Railway track data aggregation and analysis system and method for determining inspection frequency

Through data analysis technology, the rating system is generated based on the physical factors of railway assets, and the visual inspection frequency is optimized, which solves the problem of unreasonable inspection frequency in the existing technology, and improves the inspection efficiency and safety of railway assets.

CN119032038APending Publication Date: 2024-11-26BNSF RAILWAY COMPANY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380034153.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-14
Filing Date
2023-03-30
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing railway asset inspection methods are not targeted, resulting in unreasonable inspection frequency, which may lead to safety hazards and asset wear, and rely on repeated mathematical modeling and manual inspections, which are inefficient.

Method used

Through data analysis technology, based on multiple physical factor data related to railway safety maintenance, a rating system is generated, visual inspection frequency is optimized, railway assets with suboptimal conditions are focused on checking railway assets, and inspection efficiency and safety are improved.

Benefits of technology

It realizes dynamic adjustment of inspection frequency according to the specific conditions of railway assets, reduces safety hazards, extends asset life, improves inspection efficiency and safety, and avoids inefficient and repetitive work in traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119032038A_ABST
    Figure CN119032038A_ABST
Patent Text Reader

Abstract

A system and method for minimizing potential safety hazards along a railway track by optimizing the railway visual inspection frequency based on acquired data relating to railway safety maintenance. The system and method can provide various rating systems for railway assets, optimizing railway checks by emphasizing checks on railway assets in sub-optimal conditions. The rating of the railway assets is based on various data of physical factors that affect the life of the railway assets, such as rainfall, locomotive weight and frequency of passage, as well as manually detected defects. According to the system and the method, the key point of railway inspection work can be focused on railway assets which need to be more concerned due to sub-optimal conditions. The service life of railway assets can be prolonged through key inspection, the inspection efficiency is improved, and the railway safety is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates generally to management of railroad asset inspections, and more particularly to systems and methods for railroad track data aggregation and analysis to determine inspection frequency by optimizing visual railroad inspection frequency based on acquired railroad track related data. Background Art

[0002] Manually inspecting rail assets can be a time-consuming and inefficient process. Rail tracks have dozens of components to inspect, and inspectors have limited time. A single railroad in the United States may have 10,000 miles or more of track across multiple states and a variety of terrain. With such a wide range of work across the United States, inspectors can miss hazardous assets, leading to locomotive delays, increased wear and tear on rail assets, or derailments.

[0003] Current rail asset inspection methods are primarily based on a repetitive approach of assigning specific inspection frequencies to rail assets. Current methods take a best guess approach to determining inspection frequencies for all rail assets, regardless of the unique conditions of the rail asset or environment. A proper inspection may require the careful inspection and documentation of many components and conditions. If one component or condition is missed or mischaracterized, safety becomes a concern.

[0004] The current approach applies the same process to every type of rail asset, making the inspection process overgeneralized. The reality of the inspection process is that good track may require less inspection than track in poor condition. Track in non-ideal condition may experience more extreme rainfall, more locomotive traffic, or be prone to ballast fouling. Rail asset inspection methods could benefit from a more targeted process that identifies where rail track needs maintenance based on condition data affecting the track. Summary of the invention

[0005] The present disclosure achieves technical advantages as a system and method for minimizing safety hazards on railway tracks by optimizing the frequency of railway visual inspections based on data acquired related to railway safety maintenance. The system and method can provide various rating systems for specific railway assets to optimize railway inspections by focusing inspections on railway assets that experience suboptimal conditions. The rating of railway assets is based on various data of physical factors that affect the life of railway assets, such as rainfall, locomotive weight and frequency of passage, and defects detected by humans. The system and method can focus railway inspection efforts on railway assets that need more attention due to suboptimal conditions. Focused inspections can extend the service life of railway assets, improve inspection efficiency, and improve railway safety.

[0006] Thus, the present disclosure discloses concepts that are inseparable from computer technology, such that the present disclosure provides technical advantages: optimizing rail asset inspections by using data acquired from multiple physical data sources and data analysis techniques that are best suited to access and retrieve database data. The system can provide inspectors with a system configuration to rate rail assets, focus inspection efforts, and extend the life of rail assets to enhance safety. The present disclosure goes beyond the simple manual inspection of rail assets that typically specifies the frequency of rail asset inspections, combining data analysis techniques to proactively identify and predict rail asset failures based on measured physical factors. The system can generate inspection frequencies for rail assets to optimize inspection efficiency, avoiding typical general inspection methods or predictive methods. This also provides the benefit of accurately understanding the current status of rail assets, simplifying the inspection process by providing relevant information required for specific rail assets, so inspectors can quickly, clearly, and efficiently inspect assets without inefficient repetitive work.

[0007] The present disclosure proactively assigns inspection frequencies to railway assets by at least aggregating different data and analyzing different data to generate a rating system based on data analysis technology of measured physical factors affecting the railway, thereby providing a technical solution that is lacking in traditional systems. In addition, the present disclosure combines various factors to generate a hierarchical rating of inspection frequencies. The inspection frequency can be generated based on the physical environmental characteristics of the railway asset, the frequency and weight of locomotives passing through the asset, and the ballast characteristics. Traditional methods lack measurements of physical factors affecting railway assets to evaluate inspection frequencies. Traditional systems rely solely on mathematical modeling to predict defect formation or manual inspections of all assets, which may result in inefficient work by inspectors and may even lead to dangerous environments due to errors. Therefore, traditional methods lack a subjective approach to railway asset inspections. The present disclosure avoids adding pressure to an already overspent system. The systems and methods of the present disclosure may also provide at least the following functions: · Rating the frequency of railway asset inspections based on measurements of physical factors; Provide effective railway asset inspection methods to enhance railway safety; · Generate rail asset analytics based on measured characteristics of rail assets; and Provide a means to comply with regulations related to rail travel and safety.

[0008] In addition, the visual inspection model solves the problem of combining multiple factors to evaluate track inspection requirements, so that it can refresh and update data for inspectors to inspect the track at the required frequency. The system according to the present disclosure can receive data from geometry vehicles, track predetermined characteristics, traffic characteristics, artificial defects, and combine them on various track segments to generate values ​​for evaluating the frequency of visual track inspections. Variables can interpret track conditions based on values ​​and inputs. These variables can serve as leading indicators of concerns about track conditions. The visual inspection model can change based on track segment conditions and can adapt to the received data, thereby achieving "data-driven". If the test is invalid or untested, the segment is upgraded to increase visual inspections. The system can treat all input variables as classified quantities, such as CSP, GeoTag, and ClassDrop inputs.

[0009] Advantageously, the system transforms the inputs received, such as BFI, MGT, and rainfall, by converting the inputs from continuous variables to integer values ​​and rescaling (e.g., standardizing) these values ​​to match the categorical variables before including them in the overall score. The IF model can be a scoring system that assigns a specific section of the track to one of three inspection protocols based on the associated values ​​of MGT, BFI, rainfall, ClassDrop, CSP category, human defects, and CW joint count. The calculated score, which can be a function of the separate score values ​​calculated for each input variable, can be reclassified as one of the three inspection protocols. In order to assess the sensitivity of the model to each input variable, the score can be calculated as a model outcome rather than the associated inspection protocol. The IF model can generate a single score for each input track. In a "full factorial" design, every possible combination of input values ​​will be used to generate a range of model outcomes, and the outcome values ​​can be plotted as a function of the various inputs.

[0010] The general process can produce a fixed number of track records, hold one input variable at a fixed value, and allow all other variables to be drawn from a pool of random values ​​based on the empirical density function of that variable. These records can be written to text data files with a structure similar to each weekly model report. These data files can then be used as input to applications that calculate various reported metrics. The system can replicate the calculation steps derived from the weekly track inspection category reports. The system can also generate various statistics based on the weekly data records, and can generate pseudo-random data records to meet criteria related to specific analysis scenarios and metrics for evaluating model behavior.

[0011] An object of the present invention is to provide a system for minimizing safety hazards on railway tracks by optimizing the frequency of railway visual inspections based on data acquired related to railway safety maintenance. Another object of the present invention is to provide a method for minimizing safety hazards on railway tracks by optimizing the frequency of railway visual inspections based on data acquired related to railway safety maintenance. Another object of the present invention is to provide a computer-implemented method for minimizing safety hazards on railway tracks by optimizing the frequency of railway visual inspections based on data acquired related to railway safety maintenance. These and other objects are provided by at least one of the following embodiments.

[0012] In one embodiment, a system for minimizing safety hazards along a railway track by optimizing visual railway inspection frequency based on acquired data related to railway safety maintenance includes: a memory for storing acquired data related to railway safety maintenance and an inspection frequency classification model for converting the acquired data from an original form to a final inspection frequency value; and a processor configured to convert the acquired data related to railway safety maintenance from an original form to a final inspection frequency value by performing the following steps: receiving acquired railway safety maintenance data related to at least one section of railway track; assigning a railway safety value to each of a plurality of categories of the acquired data based on a user-defined hazard model; aggregating the railway safety values ​​to generate a railway safety score; multiplying the railway safety score by a user-defined multiplier when a metric gross tonnage (MGT) calculation includes a rail joint factor; and generating a final inspection frequency value for at least one section of railway track based on the railway safety score. The processor is further configured to perform a step of segmenting the acquired data into a plurality of categories. The plurality of categories include a comprehensive service plan (CSP), MGT, precipitation, geometric vehicle label, ballast fouling index (BFI), slow travel command, and artificial defect. Wherein, the geometric car tag includes an open tag or a closed tag. Wherein, the open tag and the closed tag correspond to the first tag type, the second tag type or the third tag type, respectively. Wherein, the processor is also configured to perform a step of determining whether to increase the inspection frequency of the railway track segment when the railway track segment corresponds to a minimum inspection standard threshold. Wherein the minimum inspection standard threshold includes at least 12MGT measurements of the railway track segment since the last test. Wherein, the inspection frequency is increased to the next available railway manual inspection frequency. Wherein, the final inspection frequency value is based on a user-defined inspection threshold, including a first railway manual inspection frequency, a second railway manual inspection frequency and a third railway manual inspection frequency. Wherein the first railway manual inspection frequency is twice a month, the second railway manual inspection frequency is once a week, and the third railway manual inspection frequency is three times a week.

[0013] In another embodiment, a method is provided for minimizing safety hazards along a railway track by optimizing the frequency of railway visual inspections based on acquired data related to railway safety maintenance, including: receiving acquired data related to railway safety maintenance of at least one section of railway track; assigning a railway safety value to each of a plurality of categories based on a user-defined hazard model; aggregating the railway safety values ​​to generate a railway safety score; multiplying the railway safety score by a user-defined multiplier when the metric gross tonnage (MGT) calculation includes a rail joint factor; and generating a final inspection frequency value for at least one section of railway track based on the railway safety score. Wherein, the processor is further configured to perform a step of segmenting the acquired data into a plurality of categories. Wherein, the plurality of categories include a comprehensive service plan (CSP), MGT, precipitation, geometric car tags, ballast fouling index (BFI), slow-moving commands, and artificial defects. Wherein, the geometric car tags include open tags or closed tags. Wherein, the open tags and the closed tags correspond to a first tag type, a second tag type, or a third tag type, respectively. Wherein, the processor is further configured to perform a step of determining whether to increase the inspection frequency of the railway track segment when the railway track segment corresponds to a minimum inspection standard threshold. Wherein the minimum inspection standard threshold includes at least 12MGT measurements on the railway track segment since the last test. Wherein the inspection frequency is increased to the next available railway manual inspection frequency. Wherein the final inspection frequency value is based on the user-defined inspection threshold, including the first railway manual inspection frequency, the second railway manual inspection frequency, and the third railway manual inspection frequency. Wherein the first railway manual inspection frequency is twice a month, the second railway manual inspection frequency is once a week, and the third railway manual inspection frequency is three times a week.

[0014] In another embodiment, a computer-implemented method is provided for minimizing safety hazards along a railway track by optimizing the frequency of railway visual inspections based on acquired data related to railway safety maintenance, the computer-implemented method comprising: receiving acquired data related to railway safety maintenance of at least one section of railway track; assigning a railway safety value to each of a plurality of categories based on a user-defined hazard model; aggregating the railway safety values ​​to generate a railway safety score; multiplying the railway safety score by a user-defined multiplier when the metric gross tonnage (MGT) calculation includes a rail joint factor; and generating a final inspection frequency value for at least one section of railway track based on the railway safety score. Wherein, the processor is further configured to perform a step of segmenting the acquired data into a plurality of categories. Wherein, the plurality of categories include a comprehensive service plan (CSP), MGT, precipitation, geometric car tags, ballast fouling index (BFI), slow-moving commands, and artificial defects. Wherein, the geometric car tags include open tags or closed tags. Wherein, the open tags and the closed tags correspond to a first tag type, a second tag type, or a third tag type, respectively. Wherein, the processor is further configured to perform a step of determining whether to increase the inspection frequency of the section of railway track when the section of railway track corresponds to a minimum inspection standard threshold. Wherein the minimum inspection standard threshold includes at least 12MGT measurements on the railway track segment since the last test. Wherein the inspection frequency is increased to the next available railway manual inspection frequency. Wherein the final inspection frequency value is based on the user-defined inspection threshold, including the first railway manual inspection frequency, the second railway manual inspection frequency, and the third railway manual inspection frequency. Wherein the first railway manual inspection frequency is twice a month, the second railway manual inspection frequency is once a week, and the third railway manual inspection frequency is three times a week.

[0015] In another embodiment, a method for evaluating the frequency of visual inspections of tracks may include: receiving data related to a railway track segment; generating continuous variables and categorical variables representing indicators of the condition of the track segment of interest; transforming and rescaling the continuous variables to match the categorical variables; generating inspection values ​​for each variable; and generating a model that assigns a specific portion of the track to one of a plurality of inspection protocols based on the inspection values. It also includes generating a series of model results for each combination of input values. It further includes keeping the first variable at a fixed value and allowing all other variables to be drawn from a pool of random values ​​based on the empirical density function of the variable. Wherein, if the test is invalid or untested, the model can upgrade the track segment to increase visual inspections. Wherein the inspection schedule can be three times a week, once a week, or twice a month. Wherein, the inspection protocol can be based on the relevant values ​​of MGT, BFI, rainfall, ClassDrop, CSP category, human defects, and CW joint counts. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present disclosure will be easily understood by the following detailed description in combination with the accompanying drawings, which illustrate the principles of the present disclosure by way of example. The accompanying drawings show the design and practicality of one or more exemplary embodiments of the present disclosure, wherein the same elements are represented by the same reference numerals or symbols. The objects and elements in the accompanying drawings are not necessarily drawn in proportion, ratio or precise positional relationship. Instead, the focus is on illustrating the principles of the present disclosure.

[0017] Figure 1A and 1B A data flow diagram of a railway asset inspection system according to one or more exemplary embodiments of the present disclosure is shown;

[0018] Figure 2A and 2B A flow chart illustrating a railroad asset inspection process according to one or more exemplary embodiments of the present disclosure is shown;

[0019] Figure 3 A schematic diagram showing a railway asset maintenance system according to one or more exemplary embodiments of the present disclosure is shown;

[0020] Figure 4 A schematic diagram showing a railway inspection system according to one or more exemplary embodiments of the present disclosure is shown;

[0021] Figure 5 A railway inspection control logic according to one or more exemplary embodiments of the present disclosure is shown;

[0022] Figures 6A-6C An exemplary diagram showing a railroad inspection system according to one or more exemplary embodiments of the present disclosure; and

[0023] Figure 7 A railroad inspection process according to one or more exemplary embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0024] The disclosure and its various features and advantageous details set forth in the following written description will be more fully explained with reference to the non-limiting examples included in the accompanying drawings and the contents detailed in the specification. Descriptions of well-known components are omitted herein so as not to unnecessarily obscure the main features described herein. The following examples are intended to facilitate understanding of the implementation and practice of the disclosure. One of ordinary skill in the art will understand the disclosure as meaning that any suitable combination of the following functions or exemplary embodiments can be combined to achieve the claimed subject matter. The disclosure includes the number of representative species within the genus, or structural features common to members of the genus, so that one of ordinary skill in the art can identify members of the genus. Therefore, these examples should not be construed as limiting the scope of the claims.

[0025] A person of ordinary skill in the art will understand that any system claim set forth herein encompasses all elements and limitations disclosed therein, and therefore requires that each system claim be considered as a whole. Any reasonably foreseeable item that has a functional relationship with a claim also falls within the relevant scope. Pursuant to MPEP §904, the examiner searches for prior art disclosed in patents and other published documents (i.e., non-patent literature) after thoroughly understanding the invention disclosed and claimed in the non-provisional application. Therefore, as evidenced by the issuance of this patent, the prior art fails to disclose or teach the elements and limitations set forth in the claims supported by the specification and drawings, and therefore the set forth claims are patentable under 35 U.S.C. §§101, 102, 103, and 112.

[0026] Figure 1A and 1B A data flow diagram of a railroad asset inspection system 100 according to one or more exemplary embodiments of the present disclosure is shown. The railroad asset inspection system 100 may include a comprehensive service plan (CSP) data 102, a million gross tons (MGT) data 104, precipitation data 106, geometry tag data 108, ballast contamination index (BFI) data 110, slow travel order data 112, artificial defect data 114, total score 116, rail joint decision point 118, multiplier 120, final rating 122, final rating transformation 124, temporary inspection frequency 126, MGT decision point 128, dispatch decision point 130, boost inspection frequency 132, Federal Railroad Administration (FRA) minimum inspection frequency 134, and final inspection frequency 136.

[0027] The foregoing system steps may be implemented in hardware, software, or an appropriate combination of hardware and software, and may include one or more software systems running on one or more servers having one or more processors that can access memory. The server may include electronic storage, one or more processors, and / or other components. The server may include communication lines, connections, and / or ports to exchange information through a network and / or other computing platforms. The server may also include multiple hardware, software, and / or firmware components that operate together to provide the functionality assigned to the server herein. For example, the server may be implemented as a computing platform cloud computing that operates together as a server, including SaaS, IaaS, and PaaS functions. In addition, the server may also include memory.

[0028] The structural components of the steps can be accessed through the network (e.g. Figure 3The network 340 in the system 100 is coupled to each other so that data can be transmitted. The network can be the Internet, an intranet, or other suitable network. Data transmission can be encrypted, unencrypted, through a VPN tunnel, or other suitable communication methods. The network can be a WAN, a LAN, a PAN, or other suitable network type. Network communications between system components can be encrypted using PGP, Blowfish, Twofish, 3DES, HTTPS, or other suitable encryption methods. System 100 can be configured to provide communication via API, PCI, PCI-Express, ANSI-X12, Ethernet, Wi-Fi, Bluetooth, or other suitable communication protocols or media through various systems, components, and modules disclosed herein. In addition, third-party systems and databases can be operably coupled to system components via a network.

[0029] Data transmitted to and from components of system 100 may include any format, including JSON, TCP / IP, XML, HTML, ASCII, SMS, CSV, REST, or other suitable formats. Data transmissions may include messages, flags, headers, header attributes, metadata, and / or bodies, or be encapsulated and packaged in any suitable format therewith.

[0030] In one embodiment, the CSP data 102 may include information about the CSP. In addition to the work order itself, the CSP information may include data from a geometry car that is used to sequentially segment the track into non-CSP (track with no non-compliant measurements) and CSP (track with at least one non-compliant measurement) sections. The track sections at these CSP / non-CSP transitions constitute separate records for calculating the inspection frequency classification. The CSP section of the track has the CSP data value increased by 1, 2, or 3 depending on how much the measurement deviates from the acceptable range.

[0031] In one embodiment, the MGT data 104 may include information regarding the MGT for an entire track segment. The MGT information may include data corresponding to specific requirements for certain categories of track set by the FRA. Not only is the accumulated MGT for the previous calendar year a decision criterion, but a maximum accumulated MGT allowed between two inspections is specified for certain tracks. Depending on the specific track type involved, the MGT categories used by the FRA for various regulations are limited to the following values: 2, 10, 20, 40, and 60. In one example, the system 100 may recode the MGT calculated for each track section according to the table. The MGT values ​​of the pilot track are always non-zero and range from 0.018 to 191.942.

[0032] In one embodiment, precipitation data 106 may include information about precipitation for the entire track segment. The precipitation information may include data corresponding to accumulated wet precipitation over the previous week. The IF model does not include frost, ice, snow accumulation, and snowmelt. Actual data is provided as part of your AccuWeather subscription service. rainfall Coding score 0" (or trace amount) 0 0”-1” 1 1”-2” 2 >2” 3

[0033] In one embodiment, the geometry tag data 108 may include information about defects corresponding to the track segments. The geometry tag information may include gauge, deflection under load, and other measurements that are measured by instruments carried by specialized vehicles that run periodically on all tracks. The results of these geometry vehicle runs are used to generate various work orders. The work orders are color coded to indicate defect severity and are used directly for scoring, as shown below.

[0034] In one embodiment, the BFI data 110 may include information about the ballast of a track segment. The BFI information may include the amount of fine particulate matter embedded in the gaps between the larger rocks and gravel that make up the ballast or roadbed, which is related to the ballast losing its ability to support a load without dangerous movement. A rail vehicle equipped with a ground penetrating radar instrument can provide an index of how "contaminated" the ballast is. The observed values ​​range from near zero to 200. Tracks are typically scanned twice a year, 15 feet each time. As a rule of thumb, track inspectors will typically mark track sections with a BFI of 55 or above as defective based solely on visual cues. Ballast Dirt Index Coding score <20 1 20-29 2 30-39 3 >40 4

[0035] In one embodiment, the slow order data 112 may include information regarding speed restrictions for the section of track. The slow order information may include a reduction in the maximum allowable speed for freight and / or passenger train operations, which is an administrative action that typically indicates that a defect has been observed or that track modifications are being or have occurred. Almost all speed reductions result in a reduction in the FRA grade of the affected track. Changes in freight track grade numbers are directly used for grading, as shown below.

[0036] In one embodiment, the human defect data 114 may include information about manually identified defects. Human defect information may include inspectors and personnel who observe rail and / or roadbed defects while performing other tasks and log specific defects in the work order database. For defined defect groups, the inspection frequency score is automatically increased to a maximum value of (5).

[0037] In one embodiment, the total score 116 may include aggregated values ​​corresponding to the above data values. The total score 116 may be as high as 48.5.

[0038] In one embodiment, the rail joint decision point 118 may include information corresponding to whether the track segment includes a rail joint. The rail joint information may include data corresponding to whether the bearing strength of each track segment is reduced at a track break, particularly where repairs are being made to the track or the roadbed. These temporary joints typically last for a short period of time after the repair activity, but typically they are replaced with welded joints. In one example, the total score 116 may be multiplied by a multiplier 120.

[0039] In one embodiment, if the aggregate MGT exceeds a user-defined rail joint threshold, the multiplier 120 may multiply the total score 116 by 1.5. For example, the user-defined threshold may be 20 MGT.

[0040] In one embodiment, the final rating 122 may include a summary score of the above factors. For example, the above factors may be summed up to produce a score related to various visual inspection frequencies.

[0041] In one embodiment, the final rating conversion 124 may include conditionally converting the final rating 122 to a visual inspection frequency. For example, when the final rating 122 is between 0 and 6, the visual inspection frequency is twice a month. For another example, when the final rating 122 is between 6 and 11, the visual inspection frequency is once a week. For another example, when the final rating 122 is greater than or equal to 12, the visual inspection frequency is three times a week.

[0042] In one embodiment, the interim inspection frequency 126 may include a visual inspection frequency from the final rating conversion 124. For example, the interim inspection frequency 126 may include a visual inspection frequency of twice a month, once a week, or three times a week.

[0043] In one embodiment, the MGT decision point 128 may include determining whether the track segment is subjected to a track weight greater than an MGT threshold. For example, the MGT threshold may include 12 MGT. If the track segment is subjected to a weight greater than the MGT threshold, the visual inspection frequency may be increased. If the track segment is subjected to a weight less than the MGT threshold, the system 100 determines whether the schedule meets the required criteria.

[0044] In one embodiment, the scheduling decision point 130 may include determining whether the schedule meets the required criteria. For example, the required criteria may include ATGMS requirements. If the planned length of the track segment is greater than the required criteria, the visual inspection frequency is the FRA minimum inspection frequency 134. If the planned operating time of the track segment is less than the required criteria, the interim inspection frequency 126 is the final inspection frequency 136.

[0045] In one embodiment, increasing the inspection frequency 132 may include increasing the visual inspection frequency. For example, the increase in the visual inspection frequency may be increased to the next inspection frequency. In one example, the visual inspection frequency may be increased from twice a month to once a week. In another example, the visual inspection frequency may be increased from once a week to three times a week. In another example, the visual inspection frequency may remain at three times a week.

[0046] In one embodiment, the FRA minimum inspection frequency 134 may include the minimum visual inspection frequency permitted by laws and regulations. For example, the FRA may be required by law to have a minimum inspection frequency of twice a month, once a week, three times a week, or other minimum visual inspection frequencies.

[0047] In one embodiment, the final inspection frequency 136 may include the visual inspection frequency that the inspector applies to the track segment. For example, when the final inspection frequency 136 is twice a month, the inspector will visit the track segment twice a month to check for any hazardous conditions, defects, or potential problems.

[0048] Figure 2A and 2B A flow chart of a process of railway asset inspection 200 according to one or more exemplary embodiments of the present disclosure is shown. The process of railway asset inspection 200 can be implemented as an algorithm on a computer processor (e.g., a critical logic controller, an onboard computer, a server), a machine learning module, or other suitable system. In addition, the process of railway asset inspection 200 can be implemented by software, firmware, hardware, an application programming interface (API), a network connection, a network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof. The process of railway asset inspection 200 can be implemented in a computer environment (e.g., a physical computer processor, a virtual machine) that is capable of converting the acquired data related to railway safety maintenance from a raw form to a final inspection frequency value, and is operably coupled to a memory storing the acquired data related to railway safety maintenance and an inspection frequency classification model to convert the acquired data from a raw form to a final inspection frequency value.

[0049] The process of the rail asset inspection 200 can take advantage of the ability of the computer platform to generate multiple processes and threads by processing data simultaneously. By instantiating multiple processes for managing the dual westbound trains, the speed and efficiency of the process of the rail asset inspection 200 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread can also be used and this is within the scope of the present disclosure. The process of the rail asset inspection 200 can also be distributed among multiple networked computer processors. The computer processors can be located in a server (e.g., Figure 3 The railway asset inspection process 200 of this embodiment starts from step 202.

[0050] In step 202, in one embodiment, process 200 may include a locomotive traveling along a section of track. For example, the locomotive may include a passenger locomotive, a freight locomotive, a geometry tagging vehicle, or any other type of locomotive that travels along the track segment. In one example, the locomotive is used to collect data corresponding to the physical characteristics of the track segment. For example, when the locomotive is a geometry tagging vehicle, the locomotive may identify defects along the track and assign tags to the defects. In another example, the locomotive may carry a payload for transportation across the track segment. Then, process 200 continues to step 204.

[0051] In step 204, in one embodiment, the process 200 may instruct the hardware components to collect CSP data using external sensors along the track, and the system 200 may receive the data and assign CSP values ​​to the CSP data. The process 200 may store and access the CSP data in an external database corresponding to the network architecture that best suits data access and retrieval. For example, the external database may correspond to a permanent database that stores all rail information. Alternatively, the external database may correspond to a temporary database that temporarily stores rail data for quick access. In addition to the work order itself, the CSP data may also include data from a geometry car that is used to sequentially split the track into non-CSP (track with no non-compliant measurements) and CSP (track with at least one non-compliant measurement) sections. The track sections at these CSP / non-CSP transitions constitute separate records for calculating the inspection frequency classification. The process 200 then proceeds to step 206.

[0052] In step 206, in one embodiment, the process 200 may instruct the hardware components to collect MGT data using external sensors along the track, and the system 200 may receive the data and assign MGT values ​​to the MGT data. The process 200 may store and access the MGT data in an external database corresponding to the network architecture that is most suitable for data access and retrieval. For example, the external database may correspond to a permanent database that stores all railway information. Alternatively, the external database may correspond to a temporary database for temporarily storing railway data for quick access. The process 200 may collect MGT data using external sensors corresponding to the track segments where the MGT is measured. In another example, the process 200 may collect MGT data using records of locomotives passing through the track segments. The process 200 then proceeds to step 208.

[0053] In step 208, in one embodiment, the process 200 may instruct the hardware components to collect precipitation data using external sensors along the track, and the system 200 may receive the data and assign precipitation values ​​to the precipitation data. For example, the precipitation data may include precipitation information about the entire track segment. The process 200 may store and access the precipitation data in an external database corresponding to a network architecture that is most suitable for data access and retrieval. For example, the external database may correspond to a permanent database that stores all railroad information. Alternatively, the external database may correspond to a temporary database that is used to temporarily store railroad data for quick access. The process 200 then proceeds to step 210.

[0054] At step 210, in one embodiment, the process 200 may instruct the hardware components to collect geometric tag data using external sensors corresponding to the track segments, and the system 200 may receive the data and assign geometric tag values ​​to the geometric tag data. The geometric tag data may include information about defects corresponding to the track segments. The process 200 may store and access the geometric tag data in an external database corresponding to a network architecture that is most suitable for data access and retrieval. For example, the external database may correspond to a permanent database that stores all railway information. Alternatively, the external database may correspond to a temporary database for temporarily storing railway data for quick access. The process 200 then proceeds to step 212.

[0055] In step 212, in one embodiment, the process 200 may instruct the hardware components to collect BFI data using external sensors along the track, and the system 200 may receive the data and assign BFI values ​​to the BFI data. For example, the BFI data may include information about the ballast of the track segment. The process 200 may store and access the BFI data in an external database corresponding to the network architecture that best suits data access and retrieval. For example, the external database may correspond to a permanent database that stores all railway information. Alternatively, the external database may correspond to a temporary database that is used to temporarily store railway data for quick access. The process 200 then proceeds to step 214.

[0056] In step 214, in one embodiment, the process 200 may instruct the hardware components to collect slow-order data using external sensors along the track, and the system 200 may receive the data and assign slow-order values ​​to the slow-order data. The slow-order command data may include speed limit information about the section of track. The process 200 may store and access the slow-order data in an external database corresponding to the network architecture that is most suitable for data access and retrieval. For example, the external database may correspond to a permanent database that stores all railway information. Alternatively, the external database may correspond to a temporary database for temporarily storing railway data for quick access. The process 200 then proceeds to step 216.

[0057] In step 216, in one embodiment, the process 200 may instruct the hardware components to collect artificial defect data using external sensors along the track, and the system 200 may receive the data and assign artificial defect values ​​to the artificial defect data. For example, the artificial defect data may include information about manually identified defects. The process 200 may store and access slow-order data in an external database corresponding to a network architecture that is most suitable for data access and retrieval. For example, the external database may correspond to a permanent database that stores all railway information. Alternatively, the external database may correspond to a temporary database for temporarily storing railway data for quick access. The process 200 then proceeds to step 218.

[0058] In step 218 , in one embodiment, process 200 may instruct the hardware component to add the above values ​​corresponding to the railway safety data to generate a total score. Process 200 then proceeds to step 220 .

[0059] In step 220, in one embodiment, process 200 may determine whether the MGT data for the segment of track includes information indicating the presence of rail joints along the segment of track. For example, process 200 may parse the MGT data to identify a digital variable corresponding to whether the MGT data includes information corresponding to the presence of rail joints for the segment of track. In one example, the MGT data may include a variable that indicates the presence of rail joints along the track segment using a binary value. For example, a "0" may indicate that the segment of track lacks any rail joints. Alternatively, a "1" may indicate that the segment of track contains at least one rail joint. If the MGT data includes information about rail joints, process 200 proceeds to step 222. If the MGT data does not include information about rail joints, process 200 proceeds to step 224.

[0060] In step 222, in one embodiment, process 200 may instruct the hardware component to multiply the total score by a user-defined multiplier. For example, the user-defined multiplier may be 1.5. Process 200 then proceeds to step 224.

[0061] In step 224 , in one embodiment, process 200 may instruct the hardware component to convert the total score into a corresponding inspection frequency. Process 200 then proceeds to step 226 .

[0062] In step 226, in one embodiment, process 200 may determine whether the MGT value is greater than the expected MGT value and whether the inspection frequency is less than the expected frequency value. If the MGT value recorded for the track segment is greater than the expected MGT value and the inspection frequency is less than the expected frequency value, process 200 proceeds to step 228. If the MGT value recorded for the track segment is less than the expected MGT value or the inspection frequency is greater than the expected frequency value, process 200 proceeds to step 230.

[0063] In step 228 , in one embodiment, process 200 may increase the frequency of checking. Process 200 then proceeds to step 230 .

[0064] In step 230, in one embodiment, process 200 may apply the inspection frequency to the track segment. Process 200 then terminates or waits for a new inspection creation request and may repeat the above steps.

[0065] Figure 3A schematic diagram of a railroad asset maintenance system 300 according to one or more exemplary embodiments of the present disclosure is shown. The system 300 may include one or more servers 102 having one or more processors 104, memory 130, machine-readable instructions 106, including a CSP data collection module 308, an MGT data collection module 310, a precipitation data collection module 312, a geometric car tag collection module 314, a BFI data collection module 316, a slow sequence data collection module 318, a human defect collection module 320, a message identification module 322, a log collection module 324, an information parsing module 326, a rating module 328, an accumulation module 330, an analysis module 332, and other related modules. The server 102 may be operatively coupled to one or more clients via a network 140. The client may be a mobile communication device 150, a personal laptop 352, an external sensor 354, or other types of hardware or software for communicating data via a network 340. In another exemplary embodiment, the mobile communication device 150 , the personal laptop computer 352 , or the external sensor 354 may include an application configured to communicate with the server 102 via the network 140 .

[0066] The aforementioned system components (e.g., server 102 and clients 350, 352, 354) can be coupled to each other in a communication manner through network 140, so that data can be transmitted. Network 140 can be the Internet, an intranet, or other suitable network. Data transmission can be encrypted, unencrypted, through a VPN tunnel, or other suitable communication methods. Network 140 can be a WAN, LAN, PAN, or other suitable network type. Network communications between clients, server 302, or any other system components can be encrypted using PGP, Blowfish, Twofish, AES, 3DES, HTTPS, or other suitable encryption. System 100 can be configured to provide communication via application programming interface (API), PCI, PCI-Express, ANSI-X12, Ethernet, Wi-Fi, Bluetooth, or other suitable communication protocols or media through various systems, components, and modules disclosed herein. In addition, third-party systems and databases can be operably coupled to system components through network 140.

[0067] Data transmitted to and from components of system 300 (e.g., server 302 and clients 350, 352, 354) may include any format, including JavaScript Object Notation (JSON), TCP / IP, XML, HTML, ASCII, SMS, CSV, Representational State Transfer (REST), or other suitable formats. Data transmissions may include messages, flags, headers, header attributes, metadata, and / or bodies, or be encapsulated and packaged in any suitable format therewith.

[0068] The server 102 may be implemented with hardware, software, or a suitable combination of hardware and software, and may include one or more software systems running on one or more servers, with one or more processors 104, and access to a memory 130. The server 102 may include electronic memory, one or more processors, and / or other components. The server 102 may include communication lines, connections, and / or ports to enable information to be exchanged over a network (e.g., network 140) and / or other computing platforms. The server 102 may also include a plurality of hardware, software, and / or firmware components that operate together to provide the functionality attributed to the server 102 herein. For example, the server 102 may be implemented by a computing platform cloud computing that operates together as the server 102, including software as a service (SaaS) and platform as a service (PaaS) functionality. In addition, the server 102 may include a memory 130.

[0069] The memory 130 may include electronic storage, which may include non-transitory storage media that electronically stores information. The electronic storage media of the electronic storage may include one or both of system storage and / or removable storage that may be provided integrally with the server 102 (e.g., substantially non-removable), wherein the removable storage may be removably connected to the server 102 via, for example, a port (e.g., a USB port, a FireWire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage may include one or more optically readable storage media (e.g., optical disks, etc.), magnetically readable storage media (e.g., magnetic tapes, magnetic hard disks, floppy disk drives, etc.), charge-based storage media (e.g., EEPROM, RAM, etc.), solid-state storage media (e.g., flash drives, etc.), and / or other electronically readable storage media. The electronic storage may include one or more virtual storage resources (e.g., cloud storage, virtual private networks, and / or other virtual storage resources). The electronic storage may include a database, or a public or private distributed ledger (e.g., blockchain). The electronic storage may store machine-readable instructions 106, software algorithms, control logic, data generated by a processor, data received from a server, data received from a computing platform, and / or other data that may enable a server to operate as described herein. The electronic storage may also include third-party databases accessible via the network 140.

[0070] Processor 104 may be configured to provide data processing capabilities in server 102. Thus, processor 104 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information (e.g., an FPGA or ASIC). Processor 104 may be a single entity or may include multiple processing units. These processing units may be physically located within the same device, or processor 104 may represent processing functionality of multiple devices or software functionality that operates separately or in concert.

[0071] The processor 104 may be configured to execute the machine-readable instructions 106 or the machine learning module through software, hardware, firmware, some combination of software, hardware and / or firmware, and / or other mechanisms for configuring processing capabilities on the processor 104. As used herein, the term "machine-readable instructions" may refer to any component or set of components that perform the functionality attributed to the machine-readable instruction component 106. This may include one or more physical processors 104, processor-readable instructions, circuits, hardware, storage media, or any other component during the execution of processor-readable instructions.

[0072] The server 102 may be configured with machine-readable instructions having one or more functional modules. The machine-readable instructions 106 may be implemented on one or more servers 102 having one or more processors 104 and access to a memory 130. The machine-readable instructions 106 may be a single networked node or a machine cluster, which may include a distributed architecture of multiple networked nodes. The machine-readable instructions 106 may include control logic for implementing various functions, as described in more detail below. The machine-readable instructions 106 may include certain functions related to the system 100. In addition, the machine-readable instructions 106 may include smart contracts or multi-signature contracts that may process, read, and write data to a database, a distributed ledger, or a blockchain.

[0073] Figure 4 A schematic diagram of a railroad inspection system 400 is shown in accordance with one or more exemplary embodiments of the present disclosure. The system 400 may include a data collection system 402, a data parsing system 404, and an inspection rating system 406. Although certain exemplary embodiments may be directed to railroad assets, the system 400 may be used to plan maintenance of a class of railroad assets including rails, ballast, panels, sleepers, switches, facilities, or any suitable asset.

[0074] In an exemplary embodiment, the data collection system 402 may include a CSP data collection module 308, an MGT data collection module 310, a precipitation data collection module 312, a geometry car tag collection module 314, a BFI data collection module 316, a slow order data collection module 318, and a human defect collection module 320. The CSP data collection module 308, the MGT data collection module 310, the precipitation data collection module 312, the geometry car tag collection module 314, the BFI data collection module 316, the slow order data collection module 318, and the human defect collection module 320 can implement one or more algorithms to connect to the network to communicate with the client, ultimately facilitating rail asset inspections and communicating data related to the inspection frequency of a section of track. The algorithm and its associated thresholds and / or signatures can be programmed to suit specific rail assets, applications, functions, facilities, or other requirements. The data collection system 402 can be configured to send and receive messages related to inspections or other suitable activities to a client or server. In another exemplary embodiment, the data collection system 402 can generate one or more elements for display on a user device. These elements can provide users with additional information related to the inspection. For example, data collection system 402 can generate an alarm and be displayed on the client to indicate data collection, data collection completion, data submission, data request or other suitable information. In addition, system symbols can also be displayed on the client to indicate data collection status.

[0075] In one embodiment, the CSP data collection module 308 may collect CSPs for track segments. For example, the CSP data collection module 308 may identify CSPs for track segments based on a service plan queue and store the CSPs in an external database in a tabular form. The external database may include an external memory, a virtual machine implementation or a cloud environment, or any other environment suitable for queuing CSPs. In one example, the location of the CSP may be based on a milestone measurement of the track segment. In another example, the CSP data collection module 308 may delete any redundant information from the CSP data. For example, the data may include first CSP information across a first segment of track at a first time and second CSP information across a second segment of track at a second time. When the second segment of track is completely contained within the first segment of track, the CSP data collection module 308 may delete the second CSP information as redundant information. For another example, when the second CSP information includes a segment of track that is completely contained within the first CSP information, the CSP data collection module 308 may skip the redundant information.

[0076] In another example, the CSP data collection module 308 may segment the CSP data into CSP segments and non-CSP segments. In this way, the CSP data collection module 308 may include CSP information about the entire track segment instead of a partial track segment. For example, a CSP segment may include CSP information corresponding to the track segment, and a non-CSP segment may include a placeholder value. In one example, a non-CSP segment may correspond to a track length without any CSP information. The CSP data collection module 308 may determine the length of a track without CSP information by identifying the positions of the track segments with CSP information and calculating the difference between the positions of the track segments. The CSP data collection module 308 may designate the difference between the positions as a non-CSP segment. In another example, the CSP data collection module 308 may assign CSP data to each track in a set of parallel tracks. For example, when the CSP data includes a single track segment of a parallel track segment, the CSP data collection module 308 assigns the CSP data to two parallel tracks. The CSP data collection module 308 may update the CSP data of the two parallel tracks.

[0077] In one embodiment, the MGT data collection module 310 may collect MGT data from a database. For example, the MGT data may include the MGT for a particular section of track in a particular year. The MGT on a particular track segment may include measurements from external sensors active along the track segment, and the MGT is measured when a locomotive passes through a location measured by the external sensor. In another example, the external sensor may update the database at a frequency available to a particular application (i.e., real-time, daily, weekly, etc.). In one example, the MGT data collection module 310 may access a database and search the database based on railroad information. In one example, the railroad information may include a particular year, a segment of the track, a track type, a track number, and a center point of a milepost range. For example, an example search query may include the following inputs. LS-05, track type-M, track nbr-1, start MP-4.6463, end MP-4.7580. Among them, "LS-05" means the line segment identifier is 05, "Track Type-M" is the main track, "Track nbr-1" is the identifier of the specific track, "Begin MP-4.6463" indicates that the starting point of the mile marker is 4.6463, and "End MP-4.7580" indicates that the end point of the mile marker is 4.7580.

[0078] In another example, the MGT data collection module 310 may collect MGT data from the database monthly to calculate the latest MGT and defective MGT. For example, the MGT data collection module 310 may calculate the latest MGT based on the daily MGT. The daily MGT may correspond to a daily tonnage estimate of the section of track calculated based on the MGT data measured from external sensors over a period of time. For example, the MGT data collection module 310 may query the database to collect MGT data for the entire LS for one month (30 days). The MGT data collection module 310 may calculate the daily MGT by dividing the MGT data for one month by the number of days. For example, the MGT data collection module may calculate the daily MGT by dividing the MGT data by 30 days.

[0079] In one example, the latest MGT is calculated by multiplying the daily MGT by the difference between the current date and the last test date, as shown below. Daily MGT calculation * number of days (current date - latest test date).

[0080] In another example, the defect MGT is calculated based on the daily MGT multiplied by the difference between the current date and the date the tag type first appeared. For example, the defect MGT for red tags can be calculated as shown below. Daily MGT calculation * number of days (current date - date of first occurrence of red tag test).

[0081] In one embodiment, the precipitation data collection module 312 can collect precipitation data from a database based on the location of the track segment. For example, the database can contain precipitation data for a specific time period. In one example, when the database lacks any precipitation data for the time range, the precipitation data collection module 312 can estimate the precipitation data based on the precipitation data of another time range. For example, the precipitation data collection module 312 can compare the length of the time range with another time range and calculate the average precipitation based on the precipitation data from the other time range. In another example, the precipitation data collection module 312 can multiply the average precipitation of another time range by a user-defined precipitation multiplier to overestimate the rainfall. In another example, the precipitation data collection module 312 can access a public meteorological data repository to collect public access meteorological data for precipitation data.

[0082] In one embodiment, the geometry car tag collection module 314 may identify defects for an entire track segment. For example, the geometry car will drive through the track segment to identify any defects and mark the defects accordingly. The tags may include physical tags for identifying defects, or virtual tags in the form of location identifiers, on or off values, and severity levels. The number of defects may include at least one severity level. In one example, at least one severity level may correspond to at least one tag type. For example, at least one tag type may include a yellow tag as the lowest severity, an orange tag as a medium severity, and a red tag as the highest severity. In another example, the geometry car tag collection module 314 may determine the number of defects corresponding to at least one tag type. In one example, the geometry car tag collection module 314 may search for a specific tag type in a database to identify the corresponding track segment. The geometry car tag collection module 314 may identify the number of defects for CSP segments and non-CSP segments.

[0083] In one embodiment, the BFI data collection module 316 can collect BFI data corresponding to the track segment from a database. For example, the BFI data can include the average BFI value of the track segment and the corresponding ballast test date. The average BFI value of the track segment can include measurements from external sensors that measure ballast dirt. In another example, the external sensor can update the database at a frequency available for a specific application (i.e., real-time, daily, weekly, etc.). In one example, the BFI data collection module 316 can access the database and search the database based on railway information. For example, the railway information can include a specific year, a line segment of the track, a track type, a track number, and a center point of a mileage mark range. When searched by the BFI data collection module 316, the database can include data for the BFI of the previous year. In one example, when the database lacks BFI data for a line segment of a specific date, the BFI data collection module 316 can compare the previous BFI data and assign the maximum value of the previous BFI data to the BFI data of the specific date.

[0084] In one embodiment, the slow command data collection module 318 can collect slow command data from a database. For example, the slow command data can include slow commands for the entire track segment in a particular year. In one example, the slow command indicates when the locomotive must pass through the track segment at a lower speed. The database can include slow instruction data for the entire track segment, including a series of notifications for the track segment indicating when the slow instruction is effective and the corresponding date. In one example, when the slow command is active throughout the segment, the speed requirement can vary according to the grade reduction requirement and the rating of the slow command. For example, when the locomotive is at level 4 in the CSP section and the slow command requires a grade reduction of 2 and is rated as 3, the slow command speed of the locomotive is equivalent to a level 2 locomotive. In one example, when the locomotive is at level 3 in the CSP section and the slow command requires a grade reduction of 2 and is rated as 3, the slow command speed of the locomotive is equivalent to a level 3 locomotive because the original level of the locomotive meets the rating. For another example, when the locomotive is at level 5 in a non-CSP section and the slow-speed order requirement level decreases by 3 and reaches level 4, the slow-speed order speed of the locomotive is equivalent to a locomotive at level 2. In one example, when the locomotive is at level 4 in a non-CSP section and the slow-speed order requirement level decreases by 3 and reaches a rating of 4, the slow-speed order speed of the locomotive remains unchanged because the original level of the locomotive is equivalent to the rating.

[0085] In one embodiment, the artificial defect collection module 320 can collect artificial defect data from a database. For example, the artificial defect collection module 320 can identify the total number of artificial defects for the entire track segment from the database. In one example, the database can update the artificial defect data based on input from manual or automatic inspections from a client or external sensor. For example, when an inspector finds a defect that was not previously detected, the inspector will collect artificial defect data using a client or external sensor and update the artificial defect data in the database to reflect the new defect. In one example, the artificial defect collection module 320 can query the database to identify the total number of artificial defects. In another example, the artificial defect data may include railway defect information. Railway defect information includes turnout defects, railway joint defects, and other railway defects.

[0086] In another example, the artificial defect collection module 320 can collect artificial defect data from a database based on line segment, track type, track number, and mileage. The database can return the queried identifier. In one example, the artificial defect collection module 320 can use the identifier to query the artificial defect database and return the number of artificial defects for the section of track.

[0087] In an exemplary embodiment, the data parsing system 404 may include a message identification module 322, a log collection module 324, and an information parsing module 326. The message identification module 322, the log collection module 324, and the information parsing module 326 may implement one or more algorithms to access the data collected from the data collection system 402 so as to identify and classify the data before analyzing the inspection frequency of the track segment. The algorithm and its associated thresholds and / or signatures may be programmed to suit specific railway assets, applications, functions, facilities, or other requirements. The data parsing system 404 may be configured to send and receive messages related to data collection and classification or other suitable activities to a client or server. In another exemplary embodiment, the data parsing system 404 may generate one or more elements for display on a user device. These elements may provide the user with additional information related to data storage. For example, an alarm may be generated by the data parsing system 404 and displayed on the client to indicate the initialization of data collection and storage, data classification errors or completion, or other suitable information. In addition, a system symbol may be displayed on the client to indicate the status of data storage.

[0088] In one embodiment, the message identification module 322 can classify the incoming messages and any notifications from the database. For example, the message identification module 322 can receive information about the inspection frequency analysis factor from the incoming messages and notifications. In one example, the message identification module 322 can classify the incoming messages accordingly according to the inspection frequency analysis factor.

[0089] In one embodiment, the log collection module 324 can receive query responses from the database. For example, the log collection module 324 can collect query responses from the database according to the model data acquisition date. In one example, the model data acquisition date can include at least the last week of data generation for the segment of track. In another example, the model data acquisition date can include a user-defined log collection input. For example, the log collection module 324 can receive query responses for a time range input by the user. The log collection module 324 can organize data corresponding to the query responses based on the classification from the message identification module 322.

[0090] In one embodiment, the information parsing module 326 can convert incoming data, messages, and notifications into information related to inspection frequency analysis factors. For example, the incoming messages can include information such as CSP data, MGT data, precipitation data, geometry tag data, BFI data, slow command data, and human defect data. In one example, the information parsing module 326 can establish a connection with a database. For example, the information parsing module 326 can receive incoming messages from a database and transmit relevant information to the database. The information transmitted to the database can include an indication that the inspection frequency analysis is not completed, in progress, or completed.

[0091] In an exemplary embodiment, the inspection rating system 406 may include an accumulation module 328 and an analysis module 330. The accumulation module 328 and the analysis module 330 may implement one or more algorithms to connect to the network to communicate with another system of the railway inspection system 400, and finally analyze the data and assign scores to determine the inspection frequency. The algorithm and its associated thresholds and / or signatures can be programmed to suit specific railway assets, applications, functions, facilities or other requirements. The network management system 202 can be configured to send and receive messages related to inspections or other appropriate activities to a client or server. In another exemplary embodiment, the inspection rating system 406 can generate one or more elements to be displayed on a user device. These elements can provide users with additional information related to the inspection frequency. For example, the inspection rating system 406 can generate an alert and display it on the client to indicate the current and future inspection frequencies, factors used to determine the inspection frequency, changes in the inspection frequency, or other suitable information. In addition, system symbols can be displayed on the client to indicate user-defined variables for assigning scores to track segments.

[0092] In one embodiment, the rating module 328 can convert the data into a rating for each inspection frequency analysis factor. For example, the inspection frequency analysis factors may include CSP data, MGT data, precipitation data, geometry tag data, BFI data, slow command data, and human defect data. The rating module 328 can convert the rating corresponding to the value of each inspection frequency analysis factor. For example, the rating module 328 can assign a value between 0-5 based on the severity of the inspection frequency analysis factor. In one example, the coded score disclosed in the figure. 1 is applicable to the value of the inspection frequency analysis factor.

[0093] In one embodiment, the accumulation module 330 can calculate a total score for the ratings. For example, the accumulation module 330 can add the individual ratings together to generate a value for the total score. In one example, the accumulation module 330 can determine when a track segment includes at least one rail joint. When the segment of track includes a rail joint, the accumulation module 330 multiplies the total score by a user-defined multiplier. For example, the user-defined multiplier is 1.5. In one example, based on the inspection frequency analysis factor, the total score can include a maximum value of 48.5.

[0094] In one embodiment, the analysis module 332 may determine the inspection frequency based on the inspection frequency classification model. For example, the inspection frequency classification model may classify the inspection frequency according to the total score of the rating. In one example, the analysis module 332 may identify whether the total score belongs to low inspection frequency, medium inspection frequency, or high inspection frequency. In one example, when the total score is less than 6, the analysis module 332 assigns a low inspection frequency to the track segment. In another example, when the total score is between 6 and 12, the analysis module 332 assigns a medium inspection frequency to the track segment. In another example, when the total score is greater than 12, the analysis module 332 assigns a high inspection frequency to the track segment. In one example, the analysis module 332 may determine the time of the aggregated daily MGT from the latest geometry car test date. When the aggregated daily MGT from the latest geometry car test date is greater than or equal to 12, the analysis module 332 increases the inspection frequency. In one example, when the inspection frequency is once a week, the analysis module 332 increases the inspection frequency to three times a week. In one example, when the inspection frequency is twice a month, the analysis module 332 increases the inspection frequency to once a week.

[0095] Figure 5A railroad inspection control logic 500 is shown in accordance with one or more exemplary embodiments of the present disclosure. The railroad inspection control logic 500 may be implemented as an algorithm on a server 302, a machine learning module, a client (e.g., client 350, 352, 354), a database, or other suitable system. Additionally, the railroad inspection control logic 500 may implement or include one or more features of the railroad inspection system 400, including the data collection system 402, the data parsing system 404, and the inspection rating system 406. The railroad inspection control logic 500 may be implemented by software, hardware, firmware, an API, a network connection, a network transmission protocol, HTML, DHTML, JavaScript, Dojo, Ruby, Rails, other suitable applications, or a suitable combination thereof.

[0096] The railway inspection control logic 500 can utilize the capabilities of the computer platform to generate multiple processes and threads by processing data simultaneously. In one embodiment, the railway inspection control logic 500 can implement a memory for storing the acquired data related to railway safety maintenance, and an inspection frequency classification model to convert the acquired data from an original form to a final inspection frequency value. In another embodiment, the railway inspection control logic 500 can instantiate instructions of a processor configured to convert the acquired data related to railway safety maintenance from an original form to a final inspection frequency value. By instantiating multiple processes to implement parallel railway asset inspections, the speed and efficiency of the railway inspection control logic 500 can be greatly improved. However, those skilled in the art of programming will recognize that a single processing thread can also be used, and this is within the scope of the present disclosure. The railway inspection control logic 500 of this embodiment starts from step 502.

[0097] In step 502, in one embodiment, the control logic 500 may receive data related to railroad safety maintenance of at least one section of railroad track. For example, the control logic 500 may receive data related to railroad safety maintenance of at least one section of railroad track. Figure 4 The data collection system 402 shown receives data. In one example, the control logic 500 can obtain data related to railway safety maintenance from a database, including CSP data, MGT data, precipitation data, geometric vehicle tag data, BFI data, slow command data and human defect data, or any combination of the foregoing data. In one example, the data can be structured or unstructured. For example, the control logic 500 can execute a database access instruction corresponding to the structured data based on the structure of the data, wherein specific variables in the instruction are received. In one example, the control logic 500 can execute an SQL database instruction indicating the track segment and data factors to be received. The control logic 500 then proceeds to step 504.

[0098] In step 504, in one embodiment, the control logic 500 may separate the data into multiple categories. For example, the data may come from multiple sources. In one example, the data may include a unique identifier for each source. The control logic 500 may segment the data by comparing the unique identifier of the source with a category label that matches the unique identifier. For example, the control logic 500 may include a unique numeric identifier associated with each railway safety maintenance factor. In one example, the control logic 500 may organize the data based on categories such as CSP values, MGT values, precipitation values, geometric car label values, BFI values, slow travel command values, and human defect values. In one example, the geometric car label value may include an open label or a closed label. An open label may indicate that the track segment contains an active defect. A closed label may indicate that the track segment contains a repaired defect. For example, when the defect corresponding to the open label is repaired, the open label may be converted to a closed label. In another example, the open label and the closed label may include various levels of label types. For example, the label type may include a first label type, a second label type, and a third label type. The first label type may indicate a minor problem with the track segment. The second label type may indicate a medium problem associated with the track segment. A third tag type may indicate a critical issue with the track segment. In another example, each category corresponds to a unique identifier. In another example, the control logic 500 may identify the category to which the data belongs based on comparing the data to an expected value and assigning the data to the category that matches the expected value. The control logic 500 may assign the data to the category based on a predetermined condition based on a unit associated with the data. The control logic 500 then proceeds to step 506.

[0099] In step 506, in one embodiment, the control logic 500 may assign rail safety values ​​corresponding to the categories based on the user-defined hazard model. For example, each category may correspond to a separate rail safety value in the rail safety values. In one example, one of the rail safety values ​​corresponds to a first CSP value for a first section of track, which may be different from a second CSP value for a second section of track corresponding to another rail safety value. For example, the first section of track may include various known non-compliant characteristics, resulting in a maximum CSP value, while the second section of track may include fully compliant characteristics, resulting in a minimum CSP value. The control logic 500 may assign rail safety values ​​as shown. 1. The control logic 500 then proceeds to step 510.

[0100] In step 508, in one embodiment, the control logic 500 may aggregate the railroad safety values ​​to generate a railroad safety score. For example, the control logic 500 may add the railroad safety values ​​together to generate a railroad safety score. The control logic 500 then proceeds to step 510.

[0101] In step 510, in one embodiment, the control logic 500 may determine whether the MGT data includes information identifying a rail joint. For example, the MGT data may include a variable indicating whether the track segment includes at least one rail joint. The variable may be binary, where a "0" may indicate that the track segment does not have any rail joints, and a "1" may indicate that the track segment includes a rail joint. If the control logic 500 determines that the MGT data includes information identifying a rail joint, the control logic 500 proceeds to step 512. If the control logic 500 determines that the MGT data includes information that there are no rail joints, the control logic 500 proceeds to step 514.

[0102] In step 512, in one embodiment, the control logic 500 may multiply the rail safety score by a user-defined multiplier. For example, the user-defined multiplier may be 1.5. The user-defined multiplier may be modified based on user input. The control logic 500 may receive input from the user to update the multiplier to a new value. The control logic 500 then proceeds to step 514.

[0103] In step 514, in one embodiment, the control logic 500 may determine whether the inspection frequency meets the minimum inspection frequency threshold. For example, the control logic 500 may measure the MGT of the entire track segment over a period of time and compare the MGT to the minimum inspection frequency threshold. For example, the minimum inspection frequency threshold may include a predefined MGT representing the track segment limit. In one example, when the MGT across the track segment is greater than the predefined MGT, the control logic 500 may increase the inspection frequency. In another example, the time period may include a time range between inspections based on the inspection frequency. In one example, the inspection frequency may correspond to a hierarchical structure. For example, the minimum inspection frequency threshold may be a first level, a second level, or a third level. In one example, the first level has the lowest inspection frequency, the second level has a medium inspection frequency, and the third level has the highest inspection frequency. The first level may include a frequency of two inspections per month. The second level may include a frequency of one inspection per week. The third level may include a frequency of three inspections per week. The control logic 500 may compare the inspection frequency with the known inspection frequency to determine whether the inspection frequency meets the minimum inspection frequency threshold. For example, the minimum inspection frequency threshold may be the first level. If the checking frequency satisfies the minimum checking frequency threshold, control logic 500 proceeds to step 518. If the checking frequency does not satisfy the minimum checking frequency threshold, control logic 500 proceeds to step 516.

[0104] In step 516, in one embodiment, the control logic 500 may determine whether to increase the inspection frequency of the track segment. For example, when the inspection frequency is equal to or greater than the minimum inspection frequency threshold, the control logic 500 may increase the inspection frequency of the track segment to the next level in the hierarchy. In one example, if the inspection frequency is twice a month, the control logic 500 may increase the inspection frequency to once a week. In another example, if the inspection frequency is once a week, the control logic 500 may increase the inspection frequency to three times a week. The control logic 500 then proceeds to step 518.

[0105] In step 518, in one embodiment, the control logic 500 may generate a final inspection frequency for at least one section of track based on the rail safety score. The control logic 500 may generate the final inspection frequency based on information corresponding to whether the section of track includes a rail joint and an MGT that crosses the section of track within a period of time. The control logic 500 then terminates or waits for a new inspection creation request and may repeat the above steps.

[0106] Fig. 6A -C and Figure 7 An exemplary embodiment and corresponding process for identifying railroad asset defects on four sections of track (i.e., track sections 602-608) are provided. The track sections may extend indefinitely on either side, presenting only one section of track. These examples are intended to help understand the implementation and practice of the present disclosure, and the present disclosure should not be limited to these examples.

[0107] Figures 6A-6C An exemplary diagram of a railroad inspection system 600 is shown in accordance with one or more exemplary embodiments of the present disclosure. The diagram illustrates a railroad inspection system 600 in which railroad asset defects along various sections of track are marked based on geometric vehicle testing and defect marking. The diagram 600 may include track sections 602-608 and at least one marked railroad asset defect 610.

[0108] Track segments 602-608 may correspond to mile column ranges of track segments. For example, track segment 602 may correspond to a mile column range between MP100 and MP200, where MP100 is located at the far left of track segment 602 and MP200 is located at the far right of track segment 602. Track segment 606 may correspond to a mile column range between MP200 and MP300, where MP200 is located at the far left of track segment 606 and MP300 is located at the far right of track segment 606. Runway segment 604 may correspond to a mile column range between MP90 and MP190 parallel to runway segment 602, where MP90 is located at the far left of runway segment 604 and MP190 is located at the far right of runway segment 604. Runway segment 608 may correspond to a range of mile posts parallel to runway segment 606 between MP 190 and MP 290 , where MP 190 is located at the far left side of runway segment 608 and MP 290 is located at the far right side of runway segment 608 .

[0109] The system 600 can show the path of the locomotive along the track segments 602-608 according to the geometry of the track segments 602-608. For example, the track segment 602 includes a track joint from the track segment 602 to the track segment 604, so the locomotive can travel from the track segment 602 to the track segment 604. In one example, the geometry car will travel along the track segments 602-608 in each applicable geometry of the track segments 602-608 to identify at least one marked rail asset defect 610. In another example, the track segments 602-608 can include incremental measurements for normalized analysis. For example, the track segments 602-608 can all include incremental measurements of equal lengths measured according to mile columns. For example, each track segment 602-608 can include incremental measurements of 100 MP. In this way, the track segments 602-608 can all be compared to each other to accurately compare the relative track segment status. The relative track segment status can correspond to at least one marked rail asset defect 610 and other rail factors to determine the inspection frequency.

[0110] At least one marked railroad asset defect 610 may represent a dangerous point along track segments 602-608. For example, track segment 602 may include three defects, as shown in FIG6. In one example, track segment 604 may include one defect, as shown in FIG6. In another example, track segment 606 may include five defects, as shown in FIG6. In another example, track segment 608 may include nine defects, as shown in FIG6. In one example, at least one marked railroad asset defect 610 may correspond to geometric tag data (e.g., geometric tag data 108 of FIG1) including an encoded score according to the severity of the defect. In one example, the defect may include a first tag type, a second tag type, and a third tag type. In another example, the defect may include an open tag and a closed tag.

[0111] In one embodiment, reference Fig. 6A , system 600 may be used to analyze the frequency of inspections along each track segment 602-608. For example, based strictly on the number of defects, track segment 604 may be inspected less frequently than the other track segments because track segment 604 has the fewest defects. In another example, track segment 604 may include other factors that affect the frequency of inspections, which may increase the frequency of inspections after analysis. For example, runway segment 604 may include the highest degree of MGT on runway segment 604, which would increase the overall rating of runway segment 604. The overall rating of track segment 604 corresponds to the frequency of inspections. In another example, track segment 604 may include rail joints, which would cause the overall rating to be multiplied by a user-defined multiplier when analyzed. Other factors of the number of defects may also affect the overall rating, resulting in an increased frequency of inspections.

[0112] In another example, refer to Figure 6B , based solely on the number of defects, track segment 608 may be inspected more frequently than the other track segments because track segment 608 has the greatest number of defects. The inspection frequency of track segment 608 may correspond to the type of label to which the defects correspond. For example, track segment 608 may include nine defects, eight of which are closed labels and one defect is an open label (i.e., a first label type). Additionally, track segment 604 may include one defect, where the defect is an open label that is a third label type. In this case, based strictly on the number and type of defects, track segment 608 may include a lower inspection frequency than track segment 604.

[0113] In another example, refer to Figure 6C, the inspection frequency of the track segments 602-608 may be based on multiple categories of rail safety data. For example, in addition to at least one marked rail asset defect 610, the categories may also include CSP value, MGT value, precipitation value, geometric vehicle tag value, BFI value, slow command value, and human defect value. The inspection frequency of each track segment 602-608 may correspond to the analysis of the above rail safety data categories.

[0114] refer to Figure 7 As a process of railway inspection 700, according to one or more exemplary embodiments of the present disclosure. The railway inspection process 700 of this embodiment starts at step 702. In step 702, in one embodiment, the process 700 may instruct the system to identify a track segment of a predetermined distance for inspection purposes. Then, the process 700 proceeds to step 704. In step 704, in one embodiment, the process 700 may instruct the system to establish a subdivision of the track segment. Then, the process 700 proceeds to step 706. In step 706, in one embodiment, the process 700 may instruct the system to receive data related to railway safety maintenance of the track segment. Then, the process 700 proceeds to step 708. In step 708, in one embodiment, the process 700 may instruct the system to identify defects and defect locations corresponding to the track segment based on the data. Then, the process 700 proceeds to step 710. In step 710, in one embodiment, the process 700 may instruct the system to aggregate railway safety values ​​to generate a railway safety score. Then, the process 700 proceeds to step 712. At step 712 , in one embodiment, process 700 may instruct the system to generate a final inspection frequency for at least one section of railroad track based on the railroad safety score.

[0115] The present disclosure achieves at least the following advantages:

[0116] 1. Generate a comprehensive, data-driven inspection frequency model based on measured physical factors to determine the optimal visual inspection frequency for a section of track.

[0117] 2. Convert data corresponding to physical factors on a section of track to determine visual inspection frequency.

[0118] 3. Comply with relevant federal regulations corresponding to railroad inspections.

[0119] 4. Standardize the data of each track section to accurately determine the inspection frequency of each track section.

[0120] 5. Assign safety ratings to each section of track based on measured data values ​​of physical factors related to railway operation.

[0121] 6. Improve the safety of passengers and cargo along the railway by determining the optimal inspection frequency for each section of track.

[0122] Those skilled in the art will readily appreciate that without the specific combination of computer hardware and other structural components and mechanisms assembled in the system of the present invention and described herein, the above advantages and purposes will not be possible to achieve. In addition, the algorithms, methods and processes disclosed herein improve and convert any general-purpose computer or processor disclosed in this specification and the accompanying drawings into a special-purpose computer, which is programmed to execute the disclosed algorithms, methods and processes to achieve the above functions, advantages and goals. It should also be understood that for those who are proficient in this field, there are a variety of programming tools that can be used to generate and implement the functions and operations described above. In addition, the selection of a specific programming tool may be determined by the specific goals and constraints of implementing these concepts, which are selected to implement the concepts proposed in this article and the appended claims.

[0123] The description in this patent document should not be construed as implying that any particular element, step, or function is an essential or critical element that must be included within the scope of the claims. In addition, unless the exact words "means for..." or "step for..." are expressly used in a particular claim and followed by a participatory phrase identifying the function, no claim is intended to invoke 35 USC §112(f) for any additional claim or claim element. Terms used in the claims (such as (but not limited to) "mechanism", "module", "device", "unit", "component", "element", "member", "means", "machine", "system", "processor", "processing device", or "controller") should be understood and intended to refer to structures known to those skilled in the relevant art and further modified or enhanced by the features of the claims themselves, and are not intended to invoke 35 USC §112(f). Even under the broadest reasonable interpretation, in accordance with this paragraph of the specification, the claims are not intended to invoke 35 USC §112(f) in the absence of the above specific language.

[0124] The present disclosure may be embodied in other specific forms without departing from its spirit or essential features. For example, each new structure described herein may be modified to accommodate specific local changes or requirements while retaining their basic configuration or structural relationship to each other, or while performing the same or similar functions described herein. Therefore, the present embodiments should be considered illustrative rather than restrictive in all respects. Therefore, the scope of the invention should be determined by the appended claims rather than by the foregoing description. Therefore, all changes within the meaning and equivalent scope of the claims should be included in the claims. In addition, the various elements in the claims are not well-known, conventional or traditional. Instead, the claims point to the non-traditional innovative concepts described in the specification.

Claims

1. A system for minimizing railway track safety hazards by optimizing the frequency of railway visual inspections based on acquired data related to railway safety maintenance, comprising: A memory for storing the acquired data related to railway safety maintenance and an inspection frequency classification model to convert the acquired data from an original form into a final inspection frequency value; as well as The processor is configured to convert the acquired data related to railway safety maintenance from a raw form into a final inspection frequency value by performing the following steps: Receiving acquired railway safety maintenance related data of at least one section of railway track; assigning a railway safety value to each of a plurality of categories of acquired data based on a user-defined hazard model; Aggregating rail safety values ​​to generate a rail safety score; When the MGT calculation includes a rail joint factor, multiply the rail safety score by a user-defined multiplier; and A final inspection frequency value for at least one section of railroad track is generated based on the railroad safety score.

2. The system of claim 1, wherein the processor is further configured to perform the step of classifying the acquired data into a plurality of categories.

3. The system of claim 2, wherein the plurality of categories include Comprehensive Service Plan (CSP), MGT, Precipitation, Geometry Car Tag, Ballast Fouling Index (BFI), Slow Go Command, and Artificial Defect.

4. The system of claim 3, wherein the geometric automobile tag comprises an open tag or a closed tag.

5. The system of claim 4, wherein the open label and the closed label each correspond to a first label type, a second label type, or a third label type.

6. The system of claim 1, wherein the processor is further configured to perform the step of determining whether to increase an inspection frequency of the railway track segment when the railway track segment corresponds to a minimum inspection standard threshold.

7. The system of claim 6, wherein the minimum inspection standard threshold comprises a measurement of at least 12 MGT on the railway track segment since a last test.

8. The system of claim 6, wherein the inspection frequency is increased to the next available railroad manual inspection frequency.

9. The system of claim 1, wherein the final inspection frequency value is based on a user-defined inspection threshold, including a first railroad manual inspection frequency, a second railroad manual inspection frequency, and a third railroad manual inspection frequency.

10. The system of claim 9, wherein the first railroad manual inspection frequency is twice a month, the second railroad manual inspection frequency is once a week, and the third railroad manual inspection frequency is three times a week.

11. A method for minimizing railway track safety hazards by optimizing the frequency of railway visual inspections based on acquired data related to railway safety maintenance, comprising: Receiving acquired railway safety maintenance related data of at least one section of railway track; assigning a rail safety value to each of a plurality of categories based on a user-defined hazard model; Aggregating rail safety values ​​to generate a rail safety score; When the MGT calculation includes a rail joint factor, multiply the rail safety score by a user-defined multiplier; and A final inspection frequency value for at least one section of railroad track is generated based on the railroad safety score.

12. The method according to claim 11, wherein the processor is further configured to perform the step of segmenting the acquired data into a plurality of categories.

13. The method of claim 12, wherein the plurality of categories include Comprehensive Service Plan (CSP), MGT, Precipitation, Geometry Car Tag, Ballast Fouling Index (BFI), Go Slow Command, and Artificial Defect.

14. The method of claim 13, wherein the geometric automobile tag comprises an open tag or a closed tag.

15. The method of claim 14, wherein the open label and the closed label each correspond to a first label type, a second label type, or a third label type.

16. The method of claim 11, wherein the processor is further configured to perform the step of determining whether to increase an inspection frequency of the railroad track segment when the railroad track segment corresponds to a minimum inspection criteria threshold.

17. The method of claim 16, wherein the minimum inspection standard threshold comprises at least 12 MGT measurements on the railway track segment since a last test.

18. The method of claim 16, wherein the inspection frequency is increased to the next available railroad manual inspection frequency.

19. The method of claim 11, wherein the final inspection frequency value is based on a user-defined inspection threshold, including a first railroad manual inspection frequency, a second railroad manual inspection frequency, and a third railroad manual inspection frequency.

20. The method according to claim 19, wherein the first railway manual inspection frequency is twice a month, the second railway manual inspection frequency is once a week, and the third railway manual inspection frequency is three times a week.

21. A computer-implemented method for minimizing safety hazards on railway tracks by optimizing the frequency of railway visual inspections based on data obtained related to railway safety maintenance, the computer-implemented method comprising: Receiving acquired railway safety maintenance related data of at least one section of railway track; assigning a rail safety value to each of a plurality of categories based on a user-defined hazard model; Aggregating rail safety values ​​to generate a rail safety score; When the MGT calculation includes a rail joint factor, multiply the rail safety score by a user-defined multiplier; and A final inspection frequency value for at least one section of railroad track is generated based on the railroad safety score.

22. The computer-implemented method of claim 21, wherein the processor is further configured to perform the step of segmenting the acquired data into a plurality of categories.

23. The computer-implemented method of claim 22, wherein the plurality of categories includes Comprehensive Service Plan (CSP), MGT, Precipitation, Geometry Car Tag, Ballast Fouling Index (BFI), Go Slow Command, and Artificial Defect.

24. The computer-implemented method of claim 23, wherein the geometric car tag comprises an open tag or a closed tag.

25. A method for assessing the frequency of visual track inspections comprising: receiving data associated with a railway track segment; Generate continuous and categorical variables representing track segment condition indicators of concern; Continuous variables were transformed and rescaled to match categorical variables; Generates a check value for each variable; and Generates a model that assigns specific track sections to one of multiple inspection protocols based on inspection values.

26. The method of claim 25, further comprising generating a series of model results for each combination of input values.

27. The method of claim 25, further comprising maintaining a first variable at a fixed value and allowing all other variables to be drawn from a pool of random values ​​based on an empirical density function of the variable.

28. The method of claim 25, wherein if the test is invalid or untested, the model can upgrade the track segment to increase visual inspection.

29. The method according to claim 25, wherein the inspection protocol can be three times a week, once a week or twice a month.

30. The method of claim 25, wherein the inspection protocol is based on related values ​​of MGT, BFI, Rainfall, ClassDrop, CSP Class, Human Defects, and CW Splice Count.