Accurate control method for swivel bridge attitude adjustment based on deep learning

Through deep learning-based methods, the steady attitude status of the rotating bridge traction cable is detected in real time, which solves the problem of inaccurate attitude adjustment in traditional construction, realizes automatic control of bridge construction, and improves construction efficiency and safety.

CN119061809AActive Publication Date: 2024-12-03CHINA CONSTR THIRD ENG BUREAU GRP CO LTD

Patent Information

Application Number
CN202411478403.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-12-03
Estimated Expiration
2044-10-22

AI Technical Summary

Technical Problem

The lack of real-time monitoring and automatic control in the construction of traditional rotary bridges, resulting in inaccurate posture adjustment, consumes a lot of manpower and material resources, and cannot guarantee the accuracy and timeliness of observations.

Method used

Using a deep learning-based method, pose evaluation information is obtained from multiple deployment pose evaluation points, pose evaluation features are output, and combined with rotation speed characteristics and attribute features, the pose steady state of the traction search is detected to realize real-time fault detection and automatic control.

Benefits of technology

Real-time recording of bridge posture and automatic control of hydraulic traction system are realized, manpower and material resources are saved, observation accuracy and timeliness are ensured, failure risk is reduced, and detection records are improved comprehensiveness and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119061809A_ABST
    Figure CN119061809A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of bridge construction, in particular to an accurate control method for swivel bridge attitude adjustment based on deep learning, and the method comprises the steps: obtaining attitude evaluation information from a plurality of deployment attitude evaluation points, and outputting attitude evaluation features; according to the rotation speed characteristics of the reference bridge rotation body main pier set and the attribute characteristics of the reference bridge rotation body main pier set, determining the posture stability of the reference bridge rotation body main pier set, and outputting posture stability characteristics; and detecting whether each traction cable has a fault or not according to the difference between the attitude evaluation feature and the attitude stability feature. The posture of the bridge body can be recorded in real time, a hydraulic traction system is automatically controlled during rotation, a large amount of manual observation is not needed in the whole rotation process, manpower and material resources are saved, and the accuracy and timeliness of observation are guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of bridge construction, and in particular to a precise control method for adjusting the posture of a rotating bridge based on deep learning. Background Art

[0002] In recent years, with the popularization and application of rotation construction technology, various bridge construction projects involving cross-railways and grade-separated roads often consider using rotation construction technology to resolve spatial conflicts. In traditional rotation construction, the beams often over-rotate or under-rotate. Since the rotation operation is often performed at the main pier, the micro-operation at the main pier is often magnified by dozens of times through the amplification effect of the main beam span. It is common for the beam to fluctuate between over-rotation and under-rotation during the adjustment process. Due to the very low dynamic and static friction coefficient of the rotating hinge and the problem of rotational inertia, the beam often cannot stop at the ideal position.

[0003] At present, most of the bridge rotation construction process is not monitored in real time, and is controlled by manual observation and on-site radio intercoms to send and receive instructions. The posture of the bridge body is not recorded in real time during the construction process, and the hydraulic traction system is also manually controlled during the rotation. A large amount of manual observation is used in the entire rotation process, which consumes manpower and material resources and cannot guarantee the accuracy and timeliness of the observation.

[0004] Therefore, how to provide a technical solution for the precise and real-time automatic control process of the rotating bridge posture adjustment has become a technical problem that needs to be solved urgently in this field. Summary of the invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] According to a first aspect of the present invention, the present invention claims a method for accurately controlling the posture adjustment of a rotating bridge based on deep learning, the method comprising:

[0007] Acquire posture evaluation information from multiple deployed posture evaluation points and output posture evaluation features; the posture evaluation points are used to evaluate the posture depth information of the traction cable in the main pier of the reference bridge rotation body, and each traction cable deploys multiple posture evaluation points; the posture evaluation features represent the posture stability state of each traction cable obtained in real time during the rotation process;

[0008] According to the rotation speed characteristics of the reference bridge rotation main pier set and the attribute characteristics of the reference bridge rotation main pier set, the posture stability of the reference bridge rotation main pier set is determined, and the posture stability characteristics are output; the posture stability characteristics represent the expected posture stability state of the reference bridge rotation main pier set in the associated rotation speed;

[0009] Based on the difference between the posture evaluation feature and the posture stability feature, it is detected whether each traction cable has a fault.

[0010] Further, the detecting whether each traction rope has a fault based on the difference between the posture evaluation feature and the posture stability feature includes:

[0011] For each traction rope, determine the real-time rigidity attribute and the real-time texture attribute of the associated posture evaluation point according to the posture evaluation feature, and output a first rigidity attribute and a first texture attribute;

[0012] Determine a target rigidity attribute and a target texture attribute of the associated posture evaluation point according to the posture stability feature, and output a second rigidity attribute and a second texture attribute;

[0013] According to the comparison record of the first rigidity attribute and the second rigidity attribute, detecting whether the posture stability obtained in real time is in a fault continuous stability in the rigidity dimension, and outputting a first detection record;

[0014] According to the comparison record of the first texture attribute and the second texture attribute, detecting whether the posture stability obtained in real time is in a fault-continuous stability in the texture roughness dimension, and outputting a second detection record;

[0015] When the first detection record or the second detection record indicates that the posture obtained in real time is stable and the fault persists in a stable state, it is detected that the associated traction rope has a fault.

[0016] Further, the comparison record of the first rigidity attribute and the second rigidity attribute is used to detect whether the posture stability obtained in real time is in a fault-continuous stability in the rigidity dimension, and output a first detection record, including:

[0017] Determine, according to the second rigidity attribute, an overall rigidity variance of the posture depth information acquired along the time series of the associated traction cable, and determine a rigidity variance threshold value according to the overall rigidity variance;

[0018] Determining object stiffness variance of posture depth information in a target object set obtained in real time according to the first rigidity attribute;

[0019] According to the object stiffness variance and the stiffness variance threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the stiffness dimension is detected, and a first detection record is output.

[0020] Further, the comparison record of the first texture attribute and the second texture attribute is used to detect whether the posture stability is in a fault-continuous stability in the texture roughness dimension in real time, and output a second detection record, including:

[0021] Determine, according to the second texture attribute, an overall texture roughness standard deviation of the associated traction cable posture depth information, and determine a texture roughness standard deviation threshold value according to the overall texture roughness standard deviation;

[0022] Determine, based on the first texture attribute, a standard deviation of object texture roughness of the posture depth information in the target object set obtained in real time;

[0023] According to the object texture roughness standard deviation and the texture roughness standard deviation threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the texture roughness dimension is detected, and a second detection record is output.

[0024] Further, the step of determining whether the reference bridge rotating main pier set is stable in posture based on the rotation speed characteristics of the reference bridge rotating main pier set and the attribute characteristics of the reference bridge rotating main pier set, and outputting the stable posture characteristics, includes:

[0025] Obtaining historical rotation information of the reference bridge rotating main pier set; the historical rotation information includes indicators of the reference bridge rotating main pier set when rotating normally in multiple rotation postures and obtained posture stability information; different rotation postures have different rotation speed characteristics;

[0026] Constructing a posture determination model of the reference bridge rotation main pier set according to the historical rotation information;

[0027] According to the rotation speed characteristics of the reference bridge rotation main pier set, determine the target rotation posture of the reference bridge rotation main pier set from multiple deployed determination model candidate postures, and output the posture characteristics;

[0028] According to the attribute characteristics of the reference bridge rotating main pier set and the posture characteristics, the posture determination model is used to determine whether the reference bridge rotating main pier set is in a posture stable in the current rotation posture, and the posture stable characteristics are output.

[0029] Further, the rotation speed feature includes a plurality of rotation speed indicators; the target rotation posture of the reference bridge rotation main pier set is determined from a plurality of deployed determination model candidate postures according to the rotation speed feature of the reference bridge rotation main pier set, and the posture feature is output, including:

[0030] For each first rotational gesture of the plurality of deployed first rotational gestures, determining a correlation degree between each rotational speed indicator in the rotational speed feature and a rotational tilt indicator associated with the first rotational gesture;

[0031] Performing a weighted summation on the relevance of each rotation speed index, and outputting a matching score between the rotation speed feature and the associated first rotation posture; wherein the weight of each rotation speed index is determined according to the influence of the associated rotation speed index on the stability of the main pier set of the reference bridge rotation;

[0032] According to the matching score between the rotation speed feature and each first rotation posture, a second rotation posture is determined from the multiple first rotation postures, and the second rotation posture is used as the target rotation posture of the reference bridge rotating main pier set, and the posture feature is output.

[0033] Further, the rotation speed feature includes at least one of the following rotation speed indicators:

[0034] Rotation speed;

[0035] Bridge deck type;

[0036] Ambient temperature;

[0037] Spin time;

[0038] Rotation arc length;

[0039] The center angle of the ball joint.

[0040] Furthermore, the attribute characteristics of the reference bridge rotating main pier set include mechanical indicators and rotation indicators; wherein,

[0041] The mechanical indicators include the characteristics of the polytetrafluoroethylene slide plate and the characteristics of the annular slideway;

[0042] The rotation index includes at least one of a closing segment contact property, a bridge mass distribution property, a bridge segment system property, a ring slide feature, and a bridge maintenance status.

[0043] Furthermore, the method further comprises:

[0044] According to the historical stability information of each traction cable, the correlation between the stability of each traction cable attitude and the geological characteristics is determined;

[0045] According to the structural characteristics and correlation of each traction rope, a deployment scheme of each traction rope posture evaluation point is determined; the deployment scheme includes the deployment quantity and the evaluation position; wherein, when the correlation increases, the deployment quantity increases accordingly.

[0046] The present invention relates to the technical field of bridge construction, and in particular to a precise control method for adjusting the posture of a rotating bridge based on deep learning, which obtains posture evaluation information from multiple deployed posture evaluation points and outputs posture evaluation features; determines whether the posture of the reference bridge rotating main pier set is stable based on the rotation speed characteristics of the reference bridge rotating main pier set and the attribute characteristics of the reference bridge rotating main pier set, and outputs posture stability features; detects whether each traction cable has a fault based on the difference between the posture evaluation features and the posture stability features. The present invention can record the posture of the bridge body in real time, and the hydraulic traction system is automatically controlled during the rotation. A large amount of manual observation is not required during the entire rotation process, which saves manpower and material resources and ensures the accuracy and timeliness of the observation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A workflow diagram of a precise control method for adjusting the posture of a rotating bridge based on deep learning as claimed in an embodiment of the present invention;

[0048] Figure 2 A structural module diagram of a precise control device for adjusting the posture of a rotating bridge based on deep learning as claimed in an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work according to the embodiments of the present invention are within the scope of protection of the present invention.

[0050] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" may explicitly or implicitly include multiple features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, motion state, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or structure that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or structures.

[0051] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in multiple embodiments of the invention. The presence of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] As an important bridge construction structure, the bridge's rotating main pier assembly brings great convenience to people's daily travel. However, the more powerful the system can provide, the more complex its structure assembly must be and the closer the connection between the parts, which makes the system maintenance more and more difficult. How to ensure the effective and safe rotation of the bridge's rotating main pier assembly has become an urgent issue at present. For this reason, it is particularly critical and important to establish a set of effective and reliable evaluation methods in order to improve the evaluation effect and fault diagnosis capabilities.

[0053] In the related art, the evaluation of the traction cables of the main pier assembly of the bridge rotation can be achieved through visual inspection, that is, the traction cables are visually inspected regularly to detect whether there are any faults in the traction cable structure; however, since traction cable failures mostly occur during the rotation process, the regular maintenance method cannot guarantee the real-time nature of the maintenance, and there is a major safety hazard.

[0054] In view of the above problems, the rotation information of the traction cable can be obtained in real time during the rotation process, and then the performance of each structure can be analyzed according to the obtained rotation index to detect whether the rotation of the structure is normal; however, the rotation index can only reflect whether the structure is currently rotating normally, and it is impossible to timely and reliably detect the fatigue and damage degree of the structure, so as to detect potential safety hazards in time. For example, it is impossible to detect that the external baffle of the main pier assembly of the bridge rotation body fails due to structural vibration, and it is impossible to detect that the structure and the structure are in the state of overstress and fatigue damage; therefore, there is a certain lag in the method of using the real-time rotation information of the structure for evaluation, which makes the comprehensiveness and reliability of the evaluation record low.

[0055] Based on this, in various embodiments of the present invention, the posture stability of the traction rope is obtained by setting multiple posture evaluation points, and the posture stability obtained in real time is compared with the expected posture stability, so as to detect whether the traction rope has a fault based on whether the posture stability has a fault, so that the fault characteristics of the traction rope can be obtained in time when the performance information of the traction rope does not have a fault but the structure has a safety hazard, and the detection of early structural fault signals can be achieved, thereby ensuring a comprehensive evaluation of the traction rope, reducing the risk of failure, and improving the comprehensiveness and accuracy of the traction rope evaluation record; further, since the real-time rotation speed characteristics are introduced in the process of determining the expected posture stability, the comprehensiveness of the model input characteristics is improved, and therefore, the accuracy of the expected posture stability output by the model can be improved, thereby improving the accuracy of the final detection record and ensuring the safe and stable rotation of the traction rope.

[0056] The embodiment of the present invention provides a precise control method for adjusting the posture of a rotating bridge based on deep learning, which is applied to electronic structures, and can be specifically applied to electronic structures such as computers, on-board computers of rotating main piers of bridges, servers, and cloud servers; Figure 1 As shown, the method may include:

[0057] Step 101: Acquire posture evaluation information from multiple deployed posture evaluation points and output posture evaluation features; the posture evaluation points are used to evaluate the posture depth information of the traction cable in the main pier of the reference bridge rotation body, and each traction cable deploys multiple posture evaluation points; the posture evaluation features characterize the posture stability state obtained in real time by each traction cable during the rotation process.

[0058] In real-time applications, in order to ensure the accuracy of posture assessment information, multiple posture assessment points can be deployed for each traction cable.

[0059] In real-time applications, due to the different structural characteristics of the traction cable, the stable position point may be different, and the degree of influence of the ground structure may also be different; therefore, in order to improve the accuracy of information obtained by the attitude assessment point, the setting of the attitude assessment point can be determined based on the correlation between the structural characteristics of the traction cable and the geological characteristic performance indicators.

[0060] Accordingly, in one embodiment, the method may further include:

[0061] According to the historical stability information of each traction cable, the correlation between the stability of each traction cable attitude and the geological characteristics is determined;

[0062] According to the structural characteristics and correlation of each traction rope, a deployment scheme of each traction rope posture evaluation point is determined; the deployment scheme includes the deployment quantity and the evaluation position; wherein, when the correlation increases, the deployment quantity increases accordingly.

[0063] When applied in real time, determining the correlation between the stability of the traction cable posture and geological characteristics can be understood as determining the correlation between the stability of the traction cable posture and geological characteristic performance indicators; wherein, the geological characteristic performance indicators may include ground structure and the azimuth of the center of the ball joint; for the posture evaluation point of the traction cable, the side of the traction cable associated with the posture evaluation point can be called the evaluation surface, and the azimuth of the center of the ball joint can be understood as the angle between the rotation direction and the detection surface.

[0064] In real-time applications, when determining the deployment plan, multiple force-bearing surfaces, that is, the sides that will be affected by the ground structure, can be determined based on the structural characteristics of the traction cable; then, based on the correlation between each force-bearing surface and the geological characteristics, multiple evaluation surfaces can be determined from the multiple force-bearing surfaces, and posture evaluation points can be deployed on the evaluation surfaces.

[0065] Specifically, for each force-bearing surface of the traction cable, the stability of the posture of the force-bearing surface under different ground structures under the same azimuth of the same ball joint center can be determined based on historical stability information, and the ground structure correlation of the force-bearing surface can be calculated. Specifically, the ground structure correlation of the force-bearing surface can be calculated based on the ratio of posture stability to ground structure; then, based on historical stability information, the stability of the posture of the force-bearing surface under different azimuths of the ball joint center under the same ground structure can be determined, thereby calculating the azimuth correlation of the ball joint center of the force-bearing surface. Specifically, the ground structure correlation of the force-bearing surface can be calculated based on the ratio of posture stability to ground structure. The azimuth correlation of the spherical joint center of the stress surface is calculated by the ratio of the state stability to the azimuth of the spherical joint center; then the ground structure correlation and the azimuth correlation of the spherical joint center are weighted summed to output the geological feature correlation between the stress surface and the geological feature; then it is detected whether the geological feature correlation of each stress surface is greater than the deployed correlation threshold value, and when it is greater than the deployed correlation threshold value, the stress surface is used as a monitoring surface; in real-time application, the first N stress surfaces with the largest geological feature correlation can also be selected as monitoring surfaces, where N is an integer greater than or equal to 1.

[0066] In real-time application, the number of posture evaluation points to be deployed can be determined according to the structural characteristics of the traction rope. Specifically, the traction rope can be classified according to its structural characteristics, and a first-class traction rope and a second-class traction rope can be output; wherein, the first-class traction rope is a structure with a simple structure and is less affected by geological characteristics, and the number of posture evaluation points deployed can be N1; the second-class traction rope is a structure with a complex structure and is greatly affected by geological characteristics, and the number of posture evaluation points deployed can be N2, N1 and N2 are both integers not less than 1, and N1<N2; how to deploy N1 and N2 specifically can be deployed according to real-time evaluation needs.

[0067] Step 102: Determine the posture stability of the reference bridge rotating main pier set based on the rotation speed characteristics of the reference bridge rotating main pier set and the attribute characteristics of the reference bridge rotating main pier set, and output the posture stability characteristics; the posture stability characteristics characterize the expected posture stability state of the reference bridge rotating main pier set in the associated rotation speed.

[0068] In real-time applications, a posture determination model can be first established based on simulation or historical information, and then the reference posture stability curve, that is, the target posture stability curve, can be determined using the posture determination model. Based on the difference in the associated values ​​between the posture stability curve and the target posture stability curve at the same rotation speed, it can be detected whether the real-time posture stability has any faults.

[0069] Based on this, in one embodiment, determining whether the reference bridge rotating main pier set is stable in posture based on the rotation speed characteristics of the reference bridge rotating main pier set and the attribute characteristics of the reference bridge rotating main pier set, and outputting the stable posture characteristics, includes:

[0070] Obtaining historical rotation information of the reference bridge rotating main pier set; the historical rotation information includes indicators of the reference bridge rotating main pier set when rotating normally in multiple rotation postures and obtained posture stability information; different rotation postures have different rotation speed characteristics;

[0071] Constructing a posture determination model of the reference bridge rotation main pier set according to the historical rotation information;

[0072] According to the rotation speed characteristics of the reference bridge rotation main pier set, determine the target rotation posture of the reference bridge rotation main pier set from multiple deployed determination model candidate postures, and output the posture characteristics;

[0073] According to the attribute characteristics of the reference bridge rotating main pier set and the posture characteristics, the posture determination model is used to determine whether the reference bridge rotating main pier set is in a posture stable in the current rotation posture, and the posture stable characteristics are output.

[0074] In real-time applications, it is difficult to achieve completely consistent rotation speeds at different time periods. Therefore, based on the similarity between the rotation speed features, close rotation postures can be retrieved from the model information to ensure the reliability of the posture determination model output record.

[0075] Based on this, in one embodiment, the rotation speed feature includes a plurality of rotation speed indicators; the target rotation posture of the reference bridge rotation main pier set is determined from a plurality of deployed determination model candidate postures according to the rotation speed feature of the reference bridge rotation main pier set, and the posture feature is output, including:

[0076] For each first rotational gesture of the plurality of deployed first rotational gestures, determining a correlation degree between each rotational speed indicator in the rotational speed feature and a rotational tilt indicator associated with the first rotational gesture;

[0077] Performing a weighted summation on the relevance of each rotation speed index, and outputting a matching score between the rotation speed feature and the associated first rotation posture; wherein the weight of each rotation speed index is determined according to the influence of the associated rotation speed index on the stability of the main pier set of the reference bridge rotation;

[0078] According to the matching score between the rotation speed feature and each first rotation posture, a second rotation posture is determined from the multiple first rotation postures, and the second rotation posture is used as the target rotation posture of the reference bridge rotating main pier set, and the posture feature is output.

[0079] When applying in real time, when determining the correlation between the rotation speed index and the associated rotation tilt index, the ratio of the rotation speed index to the associated rotation tilt index can be calculated, the environmental correlation can be output, and the calculated output environmental correlation can be compared with the deployed correlation threshold value to detect whether the environmental correlation is greater than the deployed correlation threshold value, and when the environmental correlation is greater than the deployed matching threshold value, the associated first rotation posture is used as a candidate posture; then, the candidate posture with the highest environmental correlation is selected from the determined candidate postures as the target rotation posture, that is, as the current rotation posture, and the posture characteristics of the target rotation posture are output.

[0080] In one embodiment, the rotation speed feature includes at least one of the following rotation speed indicators:

[0081] Rotation speed;

[0082] Bridge deck type;

[0083] Ambient temperature;

[0084] Spin time;

[0085] Rotation arc length;

[0086] The center angle of the ball joint.

[0087] In one embodiment, the attribute characteristics of the reference bridge rotating main pier set include mechanical indicators and rotation indicators; wherein,

[0088] The mechanical indicators include the characteristics of the polytetrafluoroethylene slide plate and the characteristics of the annular slideway;

[0089] The rotation index includes at least one of a closing segment contact property, a bridge mass distribution property, a bridge segment system property, a ring slide feature, and a bridge maintenance status.

[0090] When applied in real time, the attribute characteristics of the reference bridge rotation main pier set can be indicators pre-deployed during the production process.

[0091] In real-time applications, the appearance indicators, rotation indicators, and traction cable types of different bridge rotating main pier sets are also different. Therefore, the rotation information and attitude stability characteristics at the same rotation speed are also different. Using the same determination model for attitude stability determination has low accuracy. Therefore, different determination models can be established for different types of bridge rotating main pier sets to achieve more accurate and reliable determination.

[0092] Based on this, in one embodiment, constructing the posture determination model of the reference bridge rotating main pier set based on the historical rotation information may include:

[0093] According to the historical rotation information, a posture determination model of at least one type of reference bridge rotation main pier set is constructed, and multiple first posture determination models are output; different types of reference bridge rotation main pier sets have different attribute characteristics.

[0094] On this basis, in one embodiment, the method of determining whether the reference bridge rotating main pier set is stable in the current rotation posture by using the posture determination model based on the attribute characteristics of the reference bridge rotating main pier set and the posture characteristics, and outputting the posture stability characteristics, may include:

[0095] Determining a target posture determination model from a plurality of constructed first posture determination models according to the attribute characteristics of the reference bridge rotation main pier set;

[0096] The target posture determination model and the associated posture features are used to determine whether the reference bridge rotating main pier set is posture stable in the current rotation posture, and output the posture stability features.

[0097] Step 103: Detect whether each traction rope has a fault based on the difference between the posture evaluation feature and the posture stability feature.

[0098] In real-time applications, in order to ensure the comprehensiveness of the test records and thus improve the accuracy of the test records, testing can be performed from two dimensions: stiffness and texture roughness.

[0099] Based on this, in one embodiment, detecting whether each traction rope has a fault based on the difference between the posture evaluation feature and the posture stability feature may include:

[0100] For each traction rope, determine the real-time rigidity attribute and the real-time texture attribute of the associated posture evaluation point according to the posture evaluation feature, and output a first rigidity attribute and a first texture attribute;

[0101] Determine a target rigidity attribute and a target texture attribute of the associated posture evaluation point according to the posture stability feature, and output a second rigidity attribute and a second texture attribute;

[0102] According to the comparison record of the first rigidity attribute and the second rigidity attribute, detecting whether the posture stability obtained in real time is in a fault continuous stability in the rigidity dimension, and outputting a first detection record;

[0103] According to the comparison record of the first texture attribute and the second texture attribute, detecting whether the posture stability obtained in real time is in a fault-continuous stability in the texture roughness dimension, and outputting a second detection record;

[0104] When the first detection record or the second detection record indicates that the posture obtained in real time is stable and the fault persists in a stable state, it is detected that the associated traction rope has a fault.

[0105] In one embodiment, the detecting whether the posture stability obtained in real time is in a fault-continuous stability in the stiffness dimension according to the comparison record of the first stiffness attribute and the second stiffness attribute, and outputting the first detection record may include:

[0106] Determine, according to the second rigidity attribute, an overall rigidity variance of the posture depth information acquired along the time series of the associated traction cable, and determine a rigidity variance threshold value according to the overall rigidity variance;

[0107] Determining object stiffness variance of posture depth information in a target object set obtained in real time according to the first rigidity attribute;

[0108] According to the object stiffness variance and the stiffness variance threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the stiffness dimension is detected, and a first detection record is output.

[0109] When applied in real time, the overall stiffness variance of the posture depth information obtained by the associated traction cable along the time series is determined based on the second rigidity attribute, and the stiffness variance threshold value is determined based on the overall stiffness variance. The method can first average the stationary objects obtained from the traction cable associated posture evaluation points at the same moment, and then construct an object time series based on the average of the information obtained at each moment, and then use the time object series to determine the overall reference variance, that is, the overall stiffness variance, and determine the extreme stiffness variance threshold value based on the overall reference variance and the deployed coefficient.

[0110] When applied in real time, when determining the object stiffness variance of the posture depth information in the target object set obtained in real time based on the first rigid attribute, it can be understood that the information set obtained by evaluation can be obtained periodically, and each information set obtained includes multiple target objects in the current acquisition cycle. The target object information at the same time in each posture evaluation point is fused, and then arranged in time to form a target object set, and the object stiffness variance of the posture depth information in the target object set is calculated.

[0111] When applied in real time, when detecting whether there is a fault in the stiffness dimension of the posture stability information obtained in real time in the target object set based on the object stiffness variance and the stiffness variance threshold value, it can be detected whether the stiffness variance of each object in the target object set is greater than the stiffness variance threshold value. When it is greater, it can be considered that the current variance of the object is far greater than the normal range, and thus the posture stability information detected is faulty.

[0112] In real-time applications, for posture stability, the fault persistence and stability can be identified by detecting whether certain dynamic friction factor components in the friction texture are significantly higher than the normal range.

[0113] Based on this, in one embodiment, the detecting, based on the comparison record of the first texture attribute and the second texture attribute, whether the posture stability is in a fault-continuous stability in the texture roughness dimension in real time and outputting the second detection record may include:

[0114] Determine, according to the second texture attribute, an overall texture roughness standard deviation of the associated traction cable posture depth information, and determine a texture roughness standard deviation threshold value according to the overall texture roughness standard deviation;

[0115] Determine, based on the first texture attribute, a standard deviation of object texture roughness of the posture depth information in the target object set obtained in real time;

[0116] According to the object texture roughness standard deviation and the texture roughness standard deviation threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the texture roughness dimension is detected, and a second detection record is output.

[0117] When applied in real time, when determining the overall texture roughness standard deviation of the associated traction rope posture depth information and determining the texture roughness standard deviation threshold value based on the overall texture roughness standard deviation, it is possible to target each dynamic friction factor component in the friction texture and further calculate statistical characteristics, such as the mean and standard deviation, and then establish a normal range based on the statistical characteristics, i.e., determine the texture roughness standard deviation threshold value.

[0118] It should be noted that the threshold value deployed in the embodiment of the present invention can be set according to historical experience, or can be determined by using an associated simulation model, and the embodiment of the present invention is not limited to this.

[0119] In summary, the precise control method for the posture adjustment of a rotating bridge based on deep learning provided by the embodiment of the present invention obtains the posture stability of the traction cable by setting multiple posture evaluation points, and compares the posture stability obtained in real time with the expected posture stability, so as to detect whether the traction cable has a fault based on whether there is a fault in the posture stability, so that the fault characteristics of the traction cable can be obtained in time when there is no fault in the performance information of the traction cable but there are safety hazards in the structure, and the detection of early fault signals of the structure can be realized, thereby ensuring a comprehensive evaluation of the traction cable, reducing the risk of failure, and improving the comprehensiveness and accuracy of the traction cable evaluation record; further, since the real-time rotation speed characteristics are introduced in the process of determining the expected posture stability, the comprehensiveness of the model input characteristics is improved, and therefore, the accuracy of the expected posture stability output by the model can be improved, thereby improving the accuracy of the final detection record and ensuring the safe and stable rotation of the traction cable.

[0120] In order to realize the accurate control method of the rotating bridge posture adjustment based on deep learning of the present invention, the embodiment of the present invention also provides an accurate control device of the rotating bridge posture adjustment based on deep learning, which is arranged on the electronic structure, such as Figure 2 As shown, the device may include:

[0121] An evaluation unit 201 is used to obtain posture evaluation information from a plurality of deployed posture evaluation points and output a posture evaluation feature; the posture evaluation points are used to evaluate the posture depth information of the traction cable in the main pier of the reference bridge rotation body, and each traction cable is deployed with a plurality of posture evaluation points; the posture evaluation feature represents the posture stability state obtained in real time by each traction cable during the rotation process;

[0122] The calculation unit 202 is used to determine the stability of the posture of the reference bridge rotation main pier set according to the rotation speed characteristics of the reference bridge rotation main pier set and the attribute characteristics of the reference bridge rotation main pier set, and output a posture stability feature; the posture stability feature represents the expected posture stability state of the reference bridge rotation main pier set in the associated rotation speed;

[0123] The processing unit 203 is used to detect whether each traction cable has a fault according to the difference between the posture evaluation feature and the posture stability feature.

[0124] In one embodiment, the processing unit 203 may be specifically configured to:

[0125] For each traction rope, determine the real-time rigidity attribute and the real-time texture attribute of the associated posture evaluation point according to the posture evaluation feature, and output a first rigidity attribute and a first texture attribute;

[0126] Determine a target rigidity attribute and a target texture attribute of the associated posture evaluation point according to the posture stability feature, and output a second rigidity attribute and a second texture attribute;

[0127] According to the comparison record of the first rigidity attribute and the second rigidity attribute, detecting whether the posture stability obtained in real time is in a fault continuous stability in the rigidity dimension, and outputting a first detection record;

[0128] According to the comparison record of the first texture attribute and the second texture attribute, detecting whether the posture stability obtained in real time is in a fault-continuous stability in the texture roughness dimension, and outputting a second detection record;

[0129] When the first detection record or the second detection record indicates that the posture obtained in real time is stable and the fault persists in a stable state, it is detected that the associated traction rope has a fault.

[0130] In one embodiment, the comparison record of the first rigidity attribute and the second rigidity attribute is used to detect whether the posture stability obtained in real time is in a fault-continuous stability in the rigidity dimension, and output a first detection record, including:

[0131] Determine, according to the second rigidity attribute, an overall rigidity variance of the posture depth information acquired along the time series of the associated traction cable, and determine a rigidity variance threshold value according to the overall rigidity variance;

[0132] Determining object stiffness variance of posture depth information in a target object set obtained in real time according to the first rigidity attribute;

[0133] According to the object stiffness variance and the stiffness variance threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the stiffness dimension is detected, and a first detection record is output.

[0134] In one embodiment, the comparison record of the first texture attribute and the second texture attribute is used to detect whether the posture stability is in a fault-continuous stability in the texture roughness dimension in real time, and output a second detection record, including:

[0135] Determine, according to the second texture attribute, an overall texture roughness standard deviation of the associated traction cable posture depth information, and determine a texture roughness standard deviation threshold value according to the overall texture roughness standard deviation;

[0136] Determine, based on the first texture attribute, a standard deviation of object texture roughness of the posture depth information in the target object set obtained in real time;

[0137] According to the object texture roughness standard deviation and the texture roughness standard deviation threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the texture roughness dimension is detected, and a second detection record is output.

[0138] In one embodiment, the calculation unit 202 may be specifically configured to:

[0139] Obtaining historical rotation information of the reference bridge rotating main pier set; the historical rotation information includes indicators of the reference bridge rotating main pier set when rotating normally in multiple rotation postures and obtained posture stability information; different rotation postures have different rotation speed characteristics;

[0140] Constructing a posture determination model of the reference bridge rotation main pier set according to the historical rotation information;

[0141] According to the rotation speed characteristics of the reference bridge rotation main pier set, determine the target rotation posture of the reference bridge rotation main pier set from multiple deployed determination model candidate postures, and output the posture characteristics;

[0142] According to the attribute characteristics of the reference bridge rotating main pier set and the posture characteristics, the posture determination model is used to determine whether the reference bridge rotating main pier set is in a posture stable in the current rotation posture, and the posture stable characteristics are output.

[0143] In one embodiment, the rotation speed feature includes a plurality of rotation speed indicators; the target rotation posture of the reference bridge rotation main pier set is determined from a plurality of deployed determination model candidate postures according to the rotation speed feature of the reference bridge rotation main pier set, and the posture feature is output, including:

[0144] For each first rotational gesture of the plurality of deployed first rotational gestures, determining a correlation degree between each rotational speed indicator in the rotational speed feature and a rotational tilt indicator associated with the first rotational gesture;

[0145] Performing a weighted summation on the relevance of each rotation speed index, and outputting a matching score between the rotation speed feature and the associated first rotation posture; wherein the weight of each rotation speed index is determined according to the influence of the associated rotation speed index on the stability of the main pier set of the reference bridge rotation;

[0146] According to the matching score between the rotation speed feature and each first rotation posture, a second rotation posture is determined from the multiple first rotation postures, and the second rotation posture is used as the target rotation posture of the reference bridge rotating main pier set, and the posture feature is output.

[0147] In one embodiment, the rotation speed feature includes at least one of the following rotation speed indicators:

[0148] Rotation speed;

[0149] Bridge deck type;

[0150] Ambient temperature;

[0151] Spin time;

[0152] Rotation arc length;

[0153] The center angle of the ball joint.

[0154] In one embodiment, the attribute characteristics of the reference bridge rotating main pier set include mechanical indicators and rotation indicators; wherein,

[0155] The mechanical indicators include the characteristics of the polytetrafluoroethylene slide plate and the characteristics of the annular slideway;

[0156] The rotation index includes at least one of a closing segment contact property, a bridge mass distribution property, a bridge segment system property, a ring slide feature, and a bridge maintenance status.

[0157] In one embodiment, the processing unit 203 may also be used to:

[0158] According to the historical stability information of each traction cable, the correlation between the stability of each traction cable attitude and the geological characteristics is determined;

[0159] According to the structural characteristics and correlation of each traction rope, a deployment scheme of each traction rope posture evaluation point is determined; the deployment scheme includes the deployment quantity and the evaluation position; wherein, when the correlation increases, the deployment quantity increases accordingly.

[0160] It should be noted that: the precise control device for adjusting the posture of a rotating bridge based on deep learning provided in the above embodiment only uses the division of the above program modules as an example when evaluating the traction cable. In real-time applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the precise control device for adjusting the posture of a rotating bridge based on deep learning provided in the above embodiment and the precise control method for adjusting the posture of a rotating bridge based on deep learning belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0161] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in real-time implementation, such as multiple units or assemblies can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0162] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0163] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A precise control method for adjusting the posture of a rotating bridge based on deep learning, characterized in that: The method comprises: Acquire posture evaluation information from multiple deployed posture evaluation points and output posture evaluation features; the posture evaluation points are used to evaluate the posture depth information of the traction cable in the main pier of the reference bridge rotation body, and each traction cable deploys multiple posture evaluation points; the posture evaluation features represent the posture stability state of each traction cable obtained in real time during the rotation process; According to the rotation speed characteristics of the reference bridge rotation main pier set and the attribute characteristics of the reference bridge rotation main pier set, the posture stability of the reference bridge rotation main pier set is determined, and the posture stability characteristics are output; the posture stability characteristics represent the expected posture stability state of the reference bridge rotation main pier set in the associated rotation speed; Based on the difference between the posture evaluation feature and the posture stability feature, it is detected whether each traction cable has a fault.

2. The method according to claim 1, characterized in that The detecting whether each traction rope has a fault based on the difference between the posture evaluation feature and the posture stability feature comprises: For each traction rope, determine the real-time rigidity attribute and the real-time texture attribute of the associated posture evaluation point according to the posture evaluation feature, and output a first rigidity attribute and a first texture attribute; Determine a target rigidity attribute and a target texture attribute of the associated posture evaluation point according to the posture stability feature, and output a second rigidity attribute and a second texture attribute; According to the comparison record of the first rigidity attribute and the second rigidity attribute, detecting whether the posture stability obtained in real time is in a fault continuous stability in the rigidity dimension, and outputting a first detection record; According to the comparison record of the first texture attribute and the second texture attribute, detecting whether the posture stability obtained in real time is in a fault-continuous stability in the texture roughness dimension, and outputting a second detection record; When the first detection record or the second detection record indicates that the posture obtained in real time is stable and the fault persists in a stable state, it is detected that the associated traction rope has a fault.

3. The method according to claim 2, characterized in that The step of detecting whether the posture stability obtained in real time is in a fault-continuous stability in the stiffness dimension based on the comparison record of the first rigidity attribute and the second rigidity attribute, and outputting a first detection record includes: Determine, according to the second rigidity attribute, an overall rigidity variance of the posture depth information acquired along the time series of the associated traction cable, and determine a rigidity variance threshold value according to the overall rigidity variance; Determining object stiffness variance of posture depth information in a target object set obtained in real time according to the first rigidity attribute; According to the object stiffness variance and the stiffness variance threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the stiffness dimension is detected, and a first detection record is output.

4. The method according to claim 2, characterized in that The comparison record of the first texture attribute and the second texture attribute is used to detect whether the posture stability is in a fault-continuous stability in the texture roughness dimension in real time, and output a second detection record, including: Determine, according to the second texture attribute, an overall texture roughness standard deviation of the associated traction cable posture depth information, and determine a texture roughness standard deviation threshold value according to the overall texture roughness standard deviation; Determine, based on the first texture attribute, a standard deviation of object texture roughness of the posture depth information in the target object set obtained in real time; According to the object texture roughness standard deviation and the texture roughness standard deviation threshold value, whether the posture stability information obtained in real time in the target object set has a fault in the texture roughness dimension is detected, and a second detection record is output.

5. The method according to claim 1, characterized in that The step of determining whether the reference bridge rotating main pier set is stable in posture based on the rotation speed characteristics of the reference bridge rotating main pier set and the attribute characteristics of the reference bridge rotating main pier set, and outputting the stable posture characteristics, comprises: Obtaining historical rotation information of the reference bridge rotating main pier set; the historical rotation information includes indicators of the reference bridge rotating main pier set when rotating normally in multiple rotation postures and obtained posture stability information; different rotation postures have different rotation speed characteristics; Constructing a posture determination model of the reference bridge rotation main pier set according to the historical rotation information; According to the rotation speed characteristics of the reference bridge rotation main pier set, determine the target rotation posture of the reference bridge rotation main pier set from multiple deployed determination model candidate postures, and output the posture characteristics; According to the attribute characteristics of the reference bridge rotating main pier set and the posture characteristics, the posture determination model is used to determine whether the reference bridge rotating main pier set is in a posture stable in the current rotation posture, and the posture stable characteristics are output.

6. The method according to claim 5, characterized in that The rotation speed feature includes a plurality of rotation speed indicators; the target rotation posture of the reference bridge rotation main pier set is determined from a plurality of deployed determination model candidate postures according to the rotation speed feature of the reference bridge rotation main pier set, and the posture feature is output, including: For each first rotational gesture of the plurality of deployed first rotational gestures, determining a correlation degree between each rotational speed index in the rotational speed feature and a rotational tilt index associated with the first rotational gesture; Performing a weighted summation on the relevance of each rotation speed index, and outputting a matching score between the rotation speed feature and the associated first rotation posture; wherein the weight of each rotation speed index is determined according to the influence of the associated rotation speed index on the stability of the main pier set of the reference bridge rotation; According to the matching score between the rotation speed feature and each first rotation posture, a second rotation posture is determined from the multiple first rotation postures, and the second rotation posture is used as the target rotation posture of the reference bridge rotating main pier set, and the posture feature is output.

7. The method according to claim 6, characterized in that The rotation speed characteristic includes at least one of the following rotation speed indicators: Rotation speed; Bridge deck type; Ambient temperature; Spin time; Rotation arc length; The center angle of the ball joint.

8. The method according to claim 5, characterized in that The attribute characteristics of the reference bridge rotating main pier set include mechanical indicators and rotation indicators; wherein, The mechanical indicators include the characteristics of the polytetrafluoroethylene slide plate and the characteristics of the annular slideway; The rotation index includes at least one of a closing segment contact property, a bridge mass distribution property, a bridge segment system property, a ring slide feature, and a bridge maintenance status.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: According to the historical stability information of each traction cable, the correlation between the stability of each traction cable attitude and the geological characteristics is determined; According to the structural characteristics and correlation of each traction rope, a deployment scheme of each traction rope posture evaluation point is determined; the deployment scheme includes the deployment quantity and the evaluation position; wherein, when the correlation increases, the deployment quantity increases accordingly.

Citation Information

Patent Citations

  • Bridge turning method and system based on real-time monitoring of bridge turning posture

    CN115435810A

  • Swivel bridge attitude monitoring system and method based on computer vision

    CN117953048A

  • Visual mechanical arm material grabbing control method and system based on deep learning

    CN118003340A

  • Swivel bridge swivel measurement and control system and measurement and control method thereof

    CN118194416A

  • Movement Identification Device

    US20220396933A1

Cited By

  • Multi-source data fusion-based bridge swivel posture intelligent adjustment method and system

    CN120406274A