Malfunction sign diagnosing device and malfunction sign diagnosing method

Abstract

To enable a diagnosis for a malfunction sign even in a case in which pressure information is not obtainable.SOLUTION: A malfunction sign diagnosing device includes: a same-condition data extracting unit that obtains, from an operating record storing unit, an operation record data set including multiple pieces of operation record data that match with an output consumption condition corresponding to the operating time of a given running relevant equipment; a reference time calculating unit which averages, for the operating record data set, the operating times of the running relevant equipment corresponding to the output consumption condition, and which calculates a reference time in a normal operation under the output consumption condition; and a malfunction sign diagnosing unit which calculates an abnormality level based on a comparison between the operating time of the given running relevant equipment and the reference time, and which diagnoses whether the running relevant equipment has a malfunction sign or not by performing statistical processing on the abnormality level.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a failure prediction diagnosis device and a failure prediction diagnosis method, and is suitably applied to a failure prediction diagnosis device for diagnosing whether there is a failure prediction regarding equipment mounted on a moving body such as a railway vehicle, for example.

Background Art

[0002] In recent years, from the viewpoint of improving the efficiency and labor saving of maintenance work for railway vehicles, the development of a technology for performing failure prediction diagnosis (hereinafter referred to as "failure prediction diagnosis") using operation data obtained from on-vehicle equipment has been demanded. Among on-vehicle equipment, an air compressor that generates compressed air used in an air brake device, an air spring device, etc. affects the operation of other equipment such as the air brake device in the event of a failure. Therefore, there is a high need for a failure prediction diagnosis technology that detects and diagnoses the prediction before a failure occurs.

[0003] As the background art in this technical field, there is the technology disclosed in Patent Document 1. In the technology disclosed in Patent Document 1, data is extracted when the air compressor is operating and the air brake device is not operating, and the largest pressure increase amount in the accumulator system among the data obtained by dividing the data at regular intervals is extracted. Next, in the technology disclosed in Patent Document 1, the pressure increase amount is calculated by multiple regression analysis using, as explanatory variables, the pressure displacement amount of the air spring at that time, the occupancy rate calculated from the vehicle weight, the traveling speed, and the outside air temperature information. Further, in the technology disclosed in Patent Document 1, the largest pressure increase amount in the accumulator system extracted is compared with the pressure increase amount calculated by multiple regression analysis to perform a failure prediction diagnosis. Also, Patent Document 1 describes that a boundary line used for the determination of failure prediction diagnosis is calculated using data within one year after the start of business.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the technology disclosed in Patent Document 1, as described above, pressure information such as the amount of pressure increase in the accumulator system is used. However, among the data that can be obtained from railway vehicles of particularly old vehicle models, pressure information is not necessarily included, and depending on the railway vehicles of old vehicle models, only information related to running such as position and speed may be obtainable. When pressure information cannot be obtained in this way, it has been difficult to diagnose a sign of failure with the technology disclosed in Patent Document 1.

[0006] The present invention has been made in consideration of the above points, and proposes a failure prediction diagnosis device and a failure prediction diagnosis method capable of diagnosing a sign of failure even when pressure information cannot be obtained.

Means for Solving the Problems

[0007] In order to solve such problems, in the present invention, there is provided a failure prediction diagnostic device that is installed in a moving body and includes a data input unit that acquires operation information of a travel-related device that generates an output related to travel, operation information of an output use device that is installed in the moving body and uses the output related to the travel, and travel information related to the travel of the moving body. The failure prediction diagnostic device detects a failure omen of the travel-related device, calculates the operation time of the travel-related device from the operation information of the travel-related device, calculates an output consumption condition representing the operation history of the output use device during the operation time of the travel-related device from the operation information of the output use device and the travel information of the moving body, and outputs the operation time of the travel-related device and the output consumption condition as operation history data. An operation history data calculation unit, an operation history storage unit that accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area, a same condition data extraction unit that acquires from the operation history storage unit an operation history data group composed of a plurality of the operation history data that match the output consumption condition corresponding to the operation time of a certain travel-related device, a reference time calculation unit that averages the operation time of the travel-related device corresponding to the output consumption condition for the operation history data group and calculates a reference time during normal operation under the output consumption condition, and a failure prediction diagnosis unit that calculates an abnormality degree based on a result of comparing the operation time of a certain travel-related device with the reference time and diagnoses whether there is a failure omen in the travel-related device by performing statistical processing on the abnormality degree.

[0008] Further, in the present invention, an operation information of a travel-related device that is installed in a moving body and generates an output related to travel, an operation information of an output use device that is installed in the moving body and uses the output related to the travel, and a travel information related to the travel of the moving body are acquired, and a failure prediction diagnosis method for detecting a failure prediction of the travel-related device, wherein an operation history data calculation unit calculates an operation time of the travel-related device from the operation information of the travel-related device, and calculates an output consumption condition representing an operation history of the output use device during the operation time of the travel-related device from the operation information of the output use device and the travel information of the moving body, outputs the operation time of the travel-related device and the output consumption condition as operation history data, an operation history storage unit accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area, a same condition data extraction unit acquires, from the operation history storage unit, an operation history data group composed of a plurality of the operation history data that match the output consumption condition corresponding to an operation time of a certain travel-related device, a reference time calculation unit averages the operation time of the travel-related device corresponding to the output consumption condition for the operation history data group, and calculates a reference time during normal operation under the output consumption condition, and a failure prediction diagnosis unit calculates a degree of abnormality based on a result of comparing an operation time of a certain travel-related device with the reference time, and diagnoses whether there is a failure prediction in the travel-related device by performing statistical processing on the degree of abnormality.

Effect of the Invention

[0009] According to the present invention, it is possible to diagnose a failure prediction even when pressure information cannot be acquired.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Mode for Carrying Out the Invention

[0011] Hereinafter, based on the drawings, one embodiment of the present invention will be described in detail. (1) First Embodiment In the first embodiment, a failure prediction diagnosis device 100 for the moving body 20 will be described with reference to FIGS. 1 to 9. FIG. 1 is a block diagram mainly showing a configuration example of the moving body 20 and the failure prediction diagnosis device 100, and FIG. 2 is a block diagram mainly showing a configuration example of a railway vehicle 200 as an example of the moving body 20 and the failure prediction diagnosis device 100. The configuration example shown in FIG. 2 represents the configuration example shown in FIG. 1 more specifically.

[0012] As an example of the moving body 20, the railway vehicle 200 includes, as an example of the traveling-related equipment 21 that generates an output related to traveling, a pneumatic compressor 210 that generates compressed air used for traveling control of the railway vehicle 200, such as a pneumatic brake device, and an air tank that accumulates the compressed air (hereinafter, both may be collectively referred to as "pneumatic compressor 210" in some cases), output-using devices 22a and 22b as an example of output-using equipment that uses the compressed air, a traveling information acquisition unit 23, and a data output unit 260. Although not shown, the output-using devices 22a and 22b are provided with sensors for measuring pressure, and the sensors output pressure values.

[0013] The pneumatic compressor 210 outputs operation information indicating whether it is in an operating state or a stopped state to the data output unit 260.

[0014] The output-using devices 22a and 22b show an example of a plurality of output-using devices. For example, in a railway vehicle, they are any one of or a combination of a pneumatic brake device 220, a pneumatic spring device 230, and a pneumatic door device 240 that use compressed air. Note that the output-using devices 22a and 22b are not limited to the above-described devices. In addition, when there are other devices that use the compressed air generated by the pneumatic compressor 210, such devices may also be included in the output-using devices and used in this way. This is the same in other embodiments.

[0015] The air brake device 220 outputs, as operation information, the pressure value of the compressed air contained in the brake cylinder (hereinafter abbreviated as "BC pressure") to the data output unit 260. The air spring device 230 uses the pressure value of the compressed air contained in the air suspension (hereinafter abbreviated as "AS pressure") for vehicle body control. In the present embodiment, as shown in FIG. 2, it is assumed that, for example, the value of the AS pressure, which is an example of the operation information, is not output from the air spring device 230 as indicated by the "×" mark in the "operation information". The pneumatic door device 240 outputs, as operation information, the door state indicating whether the door is open or closed to the data output unit 260.

[0016] The traveling information acquisition unit 23 has a function of acquiring the traveling information of the moving body 20, and is, for example, a vehicle information control device 250 that is used for the aggregation and control of information generally acquired by each on-vehicle device in a railway vehicle.

[0017] The vehicle information control device 250 outputs, as traveling information, the information on the position and speed of the railway vehicle 200 calculated based on the wheel diameter and the number of rotations of the wheels, which is the information acquired from a speed generator (not shown) of the railway vehicle 200, to the data output unit 260. Details of the input / output and operations of each component will be described later.

[0018] The data output unit 260 takes as input the operation information of the air compressor 210, which is an example of the traveling-related device 21, the operation information of the air brake device 220, the air spring device 230, and the pneumatic door device 240, which are examples of the output use devices 22a (corresponding to the "output use device 1" shown in the figure) and 22b (corresponding to the "output use device X" shown in the figure), and the traveling information of the vehicle information control device 250, which is an example of the traveling information acquisition unit 23, and outputs these operation information and traveling information as operation data to the fault prediction diagnosis device 100.

[0019] The data output unit 260 outputs operation data (refer to FIG. 3 described later) including the operation information of the air compressor 210, the BC pressure, the door state, and the time-series information of the position and speed to the data input unit 110 of the fault prediction diagnosis device 100. As for the output method from the data output unit 260 to the data input unit 110, when the fault prediction diagnosis device 100 can be directly connected to the railway vehicle 200, it may be output using known wired communication means such as Ethernet communication. On the other hand, when the fault prediction diagnosis device 100 cannot be directly connected to the railway vehicle 200, as shown in FIG. 10 described later, it is installed as an external storage area (external storage area 300 in FIG. 10 described later) constructed on a server, cloud environment, etc. using a public communication network such as so-called LTE or 5G, and output to an operation data storage area 311 composed of a memory, a hard disk, an SSD (Solid State Drive), etc.

[0020] The fault prediction diagnosis device 100 includes a data input unit 110, an operation history data calculation unit 120, an operation history storage unit 130, a same-condition data extraction unit 140, a reference time calculation unit 150, and a fault prediction diagnosis unit 160, and is connected to a railway vehicle 200 as an example of the moving body 20 and a diagnosis result notification unit 500. The fault prediction diagnosis device 100 detects, for example, whether there is a fault prediction in the running-related equipment 21.

[0021] The data input unit 110 acquires the operation information of the running-related equipment 21 installed on the moving body 20 and generating an output related to running, the operation information of the output use devices 22a and 22b installed on the moving body 20 and using the output related to running, and the running information related to the running of the moving body 20 via the data output unit 260.

[0022] The data input unit 110 inputs operation data from the data output unit 260 of the railway vehicle 200 and outputs the operation data to the operation history data calculation unit 120. As described above, for the data input method of the data input unit 110, when the fault prediction diagnosis device 100 can be directly connected to the railway vehicle 200, it may be input by known wired communication. On the other hand, when the fault prediction diagnosis device 100 cannot be directly connected to the railway vehicle 200, as shown in FIG. 10 to be described later, the operation data stored in the operation data storage area 311 provided in the external storage area 300 may be input by reading it through wired communication or wireless communication.

[0023] The operation history data calculation unit 120 inputs operation data from the data input unit 110. The operation time (hereinafter also abbreviated as "operation time") during which the air compressor 210 was operating is extracted from the operation information of the air compressor 210 included in the operation data. Further, as conditions regarding the history of consumption of the output (for example, compressed air) generated by the air compressor 210 (hereinafter referred to as "output consumption conditions"), the integrated value of the fluctuation amount of the BC pressure (total BC pressure fluctuation amount) and the number of times the door changed from closed to open (hereinafter referred to as "door opening times") during the operation time of the air compressor 210, the position of the railway vehicle 200 when the air compressor 210 started operating (hereinafter referred to as "operation start position") and the speed of the railway vehicle 200 (hereinafter referred to as "operation start speed"), and the position of the railway vehicle 200 when the air compressor 210 ended operation (hereinafter referred to as "operation end position") and the speed of the railway vehicle 200 (hereinafter referred to as "operation end position") are calculated respectively. The operation history data calculation unit 120 outputs the operation time and the output consumption conditions together as operation history data to the operation history storage unit 130, the same condition data extraction unit 140, and the fault prediction diagnosis unit 160. Details of the operation of the operation history data calculation unit 120 will be described later.

[0024] In this embodiment, for example, in addition to the total variation amount of the BC pressure and the number of door openings, output consumption conditions based on the operation start position and the operation end position are used. The reason for setting the output consumption conditions as, for example, the total variation amount of the BC pressure, the number of door openings, the operation start position, and the operation end position is as follows. For example, the output consumption condition by the air spring device 230 is either a change in the spring load (number of passengers) or vibration during travel or the inclination of the railway vehicle 200. Therefore, if it is limited to during travel, it is considered to depend on the terrain where the railway vehicle 200 travels while the air compressor 210 is operating. The same condition data extraction unit 140 limits the data to the case where the operation start speed and the operation end speed are greater than 0. Thus, if the operation start position and the operation end position are the same condition, an output consumption condition where the air consumption amount is considered to be the same can be obtained.

[0025] The operation history data calculation unit 120 calculates the operation time of the travel-related device 21 from the operation information of the travel-related device 21, and calculates an output consumption condition representing the operation history of the output use devices 22a and 22b during the operation time of the travel-related device 21 from the operation information of the output use devices 22a and 22b and the travel information of the moving body 20. Then, the operation time of the travel-related device 21 and the output consumption condition are output as operation history data.

[0026] The operation history storage unit 130 accumulates the operation history data repeatedly output by the operation history data calculation unit 120 in a storage area such as a memory, a hard disk, or an SSD. The operation history storage unit 130 accumulates the operation history data acquired from the operation history data calculation unit 120 in the storage area. Further, when the output consumption condition is input from the same condition data extraction unit 140, the operation history storage unit 130 extracts all the operation history data that matches the output consumption condition, and outputs an operation history data group composed of the extracted multiple operation history data to the same condition data extraction unit 140. Details of the operation of the operation history storage unit 130 will be described later.

[0027] The same-condition data extraction unit 140 acquires, from the operation history storage unit 130, an operation history data group composed of a plurality of operation history data that match the output consumption conditions corresponding to the operation time of a certain operation-related device 21 (that is, the same conditions).

[0028] The same-condition data extraction unit 140 outputs the output consumption conditions of the operation history data acquired from the operation history data calculation unit 120 to the operation history storage unit 130, inputs an operation history data group that matches the output consumption conditions from the operation history storage unit 130, and outputs the operation history data group to the reference time calculation unit 150. Details of the operation of the same-condition data extraction unit 140 will be described later.

[0029] The reference time calculation unit 150 acquires an operation history data group from the same-condition data extraction unit 140, calculates a reference time, and outputs it to the fault prediction diagnosis unit 160. More specifically, the reference time calculation unit 150 averages the operation time of the operation-related device 21 corresponding to the output consumption conditions for the operation history data group, and calculates the reference time during normal operation under the output consumption conditions. Details of the operation of the reference time calculation unit 150 will be described later.

[0030] The fault prediction diagnosis unit 160 calculates the degree of abnormality based on the result of comparing the operation time of a certain operation-related device 21 with the reference time, and performs statistical processing on the degree of abnormality to diagnose whether there is a fault prediction for the operation-related device 21.

[0031] In this embodiment, when the operation-related device 21 is, for example, an air compressor 210 that generates compressed air and an air tank that stores compressed air, and the output use devices 22a, 22b are compressed air use devices that use the compressed air stored in the air tank, the fault prediction diagnosis unit 160 detects a fault prediction of at least one of the air compressor 210 and the air tank in the air system of the railway train.

[0032] In this embodiment, when the compressed air-using device is the air brake device 220, if information regarding the brake cylinder pressure is input from the data input unit 110 to the operation history data calculation unit 120 as the operation state of the air brake device 220, the operation history data calculation unit 120 calculates the output consumption condition using the integrated variation amount of the brake cylinder pressure (BC pressure) during the operation time of the air compressor 210, and the same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the integrated variation amount of the brake cylinder pressure is within a certain range as an operation history data group.

[0033] In this embodiment, when the compressed air-using device is the air spring device 230, if information regarding the air suspension pressure is input from the data input unit 110 to the operation history data calculation unit 120 as the operation state of the air spring device 230, the operation history data calculation unit 120 calculates the output consumption condition using the integrated variation amount of the air suspension pressure during the operation time of the air compressor 210, and the same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the integrated variation amount of the air suspension pressure is within a certain range as an operation history data group.

[0034] In this embodiment, when the compressed air-using device is the pneumatic door device 240, if information regarding the opening and closing of the door is input from the data input unit 110 to the operation history data calculation unit 120 as the operation state of the pneumatic door device 240, the operation history data calculation unit 120 calculates the output consumption condition using the number of times the door is opened and closed during the operation time of the air compressor 210, and the same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the number of opening and closing times is the same as a operation history data group.

[0035] In the present embodiment, when the compressed air-using device is, for example, the air spring device 230, the data input unit 110 acquires the position information of the railway vehicle 200 as the traveling information of the railway vehicle 200 as the mobile body 20 when the operating state of the air spring device 230 cannot be acquired or when it is difficult to use the operating state of the air spring device 230 for reasons such as low sensor accuracy. The operation history data calculation unit 120 calculates the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 from this position information, and calculates the output consumption condition based on the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 instead of, for example, the operation information of the air spring device 230. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 are within a certain range as an operation history data group.

[0036] In this embodiment, when the compressed air using device is, for example, the air brake device 220, if the data input unit 110 cannot obtain the operating state of the air brake device 220, or it is difficult to use the operating state of the air brake device 220 due to reasons such as low sensor accuracy, etc., for example, instead of the operating state of the air brake device 220, notch information regarding the operation state of the brake notch when the railway vehicle 200 as the moving body 20 is running and occupancy rate information regarding the occupancy rate of the railway vehicle 200, which are included in the running information of the railway vehicle 200, are obtained. The operation history data calculation unit 120 calculates, from the notch information and the occupancy rate information, for the brake notch used during the operation time of the air compressor 210, the predicted air consumption obtained by multiplying the pressure amount of the brake cylinder assumed at 0% occupancy rate for each used notch stage number, the activation time of the brake notch, and the occupancy rate, and calculates, as the output consumption condition, the value obtained by summing up the predicted air consumption during the operation time of the air compressor 210. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, as a group of operation history data, a plurality of operation history data in which the value of the predicted air consumption is within a certain range.

[0037] In this embodiment, when the compressed air using device is, for example, the pneumatic door device 240, if the data input unit 110 cannot obtain the operating state of the pneumatic door device 240, or it is difficult to use the operating state of the pneumatic door device 240 due to reasons such as low sensor accuracy, etc., for example, instead of the operating state of the pneumatic door device 240, inter-station information representing the position between stations during the running of the railway vehicle 200, which is included in the running information of the railway vehicle 200 as the moving body 20, is obtained. The operation history data calculation unit 120 calculates the output consumption condition based on the number of times the inter-station information changes during the operation time of the air compressor 210 from the inter-station information. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, as a group of operation history data, a plurality of operation history data in which the number of times of change of the inter-station information matches.

[0038] In this embodiment, the failure prediction diagnosis unit 160 may calculate the ratio of the error in the operating time of the travel-related device 21 to the above-described reference time as the abnormality degree.

[0039] In this case, in this embodiment, the failure prediction diagnosis unit 160 may previously set the maximum value of the abnormality degree during normal operation of the travel-related device 21 as a threshold value, and determine that there is a failure prediction when the abnormality degree exceeds the threshold value.

[0040] Also, in this embodiment, instead of setting the threshold value corresponding to the abnormality degree for each time (for example, once a day or each time) during normal operation of the travel-related device 21, the failure prediction diagnosis unit 160 calculates the average value of the abnormality degree for each day, and calculates the moving average for a predetermined number of days (for example, one week comprehensively considering weekday operation and weekend and holiday operation) that can comprehensively include differences in operation, and sets the maximum value of the comparison target value during the period when the travel-related device 21 is normal as the threshold value. When the comparison target value calculated from the newly acquired operation history data exceeds the threshold value, the failure prediction diagnosis unit 160 diagnoses that there is a failure prediction.

[0041] In this embodiment, when the failure prediction diagnosis unit 160 diagnoses that there is a failure prediction as a result of performing statistical processing on the abnormality degree, for example, in order to notify at least one of the operator of the moving body 20, the operation manager of the moving body 20, and the maintenance person of the moving body 20, the diagnosis result notification unit 500 is caused to notify that there is a failure prediction.

[0042] The diagnosis result notification unit 500 inputs the diagnosis result from the failure prediction diagnosis unit 160, and notifies the driver and the vehicle base that a failure prediction of the air compressor 210 has been detected by means of screen display or sound notification. Details of the diagnosis result notification method in the diagnosis result notification unit 500 will be described later.

[0043] FIG. 3 is a diagram showing an example of operation data input to the failure prediction diagnosis device 100. The operation data includes, for example, date, time, train speed, train position, operation information (ON / OFF) of the air compressor, BC pressure, and information regarding the door state.

[0044] The date and time indicate the date and time when the operation data was created. The train speed indicates the speed of the railway vehicle 200. The train position indicates the position of the railway vehicle 200. The operation information of the air compressor 210 indicates that "ON" means it is in operation and "OFF" means it is stopped. The BC pressure indicates the value [Pa] of the brake cylinder pressure. The door state indicates that "open" means the door is in the open state and "closed" means the door is in the closed state.

[0045] FIG. 4 is a diagram showing an example of operation history data used in the failure prediction diagnosis device 100. The operation history data includes, for example, date, operation time, operation start speed, operation end speed, operation start position, operation end position, total BC pressure variation amount, and information regarding the number of door openings.

[0046] The date indicates the date when the operation history data was created. The operation time indicates the time [seconds] during which the air compressor 210 was in operation. The operation start speed indicates the speed of the railway vehicle 200 when the air compressor 210 started operating. The operation end speed indicates the speed of the railway vehicle 200 when the air compressor 210 ended operation. The operation start speed and the operation end speed are calculated from the date, time, and train speed of the operation data in FIG. 3 described above.

[0047] The operation start position indicates the position of the railway vehicle 200 when the air compressor 210 started operating. The operation end position indicates the position of the railway vehicle 200 when the air compressor 210 ended operation. The operation start position and the operation end position are calculated from the date, time, and train position of the operation data in FIG. 3 described above.

[0048] The total BC pressure variation amount indicates the total value of the variation amounts of the BC pressure of the brake cylinder within the above operating time. The number of door openings indicates the number of times the door was in the open state within the above operating time.

[0049] The failure prediction diagnosis device 100 according to this embodiment has the above configuration, and the following operation example of the failure prediction diagnosis device 100 will be described. Here, first, the outline of the failure prediction diagnosis method of the failure prediction diagnosis device 100 will be described. The failure prediction diagnosis method is a method for obtaining the operation information of the traveling-related device 21 that is installed in the moving body 20 and generates an output related to traveling, the operation information of the output use devices 22a and 22b that are installed in the moving body 20 and use the output related to traveling, and the traveling information related to the traveling of the moving body 20, and detecting a failure prediction of the traveling-related device 21. The operation history data calculation unit 120 calculates the operation time of the traveling-related device 21 from the operation information of the traveling-related device 21, calculates the output consumption condition representing the operation history of the output use devices 22a and 22b during the operation time of the traveling-related device 21 from the operation information of the output use devices 22a and 22b and the traveling information of the moving body 20, and outputs the operation time and the output consumption condition of the traveling-related device 21 as operation history data. The operation history storage unit 130 accumulates the operation history data repeatedly output by the operation history data calculation unit 120 in the storage area. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, an operation history data group composed of a plurality of operation history data that match the output consumption condition corresponding to the operation time of a certain traveling-related device. The reference time calculation unit 150 averages the operation time of the traveling-related device 21 corresponding to the output consumption condition for the operation history data group and calculates the reference time during normal operation under the output consumption condition. The failure prediction diagnosis unit 160 calculates the degree of abnormality based on the result of comparing the operation time of a certain traveling-related device with the reference time, and diagnoses whether there is a failure prediction in the traveling-related device 21 by performing statistical processing on the degree of abnormality.

[0050] FIG. 5 is a flowchart showing an example of the procedure of the operation history data calculation process. The operation history data calculation process is executed by the operation history data calculation unit 120.

[0051] In step S1201, the operation history data calculation unit 120 acquires operation data from the data input unit 110 and executes step S1202. In step S1202, the operation history data calculation unit 120 determines whether the operation information of the air compressor 210 in the operation data has changed from OFF to ON. If the operation history data calculation unit 120 determines Yes, it executes step S1203; if it determines No, it executes step S1204.

[0052] In step S1203, the operation history data calculation unit 120 sets the time at which the operation data is created as the operation start time, the train speed at that time as the operation start speed, and the train position at that time as the operation start position in the operation data, and then executes step S1204.

[0053] In step S1204, the operation history data calculation unit 120 determines whether the operation information of the air compressor 210 in the operation data has changed from ON to OFF. If it determines Yes, it executes step S1205; if it determines No, it executes step S1209.

[0054] In step S1205, the operation history data calculation unit 120 sets the time at which the operation data is created as the operation end time, the train speed at that time as the operation end speed, and the train position at that time as the operation end position in the operation data, and then executes step S1206.

[0055] In step S1206, the operation history data calculation unit 120 calculates the operation time using the following formula, and then executes step S1207. Operation time = Operation stop time - Operation start time

[0056] In step S1207, the operation history data calculation unit 120 converts the operation time, operation start speed, operation end speed, operation start position, operation end position, and total BC pressure fluctuation amount into the format of operation data (see Figure 4), and then executes step S1208.

[0057] In step S1208, the operation history data calculation unit 120 outputs the operation history data to the operation history storage unit 130, the same condition data extraction unit 140, and the failure omen diagnosis unit 160, and ends the process.

[0058] In step S1209, the operation history data calculation unit 120 determines whether the operation information of the air compressor 210 is ON and whether the current BC pressure is greater than the BC pressure of one cycle ago. If the operation history data calculation unit 120 determines Yes, it executes step S1210; if it determines No, it executes step S1211.

[0059] In step S1210, the operation history data calculation unit 120 updates the total BC pressure variation amount using the following formula and executes step S1211. Total BC pressure variation amount = Total BC pressure variation amount + (Current BC pressure - BC pressure of one cycle ago)

[0060] In step S1211, the operation history data calculation unit 120 determines whether the operation information is "ON" and whether the door state has changed from "closed" to "open". If the operation history data calculation unit 120 determines Yes, it executes step S1212 and ends the process. In step S1212, the operation history data calculation unit 120 increments the door opening count by 1 and ends the process.

[0061] Figure 6 is a flowchart showing an example of the procedure for operation history storage processing. The operation history storage processing is executed by the operation history storage unit 130. In step S1301, the operation history storage unit 130 determines whether it has acquired the operation history data from the operation history data calculation unit 120. If the operation history storage unit 130 determines Yes, it executes step S1302; if it determines No, it executes step S1303.

[0062] In step S1302, the operation history storage unit 130 saves the operation history data acquired from the storage area and executes step S1303. Although not shown in the figure, this step S1302 is repeatedly executed each time operation history data is received, whereby a plurality of operation history data is accumulated in the operation history storage unit 130.

[0063] In step S1303, the operation history storage unit 130 determines whether it has acquired the output consumption conditions from the same-condition data extraction unit 140. If Yes, it proceeds to step S1304; if No, it executes step S1306.

[0064] Steps S1304 to S1305 are loop processes, and the operation history storage unit 130 searches for all the operation history data saved in the storage area one by one. In step S1304, the operation history storage unit 130 determines whether the operation history data being referred to satisfies all of the following specific conditions (conditions 1 to 4). If Yes, it executes step S1305; if No, it executes the next step of the loop process. Note that the following position threshold and pressure threshold will be described later.

[0065] Condition 1: Is the operation start position of the operation history data being referred to within the error range of the position threshold from the operation start position of the output consumption conditions? Condition 2: Is the operation end position of the operation history data being referred to within the error range of the position threshold from the operation end position of the output consumption conditions? Condition 3: Is the total BC pressure variation amount of the operation history data being referred to within the error range of the pressure threshold from the total BC pressure variation amount of the output consumption conditions? Condition 4: Does the number of door openings of the operation history data being referred to match the number of door openings of the output consumption conditions?

[0066] That is, the above-mentioned specific conditions are as follows. (Condition 1): |Operation start position of output consumption conditions - Operation start position| < Position threshold (Condition 2): |Operation end position of output consumption conditions - Operation end position| < Position threshold (Condition 3): |Total change in BC pressure of output consumption condition - Total change in BC pressure| < Pressure threshold (Condition 4): Number of door openings in output consumption condition = Number of door openings

[0067] In step S1305, the operation history storage unit 130 stores the operation history data being referred to in a packet for data transmission. When the search is completed for all the operation history data for which the next step of the loop process is to be executed, the loop process is terminated and step S1306 is executed.

[0068] In step S1306, the operation history storage unit 130 outputs all the operation history data stored in the packet for data transmission to the same condition data extraction unit 140 and ends the process.

[0069] The above-mentioned position threshold and pressure threshold will be described. First, the position threshold is a threshold for determining whether the moving body 20 is at the same position when the air compressor 210 starts and ends its operation. Therefore, in order to indicate that at least a part of the moving body 20 is at the same position, it is set to a value equal to or less than the size of the moving body 20. For example, when the moving body 20 is a railway vehicle 200 as in the present embodiment, any value equal to or less than the train length of the railway vehicle 200 is set as the position threshold.

[0070] On the other hand, the pressure threshold is a threshold for determining that the total change in BC pressure is within the range of the value variation caused by the sensor error at the time of BC pressure acquisition. Therefore, as an example, a value obtained by multiplying the value of the sensor error of the BC pressure by the number of BC pressure acquisitions and doubling the result is used. The reason for doubling is that when taking the difference between the data with the error on the side where the pressure value increases and the data with the error on the side where the pressure value decreases because the differences in pressure values are added together, an error up to twice the sensor error may occur at most.

[0071] FIG. 7 is a flowchart showing an example of the procedure of the same condition data extraction process. The same condition data extraction process is executed by the same condition data extraction unit 140.

[0072] In step S1401, the same-condition data extraction unit 140 acquires operation history data from the operation history data calculation unit 120 and executes step S1402. In step S1402, the same-condition data extraction unit 140 determines whether both the operation start speed and the operation end speed of the acquired operation history data are greater than 0. If the same-condition data extraction unit 140 determines Yes, it executes step S1403; otherwise, it ends the process.

[0073] In step S1403, the same-condition data extraction unit 140 extracts the values of the operation start position, operation end position, total BC pressure fluctuation amount, and number of door openings of the acquired operation history data, sets them as output consumption conditions, and executes step S1404.

[0074] In step S1404, the same-condition data extraction unit 140 outputs the output consumption conditions to the operation history storage unit 130 and executes step S1405. In step S1405, the same-condition data extraction unit 140 determines whether it has acquired an operation history data group from the operation history storage unit 130. If the same-condition data extraction unit 140 determines Yes, it executes step S1406; otherwise, it ends the process.

[0075] In step S1406, the same-condition data extraction unit 140 reads the operation time of all the acquired operation history data, stores it in a packet for transmission, and executes step S1407. In step S1407, the same-condition data extraction unit 140 outputs all the operation times stored in the transmission packet to the reference time calculation unit 150 and ends the process.

[0076] Figure 8 is a flowchart showing an example of the procedure of the reference time calculation process. The reference time calculation process is executed by the reference time calculation unit 150.

[0077] In step S1501, the reference time calculation unit 150 determines whether it has acquired an operation time data group from the same-condition data extraction unit 140. If the reference time calculation unit 150 determines Yes, it executes step S1502; otherwise, it ends the process.

[0078] In step S1502, the reference time calculation unit 150 calculates the average value of the acquired operation time group, sets it as the reference time, and executes step S1503. In step S1503, the reference time calculation unit 150 outputs the reference time to the fault prediction diagnosis unit 160 and ends the process.

[0079] FIG. 9 is a flowchart showing an example of the procedure of the fault prediction process. The fault prediction process is executed by the fault prediction diagnosis unit 160.

[0080] In step S1601, the fault prediction diagnosis unit 160 acquires the operation history data from the operation history data calculation unit 120 and acquires the reference time from the reference time calculation unit 150, and executes step S1602.

[0081] In step S1602, the fault prediction diagnosis unit 160 calculates the abnormality degree using the following formula from the operation time of the operation history data and the reference time, and executes step S1603. Abnormality degree = |Operation time - Reference time| ÷ Reference time

[0082] In step S1603, the fault prediction diagnosis unit 160 performs a fault prediction diagnosis process and executes step S1604. The details of the fault prediction diagnosis process will be described later. In step S1604, the fault prediction diagnosis unit 160 determines whether a fault prediction has been output in the fault prediction diagnosis process. If the fault prediction diagnosis unit 160 is Yes, it executes step S1605, while if it is No, it ends the process. In step S1506, the fault prediction diagnosis unit 160 outputs the diagnosis result to the diagnosis result notification unit 500 and ends the process.

[0083] Here, the fault prediction diagnosis process will be described. The fault prediction diagnosis process is a process of performing statistical processing or the like on the abnormality degree calculated by the fault prediction diagnosis unit 160 in step S1603 described above to diagnose whether there is a fault prediction in the air compressor 210.

[0084] Specifically, the fault prediction diagnosis unit 160 acquires in advance the maximum value of the abnormality degree when the device is normal from past data, uses this value as a threshold, and determines that there is a fault prediction when the newly acquired abnormality degree shows a value equal to or greater than the threshold multiple times.

[0085] In addition, the fault prediction diagnosis unit 160 may calculate the average value of the abnormality degree per day instead of the data for each time, and determine that there is a fault prediction when the value shows a value greater than the maximum value of the average value per day during normal times. In this method, considering the differences in daily operations, for example, a moving average is taken for the number of days (business days) that can comprehensively include all differences in operations, and it is determined that there is a fault prediction when the value is greater than the maximum value of the moving average of the abnormality degree shown during normal times. This is a method of determining that there is a fault prediction when the newly acquired amplitude or variance of the abnormality degree over a certain period shows a large value compared to the amplitude or variance of the abnormality degree over a certain period during normal times, rather than the maximum value of the abnormality degree during normal times. Furthermore, in this embodiment, in addition, a method of calculating the value of the standard deviation σ of the abnormality degree during normal times and determining that there is an abnormality when a value deviates from the value of 3σ, which is generally considered an outlier statistically, is acceptable as long as it is a method that can be determined as an outlier statistically by comparing with the abnormality degree or the transition of the abnormality degree during normal times. This also applies to other embodiments.

[0086] Next, the method of notifying the diagnosis result by the diagnosis result notification unit 500 will be described. The diagnosis result notification unit 500 notifies the driver or the vehicle base that the fault prediction of the air compressor 210 has been detected in the fault prediction diagnosis device 100 by means of screen display or sound buzzer.

[0087] When mounted on the railway vehicle 200, for example, the fault prediction diagnosis device 100 outputs the diagnosis result to the vehicle information control device 250. In the vehicle information control device 250, a screen display indicating that a fault prediction has been detected may be performed on a display on the driver's cab (not shown), or a screen display indicating that a fault prediction has been detected may be performed on a display on the driver's cab (not shown) from the fault prediction diagnosis device 100. Further, when the fault prediction diagnosis device 100 has a function of transmitting the aggregated vehicle data of the vehicle information control device to a ground system such as an operation command or an inspection area using a public wireless communication network or the like, the diagnosis result may be included in the vehicle data and transmitted to the ground system, and the diagnosis result may be notified through a screen or the like in the ground system.

[0088] Furthermore, when the fault prediction diagnosis device 100 is mounted on a ground system such as a vehicle base, the diagnosis result may be displayed on a screen or the like on the ground system. This also applies to other embodiments described later.

[0089] Next, a modification of the fault prediction diagnosis device 100 according to the first embodiment will be described. In the first embodiment, when the AS pressure in the air spring device 230 cannot be obtained, for example, a method of substituting by using the positions of the railway vehicle 200 at the start and stop of operation was described. In a modification of the first embodiment, for example, when the AS pressure can be obtained, consider the case where the BC pressure of the air brake device 220 cannot be obtained, and the case where the door state of the pneumatic door device 240 cannot be obtained. Here, the embodiments in these three cases will be described respectively.

[0090] Here, when the AS pressure can be obtained, the operation history data calculation unit 120 calculates the output consumption condition from the total value of the AS pressure fluctuations (AS pressure fluctuation total value) that fluctuated during the operation of the air compressor 210, similar to the BC pressure described above, instead of the operation start position and the operation end position. In this case, further, the determination in the same condition data extraction unit 140 that the operation start speed and the operation end speed are greater than 0 is omitted.

[0091] On the other hand, when the BC pressure cannot be obtained, in the air brake device 220, if it is known which strength of the brake has been applied for how long, the consumption amount of compressed air in the air brake device 220 can be estimated. Here, generally, the strength of the brake in a railway vehicle can be calculated from the brake notch. However, depending on the railway vehicle, in order to keep the deceleration constant for each notch, the force (the output amount of compressed air) pressing the brake pads output for each notch may be changed according to the change in the car body weight (number of passengers). From the above, the operation history data calculation unit 120 can substitute the output consumption conditions of the BC pressure by acquiring the notch information and the boarding rate information as running information from the vehicle information control device 250 and calculating the following respective values. · The brake notch used during the operation of the air compressor 210 · The usage time for each brake notch · The boarding rate during the operation of the air compressor 210

[0092] (When the door state cannot be obtained) When the door information cannot be obtained, if it is known how many times the railway vehicle 200 has stopped at stations during the operation of the air compressor 210, the air consumption amount in the pneumatic door device 240 can be estimated. Therefore, by acquiring the inter-station information as running information from the vehicle information control device 250 and calculating the following values, the output consumption conditions of the pneumatic door device 240 can be substituted. · The number of times the inter-station information has changed during the operation of the air compressor 210

[0093] In the present embodiment, the operation history storage unit 130 is not limited to the configuration described in FIG. 1. FIG. 10 is a block diagram showing a configuration example of a failure prediction diagnosis device 100a as a modification of the first embodiment. Since the failure prediction diagnosis device 100a according to the modification of the first embodiment has substantially the same configuration and operation as the above-described failure prediction diagnosis device 100, only the differences will be described below.

[0094] In the modification of the first embodiment, it is different from the above-described first embodiment in that an external storage area 300 is provided.

[0095] In the fault prediction diagnosis device 100 according to the first embodiment, the operation data was directly output from the data output unit 260 to the data input unit 110. However, in the fault prediction diagnosis device 100a according to the modified example of the first embodiment, the operation data output from the data output unit 260 is temporarily stored in the operation data storage area 311 of the external storage area 300, and the data input unit 110 of the fault prediction diagnosis device 100a indirectly acquires the operation history data. In the fault prediction diagnosis device 100a having such a configuration, it is possible to connect to an external storage area 300 constructed on an external server or in a cloud environment or the like by wired or wireless communication or the like, and store data in the operation history storage unit 130 provided in the storage area. By doing so, the processing load of the fault prediction diagnosis device 100a can be reduced.

[0096] Also, in the modified example of the first embodiment, an operation history storage unit 130 is provided in the external storage area 300.

[0097] The failure prediction diagnosis device 100 according to this embodiment is installed in a moving body and includes operation information of a travel-related device 21 that generates an output related to travel, operation information of output use devices 22a and 22b that are installed in the moving body 20 and use the output related to travel, and a data input unit 110 that acquires travel information related to the travel of the moving body 20. The failure prediction diagnosis device 100 is for detecting a failure prediction of the travel-related device 21. From the operation information of the travel-related device 21, the operation time of the travel-related device 21 is calculated, and from the operation information of the output use devices 22a and 22b and the travel information of the moving body 20, an output consumption condition representing the operation history of the output use devices 22a and 22b during the operation time of the travel-related device 21 is calculated. An operation history data calculation unit 120 that outputs the operation time and the output consumption condition of the travel-related device 21 as operation history data; an operation history storage unit 130 that accumulates the operation history data repeatedly output by the operation history data calculation unit 120 in a storage area; a same condition data extraction unit 140 that acquires, from the operation history storage unit 130, an operation history data group composed of a plurality of operation history data that match the output consumption condition corresponding to the operation time of a certain travel-related device; a reference time calculation unit 150 that averages the operation time of the travel-related device 21 corresponding to the output consumption condition for the operation history data group and calculates a reference time during normal operation under the output consumption condition; and a failure prediction diagnosis unit 160 that calculates a degree of abnormality based on the result of comparing the operation time of a certain travel-related device with the reference time, and diagnoses whether there is a failure prediction in the travel-related device by performing statistical processing on the degree of abnormality.

[0098] The fault prediction diagnosis method according to this embodiment is a fault prediction diagnosis method that is installed in the moving body 20, acquires the operation information of the travel-related device 21 that generates an output related to travel, the operation information of the output use devices 22a and 22b that are installed in the moving body 20 and use the output related to travel, and the travel information related to the travel of the moving body 20, and detects a fault prediction of the travel-related device 21. The operation history data calculation unit 120 calculates the operation time of the travel-related device 21 from the operation information of the travel-related device 21, and calculates the output consumption condition representing the operation history of the output use devices 22a and 22b during the operation time of the travel-related device 21 from the operation information of the output use devices 22a and 22b and the travel information of the moving body 20, and outputs the operation time and the output consumption condition of the travel-related device 21 as operation history data. The operation history storage unit 130 accumulates the operation history data repeatedly output by the operation history data calculation unit 120 in a storage area. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, an operation history data group composed of a plurality of operation history data that match the output consumption condition corresponding to the operation time of a certain travel-related device. The reference time calculation unit 150 averages the operation time of the travel-related device 21 corresponding to the output consumption condition for the operation history data group, and calculates the reference time during normal operation under the output consumption condition. The fault prediction diagnosis unit 160 calculates the degree of abnormality based on the result of comparing the operation time of a certain travel-related device with the reference time, and diagnoses whether there is a fault prediction in the travel-related device 21 by performing statistical processing on the degree of abnormality.

[0099] In this way, even when the operating states of the output use devices 22a and 22b cannot be directly obtained, by using the travel information of the moving body 20 and the like, it is possible to diagnose the fault prediction of the travel-related device 21 of the moving body 20. Therefore, according to this embodiment, considering the difference in information that can be obtained depending on the vehicle type of the railway vehicle 200 as an example of the moving body 20, even when the pressure information of the air compressor 210 cannot be obtained, by enabling fault prediction diagnosis from travel-related information, it is possible to perform fault prediction diagnosis regardless of the difference in available data.

[0100] In this embodiment, the travel-related device 21 includes an air compressor 210 that generates compressed air and It is an air tank that stores compressed air. When the output use devices 22a and 22b are compressed air use devices that use the compressed air stored in the air tank, the failure prediction diagnosis unit 160 detects a failure prediction of at least one of the air compressor 210 and the air tank in the air system of the railway train. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, it is possible to diagnose the failure prediction of the air compressor 210 and the like.

[0101] In the present embodiment, when the compressed air use device is the air brake device 220, when information regarding the brake cylinder pressure is input from the data input unit 110 as the operating state of the air brake device 220 to the operating history data calculation unit 120, the integrated change amount of the BC pressure during the operating time of the air compressor 210 is used to calculate the output consumption condition. The same condition data extraction unit 140 acquires, from the operating history storage unit 130, a plurality of operating history data in which the integrated change amount of the brake cylinder pressure is within a certain range as the operating history data group. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, it is possible to diagnose the failure prediction of the air compressor 210 from the operating state of the air brake device 220.

[0102] In the present embodiment, when the compressed air use device is the air spring device 230, when information regarding the air suspension pressure is input from the data input unit 110 as the operating state of the air spring device 230 to the operating history data calculation unit 120, the integrated change amount of the air suspension pressure during the operating time of the air compressor 210 is used to calculate the output consumption condition. The same condition data extraction unit 140 acquires, from the operating history storage unit 130, a plurality of operating history data in which the integrated change amount of the air suspension pressure is within a certain range as the operating history data group. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, it is possible to diagnose the failure prediction of the air compressor 210 from the operating state of the air spring device 230.

[0103] In this embodiment, when the compressed air-using device is the pneumatic door device 240, if information regarding the opening and closing of the door is input from the data input unit 110 to the operation history data calculation unit 120 as the operation state of the pneumatic door device 240, the operation history data calculation unit 120 calculates the output consumption condition using the number of door openings and closings during the operation time of the air compressor 210. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data having the same number of openings and closings as the operation history data group. By doing so, even when the pressure information of the air compressor 210 cannot be acquired, it is possible to diagnose a sign of failure of the air compressor 210 from the operation state of the pneumatic door device 240.

[0104] In this embodiment, when the compressed air-using device is, for example, the air spring device 230, if the operation state of the air spring device 230 cannot be acquired by the data input unit 110, or if it is difficult to use the operation state of the air spring device 230 for reasons such as low sensor accuracy, the data input unit 110 acquires the position information of the railway vehicle 200 as the traveling information of the railway vehicle 200 as the moving body 20. The operation history data calculation unit 120 calculates the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 from this position information, and calculates the output consumption condition based on the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 instead of, for example, the operation information of the air spring device 230. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210 are within a certain range as the operation history data group. By doing so, even when the pressure information of the air compressor 210 cannot be acquired, it is possible to diagnose a sign of failure of the air compressor 210 from the position of the railway vehicle 200 at the start of operation of the air compressor 210 and the position of the railway vehicle 200 at the end of operation of the air compressor 210.

[0105] In this embodiment, when the compressed air-using device is, for example, the air brake device 220, the data input unit 110 cannot acquire the operating state of the air brake device 220, or it is difficult to use the operating state of the air brake device 220 for reasons such as low sensor accuracy. For example, instead of the operating state of the air brake device 220, the notch information regarding the operation state of the brake notch when the railway vehicle 200 is running and the occupancy rate information regarding the occupancy rate of the railway vehicle 200, which are included in the running information of the railway vehicle 200 as the moving body 20, are acquired. The operation history data calculation unit 120 calculates, from the notch information and the occupancy rate information, for the brake notch used during the operation time of the air compressor 210, the predicted air consumption obtained by multiplying the pressure amount of the brake cylinder assumed at 0% occupancy rate for each used notch stage by the input time of the brake notch and the occupancy rate, and calculates, as the output consumption condition, the value obtained by summing up the predicted air consumption during the operation time of the air compressor 210. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data as an operation history data group in which the value of the predicted air consumption is within a certain range. By doing so, even when the pressure information of the air compressor 210 cannot be acquired, it is possible to diagnose the failure omen of the air compressor 210 from the running information of the railway vehicle 200.

[0106] In this embodiment, when the compressed air-using device is, for example, the pneumatic door device 240, if the data input unit 110 cannot obtain the operating state of the pneumatic door device 240, or if it is difficult to use the operating state of the pneumatic door device 240 due to reasons such as low sensor accuracy, for example, instead of the operating state of the pneumatic door device 240, the inter-station information indicating the position between stations during the running of the railway vehicle 200, which is included in the running information of the railway vehicle 200 as the moving body 20, is acquired. The operation history data calculation unit 120 calculates the output consumption condition based on the number of times the inter-station information has changed during the operation time of the air compressor 210 from the inter-station information. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the number of changes in the inter-station information matches as an operation history data group. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, the diagnosis of the sign of failure of the air compressor 210 can be performed from the running information of the railway vehicle 200.

[0107] In this embodiment, the sign-of-failure diagnosis unit 160 calculates the ratio of the error in the operation time of the running-related device 21 with respect to the above-described reference time as the abnormality degree. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, the diagnosis of the sign of failure of the air compressor 210 can be performed from the abnormal value.

[0108] In this embodiment, the sign-of-failure diagnosis unit 160 previously sets the maximum value of the abnormality degree during the normal operation of the running-related device 21 as a threshold value, and determines that there is a sign of failure when the abnormality degree exceeds the threshold value. By doing so, even when the pressure information of the air compressor 210 cannot be obtained, the diagnosis of the sign of failure of the air compressor 210 can be performed according to whether the abnormal value exceeds the threshold value.

[0109] In this embodiment, instead of setting the threshold value corresponding to the degree of abnormality for each occurrence (e.g., once a day or each time) when the running-related device 21 is normal, the fault prediction diagnosis unit 160 calculates the average value of the degree of abnormality per day and calculates a moving average of a predetermined number of days (e.g., one week comprehensively considering weekday operations and weekend and holiday operations) that can comprehensively include differences in operation. The calculated value is used as a comparison target value, and the maximum value of the comparison target value during the period when the running-related device 21 is normal is set as the threshold value. When the comparison target value calculated from the newly acquired operation history data exceeds the threshold value, the fault prediction diagnosis unit 160 diagnoses that there is a fault prediction. In this way, even when the pressure information of the air compressor 210 cannot be obtained, it is possible to diagnose the fault prediction of the air compressor 210 according to whether the comparison target value exceeds the threshold value.

[0110] In this embodiment, as a result of performing statistical processing on the degree of abnormality, when the fault prediction diagnosis unit 160 diagnoses that there is a fault prediction, for example, in order to notify at least one of the operator of the moving body 20, the operation manager of the moving body 20, and the maintenance personnel of the moving body 20, the diagnosis result notification unit 500 is made to notify that there is a fault prediction. In this way, since it is possible to recognize from the outside that there is a fault prediction, a prompt response can be made.

[0111] (2) Second Embodiment In this embodiment, the following will be described with reference to FIGS. 11 to 17. Since the fault prediction diagnosis device 100b according to the second embodiment has substantially the same configuration and operation as the fault prediction diagnosis device 100 according to the first embodiment, the following description will focus on the differences. Also in this embodiment, the moving body 20 is assumed to be the railway vehicle 200, and the configuration of the railway vehicle 200 is also the same as that of the railway vehicle 200 in the first embodiment.

[0112] FIG. 11 is a block diagram showing a configuration example of a fault prediction diagnosis device 100b for a railway vehicle 200 according to the second embodiment.

[0113] In the second embodiment, unlike the first embodiment, the fault prediction diagnosis device 100b receives operation management information from the outside and diagnoses the fault prediction of the traveling-related device 21. In this embodiment, the operation time calculated from the operating state of the traveling-related device 21, the operating states of the output use devices 22a and 22b, the traveling state of the moving body, and the output consumption condition calculated from the operation management information obtained from the operation management device 400 match (i.e., are the same condition). By comparing with the reference time calculated using a group of operation history data composed of a plurality of operation history data of the past operation time, and calculating the degree of abnormality, it becomes possible to diagnose the fault prediction of the traveling-related device 21 without using pressure information.

[0114] In the second embodiment, the operation management information output unit 410 outputs operation management information including information on weather, temperature, and humidity illustrated in FIG. 12 to the data input unit 110 of the fault prediction diagnosis device 100.

[0115] Note that, as for the output method to the data input unit 110, similar to the communication between the railway vehicle and the fault prediction diagnosis device 100 in the first embodiment, when the fault prediction diagnosis device 100b can be directly connected to the operation management device 400, it may be input by wired communication. When the fault prediction diagnosis device 100b cannot be directly connected to the operation management device 400, as shown in FIG. 17 described later, the operation management information stored in the operation management information storage area 312 provided in the external storage area 300 is read into the operation management information storage area 312 of the external storage area by wired communication or wireless communication, and may be input in this way.

[0116] The data input unit 110 obtains, in addition to the input of operation data, operation management information including the train diagram information and weather information of the railway vehicle 200 from the data output unit 260 of the railway vehicle 200 as an example of the moving body 20 and from the operation management information output unit 410 of the operation management device 400, and outputs this operation management information to the operation history data calculation unit 120. Note that the communication method between the railway vehicle 200 and the operation management device 400 is as described above.

[0117] In addition, in the present embodiment, the operation history data calculation unit 120 calculates output consumption conditions based on the operating state of compressed air using equipment (for example, any one or any combination of the air brake device 220, the air spring device 230, and the pneumatic door device 240), the train diagram information of the railway vehicle 200, and the weather information.

[0118] In this case, in the present embodiment, the operation management information includes, as weather information, for example, information regarding temperature, humidity, and weather. The operation history data calculation unit 120 calculates output consumption conditions from the information regarding temperature, humidity, and weather when calculating the operation time of the air compressor 210. The same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data as an operation history data group in which the temperature and humidity are respectively within a certain range and the weather is the same.

[0119] That is, the operation history data calculation unit 120 extracts, from the operation management information, information regarding temperature, humidity, and weather when the air compressor 210 starts operating as output consumption conditions. As shown in FIG. 13, the operation history data calculation unit 120 outputs, as operation history data, the output consumption conditions obtained by adding weather information including, for example, temperature, humidity, and weather to the operation time, to the operation history storage unit 130, the same condition data extraction unit 140, and the failure prediction diagnosis unit 160. The reason for adding weather information (for example, temperature, humidity, and weather) from the operation management information to the output consumption conditions is that since the air compressor 210 compresses the air flowing in from the outside while the railway vehicle 200 is running, it is considered that if the weather, temperature, and humidity change, the conditions of the inflowing air change and the operation time also changes.

[0120] FIG. 14 is a flowchart showing an example of the procedure of the operation history data calculation process according to the second embodiment. The operation history data calculation procedure is executed by the operation history data calculation unit 120. Hereinafter, only the differences from the first embodiment will be described.

[0121] In step S1201a, the operation history data calculation unit 120 acquires operation data and operation management information from the data input unit 110 and executes step S1202. Note that steps S1202 to S1205 are the same as those in the first embodiment.

[0122] In step S1213, the operation history data calculation unit 120 extracts the weather, temperature, and humidity at the operation end time from the operation management information and executes step S1206. Step S1206 is the same as that in the first embodiment. In step S1207, the operation history data calculation unit 120 converts the operation time, operation start speed, operation end speed, operation start position, operation end position, total BC pressure fluctuation amount, weather, temperature, and humidity into the format of operation history data (see FIG. 13) and executes step S1208. The operations from step S1208 to step S1212 are the same as those in the first embodiment.

[0123] FIG. 15 is a flowchart showing an example of the procedure of the operation history storage process according to the second embodiment. The operation history storage process is executed by the operation history storage unit 130. Note that only the differences from the first embodiment will be described below.

[0124] The operations from step S1301 to step S1303 are the same as those in the first embodiment. In step S1304a, the operation history storage unit 130 determines whether the operation history data being referred to satisfies all of the following specific conditions (conditions 1 to 7). If Yes, step S1305 is executed; if No, the next step of the loop process is executed.

[0125] Condition 1: Is the operation start position of the operation history data being referred to within the error of the position threshold from the operation start position of the output consumption condition? Condition 2: Is the operation end position of the operation history data being referred to within the error of the position threshold from the operation end position of the output consumption condition? Condition 3: Is the total BC pressure fluctuation amount of the operation history data being referred to within the error of the pressure threshold from the total BC pressure fluctuation amount of the output consumption condition? Condition 4: Whether the number of door openings in the operation history data in the reference matches the number of door openings in the output consumption condition? Condition 5: Whether the weather in the operation history data in the reference matches the weather in the output consumption condition? Condition 6: Whether the temperature in the operation history data in the reference is within the error range of the temperature threshold from the temperature in the output consumption condition? Condition 7: Whether the humidity in the operation history data in the reference is within the error range of the humidity threshold from the humidity in the output consumption condition?

[0126] Note that the definitions of the position threshold and the pressure threshold are the same as those in the first embodiment. Details of the temperature threshold and the humidity threshold will be described later.

[0127] That is, the above-mentioned specific conditions are as follows. Condition 1: |Operating start position in output consumption condition - Operating start position| < Position threshold Condition 2: |Operating end position in output consumption condition - Operating end position| < Position threshold Condition 3: |Total BC pressure variation amount in output consumption condition - Total BC pressure variation amount| < Pressure threshold Condition 4: Number of door openings in output consumption condition = Number of door openings Condition 5: Weather in output consumption condition = Weather Condition 6: |Temperature in output consumption condition - Temperature| < Temperature threshold Condition 7: |Humidity in output consumption condition - Humidity| < Humidity threshold

[0128] The operations from step S1305 to step S1306 are the same as those in the first embodiment.

[0129] Here, the temperature threshold will be explained. As shown by the so-called Boyle - Charles' law, when the temperature changes and the volume is constant, the pressure changes. Therefore, even with the same air inflow amount, the amount of compressed air changes, and the operating time of the air compressor 210 changes. Accordingly, from the amount of compressed air generated per unit time determined by the equipment performance of the air compressor 210 and the resolution of the operating time (for example, in seconds or milliseconds), using Boyle - Charles' law and the like, a value of the temperature change amount that is less than or equal to the resolution of the operating time is calculated and set as the temperature threshold.

[0130] Next, the humidity threshold will be described. The operating time of the air compressor 210 changes due to the reduction in the volume of the air flowing into the air compressor by the amount of water vapor calculated from the humidity. Therefore, from the amount of compressed air generated per unit time determined by the equipment performance of the air compressor 210 and the resolution of the operating time (for example, in seconds or milliseconds), a value of the humidity change amount that is equal to or less than the resolution of the operating time is calculated, and this value is set as the humidity threshold.

[0131] FIG. 16 is a flowchart showing an example of the procedure of the same-condition data extraction process according to the second embodiment. The same-condition data extraction process is executed by the same-condition data extraction unit 140.

[0132] The operations from step S1401 to step S1402 are the same as those in the first embodiment. In step S1403, the same-condition data extraction unit 140 extracts values such as the operation start position, operation end position, total BC pressure fluctuation amount, number of door openings, weather, temperature, and humidity from the acquired operation history data, sets them as output consumption conditions, and executes step S1404. Note that the operations from step S1404 to step S1407 are the same as those in the first embodiment.

[0133] FIG. 17 is a block diagram showing a configuration example of a failure prediction diagnostic device 100c or the like according to a modification of the second embodiment. Since the failure prediction diagnostic device 100c according to the modification of the second embodiment has substantially the same configuration and operation as the failure prediction diagnostic device 100b according to the second embodiment, the differences will be described below.

[0134] The failure prediction diagnostic device 100c stores operation management information in the operation management information storage area 312 installed in the external storage area 300. Thereby, even when the failure prediction diagnostic device 100c cannot be directly connected to the operation management device 400, the operation management information stored in the operation management information storage area 312 of the external storage area 300 can be input by reading it into the operation management information storage area 312 of the external storage area through wired communication or wireless communication. Since other configurations are the same as those of the failure prediction diagnostic device 100b according to the above-described second embodiment, the description thereof is omitted.

[0135] According to the present embodiment as described above, it is possible to diagnose a failure prediction by using operation management information.

[0136] Particularly in the present embodiment, the data input unit 110 acquires operation management information including train diagram information and weather information of the railway vehicle 200 as an example of the moving body 20, and the operation history data calculation unit 120 calculates output consumption conditions from the operating state of the compressed air using equipment, the train diagram information, and the weather information. In this way, even when the pressure information of the air compressor 210 cannot be acquired, it is possible to diagnose a failure prediction of the air compressor 210 from the operating state of the compressed air using equipment, the train diagram information, and the weather information.

[0137] Furthermore, in the present embodiment, the operation management information includes information regarding temperature, humidity, and weather as weather information, and the operation history data calculation unit 120 calculates output consumption conditions from the information regarding temperature, humidity, and weather when calculating the operation time of the air compressor 210, and the same condition data extraction unit 140 acquires, from the operation history storage unit 130, a plurality of operation history data in which the temperature and humidity are respectively within a certain range and the weather is the same as operation history data groups. In this way, even when the pressure information of the air compressor 210 cannot be acquired, it is possible to diagnose a failure prediction of the air compressor 210.

[0138] Also, the forms described above include at least the following technical matters. <Technical matter 1> An operation information of a running-related device that is installed in a moving body and generates an output related to running, an operation information of an output-using device that is installed in the moving body and uses the output related to the running, and a data input unit that acquires running information related to the running of the moving body, and a failure prediction diagnosis device that detects a failure omen of the running-related device, which calculates an operation time of the running-related device from the operation information of the running-related device, and calculates an output consumption condition representing an operation history of the output-using device during the operation time of the running-related device from the operation information of the output-using device and the running information of the moving body, and an operation history data calculation unit that outputs the operation time of the running-related device and the output consumption condition as operation history data, an operation history storage unit that accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area, a same-condition data extraction unit that acquires an operation history data group composed of a plurality of the operation history data that match the output consumption condition corresponding to the operation time of a certain running-related device from the operation history storage unit, a reference time calculation unit that averages the operation time of the running-related device corresponding to the output consumption condition for the operation history data group and calculates a reference time at normal times under the output consumption condition, and a failure prediction diagnosis unit that calculates an abnormality degree based on a result of comparing an operation time of a certain running-related device with the reference time and diagnoses whether there is a failure omen in the running-related device by performing statistical processing on the abnormality degree. <Technical matter 2> In the failure prediction diagnosis device described in the above Technical matter 1, the running-related device is an air compressor that generates compressed air and an air tank that stores the compressed air, the output-using device is a compressed air-using device that uses the compressed air stored in the air tank, and the failure prediction diagnosis unit detects an omen of at least one of the air compressor and the air tank in the air system of a railway train. <Technical matter 3> In the failure prediction diagnosis device described in Technical Matter 2 above, the compressed air using device is an air brake device. When information regarding the brake cylinder pressure is input from the data input unit as the operating state of the air brake device to the operation history data calculation unit, the output consumption condition is calculated using the integrated variation amount of the brake cylinder pressure during the operation time of the air compressor. The same condition data extraction unit acquires, as the operation history data group, a plurality of the operation history data in which the integrated variation amount of the brake cylinder pressure is within a certain range from the operation history storage unit. <Technical Matter 4> In the failure prediction diagnosis device described in Technical Matter 2 above, the compressed air using device is an air spring device. When information regarding the air suspension pressure is input from the data input unit as the operating state of the air spring device to the operation history data calculation unit, the output consumption condition is calculated using the integrated variation amount of the air suspension pressure during the operation time of the air compressor. The same condition data extraction unit acquires, as the operation history data group, a plurality of the operation history data in which the integrated variation amount of the air suspension pressure is within a certain range from the operation history storage unit. <Technical Matter 5> In the failure prediction diagnosis device described in Technical Matter 2 above, the compressed air using device is an air door device. When information regarding the opening and closing of the door is input from the data input unit as the operating state of the air door device to the operation history data calculation unit, the output consumption condition is calculated using the number of times the door opens and closes during the operation time of the air compressor. The same condition data extraction unit acquires, as the operation history data group, a plurality of the operation history data in which the number of times of opening and closing is the same from the operation history storage unit. <Technical Matter 6> In the failure prediction diagnosis device described in Technical Matter 2 above, the compressed air using device is a pneumatic spring device, and when the data input unit cannot acquire the operating state of the pneumatic spring device or it is difficult to use the operating state of the pneumatic spring device, the data input unit acquires the position information of the railway vehicle as the running information of the railway vehicle as the moving body. The operating history data calculation unit calculates the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor from the position information, calculates the output consumption condition based on the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor, and the same condition data extraction unit acquires, from the operation history storage unit, as the operation history data group, a plurality of the operation history data in which the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor are within a certain range. <Technical Matter 7> In the failure prediction diagnosis device described in Technical Matter 2 above, the compressed air using device is an air brake device, and when the data input unit cannot acquire the operating state of the air brake device or it is difficult to use the operating state of the air brake device, the data input unit acquires the notch information regarding the operation state of the brake notch during running of the railway vehicle and the passenger occupancy rate information regarding the passenger occupancy rate of the railway vehicle, which are included in the running information of the railway vehicle as the moving body. The operating history data calculation unit calculates, from the notch information and the passenger occupancy rate information, for the brake notch used during the operation time of the air compressor, the predicted air consumption amount obtained by multiplying the pressure amount of the brake cylinder assumed at 0% passenger occupancy rate for each used notch stage number, the input time of the brake notch, and the passenger occupancy rate, calculates the value obtained by summing up the predicted air consumption amounts during the operation time of the air compressor as the output consumption condition, and the same condition data extraction unit acquires, from the operation history storage unit, as the operation history data group, a plurality of the operation history data in which the values of the predicted air consumption amounts are within a certain range. <Technical Matter 8> In the fault prediction diagnosis device described in Technical Matter 2 above, when the compressed air using device is a pneumatic door device and the data input unit cannot acquire the operating state of the pneumatic door device or it is difficult to use the operating state of the pneumatic door device for reasons such as low sensor accuracy, the inter-station information indicating the position between stations during the running of the railway vehicle, which is included in the running information of the railway vehicle as the moving body, is acquired. The operating history data calculation unit calculates the output consumption condition based on the number of times the inter-station information has changed during the operating time of the air compressor from the inter-station information. The same condition data extraction unit acquires, as the operating history data group, a plurality of the operating history data in which the number of changes in the inter-station information matches from the operating history storage unit. <Technical Matter 9> In the fault prediction diagnosis device described in Technical Matter 2 above, the data input unit acquires operation management information including the train diagram information and weather information of the railway vehicle as the moving body, and the operating history data calculation unit calculates the output consumption condition from the operating state of the compressed air using device, the train diagram information, and the weather information. <Technical Matter 10> In the fault prediction diagnosis device described in Technical Matter 9 above, the operation management information includes information regarding temperature, humidity, and weather as the weather information. The operating history data calculation unit calculates the output consumption condition from the information regarding temperature, humidity, and weather at the time of calculating the operating time of the air compressor. The same condition data extraction unit acquires, as the operating history data group, a plurality of the operating history data in which the temperature and the humidity are respectively within a certain range and the weather matches from the operating history storage unit. <Technical Matter 11> In the fault prediction diagnosis device described in any one of Technical Matters 1 to 10 above, the fault prediction diagnosis unit calculates the ratio of the error of the operating time of the running-related device with respect to the reference time as the abnormality degree. <Technical Matter 12> In the fault prediction diagnosis device described in Technical Matter 11 above, the fault prediction diagnosis unit previously sets the maximum value of the abnormality degree during the normal operation of the driving-related equipment as a threshold value, and determines that there is a fault prediction when the abnormality degree exceeds the threshold value. <Technical Matter 13> In the fault prediction diagnosis device described in Technical Matter 12 above, instead of setting the threshold value corresponding to the abnormality degree each time during the normal operation of the driving-related equipment, the fault prediction diagnosis unit calculates the daily average value of the abnormality degree, calculates a moving average for a predetermined number of days that can comprehensively include differences in operation as a comparison target value, sets the maximum value of the comparison target value during the period when the driving-related equipment is normal as the threshold value, and diagnoses that there is a fault prediction when the comparison target value calculated from newly acquired operation history data exceeds the threshold value. <Technical Matter 14> In the fault prediction diagnosis device described in any one of Technical Matters 1 to 13 above, when the fault prediction diagnosis unit diagnoses that there is a fault prediction as a result of performing the statistical processing on the abnormality degree, the fault prediction diagnosis unit causes the diagnosis result notification unit to notify that there is a fault prediction. <Technical Matter 15> An operation information of a travel-related device installed in a moving body and generating an output related to travel, an operation information of an output-using device installed in the moving body and using the output related to the travel, and travel information related to the travel of the moving body are acquired, and a failure prediction diagnosis method for detecting a failure sign of the travel-related device, wherein an operation history data calculation unit calculates an operation time of the travel-related device from the operation information of the travel-related device, calculates an output consumption condition representing an operation history of the output-using device at the operation time of the travel-related device from the operation information of the output-using device and the travel information of the moving body, and outputs the operation time of the travel-related device and the output consumption condition as operation history data, an operation history storage unit accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area, a same condition data extraction unit acquires, from the operation history storage unit, an operation history data group composed of a plurality of the operation history data that match the output consumption condition corresponding to the operation time of a certain travel-related device, a reference time calculation unit averages the operation time of the travel-related device corresponding to the output consumption condition for the operation history data group, and calculates a reference time in a normal state under the output consumption condition, and a failure prediction diagnosis unit calculates a degree of abnormality based on a result of comparing the operation time of a certain travel-related device with the reference time, and diagnoses whether there is a failure sign in the travel-related device by performing statistical processing on the degree of abnormality.

[0139] Note that the present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail for easy understanding of the present invention, and are not necessarily limited to those having all the configurations described. Other aspects conceivable within the scope of the technical idea of the present invention are also included in the scope of the present invention. Also, a part of the configuration of one embodiment can be replaced with the configuration of another embodiment, and the configuration of another embodiment can be added to the configuration of one embodiment. Further, for a part of the configuration of each embodiment, addition, deletion, or replacement with other configurations is possible. Also, each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware, for example, by designing a part or all of them with an integrated circuit. Further, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program for realizing each function. Information such as a program, table, file, etc. for realizing each function can be placed in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC (Integrated Circuit) card, SD (Secure Digital) card, or DVD (Digital Versatile Disc).

Industrial Applicability

[0140] The present invention can be applied to a failure prediction diagnosis device related to a technique for diagnosing whether there is a failure prediction for equipment mounted on a moving body such as a railway vehicle, for example.

Explanation of Signs

[0141] 20……Moving body, 21……Running related equipment, 22a……Output use device 1, 22b……Output use device, 23……Running information acquisition unit, 100, 100a, 100b, 100c……Fault omen diagnosis device, 110……Data input unit, 120……Operation history data calculation unit, 130……Operation history storage unit, 140……Same condition data extraction unit, 150……Reference time calculation unit, 160……Fault omen diagnosis unit, 200……Railway vehicle, 210……Air compressor, 220……Air brake device, 230……Air spring device, 240……Pneumatic door device, 250……Vehicle information control device, 260……Data output unit, 300……External storage area, 311……Operation data storage area, 312……Operation management information storage area, 400……Operation management device, 410……Operation management information output unit

Claims

1. A failure prediction diagnostic device that is installed in a moving body and includes a data input unit that acquires operation information of a travel-related device that generates output related to travel, operation information of an output use device that is installed in the moving body and uses the output related to the travel, and travel information related to the travel of the moving body, and detects a failure sign of the travel-related device, calculates the operating time of the travel-related device from the operation information of the travel-related device, calculates an output consumption condition representing the operation history of the output use device during the operating time of the travel-related device from the operation information of the output use device and the travel information of the moving body, and outputs the operating time of the travel-related device and the output consumption condition as operation history data; an operation history data calculation unit; an operation history storage unit that accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area; a same-condition data extraction unit that acquires, from the operation history storage unit, an operation history data group composed of a plurality of pieces of the operation history data that match the output consumption condition corresponding to the operating time of a certain travel-related device; a reference time calculation unit that calculates the reference time during normal operation under the output consumption condition by averaging the operating times of the travel-related devices corresponding to the output consumption condition for the operation history data group; a failure prediction diagnosis unit that calculates an abnormality degree based on a result of comparing the operating time of a certain travel-related device with the reference time, and diagnoses whether there is a failure sign in the travel-related device by performing statistical processing on the abnormality degree; A failure prediction diagnostic device characterized by comprising the above.

2. The travel-related device is an air compressor that generates compressed air and an air tank that stores the compressed air, The output use device is a compressed air use device that uses the compressed air stored in the air tank, The failure prediction diagnosis unit is detecting a sign of at least one of the air compressor and the air tank in the air system of a railway train The failure prediction diagnostic device according to claim 1, characterized by the above.

3. The compressed air use device is an air brake device, The operation history data calculation unit is When information regarding the brake cylinder pressure is input from the data input unit as the operation state of the air brake device, the output consumption condition is calculated using the integrated variation amount of the brake cylinder pressure during the operating time of the air compressor, The same-condition data extraction unit is from the operation history storage unit, As the operation history data group, obtain a plurality of the operation history data in which the integrated fluctuation amount of the brake cylinder pressure is within a certain range. The fault prediction diagnosis device according to claim 2, characterized in that.

4. The compressed air using device is an air spring device, When information regarding the air suspension pressure as the operating state of the air spring device is input from the data input unit to the operating history data calculation unit, calculate the output consumption condition using the integrated fluctuation amount of the air suspension pressure during the operating time of the air compressor, The same condition data extraction unit obtains, from the operating history storage unit, As the operation history data group, obtain a plurality of the operation history data in which the integrated fluctuation amount of the air suspension pressure is within a certain range. The fault prediction diagnosis device according to claim 2, characterized in that.

5. The compressed air using device is a pneumatic door device, When information regarding the opening and closing of the door as the operating state of the pneumatic door device is input from the data input unit to the operating history data calculation unit, calculate the output consumption condition using the number of times the door is opened and closed during the operating time of the air compressor, The same condition data extraction unit obtains, from the operating history storage unit, As the operation history data group, obtain a plurality of the operation history data in which the number of opening and closing times is the same. The fault prediction diagnosis device according to claim 2, characterized in that.

6. The compressed air using device is an air spring device, When the operating state of the air spring device cannot be obtained or it is difficult to use the operating state of the air spring device, the data input unit obtains the position information of the railway vehicle as the running information of the railway vehicle as the moving body, From the position information, calculate the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor, and calculate the output consumption condition based on the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor to the operating history data calculation unit, The same condition data extraction unit obtains, from the operating history storage unit, As the operation history data group, obtain a plurality of the operation history data in which the position of the railway vehicle at the start of operation of the air compressor and the position of the railway vehicle at the end of operation of the air compressor are within a certain range. The fault prediction diagnosis device according to claim 2, characterized in that.

7. ​ The compressed air using device is an air brake device, when the data input unit cannot obtain the operating state of the air brake device or it is difficult to use the operating state of the air brake device, the data input unit acquires notch information regarding the operation state of the brake notch when the railway vehicle as the moving body is running and occupancy rate information regarding the occupancy rate of the railway vehicle, which are included in the running information of the railway vehicle. The operation history data calculation unit calculates, from the notch information and the occupancy rate information, for each notch stage used regarding the brake notch used during the operation time of the air compressor, a predicted air consumption amount obtained by multiplying the pressure amount of the brake cylinder assumed at 0% occupancy rate, the input time of the brake notch, and the occupancy rate, and calculates, as the output consumption condition, a value obtained by summing the predicted air consumption amounts during the operation time of the air compressor. The same condition data extraction unit acquires, from the operation history storage unit, a plurality of the operation history data as the operation history data group in which the values of the predicted air consumption amounts are within a certain range. The failure omen diagnosis device according to claim 2, characterized in that.

8. The compressed air using device is a pneumatic door device, when the data input unit cannot obtain the operating state of the pneumatic door device or it is difficult to use the operating state of the pneumatic door device due to reasons such as low sensor accuracy, the data input unit acquires station interval information indicating the position between stations while the railway vehicle as the moving body is running, which is included in the running information of the railway vehicle. The operation history data calculation unit calculates the output consumption condition based on the number of times the station interval information has changed during the operation time of the air compressor from the station interval information. The same condition data extraction unit acquires, from the operation history storage unit, a plurality of the operation history data as the operation history data group in which the number of changes in the station interval information matches. The failure omen diagnosis device according to claim 2, characterized in that.

9. The data input unit acquires operation management information including train diagram information and weather information of the railway vehicle as the moving body, The operation history data calculation unit calculates the output consumption condition from the operating state of the compressed air using device, the train diagram information, and the weather information. The failure omen diagnosis device according to claim 2, characterized in that.

10. The operation management information includes, as the weather information, information regarding temperature, humidity, and weather. The operation history data calculation unit calculates the output consumption condition from the information on the temperature, humidity, and weather when calculating the operation time of the air compressor, The same condition data extraction unit extracts from the operation history storage unit as the operation history data group, a plurality of the operation history data in which the temperature and the humidity are respectively within a certain range and the weather is the same The fault prediction diagnosis device according to claim 9, characterized in that.

11. The fault prediction diagnosis unit calculates the ratio of the error of the operation time of the travel-related device with respect to the reference time as the abnormality degree The fault prediction diagnosis device according to any one of claims 1 to 10, characterized in that.

12. The fault prediction diagnosis unit predetermines the maximum value of the abnormality degree during normal operation of the travel-related device as a threshold value, and when the abnormality degree exceeds the threshold value, determines that there is a fault prediction The fault prediction diagnosis device according to claim 11, characterized in that.

13. The fault prediction diagnosis unit instead of setting the threshold value corresponding to the abnormality degree for each time during normal operation of the travel-related device, calculates the daily average value of the abnormality degree, and calculates a moving average for a predetermined number of days that can comprehensively include differences in operation, and sets the maximum value of the comparison target value during the period when the travel-related device is normal as the threshold value, and when the comparison target value calculated from newly acquired operation history data exceeds the threshold value, diagnoses that there is a fault prediction The fault prediction diagnosis device according to claim 12, characterized in that.

14. The fault prediction diagnosis unit when diagnosing that there is a fault prediction as a result of performing the statistical process on the abnormality degree, causes the diagnosis result notification unit to notify that there is a fault prediction The fault prediction diagnosis device according to claim 1, characterized in that.

15. An operation information of a travel-related device installed in a moving body and generating an output related to travel, an operation information of an output use device installed in the moving body and using the output related to the travel, and a travel information related to the travel of the moving body are acquired, and a fault prediction diagnosis method for detecting a fault prediction of the travel-related device, The operation history data calculation unit calculates the operation time of the travel-related device from the operation information of the travel-related device, calculates an output consumption condition representing the operation history of the output use device during the operation time of the travel-related device from the operation information of the output use device and the travel information of the mobile body, and outputs the operation time of the travel-related device and the output consumption condition as operation history data. The operation history storage unit accumulates the operation history data repeatedly output by the operation history data calculation unit in a storage area. The same condition data extraction unit acquires, from the operation history storage unit, an operation history data group composed of a plurality of pieces of operation history data that match the output consumption condition corresponding to the operation time of a certain travel-related device. The reference time calculation unit averages the operation time of the travel-related device corresponding to the output consumption condition for the operation history data group, and calculates a reference time during normal operation under the output consumption condition. The fault prediction diagnosis unit calculates a degree of abnormality based on the result of comparing the operation time of a certain travel-related device with the reference time, and diagnoses whether there is a fault prediction in the travel-related device by performing statistical processing on the degree of abnormality. A fault prediction diagnosis method characterized by the above.

Images