JP7245007B2 - Equipment deviation prediction method and prediction system - Google Patents

Description

TECHNICAL FIELD The present invention relates to a prediction method and a prediction system for equipment deviation in equipment such as point machines.

For example, in a point machine, which is an example of equipment installed outdoors, a lock piece is incorporated in a lock piece, as exemplified in Cited Document 1, etc., but the lock piece and the lock piece If the deviation of the notch (the amount of lock deviation) becomes large, the lock piece may not fit into the notch of the lock latch, which may cause a lock failure, making it impossible to switch trains and hindering train operation. be. Therefore, it is necessary to adjust the amount of lock deviation before the lock deviation occurs. For this reason, in Patent Document 1, for example, in order to cope with the temperature change of the member, which is one of the causes of the lock failure, the temperature is estimated, and from the estimated temperature, the temperature in the vicinity of the member is adjusted so as to be kept constant. doing Note that, in Cited Document 1, weather data near the railroad track where the point machine is installed is used for estimating the temperature.

However, for example, even if the temperature is the same, the degree of change in the amount of lock shift may vary depending on the season. Therefore, even if the temperature is kept constant using weather data as in the case of Patent Document 1, the amount of lock shift in the point machine becomes large and the lock error occurs. , it is not always possible to prevent the situation. In particular, as described above, in the method of using only meteorological data obtained from sensors installed near point machines, even if it is possible to analyze the temperature at that point in time, the trend of the amount of lock shift after that may not be possible. It is not always possible to make predictions about That is, in the case of Patent Document 1, it is not always possible to know in advance the timing at which the lock deviation amount becomes large enough to cause the lock deviation. It should be noted that the above-mentioned problems can be a problem not only in point machines but also in various types of equipment.

Japanese Patent No. 5806627

The present invention has been made in view of the above-mentioned points. It is an object of the present invention to provide a prediction method and a system for predicting the amount of equipment deviation for enabling prior adjustment such as adjustment of the amount of lock deviation.

A method of predicting the amount of equipment deviation for achieving the above purpose is a method of predicting the amount of deviation of equipment that undergoes expansion and contraction displacement, and is based on accumulated data from the past to the present and environmental prediction data on the external environment of the equipment. Based on the current state, the degree of change in the amount of equipment deviation from now on is predicted.

In the above method of predicting the amount of equipment deviation, when predicting the degree of change in the amount of equipment deviation from the current state, based on the accumulated data from the past to the present, it is possible to simply obtain temperature information at that time. In addition, it is possible to make a prediction that takes into account, for example, the difference in the degree of change in the amount of equipment deviation depending on the season. In addition, based on the environment prediction data for the external environment, it is possible to make predictions in the future, that is, after the present, taking into account the information around the facility. As a result, it is expected that the amount of equipment deviation after the current state will be more accurately predicted. become.

In a specific aspect of the invention, the environmental forecast data includes weather forecast data. In this case, it is possible to make predictions for the future based on the weather forecast data.

In another aspect of the present invention, the accumulated data includes data regarding the amount of solar radiation for the external environment of the facility. In this case, the degree of change in the amount of facility deviation can be predicted based on the amount of solar radiation from the past to the present, that is, the amount of radiant energy from the sun.

In still another aspect of the present invention, the accumulated data includes information on month and day as elements for predicting the degree of change in the amount of equipment deviation. In this case, it is possible to make a prediction that takes into consideration the difference in the degree of change in the amount of equipment deviation depending on the season using the information of the month and day.

In still another aspect of the present invention, the accumulated data includes data on weather changes from the past to the present. In this case, it is possible to predict the degree of change in the amount of facility deviation based on weather changes from the past to the present.

According to still another aspect of the present invention, the accumulated data includes the progress of equipment shift from the past to the present. In this case, the degree of change in the amount of equipment deviation can be predicted based on the progress of equipment deviation from the past to the present.

According to still another aspect of the present invention, equipment deviation due to human adjustment is excluded from the accumulated data. In this case, the accuracy of prediction can be improved by eliminating elements that make prediction difficult.

In still another aspect of the present invention, the accumulated data includes the difference in equipment deviation between before and after the passage of the train in the equipment installed in the vicinity of the passage position of the train. In this case, the accuracy of prediction can be improved by taking into account the difference between before and after the train passes.

In still another aspect of the present invention, the prediction result and the actual measurement result regarding the degree of change of the equipment deviation amount are compared, and the algorithm for prediction is modified based on the difference between the comparison results. In this case, by correcting the algorithm, more accurate prediction becomes possible.

In still another aspect of the present invention, the degree of change in the amount of lock deviation in a point machine as equipment is predicted. In this case, predictions can be made about the amount of lock shift in the point machine.

A system for predicting the amount of equipment deviation for achieving the above object is a system for predicting the amount of deviation of equipment that expands and contracts. An environmental prediction data acquisition unit that acquires environmental prediction data about the environment, and an equipment deviation amount prediction unit that predicts the degree of change in the equipment deviation amount from the current state on the basis of the accumulated data and the environmental prediction data. Prepare.

In the system for predicting the amount of equipment deviation, when predicting the degree of change in the amount of equipment deviation from the current state, based on the accumulated data from the past to the present managed by the accumulated data management unit, The facility deviation forecasting unit can make predictions that take into account not only the temperature information at the point in time, but also, for example, the difference in the degree of change in the facility deviation depending on the season. Further, based on the environment prediction data about the external environment acquired by the environment prediction data acquisition unit, the facility deviation prediction unit can make predictions in the future, that is, after the present, taking into account the information around the facility. From the above, more accurate prediction is expected for the amount of equipment deviation after the current state, and for example, it is possible to inform the timing to adjust the amount of equipment deviation before lock failure occurs at the point machine. become.

In a specific aspect of the present invention, the equipment deviation amount prediction unit predicts the degree of change in the lock deviation amount in a point machine as equipment. In this case, predictions can be made about the amount of lock shift in the point machine.

BRIEF DESCRIPTION OF THE DRAWINGS It is a top view which shows notionally about the point machine which mounts the prediction system of the amount of installation deviations which concerns on 1st Embodiment. It is a perspective view which shows one structural example about the point machine in a turnout. It is a perspective view which shows one structural example about the lock piece and lock latch which were incorporated in the point machine. (A) and (B) are conceptual diagrams for explaining a lock deviation amount. FIG. 4 is a conceptual diagram for explaining an example of detection of a lock deviation amount; It is a block diagram which shows one structural example about the prediction system in a point machine. It is a conceptual diagram for demonstrating the analysis method in a prediction system. FIG. 5 is a graph showing an example of lock deviation prediction based on a prediction system; FIG. FIG. 10 is a data table showing an example of various data used for lock deviation prediction based on the prediction system; FIG. It is a flowchart for demonstrating an example about the prediction method in a prediction system. FIG. 11 is a flowchart for explaining an example of modification of an algorithm using the prediction created in FIG. 10; FIG. (A) is a graph showing an example of the relationship between a prediction in a prediction system and an actual lock deviation amount, and (B) is a graph showing a comparative example for (A). It is a block diagram which shows one structural example about the prediction system which concerns on 2nd Embodiment.

[First embodiment]
Hereinafter, with reference to FIG. 1 and the like, the system for predicting the amount of equipment deviation according to the first embodiment will be described.

As exemplified in FIGS. 1 and 2, the equipment deviation prediction system 100 of the present embodiment is a system for predicting the deviation of equipment that undergoes expansion and contraction displacement. The point machine 50 , more precisely, a part of the point machine 50 is assumed to be the equipment for which the deviation amount is to be predicted. In particular, in the present embodiment, as a specific example, it is assumed that the amount of displacement of the facility that is to be predicted and that undergoes expansion/contraction displacement is the amount of lock displacement in the point machine 50 . Here, the lock shift amount means the shift amount of the part where the lock piece is incorporated in the lock latch among the parts that expand and contract as a part of the point machine 50 . The details of the internal structure of each part of the point machine 50 will be described later.

As described above, the prediction system 100 of the present embodiment predicts the degree of change in the amount of lock deviation. Based on the prediction data, the degree of change in the amount of deviation of the point machine 50 in the future is predicted with higher accuracy from the current state. In order to make the above prediction possible, in the present embodiment, the prediction system 100 is provided inside the main unit 50A that constitutes the point machine 50, grasps the situation inside and performs various adjustments. and a prediction processing unit 60 provided outside the main body 50A that acquires information from the lock shift processing unit 40 and information on the external environment of the point machine 50 and performs prediction processing based on these. consists of

Hereinafter, as a premise for explaining the prediction system 100, first, one configuration example of the target point machine 50 will be explained.

In one example here, the point machine 50 is an electric point machine. It is a member for switching the route of the train in the turnout P.

In order to perform the above-described switching operation, the point machine 50 includes a body portion 50A including a motor as a power source, for example, an operation stick 10 extending from the body portion 50A, and a tongue rail connected to the operation stick 10. A connecting part 20 connected to the TR or a locking key 30 for fixing the position after the switching operation is provided. In addition, since the point machine 50 has the lock shift processing unit 40, it is possible to monitor the change over time of the lock shift amount.

As shown in the figure, the body part 50A is placed on one end of a first sleeper SP1 and a second sleeper SP2 that are longer than a normal sleeper SP and arranged at a predetermined interval to form a turnout of the railroad track. It is arranged on the side of P and is further fixed to the sleepers SP1 and SP2 by a fixing device or the like so as not to move. The body portion 50A has a motor, an electric power device for moving the motor, and the like, and advances and retreats the operation stick 10 to generate a conversion force when moving the tongue rail TR. It should be noted that a structure may be provided to enable the conversion operation to be performed manually when the motor is not driven.

The movement stick 10 is a plate-like or rod-like metal member extending from the inside of the main body 50A, and moves back and forth in a horizontal direction perpendicular to the traveling direction of the train on the rail in accordance with the driving operation of the main body 50A. More specifically, the action stick 10 converts the tongue rail TR from the normal position to the reverse position or from the reverse position to the normal position with respect to the base rail SR.

The connecting part 20 has a switch adjuster rod 21 made of metal as a main component, and has other connecting devices. It functions as a member that transmits the force from the action stick 10 for movement. More specifically, the connecting portion 20 is connected to the operation rod 10 on the tip end side of the switch adjuster rod 21, and is connected to the tongue rail TR on the other end side where another member connected to the switch adjuster rod 21 is provided. By being there, the conversion force from the action stick 10 is transmitted to the tongue rail TR.

The latch 30 is, as already mentioned, a member for fixing the position after the switching operation. In other words, after the changeover by the operation stick 10, the point machine 50 moves the operation stick 10 into the normal position and the reverse position by the action on the operation stick 10 accompanying the operation of the locking pin 30 inside the main body 50A. can be locked in each. For this reason, the lock pin 30 is also a plate-shaped or rod-shaped metal member extending from the inside of the main body portion 50A. A front rod 31b is provided on the side. The front rod 31b is connected to the tip side of the tongue rail TR, and when the tongue rail TR is moved by the operation stick 10, the lock stick 30 also operates.

Hereinafter, with reference to FIG. 3, the structure and operation of the lock key 30 and the like will be described more specifically. FIG. 3 is a perspective view showing a configuration example of the lock pin 30 incorporated in the point machine 50 and the pair of lock pieces LPa and LPb inserted into the notches NTa and NTb provided in the lock pin 30. be.

The pair of lock pieces LPa and LPb are a pair of rod-shaped members which are advanced and retracted by cam bars arranged so as to be slidable in the horizontal direction perpendicular to the movement of the operation stick 10 . Locking blocks LBa and LBb, one of which protrudes downward and the other of which protrudes upward, are provided at the ends of the pair of lock pieces LPa and LPb.

On the other hand, the lock key 30 is configured by, for example, a pair of upper and lower rod-shaped members 30a and 30b in a portion provided inside the main body portion 50A. A pair of rod-shaped members 30a and 30b are arranged at positions separated by a predetermined distance in the longitudinal direction. The lower rod-shaped member 30a has a notch NTa that opens upward, and the upper rod-shaped member 30b has a notch NTb that opens downward. is formed.

With the above configuration, in the rolling point machine 50, for example, when the motor (not shown) of the rolling point machine 50 rotates, the operation stick 10 operates to switch from the reverse position to the normal position, and when the conversion is completed, The locking block LBa of the lock piece LPa is locked by fitting into the corresponding notch NTa of the locking key 30 . When the normal position is changed to the reverse position, the locking block LBb of the other lock piece LPb is fitted into the corresponding notch NTb of the locking key 30 to be locked. Note that FIG. 3 illustrates a state in which the lock block LBb is fitted into the notch NTb.

Here, in order to maintain the above operation, it is necessary that the positions of the notches NTa and NTb corresponding to the locking blocks LBa and LBb of the lock pieces LPa and LPb do not deviate beyond the allowable range. . More specifically, for example, as shown in FIG. 4A, the gap DT between the lock piece LPa (LPb) and the notch NTa (NTb) at the reference position is approximately 1.5 mm. Therefore, if a deviation occurs and the gaps DT1 (=DT+α) and DT2 (=DT-α) are formed as shown in FIG. It becomes impossible to make a secure lock.

In this embodiment, in view of the above, in the prediction system 100, by performing a highly accurate prediction of the amount of shift, that is, the amount of lock shift between each part of the lock, it is possible to prevent, for example, normal locking. It is possible to take measures such as prompting maintenance before a situation occurs.

It should be noted that the measurement of the amount of displacement, that is, the detection of the size of the gap when locking by the lock piece as described above can be made possible by providing various sensors. Here, as exemplified in FIG. 5, by measuring the change in the distance to the position of the measuring piece 32 attached to the lock latch 30 with the linear sensor 54 fixed to the main body 50A side, the lock deviation amount can be calculated.

An example of the prediction method by the prediction system 100 in the point machine 50 according to the present embodiment will be described below with reference to FIG. 6 and the like. As described above and as illustrated, the prediction system 100 according to the present embodiment includes a lock shift processor 40 and a prediction processor 60 .

First, the lock shift processor 40 in the prediction system 100 will be described. The lock shift processing unit 40 is a processing unit for confirming the state of lock shift. It functions to acquire various kinds of information and to transmit the acquired information from the point machine side transmitting/receiving section 40 s to the prediction processing section 60 . Various processing operations may be performed according to instructions received from the prediction processing unit 60 via the point machine side transmission/reception unit 40s.

The lock shift processing unit 40 acquires information about various physical quantities in the point machine 50 in order to confirm the lock shift state, and performs various processes for monitoring the lock shift amount based on the information. I do.

In one example here, the lock shift processing unit 40 includes, in addition to the above-described point machine side transmission/reception unit 40s, a lock shift control unit 41, a lock shift storage unit 42, a temperature data processing unit 43, and a vibration data processing unit 44 .

The lock shift control unit 41 receives output voltages from the N side sensor 50N and the R side sensor 50R provided respectively for the lock pieces LPa and LPb (see FIG. 3) of the point machine 50, and Monitoring is performed by determining when the switching operation of the point machine 50 is completed from the operation of the output voltages of the N-side sensor 50N and the R-side sensor 50R, and detecting the amount of lock deviation at that time.

The lock shift storage unit 42 stores the lock shift amount during monitoring by the lock shift control unit 41 described above.

The temperature data processing unit 43 transmits and receives data to and from the temperature sensor TS provided in the point machine 50, and monitors the temperature data around the point machine 50 together with the current value data of the lock deviation amount by the temperature sensor TS. Thereby, for example, the acquired temperature data can be used as weather data.

The vibration data processing unit 44 transmits and receives data to and from the vibration sensor BS provided in the rolling point machine 50, and monitors the vibration data around the rolling point machine 50 together with the current value data of the lock deviation amount by the vibration sensor BS. Thereby, for example, the acquired vibration data can be used as train operation data. More specifically, it is possible to determine that a train has passed when a vibration value equal to or greater than a predetermined threshold value is output.

The point machine side transmitting/receiving section 40 s is an interface section of the lock shift processing section 40 , and transmits the data regarding the point machine 50 acquired by each section described above to the prediction processing section 60 . The prediction processing unit 60 treats these pieces of information received via the point machine side transmitting/receiving unit 40 s as accumulated data regarding the point machine 50 .

The prediction processing unit 60 of the prediction system 100 will be described below. The prediction processing unit 60 acquires various types of information from the outside as necessary in addition to the information from the lock shift processing unit 40, and predicts the amount of lock shift based on the acquired information. Therefore, in one example here, the prediction processing unit 60 includes a prediction processing side transmission/reception unit 60s, a lock shift amount prediction processing unit 61 as a main unit, and a monitor display unit 62, for example.

The lock deviation amount prediction processing unit 61 is composed of a CPU or the like, and is composed of a main control unit 61a that performs various processes for calculating the lock deviation amount, and a storage device or the like, and is composed of a database that stores and manages various data. DB, and functions as an equipment deviation amount prediction unit. In particular, here, in the database DB, an accumulated data management unit AD that manages accumulated data from the past to the present, and an environment prediction data management unit PD that manages environmental prediction data about the external environment of the point machine 50 Prepare.

The prediction processing side transmission/reception unit 60s is an interface unit of the prediction processing unit 60, and acquires various kinds of information from the outside. As described above, the prediction processing-side transmitting/receiving unit 60s acquires data related to the point machine 50 via the point machine-side transmitting/receiving unit 40s as accumulated data. Accept environmental prediction data about the external environment. More specifically, weather forecast data is accepted as environment forecast data. For example, the prediction processing unit 60 is network-connected via the prediction processing side transmitting/receiving unit 60s, so that it is possible to acquire weather forecast information in the vicinity of the place where the point machine 50 is installed. .

Further, the prediction processing side transmitting/receiving section 60s also receives, from other than the lock shift processing section 40, information indicating predetermined facts such as meteorological data from the past to the present, which should be stored data, as necessary.

Among the databases DB constituting the lock deviation amount prediction processing unit 61, the accumulated data management unit AD manages various information from the past to the present as accumulated data. Various types of data can be stored data, but here, at least data related to the amount of solar radiation in the external environment of the point machine 50, data on weather changes from the past to the present, and data on points from the past to the present. It is assumed that the data includes data on the progress of lock deviation of the machine 50, data on equipment deviation due to manual adjustment, and information on the month and date of each of these data. In particular, here, information on month and day is included as an element for predicting the degree of change in the amount of equipment deviation, that is, the amount of lock deviation. Specifically, for example, with January 1 as a reference, it is conceivable to set the change in the degree of sunlight energy according to the passage of months and days, and use the set change value as a factor in prediction. be done.

On the other hand, in the database DB, the environment prediction data management unit PD manages weather forecast data as environment prediction data regarding the external environment of the point machine 50 . That is, it manages future prediction data. Note that the environment prediction data management unit PD cooperates with the prediction processing side transmission/reception unit 60s to function as an environment prediction data acquisition unit that acquires environment prediction data regarding the external environment of the point machine 50. Become.

As described above, the database DB stores various types of information from the past to the present in the accumulated data management section AD, and stores various types of information regarding the future in the environmental prediction data management section PD.

As conceptually shown in FIG. 7, the lock shift amount prediction processing unit 61 first stores various types of information such as lock shift amounts, weather data, date data, operation data, work data, etc. from the past to the present. In addition to the data, the database DB stores and manages environmental forecast data, which is data relating to future forecasts such as weather forecast data and data relating to the surrounding conditions of the point machine 50 . Then, the lock deviation amount prediction processing unit 61 analyzes these data by the main control unit 61a as an analyzer, and based on these data, predicts the degree of change in the lock deviation amount from the current state. are doing. That is, it predicts the future lock shift amount. Various methods such as multivariate analysis and neural networks can be used as specific calculation methods (calculation algorithms) for prediction in the main control unit 61a as an analyzer. Further, as will be described later, the calculation method (algorithm) used may be modified as appropriate to further improve accuracy. In the above case, for example, the prediction processing result is transmitted to the outside of the prediction processing unit 60, particularly to the outside of the point machine 50 such as a station device, via the prediction processing side transmitting/receiving unit 60s. may

In the example of FIG. 7 and the following, date data is information about year/month/day and hour/minute, and means, for example, data including information on month/day. In this case, the date data serves as an indicator of changes in the degree of sunlight energy. Operation data means data on the operation of trains passing through the point machine 50 , that is, data on before and after the train passes through the point machine 50 . Further, work data means data relating to lock adjustment work manually performed by a worker.

FIG. 8 is a graph showing an example of lock deviation prediction based on prediction system 100 . The horizontal axis of the graph is time, and the vertical axis is temperature and lock shift amount. Further, in the vertical axis direction, an upper limit line U1 and a lower limit line B1 indicate the limit of the amount of lock deviation. Here, the upper limit and the lower limit are shown as ±1.5 mm in accordance with the above example.

On the premise of the above, here, the performance data up to the day, that is, the actual various data is the accumulated data from the past to the present, and the next day's weather forecast (temperature prediction) is the future environmental forecast data. A prediction of the next day's lock shift amount is considered and illustrated.

For example, a solid curve T1 indicates how the actual temperature changes on that day, and a dashed curve T2 following the curve T1 indicates changes in expected temperature for the next day. On the other hand, the solid-line curve C1 shows how the actual lock deviation amount changes on the day, and the belt-shaped area D2 following the curve C1 shows the expected change of the lock deviation amount for the next day. . That is, the region D2 indicates the prediction result of the prediction system 100. FIG. For the belt-shaped area D2, for example, an assumed curve following the curve C1 is calculated by various calculation methods, and the assumed curve is created with a certain amount of width in the ± direction regarding the lock deviation amount. be done. In this case, for example, the width in the ± direction (vertical width) is set to ±0.25 mm, considering that the allowable amount of deviation is originally about 1.5 mm.

In the case of FIG. 8, which is based on the above assumption, the prediction range shown in area D2 exceeds the upper limit +1.5 mm around the time when the next day's temperature is expected to be the highest, and it is possible that conversion will be impossible (lock out of order). It shows that there is sexuality. By making such a prediction on the same day, it is possible to notify the worker before the lock deviation occurs the next day, and to adjust the lock deviation amount and repair the point machine 50 in advance.

FIGS. 9(A) to 9(C) are data tables showing examples of various data used for predicting the lock deviation amount based on the prediction system 100 as described above. For example, in FIG. 9A, date data (including month and day data as well as hours and minutes) and the number of days from January 1, which is the reference date (for example, if it is May 1, the number of days is 120 days). ), actual lock shift amount data that occurred at the point machine 50, or weather data, that is, weather change data from the past to the present, which is the result of actual occurrence, forecast for the previous day, etc. are exemplified. are doing. Of these, regarding the number of days, by setting January 1 as the reference date (counting start date) and counting the number of days (120 days in May 1), for example, July 1 as the reference date (count Even if the number of days is 120 days (October 29th is 120 days) counted as the start date), it can be regarded as different numerical data. More specifically, the amount of radiant energy from the sun, such as the difference in seasonality, that is, whether it is from winter to spring or from summer to autumn, and the accompanying difference in the change in hardness in the south. It is possible to make a prediction that takes into account a certain amount of solar radiation. As such, these data can be utilized in various ways in the development of one of the predictive models.

In addition, as shown in FIG. 9B, it is conceivable that the lock adjustment implementation date is included in the data. In other words, it is conceivable to include data for equipment shift due to manual adjustment, such as work days when lock adjustment was performed by workers. As a specific use, for example, it is conceivable to exclude the lock adjustment execution date from the prediction. This is because artificial work is different from the occurrence of deviations caused by naturally occurring matters, and if such data is left as it is, there is a possibility that it will not be possible to make proper predictions. In other words, it is considered that the accuracy of prediction can be improved by eliminating such factors that may make prediction difficult. In other words, these data can be used, for example, when correcting the initially created prediction model to improve its accuracy.

In addition, as shown in FIG. 9C, it is conceivable that the data includes the train passing time at the point machine 50, that is, includes operation data. When a train passes, a large force is applied to the entire turnout P including the point machine 50 . Therefore, it is considered that the influence on the amount of lock deviation is also very large. Therefore, for example, it can be expected that a more accurate prediction can be made by performing separate analysis once before the train passes and after the train passes, and then performing comprehensive calculations.

The above is an example, and prediction may be performed including elements other than the above, or prediction may be performed without using some of the above. Among the above elements, for example, the elements surrounded by the dashed line Q1 shown in FIG. 9A are considered to be fundamental and essential.

An example of the prediction method according to this embodiment will be described below with reference to the flowchart of FIG. 10 and the like.

First, FIG. 10 is a flowchart for explaining an example of creating a prediction model among the prediction methods in the prediction system 100 . That is, in FIG. 10, a prediction model is created based on past data and future (next day) forecast data. As a result, it is possible to acquire information about future lock shift amount prediction by the prediction system 100 as exemplified in the graph of FIG. 8 .

First, as shown in FIG. 10, in the prediction system 100, accumulated data from the past to the present regarding the amount of lock shift, etc., and environment prediction data, which is forecast data for the future such as weather forecast data, are input (step S101). Next, the main control unit 61a of the prediction system 100 checks the database DB to see if there is work data for lock adjustment in the past (step S102). (step S103a). On the other hand, if there is no work data for lock adjustment in step S102 (step S102: No), localization and reversal are performed for a short period of time during the lock adjustment work because of how the lock deviation amount changes over time. It is checked whether or not there are many changes in the amount of lock deviation in a short period of time due to repetition of the data, and if such data exist, the day is excluded (step S103b). This is because even if there is no work data for lock adjustment, such a change in the amount of lock deviation can be considered to indicate that work for lock adjustment has actually been performed. It should be noted that, in step S103b, if there is no change in the amount of lock deviation as described above, the processing proceeds to the next processing without performing the processing for exclusion as described above.

In the process of step S103a or step S103b, the main control unit 61a performs the lock adjustment necessary for the excluded items. For example, if there is data on the amount of lock adjustment made artificially in step S103a, this amount is corrected (step S104). If, for example, there is no lock adjustment amount data in step S103b, the amount estimated from the difference between the lock deviation amounts before and after the lock adjustment is corrected (step S104).

Next, the main control unit 61a confirms whether or not operation data exists in the database DB (step S105). That is, it is confirmed whether or not there is a distinction between before the train passes and after the train passes. If operation data exists in step S105 (step S105: Yes), the data is separated regarding passage (step S106). As an example here, the data from immediately after the change by the point machine 50 to before the passage of the train is separated from other data. In step S105, if operation data does not exist (step S105: No), the process proceeds to the next process without performing any particular process.

Finally, for the data that has undergone the above processing, for example, multivariate analysis, neural networks, and other various techniques are appropriately used to create a predictive model for the lock adjustment amount shown in FIG. 8 (step S107). ).

In addition, in the processing in step S107, if there is a distinction between when the train passes and when the train does not pass in step S106, a prediction model is created for both of these. In step S106, if there is no distinction between when the train passes and when the train does not pass, only the prediction model A is created. Assume that model B is created.

As described above, in the prediction system 100, a prediction model based on past data for making predictions is created.

11, the prediction model created in FIG. 10 is verified to compare the prediction result and the actual measurement result of the degree of change in the lock deviation amount, and obtain the comparison result. A process for modifying algorithms for prediction based on differences is described.

In FIG. 11, predicted values are obtained by substituting events that actually occurred in the prediction model calculated in FIG. By confirming whether it was accurate, the validity of the prediction model created in FIG. 10 and the need for correction are considered.

In one example here, a prediction model is created for the next day (forecast target day) in FIG. Actual values shall be compared.

A method of calculating a predicted value from a prediction model will be described below with reference to FIG. 11 . In FIG. 11, first, the main control unit 61a of the prediction system 100 adds actual weather data for the next day to the prediction model (prediction model A) completed through each step in FIG. 10 (step S201), locks the A provisional predicted value (predicted value A) of the amount of deviation is obtained. Next, the main control unit 61a confirms whether or not there is operation data for the prediction target day in the database DB (step S202). In other words, it is confirmed whether or not there is a distinction between before and after the passage of the train for the prediction target date. If operation data does not exist in step S202 (step S202: No), the main control unit 61a further checks in the database DB whether or not work data for lock adjustment exists for the prediction target date (step S203). , does not exist (step S203: No), the prediction value A in step S201 is output as it is as a prediction result (step S204).

If work data exists in step S203 (step S203: Yes), this is excluded, the provisional predicted value A is corrected with the corresponding lock adjustment amount, and the corrected predicted value A' is the prediction result. (step S205).

On the other hand, in step S202, if there is operation data for the prediction target date (step S202: Yes), the time of passage and the time of non-passage of the train are separated, and not only prediction model A but also prediction model B are locked. A provisional predicted value (predicted value B) of the amount of deviation is obtained (step S206).

After the process in step S206, the main control unit 61a checks the database DB to see if there is work data for lock adjustment for the prediction target date (step S207), and if not (step S207: No ), the predicted values A and B obtained in step S201 are directly output as the prediction results (step S208).

If work schedule data exists in step S207 (step S207: Yes), the provisional predicted values A and B are corrected with the corresponding lock adjustment amount in consideration of this, and the predicted value A' as the corrected result is calculated. , B' are output as prediction results (step S209).

The results of steps S204, S205, S208, and S209 are used as prediction results (prediction values) based on the prediction model created in FIG. 10 (step S210).

By comparing the prediction result (prediction value) of the lock shift amount obtained in step S210 as described above with the lock shift amount that actually occurred on the prediction target day, the validity of the prediction model, that is, the figure It is possible to consider the validity of the prediction method (prediction algorithm) in 10 and the need for modification of the algorithm. That is, in the prediction system 100, the prediction result and the actual measurement result of the change degree of the lock deviation amount are compared, and based on the difference between the comparison results, the algorithm can be modified to make a more accurate prediction. can.

FIG. 12A is a graph showing an example of the relationship between the prediction in the prediction system 100 and the actual lock deviation amount. The horizontal axis is time, and the vertical axis is the amount of lock deviation. Here, as an example, an example is shown in which two weeks' worth of data is first accumulated as data from the past to the present, and data for the next day is predicted. In the figure, curve DU1 indicates the upper limit of prediction in prediction system 100, and curve DB1 indicates the lower limit of prediction. Here, as before, considering that the allowable deviation amount is about ±1.5 mm, the vertical width is set so that the difference between the curve DU1 and the curve DB1 is ±0.25 mm. ing. A curve R1 indicates the actual amount of lock deviation. In this case, the curve R1 fits between the curve DU1 and the curve DB1, and it can be said that a reasonable prediction has been made.

On the other hand, FIG. 12(B) is a graph showing a comparative example with respect to FIG. 12(A). The horizontal axis is time, and the vertical axis is temperature and lock shift amount. In the example of FIG. 12B, only the change in temperature is shown as a curve X1, and the relationship between the curve X1 and the curve R1 representing the actual lock shift amount is shown. In this figure, the scale is appropriately adjusted so that the change in temperature and the degree of change in the amount of lock shift can be compared. From this figure, it can be seen that an accurate prediction cannot always be made even if an attempt is made to predict the amount of lock shift based solely on the change in temperature. On the other hand, in the present embodiment, not only information such as the temperature at each point in time and the temperature change after that, but also the configuration as described above enables accurate and highly accurate prediction.

As described above, in the equipment deviation prediction method and the prediction system 100 using the same according to the present embodiment, when predicting the degree of change in the equipment deviation from the current state, the accumulated data management unit AD Based on the accumulated data from the past to the present managed by the system, not only temperature information at that point in time, but also predictions that take into account, for example, the difference in the degree of change in the amount of equipment deviation depending on the season, etc. This is possible in the lock shift amount prediction processing section 61 as a shift amount prediction section. Further, based on the environment prediction data about the external environment acquired by the environment prediction data acquisition unit configured by the environment prediction data management unit PD, the future, i. This becomes possible in the deviation prediction processing section 61 . As described above, more accurate prediction can be expected for the amount of equipment deviation after the current state, and for example, it is possible to inform the timing of adjusting the amount of equipment deviation before lock failure or the like occurs in the point machine 50. be possible.

[Second embodiment]
An example of the system for predicting the amount of equipment deviation according to the second embodiment will be described below with reference to FIG. 13 .

The prediction system according to the present embodiment is a modification of the prediction system exemplified in the first embodiment. Since it is the same, the explanation of the entire prediction system is omitted, and only the structure of the processing unit will be explained.

FIG. 13 is a block diagram showing one configuration example of the prediction system 200 according to this embodiment, and is a diagram corresponding to FIG.

As illustrated, the present embodiment differs from the first embodiment in that the main part of the prediction processing section 60 is provided inside the main body section 50A.

In the prediction system 200, various data related to the point machine 50 acquired by the lock shift processing section 40 are directly sent to the prediction processing section 60 via the prediction processing side transmission/reception section 60s. Also in this case, as in the case of the first embodiment, for example, to the outside of the prediction processing unit 60, particularly to the outside of the point machine 50 such as a station device, via the prediction processing side transmitting/receiving unit 60s. You may make it transmit the processing result about prediction. In this case, the prediction can be completed entirely at the point machine 50, and only the obtained result can be received.

In the present embodiment as well, based on the accumulated data from the past to the present and the environmental prediction data for the future, i.e., the future, i. It is possible to notify the timing at which the equipment deviation amount should be adjusted before lock failure or the like occurs in the iron 50 .

〔others〕
The present invention is not limited to the above embodiments, and can be implemented in various forms without departing from the scope of the invention.

First, in the above description, the object of prediction is a point machine, and in particular, the degree of change in the amount of lock deviation is predicted with respect to the lock of the point machine. The method and prediction system are applicable in various aspects without being limited to this. First, in addition to point machines, prediction of the degree of change in the amount of deviation as described above may be applied to, for example, a railroad crossing facility or each part constituting a railroad crossing facility, which is installed outdoors. Note that the point machine can be applied not only to those installed outdoors, but also to those installed indoors underground, such as in subways. Moreover, the present invention may be applied not only to the lock mechanism in the point machine, but also to other locations where similar problems may occur.

Further, for example, the degree of change in the amount of deviation may be predicted for various devices installed outdoors other than point machines and railroad crossings, or for some of them. Furthermore, the present invention may be applied to facilities installed outdoors other than those related to railways.

In the above description, the weather forecast for the next day is exemplified. However, the weather forecast is not limited to this. It is also possible to predict the amount of deviation.

In the above description, for example, in the first embodiment, the prediction system 100 includes the lock shift processing unit 40 as an element. If so, the configuration may be such that the lock shift processing unit 40 or part thereof is not included.

DESCRIPTION OF SYMBOLS 10... Operation stick, 20... Connection part, 21... Switch adjuster rod, 30... Lock pin, 30a, 30b... Rod-shaped member, 31a... Connection stick, 31b... Front rod, 32... Measuring piece, 40... Lock deviation Processing unit 40s Point machine side transmission/reception unit 41 Lock shift control unit 42 Lock shift storage unit 43 Temperature data processing unit 44 Vibration data processing unit 50 Point machine 50A main unit 50N N-side sensor 50R R-side sensor 54 Linear sensor 60 Prediction processing unit 60s Prediction processing transmitting/receiving unit 61 Lock shift amount prediction processing unit 61a Main control Part 62... Monitor display part 100, 200... Prediction system AD... Accumulated data management part B1... Lower limit line BS... Vibration sensor C1... Curve D2... Area DB... Database DB1... Curve DT DT1, DT2... Gap DU1... Curve LBa, LBb... Locking block LPa, LPb... Lock piece NTa, NTb... Notch P... Turnout PD... Environment prediction data management part Q1... Dashed line R1... Curve, SP... sleeper, SR... basic rail, T1, T2... curve, TR... tongue rail, TS... temperature sensor, U1... upper limit line, X1... curve, α... deviation amount

Claims (12)

A method for predicting the amount of displacement of equipment that expands and contracts at a point machine or a railroad crossing ,
When predicting the degree of change in the amount of equipment deviation from the current state on the basis of accumulated data from the past to the present and environmental prediction data about the external environment of the equipment by the arithmetic processing unit , as the accumulated data , a method for predicting an amount of equipment deviation, comprising monitored temperature data around the equipment together with an amount of deviation when the equipment completes its operation. 2. The method of predicting an equipment deviation amount according to claim 1, wherein said environmental prediction data includes weather forecast data. 3. The method of predicting an amount of deviation of equipment according to claim 1, wherein said accumulated data includes data relating to the amount of solar radiation for an external environment of said equipment. 4. The method for predicting an amount of equipment deviation according to claim 1, wherein the accumulated data includes information on month and day as an element for predicting the degree of change of the amount of equipment deviation. 5. The method of predicting the amount of facility deviation according to any one of claims 1 to 4, wherein the accumulated data includes data on weather changes from the past to the present. 6. The method of predicting an amount of equipment deviation according to claim 1, wherein the accumulated data includes the history of equipment deviation from the past to the present. 7. The method of predicting an amount of equipment deviation according to claim 6, wherein equipment deviation due to artificial adjustment is excluded from the accumulated data. The equipment according to any one of claims 1 to 7, wherein the accumulated data includes a difference in equipment deviation between before and after the train passes in the equipment installed in the vicinity of the train passing position. How to predict the amount of deviation. The equipment bias according to any one of claims 1 to 8, wherein the prediction result and the actual measurement result regarding the degree of change in the equipment deviation amount are compared, and the algorithm for prediction is corrected based on the difference between the comparison results. How to predict displacement. The equipment deviation prediction method according to any one of claims 1 to 9, wherein a degree of change in lock deviation in said point machine as said equipment is predicted. A prediction system for the amount of displacement of equipment that expands and contracts at a point machine or a railroad crossing ,
an accumulated data management unit that manages accumulated data from the past to the present;
an environment prediction data acquisition unit that acquires environment prediction data about the external environment of the facility;
an equipment deviation prediction unit that predicts the degree of change in the equipment deviation from the current state based on the accumulated data and the environmental prediction data;
A system for predicting an amount of deviation in equipment, wherein the stored data includes temperature data around the equipment monitored together with an amount of deviation when the operation of the equipment is completed. 12. The equipment deviation amount prediction system according to claim 11, wherein the equipment deviation amount prediction unit predicts the degree of change in the lock deviation amount in the point machine as the equipment.

Images