JP2021528302A - Systems and methods for traffic control on railway lines - Google Patents

Abstract

The present invention relates to systems and methods for traffic control on railway lines. The present invention also relates to corresponding uses. The present invention relates, in particular, to computing and predicting optimal routes for a plurality of trains, as well as optimizing train track capacity. The method includes the steps of controlling traffic on a railroad line, the method of sampling sensor data associated with a railroad line system through at least one sensor (200), and a sensor from at least one sensor (200). With the stage of using at least one server (500) to receive data, predict the state of the railway infrastructure based on all future vehicles, and control the traffic of all vehicles based on future conditions. ,including.

Description

The present invention is in the field of traffic control. The present invention is applicable in the field of traffic control on railway lines and therefore relates to systems and methods for traffic control on railway lines. The present invention specifically relates to the computing and prediction of optimal routes for a plurality of trains. The present invention further relates to optimization of train track capability.

[Introduction] Rail, rail line, or rail transport was developed to transport goods and passengers on wheeled vehicles on rails, also known as tracks. In contrast to road transport in which vehicles travel on a prepared plane, rail vehicles (all vehicles) are directionally guided by the tracks they travel. Tracks generally consist of sleepers (tiers or sleepers) and steel rails installed on ballast, on which all vehicles, usually equipped with metal wheels, travel. Other variations, such as slab tracks, where rails are fixed to a concrete foundation placed on the underground surface, are also conceivable.

Since all vehicles in a rail transport system generally experience lower frictional resistance than road vehicles, passengers and freight cars (passenger and freight cars) can be connected into longer trains. Power is provided by locomotives that either draw power from the railway line electrification system or generate their own power, usually by a diesel engine. Most orbits are accompanied by a signaling system. Railroad lines are a safer ground transportation system compared to other forms of transportation. In addition, rail lines are capable of achieving high levels of passenger and freight utilization as well as energy efficiency, but are often less flexible and more capital intensive than road transport given the lower levels of transportation. ..

Inspection of railway line equipment is essential for the safe movement of trains. Many types of defect detectors are used today. These devices utilize a variety of technologies, from simple paddles and switches to infrared and laser scans to ultrasonic audio analysis. With these, many railroad accidents have been avoided over the last few decades.

Another essential aspect of the safe movement of trains in controlling traffic on railway lines. Multiple coefficients and parameters play a role in the emergence of different scenarios on railway lines, where traffic on railway lines is concentrated to minimize the causes that can result in enormous economic and human losses. Monitoring must continue. In addition, poor traffic control can also exacerbate the impact of infrastructure failures on traffic on railway lines and can disrupt, for example, freight revenue operations and passenger services.

Unlike highways or road networks, where capacity is broken down into unlink trips on individual route sections, railway line capacity is essentially considered a network system. As a result, many factors can cause system interruptions. Railway line traffic control includes a myriad of route performances, such as train service types, number of tracks, train control types, train speeds, wear on tracks, pick times in railway networks, and circulation priorities. I have to confirm.

Rail line operation requires careful monitoring and control of traffic to ensure passenger safety and reliable service. Numerous sensors are used to monitor and obtain data from traffic on railway lines, and these sensors are used to ensure service integrity and to identify possible sources of dysfunction. May be done. Such sensors enable data collection and analysis and also ensure safer traffic on railway lines. Various sensors can be placed directly on the train, on or near the track, on the railway station and / or platform, and generally in the overall vicinity of the railway line.

The measurements of such sensors may be used for further measurement, control, prediction, and optimization of traffic control on railway lines. Several different attempts have been made to implement train traffic control systems and methods.

For example, US Pat. No. 6,179,252B1 discloses an invention relating to an intelligent intersection control system, which comprises, for example, an internal controller that receives a digital message containing detailed information items about train direction, speed, length, and identity. doing. The controller generates the appropriate commands to coordinate the functionality of the railroad crossing safety device. The controller can receive and use much more detailed train information than is possible with conventional warning systems. The railroad crossing warning function can respond more flexibly to this more detailed train information. The controller also continuously adjusts the activation state of the safety device associated with the railroad crossing. In certain embodiments, the control system is for the amount of time remaining at a railroad crossing until there is no train traffic, the approach of a second train while the first train is blocking the railroad crossing, or a waiting road vehicle. Proposal of Providing and displaying railroad crossing status information including alternative routes. The controller may be used to drive a number of standard railroad crossing warning functions, including railroad crossing blocking arms, flashing lights, warning chimes, and warning horns.

In addition, US Pat. No. 5,950,966A discloses a system for controlling train movement using a distributed architecture. The roadside controller receives signals from individual trains, including location information derived from the navigation system. The roadside controller interfaces with the central train control network and coordinates local train movements, including the issuance of incremental authorities.

Further, inventions of automatic vehicle control and placement systems have been proposed. For example, US Pat. No. 5,364,407A determines its own absolute position along a guideway based on information received from the roadside using a guidance loop or beacon system along with the distance traveled by the vehicle by an in-vehicle tachogenerator. The location can be reported to the roadside control device, which allows the roadside control device to report the location of the nearest forward obstacle to the vehicle as part of its communication message, a signaling and traffic control system. It is disclosed. Based on this information, the vehicle safely controls itself based on its characteristics contained in the terrain database and the vehicle database. This train control system is a train-focused block system (ie, a moving block). This system requires essential bidirectional data communication between the roadside and the vehicle and between adjacent control sectors.

In addition, U.S. Pat. No. 5,332,180A discloses a railway line traffic control system in which accurate vehicle information can be effectively used in real time to facilitate control of traffic flow. Unlike prior art methods of accurately monitoring train position, the present invention relies solely on vehicle-mounted equipment and position update information provided by external benchmarks placed along the track route. The dynamic motion capabilities of this system can also be used to detect and remember track rail signatures as a function of rail distance, which assists in determining rail and track conditions for preventative maintenance purposes. Therefore, it can be analyzed as a routine. In a currently preferred embodiment, the vehicle-mounted vehicle information detection device includes an inertial measurement unit that provides dynamic vehicle motion information to a position processor. Depending on the quantity and quality of prior knowledge of the vehicle route, the inertial measurement unit may be equipped with as many as three gyroscopes and as many as three accelerometers or only one accelerometer. To minimize errors between benchmarks, the processor preferably includes a recursive estimation filter for combining pre-route information with motion attributes derived from the inertial measurement unit.

Therefore, in view of the above, an object of the present invention is to overcome or at least alleviate the drawbacks and disadvantages of the prior art. More specifically, an object of the present invention is to provide a system and a method for traffic control on a railway line. A preferred object of the present invention is to disclose a control, monitoring, and processing system for sensor data related to traffic on a plurality of railway lines.

These objects are achieved by the present invention.

The present invention relates to methods and systems for controlling traffic on railway lines. In a first embodiment, the method may include sampling sensor data associated with the railway line system through at least one sensor.

The term sensor is intended to include at least one device, module, model, and / or subsystem that is intended to detect parameters and / or changes in its environment and provide their respective signals to other devices. Is intended for. It should be understood that the term "different types of sensors" is intended to mean sensors that are configured to measure the same parameters with different parameters or different techniques. An example of the latter is a laser or induction loop, both provided to measure velocity.

In addition, the term rail line system is intended to include rail line infrastructure and all vehicles. The term railway line infrastructure refers to railway tracks, total lines, tracks, electrification systems, sleepers (sleepers or crossties), tracks, rails, rail-based suspended railway lines, switches, flogs, switches, crossings, interlocking devices, sidings. , Masts, signaling equipment, electronic housings, structures, tunnels, railroad stations, and / or information computing networks are intended to be included. The railroad infrastructure basically includes any location on the railroad network where the sensors can be located, which allows the sampling of sensor data, including information that may be directly or indirectly related to railroad traffic. It should also be understood that it can be. In addition, the term all rolling stock refers to any rolling stock, wheeled rolling stock, powered and non-powered rolling stock, such as locomotives, rolling stock, passenger cars, freight cars, construction site vehicles, track bicycles, and / Or is intended to include trolleys and the like.

The present invention is configured to receive sensor data from at least one sensor, predict the state of the railway line infrastructure based on all future vehicles, and control the traffic of all vehicles based on future conditions. The use of at least one server may be further provided. Prediction and / or prediction is by predictive modeling, machine learning, and data mining that analyzes current and past facts to make predictions about future or otherwise unknown events. It should be understood that it is intended to mean predictive analysis involving various statistical techniques. It is also understood that the term server can also refer to computer programs and / or devices, and / or plural forms thereof, which may provide functionality to other programs, devices, and / or components of the invention. I want to be. For example, the server may provide various functions that may be referred to as services such as sharing data or resources among multiple clients, or performing computing and / or storage functions. It should be further understood that a single server may serve multiple clients and a single client may use multiple servers. In addition, the client process may run on the same device or connect to a server on a different device, such as a remote server or cloud, over the network. The server may have fairly primitive functions, such as transmitting fairly short information to another level of infrastructure, or it may have more sophisticated structures such as storage, processing, and transmission units. ..

In one embodiment of the invention, the method analyzes the sensor data processed to generate the processed sensor data and the sensor data processed to obtain information related to the railroad line system. It further includes a step, using the relevant information obtained for the routing plan for all vehicles, and sending the routing plan to at least one of the server and / or at least one authenticated user. It's fine. All vehicle routing is the following current or expected relevant information on the rail line: the technical state of the asset (ie, the technical state of the rail line infrastructure that may also include the effects of the infrastructure on all vehicles), all. Vehicle degradation effects (ie, effects on infrastructure caused by all vehicles), all vehicle traffic load information, risk of traffic delays, unplanned and / or planned maintenance and / or inspections, maintenance effectiveness metrics, and It may be based on at least one of the weather information.

In addition, the method may include subjecting relevant information obtained from sensor data to analysis via at least one analytical approach, each approach including signal filtering, pattern recognition, stochastic modeling, deep learning, machine learning, Supervised learning, unsupervised learning, enhanced learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction method, most probable estimation, modeling, estimation, neural network, convolution network, deep learning Includes at least one of convolutional networks, deep learning, ultra-deep learning, genetic algorithms, Markov models, and / or hidden Markov models.

In addition, the method of routing all vehicles is based on at least one analytical approach, where each approach is signal filtering, pattern recognition, stochastic modeling, Basian schemes, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistics. Analysis, Statistical Model, Principal Component Analysis, Independent Component Analysis (ICA), Dynamic Time Stretching, Most Probability Estimate, Modeling, Estimate, Neural Network, Convolution Network, Deep Convolution Network, Deep Learning, Ultra Deep Learning, Genetic Includes at least one of the algorithm, Markov model, and / or hidden Markov model. It should be understood that this is not an exhaustive list, and that, for example, the first analytical approach may differ from, for example, the second analytical approach. Further, it should be understood that the term analytical approach is intended to include any analytical tool used to analyze a signal or data and may also be referred to as an analytical method. These analytical methods can be applied continuously and / or in parallel, alone or in any combination thereof. Thus, different analytical approaches may differ solely with respect to the order of the plurality of analytical methods when one or more analytical method types and / or even the same method but only in a different order are used.

In one embodiment of the invention, the method may further include associating and / or arranging at least one sensor with at least one of all rolling stock and / or railway line infrastructure. It should be understood that this is not an exhaustive list of objects to which the sensor can be disengaged or fixedly assembled. The rail infrastructure may include, among other things, but not limited to, sleepers, flogs, switches, switch flogs, switch rail tips, and / or at least one of the interlocks to measure switch currents, especially in interlocks. It should also be understood that switch components may be included.

The method also involves using the server to provide at least one signal, including parameters that define the route of all vehicles, forecasting rail traffic, predicting the wear effect of all vehicles on the rail infrastructure. May include. In addition or alternatives, the method may be based on at least one analytical approach, where each approach is signal filtering, pattern recognition, stochastic modeling, Basian schemes, machine learning, supervised learning, unsupervised learning, reinforcement learning. , Statistical analysis, Statistical model, Principal component analysis, Independent component analysis (ICA), Dynamic time expansion and contraction method, Most probable estimation, Modeling, Estimate, Neural network, Convolution network, Deep convolution network, Deep learning, Ultra deep learning, Includes at least one of the genetic algorithm, Markov model, and / or hidden Markov model. In addition, the signal may be transmitted via wireless and / or hardwired means. Further, the present invention may provide a further step of associating, for example, first and second sensor data in order to obtain relevant information of railroad traffic, wherein the first sensor data is second. It can be advantageous as it can be possible to determine whether it has a direct or indirect effect, an impact, and / or vice versa on the analytical data.

The method is the stage of comparing the planning of routing with the current traffic on the railway line, the stage of providing and receiving feedback of the current traffic on the railway line, and / or the stage of providing the command to control the traffic on the railway line. , At least one may be further included. In addition or alternatives, the method may include a step of (semi) automatically controlling the routing of all vehicles in response to their wear effects on the railway line. Whenever the term (semi) automatic is used, step and / or process automation is preferred, eg, the method may include steps that (semi) automatically control the routing of all vehicles. It should be understood that the method may include a step of preferably automatically controlling the routing of all vehicles.

For example, the present invention may predict the future state of traffic on a railroad line by assessing the health of any asset involved. Therefore, multiple sources may be used to derive a health condition that reflects the actual use of the asset. As an example, the stress, and thus wear, of the flog (the intersection of two rails) is the main result of the train running on the flog and the temperature changing over time. The present invention can use continuously recorded and combined data to derive stresses and accumulate those stresses over time. In contrast to current state of the art, this stress reflects the train type, speed, oscillating force, temperature, and direction of travel of each passing train much more accurately than the estimated total ton approximate number passing through the asset. Calculated with consideration, this can be advantageous as it can provide information for optimizing route planning for all vehicles. The terms optimizing and / or optimizing are (semi-) automatic selections of the best available elements (with respect to some criteria) from a set of available alternatives. Please understand that it is intended to include. This can be the best value for an objective function given a defined domain (or input) that includes various different types of objective functions and different types of domains.

In addition, the present invention uses sensor data to generate signals for processing and / or machines to derive information such as longitudinal movement, vibration, train speed, train type from multiple data sources. Learning and artificial intelligence (AI) methods may be used. Therefore, the present invention is, for example, in order to collect accurate usage statistics and detect the unique attributes of trains (eg, so-called "flat wheels") that cause greater wear and wear on railway infrastructure, eg, vendor-specific trains. Using a "footprint", it may be possible to plan the routing of all vehicles based on data related to the train category (high-speed trains, passenger trains, freight trains). The present invention may associate all identified vehicles with optimal routing.

Further, in one embodiment of the invention, the method comprises at least one sensor data measurement, eg, but not limited to length, mass, time, current, voltage, temperature, humidity, photometric, and acceleration, vibration. , Speed, time, distance, lighting, image, gyroscopic information, acoustics, ultrasonic waves, pneumatics, magnetism, electromagnetics, position, optical sensor information, etc. It may also include the step of using the information sampled through at least one sensor to do so.

Furthermore, the method may include the step of (semi) automatically controlling the traffic and / or routing of all vehicles on the railway line. To this end, the method may use continuous data transmission. In another embodiment, the method may use periodic data transmission.

In another embodiment of the invention, the method may include storing all data generated by at least one server.

The system according to the present invention may particularly include at least one sensor configured to sample sensor data associated with the railway line system. In addition, the system is configured to receive sensor data from sensors, predict the future state of the railway infrastructure based on all future vehicles, and control the traffic of all vehicles based on the future state. It may also have at least one server.

The system is configured to analyze at least one sensor data processing component that is configured to generate processed sensor data and the sensor data that has been processed to generate a routing plan for all vehicles. It may further include at least one analytical component. In some cases this can be advantageous. Because this may allow the analytical component to associate the processed sensor data with the routing plan for all vehicles, eg, based on the first and second sensor data, i.e., thereby the analytical configuration. This is because elements can be able to correlate rail line traffic conditions based on the current, past, or future state of all vehicles and rail line infrastructure. Analytical components can be any that are configured to provide relevant data and may include local and / or remote and / or subelements. It should be understood that the term related data is intended to include at least two datasets that affect the other. One dataset can affect the other dataset, and / or those datasets influence each other and / or affect the integrated data and / or the integrated data. Affects the data derived from the set. It is not intended to contain mere cumulative data. A non-limiting example is one dataset (including train-specific data) that is integrated with another dataset (eg, including vibration data) and provides results that consider both datasets. obtain.

In one embodiment of the invention, the system also comprises at least one transmission component configured to transmit a route plan to at least one server and / or at least one authenticated user via an interface. good.

In addition, at least one analytical component of the system is the following current or expected relevant information on the railway line: technical status of assets, technical status of infrastructure components, degradation of all vehicles, traffic of all vehicles. All vehicle routing plans may be generated based on at least one of load information, traffic delay risk, unplanned and / or planned maintenance and / or inspection, maintenance effectiveness metrics, and weather information.

In another embodiment of the invention, at least one analytical component of the system may further include at least one analytical approach, each approach including signal filtering, pattern recognition, stochastic modeling, deep learning, machine learning, and more. Supervised learning, unsupervised learning, reinforcement learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction method, most probable estimation, modeling, estimation, neural network, convolution network, deep learning Includes at least one of convolutional networks, deep learning, ultra-deep learning, genetic algorithms, Markov models, and / or hidden Markov models.

Furthermore, in one embodiment of the invention, the server of the system may be configured to optimize the routing of all vehicles based on at least one analytical approach, where each approach is signal filtering, pattern recognition. , Probability modeling, Basian scheme, machine learning, supervised learning, unsupervised learning, enhanced learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction method, most probable estimation, modeling Includes at least one of estimation, neural network, convolution network, deep convolution network, deep learning, ultra deep learning, genetic algorithm, Markov model, and / or hidden Markov model.

The system may further include associating and / or arranging at least one sensor with at least one of all rolling stock and / or rail line infrastructure.

The system may retrieve relevant information from sensor data sampled through at least one sensor, such sampled data being sensor data measurements such as, but not limited to, length, mass, time. , Current, voltage, temperature, humidity, luminosity, and acceleration, vibration, speed, time, distance, illumination, image, gyroscopic information, acoustics, ultrasonic waves, air pressure, magnetism, electromagnetics, position, optical sensor information, etc. At least one piece of information for any parameter derived from it, such as, may be provided.

In one embodiment of the invention, the system delivers at least one signal that includes parameters defining the route of all vehicles, predicting rail traffic, and predicting the wear effect of all vehicles on the rail infrastructure. Further servers may be provided that are configured to provide. In addition or alternatives, at least one signal may be based on at least one analytical approach, where each approach is signal filtering, pattern recognition, probability modeling, deep learning, machine learning, supervised learning, unsupervised learning. , Enhanced learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction method, most probable estimation, modeling, estimation, neural network, convolution network, deep convolution network, deep learning, ultra Includes at least one of deep learning, genetic algorithms, Markov models, and / or hidden Markov models.

The system may further comprise at least one sensor that is configured to run in multiple modes of operation, which mode of operation can be configured to monitor multiple sensor data associated with the railway line system. ..

In another embodiment of the invention, the system may include interface components that are configured for bidirectional communication between at least one server and at least one authenticated user.

In addition or alternatives, the system is configured to monitor and predict the traffic of all vehicles on a railroad line, taking into account the future state of railroad line infrastructure maintenance based on at least one analytical approach. It may have at least one server, and each approach includes signal filtering, pattern recognition, stochastic modeling, basic schemes, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistical analysis, statistical models, principal component analysis, Independent Component Analysis (ICA), Dynamic Time Stretching, Most Probability Estimate, Modeling, Estimate, Neural Network, Convolution Network, Deep Convolution Network, Deep Learning, Ultra Deep Learning, Genetic Algorithms, Markov Model, and / or Hidden Includes at least one of the Markov models.

The system may also include at least one storage component that is configured to store all the data generated by at least one server.

Furthermore, the present invention may also include the use of embodiments of methods and / or embodiments of systems in traffic control. Furthermore, the present invention may include the use of embodiments of methods and / or systems for controlling traffic on railway lines.

The art is also defined by the numbered embodiments below.

Hereinafter, embodiments of the method will be discussed. These embodiments are abbreviated by the letter "M" followed by a number. References to embodiments of the method herein refer to these embodiments.

M1. How to control traffic on a railway line.

M2. The method according to a preceding embodiment, comprising the step of sampling sensor data associated with a railway line system via at least one sensor (200).

M3. The method according to any of the preceding embodiments, further comprising the step of using at least one server (500).

M4. At least one server
Receiving sensor data from at least one sensor (200)
Predicting the state of railway infrastructure based on all future vehicles,
Controlling the traffic of all vehicles based on future conditions,
The method according to any of the preceding embodiments, including.

M5. The method is
The stage of processing sensor data to generate processed sensor data, and
The stage of analyzing the sensor data processed to obtain information related to the railway line system, and
At the stage of using the relevant information obtained for planning the routing of all vehicles, and
The stage of sending a routing plan to the server and / or at least one of the authenticated users, and
The method according to embodiment M1 or M4, further comprising.

M6. All vehicle routing includes the following current or expected relevant information on railway lines:
The technical state of the asset,
Deterioration effect of all vehicles,
Deterioration of assets,
Traffic load information for all vehicles,
Risk of traffic delay,
Unplanned maintenance and / or inspection,
Planned maintenance and / or inspection,
Maintenance effectiveness metrics and
Weather information,
The method according to the preceding embodiment, based on at least one of the above.

M7. The method according to any of the preceding embodiments, with the features of embodiment M5, wherein the relevant information obtained from the sensor data is analyzed via at least one analytical approach.

M8. The method described in any of the preceding embodiments, with the features of embodiment M5, based on at least one analytical approach for routing of all vehicles.

M9. The method according to any of the preceding two embodiments, further comprising associating and / or arranging at least one sensor with at least one of all rolling stock and / or railway line infrastructure.

M10. The method is
Parameters that define the route of all vehicles,
Railroad traffic forecast,
Predicting the wear effect of all vehicles on the railway infrastructure,
The method according to any of the preceding embodiments, further comprising the step of using the server (500) to provide at least one signal comprising, wherein the at least one signal is based on at least one analytical approach.

M11. The method is
The stage of comparing routing plans with current traffic on railway lines,
The stage of providing and receiving feedback on current traffic on railway lines and / or
The stage of providing orders to control traffic on railway lines,
The method according to any of the preceding embodiments, further comprising at least one of.

M12. Machine learning and artificial intelligence (AI) to use sensor data to generate signals for processing and / or to derive information such as longitudinal movement, vibration, train speed, train type from multiple data sources. The method according to any of the preceding embodiments, further comprising the step of using the method of).

M13. The method according to any of the preceding embodiments, further comprising the step of (semi) automatically controlling the traffic and / or routing of all vehicles on a railway line.

M14. The step of (semi) automatically controlling the routing of all vehicles is the method described in any of the preceding embodiments, based on the wear action of all vehicles on the railway line.

M15. The method according to any of the preceding embodiments, comprising the step of using the information sampled through at least one sensor to recover the information of at least one sensor data measurement.

M16. The method according to any of the preceding embodiments, wherein the data transmission is continuous, with the characteristics of embodiment M7.

M17. The method according to any of embodiments M1 to M14, wherein the data transmission is periodic, with the features of embodiment M7.

M18. The method according to any of the preceding embodiments, further comprising storing all the data generated by at least one server.

Hereinafter, embodiments of the system will be discussed. These embodiments are abbreviated by the letter "S" followed by a number. References to embodiments of the system herein refer to these embodiments.

S1. A system that controls traffic (100) on a railway line.

S2. The system according to a preceding embodiment, comprising at least one sensor (200) configured to sample sensor data associated with the railway line system.

S3. the system,
Receives sensor data from the sensor (200) and
Predict the future state of railway infrastructure based on all future vehicles,
Control the traffic of all vehicles based on future conditions,
The system according to embodiment S1 or S2, further comprising at least one server (500) configured as such.

S4. The system according to embodiment S2 or S3, wherein the system further comprises at least one sensor data processing component (300) configured to generate processed sensor data.

S5. The system according to a preceding embodiment, further comprising at least one analytical component (400) configured to analyze sensor data processed to generate a routing plan for all vehicles.

S6. The system further comprises at least one transmission component (800) configured to transmit the route plan to at least one server (500) and / or at least one authenticated user via the interface (700). , The system described in the preceding embodiment.

S7. At least one analytical component (400) is the following current or expected relevant information on the railway line:
The technical state of the asset,
Deterioration effect of all vehicles,
Deterioration of assets,
Traffic load information for all vehicles,
Risk of traffic delay,
Unplanned maintenance and / or inspection,
Planned maintenance and / or inspection,
Maintenance effectiveness metrics and
Weather information,
The system according to a preceding embodiment that generates a routing plan for all vehicles based on at least one of the above.

S8. The system according to any of two preceding embodiments, wherein at least one analytical component (400) further comprises at least one analytical approach.

S9. The system according to any of the preceding system embodiments, wherein the server (500) is configured to optimize the routing of all vehicles based on at least one analytical approach.

S10. The system according to any of the embodiments of the preceding system, further comprising associating and / or arranging at least one sensor (200) with at least one of all rolling stock and / or railway line infrastructure.

S11. The system according to any of the embodiments of the preceding system, wherein the information sampled through at least one sensor (200) provides information on at least one sensor data measurement.

S12. The server (500)
Parameters that define the route of all vehicles,
Railroad traffic forecast,
Predicting the wear effect of all vehicles on the railway infrastructure,
The system according to any of the embodiments of the preceding system, wherein the at least one signal is configured to provide at least one signal comprising, based on at least one analytical approach.

S13. At least one sensor (200) is configured to run in multiple modes of operation, the mode of operation being configured to monitor multiple sensor data associated with the railway line system of the preceding system. The system according to any of the embodiments.

S14. Described in any of the embodiments of the preceding system, the server (500) comprises an interface component (700) configured to allow bidirectional communication between at least one server and at least one authenticated user. system.

S15. The server (500) further comprises monitoring and predicting the traffic of all vehicles on a railway line, taking into account the future state of railway infrastructure maintenance based on at least one analytical approach, an embodiment of a preceding system. The system described in any of.

S16. Described in any of the embodiments of the preceding system, wherein the system further comprises at least one storage component (600) configured to store all the data generated by at least one server (500). system.

Hereinafter, embodiments of use will be discussed. These embodiments are abbreviated by the letter "U" followed by a number. References made herein to embodiments of use mean these embodiments.

U1. Use of the system described in any of the preceding method embodiments in traffic control and / or any of the preceding system embodiments.

U2. Use of the system according to any of the embodiments of the preceding method for controlling traffic on a railway line and / or any of the embodiments of the preceding system.

Hereinafter, the present invention will be described with reference to the accompanying drawings showing embodiments of the present invention. These embodiments are merely exemplary of the invention and should not limit the invention.

It is a figure which shows the schematic example of the installation of a plurality of sensors in the railway line infrastructure which concerns on this invention. It is a schematic diagram of the system which controls the traffic in the railroad line which concerns on embodiment of this invention. It is a figure which shows the exemplary application of the traffic control system described in embodiment of this invention.

Note that not all drawings show all reference codes. Instead, in some drawings, some of the reference numerals have been omitted for the sake of simplicity and simplicity of the illustration. Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

FIG. 1 schematically illustrates a depiction of a system configured for a railway line infrastructure. Simply put, the system may include a railroad line section with railroad line 1 itself, including rails 2 and sleepers 3. Instead of the sleepers 3, a trackbed for the rail 2 may be provided.

Further, further examples of components are conceptually shown as masts conceptually identified by reference numeral 4. Such components are usually located near or near a railway line. Further, a tunnel conceptually identified by reference numeral 5 is shown. Needless to say, there are other structures, structures, etc., which may be used for the present invention described above and below.

For example, the first sensor 10 can be placed on one or more of the sleepers. The sensor 10 can be an accelerometer and / or any other type of railroad line specific sensor. Examples are mentioned above.

Furthermore, the second sensor 11 may be placed on another sleeper away from the first sensor 10. Although they appear to be very small distances in this example, these distances may range from the distance to the adjacent sleepers to a kilometer or more. Other sensors can also be used to attach to the sleepers. The sensor can also be of a different type. For example, if the first sensor 10 can be an accelerometer, the second sensor 11 can be a magnetic sensor or any other combination suitable for a particular need. Various sensors are listed above.

Another sensor 20, which may be a different or same type of sensor, can be attached to, for example, a mast 4 or any other structure. This may be something like a different type of sensor, such as an optical sensor, a temperature sensor, or even an accelerometer. Further types of sensors, such as the sensor 30, can be placed on the railway line at the starting point of the tunnel 5 or within the tunnel 5. This can be, for example, a height sensor, an optical sensor, a Doppler sensor, or the like that specifies the height of the train. It should be understood that all those sensors mentioned here and / or above are merely non-limiting examples. Further, the sensor can be configured to submit sensor data via a communication network such as a wireless communication network. Since this communication network has some advantages and disadvantages in terms of availability, transmission distance, cost, etc., the transmission of sensor data is optimized as described herein above and below.

FIG. 2 schematically shows a system 100 that controls traffic on a railway line. System 100 may include at least one data collection component identified by reference numeral 200. It should be understood that the data acquisition component 200 may include a plurality of sensors, a sensor system, or a plurality of sensor systems. Therefore, the data acquisition component 200 may be referred to as a plurality of sensors 200, a plurality of sensor systems 200, a sensor system 200, a sensor 200, or simply a sensor 200. The sensor 200 may be configured to sample traffic-related information on a railroad line, eg, vibrations caused by all vehicles passing a given track.

Further, the system 100 may also include a processing component 300. The processing component 300 may include a stand-alone component that is configured to receive information from the sensor 200. Simply put, the processing component 300 may be configured to allow the processing component 300 to communicate bidirectionally with the sensor 200.

In one embodiment, the processing component 300 may be integrated with at least one of the sensors 200. In other words, the processing component 300 may include an embedded module of the sensor 200.

In one embodiment of the invention, the processing component may communicate with an analytical component conceptually identified by reference numeral 400. Analytical component 400 may be configured to process sensor data based on at least one analytical approach, each approach being signal filtering, pattern recognition, stochastic modeling, deep learning, machine learning, supervised learning, Supervised learning, enhanced learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction, most probable estimation, modeling, estimation, neural network, convolution network, deep convolution network, deep Includes at least one of learning, ultra-deep learning, genetic algorithms, Markov models, and / or hidden Markov models.

Further, the analytical component may communicate with a data transmission component conceptually identified by reference numeral 800. The data transmission component 800 comprises one or more modules configured to receive information from the analysis component 400 and further transmit the received information to a server conceptually identified by reference numeral 500. May include. The data transmission component 800 may be referred to as a transmitter 800.

In another embodiment of the invention, the sensor 200, the processing component 300, the analysis component 400, and the data transmission component 800 are configured to continuously perform tasks corresponding to each individual component. It may include an integrated module. Simply put, in one embodiment, the sensor 200, the processing component 300, the analysis component 400, and the transmitter 800 may include a module consisting of a single component.

The data transmission component 800 may be configured to establish bidirectional communication with the server 500. In other words, the server 500 may collect information from the data transmission component 800 and may further provide the transmitter 800 with information, such as operating parameters. It should be understood that each component may receive a plurality of operating parameters, eg, the processing component 300 may be commanded to perform preprocessing of data received from the sensor 200. Alternatively or additionally, the processing component 200 may be instructed to transmit the original data received from the sensor 200, i.e., the data arriving from the sensor 200 will be next without performing any further tasks. It can be transferred directly to the component. The component so as to simultaneously perform a plurality of tasks, for example, processing of data arriving from the sensor 200 prior to transfer to the next component, and transfer of data arriving from the sensor 200 without any processing. Please understand that it may be configured.

In one embodiment, the server 500 may include a cloud server, a remote server, and / or a collection of different types of servers. Therefore, the server 500 may be referred to as a cloud server 500, a remote server 500, or simply the server 500. In another embodiment, the server 500 may converge to a central server.

It should be understood that the server 500 may bidirectionally communicate with the storage and interface components conceptually identified by reference numerals 600 and 700, respectively.

The storage component 600 may be configured to receive information from the server 500 for storage. Simply put, the storage component 600 may store the information provided by the server 500. The information provided by the server 500 may include, for example, but is not limited to data acquired by the sensor 200, data processed by the processing component 300, and any additional data generated by the server 500. The server 500, among other things, reads the data allocated in the storage component 600, writes and overwrites the data stored in the storage component 600, and controls and modifies the storage logic and data distribution within the storage component 600. It should be understood that access to the storage component 600, including permissions, may be granted.

In one embodiment of the invention, the server 500 may be configured to transmit signals to other components of the railway line system based on the traffic information recovered from the sensor 200. For example, given traffic data is provided by server 500, which subsequently generates a signal containing instructions, which is sent to the railway line system for implementation. The set of instructions may include, among other things, the switching of a train from one track to another to allow another train to continue its route. In addition, the signal may be based on at least one analytical approach, where each approach is signal filtering, pattern recognition, stochastic modeling, Bayesian schemes, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistical analysis, statistics. Model, Principal Component Analysis, Independent Component Analysis (ICA), Dynamic Time Stretching, Most Probability Estimate, Modeling, Estimate, Neural Network, Convolution Network, Deep Convolution Network, Deep Learning, Ultra Deep Learning, Genetic Algorithm, Markov Includes at least one of the model and / or hidden Markov model.

The interface component 700 may include a bidirectional communication component that is configured to exchange information with the server 500. In one embodiment, the interface component 700 may include a plurality of software interfaces having different levels, for example, the interface component 700 is a dedicated software front that operates, controls, and / or improves rail line traffic. May include an end. In another embodiment, the interface component 700 may include a physical terminal that provides the authenticated user with access to the server 500. Further, the interface component 700 may be configured to facilitate the provision of instructions to the server 500 and / or to request information such as traffic data acquired by the sensor 200 from the server 500. Such a set of requests and / or information may be referred to as a query.

System 100 may be applied to control traffic in a railway network. For example, a railway network may consist of a plurality of tracks, which may be referred to as railroad tracks. FIG. 3 shows an example of a section 1000 of a railway network in which trains A and B can circulate through tracks, eg, 1 and 2 which may be connected via a switch 3. The connection switch 3 is configured to allow passage from one track to any other track in a section of the railway network, for example, passage from track 1 to track 2 through the connection switch 3 and / or vice versa. You may take. The activation of the switch 3 may be controlled by the server 500, and the server 500 may provide an operation command based on the traffic data acquired from the sensor 200.

In one embodiment, the sensor 200 may be configured to allow, among other things, to identify trains, train speeds, and train wear effects on orbit. The data collected by the sensor 200 may constitute the basis for the server 500 to generate an instruction to activate the switch. Simply put, when a train is approaching this part of the railway network, the sensor 200 activates a switch to turn the train from, for example, track 1 to track 2 according to the speed and / or wear action of the train. Data that can be converted may be collected. The data collected by the sensor 200 may be communicated to the server 500, which may then send the information and corresponding instructions to the nearest asset, eg, the nearest switch, as a result. This nearest switch can be activated to control traffic in orbit. Further, in one embodiment of the invention, the system 100 may calculate the wear effect of all vehicles during a particular approach on individual switches in a given section of the network based on at least one analytical approach. , Each approach is signal filtering, pattern recognition, probability modeling, Bayesian scheme, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistical analysis, statistical model, principal component analysis, independent component analysis (ICA), dynamics. Includes at least one of target time expansion and contraction, most probable estimation, modeling, estimation, neural network, convolution network, deep convolution network, deep learning, ultra deep learning, genetic algorithm, Markov model, and / or hidden Markov model. ..

In another embodiment of the invention, the system 100 allows all specific vehicles, such as train A, to undergo greater wear action on the already more worn switches 1.4 and 2.4 of line 3, thus. For example, it may be determined that all vehicles may be rerouted to pass switches 1.5 and 2.5 of route 4. In addition, system 100 ensures that the trajectory of all other vehicles, such as train B, is unaffected.

In one embodiment of the invention, the system 100 will pass, for example, track 2 if all specific vehicles pass the track at a certain speed while other similar train types pass through normal track 1. For example, it may be determined that less wear can be received. This approach can be advantageous as it can reduce track wear and / or allow switching by evaluation and selection of the train's optimal route based on accurate circulation characteristics at train time. In addition, the system 100 may predict the future state of the railroad network based on the ability to determine optimal routing of all vehicles using data analysis based on at least one analytical approach, with each approach Signal filtering, pattern recognition, stochastic modeling, Basian schemes, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistical analysis, statistical models, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction, It includes at least one of the most probable estimation, modeling, estimation, neural network, convolution network, deep convolution network, deep learning, ultra deep learning, genetic algorithm, Markov model, and / or hidden Markov model.

For example, if all vehicles, such as train A, are approaching a recently maintained switch, such as switch 1.4, while another switch, such as switch 1.5, is approaching a maintenance cycle. The system 100 may decide to keep train A on track 1 until all vehicles reach a switch that is approaching a maintenance cycle to be performed. Subsequently, the system 100 may reroute train A to track 2 via switch 1.5 instead of switch 1.4. Such an approach can be advantageous as it can allow for maximization of the asset lifecycle. In other words, such an approach may enable optimal use of railway lines taking into account the health, maintenance and / or inspection plans of the asset.

In addition, the system 100 may be able to determine which route must be maintained to ensure optimum track performance and traffic on the railway line. More simply, based on the current conditions of the switch engine, eg, switch 2.4, the system 100 is optimal to maintain the position of the switch under that condition, i.e. do not move the switch under that condition. It may be identifiable as to what is best. As a result, the system 100 may be able to determine whether the routes of all vehicles arriving through sections of the railway network, such as switch 2.4, should be maintained in one particular position. In addition, how long the system 100 must maintain the route based on future conditions, as long as the conditions associated with the railway line (eg, wear, speed) guarantee optimal routing for traffic conditions. That is, the system 100 may be able to identify whether the routes of all vehicles may be maintained unchanged, or whether the conditions require the routes to be maintained unchanged.

More simply, the decisions of System 100 are, for example, not limited to, directly to control traffic on railway lines, taking into account other rules of traffic control such as stop at stations, speed limits, and safety regulations. May be used. In addition, the decisions of the system 100 may be communicated to a common traffic control system, which may further consider its data when controlling traffic in a plurality of rail line systems. Such route planning may take into account past and present information related to the railroad system, the analysis for predicting future conditions may be based on at least one analytical approach, and each approach is a signal. Filtering, pattern recognition, stochastic modeling, Basian schemes, machine learning, supervised learning, unsupervised learning, enhanced learning, statistical analysis, statistical models, principal component analysis, independent component analysis (ICA), dynamic time expansion and contraction, most Includes at least one of probability estimation, modeling, estimation, neural network, convolution network, deep convolution network, deep learning, ultra deep learning, genetic algorithm, Markov model, and / or hidden Markov model.

In the above, preferred embodiments have been described with reference to the accompanying drawings, but those skilled in the art will appreciate this embodiment solely for illustrative purposes and the scope of the invention as defined by the claims. You will understand that it should never be interpreted as limiting.

Whenever a relative term such as "about," "substantially," or "almost" is used herein, such term should be construed to include the exact term. That is, for example, "substantially straight" should be interpreted as including "(completely) straight".

It should be noted that the order of the steps described in this document may be accidental whenever the claims are mentioned above or in the appended claims. That is, unless otherwise specified, or otherwise unclear to one of ordinary skill in the art, the order of the steps described may be accidental. That is, if the document states, for example, that the method comprises steps (A) and (B), this does not necessarily mean that step (A) precedes step (B). However, it is also possible that step (A) is (at least partially) performed at the same time as step (B), or that step (B) precedes step (A). Furthermore, if we say that step (X) precedes another step (Z), this does not imply that there is no step between steps (X) and (Z). That is, the stage (X) preceding the stage (Z) is not only a situation in which the stage (X) is executed immediately before the stage (Z), but also one or more stages (Y1) of (X). It also includes situations where it is executed before .., followed by stage (Z). When using terms such as "after" or "before", the corresponding considerations apply.

Claims (15)

It is a method of controlling traffic on a railway line, and the above method is
At the stage of sampling sensor data related to the railway line system through at least one sensor,
The sensor data is received from the at least one sensor, and the sensor data is received.
Predict the state of railway infrastructure based on all future vehicles,
Control the traffic of all vehicles based on the above conditions in the future,
And at the stage of using at least one server,
Including methods. The stage of processing the sensor data so as to generate the processed sensor data, and
The stage of analyzing the processed sensor data to obtain information related to the railway line system, and
The stage of using the relevant relevant information obtained for planning the routing of all vehicles, and
The stage of transmitting the plan of the route to at least one of the server and / or at least one authenticated user, and
The method according to claim 1, further comprising. The routing of all vehicles is based on the following current or expected relevant information on the railway line:
The technical state of the asset,
Deterioration effect of all vehicles,
Deterioration of assets,
Traffic load information for all vehicles,
Risk of traffic delay,
Unplanned maintenance and / or inspection,
Planned maintenance and / or inspection,
Maintenance effectiveness metrics and
Weather information,
2. The method of claim 2, based on at least one of the above. The method of claim 2 or 3, wherein the analysis of the relevant information obtained from the sensor data and / or the routing of all the vehicles is based on at least one analytical approach. The method of any one of claims 1-4, wherein the method further comprises associating and / or arranging at least one sensor with at least one of all rolling stock and / or railway line infrastructure. The method is
Parameters that define the route of all vehicles,
Railroad traffic forecast,
Prediction of wear on all vehicles on the railway infrastructure,
Comparison of the route plan with the current traffic on the railway line,
Providing feedback on current transportation on railway lines,
Providing instructions to (semi) automatically control traffic on the railway line,
Providing instructions to (semi) automatically route all vehicles on railway lines,
The method of any one of claims 1-5, comprising the step of using the server to provide at least one signal, wherein the at least one signal is based on at least one analytical approach. .. A system for controlling traffic on railway lines
With at least one sensor configured to sample sensor data associated with the railway line system,
The sensor data is received from the sensor, and the sensor data is received.
Predict the future state of railway infrastructure based on all future vehicles,
Control the traffic of all vehicles based on the future conditions,
With at least one server configured to
The system. With at least one sensor data processing component configured to generate processed sensor data,
With at least one analytical component configured to analyze the processed sensor data to generate a routing plan for all vehicles.
With at least one transmission component configured to transmit the plan of the route to at least one server and / or at least one authenticated user via an interface.
7. The system according to claim 7. The at least one analytical component is the following current or expected relevant information on the railway line:
The technical state of the asset,
Deterioration effect of all vehicles,
Deterioration of assets,
Traffic load information for all vehicles,
Risk of traffic delay,
Unplanned maintenance and / or inspection,
Planned maintenance and / or inspection,
Maintenance effectiveness metrics and
Weather information,
8. The system of claim 8, which generates a routing plan for all vehicles based on at least one of the above. The system of claim 8 or 9, wherein the at least one analytical component and / or the server optimizes the routing of all the vehicles based on at least one analytical approach. The system of any one of claims 7-10, further comprising associating and / or arranging at least one sensor with at least one of all rolling stock and / or railway line infrastructure. The system according to any one of claims 7 to 11, wherein the information sampled through the at least one sensor provides information on at least one sensor data measurement. The server
Parameters that define the route of all vehicles,
Monitoring of all vehicle traffic, taking into account the future conditions of the railway infrastructure,
Forecasting railway line traffic, taking into account the future state of the railway line infrastructure,
Prediction of wear on all vehicles on the railway infrastructure,
The system according to any one of claims 7 to 12, wherein the at least one signal is configured to provide at least one signal comprising, and the at least one signal is based on at least one analytical approach. 7. The at least one sensor is configured to perform in a plurality of operating modes, the plurality of operating modes being configured to monitor a plurality of sensor data associated with a railroad line system, claim 7. The system according to any one of 13 to 13. The system according to any one of claims 7 to 14, wherein the server includes an interface component configured for bidirectional communication between the at least one server and at least one authenticated user.

Images