JP6236688B2 - Overhead inspection system using time series filter processing - Google Patents

Description

  The present invention relates to an overhead wire inspection device for inspecting and measuring the displacement of overhead wires using time-series filter processing on distance data.

  In Non-Patent Document 1 (Genshiro Kitagawa, “Monte Carlo Filter and Smoothing,” Mathematical Statistics, Vol. 44, No. 1, pp. 31-48, 1996), the Monte Carlo filter (particle filter) is a time series filter. This is a method similar to the method called “.” (Hereinafter referred to as “particle filter”).

Here, the particle filter will be described with reference to FIG.
First, the upper part of FIG. 1 is a probability density distribution in which the horizontal axis indicates the state and the vertical axis indicates the probability. In this method, the state changes depending on the situation (overlapping line deflection, wear start position, wear width x number of overhead lines), but all of them are multi-dimensional. (For example, it can be regarded as a function representing the probability of overhead line deviation). The upper left of FIG. 1 shows a uniform probability density distribution of states (overhead position, wear width, etc.), and the upper center of FIG. 1 calculates the state distribution by applying a state transition model to the posterior distribution.

Next, the middle part of FIG. 1 shows the probability density distribution displayed in a discrete manner. A continuous function such as a probability density distribution cannot be calculated when it cannot be expressed by a mathematical expression, but a value close to the original probability density distribution can be calculated by discretization and approximation. This is shown as “approximation of probability density distribution” in the figure.
Here, it is discretized using the Monte Carlo method (a method of approximating with a product sum of discretized values instead of obtaining an integral value of a continuous function). In short, the discretization is performed densely at locations showing a high value in the probability density distribution and sparsely discretized at low locations.

In the middle left of Fig. 1, the probability density distribution is uniform, so discretization is performed at regular intervals. Further, the points expressed when discretized are called particles.
The lower part of FIG. 1 evaluates whether the discretized particles obtained in the middle part are likely. For this, observation data (for example, data in which information on overhead line deviation is observed) is used. Here, a high value is given if the particle is plausible, and a low value is given if it is not plausible. This is called likelihood. Likelihood is calculated from the observed data (posterior distribution).

A posteriori probability (posterior distribution) is obtained by performing likelihood evaluation on all particles. This is because if the probability density distribution given first is the prior probability, the posterior probability is obtained by Bayes' theorem using likelihood. Therefore, the lower figure shows the posterior probability.
Figure 1 shows how this changes from left to middle to right as observation data changes with time. Actually, it does not end on the right, but this process is performed for the time. This is described as “repeat” in the figure.

  Note that “the state center is calculated by applying the state transition model to the posterior distribution in the upper center of FIG. 1”. Here, the “state transition model” means, for example, an overhead line displacement of x1. If it is the position, it is the probability that it will be the position of x2 at the next time, and it is new by using a state transition model (also referred to as state transition probability, state transition equation) for the posterior distribution of the previous time A prior distribution (of the current time) can be obtained.

  Incidentally, the prior distribution actually obtained is discretized. In FIG. 1, the lower left posterior distribution is used in terms of processing, and the middle middle prior distribution is obtained. The upper diagram is an image of what happens if this prior distribution is expressed by a continuous function (probability density distribution).

  Patent Document 1 (Japanese Patent Application Laid-Open No. 2010-243417, “Trolley Line Inspection Device”) proposes an improvement in the method of installing a sensor for detecting overhead lines using a range sensor and detection of the trolley line thereby. Is going.

  In Patent Document 2 (Japanese Patent Application Laid-Open No. 2010-243416, “trolley wire inspection device and inspection method”), in order to detect a continuous overhead wire, the linearity is viewed or the search range is limited, thereby providing an overhead wire. The accuracy of detection has been improved.

JP 2010-243417 A JP2010-243416

Genshiro Kitagawa, "Monte Carlo Filter and Smoothing," Mathematical Statistics, Vol. 44, No. 1, pp. 31-48, 1996

  The method of Non-Patent Document 1 is a paper on particle filters related to the present invention. In the present invention, this particle filter is applied to perform overhead wire inspection.

  The method of Patent Document 1 discusses the sensor placement method, but the overhead line detection method itself uses the lowest point of the measurement data, and there are multiple overhead lines or crossover lines. It is not a very robust method and depends on the influence of noise.

  In the method of Patent Document 2, overhead lines can be processed together for several lines and the connectivity can be checked to check the overhead lines with high accuracy. It is a problem that the result changes depending on the direction.

  The overhead line inspection device according to claim 1 of the present invention that solves the above-described problem is an overhead wire inspection device that accurately measures overhead lines on a train by distance data processing using a stochastic time series filter. A distance data input unit for inputting distance data including deviation, overhead line width, and height of the overhead lines obtained by a distance measuring sensor disposed on the upper surface of the train; and deviation, overhead line width, A likelihood function using a particle initialization unit that prepares particles having random height values, particles prepared by the particle initialization unit, and distance data of the previous time input by the distance data input unit And a resampling unit that performs resampling so that particles having a high likelihood value are selected with a high probability based on the likelihood value calculated by the likelihood calculating unit. A sampling unit, characterized in that it consists of a state transition unit for creating a new particle is varied based on the parameters of the particles resampled to the state transition model by the resampler.

  The overhead line inspection / measurement apparatus according to claim 2 of the present invention for solving the above-mentioned problems is characterized in that, in claim 1, the overhead lines are single or a plurality of overhead lines.

  The overhead line inspection / measurement apparatus according to claim 3 of the present invention that solves the above-described problems is characterized in that, in claim 2, the overhead lines include a suspension line.

  The overhead line inspection / measurement apparatus according to claim 4 of the present invention for solving the above-described problems is characterized in that, in claim 2 or 3, the overhead lines include a crossover.

  The overhead line inspection / measurement apparatus according to claim 5 of the present invention for solving the above-mentioned problem is that, in claim 1, the likelihood function includes an absolute value of a difference between distance data before and after the overhead line area, and a previous time It is based on the deviation / overhead width / height of the overhead lines and the difference between the deflection / overhead width / height of the overhead lines at the current time.

(1) Predicted overhead lines using distance information of the previous line, that is, single or multiple overhead lines, suspension lines / overhead lines, suspension lines / overhead lines / suspended lines / crossover lines can be measured.
(2) Inspection of overhead lines, suspension lines, and crossover lines using the state transition equations using previously measured overhead lines, that is, single or multiple overhead lines, suspension lines and overhead lines, and suspension line, overhead lines, suspension lines, and transition lines information Measurement is possible.
(3) Overhead lines using prediction based on probability theory, that is, single or multiple overhead lines, suspension lines / overhead lines, suspension lines / overhead lines / suspended lines / crossover lines can be measured.

It is a schematic diagram of a particle filter. It is a flowchart of the overhead wire inspection apparatus which concerns on the 1st-4th Example of this invention. It is a block diagram of an overhead wire inspection apparatus according to first to fourth embodiments of the present invention. It is a graph which shows the relationship between the previous line and the next line. It is an image figure of the distance data acquired by a ranging sensor in time series.

  There is a desire to accurately measure the trajectory of overhead lines using distance data of one line acquired from a train upper surface using a distance measuring sensor. Here, in the present invention, the overhead line means a single or a plurality of overhead lines, and further includes a suspended overhead line and a crossover line.

  However, it is difficult to detect only the overhead line by simple processing because various data are measured as distance data and the measurement error is large. Although there are methods for detecting overhead lines from distance data as in Patent Documents 1 and 2, there are problems as described above.

  Therefore, in the present invention, the information on the overhead wire displacement and the information on the characteristics of the overhead wire, such as “the distance greatly changes before and after the overhead wire region” and “the overhead wire region does not change significantly from the deviation or height of the previous line”. Performs measurement using height distance data processing.

  First, since there is a feature that “the overhead line area does not change significantly from the deviation or height of the previous line”, the deviation of the overhead line is detected using a particle filter that is a time series filter effective for the tracking of Non-Patent Document 1. Estimate the height.

As a feature of the particle filter, prediction using time series information can be performed, and probability theory can be handled instead of determinism.
Since the state transition probability can be introduced into the prediction using the time series information, in addition to the above features, information known by past measurement can be used as a probability model (FIG. 1).

In the particle filter, calculation difficulty is eliminated by discretizing the probability density distribution by sampling.
This sampling point is called a particle. How likely each particle is as an optimal solution is obtained by likelihood calculation.

At this time, how to set the likelihood function is very important.
In the present invention, the likelihood is calculated by using a likelihood function considering a plurality of elements. First, the state vector of the particle filter is a three-dimensional vector of the displacement of the overhead line in one line, the width of the overhead line, and the height of the overhead line acquired by the distance measuring sensor.

  Next, as a likelihood function, a likelihood function was set in consideration of the fact that the distance data greatly changes before and after the overhead line region, and that the overhead line region and height do not change significantly from the deviation of the previous line.

  That is, the likelihood function is the absolute value of the difference between the distance data before and after the overhead line area, the deviation of the previous time (previous line), the overhead line width, the overhead line height and the deviation of the current time (current line), the overhead line Based on the difference between the width and the overhead line height (the higher the value is within the overhead line width, 0 when the distance is greater).

Specifically, the two are combined into a likelihood function. At present, the sum of all the values is used, but depending on the case, processing (weighted sum) is performed to increase the weight of each item. The likelihood value is the same as the likelihood.
In addition, since it is known that the shape of the overhead wire does not change significantly, it is possible to estimate a rough displacement of the next line using the previous line information as the displacement information. By using this information to define a state transition model, high-precision estimation is possible.

Specifically, we currently consider two cases and methods.
One is a method called “random walk” in which the transition of the overhead line is not known at all. This is a technique for randomly changing the state. This method is often used for particle filters. It is known that the overhead line deviation does not change significantly in the overhead line inspection, so a random walk is performed within the changeable range.

  The other is a case where the shape and self-position of the overhead wire are known in advance. In this case, since it is almost known where the deviation of the overhead line will come at the next time, the information is used as a state transition model.

  In the present invention, by using the probability density distribution as shown in FIG. 1, even if there is an error in the estimation on the previous line (the case with the highest probability), an error has occurred in the estimation of the next line. Since information other than the result can also be used, robust estimation of each line is possible as compared with the deterministic approaches such as Patent Documents 1 and 2.

  Here, the previous line and the next line have the same meaning as the data at the previous time and the data at the next time, as shown in FIG. That is, FIG. 4 is a graph in which the line data obtained by the distance measuring sensor is arranged in order of time. In the description of the present invention, the previous line and the next line are, for example, the time for the line data obtained at time t. Data obtained at t−1, data obtained at time t + 1.

  Further, in the present invention, instead of the approach of “detection of overhead lines” → “confirmation of continuity” as in Patent Document 2, “extraction of overhead lines in a continuous area” is performed, so that false detection is reduced. Detection accuracy can be improved.

In the description of FIG. 1 described above, the words “Monte Carlo method” and “particle” are used. A time-series filter that processes time-series data using these methods is called a “particle filter” or a “Monte Carlo filter”.
There are various derivations in the method of obtaining the prior distribution from the posterior distribution, such as "important sampling method" and "Markov chain Monte Carlo method", but basically all the methods of processing in the flow of Fig. 1 are "particle filter" and "Monte Carlo filter" Say.

  Although the concept is exactly the same, it is a technique often called a particle filter in recent years. Therefore, it is also called a particle filter in the present invention. In Non-Patent Document 1, since it was called a Monte Carlo filter, it was explained that it was the same, but the concept is exactly the same. Incidentally, in the present invention, a method called “important sampling” is used to obtain a prior distribution.

  There are various types of time series filters, and the “particle filter” used here is one of them. In addition, the “particle filter” is a probabilistic approach, so it can be called a probabilistic time series filter. So we used such names in the claims. Incidentally, other probabilistic time series filters include a “Kalman filter”, but the present invention uses only a particle filter.

Here, “determinism” and “probability theory” can be briefly compared as follows. Deterministic is to explain the state where the clouds are 30% in the sky as “clear”, and probability theory is to explain that it is “clear with 30% clouds”. The advantage of the probabilistic approach is that not only XX but also the degree can be considered.
“In determinism,“ extract overhead lines ”→“ confirm continuity ”. The problem is that even if you don't know if it's really correct, you run a determinism that says "This part is an overhead line" every time, and later decide that it is correct because it was continuous.

If it is wrong somewhere at one time, or if the overhead line cannot be imaged for some reason, the continuity is interrupted, resulting in erroneous recognition.
On the other hand, the probability theory evaluates the area that seems to be an overhead line at each time and its likelihood.

In the case of the deterministic method described above, a certain point is determined as an overhead line, but in the case of the probabilistic method, the likelihood (of each particle in the present invention) of multiple points is used. Judgment that is not performed can be made.
Here, the description has been made on the assumption that one distance measuring sensor is used. However, since the error is large, it is possible to perform overhead wire inspection with the same idea even when a plurality of distance measuring sensors are used together.

  The method of finding a deviation by a distance measuring sensor is based on a technique as in Patent Document 1, that is, using information that the overhead line is closer to the background than the background. “The distance changes greatly before and after the overhead line area” “The overhead line area does not change significantly from the deviation or height of the previous line” Only the overhead line satisfies this information, so the deviation sensor is used to measure the deviation. Is possible.

(1) Basic concept (Example 1)
An object of the present invention is to provide an overhead wire inspection device that measures the displacement, overhead wire width, and height of overhead wires with high accuracy by distance data processing using a time series filter.
In the following embodiment, as an example, a distance measuring sensor (not shown) is installed on the roof of the train so as to look up vertically upward, and the distance is measured along the sleeper direction so as to cross the overhead line. The distance data is acquired, and as shown in FIG. 5, the obtained distance data for one line is arranged in time series, thereby obtaining the overhead line deviation and the overhead line height in time series.

FIG. 5 shows distance data acquired in time series by the distance measuring sensor at times (t−1), t, and (t + 1).
As for the height from the distance measuring sensor to the overhead line 1, the height to the wear width A is L, and the height to the overhead line width B other than the wear width is L + α. When α is sufficiently small, the height L up to the wear width A is substantially equal to the height L + α up to other than the wear width.

The background area is theoretically infinite distance. A distance (direction of sleepers) from the reference point C to the center E of the wear width A or the overhead line width B is the deviation D.
In addition, since the distance sensor can acquire distance information with one unit, the height of overhead lines is required.

FIG. 3 shows an apparatus configuration example according to this embodiment.
The overhead line inspection device according to the present embodiment includes a distance data input unit 10, a storage unit 20, a particle initialization unit 30, a likelihood calculation unit 40, a resampling unit 50, and a state transition unit 60.

In the distance data input unit 10, distance data for one line acquired in time series by the distance measuring sensor is input and stored in the storage unit 20. The distance data includes information on overhead line displacement, overhead line width, and height.
The storage unit 20 stores various parameter data such as distance data, particle data, and state transition probabilities.

  The particle initialization unit 30 sets random parameters (overhead deflection, overhead line width, overhead line height) in a range and density set for a certain number of particles, and the range, density, and parameters of each particle are stored in the storage unit 20. store. The state vector of the particle filter is a three-dimensional vector of the displacement of the overhead line in one line, the width of the overhead line, and the height of the overhead line acquired by the distance measuring sensor.

The likelihood calculating unit 40 calculates the likelihood using the parameter and distance data of each particle based on the likelihood function, and stores the likelihood given to each particle in the storage unit 20.
The resampling unit 50 performs resampling so that particles having a high likelihood are selected with a high probability based on the likelihood.

The resampled particles are stored in the storage unit 20, and the particles used for the resampling are deleted.
The state transition unit 60 changes the parameters of the resampled particles based on the state transition model, creates new particles, and stores them in the storage unit 20. According to the new particles that were created, as a probability theory, overhead line displacement, overhead line width, and overhead line height were measured with high accuracy.

Here, the prior distribution in the initial state is usually unknown. Therefore, as shown on the left of FIG. 1, it is common to assume that the probability density distribution is a uniform distribution.
This uniform distribution is expressed by particles having a random value by the particle initialization unit 30, the likelihood is calculated by the likelihood calculation unit 40 using distance data for each particle, and the posterior distribution is calculated by the resampling unit 50. Is the procedure of this embodiment.

The “particle filter” is to process time-series data for each time using the Monte Carlo method and particles as described with reference to FIG. Therefore, the flow shown in the flowchart of FIG. 2 becomes the flow of the particle filter itself.
Further, “distance data processing using a time series filter” is a portion in which observation data (distance data) is used when likelihood calculation is performed.

A flowchart according to this embodiment is shown in FIG.
First, one line of distance data acquired in time series by the distance measuring sensor is input by the image input unit 10 (step S1).
Next, the particle initialization unit 30 prepares particles having random values in the ranges and densities set in the respective parameters (overhead line displacement, overhead line width, overhead line height) (step S2).

Subsequently, based on the likelihood function, the likelihood of each particle is calculated by the likelihood calculating unit 40 using the parameter and distance data of each particle (step S3).
Then, a resampling process is performed by the resampling unit 50 based on the likelihood, and a new particle is created by the state transition unit 60 by using the state transition model for the resampled particles (step S4).

  Thereafter, until the acquisition of time-series distance data by the distance measuring sensor is completed (step S5), the next newly acquired one-line image data is input (step S6), and the process returns to step S3.

As described above, according to the first embodiment, the following effects can be obtained.
(1) Overhead inspection by prediction using distance information of the previous line is possible.
(2) Overhead inspection using the overhead line information measured in the past as a state transition equation is possible.
(3) Overhead inspection using prediction based on probability theory is possible.

(2) Basic concept (Example 2)
An object of the present invention is to provide an overhead wire inspection device that measures the displacement and height of a plurality of overhead wires with high accuracy by distance data processing using a time series filter.

The difference from the first embodiment is that a plurality of overhead lines can be handled instead of a single overhead line.
In the first embodiment, each particle holds a three-dimensional parameter in order to obtain the overhead line displacement, the overhead line width, and the overhead line height at the same time. However, it is necessary to change this parameter when there are a plurality of overhead lines.

  Specifically, when there are two overhead wires 1a and 1b, the displacement of the overhead wire 1a, the width of the overhead wire 1a, the height of the overhead wire 1a, the distance between the overhead wire 1a and the overhead wire 1b (the displacement of the overhead wire 1a and the overhead wire 1b). Deviation), the width of the overhead line 1b, and the height of the overhead line 1b.

Using information on the widths of two overhead lines, which are known to some extent in advance, not only enables more accurate recognition than if there was only one overhead line, but also when the number of overhead lines changes It becomes possible to respond flexibly by changing the dimension of the particles.
Likelihood calculation is realized by associating the one used in Example 1 with the number of all overhead lines.

The apparatus configuration according to the present embodiment is the same as that of the first embodiment shown in FIG.
Therefore, the overhead line inspection device according to the present invention includes a distance data input unit 10, a storage unit 20, a particle initialization unit 30, a likelihood calculation unit 40, a resampling unit 50, and a state transition unit 60.

In the distance data input unit 10, distance data for one line acquired in time series by the distance measuring sensor is input and stored in the storage unit 20. The distance data includes information on overhead line displacement, overhead line width, and height.
The storage unit 20 stores various parameter data such as distance data, particle data, and state transition probabilities.

  The particle initialization unit 30 sets random parameters (distance of the overhead line, distance of multiple overhead lines, overhead line width for the number of overhead lines, height for the number of overhead lines) in a range / density set for a fixed number of particles. The range, density, and parameters of each particle are stored in the storage unit 20. When there are two overhead lines, the state vector of the particle filter is a 6-dimensional vector of the displacement of the overhead line, the width of the overhead line, and the height of the overhead line in one line acquired by the distance measuring sensor.

The likelihood calculating unit 40 calculates the likelihood using the parameter and distance data of each particle based on the likelihood function, and stores the likelihood given to each particle in the storage unit 20.
The resampling unit 50 performs resampling so that particles having a high likelihood are selected with a high probability based on the likelihood.

The resampled particles are stored in the storage unit 20, and the particles used for the resampling are deleted.
The state transition unit 60 changes the parameters of the resampled particles based on the state transition model, creates new particles, and stores them in the storage unit 20. According to the created new particles, as the probability theory, the overhead line displacement, the distance between a plurality of overhead lines, the overhead line width for the number of overhead lines, and the height for the number of overhead lines are measured with high accuracy.

The flowchart according to this embodiment is the same as that of the first embodiment shown in FIG.
First, one line of distance data acquired in time series by the distance measuring sensor is input by the image input unit 10 (step S1).
Next, particles having a random value in a range and density set in each parameter (overhead deflection, distance of a plurality of overhead lines, overhead line width for the number of overhead lines, height for the number of overhead lines) are initialized by the particle initialization unit 30. (Step S2).

Subsequently, based on the likelihood function, the likelihood of each particle is calculated by the likelihood calculating unit 40 using the parameter and distance data of each particle (step S3).
Then, a resampling process is performed by the resampling unit 50 based on the likelihood, and a new particle is created by the state transition unit 60 by using the state transition model for the resampled particles (step S4).

  Thereafter, until the acquisition of time-series distance data by the distance measuring sensor is completed (step S5), the next newly acquired one-line image data is input (step S6), and the process returns to step S3.

As described above, according to the second embodiment, the following effects can be obtained.
(1) Multi-line inspection by prediction using distance information of previous line is possible.
(2) Multi-line inspection using multi-line information measured in the past as a state transition equation is possible.
(3) Multiple overhead inspection using prediction based on probability theory is possible.

(3) Basic concept (Example 3)
An object of the present invention is to provide an overhead wire inspection device that accurately measures the displacement / height of a plurality of overhead wires and the displacement / height of a suspension wire by distance data processing using a time series filter. .
The difference from Example 2 is that it can respond not only to overhead lines but also to suspended overhead lines.

In the second embodiment, the particle parameters are maintained as three-dimensional parameters for one overhead wire. However, in this embodiment, the displacement, width, and height of the suspension wire are added. It will hold the dimension parameters.
Likelihood calculation is realized by adding a likelihood function to the likelihood used in Example 2 in consideration of a tendency that the distance of the suspension line is closer than the background. That is, the likelihood function is also based on the distance data between the overhead line and the suspension line and the distance data between the overhead line and the background.

The apparatus configuration according to the present embodiment is the same as that of the first embodiment shown in FIG.
Therefore, the overhead line inspection device according to the present embodiment includes a distance data input unit 10, a storage unit 20, a particle initialization unit 30, a likelihood calculation unit 40, a resampling unit 50, and a state transition unit 60.

In the distance data input unit 10, distance data for one line acquired in time series by the distance measuring sensor is input and stored in the storage unit 20. The distance data includes information on the displacement, width, and height of the overhead wire and the displacement, width, and height of the suspension wire.
The storage unit 20 stores various parameter data such as distance data, particle data, and state transition probabilities.

The particle initialization unit 30 sets random parameters (overhead deflection, overhead wire width, overhead wire height, suspension wire deflection, suspension wire width, suspension wire height) within the range and density set for a certain number of particles. The range / density / parameter of each particle is stored in the storage unit 20. In the case of a single overhead line / suspended line, the state vector of the particle filter holds 6-dimensional parameters in one line acquired by the distance measuring sensor.
The likelihood calculating unit 40 calculates the likelihood using the parameter and distance data of each particle based on the likelihood function, and stores the likelihood given to each particle in the storage unit 20.

The resampling unit 50 performs resampling so that particles having a high likelihood are selected with a high probability based on the likelihood.
The resampled particles are stored in the storage unit 20, and the particles used for the resampling are deleted.

  The state transition unit 60 changes the parameters of the resampled particles based on the state transition model, creates new particles, and stores them in the storage unit 20. According to the newly created particles, as the probability theory, the overhead line deviation, the overhead line width, the overhead line height, the suspension line deviation, the suspension line width, and the suspension line height are measured with high accuracy.

The flowchart according to this embodiment is the same as that of the first embodiment shown in FIG.
First, one line of distance data acquired in time series by the distance measuring sensor is input by the image input unit 10 (step S1).
Next, particles having a random value in the range and density set in each parameter (overhead deflection, overhead line width, overhead line height, suspension line deviation, suspension line width, and suspension line height) are initialized by the particle initialization unit 30. (Step S2).

Subsequently, based on the likelihood function, the likelihood of each particle is calculated by the likelihood calculating unit 40 using the parameter and distance data of each particle (step S3).
Then, a resampling process is performed by the resampling unit 50 based on the likelihood, and a new particle is created by the state transition unit 60 by using the state transition model for the resampled particles (step S4).

  Thereafter, until the acquisition of time-series distance data by the distance measuring sensor is completed (step S5), the next newly acquired one-line image data is input (step S6), and the process returns to step S3.

As described above, according to the third embodiment, the following effects can be obtained.
(1) Overhead / suspended line inspection by prediction using distance information of the previous line is possible.
(2) It is possible to perform overhead / suspended line inspection using information on overhead lines / suspended lines measured in the past as a state transition equation.
(3) Overhead / suspended line inspection using prediction based on probability theory is possible.

(4) Basic concept (Example 4)
The object of the present invention is to measure the displacement / height of a plurality of overhead wires, the displacement / height of a suspension wire and the displacement / height of a jumper wire with high accuracy by distance data processing using a time series filter. It is to provide an inspection device.

The difference from Example 3 is that it can cope not only with an overhead wire / suspended overhead wire but also with a jumper wire.
In Example 3, the particle parameters were maintained as 6-dimensional parameters for each overhead wire / suspension wire. However, in this example, the displacement / width / height of the jumper wire is added, so that one overhead wire / suspension wire is added. If there is a crossover line in addition to a 6-dimensional parameter, a 9-dimensional parameter is added by adding a 3-dimensional parameter.

  Likelihood calculation is realized by adding a likelihood function to the likelihood used in the third embodiment in consideration of a tendency that the distance of the crossover line is closer than the background. That is, the likelihood function is also based on the distance data between the overhead line and the crossover line and the distance data between the overhead line and the background.

The apparatus configuration according to the present embodiment is the same as that of the first embodiment shown in FIG.
Therefore, the overhead line inspection device according to the present embodiment includes a distance data input unit 10, a storage unit 20, a particle initialization unit 30, a likelihood calculation unit 40, a resampling unit 50, and a state transition unit 60.

  In the distance data input unit 10, distance data for one line acquired in time series by the distance measuring sensor is input and stored in the storage unit 20. The distance data includes information on the overhead wire displacement / overhead wire width / height, suspension wire displacement / suspension wire width / suspension wire height, and crossover wire displacement / overhead wire width / overhead wire height.

The storage unit 20 stores various parameter data such as distance data, particle data, and state transition probabilities.
In the particle initialization unit 30, random parameters (overhead line deviation, overhead line width, overhead line height, suspension line deviation, suspension line width, suspension line height, crossover line deviation, with a range and density set for a certain number of particles are set. Position, crossover line width, crossover line height) are set, and the range, density, and parameters of each particle are stored in the storage unit 20.

The likelihood calculating unit 40 calculates the likelihood using the parameter and distance data of each particle based on the likelihood function, and stores the likelihood given to each particle in the storage unit 20.
The resampling unit 50 performs resampling so that particles having a high likelihood are selected with a high probability based on the likelihood.

The resampled particles are stored in the storage unit 20, and the particles used for the resampling are deleted.
The state transition unit 60 changes the parameters of the resampled particles based on the state transition model, creates new particles, and stores them in the storage unit 20. According to the new particles that were created, the probability theory includes overhead wire displacement, overhead wire width, overhead wire height, suspension wire deflection, suspension wire width, suspension wire height, crossover wire displacement, transit wire width, and transit wire height. This means that the thickness was measured with high accuracy.

The flowchart according to this embodiment is the same as that of the first embodiment shown in FIG.
First, one line of distance data acquired in time series by the distance measuring sensor is input 2 by the image input unit 10 (step S1).
Next, the range set for each parameter (overhead wire deflection, overhead wire width, overhead wire height, suspension wire displacement, suspension wire width, suspension wire height, crossover wire displacement, crossover wire width, crossover wire height) Particles having a random density value are prepared by the particle initialization unit 30 (step S2).

Subsequently, based on the likelihood function, the likelihood of each particle is calculated by the likelihood calculating unit 40 using the parameter and distance data of each particle (step S3).
Then, a resampling process is performed by the resampling unit 50 based on the likelihood, and a new particle is created by the state transition unit 60 by using the state transition model for the resampled particles (step S4).

  Thereafter, until the acquisition of time-series distance data by the distance measuring sensor is completed (step S5), the next newly acquired one-line image data is input (step S6), and the process returns to step S3.

As described above, according to the fourth embodiment, the following effects can be obtained.
(1) Overhead, suspended and crossover lines can be inspected by prediction using distance information of the previous line.
(2) Overhead line, suspension line, and crossover line measurement using the information of overhead lines, suspension lines, and crossover lines measured in the past as state transition equations is possible.
(3) Overhead, suspended and crossover inspections using prediction based on probability theory are possible.

  INDUSTRIAL APPLICABILITY The present invention is widely applicable industrially as an overhead wire inspection device for inspecting and measuring overhead wire displacement using time series filtering.

10 distance data input unit 20 storage unit 30 particle initialization unit 40 likelihood calculation unit 50 resampling unit 60 state transition unit

Claims (5)

In an overhead line inspection device that measures the overhead lines on a train with high accuracy by distance data processing using a stochastic time series filter,
A distance data input unit for inputting distance data including displacement, overhead line width, and height of the overhead lines obtained by a distance measuring sensor disposed on the upper surface of the train;
A particle initialization unit for preparing particles having random values of the displacement, overhead line width, and height of the overhead lines;
A likelihood calculation unit that calculates a likelihood value based on a likelihood function using the particle prepared by the particle initialization unit and the distance data of the previous time input by the distance data input unit;
Based on the likelihood value calculated by the likelihood calculation unit, a resampling unit that performs resampling so that particles with a high likelihood value are selected with a high probability;
An overhead line inspection and measurement apparatus comprising: a state transition unit configured to change a parameter of the particles resampled by the resampler based on a state transition model to create a new particle.   The overhead line inspection device according to claim 1, wherein the overhead lines are single or a plurality of overhead lines.   The overhead line inspection device according to claim 2, wherein the overhead lines include a suspended overhead line.   The overhead line inspection device according to claim 2 or 3, wherein the overhead lines include crossovers.   The likelihood function includes the absolute value of the difference between the distance data before and after the overhead line area, the deviation of the overhead line at the previous time, the overhead line width, the height, and the deviation of the overhead line at the current time, the overhead line width, The overhead wire inspection device according to claim 1, wherein the overhead wire inspection device is based on a difference in height.