GB2491291A - System for supporting determination of abnormality of moving object - Google Patents
System for supporting determination of abnormality of moving object Download PDFInfo
- Publication number
- GB2491291A GB2491291A GB1214932.4A GB201214932A GB2491291A GB 2491291 A GB2491291 A GB 2491291A GB 201214932 A GB201214932 A GB 201214932A GB 2491291 A GB2491291 A GB 2491291A
- Authority
- GB
- United Kingdom
- Prior art keywords
- abnormality
- failure
- state data
- moving object
- determination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005856 abnormality Effects 0.000 title abstract description 199
- 238000003745 diagnosis Methods 0.000 abstract description 36
- 238000004458 analytical method Methods 0.000 abstract description 31
- 230000002159 abnormal effect Effects 0.000 abstract description 24
- 238000001514 detection method Methods 0.000 abstract description 24
- 238000004891 communication Methods 0.000 abstract description 18
- 238000005259 measurement Methods 0.000 abstract description 13
- 238000012806 monitoring device Methods 0.000 abstract description 13
- 238000000034 method Methods 0.000 description 35
- 230000008569 process Effects 0.000 description 29
- 238000009825 accumulation Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000013500 data storage Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/50—Trackside diagnosis or maintenance, e.g. software upgrades
- B61L27/57—Trackside diagnosis or maintenance, e.g. software upgrades for vehicles or trains, e.g. trackside supervision of train conditions
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
- Traffic Control Systems (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
Provided is a system for supporting the determination of abnormality of a moving object, which improves the operation rate by appropriately predicting the possibility of abnormality from a failure generated when the moving object experiences a failure and by reducing erroneous detection. A moving object (101) of the system for supporting the determination of abnormality of a moving object comprises: various types of measurement devices (103); a status monitoring device (104) for detecting whether a failure has occurred by using status data from the measurement devices; and a communication device (107) for transmitting failure information to a ground system (102) and receiving an abnormality determination result from the ground system. The ground system (102) comprises: a communication device (114) for transmitting and receiving data to and from the moving object; a storage unit (111) for storing past failure information; an abnormality determination unit (112) for analyzing and determining whether or not a past failure is abnormal; an abnormality analysis database (113) for storing the past failure information in association with abnormality diagnosis results; and an abnormality occurrence prediction unit (115) for contrasting the failure information from the time of occurrence of the failure in question and the abnormality analysis database (113), and outputting an abnormality determination result.
Description
Description
Title of the Invention: SYSTEM FOR SUPPORTING
DETERMINATION OF ABNORMALITY OF MOVING OBJECT
Technical Field
[0001] The present invention relates to a system for supporting determination of an abnormality of a moving object including a state monitoring device that monitors states of various apparatuses provided in the moving object, and more particularly to a system for supporting determination of an abnormality of a moving object using a ground system.
Background Art
[0002] A widely known system for detecting an abnormality of a moving object is a system for acguiring state data of a moving object, and analyzing the obtained data at the time of failure occurrence to detect an abnormality.
The term "failure" herein refers to Ta state of an apparatus different from a normal state". The term "abnormality" herein refers to "a state that is undesirable as a system due to a failure of an apparatus, and requires recovery by stopping the apparatus, or the like." [0003] For example, Patent Literature 1 provides a system in which a sensor for detecting a state of a moving object is mounted to the moving object, a sensor output is stored in the moving object, a ground system has an abnormality detection condition extracting function of analyzing the sensor output to extract an abnormality detection condition, the abnormality detection condition is input to the moving object, the sensor output and the abnormality detection condition are compared on the moving object to detect an abnormality of the moving object. Thus, even an abnormality that has not been assumed in production of the moving object can be easily and quickly detected in the moving object, without a high-performance device such as the abnormality detection condition extracting function being provided on the moving object.
[0004] Management of vehicle status has been proposed in which vehicle status values collected by a vehicle are stored and controlled for each small section, vehicle status values for a plurality of vehicles for each small section are used to compile and analyze status of the vehicles, thus, without providing fixed sensors on multiple points on a route, the same advantage as in the case where vehicle status values are comprehensively observed by the sensors can be obtained (Patent Literature 2) . In this proposal, for data acquisition space, a characteristic evaluation value for evaluating whether a characteristic of a stored value follows a past characteristic for a section rather than for one value is calculated to absorb an error in calculation of a distance. When a plurality of values are acquired for the same small section, a compiling process is performed, an estimation process is performed for a small section with a loss of a vaiue to acquire a characteristic evaluation value, an attribution probability indicating a probability of the characteristic evaluation value being appropriate is calculated, a specificity determination unit compares the attribution probability with a threshold and issues an alert when the attribution probability is equai to or smaller than the threshold, thereby performing precise management of vehicle status at low cost.
Citation List Patent Literature [0005] Patent Literature 1: Japanese Patent Laid-Open Publication No. 2004-306880 Patent Literature 2: Japanese Patent Laid-Open Publication No. 2009-78764
Summary of Invention
Technical Problems [0006] In the system described above, state data of a plurality of apparatuses in the same vehicle is compared to separate the data into a position factor component and an apparatus factor component to detect an abnormality.
The data only in the same vehicle is used, and data of other vehicles is not used. Also, in the method of storing and controlling the vehicle status values for each small section, vehicle state data is classified for each small section, abnormality warning determination is made by comparison with past information on the section.
Thus, the past information is used, but communication with the ground side is highly likely to be successively made, and transmitting the vehicle status values to the ground side by radio communication causes burdens of transmission capacity, cost, or reliability, and in the case of accumulating raw data, an enormous accumulation capacity is required.
[0007] In the system, if state data (= sensor output) at the time of a failure does not include a sign of an abnormality, abnormality deteotion oannot be determined.
On the contrary, even if there is some change in state data before the time of failure occurrence and an abnormality detection condition is met, the state data may then recover, and the determination of the abnormality detection made based on condition determination may be erroneous detection. In any case, future state data is not obtained on the moving object at the time of failure occurrence, and it is difficult to provide state data sufficient for predicting future state data on the moving object. As such, even if a minor failure occurs, a crew of the moving object cannot alone determine an abnormality at that time, and often stops the moving object. Thus, erroneous detection causes an unnecessary stop of operation of the moving object due to abnormality determination, thereby reducing an operation rate. In particular, when the moving object is a train, service guality may be reduced.
[0008] Thus, it is considered that if a ground system can provide an advanced support by referring to a past case or the like at the time of failure occurrence, accuracy of abnormality determination whether a failure leads to an abnormality can be increased, and there is a problem to be solved in establishing such advanced support.
For the above problem, the present invention has an object to provide advanced support for properly predicting a possibility of a failure leading to an abnormality by transmitting state data of a moving object to a ground side at the time of failure occurrence and referring to a past case or the like on the ground side, and to reduce probability of erroneous detection that stops the moving object and increase an operation rate of the moving object.
Solution to Problems [00091 To achieve the above object, in a system for supporting determination of an abnormality of a moving object according to the present invention, a moving object includes a measurement device that measures states of various apparatuses provided in the moving object! a state monitoring device that detects failure occurrence using state data of the various apparatuses measured by the measurement device, and a communication device that transmits a type of a failure that has occurred and state data before and after the time of the failure occurrence to a ground system, and receives an abnormality determination result from the ground system. The ground system includes a communication device that transmits and receives data to and from the moving object, an accumulation unit that accumulates a type and state data of a past failure of the moving object, and an abnormality diagnosis unit that analyzes the state data of the past failure and outputs an abnormality diagnosis result of determination whether the failure is abnormal or not. The ground system further includes an abnormality analysis database that stores the type of the past failure, the abnormality diagnosis result, and the state data in association with each other, and an abnormality occurrence prediction unit that compares the type of the failure at the time of failure occurrence and the state data before and after the time of the failure occurrence transmitted from the moving object with the type of the past failure and the state data stored in the abnormality analysis database to output the abnormality determination result, and the communication device of the ground system transmits the abnormality determination result to the moving object.
[0010] According to the system for supporting determination of an abnormality of a moving object of the present invention, when a failure occurs in the moving object, the ground system returns, to the moving object, the abnormality determination result obtained by comparing the failure information (the type and the state data of the failure) with past failure information to determine a failure. Thus, the moving object can be supported by the ground system in determination on presence or absence of an abnormality, thereby allowing abnormality determination with high accuracy. Since the past information provided in the ground system is acguired off-line (at the time of a test of the moving object or the like), there is no need to provide high-cost eguipment for allowing transmission of failure information by constant communication. For the failure information acguired by the ground system, a cause of the failure can be previously analyzed automatically or manually and accumulated in the abnormality analysis database. The abnormality occurrence prediction unit searches past information in the abnormality analysis database based on a type of a failure that newly occurs in the moving object and last state data, compares the failure with a search result and outputs an abnormality determination result.
[0011] In the system for supporting determination of an abnormality of a moving object, the abnormality occurrence prediction unit can extract, from the abnormality analysis database, state data of a failure of the same type as the failure at the time of failure occurrence transmitted from the moving object, calculate similarity between the state data at the time of failure occurrence and the state data extracted from the abnormality analysis database, and output an abnormality diagnosis result of state data with high similarity or a total value thereof as an abnormality determination result. Specifically, the ground system can perform a matching process between the last failure information of the failure that occurs in the moving object and the past information extracted from the abnormality analysis database to calculate similarity of the state data, and output an abnormality diagnosis result of the failure that has occurred based on the similarity. For example, when the failure matches a minor failure, the ground system can return operation continuation determination.
The abnormality occurrence prediction unit can output reliability based on a total value of abnormality diagnosis results of state data of past failures with high similarity, and the number of oases of the extracted same type of failure in the abnormality analysis database.
[0012] In the system for supporting determination of an abnormality of a moving object, when the abnormality diagnosis result shows that similarity to either of two different tendencies is high or similarity to both of the two different tendencies is low, the high similarity can be used as an index of high reliability for each tendency corresponding to the similarity, and the low similarity can be used as an index of low reliability. When the abnormality diagnosis result shows that there is no substantial difference in similarity between the two different tendencies, an appearance frequency obtained based on state data of a past failure for each tendency can be used as an index of reliability.
[0013] In the system for supporting determination of an abnormality of a moving object, the abnormality occurrence prediction unit may include a monitor that presents the abnormality determination result, and transmit a final abnormality determination result determined based on the abnormality determination result presented by the monitor via an input interface to the moving object. The moving object may include a state data storage unit that accumulates a type of a failure and state data, and output the state data stored in the state data storage unit to the ground system using a data transmission medium different from the communication device, and the ground system may accumulate types of failures and state data of a plurality of moving objects, and output an abnormality diagnosis result based on the accumulated types of failures and the state data.
Advantageous Effects of Invention [0014] According to the system for supporting determination of an abnormality of a moving object of the present invention, the type of the failure that has occurred in the moving object and the state data before and after the time of failure occurrence do not need to be successively transmitted to the ground side by radio communication, but a regular time such as a time of a regular check is selected, and by that time, the state data of the plurality of apparatuses accumulated in the moving object may be extracted and transmitted to the ground system.
Measurement and storage of data performed in the moving object may be performed by setting a cycle at a levei allowing detailed analysis to be performed in the ground system. Also, for a result of abnormality determination made in the ground system, whether the failure occurrence leads to an abnormality or not is determined with reference to a past case, thereby allowing abnormality determination with high accuracy. Since the reference to the past case does not depend on information according to a movement section in the present invention, information on other movement sections is also referred to, thereby allowing support with higher accuracy from data with a large reference count. At the time of failure occurrence in the moving object, the moving object can be supported in abnormality determination by the ground system, and an unnecessary stop can be avoided at the time of failure occurrence that will not lead to an abnormality, thereby increasing an operation rate of the moving object. In particular, when the moving object is a train, railway operation service guality is increased.
Brief Description of Drawings
[0015] [FIG. 1] FIG. 1 is a system configuration diagram showing an embodiment of a system for supporting determination of an abnormality of a moving object according to the present invention.
[FIG. 2] FIG. 2 shows a data structure of an abnormality analysis database in the system for supporting determination of an abnormality of a moving object shown in FIG. 1.
[FIG. 3] FIG. 3 is a flowchart showing an example of a process flow of an abnormality occurrence prediction unit in a ground system of the system for supporting determination of an abnormality of a moving object shown in FIG. 1.
[FIG. 4] FIG. 4 shows a determination example of the abnormality occurrence prediction unit in the ground system of the system for supporting determination of an abnormality of a moving object shown in FIG. 1.
[FIG. 5] FIG. 5 shows an example of a determination support screen of the abnormality occurrence prediction unit in the ground system of the system for supporting determination of an abnormality of a moving object shown in FIG. 1.
[FIG. 61 FIG. 6 shows an example of a screen of a state monitoring device in the moving object of the system for supporting determination of an abnormality of a moving object shown in FIG. 1.
Description of Embodiment
[0016] An embodiment of a system for supporting determination of an abnormality of a moving object according to the present invention will be described with reference to the drawings. A system using a train as a moving object will be described below.
Embodiment 1 [0017] FIG. 1 is a system configuration diagram showing a system for supporting determination of an abnormality of a moving object according to the present invention. In FIG. 1, the system for supporting determination of an abnormality of a moving object 100 includes a moving object, that is, a train 101, and a ground system 102.
The train 101 includes a measurement device 103 that measures states of various apparatuses provided in the train 101, a state monitoring device 104 that monitors the states of the various apparatuses measured by the measurement device 103, a state data storage unit 105 that stores data of the states monitored by the state monitoring device 104, a monitor 106 that displays information of the state monitoring device 104 to a driver, and receives an input from the driver, and a communication device 107 that is connected to the state monitoring device 104 and transmits and receives data to and from the ground system 102.
[0018] The ground system 102 includes a state data accumulation unit 111 that accumulates state data of various apparatuses provided in the train 101, an abnormality diagnosis unit 112 that determines presence or absence and a cause of an abnormality from the data in the state data accumulation unit 111, an abnormality analysis database 113 that accumulates an abnormality diagnosis result analyzed by the abnormality diagnosis unit 112, a communication device 114 that transmits and receives data to and from the train by communication, an abnormality occurrence prediction unit 115 that is connected to the communication device 114 and the abnormality analysis database 113 and determines whether an abnormality will occur or not in the train in the future, and a monitor 116 that displays a state of the abnormality occurrence prediction unit 115 to an operator of the ground system, and receives an input from the operator.
[0019] With reference to FIG. 1, flows of a process and data of abnormality determination by the system for supporting determination of an abnormality of a moving object 100 will be described. To perform an abnormality determination process, the system 100 includes two processes: a normal process performed at normal time; and a failure occurrence time process performed at the time of failure occurrence.
[0020] First, the normal process will be described. The measurement device 103 acguires states of apparatuses (for example, a truck or a brake) provided in the train and states of sensors provided in the apparatuses (hereinafter, these states are collectively referred to as "states of apparatuses", and data of the states of the apparatuses are simply referred to as "state data") . The measurement device 103 transmits state data, that is, a part or all of data of measured physical guantities of the apparatuses that change every moment to the state monitoring device 104. The measurement device 103 itself may have a self-health checking function of the apparatus, and transmit a state code or a failure code of an apparatus to the state monitoring device 104. The state monitoring devioe 104 displays the state data or the state code transmitted from the measurement device 103 on the monitor 106.
[0021] The state monitoring device 104 monitors the state data, detects a failure of the apparatus from a change in the state data, and generates a failure code. At this time, a known failure detection method of the apparatus is used to generate a failure code, for example, in the case where a preset range of upper and lower limit values is exceeded, or where data cannot be acguired for a certain time. The generated failure code together with the failure code produced by the measurement device 103 are displayed on the monitor 106, and stored in the state data storage unit 105 together with the state data. The state data storage unit 105 stores and accumulates state data and a failure code at normal time. The state data is used for abnormality diagnosis in the ground system described later, and thus needs to be detailed state data with high time resolution (for example, a cycle of 100 msec or the like) [0022] A failure mode and the detailed state data stored in the state data storage unit 105 are accumulated via a data flow 108 in the state data accumulation unit 111 in the ground system 102. The data flow 108 is a flow that regularly moves a large capacity of data. Data may be transmitted to the ground system 102 by a method using a storage medium by a maintenance staff at the time of regular train check, a method of connecting a cable, or a method by near field communication. With a large data transfer capacity, a communication device 107 may be used.
The state data accumulation unit 111 accumulates failure modes and detailed state data of a plurality of trains.
The abnormality diagnosis unit 112 regularly analyzes data in the state data accumulation unit 111 to detect presence or absence of an abnormality in an apparatus for which a failure mode has been recorded.
[0023] As described above, the failure refers to a state of the apparatus different from a normal state, and the abnormality refers to a state that is undesirable as a system due to the failure of the apparatus, and requires recovery by stopping the apparatus or the like. The abnormality may be detected using a generally known data analysis method, and an abnormal point in the state data is detected using frequency analysis, principal component analysis, regression analysis, or the like to identify a cause of the abnormality. A person may observe a real apparatus with the abnormality. The abnormality diagnosis unit 112 records an abnormality diagnosis result of whether or not an abnormality has occurred for a certain failure mode in the abnormality analysis database 113. Details of the abnormality analysis database will be described later, but the failure mode, the abnormality diagnosis result, and the state data are recorded in association with each other.
[0024] By the above normal process, the system for supporting determination of an abnormality of a moving object 100 can include the state data, the failure mode, and the abnormality diagnosis result measured in the train 101 in association with each other in the abnormality analysis database 113 in the ground system 102. To derive the abnormality diagnosis result, a complex process using a large amount of detailed state data is required. It is difficult for the train 101 to include such data, and the process can be realized by the existence of the ground system 102. It is also an advantage of the ground system 102 including the abnormality analysis database 113 that state data for a plurality of trains 101 can be handled.
[0025] Next, the process at the time of failure occurrence will be described. This process is the same as the normal process before the state data or the like acquired from the measurement device 103 at the time of failure occurrence is used to produce a failure mode in the state monitoring devioe 104. At the time of failure 000urrenoe, a state of the failure occurrence is presented to the driver via the monitor 106. However, it is difficult for the driver to determine how the failure influences operation and whether the failure leads to an abnormality without the abnormality determination result at hand.
Also, if the state monitoring device 104 determines the abnormality determination result, it is difficult for the train 101 to include a large amount of detailed state data and a complex process.
[0026] Thus, the train 101 transmits the failure mode and last state data 109 via the communication device 107 to the ground system 102, and receives an abnormality determination result and reliability 110 thereof determined based on the transmitted state data 109 from the ground system 102. The abnormality determination result and the reliability 110 allow the driver to determine whether operation can be continued or not.
Specifically, in the ground system 102, the communication device 114 receives the failure mode and the last state data 109 at the time of failure occurrence. The abnormality occurrence prediction unit 115 compares the failure mode and the last state data 109 with the abnormality diagnosis result diagnosed by the abnormality diagnosis unit 112 recorded together with the failure mode in the abnormality analysis database 113, extraots a past failure mode and a past abnormality diagnosis result oorresponding to the failure mode at the time of failure ooourrenoe, and outputs, to the train 101, a prediotion result of whether the failure mode leads to an abnormality or not as the abnormality determination result and the reliability 110 thereof from the abnormality diagnosis result. Details of the process of the abnormality occurrence prediction unit 115 will be described later. The abnormality occurrence prediction unit 115 includes the monitor 116, and a maintenance staff or an operation manager may check an output result of the abnormality occurrence prediction unit 115 and determine to transmit the abnormality determination result and the reliability 110 to the train.
[0027] By the above process at the time of failure occurrence, the system for supporting determination of an abnormality of a moving object 100 can acquire the abnormality determination result and the reliability 110 thereof in both the train 101 and the ground system 102, and determine whether operation can be continued. In particular, the past case is compared with the last state data to increase reliability in response at the time of failure occurrence. Thus, it can be determined to continue operation even when an abnormality cannot be detected only from the state data, thereby increasing an operation rate of the train 101.
[0028] FIG. 2 is a data structure of the abnormality analysis database 113 of the ground system 102. The abnormality analysis database 113 includes an abnormality analysis data 201 shown in FIG. 2(a) and a related detailed state data 202 shown in FIG. 2 (b) . The abnormality analysis data 201 includes pointers 1 to N to provide access to a failure mode, an abnormality diagnosis result, and state data. The failure mode includes an apparatus that outputs the failure mode, and a code indicating a type of the failure. The abnormality diagnosis result is a result diagnosed by the abnormality diagnosis unit 112, and includes presence or absence of an abnormality of an apparatus and a cause of the abnormality in the presence of the abnormality of the apparatus. The pointer to the state data is a pointer to the state data related to the failure mode, and if a plurality of state data, for example, states of different apparatuses have an influence on the failure, the pointer may include the state data of the apparatuses. The state data pointer refers to data around a point where the failure mode is generated in the detailed state data 202.
[0029] The detailed state data 202 includes a state data header, a failure detection time, and a state data row.
The state data header includes types of state data, and various kinds of basic information relating to the state data (basic information on time of the state data row or addresses of the state data or the like) . The failure detection time includes a time when a failure mode is generated and detected. The failure detection time is included to facilitate extraction of state data around generation of the failure mode. The state data row is time series data of the state data, includes time, state data, and an abnormality flag, and stores a time when the abnormality flag is on correspondingly to a detection time. The abnormality flag indicates a result of determination whether the state data at the time is abnormal or not, which is diagnosed by the abnormality diagnosis unit 112.
[0030] Reference numeral 204 in FIG. 2(c) denotes an image of data represented by the abnormality analysis data 201 and the detailed state data 202. Reference numeral 206 denotes an example when the failure mode is a reduction in air pressure, and an abnormality diagnosis result shows an air leak abnormality, showing a state data row 203 in a time series graph (diagram) with a failure detection time 207 on the abscissa, and air pressure of a brake is taken as an example of the state data. The abnormality flag included in the state data row 203 can indicate state data with occurrence of an abnormality as denoted by 208 (the cross mark refers to the abnormality flag being ON) [0031] The system for supporting determination of an abnormality of a moving object of the present invention including the abnormality analysis database 113 described above can include the failure mode, the abnormality determination result, and the state data in association with each other, thereby facilitating extraction of an abnormality determination result for the failure mode.
Specifically, for example, when a failure mode that is a reduction in air pressure is generated on the train, the ground side can easily read a past similar case as a data row.
[0032] FIG. 3 shows a process flow of the abnormality occurrence prediction unit 115 of the ground system 102.
Now, a description will be made according to process steps.
[0033] Step 301 (corresponding to S301 in FIG. 3, hereinafter Step is abbreviated as 5): the abnormality occurrence prediction unit 115 in the ground system 102 reads a failure mode at the time of failure ooourrenoe in the moving objeot (train 101) and state data of the apparatus at the time of 000urrenoe and the last state data, aoguired by oommunioation.
5302: From the abnormality analysis database 113, data of the same failure mode as the failure mode acquired in 5301 (data accumulated in the past; generally, there are a plurality of pieces of data as shown in FIG. 2) is extracted.
S303: The number of pieces of data of the same failure mode extracted in S302 is stored in a memory.
S304: The process up to S312 is repeated for the number of pieces of data of the same failure mode.
Specifically, the process up to S312 is performed for each of extracted accumulated state data B. S305: State data (state data A) at the time of failure occurrence is matched with the state data (state data B) extracted from the abnormality analysis database 113. The matching is a process for comparing similarity of data. State data for a predetermined number of times before and after a state detection time is matched. As a matching process, for example, an inner product of vectors can be used. Time series directions of the state data are taken as dimensions of vectors, and an inner product of normalized state data A and state data B are taken. Then, values of the inner product are within -1 to 1, and a value closer to 1 represents higher similarity. Such an inner product is used as a matching rate. Besides the inner product, measures such as correlation coefficient, or determination coefficient of regression analysis may be used to determine similarity.
Instead of the time series data, data converted into a frequency domain by Fourier transform or the like may be used to perform matching.
[0034] S306: The matching rate acquired in S305 is stored in the memory.
S307: It is determined whether the matching rate is equal to or larger than a predesignated threshold. When the matching rate is equal to or larger than the threshold, the process proceeds to S308, and when the matching rate is smaller than the threshold, the process proceeds to S309.
S308: When the matching rate is equal to or larger than the threshold, it is determined that the state data A is similar to the state data B, and "matching" is stored in the memory.
S309: When the matching rate is smaller than the threshold, it is determined that the state data A is not similar to the state data B, and Tunmatching" is stored in the memory.
[0035] 5310: Whether the abnormality diagnosis result stored for the state data B is "abnormal" or "normal" is stored. When the abnormality diagnosis result is "abnormal", the process proceeds to 5311, and "abnormal" is stored in the memory. When the abnormality diagnosis result is "normal" (= no abnormality), the process proceeds to 5312, and "normal" is stored in the memory.
The above process for the state data B of 5304 and thereafter is finished. As a result, the state data A can be classified into four patterns: "abnormal" and "matching"/"unmatching", "normal" and "matching"/ "unmatching" for each of the state data B. [0036] 5313: Reliability is calculated from the number of cases of matching between the state data A and the state data B and from the abnormality diagnosis result. The state data A is data up to immediately after detection of a failure, and thus data to be matched is mostly data up to immediately before detection of the failure.
Specifically, the matching rate represents similarity to the state data B up to immediately before detection of the failure. If different tendencies of normal and abnormal are found in the state data A up to immediately before detection of the failure, it is anticipated that, in a calculation result of the matching rate between the current state data A and each of the past state data B, the matching rates with the two different tendencies are high as the abnormality diagnosis result, and the number of cases of either "normal" and "matching" or "abnormal" and "matching'T increases, and with the number of cases being used as an index of reliability, it can be predicted that the state data A is "normal" or "abnormal".
[0037] Meanwhile, when there is less difference between normal and abnormal in the state data A up to immediately before the detection of the failure for a certain failure mode, the number of cases of both "normal" and "matching" and "abnormal" and "matching" increases. Specifically, in this case, a ratio of "normal" to "abnormal" assumed for the state data A is supposed to be a ratio close to appearance frequency of "normal'T and Tabnormal'T in the past case (state data B) . In other words, when there is no difference between normal and abnormal in the state data A, a determination can be supported to make a determination based on the past case. However, if there is no "abnormal" case after matching, it can be statistically predicted with high reliability that the state is "normal" also in the past case and transits to "normal" by matching of the state data. Thus, reliability of "normal" can be increased. Further, when there is a large number of cases of "unmatching" (cases representing a data pattern that has not existed in the past) may lead to an abnormality in the future even if no abnormality occurs in the past. Thus, the number of oases of "unmatohing" can be used as an index of reliability. If the number of oases of the same past failure mode is small, an unreliable result is obtained.
[0038] From the above theory, at least one of (1) the number of oases of the same past failure mode, (2) the number of oases of "normal" and "matching", the number of oases of "abnormal" and "matching", and (3) the number of oases of "unmatohing" as reliability.
S314: Based on the reliability obtained in S3l3, an abnormality determination result for the state data A is output.
[0039] FIG. 4 shows an example of determination of the abnormality occurrence prediction unit. FIG. 4 shows a case of a reduction in air pressure of a brake.
Reference numeral 401 denotes a state data of a case to be determined ("case to be determined" that is state data of a failure that has occurred in the train 101), reference numeral 402 denotes an example of a "normal" case included in the abnormality analysis database, reference numeral 403 denotes an example of an "abnormal" case N (case 2 to case (N-i) are not shown) . The state data shown herein is expressed similarly to the graph shown in 204 in FIG. 2 (c) . Reference numeral 404 denotes a matching rate of the case 401 with the case 402, reference numeral 405 denotes a matching rate of the case 401 with the case 403. Reliability as a compiled result is denoted by 406. As the abnormality determination result, a case with a higher matching rate (95%) is used, and the high matching rate is used as an index of reliability.
[0040] In the example of the failure mode, air pressure is temporarily reduced at the time of detection of a failure, and the state is separated into "normal" and "abnormal" in the past case. The state data of the case 401 to be determined is an example with a high matching rate with state data of "normal". In this case, as in the compiled result, the matching rate with "normal" is high, and the matching rate with "abnormal" is zero, thereby allowing determination of "normal" with high reliability.
[0041] FIG. 5 is an example of a determination support screen of the abnormality occurrence prediction unit.
This screen is an example of a screen displayed on the monitor 116 of the ground system 102 in which the maintenance staff or the operation manager actually refers to the state data or the past case to support determination of abnormality. A screen 501 includes information supporting determination suoh as a failure mode 502, an ocourrenoe time, and an elapsed time 503, referenoe numeral 504 denotes state data of a failure to be determined and state data of a past oase to be compared in a superimposed manner, referenoe numerals 505 to 509 denote state data of the past oase. In 505 to 509, an order and a display size are ohanged with referenoe to a degree of matohing or presence or absence of an abnormality (in the shown example, two pieces of state data with the higher matching rate are shown in large size, and three pieces of state data with the low matching rate are shown in small size) . Selecting 505 to 509 as a subject to be compared provides a function of evaluating on the same time series graph on the screen of 504. Further, 510 includes a display function of reliability to allow reference to various pieces of information, includes an abnormality determination 511 button or an normality determination 512 button so that the maintenance staff or the operation manager can make a determination. For example, the past case of!abnormal!Y placed in an upper position of 505 to 509 allows preferential comparison with "abnormal" in 504, and if state data close to "abnormal" appears, it can be determined to be abnormal in an early stage to stop the train.
The ground system includes the above determination support screen, and thus the maintenance staff or the operation manager can support quick and reliable abnormality determination, and a determination result is output as an abnormality determination result and reliability 110 to the train 101.
[0042] FIG. 6 shows an example of a screen of a state monitoring device of the moving object. A screen 601 shown in FIG. 6 is an example of a screen for which the driver checks a failure mode and an abnormality determination result together with reliability based on a support result on the ground side performed on the determination support screen shown in FIG. 5. The screen 601 displays a failure occurrence time and an elapsed time 602, a failure occurrence area 603 in the train 101, and a failure mode 604. The screen 601 further includes a function of displaying an abnormality determination result 605 of the ground system 102, and reliability 606 thereof, and supports operation restart determination at the time of failure occurrence based on various kinds of information. The screen 601 also has a function of showing confirmation 607 or rejection 608 to the abnormality determination result on the ground side, and communicates with the ground system 102.
[0043] The moving object includes the determination support screen as described above, thereby allowing the driver to make a determination to restart operation with high reliability.
[0044] In the above embodiment, the cause of the failure is analyzed on the ground side, and the obtained abnormality determination result is transmitted to the moving object.
However, if the cause of the failure can be determined only from the last state data of the time of the failure, abnormality determination logic is provided in the moving object, thereby allowing the cause of the failure to be notified to the system of the moving object without delay.
Further, in the above embodiment, the moving object is the train, and a railway vehicle operation is mainly described. However, the present invention may be applied to other abnormality diagnosis systems, in particular, a moving object limited in on-line and off-line data collection, for example, ship or aircraft as transportation service whose operation is supported by an operation manager, or construction eguipment such as mining machinery.
Reference Signs List [0045] system for supporting determination of abnormality of moving object 101 moving object, train 102 ground system 112 abnormality diagnosis unit 113 abnormality analysis database abnormality occurrence prediction unit 204 example of data of abnormality analysis database 501 example of determination support screen in ground system 601 example of determination support screen in moving object, train
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2010067899A JP5416630B2 (en) | 2010-03-24 | 2010-03-24 | Moving object abnormality judgment support system |
| PCT/JP2011/053234 WO2011118290A1 (en) | 2010-03-24 | 2011-02-16 | System for supporting determination of abnormality of moving object |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| GB201214932D0 GB201214932D0 (en) | 2012-10-03 |
| GB2491291A true GB2491291A (en) | 2012-11-28 |
| GB2491291B GB2491291B (en) | 2015-06-03 |
Family
ID=44672863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB1214932.4A Expired - Fee Related GB2491291B (en) | 2010-03-24 | 2011-02-16 | System for supporting determination of abnormality of moving object |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP5416630B2 (en) |
| GB (1) | GB2491291B (en) |
| WO (1) | WO2011118290A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018500709A (en) * | 2014-12-01 | 2018-01-11 | アップテイク テクノロジーズ、インコーポレイテッド | Asset health scores and their use |
| CN110382389A (en) * | 2016-12-26 | 2019-10-25 | 三菱电机株式会社 | Restore support system |
| EP3437956A4 (en) * | 2016-03-31 | 2019-12-04 | Hitachi, Ltd. | Data integration and analysis system |
| US10762787B2 (en) | 2016-06-30 | 2020-09-01 | Sumitomo Electric Industries, Ltd. | Communication device, communication system, communication program, and communication control method |
| CN114756299A (en) * | 2022-04-21 | 2022-07-15 | 国汽智控(北京)科技有限公司 | Vehicle fault processing method and device, electronic device and storage medium |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5856935B2 (en) * | 2012-09-14 | 2016-02-10 | 株式会社日立製作所 | Train control system |
| JP5970327B2 (en) * | 2012-10-12 | 2016-08-17 | 公益財団法人鉄道総合技術研究所 | Abnormality detection apparatus, information processing apparatus, and abnormality detection system |
| JP6007065B2 (en) * | 2012-10-30 | 2016-10-12 | 株式会社日立製作所 | Railway vehicle maintenance system |
| US9037320B1 (en) * | 2014-01-29 | 2015-05-19 | The Boeing Company | Unscheduled maintenance disruption severity and flight decision system and method |
| JP6293697B2 (en) * | 2015-03-27 | 2018-03-14 | 三菱電機株式会社 | Device diagnostic apparatus and device diagnostic method |
| CN110088022B (en) * | 2016-12-26 | 2020-07-28 | 三菱电机株式会社 | Recovery support system |
| JP6984265B2 (en) * | 2017-09-15 | 2021-12-17 | 日本電気株式会社 | Information processing equipment, information processing methods, and programs |
| WO2019064725A1 (en) * | 2017-09-29 | 2019-04-04 | 日本電産株式会社 | Power conversion device, motor module, and electric power steering device |
| WO2020166253A1 (en) * | 2019-02-13 | 2020-08-20 | 日立オートモティブシステムズ株式会社 | Vehicle control device and electronic control system |
| US20230078191A1 (en) | 2020-03-30 | 2023-03-16 | Mitsubishi Electric Corporation | Data extraction apparatus, data extraction method, and storage medium |
| WO2024080045A1 (en) * | 2022-10-11 | 2024-04-18 | 住友電気工業株式会社 | Detecting device, detecting system, detecting method, and detecting program |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002286455A (en) * | 2001-03-26 | 2002-10-03 | Mazda Motor Corp | Method and system for remote diagnosis for vehicle, controller for vehicle, diagnostic device for vehicle, and computer program product |
| JP2005063385A (en) * | 2003-08-20 | 2005-03-10 | Kobe Steel Ltd | Monitoring method, monitoring apparatus and program |
| JP2008059102A (en) * | 2006-08-30 | 2008-03-13 | Fujitsu Ltd | Program for monitoring computer resource |
| JP2008129815A (en) * | 2006-11-20 | 2008-06-05 | Mazda Motor Corp | On-vehicle communication device |
| JP2008217609A (en) * | 2007-03-06 | 2008-09-18 | Mitsubishi Electric Corp | Moving object information analyzer and moving object information analysis method |
| JP2009227250A (en) * | 2008-03-25 | 2009-10-08 | Denso Corp | On-vehicle apparatus |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4583594B2 (en) * | 2000-12-28 | 2010-11-17 | 富士重工業株式会社 | Vehicle management system |
| JP2003331087A (en) * | 2002-05-13 | 2003-11-21 | Honda Motor Co Ltd | Demand forecast system for repair component |
| JP2004272375A (en) * | 2003-03-05 | 2004-09-30 | Mazda Motor Corp | Remote failure prediction system |
| JP4281049B2 (en) * | 2003-03-28 | 2009-06-17 | マツダ株式会社 | Remote fault diagnosis system and control method thereof |
| JP4761276B2 (en) * | 2008-07-10 | 2011-08-31 | 東芝エレベータ株式会社 | Abnormality diagnosis system for passenger conveyor |
| JP4826609B2 (en) * | 2008-08-29 | 2011-11-30 | トヨタ自動車株式会社 | Vehicle abnormality analysis system and vehicle abnormality analysis method |
| EP2330510B1 (en) * | 2008-09-18 | 2019-12-25 | NEC Corporation | Operation management device, operation management method, and operation management program |
-
2010
- 2010-03-24 JP JP2010067899A patent/JP5416630B2/en active Active
-
2011
- 2011-02-16 GB GB1214932.4A patent/GB2491291B/en not_active Expired - Fee Related
- 2011-02-16 WO PCT/JP2011/053234 patent/WO2011118290A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002286455A (en) * | 2001-03-26 | 2002-10-03 | Mazda Motor Corp | Method and system for remote diagnosis for vehicle, controller for vehicle, diagnostic device for vehicle, and computer program product |
| JP2005063385A (en) * | 2003-08-20 | 2005-03-10 | Kobe Steel Ltd | Monitoring method, monitoring apparatus and program |
| JP2008059102A (en) * | 2006-08-30 | 2008-03-13 | Fujitsu Ltd | Program for monitoring computer resource |
| JP2008129815A (en) * | 2006-11-20 | 2008-06-05 | Mazda Motor Corp | On-vehicle communication device |
| JP2008217609A (en) * | 2007-03-06 | 2008-09-18 | Mitsubishi Electric Corp | Moving object information analyzer and moving object information analysis method |
| JP2009227250A (en) * | 2008-03-25 | 2009-10-08 | Denso Corp | On-vehicle apparatus |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018500709A (en) * | 2014-12-01 | 2018-01-11 | アップテイク テクノロジーズ、インコーポレイテッド | Asset health scores and their use |
| US10754721B2 (en) | 2014-12-01 | 2020-08-25 | Uptake Technologies, Inc. | Computer system and method for defining and using a predictive model configured to predict asset failures |
| US11144378B2 (en) | 2014-12-01 | 2021-10-12 | Uptake Technologies, Inc. | Computer system and method for recommending an operating mode of an asset |
| EP3437956A4 (en) * | 2016-03-31 | 2019-12-04 | Hitachi, Ltd. | Data integration and analysis system |
| US10762787B2 (en) | 2016-06-30 | 2020-09-01 | Sumitomo Electric Industries, Ltd. | Communication device, communication system, communication program, and communication control method |
| CN110382389A (en) * | 2016-12-26 | 2019-10-25 | 三菱电机株式会社 | Restore support system |
| CN110382389B (en) * | 2016-12-26 | 2020-08-14 | 三菱电机株式会社 | Recovery support system |
| CN114756299A (en) * | 2022-04-21 | 2022-07-15 | 国汽智控(北京)科技有限公司 | Vehicle fault processing method and device, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2011118290A1 (en) | 2011-09-29 |
| GB201214932D0 (en) | 2012-10-03 |
| JP2011201336A (en) | 2011-10-13 |
| JP5416630B2 (en) | 2014-02-12 |
| GB2491291B (en) | 2015-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2491291A (en) | System for supporting determination of abnormality of moving object | |
| JP6889057B2 (en) | Information processing equipment, information processing methods and computer programs | |
| US20100204857A1 (en) | Diagnostic system and method for monitoring a rail system | |
| US6813581B1 (en) | Statistical and trend analysis of railroad bearing temperatures | |
| US20200234558A1 (en) | Mechanical failure detection system and method | |
| US20210217256A1 (en) | Method and Apparatus for Diagnosing and Monitoring Vehicles, Vehicle Components and Routes | |
| MX2015003451A (en) | Diagnostic method for rail vehicles. | |
| CN106404201A (en) | Preventive prompting method and system for axle temperature anomaly of motor train unit | |
| CN108238538A (en) | The fault monitoring method and fault monitoring system of a kind of escalator | |
| CN110672158A (en) | Pantograph health management state detection method | |
| CN110582626B (en) | System and method for monitoring a turbomachine with anomaly detection corrected by a wear factor | |
| CN111579001A (en) | Fault detection method and device for robot | |
| US20240087370A1 (en) | Method for detecting the state of a vehicle component | |
| MXPA04007888A (en) | Cab signal quality detecting and reporting system and method. | |
| KR102516227B1 (en) | A system for predicting equipment failure in ship and a method of predicting thereof | |
| JP6916632B2 (en) | Anomaly detection method for railway vehicle compressors | |
| CN109625025B (en) | BTM equipment early warning system | |
| JP6007065B2 (en) | Railway vehicle maintenance system | |
| KR102448793B1 (en) | Railway condition-based maintenance prediction system using complex interlocking device | |
| JPWO2017168940A1 (en) | Data integration analysis system | |
| KR101669401B1 (en) | System for Previous Warning of Test Apparatus | |
| JP5322568B2 (en) | Device monitoring diagnosis system and control program thereof | |
| KR101653748B1 (en) | System and Method for monitoring status of vehicle based on tire tread | |
| CN109240254A (en) | Vehicle condition assessment and fault early warning method based on vehicle condition data flow | |
| WO2019240767A1 (en) | End of train (eot) remote track-condition monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 789A | Request for publication of translation (sect. 89(a)/1977) |
Ref document number: 2011118290 Country of ref document: WO |
|
| PCNP | Patent ceased through non-payment of renewal fee |
Effective date: 20150903 |