Ballastless track intelligent laying integrated management platform and implementation method

Abstract

The invention provides a ballastless track intelligent laying integrated management platform and an implementation method, and the method comprises the steps: obtaining a component number, a track gauge value and a timestamp of a ballastless track at a target construction site, and constructing a component main index data set; on the basis of the component main index data set, abnormal component judgment logic is designed to recognize abnormal components, and an abnormal component set is formed; performing quality scoring on the abnormal component set to generate a component quality score set; and generating task suggestion items according to the component quality score set and outputting the task suggestion items to a scheduling platform for execution. The method effectively improves the construction precision, plays an important role in reducing the construction risk, improving the resource utilization efficiency and the like, has good expandability and engineering applicability, and provides a solid technical guarantee for large-scale track construction in the future.

Description

Technical Field

[0001] This invention belongs to the technical field of integrated management platforms, and particularly relates to an integrated management platform and implementation method for intelligent laying of ballastless track. Background Technology

[0002] Ballastless track, as a core infrastructure form for high-speed railways and urban rail transit, is widely used in the construction of complex working conditions and heavy-load traffic lines due to its high smoothness, stability, and low maintenance costs. However, with the development of track laying technology, ballastless track structures have greater rigidity and poor adjustability, making precise control requirements during construction more stringent, especially in the track laying stage. How to achieve high-precision quality control, real-time data acquisition and monitoring, rational allocation of construction resources, and timely response to construction anomalies while ensuring laying efficiency has become a major technical challenge for the industry. Although existing technologies have introduced BIM models, RFID tags, and sensors to assist in laying process management, these systems mostly operate independently, lacking an effective collaborative platform, resulting in difficulties in information exchange and sharing among multiple systems. The current system suffers from the following problems: First, data silos make it difficult to achieve standardized integration and real-time transmission of data among various devices and systems; second, the lack of real-time feedback and intelligent control during the laying process means that when track gauge deviations or construction quality issues occur, reliance on manual experience for judgment can easily lead to decision-making delays or misjudgments; third, component-level quality traceability is difficult, making it hard to quickly locate the specific problematic component and trace responsibility when track quality issues arise; and fourth, the poor linkage between equipment and the management platform makes it impossible to dynamically adjust the laying equipment based on the real-time construction status.

[0003] Therefore, it is necessary to develop an integrated management platform for intelligent ballastless track laying, which can realize the integration of data collection, analysis and scheduling control during the construction process, improve construction accuracy, reduce operational risks, and provide system support for subsequent large-scale track construction. Summary of the Invention

[0004] This invention addresses the problems of data fragmentation, slow feedback mechanisms, and difficulty in quality traceability in existing technologies by proposing an integrated management platform and implementation method for intelligent ballastless track laying. By establishing a unified intelligent management platform, multiple information systems are integrated for management and unified scheduling, achieving standardized integration and real-time transmission of construction site data.

[0005] To achieve the above objectives, the first aspect of the present invention provides an integrated management platform and implementation method for intelligent ballastless track laying, comprising: Obtain the component number, gauge value, and timestamp of the ballastless track at the target construction site, and construct the component master index data set; Based on the main index data set of the components, an abnormal component judgment logic is designed to identify abnormal components and form an abnormal component set; the abnormal component judgment logic is constructed and generated based on the gauge jump index between components based on the gauge value, the gauge jump index between components, and the structural continuity curvature index based on the degree of activation. The abnormal component set is scored to generate a component quality score set; Based on the component quality score set, task suggestions are generated and output to the scheduling platform for execution.

[0006] Furthermore, the track gauge value is automatically collected by the track gauge detection device; The method for identifying the validity of a component after constructing the main index data set includes a validity identification function. If the track gauge value is successfully acquired and the component is successfully positioned, the validity flag function is set to 1, which means that an availability flag is attached, and the current data is considered valid.

[0007] Furthermore, the step of designing abnormal component judgment logic to identify abnormal components based on the component master index data set, forming an abnormal component set, includes: For the same component, a gauge jump index between components is generated based on the gauge value and the gauge value at the previous moment; Based on the track gauge value, the track gauge value at the previous moment, and the track gauge value at the next moment, a structural continuity curvature index is generated by using discrete second-order difference and combining the degree of activation of the current component position under the external stress field; wherein, the degree of activation of the current component position under the external stress field is used to describe the susceptibility of structural anomalies caused by stress unevenness or temperature difference. An abnormal component judgment logic is constructed based on the gauge jump index between components and the structural continuity curvature index. The set of anomalous components is obtained by combining the mutation occurrence and the presence of structural continuity mutations.

[0008] Furthermore, the abnormal component judgment logic is as follows: If the gauge jump index between components is greater than the preset jump threshold, then the current component undergoes a sudden change; if the structural continuity curvature index is greater than the continuity change threshold, then the current component has a structural continuity change.

[0009] Furthermore, the degree of activation of the current component's location under the external stress field is generated based on the temperature gradient change and the basic support consistency coefficient; the temperature gradient change is the normalized value of the temperature difference range at different times on the laying day of the component's laying point; the basic support consistency coefficient is the mechanical uniformity index of the contact between the current component and the track bed, and when the basic support consistency coefficient approaches 0, it indicates that the track bed stiffness unevenness at that component is the most serious.

[0010] Further, the step of performing quality scoring on the set of abnormal components to generate a set of component quality scores includes: The quality score is calculated by combining the gauge jump index between components, the structural continuity curvature index of the previous moment, the structural continuity curvature index of the current moment, the structural continuity curvature index of the next moment, the temperature gradient change, and the consistency coefficient of the foundation support. Based on the quality scores, a set of component quality scores is constructed and bound to the corresponding components.

[0011] Furthermore, an environmental coupling score is constructed by combining the structural continuity curvature index and temperature gradient change to reduce the platform's misjudgment rate.

[0012] Further, the step of generating task suggestions based on the component quality score set and outputting them to the scheduling platform for execution includes: Based on the component quality score and the corresponding component composition abnormality component score pair; Based on the aforementioned abnormal component score pairs, combined with temperature gradient changes, foundation support consistency coefficient, and component pre-existing conditions, The abnormality level score of a component is calculated based on the proportion of abnormal components in each component. Based on the component anomaly level score, the recommended level is mapped to three levels: High, Medium, and Low; The component sensitivity is calculated based on the gauge jump index between components, the structural continuity curvature index, and the component type. The insertion weight is determined based on the component's position in the linear mileage and the average position of the current scheduling segment. The task suggestions are encoded into a standardized structure by combining the suggestion level, component type, component sensitivity, and insertion weight, and then pushed to the scheduling platform interface for execution.

[0013] Furthermore, the component sensitivity is used to represent the current component's response efficiency to abnormal actions, that is, the system's tendency to select its optimal processing method.

[0014] In a second aspect, the present invention provides an integrated management platform for intelligent laying of ballastless track, the management platform including at least one processor; And a memory storing instructions that, when executed by at least one processor, implement the steps of the integrated management platform for intelligent ballastless track laying as described in any of the preceding claims.

[0015] The beneficial technical effects of the present invention are at least as follows: This invention proposes an integrated management platform and implementation method for intelligent ballastless track laying, aiming to overcome problems such as data fragmentation, slow feedback mechanisms, and difficulty in quality traceability in existing technologies. By establishing a unified intelligent management platform, multiple information systems are integrated for management and unified scheduling, achieving standardized integration and real-time transmission of construction site data. Through multi-source data fusion technology, the platform can monitor the status information of each component during track laying in real time, including data such as track gauge, sleeper position, temperature stress, etc., thereby providing support for construction quality assessment, problem location, and adjustment. Regarding anomaly detection and quality assurance, this invention designs an anomaly response mechanism based on a component-level data model. When anomalies such as track gauge deviation and structural unevenness occur, the mechanism can promptly identify and locate the source of the problem, and guide construction operations in real time through preset correction strategies, ensuring improved construction accuracy and efficiency. Simultaneously, in terms of component management, this invention constructs a data binding mechanism based on the entire lifecycle, ensuring that each component has a unique identifier in the platform and can be synchronized with its quality status in real time, thereby achieving precise quality traceability of the track structure. Furthermore, the platform can interact with various equipment and smart terminals at the construction site to achieve automatic task distribution, closed-loop status feedback, and intelligent scheduling control, providing comprehensive monitoring and decision support for the construction process. Through the above innovative design, this invention significantly improves the level of digitalization and intelligence in the field of ballastless track laying. It not only effectively improves construction accuracy but also plays an important role in reducing construction risks and improving resource utilization efficiency. At the same time, it has good scalability and engineering applicability, providing a solid technical guarantee for future large-scale track construction. Attached Figure Description

[0016] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0017] Figure 1 This is a flowchart of the integrated management platform and implementation method for intelligent ballastless track laying of the present invention. Detailed Implementation

[0018] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0019] In one or more embodiments, such as Figure 1 As shown, an integrated management platform and implementation method for intelligent ballastless track laying are disclosed. The method includes the following: S1. Obtain the component number, track gauge value, and timestamp of the ballastless track at the target construction site, and construct the component master index data set.

[0020] Specifically, the goal of this step is to establish a standard data unit with time, space, and status information for each laid component, based on multi-source data collected at the construction site, serving as the basic unit for the entire system's operation. This component-based data modeling approach differs from traditional time- or mileage-based structures, enabling precise location of the status of each physical component during the actual laying process. This provides a readily available foundation for subsequent anomaly identification, quality assessment, and construction recommendations.

[0021] Furthermore, in practice, component numbering... This is the core index field of the system. All laying components are pre-assigned unique codes at the factory (e.g., sleeper numbers S102, S103, etc.) and have pre-embedded QR codes or UHF RFID chips on their end faces. During on-site laying, after hoisting, construction workers use handheld barcode scanners or UHF antennas to read the code on the component. This process connects to the main platform via Bluetooth or RS232 interface, and the component number is bound just before it is placed in position.

[0022] Track gauge value The track gauge data is automatically collected by the track laying detection device. In actual engineering projects, these devices are mostly laser track gauge measurement systems installed at the rear of the track laying machine or on the track inspection trolley. They are equipped with dual laser probes, which scan the position of the rails on both sides of the already positioned sleepers by measuring the probe spacing. The system sampling frequency is generally set to 10Hz or higher, and the raw track gauge data is transmitted to the platform's data access module in real time. To ensure that component identification is aligned with the track gauge data, the platform uses a sliding time window mechanism to extract the frame of data from the track gauge data stream that is closest to the time of the component number reading as the track gauge measurement value for that component.

[0023] For a specific example: Component S104 is located at 7:32:15.421 seconds. The platform receives component number S104 uploaded by the UHF identifier and, based on the system clock, retrieves the laser ranging data from 7:32:15.420 to 7:32:15.422 seconds, calculating the average track gauge value as... If the system does not obtain valid laser measurement data within this time period, the platform will mark the component as invalid data for subsequent correction or manual inspection.

[0024] Timestamp A unified clock source is used from the main construction control system. All data acquisition modules (barcode scanners, UHF antennas, laser ranging units) synchronize their time based on this clock to avoid data misalignment or inconsistencies. The time synchronization signal can be broadcast via the NTP protocol or aligned via the CAN bus or local synchronization signal line.

[0025] Based on the above information, the platform establishes the following component-level data structure: ; in: Indicates the first The unique number of each component is obtained through UHF or QR code identification. Indicates the first The track gauge data collected when each component is in place is provided by a laser track gauge measuring device and has been normalized. The timestamp indicating that the component is in place is provided by the platform's unified clock; Considering the possibility of component recognition failures or missing track gauge measurements during the laying process, the platform sets the following data validity identification function: ; in: The component data validity marker is generated by the data access module based on the acquisition status. and All data must be successfully aligned before the platform considers it valid. All component data structures The data is written to the platform's relational database in real time and spatially mapped to the component geometry in the BIM model. The platform uses a mapping table based on component numbers to quickly bind logical indexes to the 3D model, enabling any analysis model to directly access its spatial location and structural parameters via component numbers, achieving end-to-end data consistency.

[0026] The final output of this step is the component master index data set. Each data unit contains a component number, track gauge normalization status, and installation time, along with an availability flag. This dataset serves as the input source for all subsequent analysis and decision-making modules, forming the fundamental dependency structure for the platform's intelligent behavior.

[0027] S2. Based on the main index data set of the components, design an abnormal component judgment logic to identify abnormal components and form an abnormal component set; the abnormal component judgment logic is constructed and generated based on the gauge jump index between components based on the gauge value, the gauge jump index between components, and the structural continuity curvature index based on the degree of activation.

[0028] Specifically, this step is based on the component master index data set output in step one. Its goal is to identify, in component-level construction scenarios of ballastless track laying, sets of components that may exhibit gauge anomalies or abrupt changes in structural continuity. As a key focus for subsequent quality assessment and construction decisions, anomaly detection in traditional track laying often relies on manual sampling of measurement points or simplified methods based on the mean deviation of sections. This approach fails to identify minute jumps or stress accumulation errors at the "component level" within the structure. Furthermore, ballastless track structures are highly rigid and difficult to adjust; failure to accurately identify problematic components early on can easily lead to irreversible problems such as gauge imbalance, loose fasteners, or sleeper damage. Therefore, this step, combining the patent's practical scenarios and system structural characteristics, designs an innovative anomaly detection mechanism starting from the component-level gauge status.

[0029] The core operational process comprises three parts: 1) constructing a gauge jump index to identify sudden anomalies during construction; 2) designing a structural continuity evaluation term to simulate local curvature changes; and 3) proposing an anomaly impact factor regularization term to measure the structural excitation response of external conditions on anomalous components. These three sub-modules are integrated into an anomaly identification function, forming a compact and practically interpretable anomaly judgment mechanism.

[0030] Furthermore, the gauge jump index between components is first defined. : ; in Representing components The normalized state of the track gauge. This indicates the track gauge value of the preceding component. This indicator reflects the relative adjustment range between components during construction. Large jump values ​​often correspond to on-site errors such as misalignment during laying or improper rail clamping.

[0031] Then construct the structural continuity curvature index. : ; in, This is the track gauge value at the next moment.

[0032] The first term is the "discrete second-order difference" of the three-point component, representing whether the component is a peak point of structural abrupt change; the second term... This innovative regularization factor, designed in this step, represents the degree of activation of the component's location under an external stress field, used to describe the susceptibility of structural anomalies caused by uneven stress or temperature differences. This is an adjustable weighting coefficient. This term is introduced to address the common problem of "abnormal component displacement due to non-geometric reasons" in ballastless tracks, compensating for the blind spots in identification caused by errors resulting from temperature gradients and changes in foundation reaction forces that cannot be covered by purely geometric judgments.

[0033] Regularization factor The calculations are based on stress-driven factors in the track laying environment and temperature gradient changes obtained by the platform from geothermal sensing lines. and basic support consistency coefficient (Acquired via a pressure-sensitive thin-film array installed under the sleeper) Calculation component Motivational susceptibility: ; in This is the normalized value of the temperature difference at different times on the day of installation for the component's location. This is an index of the mechanical uniformity of the contact between the component and the track bed. .when When the value approaches 0, it indicates that the unevenness of the track bed stiffness is most severe at that component. A larger value indicates that the component is more prone to abnormal behavior under the same geometric conditions. This regularization design fully reflects the multi-source environmental factors considered by this patented system for component anomaly identification, avoiding the misinterpretation of reasonable deviations under external stimuli as construction errors.

[0034] Ultimately, the platform uniformly constructs the logic for judging abnormal components: like Then the component A mutation occurred; The preset jump threshold is used; like Then the component There is abrupt change in structural continuity; This is the threshold for continuous mutations; The platform determines the threshold based on the set threshold. and Automatically filter component sets: ; For example: a certain component The measured track gauge is , , Temperature gradient normalized value Contact coefficient ,set up ,but: ; ; ; like , If both the track gauge mutation and structural excitation of the component exceed the standard, the platform will automatically determine that the component is abnormal.

[0035] This step outputs a set of abnormal components. Each element in the component set meets at least one type of anomaly criterion and is accompanied by original track gauge data and detailed values ​​of anomaly indicators, so that they can be called by the subsequent quality assessment and task suggestion modules.

[0036] S3. Perform quality scoring on the set of abnormal components to generate a set of component quality scores.

[0037] Specifically, this step involves the set of abnormal components output in step two. Based on this, a more detailed quantitative assessment of the abnormal structural state of each component is conducted, and a structured quality score is output. This serves as the direct input for the subsequent task suggestion generation module. This step is not merely a continuation of the "is it abnormal?" judgment, but a core module for hierarchical assessment of the severity of abnormalities. In the scenario of intelligent ballastless track laying, structural deviations may originate from construction operation errors (such as gauge not being properly tightened), external environmental interference (such as temperature stress), and uneven quality of the component materials themselves (such as differences in sleeper density). Therefore, simple threshold judgment methods cannot meet the needs of accurate decision-making. The scoring model constructed in this step fully considers these factors and relies on the component data model from the previous two steps. Based on the set of abnormal indicators, a component quality scoring mechanism with practicality and structural interpretability was designed.

[0038] The input data includes: the set of abnormal components identified in step two. The gauge jump value of each component Structural curvature index Environmental motivating factors (including temperature gradient changes) Consistency coefficient with basic support All the variables mentioned above have been defined, collected, or calculated in the previous two steps. This step does not add a new data collection module, but instead performs multi-layer fusion calculations based on the existing data.

[0039] Furthermore, the platform first... for each component Constructing a multi-factor structural scoring function The influence of three dimensions is considered: geometric deviation, structural continuity, and environmental induced intensity. The geometric deviation term originates from... This is a direct manifestation of the construction process; structural continuity reflects the construction team's construction stability and indicates the degree of stability at the structural level; environmental induced items are specifically designed for this patent to reflect the unique "non-human-caused abnormal" factors in the paving area.

[0040] The quality scoring model is as follows: ; in: For components The overall quality score is calculated, and the higher the score, the more serious the deviation of the component from the normal structural state. For components The gauge difference between the current component and the previous component is derived from laser gauge measurement. The structural curvature term, namely the second-order difference in gauge between the previous component, the current component, and the next component, has already been calculated in the previous stage; The local gradient, representing the change in structural curvature, reflects dramatic fluctuations in structural continuity. It is the gradient response factor; It is the temperature fluctuation amplitude under the sleeper measured by the ground temperature sensor, which is collected by the track-side ground temperature fiber optic monitoring system at a frequency of 0.1Hz; It is the uniformity coefficient of track bed support at the bottom of the sleeper, which comes from the pressure-sensitive film array on the laying machine before laying, measuring the consistency of pressure on the laying surface; The scoring weights can be set based on historical engineering experience, such as... .

[0041] The core innovation of this formula design lies in the local curvature gradient amplification mechanism in the second term. This design addresses the common problem of misjudgment in field scenarios where "local points change drastically but the overall situation remains within the threshold range." For example, in special structural points such as turnout areas and curve sections, the platform needs a mechanism to enhance structural sensitivity, rather than simply using an absolute value for filtering. This design enables the system to maintain the accuracy of anomaly detection even in complex geometric arrangements.

[0042] Third item: Environmental Coupling Score This patent proposes a quality reduction mechanism for "non-human-caused" anomalies to reduce the platform's misjudgment rate. In actual laying processes, gauge anomalies may arise from factors such as thermal expansion and contraction, or early deformation caused by incomplete concrete curing, rather than operational errors. Therefore, if the component is located in a high-temperature gradient and unevenly supported area, even... Even if it's not high, it should still be given more attention.

[0043] For example: Components The data is as follows: , , , , , , , , ,but The second amplification factor is: ; The third environmental item is... ; Overall rating: ; This score quantifies the overall quality status of the current component and will be used in the platform's recommended strategy selection.

[0044] The output of this step is a set of component scores. The platform will automatically bind to the component number. The original component index values ​​and scoring process parameters are stored in the database structure for querying by the next task generation module.

[0045] S4. Generate task suggestions based on the component quality score set and output them to the scheduling platform for execution.

[0046] Specifically, this step is based on the component score set output in step three. This paper designs and implements a task suggestion generation and output mechanism to complete a closed-loop control process for the intelligent laying platform, from identifying structural anomalies to forming clear execution actions. In traditional construction management, even if some components are identified as having problems, manual judgment is still required on whether and how to handle them. The processing order and scheduling are often determined by human experience, which has drawbacks such as strong subjectivity, low efficiency, and lack of unified standards. In this patented system, all task generation must have: 1. Dynamic responsiveness to scoring values; 2. Matching ability with construction capabilities and resources; 3. Control over task conflicts and batch order. This step takes these as the design goal and proposes a calculable, executable, and schedulable suggestion generation model based on structural scoring.

[0047] The input data consists of all the abnormal component rating pairs output in step three. And the intermediate variable used in the scoring calculation: track gauge mutation. Structural curvature index Environmental motivating factors In addition, the platform can also access construction batches bound to components. Spatial location Component types This step involves creating existing data fields. No new data collection items are added in this step; all data originates from previous steps and the platform component index structure.

[0048] To ensure the controllability of task implementation, this step innovatively breaks down the task suggestion into three parts: suggestion level. Suggested actions Insertion weights for tasks Together they form a complete set of recommendations. .in Control the urgency level of handling this component. The types of actions the control platform should take. Used to guide the sorting and merging strategies when multiple tasks are concurrent in the task scheduling module.

[0049] First, construct the recommendation rating function. This function uses component scoring. Based on this, two modification terms are introduced: one is the environmental incentive regularization term. First, consider whether the anomaly is caused by external influences. If strong environmental stimuli lead to a high score, the recommended level can be lowered. Second, consider the cumulative stress item of the structural components. Before the components are laid... The density of abnormal components is used to determine whether a section is in a high-risk area. The component anomaly level score is as follows: ; in: The original score for the suggested grade; Rate the components; The temperature difference and support coupling terms have been normalized. Before indicating components The proportion of abnormal components in a given component is calculated as follows: ; The adjustment coefficients are used to control the weights of the external influence correction and the section anomaly density amplification terms, with recommended values ​​of 0.2 and 0.4, respectively. This indicates an indicator function.

[0050] The innovation of this formula lies in the introduction of an anomaly density sensitivity term. This feature is specifically designed for paving systems and addresses the inability to promptly handle issues in areas with continuous local errors but dispersed score distributions. For example, if a section experiences continuous small-amplitude deviations in certain components, but the re-paving condition is not triggered individually, the system will continuously release problematic components if historical density is not considered, leading to the accumulation of overall deviations in the local structure. The introduction of this concept expands the scoring from "single component score" to the expression of "overall risk of continuous structure".

[0051] according to Recommended level Mapped to three levels: like ,but ; like ,but ; like ,but .

[0052] in and This is an experience threshold value, which can be set to 0.05 or 0.08 depending on the characteristics of the project.

[0053] Action suggestions The generation no longer uses a simple interval-action lookup table, but instead introduces a component sensitivity function. This function is determined by the gauge mutation. Structural curvature and component type The combined generation of these three factors indicates the "processing response efficiency" of the component in response to abnormal actions, that is, the system's tendency to select its optimal processing method: ; in: For component sensitivity For response weights; This is a component type mapping function that converts component types (such as standard sleepers, turnout bases, etc.) into response coefficients. according to Selecting the landing interval Examples include "adjusting track gauge", "marking for observation", and "re-laying sleepers".

[0054] Finally, to support the task concurrency sorting requirements of the platform's scheduling layer, the platform generates an insertion weight for each suggestion. The calculation method comprehensively recommends the grade and the position of the component in the laying sequence. Based on the spatial density, the following scheduling index is constructed: ; in: The position of the component in the linear mileage; This represents the average position of the current scheduling segment; To adjust the rate control factor (recommended value: 0.01~0.1); The function term is a spatial offset scheduling amplification term, which assigns a higher scheduling index to components that are closer to the current job end.

[0055] The scheduling index is designed specifically to match the "rolling operation" logic of construction sites. It prioritizes high-risk components close to the work site from the set of manageable tasks, thereby improving scheduling efficiency and resource utilization.

[0056] The platform ultimately encodes the task suggestions into a standardized structure: ; The data is pushed to the scheduling platform interface. All fields are structured callable variables, supporting automatic work order generation, scheduling sorting, and team assignment by the platform.

[0057] A second embodiment of the present invention provides an integrated management platform for intelligent laying of ballastless track, the management platform including at least one processor; And a memory storing instructions, which, when executed by at least one processor, implement the steps of the integrated management platform for intelligent ballastless track laying as described above. While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather as descriptions of features that can embody specific embodiments of a particular invention. Specific features described in this specification within the context of an independent embodiment may also be implemented in combination with a single embodiment. Conversely, various features described within the context of a single embodiment may also be implemented independently in multiple embodiments, or in any suitable sub-combination. Furthermore, while features may be described for combination and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and the claimed combination may be redirected to a sub-combination or a variation thereof.

[0058] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An implementation method of an intelligent ballastless track laying integrated management platform, characterized in that, The implementation method comprises the following steps: Obtaining the component number, track gauge value and timestamp of the target construction site ballastless track, and constructing a component main index data set; Based on the component main index data set, an abnormal component judgment logic is designed to identify abnormal components, forming an abnormal component set; The abnormal component judgment logic is generated based on the track gauge value, the component-to-component track gauge jump index, and the structure continuity curvature index based on the component-to-component track gauge jump index and the degree of activation; Quality scoring is performed on the abnormal component set to generate a component quality score set; According to the component quality score set, task suggestions are generated and output to the scheduling platform for execution.

2. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 1, wherein, The track gauge value is automatically collected by a track gauge detection device; After constructing the component main index data set, an effectiveness identification function is provided: If the track gauge value is successfully collected and the component positioning is successful, the effectiveness identification function = 1, i.e. with availability mark, and the current data is identified as valid.

3. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 1, wherein, Based on the component main index data set, an abnormal component judgment logic is designed to identify abnormal components, forming an abnormal component set, which comprises: For the same component, based on the track gauge value and the track gauge value at the previous moment, a component-to-component track gauge jump index is generated; Based on the track gauge value, the track gauge value at the previous moment and the track gauge value at the next moment, through discrete second-order difference, combined with the degree of activation of the current component under the external stress field, a structure continuity curvature index is generated; wherein the degree of activation of the current component under the external stress field is used to describe the structure abnormality susceptibility caused by stress unevenness or temperature difference; Based on the component-to-component track gauge jump index and the structure continuity curvature index, an abnormal component judgment logic is constructed; Combined with the occurrence of mutation and the existence of structure continuity mutation, an abnormal component set is obtained.

4. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 3, wherein, The abnormal component judgment logic is: If the component-to-component track gauge jump index is greater than the preset jump threshold, the current component has a mutation; if the structure continuity curvature index is greater than the continuity mutation threshold, the current component has a structure continuity mutation.

5. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 3, wherein, The degree of activation of the current component under the external stress field is generated based on the temperature gradient change and the foundation support consistency coefficient; the temperature gradient change is the temperature difference range normalization value of the component at the laying point on the laying day at different times; the foundation support consistency coefficient is a mechanical uniformity index of the current component contacting the track bed, and when the foundation support consistency coefficient tends to 0, it indicates that the track bed stiffness unevenness at the component is the most serious.

6. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 5, wherein, The quality scoring of the abnormal component set to generate a component quality score set comprises: Combined with the component-to-component track gauge jump index, the previous structure continuity curvature index, the current structure continuity curvature index, the next structure continuity curvature index, the temperature gradient change and the foundation support consistency coefficient, the quality score is calculated and obtained; Based on the quality score, a component quality score set is constructed and bound to the corresponding component.

7. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 6, wherein, Combined with the structure continuity curvature index and the temperature gradient change, an environmental coupling score is constructed to reduce the platform misjudgment rate.

8. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 5, wherein, The task suggestion item is generated according to the component quality score set and output to a scheduling platform for execution, comprising: an abnormal component score pair is generated based on the component quality score and the corresponding component composition; Based on the abnormal component score, combined with temperature gradient change, foundation support consistency coefficient and component front component abnormality level score is calculated by calculating the proportion of abnormal components in the component. the suggestion level is mapped into three levels: High, Medium and Low according to the component abnormal level score; a component sensitivity is calculated based on the component track gauge jump index, the structure continuity curvature index and the component type; an insertion weight is determined according to the position of the component in the linear mileage and the current scheduling segment average position; the task suggestion item is encoded into a standardized structure in combination with the suggestion level, the component type, the component sensitivity and the insertion weight, and pushed to the scheduling platform interface for execution.

9. The implementation method of the ballastless track intelligent laying integrated management platform according to claim 8, wherein, The component sensitivity is used to represent the processing response efficiency of the current component to abnormal actions, i.e. the selection tendency of the optimal processing means of the system.

10. An intelligent integrated management platform for ballastless track laying, characterized in that, The management platform comprises at least one processor; and a memory storing instructions which, when executed by the at least one processor, implement the steps of the implementation method of the ballastless track intelligent laying integrated management platform according to any one of claims 1-9.

Images