KR20230057248A - Method and apparatus for monitoring condition of vehicle - Google Patents

Abstract

In accordance with one embodiment of the present invention, provided is a vehicle condition monitoring method performed by a vehicle condition monitoring apparatus. The method includes the following steps of: receiving driving data including speed data of a vehicle; generating predicted trend information including predicted speed data of the vehicle based on the driving data by using an artificial intelligence model trained to generate a predicted trend of input data expected based on the input data; acquiring current condition data of the vehicle including the current speed data of the vehicle in real time, and comparing the current condition data with predicted driving data according to the predicted trend information to generate a comparison result; and based on the comparison result, determining a situation, in which a difference between the current condition data and the predicted driving data corresponding to the current condition data is no less than a preset threshold value, as an abnormal situation to provide a monitoring result to a terminal connected to communicate with the vehicle condition monitoring apparatus. Therefore, the present invention is capable of reducing an error related to a malfunction determination.

Description

Vehicle condition monitoring method and apparatus {METHOD AND APPARATUS FOR MONITORING CONDITION OF VEHICLE}

The present invention relates to a vehicle condition monitoring method and apparatus, and more particularly, generates a predicted driving trend of a vehicle based on vehicle driving information and speed information, and provides a comparison result between the predicted driving trend and the current driving trend It relates to a vehicle condition monitoring method and apparatus.

A system in charge of general and common functions necessary for the operation and operation of a railway vehicle is called an operation-related subsystem. Operation information is composed of parameter values associated with the operation of a railway vehicle. The driving information of the rolling stock may also include arbitrary parameters representing operating conditions of the rolling stock. Detecting anomalies in operation information during train operation is essential for ensuring safe operation and effective maintenance of railroad vehicles, but its utilization is low.

In this way, when vehicle-related parameters are monitored during vehicle operation, it is possible to detect exceptional situations and emergency situations that may occur during vehicle operation. However, conventionally, it is necessary to install additional equipment including additional sensors in a vehicle to be monitored or a route control center to monitor a vehicle. Therefore, there is a problem in that related costs increase as additional equipment needs to be installed.

In addition, in the case of conventional railway vehicle monitoring, data is transmitted from a subsystem to an on-board computer using communication technology, and the driver directly displays the data on a screen display device to monitor the failure-related information. Therefore, there was a problem in that information could not be provided in real time and labor costs as the engineer had to manually transmit failure-related information.

The present invention is to solve the problems of the prior art, which generates a driving prediction trend based on driving information and speed information collected in real time, and provides a comparison result between the generated predicted driving trend and the current driving trend. It is a technical challenge to provide a condition monitoring method and device.

The technical problems to be achieved by the present invention are not limited to the above technical problems, and other technical problems of the present invention can be derived from the following description.

As a technical means for solving the above technical problem, an embodiment according to the first aspect of the present invention provides a vehicle condition monitoring method performed by a vehicle condition monitoring device. The method includes the steps of receiving driving data including vehicle speed data, using an artificial intelligence model learned to generate a predicted trend of the input data expected based on the input data, and based on the driving data, the driving data. Generating predictive trend information including predicted speed data of the vehicle, acquiring current state data of the vehicle including current speed data of the vehicle in real time, and predicting driving according to the current state data and the predicted trend information Comparing data to generate a comparison result; and based on the comparison result, if the difference between the current state data and the predicted driving data corresponding to the current state data is equal to or greater than a predetermined threshold value, it is determined as an exceptional situation and the vehicle is detected. and providing a monitoring result to a terminal communicatively connected to the state monitoring device.

In addition, an embodiment according to a second aspect of the present invention provides a vehicle condition monitoring device. The apparatus includes a communication module for transmitting and receiving information with a vehicle control terminal, a memory for storing a vehicle condition monitoring program, and a processor for executing the vehicle condition monitoring program, wherein the processor includes driving data including vehicle speed data. and generate predictive trend information including predictive speed data of the vehicle based on the driving data by using an artificial intelligence model learned to generate a predictive trend of the input data expected based on the input data; Obtaining current state data of the vehicle including current speed data of the vehicle in real time, comparing the current state data with predicted driving data according to the predicted trend information to generate a comparison result, and based on the comparison result If the difference between the current state data and the predicted driving data corresponding to the current state data is equal to or greater than a predetermined threshold, it is determined as an exceptional situation and provided as a monitoring result to a terminal communicatively connected to the vehicle state monitoring device. It consists of

According to the present invention, a predicted driving trend may be generated based on driving information and speed information collected in real time, and a comparison result between the generated predicted driving trend and the current driving trend may be provided.

In addition, according to the present invention, the trend of driving information when the vehicle is in a normal state is stored, and the currently collected driving information is compared with the stored trend in the normal state to quickly identify an unusual situation of the vehicle and respond to the identified situation. Appropriate action can be taken accordingly.

In addition, according to the present invention, if an error frequently occurs in the collected driving information, it is determined that the part or the whole subsystem related to the driving information including the part is replaced as defective.

In addition, according to the present invention, it is possible to determine whether a vehicle has failed based on vehicle speed information and driving information by using an artificial intelligence model based on long short-term memory (LSTM). Consumed time and cost can be reduced, and errors related to failure determination can be reduced.

In addition, according to the present invention, the condition of the vehicle can be monitored in real time by comparing the predicted driving trend with the current driving trend, so that there is no need to install additional sensors and additional equipment in the vehicle or route control center, thereby monitoring the vehicle condition. additional costs can be reduced.

1 is a diagram illustrating a vehicle condition monitoring device, a control system and a vehicle control terminal communicatively connected thereto according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an example of a train in which the vehicle control terminal and the vehicle control terminal shown in FIG. 1 are disposed.
FIG. 3 is a diagram showing a detailed configuration of the vehicle condition monitoring device shown in FIG. 1 .
4 is a diagram illustrating an example of an artificial intelligence model based on a long and short-term memory neural network according to an embodiment of the present invention.
5 is a flowchart illustrating a sequence of a vehicle condition monitoring method of a vehicle condition monitoring apparatus according to another embodiment of the present invention.
FIG. 6 is a diagram showing detailed steps for some steps of the method for monitoring the condition of a railroad car shown in FIG. 5 .

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. However, the present invention may be implemented in many different forms, and is not limited to the embodiments described herein. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the accompanying drawings. All terms including technical terms and scientific terms used herein should be interpreted as meanings commonly understood by those of ordinary skill in the art to which the present invention belongs. The terms defined in the dictionary should be interpreted as having additional meanings corresponding to the related technical literature and the currently disclosed content, and are not interpreted in a very ideal or limiting sense unless otherwise defined.

In order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and the size, shape, and shape of each component shown in the drawings may be variously modified. Same/similar reference numerals are assigned to the same/similar parts throughout the specification.

The suffixes "module" and "unit" for the components used in the following description are given or used interchangeably in consideration of ease of writing the specification, and do not have meanings or roles that are distinguished from each other by themselves. In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed description is omitted.

Throughout the specification, when a part is said to be “connected (connected, contacted, or combined)” with another part, this is not only the case where it is “directly connected (connected, contacted, or coupled)”, but also has other members in the middle. It also includes the case of being "indirectly connected (connected, contacted, or coupled)" between them. In addition, when a part "includes (provides or provides)" a certain component, it does not exclude other components, but "includes (provides or provides)" other components unless otherwise specified. means you can

Terms indicating ordinal numbers such as first and second used in this specification are used only for the purpose of distinguishing one element from another, and do not limit the order or relationship of elements. For example, a first element of the present invention may be termed a second element, and similarly, the second element may also be termed a first element. Singular forms used herein should be construed to include plural forms as well, unless the meaning is clearly indicated to the contrary.

A system in charge of general and common functions necessary for the operation and operation of a railway vehicle is called an operation-related subsystem. Representative subsystems include driver's seat control units such as daytime controllers, propulsion systems, braking systems, pantograph systems, wireless communication systems, odometry units, axle accelerometers, auxiliary power units, door units, HVAC (Heating, Ventilation, and Air Conditioning) ) device, emergency brake device and forensic black box system. As such, subsystems to be described below may be devices and systems necessary for driving and operating a vehicle.

1 is a diagram showing a vehicle condition monitoring device 200 according to an embodiment of the present invention, a control system 100 and a vehicle control terminal 300 communicatively connected therewith, and FIG. 2 is a diagram showing the vehicle control shown in FIG. 1 It is a diagram showing an example of a train in which the terminal 300 and the vehicle control terminal 300 are disposed.

Referring to FIGS. 1 and 2 , the control system 100 and the vehicle condition monitoring device 200 may be implemented as a server or a computing device, and may be implemented as Software as a Service (SaaS), Platform as a Service (PaaS), or IaaS. (Infrastructure as a Service). In addition, the control system 100 and the vehicle condition monitoring device 200 may be constructed in the form of a private cloud, public cloud, or hybrid cloud system, but the scope of the present invention is limited thereto. it is not going to be

The control system 100 may transmit/receive information with the vehicle condition monitoring device 200 and the vehicle control terminal 300 based on a communication network. The control system 100 serves as a control tower that controls the operation of railroad cars. The control system 100 may store predicted trend information for each vehicle. The control system 100 may simultaneously generate predicted trend information for a plurality of vehicles. In addition, the control system 100 may monitor the vehicle condition based on the comparison result received from the vehicle condition monitoring device 200 . For example, the control system 100 may display the vehicle condition according to the comparison result on the control system 100 for an engineer and maintenance workers.

The vehicle condition monitoring device 200 may transmit/receive information with the control system 100 and the vehicle control terminal 300 based on a communication network. The vehicle condition monitoring device 200 receives the driving data collected based on the vehicle control terminal 300, generates predicted trend information using an artificial intelligence model, and compares the current condition data with the predicted driving data to obtain a comparison result. can create Details related to this will be described later with reference to FIG. 3 . Driving data may be provided from the vehicle control terminal 300 .

The vehicle control terminal 300 may be a terminal disposed inside or outside the vehicle. The vehicle control terminal 300 may collect vehicle driving data through communication with the vehicle condition monitoring device 200 and transmit the collected vehicle driving data to the vehicle condition monitoring device. Here, driving data may be periodically collected according to a preset time interval. Operation data is the same for the same type of vehicle on the same route, but may be different for different routes or different types of vehicles.

For example, operation data includes time, vehicle number, serial number, data integrity, front-end link, service class, front-end offset, train front-head direction, speed, whether or not the train is stopped, current station number, next station number, automatic train driving device of the vehicle (ATO; Automatic Train Operation) main mode, automatic train operation system (ATO) operation status, automatic train operation system (ATO) activation status, traction status, braking status, automatic train operation system (ATO) analog output, target speed, target Distance, current gradient, proportional-integral-differential controller (Proportional-Integral-Differential controller) Expected acceleration, station stop error record, reference speed, train weight, overhead line voltage, overhead line current, traction force, air braking force, electric braking force, bogie commercial It can include the number of non-braking, the amount of emergency braking of bogie, vehicle braking, recommended speed, traction braking status, and stopping accuracy.

As another example, driving data may include essential parameters and optional parameters. Required parameters may include current time data, vehicle speed data, automatic train operation (ATO) analog output data of the vehicle, traction braking state data of the vehicle, and current gradient of the vehicle. The optional parameters are vehicle type, vehicle sub-equipment type, weather, vehicle speed limit data, vehicle location data, distance traveled by the vehicle from the starting point, name of the next station the vehicle will stop at, next from the current vehicle location It may include remaining distance data to the station, vehicle communication interface state data, and power state data of digital input/output ports corresponding to the air conditioner and door of the vehicle.

The vehicle control terminal 300 may be connected to a train control device, a propulsion control device, a braking device, and other lower devices through a communication network.

The vehicle control terminal 300 collects vehicle driving data for each route through the vehicle driving data collection terminal 301 for each route, or collects vehicle driving data for each vehicle type on one route through the vehicle driving data collection terminal 302 for each vehicle type. Driving data can be collected.

The vehicle driving data collection terminal 301 for each route may collect and store vehicle driving data for each route. For example, the vehicle driving data collection terminal 301 for each route stores the collected driving data of vehicle #2001 as driving data of a vehicle on a second route, and stores the driving data of vehicle #3001 as driving data of a vehicle on a third route. , and the driving data of the vehicle #4001 may be stored as the driving data of the vehicle on the fourth route.

The vehicle driving data collection terminal 302 may collect and store driving data of vehicles running on one route by vehicle type. For example, the driving data collection terminal 302 of each vehicle type stores the collected driving data of vehicle #1001 as driving data of the first vehicle, and stores the driving data of vehicle #1002 as driving data of the second vehicle. , driving data of vehicle #1003 may be stored as driving data of a third vehicle.

As described above, the vehicle control terminal 300 can more accurately determine the state of the vehicle by collecting and storing driving data for each route and vehicle type.

FIG. 3 is a diagram showing a detailed configuration of the vehicle condition monitoring device 200 shown in FIG. 1 .

Referring to FIGS. 1 and 3 , the vehicle condition monitoring device 200 includes a communication module 210 , a memory 220 , and a processor 230 .

The communication module 210 transmits and receives information with the control system 100 and the vehicle control terminal 300 . For example, the communication module 210 may receive collected vehicle driving data from the vehicle control terminal 300 and transmit a comparison result to the control system 100 .

The communication module 210 may include a device including hardware and software necessary for transmitting/receiving a signal such as a control signal or a data signal through a wired/wireless connection with another network device.

The memory 220 stores a vehicle condition monitoring program. The memory 220 should be interpreted as collectively referring to a non-volatile storage device that continuously maintains stored information even when power is not supplied and a volatile storage device that requires power to maintain stored information. In addition, the memory 220 may perform a function of temporarily or permanently storing data, and may be a magnetic storage medium or flash storage medium in addition to a volatile storage device that requires power to maintain stored information. media), but the scope of the present invention is not limited thereto.

The processor 230 executes a vehicle condition monitoring program. The name of the vehicle condition monitoring program is set for convenience of explanation, and the name itself does not limit the function of the program, and may be set as the name of various programs.

The processor 230 receives driving data including vehicle speed data. The processor 230 generates predictive trend information including predicted speed data of the vehicle based on the driving data, using an artificial intelligence model learned to generate a predictive trend of the expected input data based on the input data. The processor 230 obtains current state data of the vehicle including current speed data of the vehicle in real time, compares the current state data with predicted driving data according to the predicted trend information, and generates a comparison result. If the difference between the current state data and the predicted driving data corresponding to the current state data is equal to or greater than a preset threshold based on the comparison result, the processor 230 may determine an exceptional situation and display the result as a monitoring result.

Here, the comparison result may be a result of comparing predicted driving data at a current point in time according to the predicted trend information with current state data. In this way, as the processor 230 displays the abnormal situation as a monitoring result, safe operation of the vehicle can be ensured and maintenance can be performed effectively. For example, when the speed of the vehicle exceeds the speed limit in a specific section, the processor 230 determines that the difference between the driving state data and the predicted driving data is equal to or greater than a predetermined threshold value, determines it as an exceptional situation, and displays the result as a monitoring result. can

The processor 230 may periodically input driving data including speed data to the artificial intelligence model at predetermined time intervals. Here, the driving data may include essential parameters and optional parameters.

Required parameters may include current time data, vehicle speed data, automatic train operation (ATO) analog output data of the vehicle, traction braking state data of the vehicle, and current gradient of the vehicle. Optional parameters include main mode data of automatic train operation system, operation status data of automatic train operation system, activation status data of automatic train operation system, vehicle type, sub-device type of vehicle, weather, vehicle speed limit data, and vehicle location. data, the distance traveled by the vehicle from the starting point, the name of the next station the vehicle will stop at, the remaining distance data from the current vehicle location to the next station, the vehicle's communication interface status data, and the digital input/output corresponding to the vehicle's air conditioner and door It may contain the port's power state data.

The processor 230 may represent parameters that cannot be directly measured with numbers among the essential parameters and optional parameters by replacing them with numbers using an appropriate method. Taking the driving state data of the automatic train driving device as an example, the processor 230 sets the main mode data of the automatic train driving device to 0 when the driving state of the vehicle is manual, and the train automatic driving mode when the driving mode of the vehicle is semi-automatic. Main mode data of the driving device may be represented by 1, and main mode data of the automatic train driving device may be represented by 2 when the driving mode of the vehicle is automatic.

As another example, the processor 230 indicates 1 if the vehicle is moving forward, 0 if the vehicle is moving backward, 1 if the vehicle performs a propulsion operation, 0 if it does not perform, and 1 if the vehicle performs a braking operation. , it can be represented as 0 if not performed, 1 if the vehicle is located in the station yard, and 0 if it is not located.

The processor 230 may determine a degree of control for controlling the current state data of the vehicle based on a difference between a comparison result between the current state data and the predicted driving data and a predetermined threshold value. Here, the degree of control may be determined by the severity of the error and driving state data. The processor 230 may limit or stop the operation of the vehicle or correct the current state data to correspond to the predicted speed data. Here, the degree of control may be preset according to user settings. For example, if the difference between the driving state data and the predicted driving data is more than twice the preset threshold, the operation is immediately stopped, and if the difference between the driving state data and the predicted driving data is less than twice the preset threshold, The driving state data may be controlled so that the driving state data coincides with the predicted driving data.

For example, if the predicted speed data, which is the predicted driving data, is 3 km/s and the predetermined threshold value is 2 km/s, the current speed data preferably corresponds to a maximum of 5 km/s and a minimum of 1 km/s. However, if the current speed data, which is driving state data, is 7 km/s, the current speed data does not correspond to the predicted speed data considering the preset threshold value, and thus the processor 230 may control the driving of the vehicle. At this time, since the difference between the predicted speed data and the driving state data is more than twice the predetermined threshold value, the processor 230 may stop driving the vehicle.

As another example, if the predicted speed data, which is the predicted driving data, is 3 km/s and the preset threshold is 2 km/s, the current speed data preferably corresponds to a maximum of 5 km/s and a minimum of 1 km/s. However, if the current speed data, which is driving state data, is 4 km/s, since the current speed data corresponds to the predicted speed data considering a preset threshold value, the processor 230 sets the current speed data, which is driving state data, to be the same as the predicted speed data. You can control it.

The processor 230 may store the difference between the predicted travel data and the current state data, and use a weighted smoothing technique for the difference. The processor 230 may calculate an average value and standard deviation for the difference or weighted smoothing result. The processor 230 may set [average value + 2.5*standard deviation] as a maximum allowable range according to statistical quality control theory. Here, the maximum permissible range may be from a value obtained by subtracting a predetermined threshold from the predicted driving data to a value obtained by adding a preset threshold to the predicted driving data. The processor 230 may determine an exceptional situation when the current state data is equal to or greater than the maximum allowable range.

4 is a diagram illustrating an example of an artificial intelligence model based on a long and short-term memory neural network according to an embodiment of the present invention. The artificial intelligence model described below may be generated by the vehicle condition monitoring device 200 described above.

Referring to FIG. 4 , the artificial intelligence model analyzes input data, learns trends and rules through the analyzed input data, and then applies the learned content to generate predicted trend information based on the information.

If input data and output data are trained through an artificial intelligence model, the artificial intelligence model can be trained to fit the given output data based on the input data. The artificial intelligence model can predict the output data of the next time point or the future time point after a certain time based on the current point in time based on the given input data. Accordingly, the artificial intelligence model may have a trend prediction model of output data according to given input data.

The input data may be at least one of driving data at the current time point, driving data at a point prior to the current point in time, statistical data, and cross feature data. Here, the statistical data may be an average and standard deviation of driving data, and a difference between driving data at a current point in time and driving data at a previous point in time. Crossed feature data may be multiplication data of a velocity at a current time point and a velocity at a previous time point.

The output data may be one of driving data of a point in time immediately following the current point in time.

AI models can perform data preprocessing. For example, the data preprocessing process may be a process of performing one of missing value processing, duplicate value processing, and abnormal value processing.

The artificial intelligence model can optimize the predicted trend information, which is a trend that has already been generated through self-learning, or continue to apply the existing trend even when the operating environment conditions change. Here, the driving environment condition may be an external condition such as another route, another vehicle, weather, and subsystem performance deterioration due to aging.

The artificial intelligence model of the present invention may be formed based on a long short-term memory (LSTM) neural network, which is one of artificial neural networks. The long-short-term memory neural network can delete unnecessary memories and set things to remember by adding input gates, forget gates, and output gates to memory cells in the hidden layer.

A cell state (c _t-1 ) of a previous cell state may be used as an input for obtaining a cell state (c _t ) of a next time point. For the hidden state, the hidden state (h _t-1 ) of the previous time point may be used as an input to obtain the hidden state (h _t ) of the next time point. The long short-term memory neural network can use the newly added three gates to obtain the value of the hidden state and the cell state. Each gate is called a deletion gate, an input gate, and an output gate, and these three gates may have a sigmoid function (Mish) in common. After passing the sigmoid function (Mish), a value between 0 and 1 comes out, and the gate can be adjusted with these values.

An artificial intelligence model based on an artificial neural network is one of the detailed methodologies of machine learning and can provide a much better learning process. For example, an artificial neural network-based artificial intelligence model may have a form in which a plurality of neurons, which are basic computing units, are connected by weighted links, and the weighted links may adjust weights to adapt to a given environment. Weights and associations for each driving data can be adapted as neuron weights in the artificial intelligence model. Accordingly, learning of the artificial intelligence model may be to find an optimal weight among a plurality of weights.

For example, if the input of the artificial intelligence model is temperature data among optional parameters, the processor 230 may perform classification of at least three temperature ranges based on the artificial intelligence model, and output and store the classified results. . Here, a result of performing at least three classifications may be one of low temperature, normal temperature, and high temperature. If the current temperature of the vehicle is 25 degrees, the processor may determine which environment among low temperature, room temperature, and high temperature the current vehicle temperature data corresponds to, and merge the discrimination result and the input data to perform learning of the artificial intelligence model.

The artificial intelligence model can detect anomalies or errors by monitoring the state of the vehicle using a long-term short-term memory neural network. For example, the artificial intelligence model may determine an exceptional situation when the difference between the predicted driving data determined by the prediction of the long and short-term memory neural network and the current state data exceeds a predetermined threshold value by using a previously stored prediction trend.

When the artificial intelligence model generates predictive trend information, the initial location for driving data may be linked with trend information associated with the location data. That is, it is possible to store predicted trend information according to location, and it is possible to increase the accuracy of judgment on normal and abnormal conditions. Here, the location data may be information obtained from ballis, tag, GPS, and vehicle stop information.

In addition, when the artificial intelligence model generates predictive trend information, driving data related to the vehicle to be collected and information on sub-device types related to the driving data may be linked to the predicted trend information. In other words, the predicted trend information for the driving data may be changed according to the configuration of the subsystem installed in the vehicle and the driving data generated from the corresponding subsystem.

The artificial intelligence model can generate appropriate predictive trend information based on driving data of vehicles in operation, even of the same model. For example, among individual patterns of the same vehicle model, a comparable pattern may be used.

5 is a flowchart illustrating a sequence of a vehicle condition monitoring method of a vehicle condition monitoring apparatus according to another embodiment of the present invention.

The vehicle state monitoring method according to the present embodiment is a method using the vehicle state monitoring device 200 described above with reference to FIGS. 1 to 3 . Each step and detailed process of the vehicle condition monitoring method described below may be implemented through the above-described vehicle condition monitoring device 200 or server. Therefore, the contents of the embodiment previously described with reference to FIGS. 1 to 3 may be equally applied to the following embodiments, and the contents overlapping with the above description will be omitted below.

The vehicle condition monitoring method includes the steps of collecting driving data (S210), generating predicted trend information (S220), generating comparison results (S230), and displaying monitoring results (S240), and determining the degree of control of current state data ( S250) may be further included.

In the driving data collection step ( S210 ), the vehicle condition monitoring apparatus 200 receives various types of driving data including vehicle speed data from the vehicle control terminal 300 .

In the predictive trend information generating step ( S220 ), the vehicle condition monitoring device 200 generates predictive trend information including predicted speed data of the vehicle based on driving data using an artificial intelligence model. Here, the artificial intelligence model is a model learned to generate a predictive trend of the input data expected based on the input data. In the comparison result generating step (S230), the vehicle condition monitoring apparatus 200 acquires the current state data of the vehicle including the current speed data of the vehicle in real time, compares the current state data with the predicted driving data according to the predicted trend information, produce comparison results.

In the monitoring result display step (S240), based on the comparison result, the vehicle condition monitoring apparatus 200 determines that it is an exceptional situation when the difference between the current condition data and the predicted driving data corresponding to the current condition data is equal to or greater than a predetermined threshold value. displayed as monitoring results.

In addition, in the step of determining the degree of control of the current state data (S250), the vehicle state monitoring apparatus 200 controls the current state data of the vehicle based on the difference between the comparison result between the current state data and the predicted driving data and a predetermined threshold value. determine the degree of control for

FIG. 6 is a diagram showing detailed steps for some steps of the method for monitoring the condition of a railroad car shown in FIG. 5 .

5 and 6, the step of determining the degree of control of the current state data (S250) is the step of determining whether the difference between the predicted driving data and the current state data is equal to or greater than a predetermined threshold (S251), among the vehicle driving data It may include controlling at least one driving data (S252), learning an artificial intelligence model (S253), and storing current state data (S254).

In step S251 of determining whether the difference between the predicted driving data and the current state data is greater than or equal to a preset threshold value, it is determined whether the difference between the predicted driving data and the current state data is a preset threshold value to determine the current state of the vehicle. . When the difference between the predicted driving data and the current state data is equal to or greater than a predetermined threshold, a step (S252) of controlling at least one of the driving data of the vehicle is performed, and the difference between the predicted driving data and the current state data is determined by If it is less than the set threshold value, the step of storing the current state data (S254) may be performed.

Here, the step of determining whether the difference between the predicted driving data and the current state data is equal to or greater than a predetermined threshold value (S251) may be the same as the comparison result performed in the monitoring result display step (S240), and the predicted driving data and the current state Sub-steps may be performed based on the results performed in the monitoring result display step (S240), omitting the step (S251) of determining whether the difference in data is equal to or greater than a preset threshold value.

In the step of controlling at least one of the vehicle driving data ( S252 ), current state data having a difference between the predicted driving data and a predetermined threshold value or more may be controlled.

In the artificial intelligence model learning step (S253), the controlled current state data may be analyzed and trends and rules may be learned through the current state data.

In the step of storing the current state data (S254), the controlled current state data may be stored, and predicted trend information generated based on an artificial intelligence model taking the current state data as an input may be stored.

The vehicle condition monitoring method according to an embodiment of the present invention described above may be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

Those skilled in the art to which the present invention pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention based on the above description. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included in the scope of the present invention. The scope of the present application is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application.

Claims (12)

A vehicle condition monitoring method performed by a vehicle condition monitoring device,
a) receiving at least one piece of driving data including vehicle speed data;
b) Using an artificial intelligence model learned to generate a predicted trend of the input data expected based on the input data, based on the at least one or more driving data, predictive trend information including predicted speed data of the vehicle is generated. doing;
c) obtaining current state data of the vehicle including current speed data of the vehicle in real time, and generating a comparison result by comparing the current state data with predicted driving data according to the predicted trend information; and
d) Based on the comparison result, if the difference between the current state data and the predicted driving data corresponding to the current state data is greater than a predetermined threshold value, it is determined as an exceptional situation and monitored by a terminal connected to the vehicle state monitoring device. A vehicle condition monitoring method comprising the step of providing as a result. According to claim 1,
The comparison result is a result of comparing predicted driving data at a current point in time according to the predicted trend information with the current state data, the vehicle condition monitoring method. According to claim 1,
The artificial intelligence model is formed based on a long-term short-term memory neural network,
The vehicle condition monitoring method of claim 1 , wherein the driving data is periodically collected at predetermined time intervals. According to claim 1,
The operation data includes essential parameters including current time data, speed data of the vehicle, automatic train operation (ATO) analog output data of the vehicle, traction braking state data of the vehicle, and current gradient of the vehicle. A vehicle condition monitoring method comprising: According to claim 4,
The driving data includes, in addition to the essential parameters, the type of the vehicle, the type of sub-device of the vehicle, the weather, the speed limit data of the vehicle, the location data of the vehicle, the distance data the vehicle has traveled from the starting point, and the time the vehicle will stop. Option parameters including the name of the next station, the remaining distance data from the current location of the vehicle to the next station, the vehicle's communication interface state data, and the power state data of the digital input/output ports corresponding to the vehicle's air conditioner and door Further comprising, a method for monitoring rail vehicle condition. According to claim 1,
e) determining a degree of control for controlling the current state data of the vehicle based on a comparison result between the current state data and the predicted driving data according to step d) and a difference between the preset threshold That is, a vehicle condition monitoring device. In the vehicle condition monitoring device,
A communication module for transmitting and receiving information with a vehicle control terminal;
a memory for storing a vehicle condition monitoring program; and
A processor executing the vehicle condition monitoring program;
The processor receives at least one or more pieces of driving data including vehicle speed data, and uses an artificial intelligence model trained to generate a predicted trend of the input data expected based on the input data, and the at least one or more pieces of driving data Generates predictive trend information including the predicted speed data of the vehicle based on, obtains current state data of the vehicle including the current speed data of the vehicle in real time, and determines the current state data and the predicted trend information Based on the comparison result, if the difference between the current state data and the predicted driving data corresponding to the current state data is greater than a predetermined threshold value, it is determined as an exceptional situation. A vehicle condition monitoring device configured to perform providing as a monitoring result to the vehicle control terminal communicatively connected to the communication module. According to claim 7,
The comparison result is a result of comparing the predicted driving data at the current time according to the predicted trend information with the current state data, the vehicle condition monitoring device. According to claim 7,
The artificial intelligence model is formed based on a long-term short-term memory neural network,
The vehicle condition monitoring method of claim 1 , wherein the driving data is periodically collected at predetermined time intervals. According to claim 7,
The operation data includes essential parameters including current time data, speed data of the vehicle, automatic train operation (ATO) analog output data of the vehicle, traction braking state data of the vehicle, and current gradient of the vehicle. A vehicle condition monitoring device comprising: According to claim 10,
The driving data includes, in addition to the essential parameters, the type of the vehicle, the type of sub-device of the vehicle, the weather, the speed limit data of the vehicle, the location data of the vehicle, the distance data the vehicle has traveled from the starting point, and the time the vehicle will stop. Option parameters including the name of the next station, the remaining distance data from the current location of the vehicle to the next station, the vehicle's communication interface state data, and the power state data of the digital input/output ports corresponding to the vehicle's air conditioner and door Further comprising, a railway vehicle condition monitoring device. According to claim 7,
Wherein the processor is configured to further determine a degree of control for controlling the current state data of the vehicle based on a comparison result between the current state data and the predicted driving data and a difference between the predetermined threshold value and the vehicle state. monitoring device.

Images