JP6055149B2 - Temperature abnormality detection system, temperature abnormality detection method - Google Patents

Description

  The present invention relates to a technique for accurately detecting that a temperature abnormality has occurred in a monitoring target part of a moving body formed from one or more vehicles such as a track traveling vehicle.

  In a vehicle that travels on a track such as a railway vehicle, axle bearings that rotatably support the shaft are respectively attached to both ends of the shaft that supports the wheel. As this axle bearing, there are a sliding bearing depending on liquid lubrication such as lubricating oil and a rolling bearing utilizing solid lubrication. In addition, since such an axle bearing is also generally called a shaft box including the structure which supports it, in the following description, it is suitably described as a shaft box.

  By the way, in such a shaft box, a large amount of heat is generated in order to rotatably support a shaft that rotates at a high speed during traveling. And the temperature of an axle box rises abnormally at the time of vehicle travel with the generated heat, and accidents, such as overheating and burning, may occur. For this reason, in order to prevent such overheating and burnout of the axle box, a technique for detecting an abnormal temperature of the axle box has been proposed.

  For example, in Patent Document 1, the difference between the surface temperature of the monitored device of the vehicle that is running and the outside air temperature is calculated for each device as a temperature increase value, and each device is calculated from the temperature increase value in a past fixed time. It describes a technique for monitoring a temperature abnormality of each device by setting a temperature rise threshold value and comparing the current temperature rise value with the threshold value.

Japanese Patent Laid-Open No. 10-62271

  However, in the technique described in Patent Document 1, the temperature rise of each device is monitored by comparing a temperature rise value that is a difference between the surface temperature of the monitored device and the outside air temperature and a threshold value. Although there is a correlation with the outside air temperature, the correlation is not always constant, and changes under the influence of disturbance due to the incident direction of sunlight and the direction of wind (direction of rain and snow). To do. Therefore, when the variation of the temperature rise value due to the influence of the disturbance is as large as the variation of the surface temperature to be detected as a temperature abnormality, there is a problem that the temperature abnormality cannot be detected with high accuracy.

  The present invention has been made in view of such a problem, and the object of the present invention is that a temperature abnormality occurs in a monitoring target part of a moving body formed from one or more vehicles such as a track traveling vehicle. It is to provide a technique for accurately detecting the presence of the image.

  The temperature abnormality detection system of the present invention made to solve the above problems is a temperature abnormality detection system that detects that a temperature abnormality has occurred in a monitoring target part of a moving body formed from one or more vehicles. The knitting detection moving body includes a knitting detection means for detecting the vehicle knitting of the moving body for each of the moving bodies, and the moving body in which the vehicle knitting is detected by the knitting detection means as a knitting detection moving body. Temperature value acquisition means for acquiring the temperature value of the monitored part, reference temperature detection means for detecting a reference temperature correlated with the temperature value of the monitoring target part acquired by the temperature value acquisition means, and the temperature Deviation temperature for calculating a deviation temperature value in which the temperature value of the monitoring target part acquired by the value acquisition means deviates from the reference temperature detected by the reference temperature detection means Of the vehicle formations, a specific vehicle formation set in advance is set as a specific formation, and the monitoring target portion of the moving body having the specific formation among the formation detection moving bodies is set as a specific formation monitoring target portion. Identification that is an evaluation value for evaluating whether or not a temperature abnormality has occurred in the specific knitting monitoring target part, with respect to the specific knitting monitoring target part calculated by the divergence temperature value calculating unit Specific knitting evaluation value extraction means for extracting as a knitting evaluation value, and a total knitting moving average that is a moving average of temperature values in all the knitting detection moving bodies based on the deviance temperature value calculated by the deviance temperature value calculation means. All-knitting moving average calculating means to calculate, and a moving that is a standard deviation of the moving average based on the all-knitting moving average calculated by the all-knitting moving average calculating means The moving average standard deviation calculating means for calculating the average standard deviation, the specific composition evaluation value extracted by the specific composition evaluation value extracting means, and the moving average standard deviation calculated by the moving average standard deviation calculating means are preset. A comparison unit that compares the abnormality threshold value multiplied by the specified magnification, and based on the comparison result by the comparison unit, when the specific knitting evaluation value is larger than the abnormality threshold value, a temperature abnormality is detected in the specific knitting monitoring target part. Temperature abnormality determining means for determining that the temperature has occurred.

  According to the temperature abnormality detection system of the present invention configured as described above, it is determined whether or not a temperature abnormality has occurred in the monitoring target portion using a statistical method. Judgment can be made with high accuracy regardless of variations. Moreover, the divergence temperature value is used as individual data to which the statistical method is applied. For this reason, it is possible to suppress the influence of external influences caused by external factors included in the temperature value of the monitoring target part, for example, the influence of disturbance caused by the incidence of sunlight, the wind direction (direction in which rain and snow blows), etc. Thus, the accuracy of the determination performed using the statistical method, that is, the determination of whether or not the temperature abnormality has occurred in the monitoring target part can be further improved. Therefore, according to the temperature abnormality detection system of the present invention, it is possible to accurately detect that a temperature abnormality has occurred in the monitoring target part.

  The temperature abnormality detection method of the present invention made to solve the above problem is a temperature abnormality detection method for detecting that a temperature abnormality has occurred in a monitoring target part of a moving body formed from one or more vehicles. And detecting the vehicle knitting of the moving body for each of the moving bodies, using the moving body from which the vehicle knitting is detected as a knitting detection moving body, and determining the temperature value of the monitoring target part included in the knitting detection moving body. A reference temperature having a correlation with the acquired temperature value of the monitored part is detected, and a deviation temperature value that is a value at which the acquired temperature value of the monitored part deviates from the detected reference temperature is obtained. Calculating, selecting a specific vehicle composition set in advance from the vehicle composition to be a specific composition, and selecting the monitoring target part of the moving object having the specific composition among the composition detection moving objects as a specific composition monitoring target part age, The calculated deviation temperature value for the specific composition monitoring target part is extracted as a specific composition evaluation value that is an evaluation value for evaluating whether a temperature abnormality has occurred in the specific composition monitoring target part, Based on the calculated deviation temperature value, a total knitting moving average that is a moving average of temperature values in all the knitting detection moving bodies is calculated, and a standard deviation of the moving average is calculated based on the calculated all knitting moving average. The moving average standard deviation is calculated, the specific knitting evaluation value is compared with an abnormal threshold value obtained by multiplying the moving average standard deviation by a preset specified magnification, and the comparison result between the specific knitting evaluation value and the abnormal threshold value is obtained. Based on the above, it is determined that a temperature abnormality has occurred in the specific composition monitoring target part when the specific composition evaluation value is larger than the abnormality threshold.

  According to the temperature abnormality detection method of the present invention configured as described above, since it is determined whether or not a temperature abnormality has occurred in the monitoring target portion using a statistical method, the data to be determined is determined. Judgment can be made with high accuracy regardless of variations. Moreover, the divergence temperature value is used as individual data to which the statistical method is applied. For this reason, it is possible to suppress the influence of external influences caused by external factors included in the temperature value of the monitoring target part, for example, the influence of disturbance caused by the incidence of sunlight, the wind direction (direction in which rain and snow blows), etc. Thus, the accuracy of the determination performed using the statistical method, that is, the determination of whether or not the temperature abnormality has occurred in the monitoring target part can be further improved. Therefore, according to the temperature abnormality detection method of the present invention, it is possible to accurately detect that a temperature abnormality has occurred in the monitoring target part.

1 is a schematic configuration diagram showing a temperature abnormality detection system 1. FIG. It is explanatory drawing which shows temperature abnormality detection.

Embodiments of the present invention will be described below with reference to the drawings. In addition, this invention is not limited to the following embodiment, It is possible to implement in various aspects.
The temperature abnormality detection system 1 shown in FIG. 1 has a function of detecting that a temperature abnormality has occurred in a monitoring target portion of a train as a moving body formed from one or more vehicles such as a track traveling vehicle.

[1. Configuration of temperature abnormality detection system 1]
The temperature abnormality detection system 1 includes an abnormality detection condition input unit 10, a device temperature sensor 11, a train (knitting) detection unit 12, a device part detection unit 13, a data processing unit 14, a storage unit 15, and a deviation temperature. A value calculation unit 16, a specific knitting evaluation value extraction unit 17, a total knitting moving average calculation unit 18, a moving average standard deviation calculation unit 19, a comparison unit 20, and a temperature abnormality detection unit 21 are provided.

  The temperature abnormality detection system 1 is equipped with a known CPU, ROM, RAM, I / O that is an input / output circuit, and a bus line that connects these components, among which a CPU Functions as a data processing unit 14, a deviation temperature value calculation unit 16, a specific knitting evaluation value extraction unit 17, a total knitting moving average calculation unit 18, a moving average standard deviation calculation unit 19, a comparison unit 20, and a temperature abnormality detection unit 21. The RAM functions as the storage unit 15.

  Further, the CPU performs control according to control programs and data stored in the ROM and RAM. The ROM has a program storage area and a data storage area. A control program is stored in the program storage area, and data necessary for the operation of the control program is stored in the data storage area. In addition, the control program operates on the RAM in a form in which the work memory is a work area.

[1.1. Configuration of Abnormality Detection Condition Input Unit 10]
The abnormality detection condition input unit 10 inputs a temperature abnormality detection condition for the monitoring target part. Then, the abnormality detection condition input unit 10 outputs the input abnormality detection condition to the moving average standard deviation calculation unit 19 via the data processing unit 14.

[1.2. Configuration of Device Temperature Sensor 11]
The equipment temperature sensor 11 is disposed on the ground side where the track (track) is laid, corresponding to each side of the train traveling on the track, and detects the radiant heat of the monitored portion to detect the temperature value of the monitored portion. Measure. More specifically, the device temperature sensor 11 has a configuration in which an infrared radiation thermometer is built in the housing, and the infrared radiation thermometer is adapted to the intensity of infrared rays (energy) emitted from an object having temperature. By detecting the amount), the temperature of the monitored part of each vehicle of the train passing through the track is measured in a non-contact manner. The monitoring target part is a part to be monitored whether or not a temperature abnormality has occurred. The part to be monitored is a part of a train, and examples thereof include an axle box and an axle. In the present embodiment, the two sensors arranged corresponding to the both sides of the train traveling on the track are collectively referred to as the device temperature sensor 11.

  The device temperature sensor 11 starts the above-described measurement when a preset measurement start time is reached according to an instruction from the CPU, and ends the measurement when the preset measurement end time is reached. At this time, the equipment temperature sensor 11 uses the train whose train formation is detected by the train (train) detection unit 12 described later as a train detection train (knitting detection moving body), and the temperature value of the monitoring target part included in the train detection train And the acquired temperature value is output to the deviation temperature value calculation unit 16 via the data processing unit 14.

The device temperature sensor 11 corresponds to a temperature value acquisition unit.
[1.3. Configuration of Train (Composition) Detection Unit 12]
The train (train) detection unit 12 detects the train number of the train passing through the track. Specifically, the organization name is registered in an IC card affixed to the vehicle body of the train constituting the train, information is received by an antenna (not shown) provided on the ground when the train passes, and the organization name is assigned to the train ( The composition is read by the detection unit 12. Thus, the train (composition) detection unit 12 detects the train composition of the train.

The train (composition) detection unit 12 corresponds to a composition detection means.
[1.4. Configuration of Device Part Detection Unit 13]
The device part detection unit 13 outputs a signal when the flange portion of the wheel comes close, and can accurately detect the passing timing of the wheel without contact. Examples of such a non-contact detection method include a high frequency induction method and a photoelectric method.

[1.5. Configuration of Data Processing Unit 14]
The data processing unit 14 performs various calculations based on the output signal from the equipment temperature sensor 11, the output signal from the train (knitting) detection unit 12, and the output signal from the equipment part detection unit 13, and passes through the train vehicle. Determine the train (train name), train type, car number where the axle box is installed, axle position of the axle box, and whether the side where the axle box is installed is the sea side or the mountain side. The result is output to the calculation unit 16.

  In addition, the data processing unit 14 can exchange data with the storage unit 15, and outputs and stores the above determination result to the storage unit 15, or reads various data stored in the storage unit 15. Or output to the deviation temperature value calculation unit 16.

[1.6. Configuration of storage unit 15]
The storage unit 15 is used for storing various types of information.
[1.7. Configuration of Deviation Temperature Value Calculation Unit 16]
The deviation temperature value calculation unit 16 calculates a deviation temperature value that is a value at which the temperature value of the monitoring target part acquired by the device temperature sensor 11 deviates from the outside temperature as the reference temperature. Thus, by calculating the value at which the temperature value of the monitoring target part deviates from the reference temperature, it is possible to eliminate the influence of the variation in the outside air temperature, weather conditions, and the like from the temperature value of the monitoring target part. The outside air temperature corresponds to a reference temperature having a correlation with the temperature value of the monitoring target part. As for the outside air temperature, the device temperature sensor 11 may measure the outside air temperature when measuring the temperature value of the monitored part, or a thermometer (not shown) may measure the outside air temperature. . The deviation temperature value is a value at which the surface temperature value deviates from the estimated temperature value by using the surface temperature value and the estimated temperature value calculated by the method described in JP 2010-179706 A, for example. A deviation value may be calculated and used as the deviation temperature value. Moreover, you may use the surface temperature of the apparatus arrange | positioned around the monitoring object site | part instead of external temperature as reference temperature.

The deviation temperature value calculation unit 16 corresponds to a reference temperature detection unit and a deviation temperature value calculation unit.
[1.8. Configuration of specific composition evaluation value extraction unit 17]
The specific composition evaluation value extraction unit 17 extracts a specific composition evaluation value for the specific composition monitoring target part. The specific train is a specific vehicle train set in advance among the vehicle trains. The specific formation monitoring target part is a monitoring target part of a train having a specific formation. The specific knitting evaluation value is an evaluation value for evaluating whether or not a temperature abnormality has occurred in the specific knitting monitoring target part. First, the specific knitting evaluation value extraction unit 17 selects the divergence temperature value of the specific knitting monitoring target part among the divergence temperature values calculated by the divergence temperature value calculation unit 16. Subsequently, the specific composition evaluation value extraction unit 17 further selects a deviation temperature value during a preset calculation period from the selected deviation temperature value. The calculation period may be a period immediately after the present time or a period retroactive from a past time. As shown in FIG. 2, on the graph as a two-dimensional plane with the measurement time, which is the time when the temperature of the specific composition monitoring target part is measured, as the horizontal axis and the deviation temperature value as the vertical axis, Plot the relationship points indicating the relationship with the deviation temperature value of the composition monitoring target part. The line segment connecting the relation points plotted on this graph becomes a divergence temperature value transition line which is a line segment indicating a transition in which the divergence temperature value of the specific knitting monitoring target portion fluctuates with time during the calculation period. Furthermore, the specific composition evaluation value extraction unit 17 sets a value on the vertical axis of one or more arbitrary related points on the deviation temperature value transition line as the specific composition evaluation value.

  For specific trains, one vehicle train is set in advance from all vehicle trains, and the temperature abnormality determination of this embodiment is performed. The determination of temperature abnormality according to this embodiment may be performed for a plurality of vehicle formations or all vehicle formations.

The specific composition evaluation value extraction unit 17 corresponds to a specific composition evaluation value extraction unit.
[1.9. Configuration of all-knitting moving average calculation unit 18]
The all-knitting moving average calculation unit 18 calculates the all-knitting moving average based on the deviation temperature value calculated by the deviation temperature value calculation unit 16. Specifically, the all-set moving average calculating unit 18 calculates the all-set moving average that is a moving average of temperature values in all the set detection trains. For example, for the divergence temperature value, an average value of the divergence temperature values during the most recent calculation period is calculated. The moving average calculation period is the same as the calculation period of the measured temperature value transition described above, and can be changed by optimization according to various conditions such as the measurement target and abnormality detection requirements.

The all-knitting moving average calculating unit 18 corresponds to all-knitting moving average calculating means.
[1.10. Configuration of Moving Average Standard Deviation Calculation Unit 19]
The moving average standard deviation calculation unit 19 calculates a moving average standard deviation that is a standard deviation of the moving average based on the all-knitting moving average calculated by the all-knitting moving average calculation unit 18. At this time, the moving average standard deviation calculation unit 19 receives the abnormality detection conditions input from the abnormality detection condition input unit 10 and inputs parameters such as the moving average period and the standard deviation standard magnification within the abnormality detection conditions. The moving average standard deviation is calculated after optimization. Here, the abnormality detection condition is set from the viewpoint of detecting that the temperature abnormal state continues. In addition, regarding the recognition that the abnormal temperature state continues, for example, a predetermined number of data continues, the abnormal temperature state exceeds a predetermined ratio (%), and the number of times the temperature value is set in advance is measured. A case in which at least one of the predetermined number of times is an abnormal temperature condition is satisfied. For this reason, this embodiment has a feature that it is not necessary to set conditions for abnormality detection on the user side.

The moving average standard deviation calculating unit 19 corresponds to moving average standard deviation calculating means.
[1.11. Configuration of Comparison Unit 20]
The comparison unit 20 includes an abnormal threshold obtained by multiplying the specific composition evaluation value extracted by the specific composition evaluation value extraction unit 17 and the moving average standard deviation calculated by the moving average standard deviation calculation unit 19 by a preset specified magnification. Compare The abnormality threshold is a threshold for determining that a temperature abnormality has occurred in the monitoring target part. The specified magnification is set in advance by experiments or the like.

The comparison unit 20 corresponds to comparison means.
[1.12. Configuration of temperature abnormality detection unit 21]
The temperature abnormality detection unit 21 determines whether or not a temperature abnormality has occurred in the specific composition monitoring target part based on the comparison result by the comparison unit 20. Specifically, the temperature abnormality detection unit 21 determines that a temperature abnormality has occurred in the specific composition monitoring target part when the specific composition evaluation value is larger than the abnormality threshold as a comparison result by the comparison unit 20.

The temperature abnormality detection unit 21 corresponds to a temperature abnormality determination unit.
[2. Effects of the embodiment]
As described above, according to the temperature abnormality detection system 1 of the present embodiment, since it is determined whether or not a temperature abnormality has occurred in the specific composition monitoring target portion using a statistical method, the data to be determined Judgment can be made with high accuracy regardless of the variation of. Moreover, the divergence temperature value is used as individual data to which the statistical method is applied. For this reason, the influence tendency which acts by the external factor included in the temperature value of the specific composition monitoring target part, for example, the influence of the disturbance due to the incidence of sunlight, the wind direction (direction in which rain and snow blows), etc., is suppressed. Thus, it is possible to further improve the accuracy of the determination performed using the statistical method, that is, the determination of whether or not the temperature abnormality has occurred in the specific composition monitoring target part. Therefore, it is possible to accurately detect that a temperature abnormality has occurred in the specific composition monitoring target part.

[3. Other Embodiments]
As mentioned above, although the form for implementing this invention was demonstrated, this invention is not limited to the above-mentioned embodiment, It can implement in various deformation | transformation.

  (1) In the above embodiment, the specific composition evaluation value is compared with the abnormal threshold value using the value on the vertical axis of one or more arbitrary relation points on the deviation temperature value transition line as the specific composition evaluation value, and the specific composition evaluation is performed. When the value is larger than the abnormality threshold, it is determined that a temperature abnormality has occurred in the specific composition monitoring target part, but this is not a limitation. For example, when a specific composition evaluation value and an abnormal threshold are compared with each divergence temperature value for a specific composition monitoring target part as a specific composition evaluation value, and the specific composition evaluation value is larger than the abnormality threshold, the specific composition monitoring target You may make it determine with temperature abnormality having generate | occur | produced in the site | part.

  DESCRIPTION OF SYMBOLS 1 ... Temperature abnormality detection system, 10 ... Abnormality detection condition input part, 11 ... Equipment temperature sensor, 12 ... Train (composition) detection part, 13 ... Equipment part detection part, 14 ... Data processing part, 15 ... Memory | storage part, 16 ... Deviation temperature value calculation unit, 17 ... specific knitting evaluation value extraction unit, 18 ... all-knitting moving average calculation unit, 19 ... moving average standard deviation calculation unit, 20 ... comparison unit, 21 ... temperature abnormality detection unit.

Claims (2)

A temperature abnormality detection system for detecting that a temperature abnormality has occurred in a monitoring target part of a moving body formed from one or more vehicles,
Knitting detection means for detecting vehicle knitting of the moving body for each moving body;
A temperature value acquiring means for acquiring a temperature value of the monitoring target part included in the knitting detection moving body, with the moving body in which the vehicle knitting is detected by the knitting detection means as a knitting detection moving body;
A reference temperature detecting means for detecting a reference temperature having a correlation with the temperature value of the monitored part acquired by the temperature value acquiring means;
A deviation temperature value calculating means for calculating a deviation temperature value in which the temperature value of the monitoring target part acquired by the temperature value acquisition means is a value that deviates from the reference temperature detected by the reference temperature detection means;
Among the vehicle formations, a predetermined specific vehicle formation is set as a specific formation, and among the formation detection moving bodies, the monitoring target portion of the moving body having the specific formation is set as a specific formation monitoring target portion, and the deviation temperature value As the specific knitting evaluation value that is an evaluation value for evaluating whether or not a temperature abnormality has occurred in the specific knitting monitoring target part, the divergence temperature value for the specific knitting monitoring target part calculated by the calculation means Specific organization evaluation value extraction means for extracting;
Based on the divergence temperature value calculated by the divergence temperature value calculation means, the total knitting moving average that is a moving average of temperature values in all the knitting detection moving bodies included in a preset calculation period in which the timing is sequentially shifted is calculated. All-train moving average calculating means to calculate,
Moving average standard deviation calculation means for calculating the moving average standard deviation is the standard deviation of the moving average based on the collection of all the knitting moving average calculated for each predetermined calculation period by the total knitting moving average calculating means ,
A comparison for comparing the specific composition evaluation value extracted by the specific composition evaluation value extraction means with an abnormal threshold value obtained by multiplying the moving average standard deviation calculated by the moving average standard deviation calculation means by a preset specified magnification. Means,
A temperature abnormality determination unit that determines that a temperature abnormality has occurred in the specific knitting monitoring target part when the specific knitting evaluation value is larger than the abnormality threshold based on a comparison result by the comparison unit;
A temperature abnormality detection system comprising: A temperature abnormality detection method for detecting that a temperature abnormality has occurred in a monitoring target part of a moving body formed from one or more vehicles,
Detecting the vehicle organization of the moving body for each moving body;
Using the mobile body from which the vehicle formation is detected as a formation detection mobile body, obtain a temperature value of the monitoring target part included in the formation detection mobile body,
Detect a reference temperature having a correlation with the acquired temperature value of the monitoring target part,
Calculate a deviation temperature value, which is a value at which the acquired temperature value of the monitoring target part deviates from the detected reference temperature,
Among the vehicle formations, a predetermined specific vehicle formation is set as a specific formation, and among the formation detection moving bodies, the monitoring target portion of the moving body having the specific formation is set as a specific formation monitoring target portion, and the calculated The deviation temperature value for the specific composition monitoring target part is extracted as a specific composition evaluation value that is an evaluation value for evaluating whether a temperature abnormality has occurred in the specific composition monitoring target part,
Based on the calculated deviation temperature value, calculate a total knitting moving average that is a moving average of temperature values in all the knitting detection moving bodies included in a preset calculation period in which the timing is sequentially shifted ,
Calculating a moving average standard deviation which is a standard deviation of the moving average based on the collection of all the train moving averages calculated for each of the predetermined calculation periods ;
Comparing the specific knitting evaluation value and the abnormal threshold value obtained by multiplying the moving average standard deviation by a preset specified magnification,
Based on the comparison result between the specific knitting evaluation value and the moving average standard deviation, it is determined that a temperature abnormality has occurred in the specific knitting monitoring target part when the evaluation value is larger than the abnormality threshold value. A temperature abnormality detection method.

Images