Train anomaly detection system and method

Abstract

To detect abnormality in a train on the basis of a measurement result by measuring movement of passengers in the train without using information by a video image.SOLUTION: An intra-train abnormality detection system includes: a plurality of pieces of measurement means for measuring movement of passengers in each vehicle of a train obtained by connecting a plurality of vehicles; and abnormality detection means for comparing each measurement value of the plurality of pieces of measurement means with an abnormality determination value, and detecting that abnormality occurs in the train when a measurement value of at least one measurement means among the plurality of pieces of measurement means exceeds a range of the abnormality determination value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a train interior abnormality detection system and method for detecting abnormalities in a train.

Background Art

[0002] In order to ensure the reliability of railways, in addition to ensuring normal quality, it is important to quickly respond to abnormalities that occur during operation. The initial response to abnormalities that occur inside the train is generally the responsibility of the crew. However, the crew is often in the driver's cab located at the front or rear of the train for monitoring the front and rear during travel.

[0003] Therefore, in a formation train (train) in which a plurality of vehicles are connected, it is difficult for the crew to visually grasp abnormalities in the intermediate vehicles.

[0004] Therefore, systems for notifying the occurrence of abnormalities have been introduced according to the type of abnormality. For example, regarding abnormalities in vehicle equipment, there are those that detect wheel derailment using the internal pressure value of the air spring (Patent Document 1), and those that detect vehicle overload using the internal pressure value of the air spring (Patent Document 2). In addition, regarding abnormalities of passengers, there are those that can monitor passengers and grasp abnormalities by distributing the video of the monitoring camera installed in the passenger compartment and the analysis result of suspicious persons to the operation manager (Patent Document 3).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document *2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, to monitor passengers on existing trains that do not have surveillance cameras installed, using image information including surveillance camera footage, it is necessary to install new equipment such as surveillance cameras. Moreover, transmitting and receiving image information including surveillance camera footage requires a network with sufficient communication capacity to distribute large amounts of image data. For this reason, using surveillance cameras to detect abnormalities inside trains would increase the cost of installing the equipment.

[0007] The objective of this invention is to measure the movement of passengers inside a train without using video information, and to detect abnormalities inside the train based on these measurement results. [Means for solving the problem]

[0008] To solve the above problems, the present invention is characterized by comprising: a plurality of measuring means for measuring the movement of passengers in each car of a train in which a plurality of cars are connected; and an abnormality detection means for comparing the measured value of each of the plurality of measuring means with an abnormality judgment value, and detecting that an abnormality has occurred in the train when the measured value of at least one of the plurality of measuring means exceeds the range of the abnormality judgment value. [Effects of the Invention]

[0009] According to the present invention, it is possible to measure the movement of passengers inside a train without using video information, and to detect abnormalities inside the train based on these measurement results.

[0010] Other issues, configurations, and effects not mentioned above will be clarified by the following description of embodiments for carrying out the invention. [Brief explanation of the drawing]

[0011] [Figure 1] This is a configuration diagram showing an example of the configuration of a train anomaly detection system according to Embodiment 1 of the present invention. [Figure 2] This flowchart shows an example of the processing of the anomaly detection logic according to Embodiment 1 of the present invention. [Figure 3] This is a characteristic diagram illustrating the internal air spring pressure and the time difference in the internal air spring pressure value for each vehicle in the train anomaly detection system according to Embodiment 1 of the present invention. [Figure 4] This is a characteristic diagram of the normal distribution applied to the train anomaly detection system according to Embodiment 1 of the present invention. [Figure 5] This is a diagram showing an example configuration of a train anomaly detection system according to Embodiment 2 of the present invention. [Figure 6] This is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 2 of the present invention. [Figure 7] This is a characteristic diagram illustrating the internal air spring pressure and the time difference in internal air spring pressure values ​​for each car and train set in the train abnormality detection system according to Embodiment 2 of the present invention. [Figure 8] This is a configuration diagram showing an example of the configuration of a train anomaly detection system according to Embodiment 3 of the present invention. [Figure 9] This is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 3 of the present invention. [Figure 10] This is a characteristic diagram illustrating the internal air spring pressure and the difference in the time of change of the internal air spring pressure in each vehicle in the train anomaly detection system according to Embodiment 3 of the present invention. [Figure 11] This is a diagram showing an example configuration of a train anomaly detection system according to Embodiment 4 of the present invention. [Figure 12] This is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 4 of the present invention. [Figure 13] This is a characteristic diagram illustrating the air spring internal pressure and the difference in air spring internal pressure reduction time for each car and train set in the train abnormality detection system according to Embodiment 4 of the present invention. [Modes for carrying out the invention]

[0012] Examples 1 to 4 will be described below with reference to the drawings. The meaning of the symbols mentioned in Example 1 will be the same and will be applied to the descriptions of the other examples. [Examples]

[0013] Embodiment 1 is an abnormality detection method for dealing with the situation where an abnormality occurs while passengers are confined inside the train during a train stop. It detects the evacuation behavior of passengers moving between vehicles by using the variation in the internal pressure value of the air springs between vehicles. In this embodiment, an example using an air spring internal pressure value measuring device that measures the air spring internal pressure will be described as a representative of the measuring means for measuring the movement of passengers. As the measuring means, other means capable of grasping the number of passengers and the boarding rate, such as a PCS (Passenger Count System) including an infrared sensor and a thermal sensor, a tire pressure measuring device, a vehicle suspension device, a concentration measuring device for measuring oxygen concentration and carbon dioxide concentration, a mat using a piezoelectric element, and an optical sensor, can also be used. In that case, it is desirable to configure it so that the moving direction of the passengers can be detected.

[0014] FIG. 1 is a configuration diagram showing a configuration example of a train interior abnormality detection system according to Embodiment 1 of the present invention. In FIG. 1, the train interior abnormality detection system includes a plurality of vehicles 101, 102, an abnormality notification device 103, a vehicle information control device 104, an abnormality detection logic 105, air springs 106, 107, and air spring internal pressure value measuring devices 108, 109. In vehicle 101, an abnormality notification device 103, a vehicle information control device 104, an abnormality detection logic 105, an air spring 106, and an air spring internal pressure value measuring device 108 are mounted, and in vehicle 102, an air spring 107 and an air spring internal pressure value measuring device 109 are mounted.

[0015] The air springs 106 and 107 are composed of, for example, a diaphragm and laminated rubber, and are installed between the bogies and the car bodies (both not shown) of vehicles 101 and 102, respectively. The air spring internal pressure value measuring device 108 measures the internal pressure value acting on the air spring 106 and outputs the measurement result to the vehicle information control device 104 as the air spring internal pressure value 111. The air spring internal pressure value measuring device 109 measures the internal pressure value acting on the air spring 107 and outputs the measurement result to the vehicle information control device 104 as the air spring internal pressure value 112.

[0016] Vehicle information control device 10 4The vehicle information control device 10 constantly acquires the measurement results of each air spring internal pressure measurement device 108, 109 while in operation, and monitors the air spring internal pressure values ​​111, 112 of the air springs 106, 107 mounted on each vehicle 101, 102. 4 The system uses anomaly detection logic 105 to monitor changes in the internal air spring pressure values ​​111 and 112 of the air springs 106 and 107. For example, if it detects an abnormal movement in the internal air spring pressure values ​​111 and 112 caused by passenger evacuation actions, it outputs an anomaly detection result 110 to the anomaly notification device 103, indicating that an anomaly has occurred in one of the vehicles 101 or 102. The anomaly notification device 103 notifies of the anomaly upon receiving the anomaly detection result 110. When passenger movement is measured by the number of passengers, the vehicle information control device 10 4 This system can calculate the number of passengers in each vehicle based on the measured values ​​(loads acting on the vehicle) from the air spring internal pressure measuring devices 108 and 109 and the average weight of the passengers.

[0017] The vehicle information control device 104 is composed of, for example, a computer (not shown) that includes a processor, main memory, auxiliary memory, input device, output device, and communication device.

[0018] A processor is composed of components such as a CPU (Central Processing Unit) and an MPU (Micro Processing Unit).

[0019] Main memory is a device that stores computer programs and data, and includes, for example, ROM (Read Only Memory), RAM (Random Access Memory), and non-volatile semiconductor memory.

[0020] Auxiliary storage devices include, for example, hard disk drives, SSDs (Solid State Drives), optical storage media (i.e., CDs (Compact Discs) and DVDs (Digital Versatile Discs), etc.), storage systems, IC cards (Integrated Circuit Cards), SD (Secure Digital) memory cards, and other reading / writing devices for storage media, as well as the storage areas of cloud servers. Computer programs and data stored in auxiliary storage devices are read into main memory as needed.

[0021] An example of a computer program stored in auxiliary storage is an anomaly detection program, which functions as an anomaly detection logic. The CPU reads the anomaly detection program from auxiliary storage and executes it, thereby realizing the function of an anomaly detection logic or anomaly detection unit.

[0022] Input devices include, for example, keyboards, mice, touch panels, card readers, and audio input devices. Output devices (display devices) are user interfaces that provide users with various information such as processing progress and processing results. Output devices include, for example, screen display devices (i.e., liquid crystal monitors, LCDs, or graphics cards), audio output devices (i.e., speakers, etc.), or printing devices.

[0023] A communication device is a wired or wireless communication interface that enables communication with other devices via communication means such as a LAN or the Internet. Examples of communication devices include a NIC (Network Interface Card), wireless communication module, USB (Universal Serial Bus) module, or serial communication module.

[0024] Figure 2 is a flowchart showing an example of the processing of the anomaly detection logic according to Embodiment 1 of the present invention. In Figure 2, this process is started when the processor activates the anomaly detection logic 105. The anomaly detection logic 105 acquires the current air spring internal pressure values ​​111 and 112 of each air spring internal pressure value measuring device 108 and 109 as the current air spring internal pressure values ​​of each vehicle (S201).

[0025] Next, the anomaly detection logic 105 calculates the difference in air spring internal pressure values ​​and the time difference for each vehicle based on the air spring internal pressure values ​​111 and 112 measured by the air spring internal pressure value measuring devices 108 and 109 (S202). At this time, the anomaly detection logic 105 calculates the time change (change per unit time) of the air spring internal pressure values ​​111 and 112 acquired in step S201 as the difference in air spring internal pressure values ​​for each vehicle, compares the air spring internal pressure values ​​111 and 112 acquired in step S201 with the air spring internal pressure values ​​111 and 112 acquired in step S201 in the previous processing loop (previous measurement cycle), and calculates the comparison result showing the difference between the two as the time difference in air spring internal pressure values ​​for each vehicle. In other words, the anomaly detection logic 105 acquires the air spring internal pressure values ​​111 and 112 for each measurement cycle, and calculates the difference between the acquired air spring internal pressure values ​​111 and 112 for each measurement cycle as the time difference of the air spring internal pressure values ​​for each vehicle. Note that in the initial calculation, the set values ​​are used as the air spring internal pressure values ​​111 and 112 acquired in the previous processing loop. Also, one processing loop refers to the processing from step S201 to step S203.

[0026] Next, the anomaly detection logic 105 determines, based on the calculation results of the difference in air spring internal pressure values ​​and the time difference for each vehicle, whether the difference in air spring internal pressure values ​​and the time difference for each vehicle simultaneously exceed the threshold values ​​for increase or decrease, which are threshold values ​​for determining the occurrence of an anomaly (S203).

[0027] If the anomaly detection logic 105 obtains a negative (NO) result in step S203, it returns to step S201 and repeats the processing from steps S201 to S203.

[0028] On the other hand, if the anomaly detection logic 105 obtains a positive (YES) judgment result in step S203, it outputs the anomaly detection result 110 to the anomaly notification device 103. For example, if an anomaly occurs in vehicle 101, the passenger evacuation action (the evacuation action of passengers in vehicle 101 moving to vehicle 102) causes the air spring internal pressure value 111 to decrease in vehicle 101 and the air spring internal pressure value 112 to increase in vehicle 102. Therefore, in vehicle 101, the difference and time difference of the air spring internal pressure value 111 exceed the threshold for decrease (exceeding the range of anomaly judgment values), and in vehicle 102, the difference and time difference of the air spring internal pressure value exceed the threshold for increase (exceeding the range of anomaly judgment values). Specifically, in vehicle 101, the difference and time difference of the air spring internal pressure value 111 fall below the threshold for decrease, and in vehicle 102, the difference and time difference of the air spring internal pressure value exceed the threshold for increase. In this case, the anomaly detection logic 105 outputs an anomaly detection result 110 to the anomaly notification device 103, indicating that an anomaly has occurred in the vehicle 101.

[0029] Subsequently, the abnormality notification device 103 notifies the crew that an abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased. For example, if an abnormality occurs in vehicle 101, the abnormality notification device 103 notifies the crew that an abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased, i.e., in vehicle 101.

[0030] Figure 3 is a characteristic diagram illustrating the air spring internal pressure and the time difference in air spring internal pressure values ​​for each vehicle in the train abnormality detection system according to Embodiment 1 of the present invention. Figure 3(a) shows the behavior of the air spring internal pressure of vehicle 101, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 108. In Figure 3(a), the air spring internal pressure (difference) of vehicle 101 (vehicle 1) remains at a substantially constant value over time as the air spring internal pressure value 301 progresses under normal conditions. Here, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). The air spring internal pressure value 301 of vehicle 101 gradually decreases, and thereafter, the decrease 304 falls below the threshold 306, which indicates the air spring internal pressure threshold for the decrease. That is, the decrease 304 falls outside the range of the threshold 306, which indicates the abnormality judgment value.

[0031] Figure 3(b) shows the behavior of the air spring internal pressure of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 109. In Figure 3(b), the air spring internal pressure (difference) of vehicle 102 (vehicle 2) remains approximately constant over time as the air spring internal pressure value 302 under normal conditions. Here, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). At this point, the air spring internal pressure value 301 of vehicle 101 gradually decreases, while the air spring internal pressure value 302 of vehicle 102 gradually increases. Subsequently, the increase 305 exceeds the threshold 307, which indicates the air spring internal pressure threshold for the increase. That is, the increase 305 falls outside the range of the threshold 307, which indicates the abnormality judgment value.

[0032] Figure 3(c) shows the behavior of the time difference of the air spring internal pressure value of vehicle 101, where the horizontal axis represents elapsed time and the vertical axis represents the time difference of the air spring internal pressure value measured by the air spring internal pressure value measuring device 108. In Figure 3(c), the time difference of the air spring internal pressure value of vehicle 101 (vehicle 1) normally remains at a nearly constant value as time progresses, as the air spring internal pressure value time difference 308. Here, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). The air spring internal pressure value time difference 308 of vehicle 101 decreases rapidly and falls below the threshold 309, which indicates the air spring internal pressure value time difference threshold. After that, the air spring internal pressure value time difference 308 remains below the threshold 309 and returns to its original value when the evacuation of the passengers of vehicle 101 is complete. In this case, if the time difference 308 of the air spring internal pressure value remains below the threshold 309 for a set time or longer from time 303, and exceeds the duration threshold 310 which indicates the elapsed time threshold of the air spring internal pressure value, that is, if the time difference 308 of the air spring internal pressure value remains below the threshold 309 for a continuous period of 310 or more, the time difference 308 of the air spring internal pressure value of the vehicle 101 is determined to be abnormal.

[0033] Figure 3(d) shows the behavior of the time difference of the air spring internal pressure value of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the time difference of the air spring internal pressure value measured by the air spring internal pressure value measuring device 109. In Figure 3(d), the time difference of the air spring internal pressure value of vehicle 102 (vehicle 2) normally remains at a nearly constant value as time progresses, as the air spring internal pressure value time difference 311. Here, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). As the time difference of the air spring internal pressure value 308 of vehicle 101 rapidly decreases, the time difference of the air spring internal pressure value 311 of vehicle 102 rapidly increases and exceeds the threshold 312, which indicates the threshold of the air spring internal pressure value time difference. Subsequently, the air spring internal pressure value time difference 311 continues to be above the threshold 312, and returns to its original value when the evacuation of the passengers of vehicle 101 is completed. In this case, if the time difference 311 of the air spring internal pressure value exceeds the threshold 312 for a set period of time or longer, and exceeds the duration threshold 313 which indicates the elapsed time threshold of the air spring internal pressure value, that is, if the time difference 311 of the air spring internal pressure value exceeds the threshold 312 for a continuous period of 313 or more, the time difference 311 of the air spring internal pressure value of the vehicle 102 is determined to be abnormal.

[0034] At time 303, if an abnormality occurs in vehicle 101, passengers in vehicle 101 evacuate to vehicle 102, the air spring internal pressure value 301 in vehicle 101 decreases, the air spring internal pressure value 302 in vehicle 102 increases, and all of the following conditions (1) to (4) are met, then it is detected that an abnormality has occurred in vehicle 101 (the vehicle in which the air spring internal pressure value 301 decreased), and the crew is notified that an abnormality has occurred in vehicle 101.

[0035] (1) The decrease of 304 in the internal pressure value of the air spring (301) falls below the threshold of 306. (2) The increase of 305 in the internal pressure value of the air spring (302) exceeds the threshold value (307). (3) The time difference of the internal pressure value of the air spring, 308, is continuously below the threshold value of 309 for a duration of 310 or more. (4) The time difference 311 of the internal pressure value of the air spring continuously exceeds the threshold 312 for a duration of 313 or more.

[0036] As a result, it becomes possible to detect an emergency in a vehicle and the evacuation action of passengers moving from the vehicle 101 where the emergency occurred to the adjacent vehicle 102. By notifying the crew of the vehicle 101 where the emergency occurred, it becomes possible to respond to the emergency.

[0037] Furthermore, even if only conditions (1) to (2) above are met, it is still possible to detect that an abnormality has occurred in vehicle 101. However, if an abnormality in vehicle 101 is detected only when conditions (1) to (2) are met, then if the air spring internal pressure values ​​301 and 302 contain errors such as sudden noise or outliers, the decrease 304 and increase 305 cannot be measured accurately, and it may not be possible to accurately detect that an abnormality has occurred in vehicle 101. Also, even if only conditions (3) to (4) above are met, it is still possible to detect that an abnormality has occurred in any of the vehicles. However, if only conditions (3) to (4) are met, it is difficult to identify the vehicle in which the abnormality occurred. For this reason, by making the detection of abnormalities within the vehicle require that all of the above conditions (1) to (4) be met, it is possible to accurately detect that an abnormality has occurred in vehicle 101.

[0038] Furthermore, the values ​​of each threshold can be calculated from empirical data or statistical information, and the calculated values ​​may be pre-recorded in a recording device such as memory, transmitted wirelessly from a ground station to the vehicle, or calculated based on data collected on the vehicle.

[0039] As a statistical method for distinguishing between normal and abnormal values, for example, a method based on the normal distribution can be used. Furthermore, since the only requirement for distinguishing between normal and abnormal values ​​is to determine a threshold, various statistical methods other than the normal distribution are available, such as the t-distribution, F-distribution, Fisher's linear discriminant analysis, quadratic discriminant analysis, support vector machines, and Bayesian statistics (MCMC method, conjugate distribution method). Any of these can be used.

[0040] One of the simplest methods when using a normal distribution is to use the central limit theorem to take the average over a finite time and collect those average values.

[0041] Figure 4 is a characteristic diagram of a normal distribution applied to the train anomaly detection system according to Embodiment 1 of the present invention. The horizontal axis represents the random variable, and the vertical axis represents the probability.

[0042] In Figure 4, for example, if the 1-minute average value X of the internal air spring pressure at a certain point in time is 85, the average value μ of the internal air spring pressure while the train is stopped is 100, and the standard deviation σ is 3, then the calculation can be performed using equation (1) of Equation 1 below.

number

[0043] In a normal distribution, the probability of exceeding ±5 is approximately 0.000057%, meaning that such a phenomenon can only occur about once every 29,240 hours under normal circumstances.

[0044] If we apply the above to an actual vehicle, it would be equivalent to 15 people moving from a vehicle with 100 passengers to an adjacent vehicle every minute. If the vehicle has doors on both sides, this would be equivalent to 1 person moving to the adjacent vehicle every 8 seconds per door. This is something that would almost never happen under normal circumstances, but it is considered a possible event if an anomaly occurs.

[0045] The mean value X can be any value other than 1 minute, such as 30 seconds, and the mean value μ does not necessarily have to be the average, but can be a value at a point in time when the values ​​are relatively stable (such as 1 minute after the doors close). The standard deviation can be calculated using values ​​from previous instances where X and μ were taken at similar intervals, or it can be calculated using values ​​taken after the doors close or while the train is stopped. When the sample size is small, a t-distribution can be used instead of a normal distribution.

[0046] Furthermore, while "5" was used as the threshold above, other values ​​may be used depending on the differences between railway operators and lines.

[0047] According to this embodiment, passenger movement within a train can be measured without using video information, and abnormalities within the train can be detected based on these measurement results. Furthermore, according to this embodiment, when an abnormality occurs within a train, it is possible to detect evacuation behavior in which passengers move from the abnormal train 101 to an adjacent train 102, and by notifying the crew of the abnormal train 101, it becomes possible to respond to the abnormality. Moreover, according to this embodiment, even in existing trains where surveillance cameras are not installed, if an air spring internal pressure value measuring device and a train information control device are installed, abnormalities within the train can be detected by modifying the software (abnormality detection logic) installed in the train information control device, and the cost of introducing equipment to existing trains where surveillance cameras are not installed can be significantly reduced. [Examples]

[0048] Example 2 is an anomaly detection method for situations where passengers are trapped inside a train while it is stopped, and an anomaly occurs, causing some passengers to escape through windows or other openings. In this situation, the amount of passenger evacuation to cars that are not experiencing an anomaly decreases. To address this, Example 2 employs an anomaly detection method that uses the total internal air spring pressure value of the entire train. That is, if some passengers escape through windows or other openings when an anomaly occurs, the amount of movement between cars decreases, making it impossible to detect the anomaly using the method of Example 1. On the other hand, if the total internal air spring pressure value of the entire train decreases while the train is stopped at a station or without opening doors, it is highly likely that some kind of anomaly has occurred in the train. Therefore, a method is adopted to detect anomalies inside the train based on the total internal air spring pressure value of the entire train and its time difference.

[0049] In this embodiment, as in Embodiment 1, we will describe a representative example in which an air spring internal pressure value measuring device is used as a measuring means for measuring passenger movement. Also in this embodiment, as in Embodiment 1, the measuring means and do Other means can be used.

[0050] Figure 5 is a configuration diagram showing an example of the configuration of an in-train anomaly detection system according to Embodiment 2 of the present invention. In this embodiment, an anomaly detection logic 405 is placed in the vehicle information control device 104 instead of the anomaly detection logic 105, and the other configurations are the same as in Embodiment 1. The processing of the anomaly detection logic 405 will be described below, mainly focusing on the processing that differs from Embodiment 1.

[0051] Figure 6 is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 2 of the present invention. This process is started when the processor activates the anomaly detection logic 405. Steps S201 to S204 perform the same processing as steps S201 to S204 in Figure 2, so the explanation of these steps is omitted. However, if the result in step S204 is negative, instead of returning to step S201, the process proceeds to step S601.

[0052] If the abnormality detection logic 405 obtains a negative (NO) result in step S203, it sums the air spring internal pressure values ​​of all vehicles in the train set (S601). For example, if vehicle 101 and vehicle 102 are vehicles in the train set, the abnormality detection logic 405 obtains the air spring internal pressure values ​​111 and 112 measured by the air spring internal pressure value measuring devices 108 and 109 as the air spring internal pressure values ​​of all vehicles in the train set and sums them up.

[0053] Next, the anomaly detection logic 405 calculates the difference and time difference between the total air spring pressure value and the total air spring pressure value in the previous processing loop, based on the air spring internal pressure values ​​111 and 112 measured by the air spring internal pressure value measuring devices 108 and 109 (S602). At this time, the anomaly detection logic 405 compares the total air spring internal pressure values ​​111 and 112 obtained in step S601 with the total air spring internal pressure values ​​111 and 112 obtained in the previous processing loop, and calculates the difference and time difference between the total air spring internal pressure values.

[0054] Next, the anomaly detection logic 405 determines whether the difference in the total value of the air spring internal pressure and the difference in time exceeds a threshold for the decrease, based on the calculation results of the difference in the total value of the air spring internal pressure and the difference in time (S603).

[0055] If the anomaly detection logic 405 obtains a negative (NO) result in step S603, it returns to step S201 and repeats the processing of steps S201 to S203.

[0056] On the other hand, if the anomaly detection logic 405 obtains a positive (YES) result in step S603, it outputs an anomaly detection result 110 to the anomaly notification device 103. For example, if an anomaly occurs in vehicle 101, and some passengers in vehicle 101 escape through windows or the like, and the remaining passengers trapped inside vehicle 101 move from vehicle 101 to vehicle 102, the number of people who move due to the passenger evacuation action will be less than in Embodiment 1. Therefore, provided that the total value of the air spring internal pressure of the entire vehicle exceeds the threshold for the decrease, the anomaly detection logic 405 outputs an anomaly detection result 110 to the anomaly notification device 103 indicating that an anomaly has occurred in the train set.

[0057] Subsequently, the abnormality notification device 103 notifies the crew that an abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased (S204). For example, if an abnormality occurs in a train set, the abnormality notification device 103 notifies the crew that the abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased.

[0058] Figure 7 is a characteristic diagram illustrating the air spring internal pressure and the time difference in air spring internal pressure values ​​for each car and train set in the train abnormality detection system according to Embodiment 2 of the present invention. Figure 7(a) shows the behavior of the air spring internal pressure of car 101, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 108. In Figure 7(a), the air spring internal pressure (difference) of car 101 (car 1) remains at a substantially constant value over time as the air spring internal pressure value 301 progresses under normal conditions. Here, at time 303, an abnormality occurs in car 101, and some of the passengers in car 101 escape to the outside of car 101 through windows, etc., and the remaining passengers evacuate to car 102 (car 2). At this point, the air spring internal pressure value 301 of car 101 gradually decreases, and thereafter, the decrease 304 falls below the threshold 306, which indicates the air spring internal pressure threshold for the decrease. In other words, the decrease of 304 falls outside the range of the threshold 306 that indicates an abnormal value.

[0059] Figure 7(b) shows the behavior of the air spring internal pressure of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 109. In Figure 7(b), the air spring internal pressure (difference) of vehicle 102 (vehicle 2) remains approximately constant over time as an air spring internal pressure value 602 under normal conditions. Here, at time 303, an abnormality occurs in vehicle 101, and some of the passengers of vehicle 101 escape to the outside of vehicle 101 through windows, etc., and the remaining passengers take refuge in vehicle 102 (vehicle 2). As a result, the air spring internal pressure value 602 of vehicle 102 gradually increases. However, the increase 605 in the air spring internal pressure value 602 of vehicle 102 is subsequently maintained at a value smaller than the threshold 307, which indicates the threshold value of the increased air spring internal pressure. That is, the increase 605 falls outside the range of the threshold 307, which indicates the abnormality judgment value.

[0060] Figure 7(c) shows the behavior of the total air spring pressure of the entire train set, including vehicles 101 and 102. The horizontal axis represents elapsed time, and the vertical axis represents the total air spring pressure measured by air spring pressure measuring devices 108 and 109. In Figure 7(c), under normal circumstances, the total air spring pressure of the entire train set remains approximately constant over time as the total air spring pressure value of the entire train set, 606. At time 303, an abnormality occurs in vehicle 101, and some passengers escape to the outside of vehicle 101 through windows, etc., while the remaining passengers evacuate to vehicle 102 (vehicle 2). In this case, the total air spring pressure value of the entire train set, 606, gradually decreases and falls below the threshold 608, which indicates the threshold for the decrease in total air spring pressure across the entire train set.

[0061] Figure 7(d) shows the behavior of the total time difference of the internal air spring pressure of the entire train set, where the horizontal axis represents elapsed time and the vertical axis represents the total time difference of the internal air spring pressure measured by the internal air spring pressure measuring devices 108 and 109. In Figure 7(d), under normal circumstances, the total time difference of the internal air spring pressure of the entire train set remains at a nearly constant value over time as the total internal air spring pressure of the entire train set elapses, as 609. However, at time 303, an abnormality occurs in car 101, and some passengers in car 101 escape to the outside of car 101 through windows, etc., while the remaining passengers evacuate to car 102 (car 2). In this case, the total time difference of the internal air spring pressure of the entire train set 609 decreases rapidly and falls below the threshold 610, which represents the threshold for the decrease in the total internal air spring pressure of the entire train set. Subsequently, the total time difference 609 of the air spring internal pressure of the entire train set remains below the threshold 610, and returns to its original value once the evacuation of passengers from train 101 is complete. At this time, if the state in which the total time difference 609 of the air spring internal pressure of the entire train set remains below the threshold 610 continues for a set time or longer from time 303, and exceeds the duration threshold 611 which indicates the elapsed time threshold for the total time difference of the air spring internal pressure of the entire train set, that is, if the total time difference 609 of the air spring internal pressure of the entire train set remains below the threshold 610 for a continuous period of 611 or more, the total time difference 609 of the air spring internal pressure of the entire train set is determined to be abnormal.

[0062] If, at time 303, an abnormality occurs in vehicle 101, some of the passengers in vehicle 101 escape to the outside of vehicle 101 through the windows, the remaining passengers evacuate to vehicle 102 (vehicle 2), the internal air spring pressure value of vehicle 101 decreases to 301, the internal air spring pressure value of vehicle 102 increases to 602, and all of the following conditions (1) and (2) are met, then an abnormality in vehicle 101 will be detected, and information that an abnormality has occurred in vehicle 101 will be reported to the crew.

[0063] (1) The total internal pressure of the air springs is 606, which is below the total internal pressure threshold of 608. (2) The total internal pressure of the air spring over time, with a difference of 609, is continuously below the threshold of 610 for a duration of 611 or more.

[0064] According to this embodiment, even if an anomaly occurs while passengers are trapped inside a train while it is stopped, and passengers are escaping through windows or other openings, the anomaly inside the train can be detected based on the total value of the air spring internal pressure of all the train cars and the time difference between those values. Furthermore, according to this embodiment, it is possible to detect evacuation behavior in which passengers move from the anomaly-affected car 101 to an adjacent car 102 when an anomaly occurs inside a train car. By notifying the crew of the car with the greatest decrease in air spring internal pressure among the air spring internal pressure values ​​301 and 602 as the car where the anomaly occurred, it becomes possible to respond to the anomaly. The threshold can be set in the same way as in Embodiment 1. [Examples]

[0065] Example 3 detects abnormalities occurring inside a vehicle while it is in motion. When a vehicle is in motion, the air spring internal pressure value is affected not only by fluctuations due to passenger evacuation actions but also by fluctuations due to the vehicle's movement. To address this, Example 3 employs a method of detecting abnormalities inside the vehicle by comparing a base value of the air spring internal pressure obtained by analyzing past driving data and vehicle motion with the measured air spring internal pressure value and based on the comparison result.

[0066] In this embodiment, similar to Embodiment 1, we will primarily describe an example in which an air spring internal pressure measuring device is used as a measuring means for measuring passenger movement. Furthermore, similar to Embodiment 1, other means may be used as the measuring means in this embodiment.

[0067] Figure 8 is a configuration diagram showing an example of the configuration of an in-train abnormality detection system according to Embodiment 3 of the present invention. In this embodiment, an abnormality detection logic 705 is placed in the vehicle information control device 104 instead of the abnormality detection logic 105, an air spring internal pressure base value recording unit 710 that records the base value of the air spring internal pressure is mounted on the vehicle 101 as an air spring internal pressure base value recording device, and the air spring internal pressure base value 711 recorded in the air spring internal pressure base value recording unit 710 is output to the vehicle information control device 104. The other configurations are the same as in Embodiment 1. The processing of the abnormality detection logic 705 will be described below, mainly focusing on the processing that differs from Embodiment 1.

[0068] Figure 9 is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 3 of the present invention. This process is started when the processor activates the anomaly detection logic 705. The processing of step S901 is executed in parallel with step S201, and the processing of step S902 is executed as processing between step S201 and step S203. Furthermore, the processing of steps S201, S203, and S204 is the same as the processing of steps S201, S203, and S204 in Figure 2.

[0069] The anomaly detection logic 705, in parallel with the process of acquiring the current air spring internal pressure value of each vehicle (S201), acquires the air spring internal pressure base value 711 recorded in the air spring internal pressure base value recording unit 710 from the air spring internal pressure base value recording unit 710 (S901).

[0070] Next, the anomaly detection logic 705 calculates the difference between the current air spring internal pressure value and the base value, as well as the time difference, for each vehicle, based on the current air spring internal pressure value for each vehicle obtained in step S201 and the air spring internal pressure base value 711 obtained in step S901 (S902).

[0071] In other words, if an abnormality occurs inside the train while it is in motion, fluctuations in the air spring pressure will occur not only due to passenger movement but also due to the train's motion. Therefore, a process is performed to compare the air spring pressure of each car with the base value.

[0072] Here, the fluctuations in the air spring internal pressure due to the train's motion when no abnormalities occur can be inferred using past data. Specifically, one method is to refer to past data on air spring internal pressure values ​​for the same vehicle, the same travel section, and similar occupancy rates, and then average the obtained data over time for each travel section to determine the base value of the air spring internal pressure. Another method is to analytically solve the vehicle's oscillation and the forces acting on the air springs based on the vehicle's speed, the track's alignment, the occupancy rate, and the vehicle's specifications to determine the base value of the air spring internal pressure.

[0073] Therefore, a reference value for the fluctuation of the air spring internal pressure value due to vehicle operation is determined as the air spring internal pressure value base value 711. The difference and time difference between the actual air spring internal pressure value 901 and the air spring internal pressure value base value 711 are calculated, as well as the difference and time difference between the actual air spring internal pressure value 902 and the air spring internal pressure value base value 711.

[0074] Subsequently, the anomaly detection logic 705 determines, based on the calculation results from step S902, whether the difference in the internal air spring pressure value and the time difference in each vehicle simultaneously exceed the threshold value for increase or decrease, which is the threshold value for determining an anomaly (S203).

[0075] If the anomaly detection logic 705 obtains a negative (NO) result in step S203, it returns to step S201 and repeats the processing of steps S201, S901, S902, and S203.

[0076] On the other hand, if the anomaly detection logic 705 obtains a positive (YES) result in step S203, it outputs the anomaly detection result 110 to the anomaly notification device 103. For example, if an anomaly occurs in vehicle 101 while the train is running, the passenger evacuation action (the evacuation action of passengers in vehicle 101 moving to vehicle 102) causes the air spring internal pressure value 111 in vehicle 101 to decrease below the air spring internal pressure base value 711, and the air spring internal pressure value 112 in vehicle 102 to increase above the air spring internal pressure base value 711. In this case, the air spring internal pressure values ​​111 and 112 fluctuate not only due to the passenger evacuation action but also due to the movement of vehicles 101 and 102. That is, the air spring internal pressure values ​​111 and 112 are affected not only by the fluctuation due to the passenger evacuation action but also by the fluctuation due to the movement of vehicles 101 and 102.

[0077] Therefore, in vehicle 101, the difference and time difference between the air spring internal pressure value 111 and the air spring internal pressure base value 711 fall below the threshold for decrease, while in vehicle 102, the difference and time difference between the air spring internal pressure value 112 and the air spring internal pressure base value 711 exceed the threshold for increase. In this case, the abnormality detection logic 705 outputs an abnormality detection result 110 to the abnormality notification device 103, indicating that an abnormality has occurred in vehicle 101.

[0078] Subsequently, the abnormality notification device 103 notifies the crew that an abnormality has occurred in the vehicle in which the air spring internal pressure value has decreased. For example, if an abnormality occurs inside a vehicle while the train is in motion, the abnormality notification device 103 notifies the crew that the abnormality has occurred in the vehicle in which the air spring internal pressure value has decreased, i.e., vehicle 101.

[0079] Figure 10 is a characteristic diagram illustrating the air spring internal pressure and the difference in air spring internal pressure change time for each vehicle in the train abnormality detection system according to Embodiment 3 of the present invention. Figure 10(a) shows the behavior of the air spring internal pressure of vehicle 101, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 108. In Figure 10(a), the air spring internal pressure (difference) of vehicle 101 (vehicle 1) is normally set to an air spring internal pressure value of 901 and changes over time in accordance with the swaying of vehicle 101 (vehicle 1). Here, while the train is in motion, at time 303, an abnormality occurs in vehicle 101, and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). The air spring internal pressure value 901 of vehicle 101 gradually decreases, and thereafter, the decrease 904, which represents the difference between the air spring internal pressure value 901 and the air spring internal pressure base value 711 (the decrease including high-frequency components due to the movement of passengers), falls below the threshold 906, which represents the air spring internal pressure threshold. In other words, the decrease 904 falls outside the range of the threshold 906, which represents the abnormality detection value.

[0080] Figure 10(b) shows the behavior of the air spring internal pressure of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 109. In Figure 10(b), the air spring internal pressure (difference) of vehicle 102 (vehicle 2) changes over time in accordance with the movement of vehicle 102 (vehicle 2), with the air spring internal pressure value 902 being normal. Here, while the train is running, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). The air spring internal pressure value 902 of vehicle 102 gradually increases, and thereafter, the increase 905, which represents the difference between the air spring internal pressure value 902 and the air spring internal pressure base value 711 (an increase including high-frequency components due to passenger movement), exceeds the threshold 907, which represents the air spring internal pressure threshold. In other words, the increase of 904 falls outside the range of the threshold 907 that indicates an abnormal value.

[0081] Figure 10(c) shows the behavior of the time difference in air spring internal pressure reduction of vehicle 101, where the horizontal axis represents elapsed time and the vertical axis represents the time difference in air spring internal pressure reduction measured by the air spring internal pressure value measuring device 108. In Figure 10(c), the time difference in air spring internal pressure reduction of vehicle 101 (vehicle 1) remains at a roughly constant value over time as the air spring internal pressure value reduction time difference 908 progresses. Here, while the train is running, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). The time difference in air spring internal pressure value reduction time difference 908 of vehicle 101 decreases rapidly and falls below the threshold 909, which indicates the threshold for the time difference in air spring internal pressure value reduction time difference. Subsequently, the air spring internal pressure value reduction time difference 908 remains below the threshold 909 and returns to approximately its original value when the evacuation of the passengers from vehicle 101 is complete. In this case, if the difference in time 908 of the decrease in air spring internal pressure value remains below the threshold 909 for a set time or longer from time 303, and exceeds the duration threshold 910 which indicates the elapsed time threshold for the decrease in air spring internal pressure value, that is, if the difference in time 908 of the decrease in air spring internal pressure value remains below the threshold 909 for a continuous period of 910 or more, the difference in time 908 of the decrease in air spring internal pressure value of the vehicle 101 is determined to be abnormal.

[0082] Figure 10(d) shows the behavior of the time difference in air spring pressure increase of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the time difference in air spring pressure increase measured by the air spring pressure measuring device 109. In Figure 3(d), the time difference in air spring pressure value of vehicle 102 (vehicle 2) remains at a roughly constant value as time progresses, as the time difference in air spring pressure increase 911. Here, while the train is running, at time 303, an abnormality occurs in vehicle 101 and the passengers of vehicle 101 evacuate to vehicle 102 (vehicle 2). As the time difference in air spring pressure decrease 908 of vehicle 101 decreases rapidly, the time difference in air spring pressure increase 911 of vehicle 102 increases rapidly and exceeds the threshold 912 which indicates the threshold for the time difference in air spring pressure increase. Subsequently, the difference in air spring internal pressure increase time 911 continues to exceed the threshold 912, and returns to approximately its original value once the evacuation of passengers from vehicle 101 is complete. At this time, if the difference in air spring internal pressure increase time 911 continues to exceed the threshold 912 for a set time or longer from time 303, and exceeds the duration threshold 913 which indicates the threshold for the elapsed time of the air spring internal pressure, that is, if the difference in air spring internal pressure increase time 911 continuously exceeds the threshold 912 for a duration threshold 913 or longer, the difference in air spring internal pressure increase time 911 of vehicle 102 is determined to be abnormal.

[0083] If, while the train is in motion, at time 303, an abnormality occurs in car 101, passengers in car 101 evacuate to car 102, the internal air spring pressure value of car 101 decreases by 901, the internal air spring pressure value of car 102 increases by 902, and all of the following conditions (1) to (4) are met, then an abnormality in car 101 will be detected, and the crew will be notified that an abnormality has occurred in car 101.

[0084] (1) The internal air spring pressure value 901 of vehicle 101 is below the internal air spring pressure threshold value 906 of vehicle 101. (2) The internal air spring pressure value 902 of vehicle 102 exceeds the internal air spring pressure threshold value 907 of vehicle 102. (3) The time difference 908 of the decrease in the internal pressure value of the air spring of vehicle 101 is continuously below the threshold 909 for a duration of 910 or more. (4) The time difference 911 of the increase in the internal pressure value of the air spring of the vehicle 102 continuously exceeds the threshold 912 for a duration of 913 or more.

[0085] According to this embodiment, when an abnormality occurs in a vehicle while the train is running, it becomes possible to detect the evacuation action of passengers moving from the vehicle 101 where the abnormality occurred to the adjacent vehicle 102, and by notifying the crew of the vehicle 101 where the abnormality occurred, it becomes possible to respond to the abnormality. The threshold can be set in the same way as in Embodiment 1. In addition, even if conditions (1) to (2) of the above conditions (1) to (4) are met, it is possible to detect that an abnormality has occurred in vehicle 101 as long as the air spring internal pressure values ​​901 and 902 do not contain errors such as sudden noise or outliers. [Examples]

[0086] Example 4 describes a method for detecting abnormalities while the train is stopped at a station and the doors are open. When the train is stopped at a station and the doors are open, a large-scale evacuation of passengers is expected due to their evacuation actions. Because the doors are open, the method described in Example 2, which uses the total internal air spring pressure value of the entire vehicle, cannot determine whether or not an abnormality has occurred. To address this, Example 4 presents an abnormality detection method that uses a base value of internal air spring pressure obtained by processing past driving data.

[0087] In this embodiment, similar to Embodiment 1, we will primarily describe an example in which an air spring internal pressure measuring device is used as a measuring means for measuring passenger movement. Furthermore, similar to Embodiment 1, other means may be used as the measuring means in this embodiment.

[0088] Figure 11 is a configuration diagram showing an example of the configuration of an in-train abnormality detection system according to Embodiment 4 of the present invention. In this embodiment, an abnormality detection logic 1005 is placed in the vehicle information control device 104 instead of the abnormality detection logic 105, an air spring internal pressure base value recording unit 1010 that records the base value of the air spring internal pressure is mounted on the vehicle 101, and the air spring internal pressure base value 1011 recorded in the air spring internal pressure base value recording unit 1010 is output to the vehicle information control device 104. The other configurations are the same as in Embodiment 1. The processing of the abnormality detection logic 1005 will be described below, mainly focusing on the processing that differs from Embodiment 1.

[0089] Figure 12 is a flowchart illustrating an example of the processing of the anomaly detection logic according to Embodiment 4 of the present invention. This process starts when the processor activates the anomaly detection logic 1005. Note that, unlike the process in Figure 2, the process of step S1201 is executed in parallel with step S201, the process of step S1202 is executed between step S201 and step S203, and the processes of steps S1203 to S1205 are executed between step S203 and step S204. Also, the processes of steps S201, S203, and S204 are the same as the processes of steps S201, S203, and S204 in Figure 2.

[0090] The anomaly detection logic 1005, in parallel with the process of acquiring the current air spring internal pressure value of each vehicle (step S201), acquires the air spring internal pressure base value 1011 recorded in the air spring internal pressure base value recording unit 1010 from the air spring internal pressure base value recording unit 1010 (S1201).

[0091] Next, the anomaly detection logic 1005 calculates the difference between the current air spring internal pressure value and the base value, as well as the time difference, for each vehicle, based on the current air spring internal pressure value for each vehicle obtained in step S201 and the air spring internal pressure base value 1011 obtained in step S1201 (S1202).

[0092] In other words, if an abnormality occurs inside the train when the doors are open, passengers may all escape through the doors to the outside of the train for evacuation. On the other hand, the number of passengers boarding a train experiencing an abnormality from a station will decrease compared to normal times. At this time, the air spring internal pressure value will decrease more significantly than the fluctuation caused by passengers boarding and alighting when the doors are open under normal circumstances. In this case, as in Example 3, if no abnormality occurs, the fluctuation in the air spring internal pressure value due to passengers boarding and alighting when the train doors are open can be inferred using past data. Therefore, based on this inference, the fluctuation in the air spring internal pressure value due to train operation is determined as the air spring internal pressure base value, and the difference and time difference between the actual air spring internal pressure value and the air spring internal pressure base value are calculated.

[0093] In this process, a reference value for the fluctuation of the air spring internal pressure value due to vehicle operation is determined as the air spring internal pressure value base value 711. The difference and time difference between the actual air spring internal pressure value 901 and the air spring internal pressure value base value 711 are calculated, as well as the difference and time difference between the actual air spring internal pressure value 902 and the air spring internal pressure value base value 711.

[0094] Subsequently, the anomaly detection logic 1005 determines, based on the calculation results of step S1202, whether the difference in the internal pressure value of the air spring in each vehicle and the time difference simultaneously exceed the threshold value for increase or decrease, which are the threshold values ​​for determining anomalies (S203).

[0095] If the anomaly detection logic 1005 obtains a positive (YES) result in step S203, it proceeds to the processing of step S204; if it obtains a negative (NO) result in step S203, it proceeds to the processing of step S1203.

[0096] If the abnormality detection logic 1005 obtains a negative (NO) result in step S203, it sums the air spring internal pressure values ​​and air spring internal pressure base values ​​of all vehicles in the train set (S1203). For example, if vehicle 101 and vehicle 102 are in a train set, the abnormality detection logic 1005 sums the air spring internal pressure values ​​111 and 112 of each vehicle obtained in step S201 as the air spring internal pressure values ​​of all vehicles in the train set, and obtains the air spring internal pressure base value 1011 from the air spring internal pressure base value recording unit 1010 and sums it up as the air spring internal pressure base value of all vehicles in the train set.

[0097] Next, the anomaly detection logic 1005 calculates the difference in air spring internal pressure values ​​and the time difference for all vehicles in the train set, based on the calculation results of step S1203 (S1204). At this time, the anomaly detection logic 1005 compares the sum of the air spring internal pressure base values ​​1011 obtained in step S1201 with the sum of the air spring internal pressure values ​​111 and 112 obtained in the previous processing loop (the previous measurement cycle), and calculates the comparison result showing the difference between the two as the time difference of the sum of the air spring internal pressure values.

[0098] Next, the anomaly detection logic 1005 determines, based on the calculation results of step S1204, whether the difference and time difference of the air spring internal pressure values ​​(total value) of all vehicles in the train set exceed a threshold (S1205).

[0099] If the anomaly detection logic 1005 obtains a negative (NO) result in step S1205, it returns to steps S201 and S1201, and repeats the processing in steps S201 to S203 and the processing in S1201.

[0100] On the other hand, if the anomaly detection logic 1005 obtains a positive (YES) result in step S1203, it outputs an anomaly detection result 110 to the anomaly notification device 103. For example, if an anomaly occurs in vehicle 101, and some passengers in vehicle 101 escape through windows or the like, and the remaining passengers trapped inside vehicle 101 move from vehicle 101 to vehicle 102, the number of people moving due to the passenger evacuation action will be less than in Embodiment 1. Therefore, provided that the total value of the internal air spring pressure of the entire vehicle exceeds the threshold for the decrease, the anomaly detection logic 1005 outputs an anomaly detection result 110 to the anomaly notification device 103 indicating that an anomaly has occurred in the train set.

[0101] Subsequently, the abnormality notification device 103 notifies the crew that an abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased (S204). For example, if an abnormality occurs in a train set, the abnormality notification device 103 notifies the crew that the abnormality has occurred in the vehicle in which the internal air spring pressure value has decreased.

[0102] Figure 13 is a characteristic diagram illustrating the air spring internal pressure and the difference in air spring internal pressure decrease time for each car and train set in the train abnormality detection system according to Embodiment 4 of the present invention. Figure 13(a) shows the behavior of the air spring internal pressure of car 101, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 108. In Figure 13(a), the air spring internal pressure (difference) of car 101 (car 1) remains at a substantially constant value of 1201 over time under normal conditions. Here, at time 303, when the doors open, an abnormality occurs in car 101, and the passengers of car 101 all escape out of the car through the doors, and some of the passengers of car 102 (car 2) also escape out of the car through the doors, the air spring internal pressure value 1201 of car 101 gradually decreases. The internal air spring pressure value 1201 of vehicle 101 gradually increases by a decrease of 1202 from the base value 1011 of the internal air spring pressure, and then becomes approximately constant.

[0103] Figure 13(b) shows the behavior of the air spring internal pressure of vehicle 102, where the horizontal axis represents elapsed time and the vertical axis represents the air spring internal pressure measured by the air spring internal pressure value measuring device 109. In Figure 13(b), the air spring internal pressure (difference) of vehicle 102 (vehicle 2) remains approximately constant over time as an air spring internal pressure value of 1204 under normal conditions. Here, at time 303, when the door is opened, an abnormality occurs in vehicle 101, and the passengers of vehicle 101 all escape out of the vehicle through the door. When some of the passengers of vehicle 102 (vehicle 2) also escape out of the vehicle through the door, the air spring internal pressure value 1204 of vehicle 102 gradually decreases. However, the decrease 1205 from the air spring internal pressure base value 1011 of vehicle 102 gradually increases, but is smaller than the decrease 1202, and thereafter becomes approximately constant.

[0104] Figure 13(c) shows the behavior of the total air spring pressure of the entire train set, including vehicles 101 and 102. The horizontal axis represents elapsed time, and the vertical axis represents the total air spring pressure of the entire train set as measured by air spring pressure measuring devices 108 and 109. In Figure 13(c), under normal circumstances, the total air spring pressure of the entire train set remains approximately constant over time, with a total value of 1206. However, at time 303, when the doors open, an abnormality occurs in vehicle 101, causing all passengers in vehicle 101 to escape through the doors. When some passengers in vehicle 102 (vehicle 2) also escape through the doors, the total air spring pressure of the entire train set, 1206, gradually decreases. The decrease of 1207 from the base value of 1011 falls below the threshold 1208, which indicates the total air spring pressure threshold for the entire train set, and then becomes approximately constant.

[0105] Figure 13(d) shows the behavior of the time difference in the decrease of air spring internal pressure for the entire train set, where the horizontal axis represents elapsed time and the vertical axis represents the time difference in the decrease of air spring internal pressure measured by the air spring internal pressure measuring devices 108 and 109. In Figure 13(d), the time difference in the decrease of air spring internal pressure for the entire train set remains approximately constant over time under normal conditions, as the time difference in the decrease of air spring internal pressure for the entire train set 1209. Here, at time 303, when the doors open, an abnormality occurs in car 101, and the passengers of car 101 all escape out of the car through the doors, and some of the passengers of car 102 (car 2) also escape out of the car through the doors, the time difference in the decrease of air spring internal pressure for the entire train set 1209 decreases rapidly and falls below the threshold 1210, which indicates the threshold for the time difference in the decrease of air spring internal pressure for the entire train set. Subsequently, the time difference 1209 of the decrease in the internal air spring pressure value of the entire train set remains below the threshold 1210, and returns to its original value once the evacuation of passengers from train 101 is complete. At this time, if the state in which the time difference 1209 of the decrease in the internal air spring pressure value of the entire train set remains below the threshold 1210 continues for a set time or longer from time 303, and exceeds the duration threshold 1211 which indicates the elapsed time threshold for the decrease in the internal air spring pressure value of the entire train set, that is, if the time difference 1209 of the decrease in the internal air spring pressure value of the entire train set remains below the threshold 1210 for a continuous period of 1211 or more, the total time difference 1209 of the internal air spring pressure of the entire train set is determined to be abnormal.

[0106] At time 303, when the doors open, if an abnormality occurs in vehicle 101, all passengers in vehicle 101 escape out of the vehicle through the doors, some passengers in vehicle 102 (vehicle 2) escape out of the vehicle through the doors, the air spring internal pressure value of vehicle 101 decreases to 1201, the air spring internal pressure value of vehicle 102 decreases to 1204, and all of the following conditions (1) and (2) are met, then it will be detected that an abnormality has occurred in vehicle 101, and the crew will be notified that an abnormality has occurred in vehicle 101.

[0107] (1) The total internal air spring pressure of the entire train set is 1206, which is below the total internal air spring pressure threshold of 1208. (2) The time difference of the decrease in the internal air spring pressure value of the entire train set, 1209, is continuously below the threshold of 1210 for a duration of 1211 or more.

[0108] According to this embodiment, when a door is opened, an abnormality occurs inside the vehicle, and it becomes possible to detect an evacuation action in which passengers simultaneously escape from the vehicle 101 where the abnormality occurred. By notifying the crew of the vehicle 101, which has the lowest air spring internal pressure value among the air spring internal pressure values ​​1201 and 1204, as the vehicle where the abnormality occurred, it becomes possible to respond to the abnormality. The threshold can be set in the same way as in Embodiment 1.

[0109] In Examples 1 to 4, air spring internal pressure measuring devices 108 and 109 were used as multiple measuring means to measure the movement of passengers in each vehicle. A vehicle information control device 104 was used as an abnormality detection means to detect that an abnormality has occurred in the train when the measured value of at least one of the multiple measuring means exceeds the range of the abnormality detection value, and an abnormality notification device 103 was used as an abnormality notification means to notify the train that an abnormality has occurred when the abnormality detection means detects that an abnormality has occurred in the train. However, passenger movement can also be measured as a change in the number of passengers.

[0110] In this case, the multiple measurement means include multiple passenger count measuring devices that measure the fluctuation in the number of passengers in each vehicle as passenger movement, and the anomaly detection means detects that an anomaly has occurred in the train when the measured value of at least one of the multiple passenger count measuring devices falls outside the range of an anomaly judgment value indicating the acceptable range of fluctuation in the number of passengers. For example, the number of passengers is calculated by dividing the load obtained from the air spring internal pressure value 301 (load acting on the air spring) (load acting on the vehicle when passengers are on board) by the average weight of the passengers, and when the calculated decrease in the number of passengers (corresponding to decrease 304) falls outside the passenger threshold corresponding to the threshold 306, it is detected that an anomaly has occurred in the train, as the decrease in the number of passengers has fallen outside the range of an anomaly judgment value indicating the acceptable range of fluctuation in the number of passengers. In this way, when the fluctuation in the number of passengers in any vehicle falls outside the range of an anomaly judgment value indicating the acceptable range of fluctuation in the number of passengers, it is possible to detect that an anomaly has occurred in the train.

[0111] The multiple passenger count measurement device can be configured to include multiple air spring internal pressure value measuring devices 108, 109 that measure the internal air spring pressure value acting on the air springs in each vehicle, and a vehicle information control device 104 that calculates the number of passengers in each vehicle (a numerical value obtained by dividing the load acting on the vehicle by the average weight of the passengers) based on the measured values ​​(load) of each of the multiple air spring internal pressure value measuring devices 108, 109 and the average weight of the passengers.

[0112] Furthermore, multiple passenger counting devices can be configured to measure a first absolute value (the absolute value of the increase and decrease in the change in the number of passengers within the set time) that indicates the change in the number of passengers in each car within a set time, and a second absolute value (the absolute value of the increase and decrease in the time difference of the change in the number of passengers within the set time) that indicates the change in the number of passengers in each car within a set time. The anomaly detection means can be configured to detect that an anomaly has occurred in the train if the first absolute value of the measured value of at least one of the multiple passenger counting devices exceeds a first threshold that falls within the range of anomaly judgment values, and the second absolute value of the measured value of one of the passenger counting devices exceeds a second threshold that falls within the range of anomaly judgment values.

[0113] The multiple passenger count measurement device can employ a configuration that includes multiple tire pressure measurement devices that measure the tire pressure acting on the tires in each vehicle, and a passenger count calculation device that calculates the number of passengers in each vehicle based on the measured values ​​of each of the multiple tire pressure measurement devices and the average weight of the passengers.

[0114] The multiple passenger count measurement device can employ a configuration that includes multiple spring compression force measuring devices that measure the compression force of springs mounted on the vehicle suspension system in each vehicle, and a passenger count calculation device that calculates the number of passengers in each vehicle based on the measured values ​​of each of the multiple spring compression force measuring devices and a proportionality constant that identifies the number of passengers.

[0115] The multiple passenger count measurement device can employ a configuration that includes multiple concentration measuring devices for measuring oxygen concentration or carbon dioxide concentration in each vehicle, and a passenger count calculation device that calculates the number of passengers in each vehicle based on the measured values ​​of each of the multiple concentration measuring devices and a proportionality constant that identifies the number of passengers.

[0116] The multiple passenger count measurement device can employ a configuration that includes multiple pressure measuring devices that measure the pressure acting on pressure-sensing mats (mats containing piezoelectric elements) placed in the aisles of each vehicle, and a passenger count calculation device that calculates the number of passengers in each vehicle based on the fluctuations in the measured values ​​of each of the multiple pressure measuring devices.

[0117] Multiple passenger counting devices can employ a configuration that includes a passenger counting device that irradiates light (infrared) towards the target (passengers) passing through the side doors or inter-car doors within each vehicle, and calculates the number of passengers in each vehicle based on the fluctuations in the amount of incident light reflected from the target.

[0118] It should be noted that the present invention is not limited to the embodiments described above, but includes various modifications and equivalent configurations within the spirit of the attached claims. For example, the embodiments described above are explained in detail for the purpose of clearly illustrating the present invention, and the present invention is not necessarily limited to those having all the configurations described.

[0119] Furthermore, each of the aforementioned configurations and functions may be implemented in hardware, for example, by designing them as integrated circuits, or in software, by having a processor interpret and execute programs that realize each function.

[0120] Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or on recording media such as IC (Integrated Circuit) cards, SD (Secure Digital) cards, and DVDs (Digital Versatile Discs). [Explanation of symbols]

[0121] 101, 102 Vehicle, 103 Anomaly notification device, 104 Vehicle information control device, 105 Anomaly detection logic, 106, 107 Air spring, 108, 109 Air spring internal pressure value measuring device, 405 Anomaly detection logic, 705 Anomaly detection logic, 710 Air spring internal pressure base value recording unit, 1005 Anomaly detection logic, 1010 Air spring internal pressure base value recording unit

Claims

1. Multiple measuring means for measuring passenger movement in each car of a train consisting of multiple connected cars, The system includes an anomaly detection means that compares the measured value of each of the plurality of measuring means with an anomaly determination value, and detects that an anomaly has occurred in the train when the measured value of at least one of the plurality of measuring means exceeds the range of the anomaly determination value, The aforementioned anomaly detection means is The vehicle information control device includes a vehicle information control device that acquires each measured value from each measuring means in each vehicle, and calculates the difference in the internal pressure value of the air spring that shows the change in each measured value over time based on the acquired measured values. The aforementioned vehicle information control device is A train anomaly detection system characterized in that it detects an anomaly in one of the vehicles when four conditions are met, including a first condition in which the decrease in the difference in the measured value in any one of the plurality of vehicles falls below a first measurement threshold, and a second condition in which the increase in the difference in the measured value in an adjacent vehicle adjacent to the one vehicle exceeds a second measurement threshold.

2. In the train anomaly detection system according to claim 1, Each of the aforementioned plurality of measuring means is The system includes an air spring internal pressure measuring device for measuring the internal air spring pressure acting on the air springs in each of the aforementioned vehicles, The aforementioned anomaly detection means is The vehicle information control device includes an air spring internal pressure measurement device in each vehicle that acquires the internal air spring internal pressure values ​​measured by the respective air spring internal pressure measurement devices, and calculates the difference in the internal air spring internal pressure values ​​that shows the change in the internal air spring internal pressure values ​​over time based on the acquired internal air spring internal pressure values. The aforementioned vehicle information control device is A train anomaly detection system characterized by detecting an anomaly in one of the vehicles when two conditions are met, including a first condition in which the decrease in the difference in the internal air spring pressure value in any one of the plurality of vehicles falls below a first internal air spring pressure threshold, and a second condition in which the increase in the difference in the internal air spring pressure value in an adjacent vehicle adjacent to the one vehicle exceeds a second internal air spring pressure threshold.

3. In the train anomaly detection system according to claim 2, The vehicle information control device further calculates the time difference of the internal pressure value of the air springs, which shows the change in the internal pressure value of each air spring for each measurement cycle. A train anomaly detection system characterized in that it detects an anomaly in one vehicle when four conditions are met, including the first condition, the second condition, a third condition in which the time difference of the internal air spring pressure value in one vehicle is continuously below a first internal air spring pressure value time difference threshold by a first duration threshold or more, and a fourth condition in which the time difference of the internal air spring pressure value in an adjacent vehicle is continuously above a second internal air spring pressure value time difference threshold by a second duration threshold or more.

4. In the train anomaly detection system according to claim 3, The aforementioned vehicle information control device is If the above four conditions are not met, the air spring internal pressure values ​​obtained from the air spring internal pressure measurement devices of all vehicles belonging to the train are totaled, and based on the total value of the air spring internal pressure values, the difference in the total air spring internal pressure values, which shows the change in the total air spring internal pressure values ​​over time, and the difference in the total air spring internal pressure values ​​over time, which shows the change in the total air spring internal pressure values ​​for each measurement cycle are calculated. A train anomaly detection system characterized by detecting an anomaly in one vehicle when two conditions are met, including a fifth condition in which the difference in the total internal pressure of the air springs falls below a threshold for the decrease in the total internal pressure of the air springs, and a sixth condition in which the time difference in the total internal pressure of the air springs falls below a threshold for the time difference in the total internal pressure of the air springs for a continuous period of time or longer than a third duration threshold.

5. In the train anomaly detection system according to claim 1, Each of the aforementioned plurality of measuring means is The system includes an air spring internal pressure measuring device for measuring the internal air spring pressure acting on the air springs in each of the aforementioned vehicles, The aforementioned anomaly detection means is An air spring internal pressure base value recording device that records the air spring internal pressure base value which serves as a reference for the aforementioned air spring internal pressure value, The vehicle information control device includes: an air spring internal pressure value obtained from each air spring internal pressure value measuring device in each vehicle, an air spring internal pressure base value obtained from the air spring internal pressure base value recording device, and a vehicle information control device that calculates the difference in air spring internal pressure values ​​showing the change over time and the time difference in air spring internal pressure values ​​showing the change over each measurement cycle based on the difference between the obtained air spring internal pressure values ​​and the air spring internal pressure base value; The aforementioned vehicle information control device is A train anomaly detection system characterized by detecting an anomaly in one of the vehicles when four conditions are met, including: a first condition in which the decrease in the difference between the air spring internal pressure value and the air spring internal pressure base value in any one of the plurality of vehicles falls below a first air spring internal pressure threshold; a second condition in which the increase in the difference between the air spring internal pressure value and the air spring internal pressure base value in an adjacent vehicle adjacent to the one vehicle exceeds a second air spring internal pressure threshold; a third condition in which the time difference of the air spring internal pressure value decrease in the one vehicle is continuously below the air spring internal pressure value decrease time difference threshold for a period of time or longer; and a fourth condition in which the time difference of the air spring internal pressure value increase in the adjacent vehicle is continuously above the air spring internal pressure value increase time difference threshold for a period of time or longer.

6. In the train anomaly detection system according to claim 5, The aforementioned vehicle information control device is If the above four conditions are not met, the air spring internal pressure values ​​obtained from the air spring internal pressure value measuring device and the air spring internal pressure base value obtained from the air spring internal pressure base value recording device of all vehicles belonging to the train are totaled, and based on the total value of the total air spring internal pressure values, the difference in the total air spring internal pressure values, which shows the change in the total air spring internal pressure values ​​over time, and the difference in the total air spring internal pressure values ​​over time, which shows the change in the total air spring internal pressure values ​​for each measurement cycle are calculated. A train anomaly detection system characterized by detecting an anomaly in one vehicle when two conditions are met, including a fifth condition in which the difference in the total internal pressure of the air springs is below a threshold for the decrease in the total internal pressure of the air springs, and a sixth condition in which the time difference in the decrease in the total internal pressure of the air springs among the time difference in the total internal pressure of the air springs is continuously below a threshold for the decrease in the time difference of the total internal pressure of the air springs for a period of time or longer.

7. Multiple measuring means for measuring passenger movement in each car of a train consisting of multiple connected cars, The system includes an anomaly detection means that compares the measured value of each of the plurality of measuring means with an anomaly determination value, and detects that an anomaly has occurred in the train when the measured value of at least one of the plurality of measuring means exceeds the range of the anomaly determination value, The aforementioned anomaly detection means is The vehicle information control device includes a vehicle information control device that acquires each measured value from each measuring means in each vehicle, and calculates the time difference of the measured values, which shows the change in each measured value for each measurement cycle, based on the acquired measured values. The aforementioned vehicle information control device is A train anomaly detection system characterized in that it detects an anomaly in one of the vehicles when two conditions are met, including a first condition in which the time difference of the measured value in any one of the plurality of vehicles is continuously below a first time difference threshold of the measured value by a first duration threshold or more, and a second condition in which the time difference of the measured value in an adjacent vehicle adjacent to the one vehicle is continuously above a second time difference threshold of the measured value by a second duration threshold or more.

8. In the train anomaly detection system according to claim 7, Each of the aforementioned plurality of measuring means is The system includes an air spring internal pressure measuring device for measuring the internal air spring pressure acting on the air springs in each of the aforementioned vehicles, The aforementioned anomaly detection means is The vehicle information control device includes an air spring internal pressure measurement device in each vehicle that acquires the internal air spring internal pressure values ​​measured by each air spring internal pressure measurement device, and calculates the time difference of the internal air spring internal pressure values ​​that shows the change in the internal air spring internal pressure values ​​for each measurement cycle based on the acquired internal air spring internal pressure values. The aforementioned vehicle information control device is A train anomaly detection system characterized by detecting an anomaly in one of the vehicles when two conditions are met, including a first condition in which the time difference of the internal air spring pressure value in any one of the plurality of vehicles is continuously below a first internal air spring pressure value time difference threshold by a first duration threshold or more, and a second condition in which the time difference of the internal air spring pressure value in an adjacent vehicle is continuously above a second internal air spring pressure value time difference threshold by a second duration threshold or more.

9. A method for detecting an anomaly inside a train, comprising a train anomaly detection system with multiple measurement means and an anomaly detection means, Each of the aforementioned multiple measuring means includes a measurement step of measuring the movement of passengers in each car of a train consisting of multiple connected cars, The abnormality detection means includes an abnormality detection step in which it compares the measured value of each of the plurality of measuring means with an abnormality determination value, and detects that an abnormality has occurred in the train when the measured value of at least one of the plurality of measuring means exceeds the range of the abnormality determination value. A train abnormality detection method characterized in that, in the abnormality detection step, the difference in measured values ​​indicating the time change of each measured value is calculated based on each of the plurality of measuring means measured in the measurement step, and if two conditions are met from the calculated result, including a first condition in which the decrease in the difference in the internal air spring pressure value in any one of the plurality of vehicles is below a first internal air spring pressure threshold, and a second condition in which the increase in the difference in the internal air spring pressure value in an adjacent vehicle adjacent to the one vehicle exceeds a second internal air spring pressure threshold, an abnormality in one of the vehicles is detected.

10. In the train abnormality detection method described in claim 9, Each of the aforementioned plurality of measuring means is In the measurement step, the internal air spring pressure value acting on the air spring in each vehicle is measured. The aforementioned anomaly detection means is In the abnormality detection step, based on the air spring internal pressure values ​​measured by each of the plurality of measuring means in the measurement step, the difference in air spring internal pressure values ​​showing the change in each air spring internal pressure value over time and the time difference in air spring internal pressure values ​​showing the change in each air spring internal pressure value for each measurement cycle are calculated, and from the calculated results, a first condition is set in which the decrease showing the difference in air spring internal pressure values ​​in any one of the plurality of vehicles falls below a first air spring internal pressure threshold, and the air spring internal pressure values ​​in adjacent vehicles adjacent to the one vehicle A method for detecting abnormalities in a train, characterized in that an abnormality in one vehicle is detected when four conditions are met, including: a second condition in which the increase representing the difference in internal pressure values ​​exceeds a second air spring internal pressure threshold; a third condition in which the time difference of the air spring internal pressure value in one vehicle is continuously below a first air spring internal pressure value time difference threshold for a period of time or longer; and a fourth condition in which the time difference of the air spring internal pressure value in an adjacent vehicle is continuously above a second air spring internal pressure value time difference threshold for a period of time or longer.

11. In the train abnormality detection method according to claim 10, The aforementioned anomaly detection means is In the abnormality detection step, if the four conditions are not met, the internal air spring pressure values ​​of all vehicles belonging to the train are totaled, and based on the total internal air spring pressure values, the difference in the total internal air spring pressure values, which shows the change in the total internal air spring pressure values ​​over time, and the difference in the total internal air spring pressure values ​​over time, which shows the change in the total internal air spring pressure values ​​for each measurement cycle, are calculated, and if two conditions are met from the calculated results, including a fifth condition that the difference in the total internal air spring pressure values ​​is below the threshold for the decrease in the total internal air spring pressure, and a sixth condition that the difference in the total internal air spring pressure values ​​over time is continuously below the threshold for the difference in the total internal air spring pressure values ​​over time for a period of time equal to or longer than a third duration threshold, an abnormality is detected in one of the vehicles.

12. In the train abnormality detection method described in claim 9, The abnormality detection means further includes a recording step of recording an air spring internal pressure base value, which serves as a reference for the air spring internal pressure value, in an air spring internal pressure base value recording device. Each of the aforementioned plurality of measuring means is In the measurement step, the internal air spring pressure value acting on the air spring in each vehicle is measured. The aforementioned anomaly detection means is In the abnormality detection step, the following are obtained: each air spring internal pressure value measured by each of the plurality of measuring means in the measurement step and the air spring internal pressure base value recorded in the recording step; the difference between the obtained air spring internal pressure value and the air spring internal pressure base value is used to calculate the difference in air spring internal pressure value showing the change in each air spring internal pressure value over time and the difference in air spring internal pressure value over time showing the change in each air spring internal pressure value for each measurement cycle; and from the calculated results, a first condition is met in which the decrease showing the difference between the air spring internal pressure value and the air spring internal pressure base value in any one of the plurality of vehicles falls below a first air spring internal pressure threshold, and adjacent to the one vehicle A method for detecting abnormalities in a train, characterized in that an abnormality in one vehicle is detected when four conditions are met, including: a second condition in which the increase in the difference between the air spring internal pressure value and the air spring internal pressure base value in an adjacent vehicle exceeds a second air spring internal pressure threshold; a third condition in which the time difference in the air spring internal pressure value within the time difference of the air spring internal pressure value within one vehicle is continuously below the air spring internal pressure value decrease time difference threshold by a first duration threshold or more; and a fourth condition in which the time difference in the air spring internal pressure value within the time difference of the air spring internal pressure value within the adjacent vehicle is continuously above the air spring internal pressure value increase time difference threshold by a second duration threshold or more.

13. In the train abnormality detection method according to claim 12, The aforementioned anomaly detection means is In the abnormality detection step, if the four conditions are not met, the method for detecting an abnormality in a train is characterized by: summing the air spring internal pressure values ​​of all vehicles belonging to the train and the air spring internal pressure base value obtained from the air spring internal pressure base value recording device; calculating the difference in the total air spring internal pressure value, which shows the change in the total air spring internal pressure value over time, and the difference in the total air spring internal pressure value over time, which shows the change in the total air spring internal pressure value for each measurement cycle, based on the summed total air spring internal pressure value; and detecting an abnormality in one of the vehicles if two conditions are met from the calculated results, including a fifth condition that the difference in the total air spring internal pressure value is below the threshold for the decrease in total air spring internal pressure value, and a sixth condition that the difference in the time difference of the decrease in air spring internal pressure value among the difference in the time difference of the decrease in air spring internal pressure value is continuously below the threshold for the difference in the time difference of the decrease in air spring internal pressure value for a period of time of a third duration threshold or longer.

14. In the train abnormality detection method described in claim 9, Each of the aforementioned plurality of measuring means is In the measurement step, the internal air spring pressure value acting on the air spring in each vehicle is measured. The aforementioned anomaly detection means is A train abnormality detection method characterized in that, in the abnormality detection step, based on the air spring internal pressure values ​​measured by each of the plurality of measuring means in the measurement step, the difference in air spring internal pressure values ​​showing the change in each air spring internal pressure value over time and the difference in air spring internal pressure values ​​showing the change in each air spring internal pressure value for each measurement cycle are calculated, and if two conditions are met from the calculated results, an abnormality is detected in one of the vehicles, including a first condition in which the decrease showing the difference in air spring internal pressure values ​​in any one of the plurality of vehicles falls below a first air spring internal pressure threshold, and a second condition in which the increase showing the difference in air spring internal pressure values ​​in an adjacent vehicle adjacent to the one vehicle exceeds a second air spring internal pressure threshold.

15. A method for detecting an anomaly inside a train, comprising a train anomaly detection system with multiple measurement means and an anomaly detection means, Each of the aforementioned multiple measuring means includes a measurement step of measuring the movement of passengers in each car of a train consisting of multiple connected cars, The abnormality detection means includes an abnormality detection step in which it compares the measured value of each of the plurality of measuring means with an abnormality determination value, and detects that an abnormality has occurred in the train when the measured value of at least one of the plurality of measuring means exceeds the range of the abnormality determination value. A method for detecting abnormalities in a train, characterized in that, in the abnormality detection step, the time difference of the measured values, which indicates the change in each of the measured values ​​for each measurement cycle, is calculated based on each of the multiple measurement means measured in the measurement step, and if two conditions are met from the calculated result, an abnormality is detected in one of the vehicles, including a first condition in which the time difference of the measured values ​​in any one of the multiple vehicles is continuously below a first time difference threshold of a first duration threshold or more, and a second condition in which the time difference of the measured values ​​in an adjacent vehicle adjacent to the one vehicle is continuously above a second time difference threshold of a second duration threshold or more.

Images