System and method for predicting rail track surface damage

Abstract

According to some embodiments, a method includes accessing track geometry data for a railway track. The track geometry data includes historical measurements for multiple types of surface conditions for the railway track over a period of time. The method also includes determining, by analyzing the track geometry data for a particular type of surface condition, a plurality of measurements that exceed a predetermined value. The method also includes identifying, by clustering the plurality of measurements that exceed the predetermined value, a particular track location on the railway track as a progressive defect location. The method also includes determining, using a remaining useful life model and the track geometry data for the particular type of surface condition at the progressive defect location, a future time at which the particular type of surface condition at the progressive defect location will exceed a predetermined limit.

Description

Technical Field

[0001] This disclosure generally relates to the condition of railway track surfaces, and more specifically to systems and methods for predicting railway track surface degradation. Background Technology

[0002] Trains typically consist of a locomotive and one or more carriages, traveling on railway tracks to transport passengers and goods. A typical railway track consists of two rails laid parallel to each other, providing the surface on which the wheels of the carriages can move and be guided. The parallel rail lines can be attached to sleepers, which are laid perpendicular to the rails and provide structural support for the railway track. Each rail in a railway track can consist of multiple rail sections. For example, each of multiple rail sections can be connected end-to-end to another rail section to form a single rail of the railway track.

[0003] Due to various factors such as weather and train traffic, the surface of railway tracks can deteriorate over time. For example, rails may sink or bulge, and this can worsen over time. Similarly, the elevation difference between the left and right rails may increase over time, causing the track to become uneven. Such track surface damage is dangerous and must be monitored and repaired. However, current technologies for monitoring track surface damage are often reactive in nature, addressing problems only after they have progressed to unacceptable levels. Summary of the Invention

[0004] This disclosure offers technical advantages by providing a system, method, and computer-readable storage medium for predicting surface damage on railway tracks. This disclosure provides a system that can be integrated into practical applications and has meaningful limitations, which may include: accessing track geometry data of the railway track. This track geometry data includes historical measurements of various types of surface conditions for the railway track over a period of time and may be captured by sensors from aircraft (e.g., drones), locomotives, robotic trolleys, railway inspection vehicles, etc. Other meaningful limitations of the system integrated into practical applications include: identifying multiple measurements exceeding predetermined values ​​by analyzing track geometry data for a specific type of surface condition; identifying specific track locations on the railway track as progressive defect locations by clustering the multiple measurements exceeding predetermined values; and determining the future time at which the specific type of surface condition at the progressive defect location will exceed a predetermined limit using a remaining service life model and track geometry data for that specific type of surface condition at the progressive defect location.

[0005] This disclosure addresses the technical problem of a lack of technical functionality for monitoring railway track defects by providing a method and system that automatically analyzes track geometry data and then predicts the future time at which a specific type of surface condition at the location of an incremental defect will exceed a predetermined limit. The technical solution provided herein—lacking in conventional systems—is not merely the application of manual processes to a computerized environment, but includes functionality for implementing a technical process that complements current manual solutions for monitoring railway track defects by providing a mechanism for automatically determining the future time at which a specific type of surface condition at the location of an incremental defect will exceed a predetermined limit. In doing so, this disclosure goes far beyond simply applying manual processes to a computer.

[0006] Unlike existing solutions that may require manual monitoring of railway track defects, embodiments of this disclosure provide a system and method for automatically determining the future time when a specific type of surface condition of a railway track will exceed a predetermined limit. By providing the future time when a specific type of surface condition of a railway track will exceed a predetermined limit, railway track safety and availability / efficiency can be improved. Other technical advantages will become apparent to those skilled in the art from the following figures, description, and claims. Furthermore, while specific advantages have been listed above, various embodiments may include all, some, or none of the listed advantages.

[0007] Therefore, this disclosure discloses concepts inextricably linked to computer technology, providing the technical benefits of implementing a function for automatically analyzing track geometry data of railway tracks and then predicting the future time when a specific type of surface condition at the location of progressive defects will exceed predetermined limits. The systems and techniques implemented provide improved systems by offering the ability to perform functions that are currently not possible to perform manually, as well as functions that are currently impossible to perform manually.

[0008] One object of the present invention is to provide a system for automatically analyzing track geometry data of a railway track and then predicting the future time when a specific type of surface condition at the location of an asymptotic defect will exceed a predetermined limit. Another object of the present invention is to provide a method for automatically analyzing track geometry data of a railway track and then predicting the future time when a specific type of surface condition at the location of an asymptotic defect will exceed a predetermined limit. A further object of the present invention is to provide a computer-based tool for automatically analyzing track geometry data of a railway track and then predicting the future time when a specific type of surface condition at the location of an asymptotic defect will exceed a predetermined limit. These and other objects are achieved by the present disclosure, which includes at least the following embodiments.

[0009] In one embodiment, a system includes one or more memory units and one or more computer processors communicatively coupled to the one or more memory units. The one or more computer processors are configured to access track geometry data of a railway track. The track geometry data includes historical measurements of various types of surface conditions of the railway track over a period of time. The one or more computer processors are further configured to: determine multiple measurements exceeding predetermined values ​​by analyzing the track geometry data for a specific type of surface condition. The one or more computer processors are further configured to: identify specific track locations on the railway track as progressive defect locations by clustering the multiple measurements exceeding the predetermined values. The one or more computer processors are further configured to: determine the future time at which the specific type of surface condition at the progressive defect location will exceed a predetermined limit, using a remaining service life model and track geometry data for the specific type of surface condition at the progressive defect location.

[0010] In another embodiment, a method includes accessing track geometry data of a railway track. The track geometry data includes historical measurements of various types of surface conditions for the railway track over a period of time. The method further includes identifying multiple measurements exceeding predetermined values ​​by analyzing the track geometry data for a specific type of surface condition. The method also includes identifying a specific track location on the railway track as a progressive defect location by clustering the multiple measurements exceeding the predetermined values. The method further includes determining, using a remaining service life model and track geometry data for the specific type of surface condition at the progressive defect location, the future time at which the specific type of surface condition at the progressive defect location will exceed a predetermined limit.

[0011] In another embodiment, one or more computer-readable non-transitory storage media contain instructions that, when executed by a processor, cause the processor to perform operations including: accessing track geometry data of a railway track. The track geometry data includes historical measurements of various types of surface conditions for the railway track over a period of time. The operation further includes: identifying multiple measurements exceeding predetermined values ​​by analyzing the track geometry data for a specific type of surface condition. The operation further includes: identifying a specific track location on the railway track as a progressive defect location by clustering the multiple measurements exceeding the predetermined values. The operation further includes: using a remaining service life model and track geometry data for the specific type of surface condition at the progressive defect location, determining the future time at which the specific type of surface condition at the progressive defect location will exceed a predetermined limit.

[0012] The features and technical advantages of the invention have been broadly outlined above to facilitate a better understanding of the subsequent detailed description of the invention. Additional features and advantages of the invention that form the subject matter of the claims will be described below. Those skilled in the art will understand that the disclosed concepts and specific embodiments can be readily used as the basis for modifications or the design of other structures for achieving the same purpose as the invention. Those skilled in the art will also recognize that such equivalent constructions do not depart from the spirit and scope of the invention as set forth in the appended claims. Novel features considered characteristic of the invention, both in their organization and manner of operation, together with further objects and advantages, will be better understood from the following description when considered in conjunction with the accompanying drawings. However, it should be clearly understood that each drawing is provided for illustrative and descriptive purposes only and is not intended to be a definition of limitation of the invention. Attached Figure Description

[0013] To gain a more complete understanding of the invention, reference is now made to the following description in conjunction with the accompanying drawings, in which: Figure 1 This is a schematic diagram illustrating a system for predicting damage to the surface of railway tracks, based on a specific implementation plan.

[0014] Figures 2A-2C Examples are given of what can be achieved by implementing a specific scheme. Figure 1 The system analyzes various track surface defects.

[0015] Figure 3 This is a flowchart illustrating an example method for predicting damage to railway track surfaces, based on a specific implementation plan.

[0016] Figure 4 This is an example based on a specific implementation plan. Figure 3 A chart providing an overview of the data manipulation methods.

[0017] Figure 5A This is an example based on a specific implementation plan. Figure 3 A graph of the clustering operations of the method.

[0018] Figure 5B This is an example based on a specific implementation plan. Figure 5A The chart highlights the maximum absolute value of the defective areas.

[0019] Figure 6 This is an example of a specific implementation plan. Figure 3 The method used to determine the example regression line in the graph.

[0020] Figure 7 This is a chart illustrating example channel limits based on a specific implementation plan.

[0021] Figure 8These are example computer systems that, according to specific implementation schemes, can be used to implement various aspects of the technologies presented herein.

[0022] It should be understood that the accompanying drawings are not necessarily drawn to scale, and the disclosed embodiments are sometimes illustrated schematically and in partial views. In some cases, details that are not essential for understanding the disclosed methods and apparatus or that make other details difficult to perceive may have been omitted. Of course, it should be understood that the invention is not limited to the specific embodiments illustrated herein. Detailed Implementation

[0023] The disclosure and its various features and advantageous details presented in the following written description are explained more fully with reference to the accompanying drawings and non-limiting embodiments as detailed in the specification. Descriptions of well-known components have been omitted so as not to unnecessarily obscure the key features described herein. The embodiments used in the following description are intended to facilitate an understanding of how the invention can be practiced and carried out. This disclosure will be interpreted by those skilled in the art as meaning that any suitable combination of the following functions or exemplary embodiments can be combined to achieve the claimed subject matter. This disclosure includes structural features common to a representative number of species or members of a genus falling within its scope, enabling those skilled in the art to identify members of that genus. Therefore, these embodiments should not be construed as limiting the scope of the claims.

[0024] Those skilled in the art will understand that any system claims presented herein encompass all elements and limitations disclosed therein, and therefore each system claim is required to be considered as a whole. Any reasonably foreseeable items functionally related to the claims are also relevant. Having obtained a thorough understanding of the disclosure and claims of this application, the examiner has searched for prior art disclosed in patents and other published documents (i.e., non-patent literature). Therefore, as demonstrated by the grant of this patent, the prior art fails to disclose or teach the elements and limitations presented in the claims as supported by the specification and drawings, thereby rendering the presented claims patentable under the applicable laws and rules of this jurisdiction.

[0025] Trains—which typically consist of a locomotive and one or more carriages—travel on railway tracks to transport passengers and goods. A typical railway track consists of two rails laid parallel to each other, providing a surface on which the train's wheels can move and be guided. The parallel rail lines can be attached to sleepers, which are laid perpendicular to the rails and provide structural support for the railway track. Each rail in a railway track can consist of multiple rail sections. For example, each of multiple rail sections is connected end-to-end to another rail section to form a single rail of the railway track.

[0026] Due to a variety of factors such as weather and train traffic, the surface of railway tracks can deteriorate over time. For example, rails may sink or bulge, and this can worsen over time. Similarly, the elevation difference between the left and right rails may increase over time, causing the track to become uneven. Such track surface damage is dangerous and must be monitored and repaired. However, current technologies for monitoring track surface damage are often reactive in nature, addressing problems only after they have progressed to unacceptable levels.

[0027] To address these and other issues related to managing track surface damage, the disclosed embodiments provide systems and methods for predicting railway track surface damage. In some embodiments, the disclosed systems and methods utilize historical track geometry channel data (e.g., track data for defects such as surface anomalies, subsidence, and crosslevel) from a previous time period (e.g., a previous six-month period). A clustering algorithm is then used to identify local track sections with progressively increasing defect amplitudes. A pattern of channel growth over time is then fitted for each location, and the date on which the defect amplitude will exceed the regulatory limits for the track class is calculated.

[0028] The disclosed method for predicting when and where track geometry (if unmaintained) will exceed a set threshold is predictive and proactive. This allows maintenance to be scheduled before surface anomalies reach unacceptable levels (e.g., exceeding regulatory thresholds). Furthermore, the disclosed implementation can modify or supplement manual inspection plans based on the predicted date when surface anomalies will reach a certain threshold. For example, a geometry car can be scheduled to make one or more additional passes over a specific track section based on predicted surface damage. Therefore, railway track safety can be significantly improved.

[0029] Figure 1 This is a schematic diagram illustrating a track surface damage prediction system 100 according to a specific implementation. The track surface damage prediction system 100 includes a computing system 110, a railway track 120, a train 130, one or more track geometry sensors 140, and a network 150. The computing system 110 includes a memory 115 for storing track geometry data 145 and a track surface damage prediction module 118.

[0030] In general, the track surface damage prediction module 118 of the computing system 110 acquires track geometry data 145 from the track geometry sensor 140 and applies various logics and algorithms to determine the future time at which a specific type of surface condition at a specific location on the railway track 120 will exceed a predetermined limit. For example, the track geometry sensor 140 may periodically travel along the railway track 120 and collect track geometry data 145 about the railway track 120. The track geometry data 145 may include various geometric data “channels,” such as surface anomalies, DIP31 anomalies, and horizontal anomalies, which are explained in more detail below. The track surface damage prediction module 118 can then analyze each specific channel of the track geometry data 145 to first identify specific locations on the railway track 120 with defects that gradually worsen over time. For each specific defect location, the track surface damage prediction module 118 can apply logic (e.g., a remaining service life model) to determine the future time at which that particular type of surface condition will exceed a predetermined limit. Based on the predicted future timeframe for exceeding predetermined limits, the track surface damage prediction module 118 can perform one or more actions, such as automatically generating an alarm or automatically dispatching maintenance technicians to repair the progressive defect location. Therefore, the railway track 120 can be proactively repaired, thereby improving the safety and availability of the railway track 120. Further details regarding the operation of the track surface damage prediction module 118 are discussed below.

[0031] It should be noted that the functional blocks and components of the track surface damage prediction system 100 of the embodiments of the present invention can be implemented using processors, electronic devices, hardware devices, electronic components, logic circuits, memories, software code, firmware code, etc., or any combination thereof. For example, one or more functional blocks or a portion thereof can be implemented as discrete gate or transistor logic, discrete hardware components, or combinations thereof, configured to provide logic for performing the functions described herein. Additionally or alternatively, when implemented in software, one or more functional blocks or a portion thereof may include code segments operable on a processor to provide logic for performing the functions described herein.

[0032] It should also be noted that the various components of the track surface damage prediction system 100 are exemplified as individual and independent components. However, it should be understood that each of the exemplified components can be implemented as a single component (e.g., a single application, server module, etc.), can be a functional component of a single component, or the functionality of these various components can be distributed across multiple devices / components. In such an implementation, the functionality of each corresponding component can be derived from the aggregation of the functionality of multiple modules residing in one or more devices.

[0033] It should be further noted that each of the described functions in the different functional blocks of the track surface damage prediction system 100 described herein is provided for illustrative purposes and not in a limiting manner, and the functions described as being provided by the different functional blocks may be combined into a single component or may be provided via computing resources set up in a cloud-based environment accessible through a network (such as one of the networks 150).

[0034] According to embodiments of this disclosure, the computing system 110 can be configured to facilitate operations for predicting damage to railway track surfaces. The functionality of the computing system 110 can be provided by the coordinated operation of various components of the computing system 110, as will be described in more detail below. Although Figure 1 A single computing system 110 is shown, but it should be understood that the computing system 110 and its various functional blocks can be implemented as a single device or distributed across multiple devices with their own processing resources, the aggregation function of which can be configured to perform operations according to this disclosure. Furthermore, those skilled in the art will recognize that, although Figure 1 The components of computing system 110 are exemplified as single and independent blocks, but each of the various components of computing system 110 can be a single component (e.g., a single application, server module, etc.), a functional component of the same component, or functionality can be distributed across multiple devices / components. In such an implementation, the functionality of each corresponding component can be aggregated from the functionality of multiple modules residing in one or more devices. Furthermore, a specific function described for a specific component of computing system 110 can actually be part of different components of computing system 110, and therefore, the description of a specific function for a specific component of computing system 110 is for illustrative purposes and not intended to be limiting in any way. Reference Figure 8 An example of a specific implementation of the computing system 110 is shown.

[0035] In some embodiments, the track surface damage prediction system 100 includes a track surface damage prediction module 118 that performs one or more of the operations described herein. The track surface damage prediction module 118 represents any suitable set of instructions, logic, or code embodied in a computer-readable storage medium. For example, the track surface damage prediction module 118 may be embodied in a memory 115, a disk, a CD, or a flash drive. In specific embodiments, the track surface damage prediction module 118 may include instructions (e.g., a software application) executable by a computer processor to perform one or more of the functions described herein. The following discussion... Figure 3 A more detailed description of the specific methods that can be performed by the track surface damage prediction module 118 is provided.

[0036] The railway track 120 of the track surface damage prediction system 100 is a structure that allows the train 130 to move by providing a surface on which the wheels of the train 130 roll. In some embodiments, the railway track 120 includes rails, fasteners, sleepers, ballast, etc. In some embodiments, the railway track 120 includes a left rail and a right rail.

[0037] The orbital geometry sensor 140 (e.g., 140A-140B) is a vehicle or object that captures orbital geometry data 145 about a railway track 120. For example, the aerial orbital geometry sensor 140A could be a drone or any other unmanned / manned aircraft that flies above the railway track 120 and uses multiple sensors to capture orbital geometry data 145. The sensors may include, for example, cameras, lidar, radar, etc.

[0038] In some implementations, the track geometry sensor 140 includes an inspection "geometry" vehicle 140B. The geometry vehicle 140B can be manned or unmanned, and can be a modified passenger car equipped with a computer that allows analysts (whether onboard or remote) to monitor track conditions as the train travels along the railway track 120. The geometry vehicle 140B may include onboard sensors, such as cameras, lasers, radar, and machine vision systems, for surveying the structure of the railway track 120 passing beneath.

[0039] Track geometry sensor 140 monitors and captures various characteristics of railway track 120. These characteristics may include one or more of the following: track alignment (how straight the track is), levelness (the tilt or pitch of the track), curvature (the actual degree of a curve), gauge (the distance between rails), rail profile (rail wear), ballast condition (the condition of the ballast and subgrade beneath the track), and rail joint condition (the fastening system at the junction of two rail ends). The monitored characteristics are reported by track geometry sensor 140 in track geometry data 145.

[0040] Track geometry data 145 is data about railway track 120 captured by track geometry sensor 140 over a period of time. Generally, track geometry data 145 contains various "channels" of various types of surface conditions of railway track 120. These various types of surface conditions can include surface anomalies (i.e., bulges or depressions in the rails of railway track 120) and level anomalies (i.e., the elevation difference between the top surfaces of the left and right rails of railway track 120). The various types of surface conditions recorded in track geometry data 145 are... Figures 2A-2C Examples are shown below, and will be discussed in more detail below.

[0041] Figure 2AAn embodiment of surface anomalies of a railway track 120 that can be included in track geometry data 145 is illustrated. In some embodiments, surface anomalies are measurements of the uniformity of the track surface, measured over a short distance along the top surface of the rails of the railway track 120. In some embodiments, the surface is measured over a chord length of 62 feet, such as... Figure 2A As illustrated in the example. Generally, surface anomalies are determined by subsidence / depression (negative signal "-") or bulge / protrusion (positive signal "+") on the surfaces of the left and right rails of the railway track 120. Surface anomalies can be measured and recorded separately for the left and right rails of the railway track 120 in the track geometry data 145. For example, as... Figure 2A As illustrated, the surface anomaly of the right rail (“RSURF”) is plotted in Figure 202, while the surface anomaly of the left rail (“LSURF”) is plotted in Figure 203. Figure 2A In the illustrated embodiment, each scale mark on graphs 202 and 203 is equal to 1 / 4 inch. In this embodiment, a sunken surface anomaly at position 201 of the right rail of railroad track 120 is indicated as a 3 / 4-inch depression.

[0042] Figure 2B An embodiment of a DIP31 anomaly of railway track 120 that can be included in track geometry data 145 is illustrated. In some embodiments, the DIP31 anomaly is the maximum change in elevation of the centerline of railway track 120 within a 31-foot movement window. Generally, the DIP31 anomaly is determined by a drop (negative signal "-") or rise (positive signal "+") of the centerline of railway track 120. Figure 2B In the diagram, the DIP31 anomaly of railway track 120 is plotted in Figure 204. Figure 2B In the illustrated embodiment, each scale mark on graph 204 is equal to 1 / 2 inch. In this embodiment, a surface anomaly of DIP31 at position 205 of railroad track 120 is indicated as a 2-inch anomaly.

[0043] Figure 2C An embodiment of a horizontal anomaly of railway track 120 that can be included in track geometry data 145 is illustrated. In some embodiments, the horizontal anomaly is the difference in elevation between the top surfaces of the left and right rails of railway track 120, measured perpendicular to the centerline of the track, at a single point in a straight track section. Figure 2C The horizontal anomaly of railway track 120 is plotted in Figure 206. Figure 2C In the illustrated embodiment, each scale mark on graph 206 is equal to 1 inch. In this embodiment, a horizontal anomaly at position 207 of railway track 120 is indicated as a 1-inch anomaly.

[0044] Back Figure 1 The network 150 of the track surface damage prediction system 100 is any type of network that facilitates communication between the components of the track surface damage prediction system 100. For example, network 150 can connect the track geometry sensor 140 of the track surface damage prediction system 100 to the computing system 110 of the track surface damage prediction system 100. One or more parts of network 150 may include an ad hoc network, intranet, extranet, virtual private network (VPN), local area network (LAN), wireless local area network (WLAN), wide area network (WAN), wireless wide area network (WWAN), metropolitan area network (MAN), a portion of the Internet, a portion of the public switched telephone network (PSTN), cellular telephone network, 3G network, 4G network, 5G network, LTE cellular network, a combination of two or more of these, or other suitable types of network. One or more parts of network 150 may include one or more access (e.g., mobile access) networks, core networks, and / or edge networks. Network 150 can be any communication network, such as a private network, a public network, a connection via the Internet, a mobile network, a Wi-Fi network, a Bluetooth network, etc. Network 150 may include cloud computing capabilities. One or more components of the track surface damage prediction system 100 may communicate via network 150. For example, track geometry sensor 140 may communicate via network 150, including transmitting information (e.g., track geometry data 145) to computing system 110 and / or receiving information (e.g., updated scheduling plans) from computing system 110.

[0045] In operation, the track surface damage prediction module 118 of the computing system 110 accesses track geometry data 145 from the track geometry sensor 140 and determines the future time at which a specific type of surface condition at a specific location on the railway track 120 will exceed a predetermined limit. First, the track surface damage prediction module 118 analyzes each specific channel of the track geometry data 145 to identify specific locations on the railway track 120 with defects that gradually worsen over time. For each specific defect location, the track surface damage prediction module 118 can apply logic (e.g., a remaining service life model discussed below) to determine the future time at which that specific type of surface condition will exceed the predetermined limit. Based on the predicted future time at which the predetermined limit will be exceeded, the track surface damage prediction module 118 can perform one or more actions, such as automatically generating an alarm or automatically dispatching maintenance technicians to repair the progressive defect location. Thus, the railway track 120 can be proactively repaired, thereby improving the safety and availability of the railway track 120. (The following section discusses...) Figure 3 The specific methods that can be used in the track surface damage prediction module 118 will be discussed in more detail.

[0046] Figure 3 This is a flowchart illustrating an example method 300 for predicting damage to railway track surfaces according to certain implementations. In some implementations, Figure 3 The functions illustrated in the example block shown can be derived from Figure 1 The track surface damage prediction module 118 is executed according to the embodiments described herein. In some embodiments, the operation of method 300 may be stored as instructions that, when executed by one or more processors, cause the one or more processors to perform the operation of method 300.

[0047] Overall, method 300 analyzes track geometry data of a railway track (e.g., track geometry data 145) and attempts to locate specific locations on the track where surface conditions gradually deteriorate over time and approach a predetermined threshold. For example, Figure 4 The overall operation of method 300 is illustrated. In this figure, the maximum value of a specific channel of the orbital geometry data (i.e., "measurement data") is plotted on a graph. The channel maximum value is plotted on the Y-axis, and time (in days) is plotted on the X-axis. In this embodiment, the channel maximum value rapidly approaches the failure threshold 410. The goal of method 300 is to analyze the measurement data and fit a prediction line 420 to determine the remaining useful life (i.e., the amount of time remaining before the measurement data for that channel crosses the failure threshold 410). In this specific embodiment, the fitted prediction line 420 crosses the failure threshold 410 in approximately 9.5 days. Therefore, method 300 determines the remaining useful life to be approximately 9.5 days. Specific implementations of the operation of method 300 for determining the remaining useful life are discussed in more detail below.

[0048] Back Figure 3 Method 300 may begin in step 310. In step 310, method 300 accesses track geometry data of the railway track. In some embodiments, the track geometry data is track geometry data 145 stored in a memory such as memory 115. The track geometry data includes historical measurements of various types of surface conditions of the railway track over a period of time. In some embodiments, the types of surface conditions of the railway track include: bulges or depressions in the left rail of the railway track, bulges or depressions in the right rail of the railway track, and the elevation difference between the top surfaces of the left and right rails of the railway track. In some embodiments, the track geometry data is captured by multiple sensors of a geometry vehicle as the geometry vehicle travels on the railway track. In some embodiments, the track geometry data is captured by multiple sensors of an aircraft (such as a drone). In some embodiments, the track geometry data accessed in step 310 is data for a given track section and channel, spanning a certain amount of time from the current date (e.g., a window of the past six months).

[0049] In step 320, method 300 identifies multiple measurements exceeding predetermined values ​​by analyzing orbital geometry data for a specific type of surface condition. For example, for a given orbital partition, channel, and date, the maximum / minimum values ​​exceeding a preset channel value threshold are collected (i.e., the peak maximum / minimum values ​​in any direction are collected). The preset channel value threshold can be configurable and can be different for each data channel. As a specific embodiment, the predetermined value of the threshold can be 0.1 to 0.9 in any direction.

[0050] In step 330, method 300 identifies specific track locations on the railway track as progressive defect locations by clustering multiple measurements exceeding predetermined values ​​from step 320. In some embodiments, step 330 includes utilizing a clustering algorithm, such as dbscan (density-based noisy spatial clustering algorithm). In these embodiments, method 300 may first arbitrarily select a point in the dataset until all points have been visited. If at least a predetermined number (e.g., two) of points exist within a radius “ε” of that point, method 300 considers all these points to belong to the same cluster. The radius “ε” may vary for each data channel (e.g., ε = 200 feet for horizontal; ε = 3 feet for subsidence; ε = 3 feet for surface anomalies, etc.). Method 300 then expands the clusters by recursively repeating neighborhood calculations for each adjacent point. An embodiment of the clustering in step 320 is described in... Figure 5A and Figure 5B shown in the example. Figure 5A The original channel values ​​for damage with an LSURF defect near the 166.44 milepost are illustrated. Each plotted line represents channel measurements at different time points (e.g., different passes of Geometry 140B). As can be seen from the circled portion of this image, the peak increases over time, indicating that the area deteriorates over time. Figure 5B Examples from Figure 5A The maximum absolute value of the LSURF defect area highlighted at milestone 166.44. When method 300 takes the maximum absolute value from a specific local defect, the linear trend of the data is... Figure 5B The data becomes readily apparent. Method 300 then uses this data to fit a regression line to predict future failure dates, as explained in more detail below.

[0051] At step 340, method 300 uses the remaining useful life model and trajectory geometry data for a specific type of surface condition at the progressive defect location to determine the future time when the specific type of surface condition at the progressive defect location will exceed a predetermined limit. Overall, method 300 iterates over each clustered / identified defect location with a defect amplitude increase history from step 330 in step 340 to predict the remaining useful life. For illustrative purposes only, as a specific embodiment, consider... Figure 6 The channel data is plotted in the figure. In this figure, the channel values ​​for a specific defect (i.e., LSURF) at a specific location (i.e., milestone 166.44) are plotted over time (i.e., T0-T3). Method 300 can perform three different operations to calculate regression line 610 and determine the future time T4 when regression line 610 crosses a predetermined channel limit 620. The three different operations in step 340 of method 300, which can be performed by certain embodiments, are discussed below.

[0052] The first operation in step 340 of method 300, which may be performed by certain embodiments, is to calculate the correlation coefficient. Generally, the correlation coefficient indicates the direction, form (shape), and degree (strength) of the relationship between two variables. In some embodiments, correlation coefficients above a certain correlation threshold are considered for prediction. The correlation threshold can be a value between 0.1 and 1.0. In some embodiments, correlation coefficients below the correlation threshold are not considered for prediction. In some embodiments, the correlation coefficient can be calculated according to the following formula: in: = Correlation coefficient; = The value of the variable x (Time_Diff); = The mean of the values ​​of the x variable (Time_Diff); = The value of the y variable (Channel_Vals); = The mean of the values ​​of the y variable (Channel_Vals); Time_Diff is the difference between each run date and the start date (T0); and Channel_Vals is the absolute channel value for each run date.

[0053] The second operation in step 340 of method 300, which can be performed by certain implementations, is fitting a regression line 610. Overall, the regression line 610 (i.e., the best-fit line) = (Time_Diff / RANGE, log(Channel_Vals)). RANGE is... Figure 6 The maximum and minimum values ​​of the date values ​​on the X-axis. In some implementations, the two variables, Time_Diff and Channel_Vals, are normalized before applying model predictions to make them comparable. Therefore, Time_Diff can be normalized using RANGE, and Channel_Vals can be normalized using the natural logarithm. The regression line 610 is fitted such that it captures the trends of the two data points (Time_Diff and Channel_Vals). The intercept is the point where the regression line 610 intersects the Y-axis. The slope of the regression line gives a measure of its steepness and direction. Here, Xi is Time_Diff / RANGE, and Yi is log(Channel_Vals). The intercept and slope values ​​can be calculated from these using the following equations: in: = Dependent variable; = constant / intercept; = Slope / Coefficient; and = Independent variable.

[0054] The third operation in step 340 of method 300, which can be performed by certain embodiments, is to determine the remaining useful life, which indicates the future time that a particular type of surface condition at the location of the progressive defect will exceed a predetermined channel limit 620. In some embodiments, the remaining useful life (“rul”) can be calculated using the following formula:

[0055] Here, "X" is the maximum channel value threshold of 620 for a given location, orbital class, and channel, and is a predetermined, configurable threshold. Figure 7 An embodiment of the predetermined channel limit 620 is illustrated below. After step 340, method 300 can end.

[0056] In some embodiments, method 300 may optionally include initiating one or more actions based on the future timeframe at which a specific type of surface condition at the determined progressive defect location will exceed a predetermined limit. For example, method 300 may automatically transmit an alarm electronically via a communication network for display on an electronic display. The alarm may indicate that a specific type of surface condition at the progressive defect location will exceed a predetermined limit in the future. As another example, method 300 may automatically dispatch or schedule maintenance technicians to repair the progressive defect location.

[0057] Figure 8 An example computer system 800 is illustrated. In specific embodiments, one or more computer systems 800 perform one or more steps of one or more methods described or illustrated herein. In specific embodiments, one or more computer systems 800 provide the functionality described or illustrated herein. In specific embodiments, software running on one or more computer systems 800 performs one or more steps of one or more methods described or illustrated herein, or provides the functionality described or illustrated herein. Specific embodiments include one or more portions of one or more computer systems 800. In this document, references to computer systems may cover computing devices and vice versa, where appropriate. Furthermore, references to computer systems may cover one or more computer systems, where appropriate.

[0058] This disclosure contemplates any suitable number of computer systems 800. This disclosure contemplates that the computer systems 800 may take any suitable physical form. By way of example and not limitation, the computer system 800 may be an embedded computer system, a system-on-a-chip (SOC), a single-board computer system (SBC) (such as, for example, a computer module (COM) or system module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive self-service terminal, a mainframe, a computer system grid, a mobile phone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented / virtual reality device, or a combination of two or more of these. Where appropriate, the computer system 800 may: comprise one or more computer systems 800; be single or distributed; span multiple locations; span multiple machines; span multiple data centers; or reside in a cloud that may include one or more cloud components in one or more networks. Where appropriate, one or more computer systems 800 may perform one or more steps of one or more methods described or illustrated herein without substantial spatial or temporal limitations. By way of example and not limitation, one or more computer systems 800 may execute one or more steps of the methods described or illustrated herein in real time or in batch mode. Where appropriate, one or more computer systems 800 may execute one or more steps of the methods described or illustrated herein at different times or at different locations.

[0059] In a specific embodiment, computer system 800 includes processor 802, memory 804, storage device 806, input / output (I / O) interface 808, communication interface 810, and bus 812. Although this disclosure describes and exemplifies a particular computer system with a particular arrangement and a particular number of particular components, this disclosure contemplates any suitable computer system with any suitable arrangement and any suitable number of suitable components.

[0060] In a specific embodiment, processor 802 includes hardware for executing instructions, such as those constituting a computer program. By way of example, and not limitation, to execute instructions, processor 802 may: retrieve (or fetch) instructions from internal registers, internal caches, memory 804, or storage device 806; decode and execute them; and then write one or more results to internal registers, internal caches, memory 804, or storage device 806. In a specific embodiment, processor 802 may include one or more internal caches for data, instructions, or addresses. This disclosure contemplates that processor 802 may include any suitable number of suitable internal caches where appropriate. By way of example, and not limitation, processor 802 may include one or more instruction caches, one or more data caches, and one or more translation lookup buffers (TLBs). Instructions in the instruction cache may be copies of instructions in memory 804 or storage device 806, and the instruction cache may speed up the retrieval of these instructions by processor 802. The data in the data cache may be: a copy of data in memory 804 or storage device 806 for operation by instructions executed at processor 802; the result of a previous instruction executed at processor 802 for access by a subsequent instruction executed at processor 802 or for writing to memory 804 or storage device 806; or other suitable data. The data cache can speed up read or write operations of processor 802. The TLB can speed up virtual address translation of processor 802. In specific embodiments, processor 802 may include one or more internal registers for data, instructions, or addresses. This disclosure contemplates that processor 802 may include any suitable number of suitable internal registers where appropriate. Where appropriate, processor 802 may: include one or more arithmetic logic units (ALUs); be a multi-core processor; or include one or more processors 802. Although this disclosure describes and exemplifies particular processors, this disclosure contemplates any suitable processor.

[0061] In a specific implementation, memory 804 includes main memory for storing instructions to be executed by processor 802 or data to be operated by processor 802. By way of example and not limitation, computer system 800 may load instructions from storage device 806 or other sources (such as, for example, another computer system 800) into memory 804. Processor 802 may then load the instructions from memory 804 into internal registers or internal caches. To execute an instruction, processor 802 may retrieve the instruction from the internal register or internal cache and decode it. During or after instruction execution, processor 802 may write one or more results (which may be intermediate or final results) into internal registers or internal caches. Processor 802 may then write one or more of these results into memory 804. In a specific implementation, processor 802 executes only instructions that are in one or more internal registers or internal caches or in memory 804 (not in storage device 806 or elsewhere), and operates only on data that is in one or more internal registers or internal caches or in memory 804 (not in storage device 806 or elsewhere). One or more memory buses (each of which may include an address bus and a data bus) couple processor 802 to memory 804. Bus 812 may include one or more memory buses, as described below. In a specific embodiment, one or more memory management units (MMUs) are located between processor 802 and memory 804 and facilitate access to memory 804 requested by processor 802. In a specific embodiment, memory 804 includes random access memory (RAM). Where appropriate, this RAM may be volatile memory. Where appropriate, this RAM may be dynamic RAM (DRAM) or static RAM (SRAM). Furthermore, where appropriate, this RAM may be single-port or multi-port RAM. This disclosure contemplates any suitable RAM. Where appropriate, memory 804 may include one or more memories 804. Although this disclosure describes and exemplifies specific memories, this disclosure contemplates any suitable memory.

[0062] In a specific embodiment, storage device 806 includes a mass storage device for data or instructions. By way of example and not limitation, storage device 806 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, storage device 806 may include removable or non-removable (or fixed) media. Where appropriate, storage device 806 may be internal or external to computer system 800. In a specific embodiment, storage device 806 is a non-volatile solid-state memory. In a specific embodiment, storage device 806 includes read-only memory (ROM). Where appropriate, this ROM may be a mask-programmable ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these. This disclosure contemplates that mass storage device 806 may take any suitable physical form. Where appropriate, storage device 806 may include one or more storage control units that facilitate communication between processor 802 and storage device 806. Where appropriate, storage device 806 may include one or more storage devices 806. Although this disclosure describes and exemplifies particular storage devices, any suitable storage device is contemplated herein.

[0063] In specific implementations, I / O interface 808 includes hardware, software, or both, providing one or more interfaces for communication between computer system 800 and one or more I / O devices. Where appropriate, computer system 800 may include one or more of these I / O devices. One or more of these I / O devices can enable communication between a person and computer system 800. By way of example and not limitation, I / O devices may include a keyboard, keypad, microphone, display, mouse, printer, scanner, speaker, still camera, stylus, tablet computer, touchscreen, trackball, video camera, another suitable I / O device, or a combination of two or more of these. I / O devices may include one or more sensors. This disclosure contemplates any suitable I / O devices and any suitable I / O interface 808 for them. Where appropriate, I / O interface 808 may include one or more device or software drivers that enable processor 802 to drive one or more of these I / O devices. Where appropriate, I / O interface 808 may include one or more I / O interfaces 808. Although this disclosure describes and exemplifies specific I / O interfaces, this disclosure contemplates any suitable I / O interface.

[0064] In specific implementations, communication interface 810 includes hardware, software, or both of these providing one or more interfaces for communication (such as, for example, packet-based communication) between computer system 800 and one or more other computer systems 800 or one or more networks. By way of example, and not limitation, communication interface 810 may include a network interface controller (NIC) or network adapter for communicating with Ethernet or other wired-based networks, or a wireless NIC (WNIC) or wireless adapter for communicating with wireless networks, such as Wi-Fi networks. This disclosure contemplates any suitable network and any suitable communication interface 810 for it. By way of example, and not limitation, computer system 800 may communicate with one or more portions of an ad hoc network, personal area network (PAN), local area network (LAN), wide area network (WAN), metropolitan area network (MAN), or the Internet, or a combination of two or more of these. One or more portions of one or more of these networks may be wired or wireless. As an example, computer system 800 may communicate with wireless PAN (WPAN) (such as, for example, Bluetooth WPAN), Wi-Fi network, Wi-Fi Max network, cellular telephone network (such as, for example, GSM network, LTE network, or 5G network), or other suitable wireless network, or a combination of two or more of these. Where appropriate, computer system 800 may include any suitable communication interface 810 for any of these networks. Where appropriate, communication interface 810 may include one or more communication interfaces 810. Although specific communication interfaces are described and illustrated in this disclosure, any suitable communication interface is contemplated in this disclosure.

[0065] In a specific implementation, bus 812 includes hardware, software, or both, that couple the components of computer system 800 to each other. By way of example and not limitation, bus 812 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 812 may include one or more buses 812. While this disclosure describes and exemplifies specific buses, any suitable bus or interconnect is contemplated herein.

[0066] In this document, where appropriate, a computer-readable non-transitory storage medium may include one or more semiconductor-based or other integrated circuits (ICs) (such as, for example, field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs)), hard disk drives (HDDs), hybrid hard disk drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical drives, floppy disks, floppy disk drives (FDDs), magnetic tape, solid-state drives (SSDs), RAM drives, secure digital cards or drives, any other suitable computer-readable non-transitory storage medium, or any suitable combination of two or more of these. Where appropriate, a computer-readable non-transitory storage medium may be volatile, non-volatile, or a combination of volatile and non-volatile.

[0067] Those skilled in the art will readily understand that the advantages and objectives described above would be impossible without the specific combinations of computer hardware and other structural components and mechanisms assembled in the system of the present invention and as described herein. Furthermore, the algorithms, methods, and processes disclosed herein improve upon any general-purpose computer or processor disclosed in this specification and accompanying drawings and transform it into a special-purpose computer programmed to execute the disclosed algorithms, methods, and processes to achieve the foregoing functions, advantages, and objectives. It will be further understood that those skilled in the art will recognize that various programming tools can be used to generate and implement the features and operations described above. Moreover, the specific selection of programming tools may depend on the specific objectives and constraints imposed on the chosen implementation methods to achieve the concepts set forth herein and in the appended claims.

[0068] The descriptions in this patent document should not be construed as implying that any particular element, step, or function may be a necessary or critical element that must be included within the scope of the claims. Furthermore, unless the exact words “means for…” or “steps for…” are explicitly used in a particular claim, followed by a participle phrase identifying the function, no claim is intended to invoke 35 USC § 112(f) with respect to any appended claim or claim element. The use of terms such as (but not limited to) “mechanism,” “module,” “device,” “unit,” “component,” “element,” “building block,” “device,” “machine,” “system,” “processor,” “processing device,” or “controller” within the claims may be understood and intended to refer to structures known to a person skilled in the art, as further modified or enhanced by features of the claims themselves, and is not intended to invoke 35 USC § 112(f). For example, the terms “processor” and “controller” may be a class of structures rather than a specific structure, and may be defined in functional terms, but this does not make them a device plus a function. Even under the broadest reasonable interpretation, given this paragraph of the specification, the claims are not intended to invoke 35 USC § 112(f) in the absence of the specific language described above.

[0069] This disclosure may be embodied in other specific forms without departing from its spirit or essential characteristics. For example, each new structure described herein may be modified to accommodate specific local changes or requirements while retaining its basic configuration or structural relationships with each other, or performing the same or similar functions described herein. Therefore, this embodiment should be considered illustrative rather than restrictive in all respects. Consequently, the scope of the invention may be established by the appended claims rather than the foregoing description. Therefore, all modifications falling within the meaning and scope of equivalents of the claims are intended to be covered therein. Furthermore, the elements of the claims are not well-known, conventional, or routine. Rather, the claims relate to unconventional inventive concepts described in the specification.

[0070] Those skilled in the art will further understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, various exemplary components, blocks, modules, circuits, and steps have been described above generally according to their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure. Those skilled in the art will also readily recognize that the order or combination of components, methods, or interactions described herein are merely examples, and that components, methods, or interactions of various embodiments of this disclosure can be combined or performed in ways other than those illustrated and described herein.

[0071] The functional blocks and modules disclosed herein may include processors, electronic devices, hardware devices, electronic components, logic circuits, memories, software code, firmware code, and any combination thereof. Consistent with the foregoing, the various exemplary logic blocks, modules, and circuits described in connection with this disclosure may be implemented or performed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration.

[0072] The steps of the methods or algorithms described in connection with the disclosure herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, allowing the processor to read information from and write information to it. Alternatively, the storage medium may be integrated with the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal, base station, sensor, or any other communication device. Alternatively, the processor and storage medium may reside as discrete components in the user terminal.

[0073] In one or more exemplary designs, the described functionality can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality can be stored or transmitted as one or more instructions or code on or through a computer-readable medium. Computer-readable media includes computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transfer of a computer program from one place to another. Computer-readable storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, and not limitingly, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Furthermore, a connection can be appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL), then coaxial cable, fiber optic cable, twisted pair, or DSL is included in the definition of medium. The terms disk and disc can include compact optical discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while discs typically reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0074] Although the invention and its advantages have been described in detail, it should be understood that various changes, substitutions, and modifications may be made herein without departing from the spirit and scope of the invention as defined by the appended claims. Furthermore, the scope of this application is not intended to be limited to the specific embodiments of the processes, machines, manufactures, compositions of matter, apparatuses, methods, and steps described in the specification. As will be readily understood by those skilled in the art from the disclosure of this invention, according to the invention, processes, machines, manufactures, compositions of matter, apparatuses, methods, or steps that are currently existing or will be developed thereafter can be utilized to perform substantially the same function, in substantially the same manner, or achieve substantially the same results as the corresponding embodiments described herein. Therefore, the appended claims are intended to include such processes, machines, manufactures, compositions of matter, apparatuses, methods, or steps within their scope.

Claims

1. A system comprising: One or more memory units; as well as One or more computer processors, the one or more computer processors being communicatively coupled to the one or more memory units, and configured to: Access the track geometry data of the railway track, which includes historical measurements of various types of surface conditions of the railway track over a period of time; By analyzing the orbital geometry data for a specific type of surface condition, multiple measurement results exceeding predetermined values ​​are identified; By clustering the multiple measurement results that exceed the predetermined value, specific track locations on the railway track are identified as progressive defect locations; as well as Using the remaining useful life model and the orbital geometry data for the specific type of surface condition at the location of the progressive defect, determine the future time at which the specific type of surface condition at the location of the progressive defect will exceed a predetermined limit.

2. The system according to claim 1, wherein, The various types of surface conditions of the rails of the railway track include: The bulge or depression in the left rail of the railway track; A bulge or depression in the right rail of the railway track; and The elevation difference between the top surfaces of the left and right rails of the railway track.

3. The system according to claim 1, wherein, The track geometry data is captured by multiple sensors of the geometry vehicle as it travels on the railway track.

4. The system according to claim 1, wherein, The orbital geometry data was captured by multiple sensors on the spacecraft.

5. The system of claim 1, wherein the one or more computer processors are further configured to: automatically initiate one or more actions based on a future timeframe in which the specific type of surface condition at the determined progressive defect location will exceed the predetermined limit, the actions comprising: Alarms are automatically transmitted electronically via a communication network for display on an electronic display. as well as Automatically dispatch or arrange maintenance technicians to repair the location of the progressive defect.

6. The system according to claim 1, wherein, The future time at which the specific type of surface condition at the location of the progressive defect will exceed the predetermined limit includes: Calculate the correlation coefficient; and Fit the regression line.

7. The system according to claim 6, wherein, Before determining the future time at which the specific type of surface condition at the location of the progressive defect will exceed the predetermined limit, the calculated correlation coefficient is compared with a correlation threshold.

8. A method performed by a computing system, the method comprising: Access the track geometry data of the railway track, which includes historical measurements of various types of surface conditions of the railway track over a period of time; By analyzing the orbital geometry data for a specific type of surface condition, multiple measurement results exceeding predetermined values ​​are identified; By clustering the multiple measurement results that exceed the predetermined value, specific track locations on the railway track are identified as progressive defect locations; as well as Using the remaining useful life model and the orbital geometry data for the specific type of surface condition at the location of the progressive defect, determine the future time at which the specific type of surface condition at the location of the progressive defect will exceed a predetermined limit.

9. The method according to claim 8, wherein, The various types of surface conditions of the rails of the railway track include: The bulge or depression in the left rail of the railway track; A bulge or depression in the right rail of the railway track; and The elevation difference between the top surfaces of the left and right rails of the railway track.

10. The method according to claim 8, wherein, The track geometry data is captured by multiple sensors of the geometry vehicle as it travels on the railway track.

11. The method according to claim 8, wherein, The orbital geometry data was captured by multiple sensors on the spacecraft.

12. The method according to claim 8, further comprising: Based on the future timeframe at which the specific type of surface condition at the determined progressive defect location will exceed the predetermined limit, one or more actions are automatically initiated, the actions including: Automatically transmit alarms electronically via a communication network for display on an electronic display; and Automatically dispatch or arrange maintenance technicians to repair the location of the progressive defect.

13. The method according to claim 8, wherein, The future time at which the specific type of surface condition at the location of the progressive defect will exceed the predetermined limit includes: Calculate the correlation coefficient; and Fit the regression line.

14. The method according to claim 13, wherein, Before determining the future time at which the specific type of surface condition at the location of the progressive defect will exceed the predetermined limit, the calculated correlation coefficient is compared with a correlation threshold.

15. One or more computer-readable non-transitory storage media, comprising instructions that, when executed by a processor, cause the processor to perform operations, the operations including: Access the track geometry data of the railway track, which includes historical measurements of various types of surface conditions of the railway track over a period of time; By analyzing the orbital geometry data for a specific type of surface condition, multiple measurement results exceeding predetermined values ​​are identified; By clustering the multiple measurement results that exceed the predetermined value, specific track locations on the railway track are identified as progressive defect locations; as well as Using the remaining useful life model and the orbital geometry data for the specific type of surface condition at the location of the progressive defect, determine the future time at which the specific type of surface condition at the location of the progressive defect will exceed a predetermined limit.

16. One or more computer-readable non-transitory storage media according to claim 15, wherein, The various types of surface conditions of the rails of the railway track include: The bulge or depression in the left rail of the railway track; A bulge or depression in the right rail of the railway track; and The elevation difference between the top surfaces of the left and right rails of the railway track.

17. One or more computer-readable non-transitory storage media according to claim 15, wherein, The track geometry data is captured by multiple sensors of the geometry vehicle as it travels on the railway track.

18. One or more computer-readable non-transitory storage media according to claim 15, wherein, The orbital geometry data was captured by multiple sensors on the spacecraft.

19. The operation further comprises: one or more computer-readable non-transitory storage media according to claim 15. Based on the future timeframe at which the specific type of surface condition at the determined progressive defect location will exceed the predetermined limit, one or more actions are automatically initiated, the actions including: Automatically transmit alarms electronically via a communication network for display on an electronic display; and Automatically dispatch or arrange maintenance technicians to repair the location of the progressive defect.

20. One or more computer-readable non-transitory storage media according to claim 15, wherein, The future time at which the specific type of surface condition at the location of the progressive defect will exceed the predetermined limit includes: Calculate the correlation coefficient; and Fit the regression line.

Images