Rail eccentricity comprehensive evaluation system, method and device based on small-radius curve bridge scene

Abstract

The invention relates to a rail eccentricity comprehensive evaluation system, method and device based on a small-radius curve bridge scene. Eccentricity data are obtained through the eccentricity measurement module, bridge operation performance data are collected through the operation performance monitoring module, a time reference is provided through the clock module, timestamp alignment and storage are conducted on the eccentricity data and the bridge operation performance data through the eccentricity monitoring module, and comprehensive and accurate basic data are provided for follow-up analysis. An analysis module in the online module obtains data stored in a local database through a data exchange module, an analysis model is used for deep analysis, the relationship between the data is mined, the proportion of dynamic and static influence factors of line bridge eccentricity is determined, a data change rule and an influence mechanism are clarified, and a basis is provided for measure formulation. And the measure module is used for selecting a proper improvement scheme from a plurality of eccentricity solving measures such as track lining, line strengthening measures, line bridge combination strengthening measures and the like according to the proportion condition of the dynamic and static influence factors obtained by the analysis module.

Description

Technical Field

[0001] This invention relates to the field of railway track eccentricity evaluation technology for curved bridges, and in particular to a comprehensive evaluation system, method and apparatus for railway track eccentricity in the scenario of small-radius curved bridges. Background Technology

[0002] The routine operation of heavy-haul railways with high axle load trains subjects curved bridges to prolonged high impacts and vibrations, making them prone to exceeding the eccentricity limit. Severe eccentricity affects the stress on the upper and lower structures of the bridge, increases the live load effect on the eccentric side beams and substructure, and impacts the lateral overturning stability of the beams. Under heavy axle loads and high transport volumes, it may trigger other structural defects, accelerate structural deterioration, and jeopardize operational safety. Defects develop more rapidly, especially on small-radius curves, affecting track performance, train operation, and even safety. Therefore, eccentricity assessment of small-radius curved bridges has become an urgent problem to be solved. Summary of the Invention

[0003] Therefore, it is necessary to provide a comprehensive evaluation system, method, and device for track eccentricity in the scenario of small-radius curved bridges.

[0004] The first aspect provides a comprehensive evaluation system for track eccentricity in the scenario of small-radius curved bridges, including: an eccentricity monitoring module, a clock module, an eccentricity measurement module, an operational performance monitoring module, a data exchange module, an analysis module, and a measures module;

[0005] The clock module is used to generate a continuous, periodic clock pulse signal with a fixed duty cycle, starting from the bridge's service life. The duty cycle of the clock pulse signal is less than the minimum time interval for the operation performance monitoring module to acquire data.

[0006] The eccentricity measurement module is connected to the clock module, and the eccentricity measurement module is used to acquire eccentricity data based on the clock pulse signal;

[0007] The operation performance monitoring module is connected to the clock module, and the operation performance monitoring module is used to periodically acquire bridge operation performance data of the bridge based on the pulse signal;

[0008] The eccentricity monitoring module is connected to the clock module, the eccentricity measurement module, and the operational performance monitoring module, respectively. The eccentricity monitoring module is used to acquire the eccentricity data and the bridge operational performance data based on the pulse signal, and after corresponding them with the timestamps, sort them in chronological order to form a timestamp data table and record it in the local database; when the data in the timestamp data table reaches the eccentricity analysis trigger condition, an analysis request is sent to the measures module.

[0009] The data exchange module is used to acquire data from the local database corresponding to multiple different bridges and send it to the analysis module. The analysis module trains an analysis model based on the data in the local database to reflect the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge. The eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data.

[0010] The measures module is used to respond to the analysis request, control the analysis module to obtain the dynamic and static impact ratio based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model, and determine the matching eccentricity solution measures based on the dynamic and static impact ratio.

[0011] In one embodiment, the analysis model includes a static analysis model, a dynamic analysis model, and a reverse influence model.

[0012] In one embodiment, the static analysis model includes a finite element model of a curved bridge-track structure, and the analysis module is further used for:

[0013] Constructing finite element models of curved bridges and track structures;

[0014] Based on the longitudinal resistance curve of the fastener, the longitudinal resistance curve of the track bed, and the lateral resistance curve of the track bed, a finite element model of the curved bridge and the track structure is generated by using the track bed resistance spring to connect the finite element model of the curved bridge and the track structure. The finite element model of the curved bridge-track structure represents the relationship between the lateral force, expansion force, and flexural force applied to the bridge, the temperature force applied to the rail, and the lateral displacement of the track structure.

[0015] In one embodiment, the dynamic analysis model includes a vehicle-track-bridge coupled dynamic model, and the analysis module is further used for:

[0016] Construct finite element models of the vehicle system, the track system, and the bridge system;

[0017] Using the route mileage as the core variable, the finite element models of the vehicle system, the track system, and the bridge system are coupled.

[0018] To identify the main influencing factors of track eccentricity on curved bridges under dynamic load;

[0019] The main influencing factors are divided into railway-related data and bridge-related data, and the obtained eccentricity features are mapped using a machine learning algorithm to obtain the vehicle-track-bridge coupled dynamic model. The vehicle-track-bridge coupled dynamic model represents the influence ratio of railway-related data and bridge-related data under different eccentricity features.

[0020] In one embodiment, the machine learning algorithm is the Apriori association analysis algorithm, and when mining itemsets based on the Apriori association analysis algorithm, different states of the same physical property are mutually exclusive as constraints.

[0021] In one embodiment, the reverse influence model is used to continuously exert dynamic mechanical influence on the dynamic analysis model in a finite element simulation environment according to different vehicle speeds, axle loads, and frequencies until the bridge reaches the eccentricity analysis trigger condition, and the duration before reaching the eccentricity analysis trigger condition is recorded.

[0022] In one embodiment, the eccentricity data includes track slab displacement, track creep, and semantic features determined based on acquired rail images.

[0023] In one embodiment, the bridge performance data includes beam vibration characteristics, beam dynamic strain, beam dynamic deflection and deformation, and pier vibration characteristics.

[0024] Secondly, a comprehensive evaluation method for track eccentricity of small-radius curved bridges is provided, applied to the aforementioned comprehensive evaluation system for track eccentricity in the scenario of small-radius curved bridges. The method includes:

[0025] Data is acquired from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order;

[0026] Based on the data in the local database, an analytical model reflecting the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge is trained; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data;

[0027] In response to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, the dynamic and static influence ratio is obtained based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model.

[0028] Based on the ratio of dynamic and static influences, a matching eccentricity solution is determined.

[0029] In one embodiment, the analysis model includes a static analysis model, a dynamic analysis model, and a reverse influence model.

[0030] Thirdly, a comprehensive evaluation device for track eccentricity of small-radius curved bridges is provided, which is applied to the aforementioned comprehensive evaluation system for track eccentricity in the scenario of small-radius curved bridges. The device includes:

[0031] The local data acquisition module is used to acquire data from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order;

[0032] The model training module is used to train an analytical model that reflects the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge based on the data in the local database; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data;

[0033] The influence ratio analysis module is used to respond to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, and to obtain the dynamic and static influence ratios based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model.

[0034] The eccentricity response decision module is used to determine the matching eccentricity solution based on the ratio of dynamic and static influences.

[0035] The aforementioned system, method, and device for comprehensive evaluation of track eccentricity in small-radius curved bridge scenarios utilize local modules (eccentricity measurement module, operational performance monitoring module, clock module, and eccentricity monitoring module) for multi-dimensional data acquisition. Specifically, the eccentricity measurement module acquires eccentricity data, the operational performance monitoring module collects bridge operational performance data, the clock module provides a time reference, and the eccentricity monitoring module timestamps and stores the eccentricity data and bridge operational performance data, providing comprehensive and accurate foundational data for subsequent analysis. The online analysis module acquires data stored in the local database through the data exchange module, employs analytical models for in-depth analysis, uncovers relationships between data, determines the proportion of dynamic and static influencing factors of track-bridge eccentricity, clarifies data change patterns and influencing mechanisms, and provides a scientific basis for measure formulation. Based on the proportion of dynamic and static influencing factors obtained from the analysis module, the measures module selects appropriate remediation schemes from multiple eccentricity solutions, such as track realignment, track strengthening measures, and track-bridge combined strengthening measures, to specifically address the track-bridge eccentricity problem and ensure the rationality and effectiveness of the measures.

[0036] By combining offline monitoring with online model training and optimization, the accuracy of the analysis model in judging the proportion of dynamic and static influencing factors is improved, enabling the analysis model to better adapt to changes in actual conditions and provide more accurate support for solving similar problems in the future, thereby further improving the accuracy of eccentricity assessment results in the scenario of small-radius curved bridges. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the structure of a comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario, according to one embodiment.

[0039] Figure 2 This is the execution logic diagram of a comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario.

[0040] Figure 3 This is a schematic diagram illustrating the Apriori association analysis algorithm for mining itemsets in one embodiment. Detailed Implementation

[0041] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0043] As described in the background section, with the routine operation of high-density, long-formation trains with large axle loads on heavy-haul railways, curved bridges are subjected to significant impacts and vibrations over long periods, making them prone to exceeding the eccentricity limit. This is especially true on small-radius curves, where eccentricity issues develop rapidly, not only affecting the long-term performance of the track structure and causing severe train swaying, but also posing a risk of boundary violations, which can seriously impact safe train operation.

[0044] Eccentricity in curved bridges refers to the eccentricity between the beam and the rail. Current research primarily focuses on the remediation of eccentricity exceeding limits and the management of beam-rail eccentricity exceeding limits. For example, based on eccentricity remediation methods such as the rope straightening method, a calculation model has been established that can automatically generate remediation schemes for eccentricity exceeding limits, reducing the amount of eccentricity in curved bridges and playing a certain role in preventing beam-rail eccentricity exceeding limits. Another example is the maintenance and repair decision model proposed for bridges exceeding eccentricity limits. This model can derive the overall maintenance strategy for the bridge and can also generate detailed maintenance and repair plans based on the track parameters and the current condition of the bridge. Yet another example is the Petri-Net-based modeling method, composed of different modules, each with its own data source and function, and interconnected with each other. This enables an integrated management model for the deterioration and maintenance of curved bridges exceeding eccentricity limits, assisting bridge management departments in bridge management.

[0045] Furthermore, by utilizing an aggregated computation algorithm, combined with the degree analysis fuzzy hierarchical analysis method (EA FAHP) and the dominant hierarchical analysis method (DAHP), maintenance decisions for bridges exceeding limits are made; and by employing a secondary rectification method, the risk of altering the relative stability of the track due to excessive one-time track shifting is reduced.

[0046] Choosing a suitable preset eccentricity can reduce the interaction force between the beam and the rail, and also reduce the internal force of the bridge structure. Research results show that when the curve radius is greater than 2000 m, it is possible to choose not to set a preset eccentricity. When the bridge has unequal spans, the non-coincidence of the pier centerline and the beam joint centerline should be considered, and a suitable longitudinal eccentricity should be set in the direction of the long span bridge.

[0047] It is evident that existing research mainly focuses on methods for correcting eccentricity in railway line bridges, with less attention paid to the effectiveness of eccentricity correction and the deterioration of the condition of railway line bridges on small-radius curves in heavy-haul railways.

[0048] For railway bridges with small-radius curves, research shows that, under the premise of setting a pre-set eccentricity, strict control of construction precision is necessary. Accurate measurements using total stations and levels are crucial to ensure the accuracy of bridge structure construction, especially during the transportation and erection of the bridge beams, to prevent dimensional deviations. Under train loads, the operational performance of the bridge is evaluated and analyzed based on the vibration amplitude and acceleration of the beams. For curved bridges with beam-rail eccentricity exceeding 70 mm, the bridge's load-bearing capacity needs to be recalculated and track realigned, as excessive beam-rail eccentricity may negatively impact the bridge's load-bearing capacity. Heavy-haul railway bridges with small-radius curves typically suffer from the following problems: rail spalling and corrugation near joints; insufficient lateral resistance of the track bed; and insufficient ballast shoulder height.

[0049] Track beam eccentricity significantly affects the lateral (vertical) amplitude and vertical acceleration at mid-span of bridges, with all parameters increasing with the eccentricity value. Track beam eccentricity mostly occurs on curved bridges, with a smaller proportion on straight bridges. On straight bridges, track beam eccentricity is addressed by shifting beams within the bridge maintenance area, making the influencing factors and intervention methods relatively direct. However, track beam eccentricity on curved bridges requires adjustment by the track maintenance area, making the influencing factors and adjustment methods more complex and diverse. This leads to a complex problem in choosing the appropriate adjustment method to achieve the best state maintenance effect. Furthermore, research on small-radius curved bridges is scarce, yet their impact is significant. Therefore, a track eccentricity assessment scheme for small-radius curved bridges is urgently needed.

[0050] In response to this, such as Figures 1-2 As shown, this application provides a comprehensive evaluation system 100 for track eccentricity in a small-radius curved bridge scenario, including: an eccentricity monitoring module 110, a clock module 120, an eccentricity measurement module 130, an operational performance monitoring module 140, a data exchange module 150, an analysis module 160, and a measures module 170.

[0051] The clock module 120 is used to generate a continuous, periodic clock pulse signal with a fixed duty cycle, starting from the bridge's service life. The duty cycle of the clock pulse signal is less than the minimum time interval for the operation performance monitoring module 140 to acquire data.

[0052] The eccentricity measurement module 130 is connected to the clock module 120. The eccentricity measurement module 130 is used to acquire eccentricity data based on the clock pulse signal. Specifically, the eccentricity measurement module 130 can measure the eccentricity data at each railway node location in real time, determine whether eccentricity has actually occurred based on the eccentricity measurement data and a set eccentricity threshold, classify and organize the eccentricity measurement data according to different line parameters, and acquire the eccentricity data. The eccentricity data mainly includes the line plane curve, line gradient, and outer rail superelevation. The frequency at which the eccentricity measurement module 130 acquires data is based on the operating frequency of the clock module 120.

[0053] The eccentricity measurement module 130 measures the eccentricity of each railway node in real time, primarily using image measurement. The measurement results are divided into data such as rail eccentricity distance to calculate track slab displacement and track creep. Simultaneously, the calculated data and corresponding semantic features derived from the images are transmitted as eccentricity data sets to the eccentricity monitoring module 110. Specifically, high-resolution main stream images can be acquired and used as input to the super-resolution network. The training data for image super-resolution is typically generated using two methods: bicubic interpolation image degradation synthesis; and images acquired using low-resolution sub-streams and high-resolution main streams, serving as input and supervision images, respectively.

[0054] The operational performance monitoring module 140 is connected to the clock module 120, and the operational performance monitoring module 140 is used to periodically acquire bridge operational performance data based on the pulse signal. The bridge operational performance data includes beam vibration characteristics, beam dynamic strain, beam dynamic deflection and deformation, and pier vibration characteristics.

[0055] The eccentricity monitoring module 110 is connected to the clock module 120, the eccentricity measurement module 130, and the operational performance monitoring module 140, respectively. The eccentricity monitoring module 110 is used to acquire the eccentricity data and the bridge operational performance data based on the pulse signal, and after corresponding them with the timestamps, sort them in chronological order to form a timestamp data table and record it in the local database as the actual recorded data of the bridge. When the data in the timestamp data table reaches the eccentricity analysis trigger condition, an analysis request is sent to the measures module 170.

[0056] The eccentricity monitoring module 110 can, based on the timing pulses received from the clock module 120, request eccentricity data from the eccentricity measurement module 130 and obtain bridge operation performance data from the operation performance monitoring module 140 at the time points when the pulses are acquired. The bridge operation performance data is obtained through online bridge monitoring.

[0057] The eccentricity analysis triggering condition can include data exceeding a triggering threshold. To meet the requirements of automatic monitoring, triggering thresholds can be set for different attributes in the timestamp data table. If the data for each attribute exceeds the corresponding triggering threshold, the eccentricity analysis triggering condition is considered met, and an analysis request is sent to the measures module 170.

[0058] The data exchange module 150 is used to acquire data from the local database corresponding to multiple different bridges and send it to the analysis module 160. The analysis module 160 trains an analysis model based on the data in the local database to reflect the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge. The eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data.

[0059] The measures module 170, in response to the analysis request, controls the analysis module 160 to obtain the dynamic and static impact ratios based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model, and determines matching eccentricity solutions based on the dynamic and static impact ratios. Optionally, the system provided in this application embodiment can also manually set the detection time limit of the measures module 170 as needed to trigger the measures module 170 to analyze the dynamic and static impact ratios based on the analysis module 160, thereby selecting eccentricity solutions.

[0060] After the measures module 170 receives the analysis request, the analysis module 160 provides the dynamic and static impact ratio based on the data at this time node, and the measures module 170 provides the treatment measures for the line bridge based on the feedback data.

[0061] The eccentricity monitoring module 110, clock module 120, eccentricity measurement module 130, operational performance monitoring module 140, and measures module 170 are local modules (deployed at the location of the curved bridge), while the data exchange module 150 and analysis module 160 are online modules (which can be deployed in a monitoring room or cloud server, etc.). Eccentricity mitigation measures include, but are not limited to, track realignment measures, track reinforcement measures, and track-bridge combination reinforcement measures. Track realignment measures involve changing the planar alignment of the track to ensure that the track-bridge eccentricity meets the specifications. Track realignment should aim to achieve the optimal track alignment to meet the track-bridge eccentricity requirements. Track realignment is a direct method to eliminate track-bridge eccentricity, but the causes of track eccentricity may still exist, and track eccentricity may reappear after remediation. In actual engineering, there are two extreme cases. One is that only the smoothness requirement of the horizontal curve of the track is considered, and the impact on the bridge is not taken into account when adjusting the track alignment. This leads to the gradual increase of track-bridge eccentricity as track maintenance work progresses. The other is that only the requirement of track-bridge eccentricity is considered, and the track alignment of local sections is adjusted, resulting in the overall track smoothness not being met.

[0062] The track reinforcement measures are as follows: the occurrence of track and bridge eccentricity is limited by adjusting the state of the rails and their related structures or changing the relevant structural parameters.

[0063] The measures to strengthen the connection between the track and the bridge are as follows: consider the lateral connection between the track and the bridge structure to a certain extent, and improve the lateral resistance of the track structure while ensuring the safety of the bridge structure.

[0064] Specifically, multi-dimensional data collection is performed through the system's local modules (eccentricity measurement module 130, operational performance monitoring module 140, clock module 120, and eccentricity monitoring module 110). The eccentricity measurement module 130 acquires eccentricity data, the operational performance monitoring module 140 collects bridge operational performance data, the clock module 120 provides a time reference, and the eccentricity monitoring module 110 timestamps and stores the eccentricity data and bridge operational performance data, providing comprehensive and accurate foundational data for subsequent analysis. The analysis module 160 in the online module acquires data stored in the local database through the data exchange module 150, uses analytical models for in-depth analysis, uncovers relationships between data, determines the proportion of dynamic and static influencing factors of bridge-line eccentricity, clarifies data change patterns and influencing mechanisms, and provides a scientific basis for measure formulation. Based on the proportion of dynamic and static influencing factors obtained from the analysis module 160, the measures module 170 selects appropriate remediation schemes from multiple eccentricity solutions, such as track realignment, track reinforcement measures, and combined bridge-line reinforcement measures, to specifically address the bridge-line eccentricity problem and ensure the rationality and effectiveness of the measures.

[0065] By combining offline monitoring with online model training and optimization, the accuracy of the analysis model in judging the proportion of dynamic and static influencing factors is improved, enabling the analysis model to better adapt to changes in actual conditions and provide more accurate support for solving similar problems in the future, thereby further improving the accuracy of eccentricity assessment results in the scenario of small-radius curved bridges.

[0066] The online system trains the model using historical data from similar bridges in the field, and continuously acquires new real-time data (eccentricity data and bridge performance data) from bridges currently in operation to further train and optimize the overall analysis model. This trained model distinguishes the proportions of dynamic and static influencing factors affecting the eccentricity characteristics of the current bridge. In other words, besides being trained on historical data, the analysis model can be iteratively optimized based on newly generated real-time data to better adapt to changes in actual conditions, providing more accurate support for solving similar problems in the future and further improving the accuracy of eccentricity assessment results in small-radius curved bridge scenarios.

[0067] In one embodiment, the analysis model includes a static analysis model, a dynamic analysis model, and a reverse influence model.

[0068] In one embodiment, the static analysis model includes a finite element model of a curved bridge-track structure, and the analysis module 160 is further configured to:

[0069] Constructing finite element models of curved bridges and track structures;

[0070] Based on the longitudinal resistance curve of the fastener, the longitudinal resistance curve of the track bed, and the lateral resistance curve of the track bed, a finite element model of the curved bridge and the track structure is generated by using the track bed resistance spring to connect the finite element model of the curved bridge and the track structure. The finite element model of the curved bridge-track structure represents the relationship between the lateral force, expansion force, and flexural force applied to the bridge, the temperature force applied to the rail, and the lateral displacement of the track structure.

[0071] The static analysis model is based on a static finite element model of the bridge and track structure, specifically a curved bridge-track structure finite element model. The track structure finite element model consists of rail models, fastener models, sleeper models, and ballast models. The rail and sleeper models must exhibit torsional and shear effects. The fastener and ballast models must be unidirectional elements with strong nonlinearity, possessing both axial and torsional functions. The axial function characterizes the relative displacement between connecting nodes, simulating the tension-compression characteristics between the two structures; the torsional function characterizes the relative rotation angle between connecting nodes, simulating the torsional characteristics between the two structures.

[0072] Obtain the curves of longitudinal resistance of fasteners, longitudinal resistance of track bed, and transverse resistance of track bed.

[0073] Based on the actual conditions, a finite element model of the curved bridge is established, and a finite element model of the track structure is introduced into the finite element model of the curved bridge. The two are connected by the resistance spring of the track bed model. During modeling, the track structure at the front and rear of the bridge can be extended by 100m to eliminate the influence of abrupt changes at the beam ends.

[0074] Based on the above method, finite element models of curved bridge-track structures with different curve radii, different lateral resistance of track beds, and different pier heights are established. While applying different lateral forces, different expansion forces, and different flexural forces, temperature forces are applied to the rails, and the lateral displacement of the track structure is calculated and analyzed.

[0075] In one embodiment, the dynamic analysis model includes a vehicle-track-bridge coupled dynamic model, and the analysis module 160 is further configured to:

[0076] Construct finite element models of the vehicle system, the track system, and the bridge system;

[0077] Using the route mileage as the core variable, the finite element models of the vehicle system, the track system, and the bridge system are coupled.

[0078] To identify the main influencing factors of track eccentricity on curved bridges under dynamic load;

[0079] The main influencing factors are divided into railway-related data and bridge-related data, and the obtained eccentricity features are mapped using a machine learning algorithm to obtain the vehicle-track-bridge coupled dynamic model. The vehicle-track-bridge coupled dynamic model represents the influence ratio of railway-related data and bridge-related data under different eccentricity features.

[0080] The dynamic analysis model is a vehicle-track-bridge coupled dynamic model. For the finite element model of the vehicle system, the car body, bogie, and wheelsets can be simulated using beam elements, plate and shell elements, solid elements, mass elements, and combinations thereof in finite element analysis software. The linear elastic stiffness of the primary and secondary suspensions is simulated using spring elements, while the damping and nonlinear spring elements are treated as virtual forces using the pseudo-force method.

[0081] For the finite element model of the track system, the rails can be simulated using spatial beam elements, the track slabs using plate elements, the sleepers and ballast mass using mass elements, and the rail pads, elastic mortar pads, ballast stiffness and foundation stiffness using vertical, horizontal and longitudinal spring elements.

[0082] The implementation process of coupling the finite element models of the vehicle system, track system, and bridge system with the line mileage as the core variable can be as follows: taking the line mileage as the basic variable, considering the actual loading position of each wheelset on the curve, establishing its moving coordinate system, and realizing the correct coupling relationship between the bridge and the wheelset through coordinate transformation; adopting the creep assumption for the lateral contact between the wheel and the rail, considering the creep rate caused by the difference in the arc length of the inner and outer rails and the creep rate caused by the rotation of the wheelset around the center of curvature when passing through the curve; taking into account centrifugal force and superelevation component force; and considering the vehicle suspension force when passing through the curve as if passing through a straight line.

[0083] Influencing factors include, but are not limited to, axle load, train speeds, curve radii, track bed resistance, and gradient conditions. A comprehensive consideration of vehicle conditions, track conditions, and bridge performance is obtained. By mapping the above influencing factors into railway-related and bridge-related data with the acquired eccentricity features using machine learning, the relationship between railway-related data, bridge-related data, and eccentricity features is obtained, revealing the proportion of railway-related data influence and bridge-related data influence under different eccentricity features.

[0084] In one embodiment, the machine learning algorithm is the Apriori association analysis algorithm, and when mining itemsets based on the Apriori association analysis algorithm, different states of the same physical property are mutually exclusive as constraints.

[0085] The Apriori algorithm is an association rule mining technique, specifically a parallel data mining algorithm for association rules. The core idea of ​​the Apriori algorithm is a recursive method based on frequent itemset theory. It uses a layer-by-layer iterative search to mine all frequent itemsets in the target transaction database until the highest-order frequent itemset is found. Finally, strong association rules are obtained by calculating the obtained frequent itemsets.

[0086] For example, dataset D has 4 records: 134, 235, 1235, and 25. If the Apriori algorithm is used to find frequent k-itemsets, the minimum support is set to 50%. Figure 3 As shown, first, candidate frequent one-itemsets are generated, including all 5 data points, and the support of each data point is calculated. After calculation, pruning is performed, and data point 4 is pruned because its support is only 25%. The final frequent one-itemsets are 1235. Then, these are linked to generate candidate frequent two-itemsets, including 12, 13, 15, 23, 25, and 35, for a total of 6 sets. At this point, our first iteration ends.

[0087] In the second iteration, the support of candidate frequent 2-itemsets is calculated on the dataset, followed by pruning. Items 12 and 15, with only 25% support, are discarded, resulting in the true frequent 2-itemsets: 13, 23, 25, and 35. Next, candidate frequent 3-itemsets are generated: 123, 135, and 235 (three groups in total, not shown in the diagram). Calculating the support of these candidate frequent 3-itemsets reveals that 123 and 135 both have 25% support, so they are pruned, resulting in the final true frequent 3-itemset group being 235. Since further data joins are not possible at this point, candidate frequent 4-itemsets are generated, and the final result is the frequent 3-itemset 235.

[0088] In this embodiment, railway-related data, bridge-related data, and corresponding eccentric features are all used as items in the basic itemset. To ensure the physical meaning of the data output has practical significance, no correlation is established between the railway-related data and bridge-related data. When establishing the itemset, different states of the same physical property need to be mutually exclusive to ensure that no noise that contradicts common sense about physics occurs.

[0089] At this point, the above relationship is evaluated based on three points:

[0090] 1. Support(x, y): The ratio of the number of times a data item appears to the total number of data items in the set;

[0091]

[0092] Where num{x,y} represents the number of transactions containing the itemset {x,y}, and num{samples} represents the total number of transactions.

[0093] 2. Confidence level: The probability that another data point will appear after a certain data point has been found.

[0094] The confidence (x, y) of x with respect to y can be expressed as:

[0095]

[0096] Where num{x} is the number of transactions containing itemset x, and confidence(x,y) represents the probability that itemset y will appear if itemset x appears.

[0097] 3. Lift: The ratio of the probability of x occurring given y to the overall probability of x occurring.

[0098]

[0099] Where P(x) is the overall probability of the occurrence of itemset x.

[0100] If the lift is greater than one, it means that y has a valid strong association with x; if the lift is less than one, it means that y has an invalid strong association with x.

[0101] Based on the above three points, the relations existing in the above itemset can take two forms:

[0102] Frequent itemsets: A set of items that frequently appear in a group.

[0103] Association rules: imply a strong relationship between two items.

[0104] Once the relationships between railway-related data, bridge-related data, and their corresponding eccentricity features are determined, it can be determined whether the data are strongly correlated or strongly correlated (mutually exclusive, etc.). Based on the above correlations and the numerical changes in the data, a data change relationship matrix can be established (as a vehicle-track-bridge coupled dynamics model).

[0105] Once the data change relationships are determined, during data changes, since railway-related data and bridge-related data influence each other, the proportion of changes in these two types of data (railway-related data and bridge-related data) relative to the total data change can be obtained based on the change relationships. This allows us to determine the relationship between the changes in the railway and bridge data during data changes.

[0106] In one embodiment, the reverse influence model is used to continuously exert dynamic mechanical influence on the dynamic analysis model in a finite element simulation environment according to different vehicle speeds, axle loads, and frequencies until the bridge reaches the eccentricity analysis trigger condition, and the duration before reaching the eccentricity analysis trigger condition is recorded.

[0107] The measures module 170 selects appropriate measures to output based on the proportion of influencing factors corresponding to the received eccentric features.

[0108] The measures module 170 is used to obtain reasonable eccentricity solutions based on the above analysis data. The solutions are mainly divided into three categories: track realignment, line reinforcement measures, and line-bridge combined reinforcement measures.

[0109] If the frequency of the eccentricity feature is low enough (which can be determined by setting a low frequency threshold), then the exclusive selection of the channel is taken as the current measure.

[0110] If railway-related data has a higher impact, then line reinforcement measures should be selected; if bridge-related data has a higher impact, then combined line and bridge reinforcement measures should be selected.

[0111] If the reverse impact output by the reverse analysis module 160 is greater than the normal development speed, or if any data of the bridge is close to the bridge safety critical value, the track will be diverted first, and the track reinforcement measures or the track-bridge combined reinforcement measures will be selected according to the proportion of the influence of dynamic and static factors.

[0112] In one embodiment, the eccentricity data includes track slab displacement, track creep, and semantic features determined based on acquired rail images.

[0113] In one embodiment, the bridge performance data includes beam vibration characteristics, beam dynamic strain, beam dynamic deflection and deformation, and pier vibration characteristics.

[0114] To better illustrate the implementation of the comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario provided in this application, the following example is given:

[0115] A railway bridge with a small-radius curve has a curve radius of 400m. During operation and maintenance, there are instances of severe rail wear and track eccentricity on the uphill heavy train track. Therefore, it is necessary to monitor relevant data over a period of time, summarize and analyze it to understand the relationship between factors such as load, train speed, rail temperature, and sleeper displacement. Combined with bridge structural health monitoring, this will form an integrated monitoring system for the small-radius curve. The eccentricity measurement module 130 can include a sleeper displacement monitoring system and a rail temperature monitoring system.

[0116] The sleeper displacement monitoring system in the eccentricity measurement module 130 mainly consists of an infrared monitoring camera installed beside the track, checkerboard-patterned targets placed on the sleepers, an industrial control computer for data processing and storage, monitoring data management software, and power supply and communication cables. It employs infrared image recognition technology to monitor sleeper displacement in real time, with a measurement error of ±0.5mm. Three monitoring sections are selected: the bridgehead, the center of the circular curve, and the transition point on the bridge. Each monitoring section is equipped with a monitoring system, including an industrial control computer and main control box, a camera (including a housing) and mounting bracket, a rail temperature monitoring probe and clamping frame, and external power supply and communication cables.

[0117] In sections with sound barriers, the camera bracket can be fixed to the sound barrier reinforcement plate by clamping (or drilling), and then the camera (including the outer cover) can be mounted on the camera bracket. To avoid bumping into construction workers, the mounting height should be around 1.8m. In the other two measurement sections without sound barriers, the camera bracket can be fixed to the angle iron on the upper part of the guardrail by clamping (or drilling), and then the camera (including the outer cover) can be mounted on the camera bracket. Similarly, to avoid bumping into construction workers, the camera should be placed on the outside of the guardrail.

[0118] Depending on the site conditions, two methods can be used for the targets: one is to attach the checkerboard-shaped target to the outer sides of the two facades of the right-angled target mounting frame, and then fix the mounting frame to one end of the sleeper. During installation, it is necessary to ensure that one facade of the right-angled mounting frame is parallel to the sleeper and the other facade is perpendicular to the sleeper. To avoid mutual interference when the two targets are identified, different colored strips are used to separate them.

[0119] The rail temperature monitoring system in the eccentricity measurement module 130 mainly consists of a rail temperature monitoring probe, a monitoring host, and a probe clamping fixture, providing all-weather monitoring of rail temperature. The monitoring probe and the monitoring host communicate via 2.4G wireless transmission. The monitoring host can transmit data to an industrial control computer via a data cable, and then to a server via a network. Alternatively, it can directly upload data to the server via 4G wireless transmission. In this application, the data cable transmission method between the monitoring host and the industrial control computer is selected.

[0120] For small-radius curves, in order to reduce the impact of eccentric measurement equipment on daily track maintenance, non-contact video methods can be used to capture images of sleeper lateral displacement, rail temperature, and sleeper temperature on sections of heavy-duty track with and without side sound barriers. By identifying and extracting sleeper displacement characteristics, the track structure displacement variation pattern can be understood.

[0121] Based on the sleeper displacement monitoring system and the rail temperature monitoring system, the eccentricity measurement module 130 can perform the following steps:

[0122] The surface temperature of the rails and track slabs is obtained, the distance between the rails is measured and converted into rail eccentricity, and observation images are acquired.

[0123] A super-resolution network was designed to enhance the contrast of the observation scale edges and corners. To ensure that the super-resolution image has the same contrast and texture as the target image, the correlation between different feature channels of the image was used to measure the image texture, i.e.: Gij(I)=φi·φj

[0124] Where φi and φj are the features of the i-th and j-th channels of the image, respectively;

[0125] To minimize the difference between the relevance of the target image and the relevance of the generated image, the loss function used for image super-resolution and contrast enhancement training is... for:

[0126] ;

[0127] Where I represents the super-resolution image predicted by the network. To monitor the actual acquired images, c represents the number of channels for image texture features, and G... ij The inner product of feature channel i and feature channel j;

[0128] Image segmentation is used to locate the boundary position of the scale and obtain the observation scale mask image. At the same time, key point detection is performed, and the coordinates of the displacement observation reference point are calculated in conjunction with the corner points of the mask image.

[0129] By combining the rotation of the rotating mechanism and the standard dimensions of the scale, the camera parameter self-calibration and the actual displacement of the scale are calculated;

[0130] The surface temperature, rail eccentricity, and observation images are transmitted to the module, which combines deep learning networks and visual detection technology to calculate the track slab displacement and track creep.

[0131] Temperature and displacement trends were analyzed at each monitoring point.

[0132] The track slab displacement and track creep are used as the measurement range, and the semantic features in the observed images are used as the features. The composite is the eccentric feature.

[0133] The system provided in this application fully considers the complex influencing factors of railway bridge girder eccentricity under curved bridge conditions. Based on the characteristics of feasible intervention measures, the influencing factors determining different categories of measures are divided into dynamic and static influencing factors. A dataset is formed based on the mathematical characteristics of the influencing factors, and mathematical laws are mapped onto the dataset to obtain the relationship between the data and the actual physical properties of the bridge. The dynamic and static influence ratios are obtained based on the mathematical results, and bridge repair measures are rationally configured according to different results to achieve the maximum bridge condition maintenance effect.

[0134] This application embodiment also provides a comprehensive evaluation method for track eccentricity of small-radius curved bridges, applied to the above-mentioned comprehensive evaluation system for track eccentricity in the scenario of small-radius curved bridges. The method includes:

[0135] Data is acquired from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order;

[0136] Based on the data in the local database, an analytical model reflecting the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge is trained; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data;

[0137] In response to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, the dynamic and static influence ratio is obtained based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model.

[0138] Based on the ratio of dynamic and static influences, a matching eccentricity solution is determined.

[0139] In one embodiment, the analysis model includes a static analysis model, a dynamic analysis model, and a reverse influence model.

[0140] For the implementation process and derivation of the beneficial effects of each part of the method steps, please refer to the description in the above system embodiment, which will not be repeated here.

[0141] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0142] Based on the same inventive concept, this application also provides a comprehensive evaluation device for track eccentricity of small-radius curved bridges, used to implement the aforementioned comprehensive evaluation method for track eccentricity of small-radius curved bridges. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the comprehensive evaluation device for track eccentricity of small-radius curved bridges provided below can be found in the limitations of the comprehensive evaluation method for track eccentricity of small-radius curved bridges described above, and will not be repeated here.

[0143] This application embodiment also provides a comprehensive evaluation device for track eccentricity of small-radius curved bridges, applied to the above-mentioned comprehensive evaluation system for track eccentricity in the scenario of small-radius curved bridges. The device includes:

[0144] The local data acquisition module is used to acquire data from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order;

[0145] The model training module is used to train an analytical model that reflects the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge based on the data in the local database; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data;

[0146] The influence ratio analysis module is used to respond to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, and to obtain the dynamic and static influence ratios based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model.

[0147] The eccentricity response decision module is used to determine the matching eccentricity solution based on the ratio of dynamic and static influences.

[0148] The various modules in the aforementioned comprehensive evaluation device for track eccentricity of small-radius curved bridges can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0149] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0150] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0151] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario, characterized in that, include: The module includes an eccentricity monitoring module, a clock module, an eccentricity measurement module, an operational performance monitoring module, a data exchange module, an analysis module, and a mitigation module. The clock module is used to generate a continuous, periodic clock pulse signal with a fixed duty cycle, starting from the bridge's service life. The duty cycle of the clock pulse signal is less than the minimum time interval for the operation performance monitoring module to acquire data. The eccentricity measurement module is connected to the clock module, and the eccentricity measurement module is used to acquire eccentricity data based on the clock pulse signal; The operation performance monitoring module is connected to the clock module, and the operation performance monitoring module is used to periodically acquire bridge operation performance data of the bridge based on the pulse signal; The eccentricity monitoring module is connected to the clock module, the eccentricity measurement module, and the operational performance monitoring module, respectively. The eccentricity monitoring module is used to acquire the eccentricity data and the bridge operational performance data based on the pulse signal, and after corresponding them with the timestamps, sort them in chronological order to form a timestamp data table and record it in the local database; when the data in the timestamp data table reaches the eccentricity analysis trigger condition, an analysis request is sent to the measures module. The data exchange module is used to acquire data from the local database corresponding to multiple different bridges and send it to the analysis module. The analysis module trains an analysis model based on the data in the local database to reflect the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge. The eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data. The measures module is used to respond to the analysis request, control the analysis module to obtain the dynamic and static impact ratio based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model, and determine the matching eccentricity solution measures based on the dynamic and static impact ratio.

2. The system according to claim 1, characterized in that, The analysis models include static analysis models, dynamic analysis models, and reverse influence models.

3. The system according to claim 2, characterized in that, The static analysis model includes a finite element model of a curved bridge-track structure, and the analysis module is also used for: Constructing finite element models of curved bridges and track structures; Based on the longitudinal resistance curve of the fastener, the longitudinal resistance curve of the track bed, and the lateral resistance curve of the track bed, a finite element model of the curved bridge and the track structure is generated by using the track bed resistance spring to connect the finite element model of the curved bridge and the track structure. The finite element model of the curved bridge-track structure represents the relationship between the lateral force, expansion force, and flexural force applied to the bridge, the temperature force applied to the rail, and the lateral displacement of the track structure.

4. The system according to claim 2, characterized in that, The dynamic analysis model includes a vehicle-track-bridge coupled dynamic model, and the analysis module is also used for: Construct finite element models of the vehicle system, the track system, and the bridge system; Using the route mileage as the core variable, the finite element models of the vehicle system, the track system, and the bridge system are coupled. To identify the main influencing factors of track eccentricity on curved bridges under dynamic load; The main influencing factors are divided into railway-related data and bridge-related data, and the obtained eccentricity features are mapped using a machine learning algorithm to obtain the vehicle-track-bridge coupled dynamic model. The vehicle-track-bridge coupled dynamic model represents the influence ratio of railway-related data and bridge-related data under different eccentricity features.

5. The system according to claim 4, characterized in that, The machine learning algorithm is the Apriori association analysis algorithm, and when mining itemsets based on the Apriori association analysis algorithm, different states of the same physical property are mutually exclusive as constraints.

6. The system according to claim 2, characterized in that, The reverse influence model is used to continuously exert dynamic mechanical influence on the dynamic analysis model in a finite element simulation environment according to different vehicle speeds, axle loads and frequencies until the bridge reaches the eccentricity analysis trigger condition, and records the duration before the eccentricity analysis trigger condition is reached.

7. The system according to claim 1, characterized in that, The eccentricity data includes track slab displacement, track creep, and semantic features determined based on acquired rail images.

8. The system according to claim 1, characterized in that, The bridge's operational performance data includes beam vibration characteristics, beam dynamic strain, beam dynamic deflection and deformation, and pier vibration characteristics.

9. A comprehensive evaluation method for track eccentricity of small-radius curved bridges, characterized in that, The method applied to the comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario as described in any one of claims 1-8 includes: Data is acquired from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order; Based on the data in the local database, an analytical model reflecting the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge is trained; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data; In response to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, the dynamic and static influence ratio is obtained based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model. Based on the ratio of dynamic and static influences, a matching eccentricity solution is determined.

10. A comprehensive evaluation device for track eccentricity of a small-radius curved bridge, characterized in that, The device, applied to the comprehensive evaluation system for track eccentricity in a small-radius curved bridge scenario as described in any one of claims 1-8, comprises: The local data acquisition module is used to acquire data from local databases corresponding to multiple different bridges; wherein, the data in the local databases includes a timestamp data table generated by the eccentricity monitoring module based on the pulse signal provided by the clock module, and by sorting the eccentricity data of the eccentricity measurement module and the bridge operation performance data of the operation performance monitoring module according to the timestamp correspondence and in chronological order; The model training module is used to train an analytical model that reflects the relationship between the eccentricity features in the timestamp data table and the dynamic and static influencing factors of the bridge based on the data in the local database; the eccentricity features include the eccentricity data corresponding to the timestamp and the bridge operation performance data; The influence ratio analysis module is used to respond to the analysis request sent by the eccentricity monitoring module when the data in the timestamp data table reaches the eccentricity analysis trigger condition, and to obtain the dynamic and static influence ratios based on the timestamp data table reflecting the current eccentricity of the bridge in the local database and the analysis model. The eccentricity response decision module is used to determine the matching eccentricity solution based on the ratio of dynamic and static influences.

Images