 550 by the processor 112 according to an embodiment of the present invention using the failure analyzer 620.

In the present invention, the 'failure analyzer' 620 may be a data set expressing a correlation between a plurality of failure cases and a plurality of failure sites. In other words, when a failure analyzer 532 is input, the failure analyzer may output one or more failure sites 550 for the received failure case 532.

Looking at the process of the processor 112 according to an embodiment of the present invention to learn the failure analyzer 620 in more detail, first, the processor 112 according to an embodiment of the present invention constitutes an electric locomotive 300 A plurality of second learning data including sensor data including a sensing result of a plurality of parts and a failure case corresponding to the sensor data may be obtained.

The processor 112 may calculate a degree of association between the plurality of portions constituting the electric locomotive 300 and the first failure case, based on the plurality of second training data. In this case, the processor 112 may calculate a degree of association between the plurality of parts and the first failure case according to various known techniques.

For example, the processor 112 may calculate the degree of association between the two, that is, the parts constituting the train and the failure case according to the association rule. On the other hand, 'association degree' may mean the degree to which the failure of a part is related to what failure.

As a specific example, for example, if the processor 112 shows a similar tendency in the plurality of sensor data for a failure case, the sensor value for a specific region, the processor 112 may be associated with the specific region and the corresponding failure case. The association may be judged to be high.

On the other hand, the processor 112 may update the failure analyzer 620 to correspond to the first failure case and one or more sites where the degree of association satisfies a predetermined condition. In this case, the 'predetermined condition' may be a condition in which the degree of association is greater than or equal to the critical degree of association, or the condition in which the degree of association is within the upper N (N is a natural number).

In other words, when the first failure case is input to the failure analyzer 620, the processor 112 may update the failure analyzer 620 to output one or more parts corresponding to a predetermined condition in response thereto. Can be.

In this case, the processor 112 may update the failure analyzer 620 by preparing information about a failure part of each failure case in the form of a look-up table. In this case, 'learning' may mean updating the lookup table.

Meanwhile, the processor 112 may generate and update the failure analyzer 620 by a machine learning method. In this case, 'learning' may mean updating the coefficients constituting the failure analyzer 620. However, the two cases described above are exemplary and the spirit of the present invention is not limited thereto.

Meanwhile, the learning process of the failure analyzer 620 may be repeatedly performed for the plurality of first failure cases.

As described above, the present invention can provide more accurate cause analysis for a failure by providing a failure site in a train failure diagnosis, and further reduce costs and resources for maintenance of an electric locomotive.

On the other hand, the processor 112 according to an embodiment of the present invention may provide the user terminal 200 with information about a failure site determined by the above-described process. The user may identify a failure site through the user terminal 200 and take appropriate measures.

7 is a flowchart illustrating a failure site inference method performed by the failure site inference apparatus 100 according to an exemplary embodiment of the present invention. Hereinafter, descriptions of contents overlapping with those described in FIGS. 1 to 6 will be omitted, but will be described with reference to FIGS. 1 to 6.

Failure site inference apparatus 100 according to an embodiment of the present invention can train the case analyzer and the failure analyzer. (S71) (S72)

Referring to FIG. 4 again, a process of learning the case analyzer 610 by the failure site inference apparatus 100 according to an exemplary embodiment will be described in more detail. The failure site inference apparatus 100 according to an exemplary embodiment may obtain a plurality of first learning data including failure identification information and a failure case corresponding to the failure identification information. In addition, the failure site inference apparatus 100 may update the case analyzer 610 based on the plurality of first learning data.

In other words, the failure site inference apparatus 100 according to an embodiment of the present invention may update the case analyzer 610 based on the failure identification information and the failure case in which the corresponding relationship is already known.

In this case, the failure site inference apparatus 100 may update the case analyzer 610 by creating information about a failure case for each failure identification information in the form of a look-up table. In this case, 'learning' may mean updating the lookup table.

Meanwhile, the failure site inference apparatus 100 may generate and update the case analyzer 610 using a machine learning method. In this case, 'learning' may mean updating the coefficients constituting the case analyzer. However, the two cases described above are exemplary and the spirit of the present invention is not limited thereto.

Referring to FIG. 6 again, a process of training the failure analyzer 620 by the failure site inference apparatus 100 according to an embodiment of the present invention will be described in more detail. The failure site inference apparatus 100 according to an embodiment of the present invention may include a plurality of sensor data including detection results of a plurality of parts of the electric locomotive 300 and a failure case corresponding to the sensor data. Second training data may be obtained.

The failure site inference apparatus 100 may calculate a degree of association between the plurality of sites constituting the electric locomotive 300 and the first failure case, based on the plurality of second learning data. In this case, the failure site inference apparatus 100 may calculate a degree of association between the plurality of sites and the first failure case according to various known techniques.

For example, the failure site inference apparatus 100 may calculate a degree of association between the two (that is, the site constituting the train and the failure case) according to an association rule. On the other hand, 'association degree' may mean the degree to which the failure of a part is related to what failure.

As a specific example, if the failure site inference apparatus 100 shows a similar tendency in the plurality of sensor data for a failure case, the sensor value for a particular site, the failure site inference apparatus 100 may identify the specific location. It can be judged that the association between the site and the failure case is high.

Meanwhile, the failure site inference apparatus 100 may update the failure analyzer 620 to correspond the first failure case with one or more sites where the degree of association satisfies a predetermined condition. In this case, the 'predetermined condition' may be a condition in which the degree of association is greater than or equal to the critical degree of association, or the condition in which the degree of association is within the upper N (N is a natural number).

In other words, when the failure location inference apparatus 100 inputs the first failure case to the failure analyzer 620, the failure location analyzer 620 may output one or more locations that correspond to a predetermined condition in response thereto. Can be updated.

In this case, the failure site inference apparatus 100 may update the failure analyzer 620 by creating information on failure areas for each failure case in the form of a look-up table. In this case, 'learning' may mean updating the lookup table.

Meanwhile, the failure site inference apparatus 100 may generate and update the failure analyzer 620 using a machine learning method. In this case, 'learning' may mean updating the coefficients constituting the failure analyzer 620. However, the two cases described above are exemplary and the spirit of the present invention is not limited thereto.

Meanwhile, the learning process of the failure analyzer 620 may be repeatedly performed for the plurality of first failure cases.

Subsequently, the failure site inference apparatus 100 according to an exemplary embodiment may acquire failure identification information of the electric locomotive 300 and first sensor data of the electric locomotive 300. (S73) As described above. In the present invention, the 'failure identification information' is information generated by the control device of the electric locomotive 300 to inform the failure situation and / or status of the electric locomotive 300, and may be a predefined failure code such as '4004'. Can be.

In addition, in the present invention, the 'sensor data' such as the first sensor data and the second sensor data may refer to sensor values obtained by the controller of the electric locomotive 300 from sensors installed at respective parts of the electric locomotive 300.

Referring again to FIG. 3, the failure identification information 510 and the first sensor data 520 of the electric locomotive 300 acquired by the failure site inference apparatus 100 according to an embodiment of the present invention will be described.

As described above, the failure identification information 510 may be in the form of a predefined failure code. In addition, the sensor data 520 may be in the form of numbers (or in the form of numbers and letters, as shown).

For example, referring to the first sensor data 501, the failure site inference apparatus 100 may obtain the failure identification information 511 and the first sensor data (the numbers corresponding to X1 to X3) corresponding thereto.

Meanwhile, although FIG. 3 shows two sensor data and each sensor data includes only three sensor values (X1, X2, X3), it should be understood as an example.

The failure site inference apparatus 100 according to an embodiment of the present invention may determine one or more candidate failure cases corresponding to the failure identification information by the case analyzer.

Referring to FIG. 4 again, a process of determining the failure points of the failure cases 531 to 533 by the case analyzer 610 according to an embodiment of the present invention will be described.

First, in the present invention, the 'case analyzer' 610 may be a data set representing a correlation between a plurality of failure identification information and a plurality of failure cases. In other words, when the case analyzer 610 receives the specific failure identification information 511, the case analyzer 610 may output one or more candidate failure cases 531 to 533 with respect to the received failure identification information 511.

In this case, the candidate failure case may refer to one or more failure states that share failure identification information. For example, when there are three failure states in which the failure identification information is '4004' as shown in FIG. 4, each of the three failure states is a candidate failure case (531 to 533) when the failure identification information is '4004'. It may correspond to.

As described above, various failure cases 531 to 533 may exist under the same failure identification information 511, so that the failure sites according to the exemplary embodiment of the present disclosure may be more clearly identified according to the failure identification information 511. The inference apparatus 100 may compare the second sensor data and the first sensor data for each of the one or more candidate failure cases 531 to 533. In addition, the failure site inference apparatus 100 may determine any one of the one or more candidate failure cases 531 to 533 as a failure case of the electric locomotive. (S75) In this case, the first sensor data may be broken by the above-described process. The site inference apparatus 100 may be obtained from the electric locomotive 300.

Referring back to FIG. 5, a process of determining a failure case of an electric locomotive by the failure site inference apparatus 100 according to an embodiment of the present invention from among one or more candidate failure cases 531 to 533 is described. For convenience of description, the second sensor data 541 to 543 for each of the candidate failure cases 531 to 533 are shown in FIG. 5, and each of the second sensor data 541 to 543 and the first sensor data is shown in FIG. 5. Assume that the similarity between the sensor data 521 is as shown.

Under the above-described assumption, the failure site inference apparatus 100 according to an embodiment of the present invention may have the second sensor data 542 having the highest similarity with the first sensor data 521 among the second sensor data 541 to 543. You can search for. At this time, the failure site inference apparatus 100 according to an embodiment of the present invention may determine the similarity between sensor data according to various known techniques. For example, the failure site inference apparatus 100 generates two vectors for each of the first sensor data and the second sensor data, each of which has individual sensor values as components of the vector, and calculates the similarity between the sensor data based on the distance between the two vectors. You can judge. However, this is merely exemplary and the spirit of the present invention is not limited thereto.

Subsequently, the failure site inference apparatus 100 according to an exemplary embodiment may determine the candidate failure case 532 corresponding to the second sensor data 542 having the highest similarity as the failure case of the electric locomotive 300. .

The failure site inference apparatus 100 according to an embodiment of the present invention may determine a failure site corresponding to the failure case (that is, the candidate failure case 532) of the electric locomotive 300 by the failure analyzer. )

FIG. 6 is a diagram illustrating a process of determining a failure site 550 by the failure site inference apparatus 100 according to an exemplary embodiment of the present invention using the failure analyzer 620.

In the present invention, the 'failure analyzer' 620 may be a data set expressing a correlation between a plurality of failure cases and a plurality of failure sites. In other words, when a failure analyzer 532 is input, the failure analyzer may output one or more failure sites 550 for the received failure case 532.

As described above, the present invention can provide more accurate cause analysis for a failure by providing a failure site in a train failure diagnosis, and further reduce costs and resources for maintenance of an electric locomotive.

On the other hand, the failure site inference apparatus 100 according to an embodiment of the present invention may provide the user terminal 200 with information about the failure site determined by the above-described process. (S77) The user is the user terminal 200 You can check the fault site and take appropriate measures.

8 is an illustration of a screen 800 displayed on the display means of the user terminal 200 according to an embodiment of the present invention.

Referring to FIG. 8, the screen 800 includes an area 810 on which an image of the electric locomotive 300 is displayed, an area 820 on which information about the electric locomotive 300 is displayed, and fault data including failure identification information. It may include an area 830 that is displayed and an area 840 where a failure site is displayed.

Various information about the electric locomotive 300 may be displayed in an area 810 where an image of the electric locomotive 300 is displayed and an area 820 where information about the electric locomotive 300 is displayed. For example, as shown, the model name, manufacturer, operator, etc. of the electric locomotive 300 may be displayed, as well as an image of the electric locomotive 300.

In other words, the failure site inference apparatus 100 according to an embodiment of the present invention obtains information about the electric locomotive 300 from the electric locomotive 300 or another external device (not shown), and the user terminal 200. Can be provided to

Meanwhile, various items of one or more failure data of the electric locomotive 300 may be displayed in the region 830 in which the failure data is displayed. For example, as illustrated, the area 830 in which fault data is displayed may display a time at which a fault occurs, fault identification information of the fault, and a sensor value of each sensor when the fault occurs.

In other words, the failure site inference apparatus 100 according to an exemplary embodiment of the present invention may provide the failure data to the user terminal 200 in addition to the information on the failure site to be displayed together with the information about the failure site.

On the other hand, when the user selects any one data (for example, the first failure data 831) in the area 830 in which the failure data is displayed, the failure area according to the corresponding failure is displayed in the area 840 in which the failure area is displayed. Can be. In this case, when the user selects a specific part, specific information (eg, a sensor value) about the corresponding part may be further displayed.

In other words, the failure site inference apparatus 100 according to an embodiment of the present invention receives a request for detailed information on a specific failure site from the user terminal 200, and correspondingly, the sensor value and the like related to the failure site are correspondingly received. Information can be provided.

As a result, the present invention may allow a user to more easily and quickly perform a diagnosis of the electric locomotive 300.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments are, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs). May be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For the convenience of understanding, the processing apparatus may be described as one used, but those skilled in the art will appreciate that the processing apparatus includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as parallel processors.

The software may include a computer program, code, instructions, or a combination of one or more of the above, and may configure the processing device to operate as desired, or process independently or collectively. You can command the device. Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. Or may be permanently or temporarily embodied in a signal wave to be transmitted. The software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner. Software and data may be stored on one or more computer readable recording media.

The method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. Computer-readable media may include, alone or in combination with the program instructions, data files, data structures, and the like. The program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described by the limited embodiments and the drawings as described above, various modifications and variations are possible to those skilled in the art from the above description. For example, the described techniques may be performed in a different order than the described method, and / or components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different manner than the described method, or other components. Or even if replaced or substituted by equivalents, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are within the scope of the claims which follow.

100: failure site inference device
111: memory
112: processor
113: communication module
114: I / O interface
115: I / O device
200: user terminal
300: electric locomotive
400: network

Claims (9)

In the method of inferring the failure site of the electric locomotive based on the failure identification information of the electric locomotive,
Training a failure analyzer;
Acquiring first sensor data including failure identification information of the electric locomotive and a detection result of a plurality of parts constituting the electric locomotive;
Determining, by the case analyzer, one or more candidate failure cases corresponding to the failure identification information;
Comparing second sensor data with respect to each of the one or more candidate failure cases and the first sensor data to determine any one of the one or more candidate failure cases as a failure case of an electric locomotive; And
Determining, by the failure analyzer, a failure site corresponding to a failure case of the electric locomotive.
Learning the fault analyzer
Acquiring a plurality of second learning data including third sensor data including a sensing result of a plurality of parts of the electric locomotive and a failure case corresponding to the third sensor data;
Calculating a degree of association between a plurality of parts constituting the electric locomotive and a first failure case based on the plurality of second learning data; And
And updating the failure analyzer so as to correspond the first failure case to a site where a degree of association satisfies a predetermined condition. The method of claim 1
The case analyzer
A data set representing a correlation between a plurality of failure identification information and a plurality of failure cases,
The failure site inference method of the electric locomotive
Before the acquiring step
Learning the case analyzer further comprises, the failure site reasoning method of the electric locomotive. The method of claim 2
Training the case analyzer
Obtaining a plurality of first learning data including failure identification information and a failure case corresponding to the failure identification information; And
And updating the case analyzer based on the plurality of first training data. The method of claim 1
Determining a failure case of the electric locomotive
Retrieving second sensor data having the highest similarity with the first sensor data among the second sensor data; And
And determining a candidate failure case corresponding to the second sensor data having the highest similarity as the failure case of the electric locomotive. delete delete The method of claim 1
Learning the fault analyzer
About plural first trouble cases
And calculating the degree of association and determining the failure site repeatedly. The method of claim 1
The failure site inference method of the electric locomotive
After determining the failure site
Providing information on the failure site to the user terminal; further comprising, failure site inference method of the electric locomotive. A computer program stored in a medium for executing the method of any one of claims 1 to 4 and 7 to 8 using a computer.

Images