TW201908181A - Anomaly diagnosis device, anomaly diagnosis method, and computer program - Google Patents

Abstract

Embodiments of the present invention achieve highly accurate diagnosis. According to one embodiment, an anomaly diagnosis device includes an anomaly detector and a diagnoser. The anomaly detector performs anomaly detection of deceleration performance of a vehicle based on a control command value for a brake device and a prediction model for deceleration of the vehicle. The anomaly detector performs anomaly detection of the brake device based on the control command value and a prediction model for braking force of the brake device. The diagnoser diagnoses the vehicle based on a result of the anomaly detection of the deceleration performance and a result of the anomaly detection of the brake device.

Description

Abnormal diagnostic device, abnormal diagnostic method, and computer readable recording medium

Embodiments of the present invention relate to an abnormality diagnostic apparatus, an abnormality diagnosis method, and a computer readable recording medium.

In order to maintain the safe and stable operation of the railway, it is necessary to routinely implement maintenance management or inspection of railway vehicles. For example, when a brake device of a railway vehicle fails, the obtained braking force becomes small, there is a case where the vehicle cannot stop at the target position, which is detrimental to convenience, or in the worst case, there is an accident. Therefore, for railway practitioners, the maintenance and management of vehicles is positioned at a very important position.

In the past, maintenance management centered on the regular inspection of railway vehicles has been carried out. However, in recent years, the following technologies have been developed: collecting and utilizing vehicle information such as sensor values or control values obtained from railway vehicles, and An abnormality of the brake was found early.

However, in a railway vehicle in which the traveling condition dynamically changes in time series due to changes in the route gradient or the weather, the passenger getting on or off, the driver's operation, and the like, it is difficult to perform accurate diagnosis.

[Problems to be Solved by the Invention] An embodiment of the present invention provides an abnormality diagnostic device, an abnormality diagnosis method, and a computer program that realize high-precision diagnosis. [Means for solving the problem]

An abnormality diagnosis device according to an embodiment of the present invention includes an abnormality detecting unit and a diagnosis unit. The abnormality detecting unit performs abnormality detection of the deceleration performance of the vehicle based on a predicted model of a control command value for the brake device and a deceleration of the vehicle, and predicts a braking force according to the control command value and the braking device. The model performs an abnormality detection of the brake device. The diagnosis unit diagnoses the vehicle based on the abnormality detection result of the deceleration performance and the abnormality detection result of the brake device.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In the drawings, the same components are denoted by the same reference numerals, and the description is omitted.

Fig. 1 is a block diagram showing an example of an abnormality diagnosis system according to an embodiment of the present invention.

The abnormality diagnosis system of FIG. 1 includes an abnormality diagnostic device 100, a vehicle system 200, an environmental information system 300, a terminal 400, an input device 500, and a screen display device 600. The outline of this abnormality diagnosis system will be described.

The abnormality diagnostic device 100 includes a learning mode and an operation mode. In the learning mode, the model generation unit 140 generates a deceleration of the vehicle based on at least one of the measurement information of the railway vehicle (hereinafter, the vehicle) acquired from the vehicle system 200 and the environmental information of the vehicle acquired from the environmental information system 300. Anomaly detection model for performance. The information including at least one of the measurement information of the vehicle and the environmental information of the vehicle is referred to as driving information. The vehicle may also be a group of vehicles that connect a plurality of vehicles.

Further, the model generation unit 140 generates an abnormality detection model of the brake device of the vehicle based on the travel information. In the embodiment of the present embodiment, an air brake is assumed as a brake device, and an abnormality detecting model of the air brake is generated. In the case of a vehicle grouping, an abnormality detecting model of the braking device can also be generated for each vehicle in which the braking device is provided. It is also possible to generate an abnormality detection model that is common to a plurality of brake devices without generating an abnormality detection model for each of the brake devices.

Further, the model generation unit 140 generates an abnormality detection model of the brake system (hereinafter referred to as a group brake). The group brake includes a brake device provided in a plurality of vehicles, and the abnormality detection model of the group brake is an overall abnormality detection model of the brake devices.

The various abnormality detection models generated by the model generation unit 140 are stored in the model database 102.

The abnormality detecting unit 150 performs abnormality detection of the deceleration performance using the abnormality detecting model of the deceleration performance in the operation mode. In addition, an abnormality detection model of the air brake is used to detect the abnormality of the air brake. In addition, the abnormality detection model of the group brake is used to perform abnormality detection of the group brake. The abnormality detection means determining whether there is an abnormality. Anomaly detection is also called an abnormality determination. The abnormality detection results of the deceleration performance, the air brake, and the group brake are stored in the detection result database 103.

The diagnosis unit 160 performs diagnosis of the vehicle based on the abnormality detection result of the deceleration performance, the abnormality detection result of the air brake, and the abnormality detection result of the group brake. As an example, when the deceleration performance is normal, the air brake is abnormal, or the group brake is abnormal, it is diagnosed that there is a deterioration precursor of the entire air brake. Further, if the deceleration performance is abnormal, the group brake is normal, or one of the air brakes is abnormal, it is diagnosed that there is an abnormality in the deceleration performance caused by the deterioration of the one brake device. Various diagnostic rules stored in the diagnostic rule database 104 are used in such diagnostics.

The diagnosis unit 160 generates diagnosis output information corresponding to the diagnosis result, and causes the generated diagnosis output information to be displayed on the screen display device 600. Thereby, monitoring by a maintenance person or a driver of the railway is supported.

The learning mode and the usage mode can be automatically switched or switched by an instruction of a maintenance person or the like, or can be performed simultaneously.

Here, the air brake of the vehicle of the present embodiment, its peripheral configuration, and the braking level will be described. Fig. 2 shows a configuration example of a brake level, an air brake for a specific wheel in a vehicle, and an air cushion. Furthermore, the brake level is actually located in the cab of the tram.

A brake lever 10 as an example of a controller provides a means for the driver to perform a braking operation. The driver moves the brake lever from the bottom upwards, thereby applying a brake to the vehicle. The value of 1 to 8 displayed on the brake lever 10 is the brake level (braking phase), and the larger the value, the stronger the braking force acts on the vehicle. The number of levels here is an example, and it is not excluded to use more or less ranks. The brake level corresponds to an example of a control command value for the vehicle or the air brake.

Furthermore, the braking operation for the vehicle is not limited to the braking operation performed by the driver. For example, in a vehicle equipped with an automatic train stop (ATS), an automatic train control (ATC), or an automatic train operation (ATO), there are these devices instead of driving. The case of the brake operation. In this case, as an example, the command related to the brake brake output from the devices corresponds to the control command value.

The wheel 30 of the vehicle traveling on the track 20 is shown in FIG. One of the means for braking the brake using the brake is a tread brake 42 which is a type of air brake. Here, only one wheel is shown for the sake of explanation, but actually a plurality of sets of left and right wheels are provided. Furthermore, as an example, one air brake is provided in each vehicle. However, there may be vehicles that do not have an air brake.

The tread brake 42 uses the cylinder as a power. The brake shoe 41 is pressed against the tread surface of the wheel 30 as a surface in contact with the rail by raising the pressure of the brake cylinder as the pressure in the cylinder 43. The frictional force between the wheel 30 and the brake pad 41 becomes the braking force of the tread brake 42.

As described above, since the tread brake utilizes the frictional force of the brake pad, there is a possibility that the brake pad is worn by continuous use and the braking force is lowered. The tread brake is an example of a mechanical brake used for a vehicle, and a disk brake that obtains a braking force by pressing a disk fixed to a wheel axle with a pad or the like to obtain a braking force. The braking force of the brake varies depending on the wear state of the brake pad or the pad. When an abnormality is detected in the air brake by the abnormality diagnostic device, the worker or the like can check the brake block or the disk of the air brake to confirm whether or not there is actually no abnormality.

In addition to the wear of the parts, the braking force of the air brake also varies depending on the load on the vehicle. A load compensating device 50 is mounted on the vehicle of FIG. 2 . The load compensation device 50 includes an air cushion 51, and by detecting the air cushion pressure of the air cushion 51, the load on the vehicle can be measured. As the brake control of the vehicle, in addition to the operation of the brake lever 10, the braking force of the brake can be adjusted in accordance with the air cushion pressure detected by the load compensation device 50. Thereby, the desired deceleration can be achieved regardless of the increase or decrease of the load on the vehicle.

In order to supplement the braking force of the mechanical brake, an electric brake can also be used in combination. Alternatively, there is a case where a mechanical brake is used in order to supplement the braking force of the electric brake. Here, the electric brake will be described using FIG. 3. Fig. 3 shows an example of the configuration of a power generating brake and a regenerative brake of a certain vehicle. Furthermore, the vehicle is one of the vehicles in the group, and other vehicles are connected to the front and rear of the vehicle.

A main motor 60a and a main motor 60b are mounted on the vehicle of Fig. 3. When the power generating brake is used, the main motor 60a, the main motor 60b, and the resistor 70 constitute a closed circuit, and the electric power of the main motor is further converted into thermal energy.

On the other hand, when the regenerative brake is used, the electric power generated by the main motor 60a and the main motor 60b is transmitted from the pantograph 80 to the overhead wire 90. Alternatively, when a battery is mounted in the vehicle, the battery can be charged using the generated electric power. As described above, in the regenerative brake, the main motor 60a and the main motor 60b are used as generators, and kinetic energy is converted into electric power, thereby securing the braking force.

The mechanical brake or the power generating brake is an example, and even when another type of brake is used, it can be used as an object for abnormality detection and diagnosis by the abnormality diagnostic device 100.

Here, since the configuration of the brake is complicated and the characteristics of the brake can be varied by a plurality of factors or conditions, it is difficult to accurately detect the abnormality of the brake of the vehicle.

For example, in a vehicle, a plurality of types of brakes having different characteristics are used in combination as described. Further, as described above, the braking force of the brake of the vehicle changes depending on the load. For example, in the passenger vehicle, the number of passengers greatly varies depending on the time zone or the operation section, and therefore the braking force of the brake greatly changes in a short period of time. Regarding the vehicle used for the cargo, the load also varies greatly depending on the cargo load. Further, the tendency of the slope or the cand varies depending on the route or section in which the vehicle travels, and there is a possibility that the deceleration is changed when the brake operation is performed. Further, the difference in meteorological conditions such as the presence or absence of precipitation and the temperature of the air changes the physical properties of the components constituting the brake, and affects the characteristics of the brake. Further, the characteristics of the brake operation differ depending on the driver, and sometimes there is a difference in the characteristics of the brake due to the individual difference of each vehicle.

Therefore, in the present embodiment, not only the abnormality detection model of the air brake but also the abnormality detection model of the deceleration performance (abnormality detection model of the brake performance) and the abnormality detection model of the brake are used, thereby reducing the risk of erroneous diagnosis. Maintain early detection of anomalies and safe and stable operation of the railway.

Hereinafter, the abnormality diagnostic device 100 of Fig. 1 will be described in more detail. In the following description, the vehicle that is the target of the abnormality diagnosis is assumed to be a railway vehicle. However, the present invention is not limited thereto, and may be any vehicle including a wheel such as an automobile, a construction machine, or an airplane.

The abnormality diagnostic apparatus 100 of FIG. 1 includes a vehicle information collecting unit 110, an environment information collecting unit 120, a material processing unit 130, a model generating unit 140, an abnormality detecting unit 150, a diagnosis unit 160, and a transmitting unit 170.

The vehicle information collecting unit 110 acquires measurement information (also referred to as measurement data) related to the vehicle from various sensors of the vehicle system 200 in the vehicle. As an example of the sensor, there are a sensor that detects a brake operation or the like of the vehicle as a control command value, a sensor that detects a deceleration of the vehicle, a sensor that detects a driving speed, and a load that measures the load on the vehicle. Sensors, etc. In addition, various sensors can also be considered. The measurement information includes the detected value of the sensor (control command value, etc.), the measured value of the sensor (driving speed, load, deceleration, etc.). Further, when the deceleration is calculated based on the value of the speed sensor in the vehicle system 200, the calculated deceleration may be obtained as a measured value of the deceleration.

The type of measurement information to be acquired (the type of the sensor or the type of the control command value) can be arbitrarily set. The period in which measurement information is obtained can be arbitrarily set. For example, regarding the measurement information associated with the driving speed of the vehicle, the value is acquired in a short sampling period in milliseconds. A sensor for measuring the load on a vehicle takes a value in a sampling period in minutes.

The environmental information collecting unit 120 acquires environmental information of the vehicle from the environmental information system 300. As an example of environmental information, there are information related to the route of operation, or information related to weather. As an example of the information related to the running route, there are information related to the running route such as the gradient or the slope of each section (the height difference of the inner and outer rails of the railway). Examples of meteorological-related information include weather-related information such as weather, temperature, precipitation, wind speed, and air pressure. The acquisition of environmental information can be carried out by obtaining information accumulated in the database from the above-ground system, or by acquiring information transmitted from an external server. The type of environmental information to be acquired and the frequency of acquisition can be arbitrarily set.

The abnormality diagnostic device 100 can be installed as a ground device in a facility or an operation direction center of a railway operation management company, or can be installed as a vehicle installation device on a vehicle. The form of installation of the abnormality diagnostic device 100 is not particularly limited.

When the abnormality diagnostic device 100 is installed outside the vehicle as a ground device, as an example, measurement information and the like of the vehicle system 200 in the vehicle are received via the on-vehicle coil, the above-ground coil of the interrogator, and the information network on the ground. That is, the vehicle system 200 transmits data to the information network on the ground via the ground coil or the like, and the abnormality diagnostic device 100 receives the data via the information network on the ground. A metal cable, a coaxial cable, an optical cable, a telephone line, a wireless cable, an Ethernet (registered trademark), or the like can be used in the information network on the ground, but the method is not particularly limited. Moreover, the abnormality diagnostic device 100 can also receive data from the environmental information system 300 via the information network on the ground.

When the abnormality diagnostic device 100 is a vehicle-mounted device, the abnormality diagnostic device 100 acquires data from the vehicle system 200 via the information network in the vehicle. The information network in the vehicle has an Ethernet network or a local area network (LAN), but it can also be a network using other methods. The abnormality diagnostic device 100 can also acquire the data of the environmental information system 300 connected to the above-ground information network by using the on-board coil or the interrogator's ground coil.

Input device 500 provides an interface for maintenance personnel to operate. The input device 500 includes a mouse, a keyboard, a voice recognition system, an image recognition system, a touch panel, or a combination thereof. The maintenance personnel can input various instructions or materials from the input device 500 toward the abnormality diagnostic device 100 and operate.

The screen display device 600 displays the data or information output by the abnormality diagnostic device 100 in the form of a still image or a moving image. As an example, the screen display device 600 is a liquid crystal display (LCD), an organic electroluminescence display, or a fluorescent display (Vucuum Fluorescent Display (VFD)), but may be other methods. Display device.

A plurality of input devices 500 and screen display devices 600 can be provided. For example, the input device 500 and the screen display device 600 may be separately provided in the operation command center and the cab of the vehicle.

In addition, the input device 500 and the screen display device 600 may be an integrated device. For example, when there is a display with a touch panel function, the same device can serve both the input device 500 and the screen display device 600.

The abnormality diagnostic apparatus 100 includes an information database 101, a model database 102, a detection result database 103, and a diagnosis rule database 104 as a database.

In FIG. 1, the database 101, the database 102, the database 103, and the database 104 are all disposed inside the abnormality diagnostic apparatus 100. However, the method of configuring the database is not particularly limited. For example, a part of the database may be disposed in an external server or storage device or the like. The database can be installed by an associated database management system or various Not Only Structured Query Language (NoSQL) systems, but other methods can be used. The storage format of the database may be an Extensible Markup Language (XML), a JavaScript Object Notation (JSON), a Comma-Separated Values (CSV), or a binary. Forms and other forms. All the databases in the abnormality diagnostic device 100 need not be implemented in the same database system and storage format, and may be mixed and used in various ways.

The information database 101 internally stores the measurement information acquired by the vehicle information collecting unit 110 and the environmental information acquired by the environmental information collecting unit 120. The travel information of this embodiment includes at least one of measurement information and environmental information. A memory medium such as a memory element storing the travel information may be inserted into the abnormality diagnostic apparatus 100, and the memory medium may be used as the information database 101.

An example of the information database 101 is shown in FIGS. 4 and 5. As an example, the travel information (measurement information and environmental information) is stored in the form of the table 101a shown in FIG. 4 and the table 101b shown in FIG. 5. Here, it is divided into two tables to be saved corresponding to the frequency of the sampling.

The "time" column of the table 101a of Fig. 4 stores the generation time of the entry. In this example, an entry is generated at each fixed sampling time. However, the entry can also be generated by other criteria, such as generation of a section unit set in advance on the rail.

The values for identifying the group and the vehicle are stored in the "Group/Vehicle" column of Table 101a. In the present embodiment, a case where one brake device is disposed in each vehicle is assumed. However, there may be vehicles that do not have a brake device. In addition, it is not excluded to arrange a plurality of brake devices in one vehicle.

Weather-related information obtained from environmental information system 300 is stored in the "Weather" column of Form 101a.

The temperature-related information obtained from the environmental information system 300 is stored in the "air temperature" column of the table 101a. The temperature-related information may be the measured value measured, or may be a label that ranks the measured value. In the illustrated example, the conversion table 101c of FIG. 6 is used to store the labels of any one of T1, T2, T3, T4, T5, T6, and T7 converted from the real temperature. For example, when the temperature is -11 ° C, it is converted to level T1, when the temperature is 15 ° C, it is converted to level T4, and when the temperature is 33 ° C, it is converted to level T6.

Columns other than the "Temperature" column can also store processed information that has been calculated or converted for measurement information or environmental information.

In the "ride rate" column of Table 101a, the occupancy rate in percentage form is stored as an indicator of the load on the vehicle. Other indicators can also be used to indicate the load. As an example, the ride rate is defined by the ratio of the capacity of the vehicle to the number of passengers of the vehicle. The ride rate is mostly estimated based on the air cushion pressure of the load compensation device, so the air cushion pressure can also be directly used for the index.

The air cushion pressure is a measured value of the sensor, and is not a value indirectly estimated using a conversion table or a formula as in the ride rate, and therefore there is a possibility that the error at the time of model generation can be reduced. However, the air cushion pressure is dependent on the value of the manufacturer or model of the load compensation device mounted in the vehicle, and there is also a lack of versatility. Therefore, it is considered that there is a case where the difference between the difference of the load compensation devices of the respective vehicles can be absorbed using an index generally used as the ride rate.

The value of the slope of the route expressed in units of permils is stored in the "Slope" column of Table 101a. The so-called thousandth rate refers to a value indicating the height difference of the horizontal distance per 1000 m in meters. The thousandth rate is an example, and the value of other units can also be stored.

The slopes in millimeters are stored in the "Bevel" column of Form 101a, but values in other units can also be stored.

In addition, the "wind speed" column and the "barometric pressure" column are displayed in the table 101a. There may also be columns that store other information such as the current location, the current interval in the track, and the like.

The table 101b of FIG. 5 stores the time information, the brake level, the measured value of the deceleration of the vehicle, and the measured values of the air brake pressure of the air brake 1 to the air brake N provided in the plurality of vehicles. The entries of table 101b are generated at shorter time intervals than table 101a. The generation interval (sampling interval) of the entry of the table 101b may also be the same as the table 101a. Alternatively, a table in which the table 101b and the table 101a are integrated may be used. The deceleration can be the value of the acceleration sensor or a value calculated from the value of the speed sensor.

The processing of the data stored in the information database 101 can also be performed. For example, the material processing unit 130 displays the contents of the respective tables stored in the information database 101 on the screen display device 600. The maintenance person or the driver uses the input device 500 to perform processing operations on the materials. The data processing unit 130 performs data processing in accordance with the processing operation.

Further, the interval at which the information or the data is acquired by the vehicle information collecting unit 110 or the environmental information collecting unit 120 may be adjusted. For example, the data processing unit 130 receives the designation operation of the acquisition interval from the maintenance person or the driver via the input device 500, and adjusts the acquisition interval according to the content of the operation.

The model generation unit 140 generates an abnormality detection model of the deceleration performance, an abnormality detection model of the brake device (air brake), and an abnormality detection model of the group brake using the data stored in the information database 101.

The abnormality detection model of the deceleration performance includes a prediction model of deceleration (hereinafter, a deceleration model) and a threshold value (hereinafter, deceleration threshold value) related to the deviation from the predicted value of the deceleration model. The deceleration threshold value is used in the abnormality detection of the deceleration of the vehicle by the abnormality detecting unit 150. Specifically, the deceleration threshold is used in order to compare with the deviation of the difference between the predicted value of the deceleration model and the measured value of the deceleration.

The abnormality detection model of the brake device includes a prediction model of the braking force and a threshold value (hereinafter, individual brake threshold value) related to the deviation from the predicted value of the self-predicted model. In the case of an air brake, the braking force is equivalent to the air brake pressure. In the present embodiment, a prediction model of the air brake pressure (hereinafter, an air brake pressure model) is assumed as a prediction model of the braking force. The individual brake threshold value is used in the abnormality detection by the abnormality detecting unit 150 for the brake device. Specifically, the individual brake threshold is used in order to compare with the deviation of the difference between the predicted value of the air brake pressure model and the measured value of the air brake pressure.

The abnormality detection model of the group brake includes a prediction model based on the values of the braking forces of the plurality of brake devices (hereinafter, the group brake model) and a threshold associated with the deviation of the predicted value of the self-predicted model (hereinafter, group brake threshold) value). In the present embodiment, an air brake is assumed as the brake device, and a prediction model of the total of the air brake pressure is assumed. If the value is based on the braking force of a plurality of brake devices, other values such as a statistical value such as an average value or an intermediate value may be used instead of the total of the braking forces. Specifically, the group brake threshold value is used in order to compare with the deviation of the difference between the predicted value of the group brake model and the measured value of the air brake pressure.

The abnormality detection models generated by the model generation unit 140 are stored in the model database 102.

FIG. 7 is an example of a model database 102. Each anomaly detection model is identified by a model identifier (Identifier, ID). The data indicating the prediction model or the address (pointer) of the memory in which the prediction model is stored is stored in the column of the prediction model. The threshold set for the prediction model is stored in the column of the threshold.

As an example, when the abnormality diagnostic apparatus 100 is started or when a vehicle to be diagnosed is newly added, the abnormality detection model is generated by the learning mode. When there are a plurality of diagnostic objects, an abnormality detecting model is generated for each diagnostic object. The model generation unit 140 may reproduce the abnormality detection model periodically or in response to an instruction from a maintenance person or the like, and update the previous abnormality detection model using the abnormality detection model created again.

Hereinafter, a method of generating an abnormality detection model will be described in detail. The abnormality detection model is generated using a data sample (feature vector) extracted from the information database 101. Hereinafter, an example of the abnormality detecting model for generating the deceleration will be described. However, the abnormality detecting model of the air brake and the abnormality detecting model of the group brake can be generated in the same manner.

The data sample (feature vector) contains more than one explanatory variable. As an example of the explanatory variable, the value of the brake level (control command value) of the table 101b is used. In addition to this, other kinds of values (speed, etc.) in the travel information or the specifications of the vehicle (size or weight of the vehicle, etc.) may be used as explanatory variables. It is also possible to calculate a plurality of items included in the driving information to generate explanatory variables. In addition, the target variable of the prediction model here is deceleration. The data sample can be generated in the item unit of the brake information table 101b, and the granularity of time can be reduced, a plurality of consecutive items are combined into one, and a data sample is generated based on the data samples.

Hereinafter, a method of generating a prediction model (here, a deceleration model) will be described. Imagine the use of a regression model as a predictive model. Using the information database 101, the model generation unit 140 obtains the feature vector X=(x ₁ , x ₂ , x ₃ , . . . , x _n ) having the explanatory variable as an element.

Then, the model generation unit 140 performs a multiple regression analysis to obtain a formula (1) for predicting the deceleration as the target variable. [Math 1] (1) Here, y is the target variable, x _n is the explanatory variable, and b _n is the partial regression coefficient (parameter). The parameters may be obtained by maximum likelihood estimation or the like. Furthermore, in order to absorb the difference in the unit of measurement of each explanatory variable, the target variable and all explanatory variables are normalized to an average value of 0 and a dispersion of 1, whereby a standard partial regression coefficient can be used as the partial regression coefficient b _n . The explanatory variables can be one or more than one.

Model generation using complex regression analysis is an example. In addition, other methods such as Support Vector Regression and self-regression can be used to generate a prediction model of the target variable.

Cross-validation can also be used when generating predictive models. For example, the data sample can be divided into multiple sets, at least one of which is set as test data for verification, and other sets are used for model generation. Thereby, the performance of the generated model can be confirmed.

There is also a case where a sufficient degree of estimation accuracy cannot be obtained by a simple relational case using only a control command value as an explanatory variable. The reason for this may be, for example, transient responsiveness of deceleration or external factors such as route gradient. Therefore, in order to construct a prediction model with better accuracy, it is also possible to estimate the parameters in the transient response, the steady state, or the braking level switching mode, and the influence of the route gradient.

Here, an example of generation of an abnormality detection model indicating deceleration is shown. When an abnormality detection model of the air brake is generated, as an example, the air brake pressure may be used as the target variable as long as the control command value (braking level) is used as the explanatory variable. When the abnormality detection model of the group brake is generated, as an example, the control command value (braking level) is used as the explanatory variable, and the total of the air brake pressures of the plurality of air brakes may be used as the target variable. It is also possible to add an explanatory variable other than the control command value.

Here, when it is set in the learning mode, the information database 101 stores information acquired in a state in which the brake device (air brake) group is in a normal state. Therefore, the various prediction models (deceleration model, air brake pressure model, and group brake model) generated in the learning mode can be said to be modeled on the premise that the air brakes are in a normal state. However, it is also possible to allow a part of the air brake to malfunction, and the measurement information of the air brake is stored in the information database 101.

Next, a method of determining the threshold value set for the prediction model will be described. In the following description, when described as a prediction model, any of the deceleration model, the air brake pressure model, and the group brake model can be expressed. Similarly to the threshold, any of the deceleration threshold, the individual brake threshold, and the group brake threshold can be expressed.

Here, as a method of using the threshold value, when the difference between the predicted value of the target variable calculated by the prediction model (for example, the predicted value of the deceleration) and the measured value (measured value) of the deceleration exceeds the threshold value, Make an abnormal decision. The decision to make an abnormality is also called a detection abnormality. The difference between the predicted value and the measured value is called the deviation. There may be cases where the measured value is larger than the predicted value and the case where the measured value is smaller than the predicted value, and thus the value of the deviation may be a sign of either positive or negative. When looking at the absolute value of the distance from the predicted value, and the symbol does not become a problem, the absolute value of the difference can also be defined as a deviation.

Fig. 8 shows an example of a method of determining the threshold value using the normal distribution. The graph of Fig. 8 shows the normal distribution 401 of deviation, with the horizontal axis being the deviation and the vertical axis being the probability density. A deviation of the predicted values of the plurality of prediction models from the measured values is obtained, and a normal distribution 401 is created assuming that the plurality of deviations are distributed according to a normal state. The data used to obtain the plurality of deviations may be a data sample used for predicting the generation of the model, or may be test data, or other driving information irrelevant to the generation of the prediction model, or any combination of the foregoing. When the deviation of the deviation is larger, as in the normal distribution 402 indicated by the broken line, the normal distribution 403 becomes a distribution in which the edge is further enlarged.

With the normal distribution 401, the threshold for the prediction model is set. As an example, when the standard deviation is σ, the value of the constant multiple of the standard deviation such as 2σ or 3σ is set as the threshold value. When 2σ is set to the threshold value, if the deviation exceeds 2σ, an abnormality is detected in the abnormality detection. If such a threshold is set, about 95% of the measured value is judged to be abnormal (normal). As another setting example of the threshold value, a deviation value corresponding to a predetermined probability (for example, upper X percentage points or lower X percentage points) or an absolute value thereof may be set as a threshold value. The method for determining the threshold value described here is an example, and the use of other methods is not excluded. For example, a distribution other than the normal distribution can be assumed to determine the threshold, and maintenance personnel, drivers, and the like can also set the threshold based on experience.

Any of the deceleration threshold, the individual brake threshold, and the group brake threshold can be determined by the method described above.

The abnormality detecting unit 150 performs abnormality detection using various abnormality detecting models stored in the model database 102 and traveling information stored in the information database 101 in the operation mode. For example, a feature vector may be created in each entry of the table 101b or the table 101a of FIG. 5 to perform abnormality detection, or an entry of a fixed time interval may be selected, and a feature vector may be created according to the selected entry to perform abnormality detection, or may be fixed according to the fixed The item group during the period creates a feature vector to perform anomaly detection. Alternatively, the abnormality detection may be performed by creating a feature vector based on an entry at a time specified by a maintenance person or the like, or an entry group in a period specified by the maintenance person.

The abnormality detecting unit 150 performs abnormality detection of the deceleration performance, abnormality detection of the air brake, and abnormality detection of the group brake.

In the abnormality detection of the deceleration performance, a feature vector (control command value or the like) is generated based on the travel information for the abnormality detection, and the deceleration is predicted using the generated feature vector and the deceleration model. The deviation of the predicted deceleration from the measured deceleration (e.g., obtained from Table 101b) is compared to the deceleration threshold. If it is less than the deceleration threshold, it is determined that the deceleration performance is normal, and if it is greater than the deceleration threshold, it is determined that the deceleration performance is abnormal.

In the abnormality detection of the air brake, a feature vector (control command value or the like) is generated based on the travel information for abnormality detection, and the air brake pressure is predicted using the generated feature vector and the air brake pressure model. The deviation of the predicted air brake pressure from the measured air brake pressure (e.g., obtained from Table 101b) is compared to the individual brake threshold. If it is below the individual brake threshold, it is determined that the air brake is normal, and if it is greater than the individual brake threshold, it is determined that the air brake is abnormal.

In the abnormality detection of the group brake, a feature vector (control command value or the like) is generated based on the travel information for abnormality detection, and the total of the air brake pressures of the plurality of air brakes is performed using the generated feature vector and the group brake model. prediction. The deviation of the sum of the predicted air brake pressures from the sum of the measured air brake pressures is compared to the group brake threshold. If it is below the group brake threshold, it is determined that the group brake is normal, and if it is greater than the group brake threshold, it is determined that the group brake is abnormal.

Here, a specific example of the operation of the abnormality detection using the deceleration performance of the abnormality detecting unit 150 is shown.

FIG. 9 is a view for explaining an operation example of the abnormality detecting unit 150. The upper stage of Fig. 9 shows the brake level. The middle section indicates the deceleration of the brake. The lower section shows the deviation of the measured value from the predicted value obtained from the predictive model. In the deceleration model, the braking level corresponds to the explanatory variable, and the deceleration corresponds to the target variable.

At time t1, an operation of bringing the brake level to four levels is performed. Each of the air brakes receives this operation and applies a braking force to the vehicle. Therefore, the deceleration of the vehicle increases, and thereafter, it is temporarily stabilized at a fixed value. Although the predicted value of the deceleration is slightly deviated from the measured value (actual measured value), the shift is substantially the same, and the deviation between the predicted value and the measured value becomes a range of the imperfect deceleration threshold.

Thereafter, at the time t2, the time t3, and the time t4, the timing of the three deviations exceeding the deceleration threshold is generated, and the abnormality detecting unit 150 detects the abnormality at each timing.

At time t5, an operation of changing the brake level from four levels to two levels is performed. Each air brake receives this operation, reducing the braking force applied to the vehicle, and thus the deceleration of the vehicle is reduced.

At time t6, an operation to release the brake is performed. Each air brake receives this operation, further reducing the braking force applied to the vehicle, and thus the deceleration of the vehicle is further reduced.

After the abnormality is detected at the time t4, since the deviation is within the range of the deceleration threshold, the abnormality is not detected.

Although an example of the operation of the abnormality detection of the deceleration performance is shown here, the abnormality detection of the air brake of each vehicle and the abnormality detection of the group brake can be performed in the same manner.

The abnormality detecting unit 150 stores the information in the detection result database 103 based on the abnormality detection result of the deceleration performance, the abnormality detection result of the air brake, and the abnormality detection result of the group brake.

FIG. 10 shows an example of the detection result database 103. For a certain group, the abnormality detection result of the braking level and the deceleration performance, the abnormality detection result of the air brake of each vehicle, and the abnormality detection result of the group brake are stored in time series. In this example, in the first to sixth entries, the abnormality detection results are all abnormal, but in the seventh and eighth entries, an abnormality is detected in the air brake 1.

When a predetermined abnormality is detected, the transmitting unit 170 transmits a message of the abnormality notification to the terminal 400 used by the operator of the railway, the driver, or the maintenance person. The predetermined abnormality can be arbitrarily defined as a case where an abnormality of the deceleration performance is detected, a case where an abnormality of the air brake is fixed in the air brake or more, and an abnormality in which the group brake is detected.

The message notification can be performed by the transmission of an e-mail, the display of a pop-up message on the operation screen of the terminal 400, the notification by a predetermined machine management agreement, or the like, or by other means. The notification may also contain detailed information about the exception (eg, the location on the map where the exception has occurred (current value), the identifier of the vehicle that has generated the exception, etc.). By receiving the notification, the user or maintenance personnel can know the meaning of the abnormality detected and its details.

The diagnosis unit 160 performs diagnosis of the vehicle based on the detection result database 103 and the diagnosis rule database 104.

The diagnostic rule database 104 holds diagnostic rule data that specifies the diagnosis result in combination with the detection of the presence or absence of the abnormality of each air brake (brake device), the detection of the abnormality of the presence or absence of the deceleration performance, and the detection of the presence or absence of the abnormality of the group brake.

FIG. 11 shows an example of the diagnostic rule database 104. In this example, there are eight diagnostic rules each having a diagnosis rule number 1 to a diagnosis rule number 8. "○" in the figure indicates that the abnormality detection result is no abnormality. The "x" in the figure indicates that the abnormality detection result is abnormal.

In the diagnostic rule 1, the abnormality detection results of the air brake 1 to the air brake N are all abnormal, and the abnormality detection result of the group brake is also abnormal, and the abnormality detection result of the deceleration performance is also the diagnosis result when there is no abnormality. Specifically, the diagnosis result of the diagnosis rule 1 indicates normal.

In the diagnostic rule 2, the abnormality detection results of the air brake 1 to the air brake N are all abnormal, and the abnormality detection result of the group brake is also abnormal, but the abnormality detection result of the deceleration performance is a diagnosis result when there is an abnormality. Specifically, the diagnosis result of the diagnosis rule 2 indicates that there is an abnormality in the brake block, the wheel, or the road surface state.

The diagnosis rule 3 specifies that the abnormality detection results of the air brake 1 to the air brake N are all abnormal, but the abnormality detection result of the group brake is abnormal, and the abnormality detection result of the deceleration performance is the diagnosis result when there is no abnormality. Specifically, the diagnosis result of the diagnosis rule 3 indicates that there is a precursor to deterioration of the entire air brake.

The diagnostic rule 4 specifies that the abnormality detection results of the air brake 1 to the air brake N are all abnormal, but the abnormality detection result of the group brake is abnormal, and the abnormality detection result of the deceleration performance is also the diagnosis result when there is an abnormality. Specifically, the diagnosis result of the diagnosis rule 4 indicates that there is an abnormality in the deceleration performance caused by the deterioration of the entire air brake.

The diagnosis rule 5 specifies that at least one of the abnormality detection results of the air brake 1 to the air brake N is abnormal, but the abnormality detection result of the group brake is no abnormality, and the abnormality detection result of the deceleration performance is also a diagnosis result when there is no abnormality. Specifically, the diagnosis result of the diagnosis rule 5 indicates that there is a precursor to deterioration in the abnormal air brake, or an abnormal air brake is deteriorating.

The diagnosis rule 6 specifies that at least one of the abnormality detection results of the air brake 1 to the air brake N is abnormal, but the abnormality detection result of the group brake is abnormal, and the abnormality detection result of the deceleration performance is abnormal. diagnostic result. Specifically, the diagnosis result of the diagnosis rule 6 indicates that there is an abnormality in the deceleration performance caused by the abnormal air brake.

The diagnosis rule 7 specifies that all the abnormality detection results of the air brake 1 to the air brake N abnormality detection result are abnormal, and the abnormality detection result of the group brake is also abnormal, but the abnormality detection result of the deceleration performance is the diagnosis result when there is no abnormality. . Specifically, the diagnosis result of the diagnosis rule 7 indicates that there is an abnormal symptom of the deceleration performance due to deterioration of the entire air brake.

The diagnosis rule 8 specifies that all the abnormality detection results of the air brake 1 to the air brake N abnormality detection result are abnormal, and the abnormality detection result of the group brake is also abnormal, and the abnormality detection result of the deceleration performance is also an abnormality diagnosis. result. Specifically, the diagnosis result of the diagnosis rule 8 indicates that there is an abnormality in the deceleration performance due to deterioration of the entire air brake.

Diagnostic rules other than diagnostic rule 1 to diagnosis rule 8 can also be defined. For example, in a modified example of the diagnostic rule 7, when an abnormality detection result of a predetermined number or more of air brakes is abnormal, an abnormality indicating a deceleration performance due to deterioration of the abnormal air brake may be defined. The diagnosis of the symptoms. Further, as a modification of the diagnostic rule 8, when the abnormality detection result of the predetermined number or more of the air brakes is abnormal, an abnormality indicating the deceleration performance due to the deterioration of the abnormal air brake may be defined. The diagnosis result. Other diagnostic rules can also be defined.

The diagnosing unit 160 determines which one of the diagnostic rule 1 to the diagnostic rule 8 is satisfied for each entry stored in the detection result database 103, and generates diagnostic output information corresponding to the diagnosis result indicated by the matching diagnostic rule. There are also cases where multiple diagnostic rules are met. The diagnosis unit 160 displays the generated diagnosis output information on the screen display device 600. When the diagnosis rule 1 indicating the normal diagnosis result is met, the configuration of generating and displaying the diagnosis output information may not be performed.

Further, when an abnormality in the deceleration performance is detected, the diagnosis unit 160 may calculate error information corresponding to the difference between the predicted value of the deceleration model and the measured value of the deceleration, and output it as diagnostic output information. As an example of calculation of the error information, the difference between the braking distance in the case of the deceleration of the predicted value and the braking distance in the case of the deceleration of the measured value may be calculated. The braking distance refers to the distance from the start of braking to the stop of braking, or the distance until the desired deceleration or speed is reached. Thereby, it is possible to grasp how much the deterioration of the air brake or the deterioration of the group brake affects the deceleration compared to the normal time. That is, the difference in the braking distance represents the abnormal influence degree information.

FIG. 12 shows an example of a display screen (diagnosis result screen) of the diagnostic output information displayed by the screen display device 600. On this screen, the result of the diagnosis performed on the group A is displayed. Here, it is assumed that the screen display device 600 is located in a command room for management and monitoring of the formation.

At the top of the diagnosis result screen, the group to be diagnosed is displayed as group A. In the second paragraph, the number of the diagnostic rules that match the multiple diagnostic rules is displayed. In paragraph 3, the diagnostic results shown in the compliant diagnostic rules are displayed. Here, since the diagnosis rule 6 is satisfied, there is an abnormality in the deceleration performance caused by the deterioration of the individual air brakes. In the fourth paragraph, information indicating the air brake that is the cause of the abnormality in the deceleration performance is displayed. Which air brake is a cause may be, for example, an air brake that is abnormal in the abnormality detection result in the detection result database. In the fifth paragraph, the difference in the braking distance when compared with the normal time is shown as the degree of abnormal influence.

The diagnostic output information shown here is an example and can be used in various display forms depending on the application. The diagnostic output information can also be recorded in a separately prepared database. In this case, the maintenance person or the like may select a record from the database to perform a display instruction operation, thereby displaying it on the screen display device 600.

The diagnostic rule of FIG. 11 is defined using three abnormal detection results of the air brake, the deceleration, and the group brake, but may be defined using two of them. For example, the diagnosis rule can also be defined using the abnormality detection result of the deceleration and the abnormality detection result of the air brake.

For example, the abnormality detection result of the air brake can be combined with the abnormality detection result of the deceleration, and the diagnosis rule as shown in FIG. 13 can be defined. Alternatively, the abnormality detection result of the group brake and the abnormality detection result of the deceleration may be combined to define a diagnosis rule as shown in FIG.

According to the abnormality diagnostic device of the present embodiment, the three types of abnormality detection results of the air brake, the deceleration, and the group brake are combined, and the vehicle is diagnosed, whereby the diagnosis of the vehicle with high accuracy can be performed. For example, the diagnosis of the anomaly of the air brake can be performed by the diagnosis rule 3, the diagnosis rule 5, or the diagnosis rule 7. In addition, with the diagnosis rule 2, the environment outside the vehicle can be specified as a factor when the desired deceleration performance (braking performance) cannot be obtained.

Fig. 15 shows a hardware configuration of the abnormality diagnostic device of the present embodiment. The abnormality diagnostic device of this embodiment includes a computer device 100. The computer device 100 includes a central processing unit (CPU) 151, an input interface 152, a display device 153, a communication device 154, a main memory device 155, and an external memory device 156, and the devices are mutually connected by the bus bar 157. connection.

The CPU (Central Processing Unit) 151 executes an abnormality diagnostic program as a computer program on the main memory device 155. The abnormality diagnostic program is a program that realizes each of the above-described functions of the abnormality diagnostic device. Each function configuration is realized by the CPU 151 executing an abnormality diagnostic program.

The input interface 152 is a circuit for inputting an operation signal from an input device such as a keyboard, a mouse, and a touch panel to the abnormality diagnostic device.

The display device 153 displays the material or information output from the abnormality diagnostic device. The display device 153 is, for example, an LCD (Liquid Crystal Display), a cathode ray tube (CRT), and a plasma display panel (PDP), but is not limited thereto. The data or information outputted from the computer device 100 can be displayed by the display device 153.

The communication device 154 is a circuit for causing the abnormality diagnostic device to communicate with the external device by wireless or by wire. The measurement information can be input from an external device via the communication device 154. The measurement information input from the external device can be stored in the information database 101.

The main memory device 155 stores the abnormality diagnostic program, the data required for execution of the abnormality diagnostic program, and the data generated by the execution of the abnormality diagnostic program. The abnormality diagnostic program is expanded on the main memory device 155 and executed. The main memory device 155 is, for example, a random access memory (RAM), a dynamic random access memory (DRAM), or a static random access memory (SRAM). It is not limited to this. The information database 101, the model database 102, the test result database 103, and the diagnostic rule database 104 may also be constructed on the main memory device 155.

The external memory device 156 stores an abnormality diagnostic program, data required for execution of the abnormality diagnostic program, and data generated by execution of the abnormality diagnostic program. The programs or materials are read by the main memory device 155 when the abnormality diagnostic program is executed. The external memory device 156 is, for example, a hard disk, a compact disk, a flash memory, or a magnetic tape, but is not limited thereto. The information database 101, the model database 102, the test result database 103, and the diagnostic rule database 104 may also be constructed on the external memory device 156.

Furthermore, the abnormality diagnostic program can be installed in the computer device 100 in advance, or can be stored in a memory medium such as a compact disc-read only memory (CD-ROM). In addition, the exception diagnostics can be uploaded to the Internet.

Furthermore, the computer device 100 may include one or more processors 151, an input interface 152, a display device 153, a communication device 154, and a main memory device 155, and may be connected to peripheral devices such as a printer or a scanner.

Further, the abnormality detecting device may be constituted by a single computer device 100, or may be configured in the form of a system including a plurality of computer devices 100 connected to each other.

Fig. 16 is a flowchart showing a diagnosis process performed in an operation mode according to an embodiment of the present invention. The process of the flowchart of FIG. 16 can be executed by a certain operation of the vehicle to be diagnosed, or can be executed at a fixed cycle, or can be executed at a timing when the user such as a maintenance person receives the instruction, or Other timings are executed. Here, as the vehicle to be diagnosed, vehicle grouping is assumed.

In step S101, the abnormality detecting unit 150 acquires travel information related to the vehicle group to be diagnosed from the information database 101 (see FIGS. 5 and 4).

In step S102, the abnormality detecting unit 150 acquires an abnormality detecting model related to the vehicle group to be diagnosed from the model database 102. Specifically, an abnormality detection model for deceleration, an abnormality detection model for an air brake mounted in each vehicle, and an abnormality detection model for the group brake are obtained. An abnormality detecting model of the air brake may be present in each air brake, but a case where a common abnormality detecting model is included in a plurality of air brakes is conceived here.

The anomaly detection model of the deceleration includes a deceleration model and a deceleration threshold. The air brake anomaly detection model includes an air brake pressure model and individual brake thresholds. The anomaly detection model of the group brake includes a group brake model and a group brake threshold.

In step S103, the abnormality detecting unit 150 performs abnormality detection using various abnormality detecting models stored in the model database 102 and the information database 101. Specifically, a feature vector (control command value or the like) for detecting the abnormality of the deceleration is generated based on the travel information, and the deceleration is predicted using the generated feature vector and the deceleration model. The deviation between the predicted deceleration and the measured deceleration is compared to the deceleration threshold. If it is below the deceleration threshold, it is judged to be normal, and if it is greater than the deceleration threshold, it is determined to be abnormal.

Similarly, a feature vector (control command value or the like) for detecting an abnormality of the air brake is generated based on the travel information, and the air brake pressure is predicted using the generated feature vector and the air brake pressure model. The deviation of the predicted air brake pressure from the measured air brake pressure is compared to the individual brake threshold. If it is below the individual brake threshold, it is judged to be normal, and if it is greater than the individual brake threshold, it is determined to be abnormal.

Further, a feature vector (control command value or the like) for detecting an abnormality of the group brake is generated based on the travel information, and the total of the air brake pressures of the plurality of air brakes is predicted using the generated feature vector and the group brake model. The deviation of the sum of the predicted air brake pressures from the sum of the measured air brake pressures is compared to the group brake threshold. If it is below the group brake threshold, it is judged to be normal, and if it is greater than the group brake threshold, it is determined to be abnormal.

In step S104, the diagnosis unit 160 uses the abnormality detection result of the deceleration, the abnormality detection result of the air brake, and the abnormality detection result of the group brake and the plurality of diagnosis rules stored in the diagnosis rule database to perform the vehicle to be diagnosed. Grouped diagnosis. The diagnosis unit 160 specifies a diagnosis rule that satisfies the abnormality detection results, and determines a diagnosis result indicated by the diagnosis rule.

In step S105, the diagnosis unit 160 generates diagnosis output information corresponding to the diagnosis result, and displays the diagnosis output information on the screen of the screen display device 600.

In the processing of this flowchart, the diagnosis is performed using three kinds of abnormality detection results of the air brake, the deceleration, and the group brake, but it is also possible to perform diagnosis using two of them.

In addition, the present invention is not limited to the above-described embodiments, and constituent elements may be modified and embodied in the scope of the invention without departing from the spirit and scope of the invention. Further, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the above embodiments. Further, for example, a configuration in which several constituent elements are deleted from all the constituent elements shown in the respective embodiments may be considered. Further, the constituent elements described in the different embodiments may be combined as appropriate.

10‧‧‧ brake lever

20‧‧‧ Track

30‧‧‧ Wheels

41‧‧‧ brake pads

42‧‧‧Tread brake

43‧‧‧ cylinder

50‧‧‧Load compensation device

51‧‧‧ air cushion

60a, 60b‧‧‧ main motor

70‧‧‧Resistors

80‧‧‧Split bow

90‧‧‧Wired

100‧‧‧Abnormal diagnostic device/computer device

101‧‧‧Information Database

Forms 101a, 101b, 101c‧‧

102‧‧‧Model database

103‧‧‧Test Results Database

104‧‧‧Diagnostic Rules Database

110‧‧‧Vehicle Information Collection Department

120‧‧‧Environment Information Collection Department

130‧‧‧Data Processing Department

140‧‧‧Model Generation Department

150‧‧‧Anomaly Detection Department

151‧‧‧CPU

152‧‧‧Input interface

153‧‧‧ display device

154‧‧‧Communication device

155‧‧‧Main memory device

156‧‧‧External memory device

157‧‧ ‧ busbar

160‧‧ ‧Diagnosing Department

170‧‧‧Reporting Department

200‧‧‧ Vehicle System

300‧‧‧Environmental Information System

400‧‧‧ Terminal

401, 402, 403‧‧‧ normal distribution

500‧‧‧ input device

600‧‧‧ screen display device

t, t1~t6‧‧‧

Σ‧‧ standard deviation

S101～S105‧‧‧Steps

Fig. 1 is a block diagram showing an abnormality diagnosis system according to an embodiment of the present invention. 2 is a view showing a configuration example of a brake notch, a brake, and an air spring of a railway vehicle. 3 is a view showing an example of the configuration of a power generating brake and a regenerative brake of a railway vehicle. 4 is a diagram showing an example of a table related to measurement information and environmental information. FIG. 5 is a diagram showing an example of a table related to measurement information. Fig. 6 is a diagram showing an example of a conversion table. Fig. 7 is a diagram showing an example of a model database. FIG. 8 is a view showing an example of a method of determining a threshold value using a normal distribution. FIG. 9 is a view showing an operation example of the abnormality detecting unit. Fig. 10 is a view showing an example of a detection result database. 11 is a diagram showing an example of a diagnostic rule database. Fig. 12 is a view showing an example of a display screen of diagnostic output information. Fig. 13 is a view showing another example of a diagnostic rule database. Fig. 14 is a view showing still another example of the diagnostic rule database. Fig. 15 is a view showing a hardware configuration of an abnormality diagnosing device according to the embodiment of the present invention. Fig. 16 is a flowchart of the diagnosis process of the embodiment of the present invention.

Claims (14)

An abnormality diagnosing device comprising: an abnormality detecting unit that performs an abnormality detection of a deceleration performance of the vehicle according to a predicted model of a control command value for the brake device and a deceleration of the vehicle, and according to the control command value and the A prediction model of the braking force of the brake device performs abnormality detection of the brake device; and a diagnosis unit that diagnoses the vehicle based on the abnormality detection result of the deceleration performance and the abnormality detection result of the brake device. The abnormality diagnostic device according to claim 1, wherein the control command value is for a plurality of brake devices included in a plurality of connected vehicles, and the abnormality detecting portion performs the plurality of brake devices The abnormality detection is performed by the diagnosis unit based on the abnormality detection result of the deceleration performance and the abnormality detection result of the plurality of brake devices. The abnormality diagnostic apparatus according to the second aspect of the invention, wherein the diagnostic unit specifies a diagnosis rule of a diagnosis result based on a combination of detection of an abnormality of the deceleration performance and detection of an abnormality of the brake device. Information on the diagnosis of the vehicle. The abnormality diagnostic device according to claim 2, wherein the abnormality detecting unit performs the inclusion of the plurality of braking devices based on a prediction model based on a value of a braking force of the plurality of braking devices. Abnormality detection of the brake system The diagnosis unit diagnoses the vehicle using the abnormality detection result of the brake system. The abnormality diagnostic device according to claim 4, wherein the value based on the braking force of the plurality of braking devices is a total of braking forces of the plurality of braking devices. The abnormality diagnostic device according to Item 4 or 5, wherein the diagnostic unit detects the abnormality of the deceleration performance and the presence or absence of the abnormality of the brake device, and the presence or absence of the brake. The combination of the abnormal detection of the system specifies the diagnostic rule data of the diagnosis result, and the vehicle is diagnosed. The abnormality diagnosing device according to any one of the first to sixth aspect, wherein the abnormality detecting unit is based on a difference between a predicted value of the predicted model of the deceleration and a measured value of the deceleration, An abnormality detection of the deceleration performance is performed. The abnormality diagnosing device according to any one of the preceding claims, wherein the abnormality detecting unit is based on a difference between a predicted value of the predicted model of the braking force and a measured value of the braking force, An abnormality detection of the brake device is performed. The abnormality diagnostic device according to claim 8, wherein the diagnostic unit calculates a predicted value of the predicted model corresponding to the deceleration and a measurement of the deceleration when an abnormality of the brake device is detected Abnormal influence information of the difference of values. The abnormality diagnostic device according to claim 9, wherein the diagnosis unit calculates a difference between a braking distance depending on a deceleration of the predicted value and a braking distance depending on a deceleration of the measured value as the Abnormal impact information. The abnormality diagnostic device according to any one of claims 1 to 10, wherein the control command value is a command value related to the braking force. The abnormality diagnostic device according to any one of claims 1 to 11, wherein the brake device is an air brake, and the braking force is an air brake pressure. An abnormality diagnosis method, comprising: performing an abnormality detection of a deceleration performance of the vehicle according to a prediction model for a braking device and a deceleration model of the vehicle; and braking force according to the control command value and the braking device a prediction model for performing an abnormality detection of the braking device; and performing diagnosis on the vehicle based on an abnormality detection result of the deceleration performance and an abnormality detection result of the braking device. A computer readable recording medium storing a computer program for causing a computer to perform the following steps: performing an abnormality detecting step of the deceleration performance of the vehicle according to a prediction model for a braking device and a prediction model of a deceleration of the vehicle And performing a step of detecting abnormality of the braking device according to the predicted value of the control command value and a braking force of the braking device; and an abnormality detecting result according to the deceleration performance and an abnormality detecting result of the braking device, The step of diagnosing the vehicle.